vwemirror/TeslaRel410
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Emulator: parity-safe EMU8000 sample counter -- AWEUTIL runs; wire the

Browse Source 
VGL_LABS cockpit test suite as pod-launch 'test' mode

The WC hang, root-caused in three layers (each necessary):
1. WC was rendered-samples + 100ms-capped interpolation; AWEUTIL's poll
   storm (~550k port-ops/s) starved the render thread of awe_lock, so the
   clock crawled ~90x slow. Fixed: free-running host-clock derivation +
   a fairness gate so the render thread can always take the lock.
2. Free-running at true 44.1kHz still failed: trapped port reads cost
   ~30us -- MORE than one 22.7us tick -- so consecutive reads skipped
   counter values, and AWEUTIL's WaitUntilWC (decoded at COM offset
   0x5F42) exits only on EQUALITY with a target tick: skipped value =
   missed target = 1.49s wrap penalty, or forever.
3. Advancing +1 per read still failed: WaitUntilWC reads WC TWICE per
   iteration, so its equality sample saw only every 2nd value -- wrong
   parity = infinite loop. Final semantics: during a poll storm the
   counter advances once per FOUR reads (every value observable by all
   of AWEUTIL's loop shapes; its 8192-unchanged-reads dead-clock bailout
   never trips), and resyncs to true wall time after any 50ms idle gap.
   Result: the full stock TEST.BAT (DIAGNOSE + AWEUTIL /S on both cards)
   completes in seconds.

Also: pod-launch 'test' mode -> vwetest.conf (stock TEST.BAT -> TSTALL),
DOSBox window defaults to 900,600 in test mode (the DOS screen is the
suite's UI), VWE_AWE_LOG gains storm bursts with guest cs:ip + caller and
rare-read tracing (the instrumentation that cracked this).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Cyd
2026-07-16 23:51:52 -05:00
co-authored by Claude Fable 5
parent 6dc017cb3d
commit 72da9b2f14
7 changed files with 184 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files
emulator/deploy/vwetest.conf.tmpl
+54
View File
@@ -0,0 +1,54 @@
# DEPLOY TEMPLATE -- rendered to vwetest.conf by deploy/configure.ps1 at install.
# Tokens (filled by postinstall): @@ROOT@@ = package dir (C:\games\<folder>),
# @@REALNIC@@ = this pod's NIC GUID fragment, @@MACADDR@@ = stable derived MAC.
# VGL_LABS factory cockpit test suite: the stock C:\VWETEST\TEST.BAT chain
# (DIAGNOSE + AWEUTIL /S on both AWE cards, SETSVGA, VGLTEST\TSTALL.EXE --
# RIO, plasma, audio, video/Division calibration, Munga-net). Launch:
# pod-launch test. AWEUTIL's WC-timed init needs the parity-safe EMU8000
# sample-counter readback (vweawe.cpp, 2026-07-16) -- on older dosbox-x.exe
# builds it hangs at AWEUTIL. Drops to a DOS prompt when the suite exits.
[sdl]
output=opengl
priority=highest,highest
[dosbox]
memsize=32
machine=svga_s3
[cpu]
core=dynamic
cputype=pentium
cycles=max
[ne2000]
ne2000=true
nicbase=340
# IRQ 10, NOT 3: COM2 (plasma) owns IRQ 3 in the suite, same as in-game.
nicirq=10
macaddr=@@MACADDR@@
backend=pcap
[ethernet, pcap]
realnic=@@REALNIC@@
[sblaster]
sbtype=sb16
sbbase=220
irq=5
dma=1
hdma=5
[mixer]
rate=44100
blocksize=1024
prebuffer=60
[serial]
serial1=directserial realport:COM1 rxpollus:100 rxburst:16
serial2=directserial realport:COM2
[autoexec]
mount c "@@ROOT@@\ALPHA_1"
mount d "@@ROOT@@\net-boot"
d:
echo === loading NE2000 packet-driver stack (for the Munga-net tests) ===
d:\lsl
d:\ne2000
d:\odipkt
c:
cd \vwetest
echo === VGL_LABS cockpit test suite (stock TEST.BAT) ===
call test.bat
echo === test suite exited -- DOS prompt ===
emulator/pod-launch/Modes.cs
+2
View File
@@ -30,6 +30,8 @@ namespace VwePod
Note = "BattleTech, networked cockpit. Also serves the camera ship and LIVE mission-review -- the console sets the role per-IP via the egg hostType, so no separate mode is needed." },
new Mode { Name = "rp", ConfBase = "net_rp", Supported = true,
Note = "Red Planet, networked cockpit (also camera / live mission-review via egg hostType)." },
new Mode { Name = "test", ConfBase = "vwetest", Supported = true,
Note = "VGL_LABS factory cockpit test suite (C:\\VWETEST TEST.BAT -> TSTALL.EXE): RIO, plasma, audio (both AWE cards), video/Division calibration, Munga-net diagnostics." },
// Distinct launches, mechanics not yet wired on the emulator:
new Mode { Name = "review", ConfBase = null, Supported = false,
emulator/pod-launch/Options.cs
+12 -6
View File
@@ -49,6 +49,7 @@ namespace VwePod
var o = new Options();
string modeName = null, confArg = null, rootArg = null, dosboxArg = null,
bridgeScriptArg = null, rendererArg = null, aweArg = null;
bool dosboxXySet = false;
for (int i = 0; i < args.Length; i++)
{
@@ -72,7 +73,7 @@ namespace VwePod
case "--layout": o.Layout = Next(a).Equals("explode", StringComparison.OrdinalIgnoreCase) ? LayoutMode.Explode : LayoutMode.Cockpit; break;
case "--bridge-pos": o.BridgePos = Next(a); break;
case "--bridge-size": ParseWH(Next(a), out o.BridgeW, out o.BridgeH); break;
case "--dosbox-xy": ParseWH(Next(a), out o.DosBoxX, out o.DosBoxY); break;
case "--dosbox-xy": ParseWH(Next(a), out o.DosBoxX, out o.DosBoxY); dosboxXySet = true; break;
case "--no-bridge": o.NoBridge = true; break;
case "--no-sound": o.NoSound = true; break;
case "--mipmap": o.Mipmap = true; break;
@@ -92,6 +93,10 @@ namespace VwePod
// reason and exits without touching the launch env.
if (!o.Mode.Supported) return o;
// test mode: the DOS screen IS the suite's UI -- default it out from
// under the render window unless the caller placed it explicitly.
if (!dosboxXySet && o.Mode.Name == "test") { o.DosBoxX = 900; o.DosBoxY = 600; }
o.DosBox = dosboxArg ?? FirstExisting(
Path.Combine(o.Root, "dosbox-x.exe"),
Path.Combine(o.Root, "src", "src", "dosbox-x.exe"))
@@ -155,11 +160,12 @@ namespace VwePod
Supervising entry-point: launches DOSBox-X + the render bridge into a job
object and blocks; killing this process kills them too (no orphans).
mode bt | rp (default bt). bt/rp also serve the camera ship
+ live mission-review roles -- the console picks the
role via the egg hostType, so no separate mode. Also
recognized (not yet wired): review, test-plasma,
reset-rio, audio-test.
mode bt | rp | test (default bt). bt/rp also serve the
camera ship + live mission-review roles -- the console
picks the role via the egg hostType, so no separate
mode. test = the VGL_LABS factory cockpit test suite
(C:\VWETEST -> TSTALL.EXE). Also recognized (not yet
wired): review, test-plasma, reset-rio, audio-test.
--mode <name> same as the positional mode
--conf <path> explicit conf (overrides the mode's conf)
--root <dir> base dir for dosbox/conf/bridge (default: exe dir)
emulator/pod-launch/README.md
+1
View File
@@ -51,6 +51,7 @@ layout is fixed at `postinstall` time, so a typical call is just `pod-launch bt`
|---|---|---|
| `bt` | BattleTech, networked cockpit (`net_loop.conf`, looped) | wired |
| `rp` | Red Planet, networked cockpit (`net_rp.conf`, looped) | wired |
| `test` | VGL_LABS factory cockpit test suite (`vwetest.conf` → `C:\VWETEST` → `TSTALL.EXE`): RIO, plasma, audio, video/Division calibration, Munga-net. DOSBox window defaults to 900,600 (the DOS screen is the suite's UI) | wired |
| `review` | mission-review PLAYBACK of `last.spl` | recognized, exits 3 (DOS arg TBD) |
| `test-plasma` | plasma-display diagnostic | recognized, exits 3 |
| `reset-rio` | RIO reset diagnostic | recognized, exits 3 |
emulator/vpx-device/emu8k.cpp
+5 -5
View File
@@ -712,11 +712,11 @@ emu8k_inw(uint16_t addr, void *priv)
it is used by programs to wait. Not critical, but should help reduce
the amount of calls and wait time */
case 27: /*Sample Counter ( 44Khz clock) */
/* VWE: interpolate between mixer blocks so
* driver busy-waits on the clock resolve at
* sample granularity instead of block steps */
return (uint16_t)(emu8k->wc +
emu8k_shim_wc_extra());
/* VWE: free-running host-clock counter, like the
* silicon. Software (AWEUTIL) busy-waits on this;
* tying it to render progress made those waits
* crawl under lock contention. */
return emu8k_shim_wc_read();
default:
break;
emulator/vpx-device/emu8k_shim.h
+4 -2
View File
@@ -37,8 +37,10 @@ void io_removehandler(uint16_t base, int size,
extern int wavetable_pos_global;
FILE *emu8k_shim_rom_fopen(void);
/* samples elapsed since the last mixer render (WC interpolation) */
unsigned emu8k_shim_wc_extra(void);
/* the WC sample counter readback: free-running 44100Hz off the host clock,
* exactly like the silicon (guest software busy-waits on it; deriving it
* from render progress made those waits crawl under lock contention) */
uint16_t emu8k_shim_wc_read(void);
#define pclog(...) fprintf(stderr, __VA_ARGS__)
#define pclog_ex(fmt, ap) vfprintf(stderr, fmt, ap)
emulator/vpx-device/vweawe.cpp
+106 -20
View File
@@ -46,6 +46,7 @@
#include "dosbox.h"
#include "inout.h"
#include "regs.h" /* guest CS:IP in the storm trace */
#ifndef WIN32_LEAN_AND_MEAN
#define WIN32_LEAN_AND_MEAN
@@ -63,21 +64,71 @@ int wavetable_pos_global = 0;
* per-chunk renders, so contention stays in the microseconds. */
static CRITICAL_SECTION awe_lock;
/* WC interpolation: real-time samples elapsed since the render thread's
* last pass, so guest busy-waits on the 44kHz sample counter see smooth
* advancement between render chunks */
static volatile LONGLONG awe_last_render_qpc = 0;
/* WC: the EMU8000 sample counter is a FREE-RUNNING 44100Hz 16-bit counter on
* silicon -- it ticks regardless of what the host, driver, or synth is doing,
* and software (AWEUTIL /S in particular) busy-waits on it for every timed
* init step. Derive it from QPC alone. The old render-coupled version
* (rendered samples + interpolation capped at 100ms) crawled ~90x slow when
* a guest poll storm starved the render thread of the shared lock -- AWEUTIL
* "hang", root-caused 2026-07-16. See also awe_render_waiting below. */
static LONGLONG awe_qpc_freq = 1;
unsigned emu8k_shim_wc_extra(void) {
static LONGLONG awe_wc_origin_qpc = 0;
uint16_t emu8k_shim_wc_read(void) {
/* Free-running 44100Hz -- but with one more piece of silicon truth: on
* real ISA a poll loop reads the port many times per tick, so software
* NEVER observes the counter skipping a value, and AWEUTIL's timed waits
* exit on EQUALITY with a target tick. Our trapped port reads cost ~30us
* (heavier than one 22.7us tick), so a raw time-derived counter jumps
* +2..+4 per poll and equality targets get skipped -- each miss costs a
* full 1.49s wrap (the "AWEUTIL hang", 2026-07-16). So: while the guest
* is polling TIGHTLY (<200us between reads), advance at most one tick
* per read -- every value is observed, waits terminate, and the counter
* runs at worst ~25% slow during the poll itself. Any idle gap snaps it
* back to true wall-clock time. Single caller thread (emulation). */
LARGE_INTEGER now;
QueryPerformanceCounter(&now);
LONGLONG d = now.QuadPart - awe_last_render_qpc;
if (d < 0) d = 0;
LONGLONG smp = (d * 44100) / awe_qpc_freq;
if (smp > 4410) smp = 4410;
return (unsigned)smp;
static uint16_t last_ret = 0;
static LONGLONG last_qpc = 0;
static unsigned reads_since_adv = 0;
LONGLONG gap_us = ((now.QuadPart - last_qpc) * 1000000) / awe_qpc_freq;
uint16_t ret;
if (gap_us < 50000) {
/* Poll storm. The hard constraint (AWEUTIL WaitUntilWC @5F42,
* decoded 2026-07-16): its wait exits on EQUALITY with a target
* tick, and each loop iteration reads WC TWICE -- so the counter
* must advance SLOWER than the guest reads, or the equality sample
* only sees every 2nd value and misses targets of the wrong parity
* forever. Real silicon polls at ~1us vs the 22.7us tick, so every
* value is observed many times; our trapped reads cost ~30us, more
* than a real tick, so we peg the storm-time counter to the READ
* rate instead: +1 per 4 reads. Every value is then observable by
* loops that re-check at least once per 4 reads (all of AWEUTIL's
* do), waits stretch ~5x (seconds, not minutes), and the dead-clock
* bailouts (8192 unchanged reads) never trip. Never consult real
* time mid-storm. */
if (++reads_since_adv >= 4) {
last_ret = (uint16_t)(last_ret + 1);
reads_since_adv = 0;
}
ret = last_ret;
} else {
/* genuinely idle since the last read: resync to true wall time */
ret = (uint16_t)(((unsigned long long)
(now.QuadPart - awe_wc_origin_qpc)
* 44100ull) / (unsigned long long)awe_qpc_freq);
last_ret = ret;
reads_since_adv = 0;
}
last_qpc = now.QuadPart;
return ret;
}
/* Fairness gate: guest port I/O at storm rates (AWEUTIL polls WC ~550k/s)
* re-acquires awe_lock so fast that the render thread starves for seconds.
* The render thread raises this flag while it waits for the lock; the guest
* side backs off until it's through. */
static volatile LONG awe_render_waiting = 0;
/* activity stats (reported every ~10s of rendered audio per card) */
struct AweStats { unsigned long wr, rd_wc, rd, smld_w; };
static AweStats awe_stats[2]; /* 0 = front, 1 = rear */
@@ -100,21 +151,35 @@ static AweIoRange *awe_io_find(Bitu port) {
return NULL;
}
/* VWE_AWE_LOG=1: trace the first accesses + growth-of-count milestones */
/* VWE_AWE_LOG=1: trace the first accesses + growth-of-count milestones.
* VWE_AWE_LOG=2: additionally dump a 64-op CONSECUTIVE burst (with us
* timestamps) every 4M ops -- shows the guest's actual poll-loop structure
* instead of isolated samples. */
static int awe_log_on = -1;
static unsigned long awe_access_count = 0;
static void awe_io_trace(const char *dir, Bitu port, Bitu val, Bitu iolen) {
if (awe_log_on < 0) {
const char *l = getenv("VWE_AWE_LOG");
awe_log_on = (l && l[0] && l[0] != '0') ? 1 : 0;
awe_log_on = (l && l[0] && l[0] != '0') ? (l[0] == '2' ? 2 : 1) : 0;
}
if (!awe_log_on) return;
awe_access_count++;
if (awe_access_count <= 64 ||
(awe_access_count & (awe_access_count - 1)) == 0)
fprintf(stderr, "VWE AWE32 io[%lu]: %s %03lx val=%04lx len=%lu\n",
awe_access_count, dir, (unsigned long)port,
bool burst = awe_log_on >= 2 && (awe_access_count & 0x3FFFFF) < 64;
if (awe_access_count <= 64 || burst ||
(awe_access_count & (awe_access_count - 1)) == 0) {
LARGE_INTEGER t;
QueryPerformanceCounter(&t);
/* caller of the port-access primitive: real-mode [ss:bp+2] */
unsigned ret_ip = mem_readw(((PhysPt)SegValue(ss) << 4) +
((reg_bp + 2) & 0xFFFF));
fprintf(stderr, "VWE AWE32 io[%lu @%lluus cs:ip=%04x:%04x ret=%04x]: %s %03lx val=%04lx len=%lu\n",
awe_access_count,
(unsigned long long)((t.QuadPart - awe_wc_origin_qpc) * 1000000
/ awe_qpc_freq),
(unsigned)SegValue(cs), (unsigned)reg_ip, ret_ip,
dir, (unsigned long)port,
(unsigned long)val, (unsigned long)iolen);
}
}
/* PTR shadow per card: mirror of the core's cur_reg/cur_voice, so the glue
@@ -141,6 +206,7 @@ static Bitu awe_io_read(Bitu port, Bitu iolen) {
AweIoRange *r = awe_io_find(port);
if (!r) return ~0ul;
Bitu v;
while (awe_render_waiting) Sleep(1); /* let the render thread through */
EnterCriticalSection(&awe_lock);
if (iolen >= 2 && r->inw) v = r->inw((uint16_t)port, r->priv);
else if (r->inb) v = r->inb((uint16_t)port, r->priv);
@@ -148,6 +214,22 @@ static Bitu awe_io_read(Bitu port, Bitu iolen) {
LeaveCriticalSection(&awe_lock);
AweStats &s = awe_stats[(port & 0x40) ? 1 : 0];
if ((port & 0xF9F) == 0xA02) s.rd_wc++; else s.rd++; /* A22/A42 */
/* the RARE reads are the interesting ones during a WC-delay storm: log
* every read that isn't a WC poll, with the PTR shadow, to expose the
* never-satisfied outer wait condition (VWE_AWE_LOG>=1, first 200) */
{
const int ci2 = (port & 0x40) ? 1 : 0;
if (awe_log_on > 0 && !((port & 0xF9F) == 0xA02 &&
(awe_ptr[ci2] & 0xFF) == 0x3B)) {
static int rare_n = 0;
if (rare_n < 200) { rare_n++;
fprintf(stderr,
"VWE AWE32 rareR[%d]: port=%03lx ptr=%04x val=%04lx len=%lu\n",
rare_n, (unsigned long)port, awe_ptr[ci2],
(unsigned long)v, (unsigned long)iolen);
}
}
}
if ((port & 0xF1C) == 0xA00) /* A20-A23/A40-A43 */
awe_sm_trace("R", (port & 0x40) ? 1 : 0, port, v);
awe_io_trace("R", port, v, iolen);
@@ -167,6 +249,7 @@ static void awe_io_write(Bitu port, Bitu val, Bitu iolen) {
if ((port & 0xF1C) == 0xA00)
awe_sm_trace("W", ci, port, val);
awe_io_trace("W", port, val, iolen);
while (awe_render_waiting) Sleep(1); /* let the render thread through */
EnterCriticalSection(&awe_lock);
if (iolen >= 2 && r->outw) r->outw((uint16_t)port, (uint16_t)val, r->priv);
else if (r->outb) r->outb((uint16_t)port, (uint8_t)val, r->priv);
@@ -323,13 +406,14 @@ static DWORD WINAPI awe_thread_proc(LPVOID) {
Sleep(2);
continue;
}
/* render one 10ms chunk from both cards, sum into the slot */
LARGE_INTEGER now;
/* render one 10ms chunk from both cards, sum into the slot. The
* waiting flag holds off guest port-I/O storms (see above) so this
* acquire can't be starved. */
awe_render_waiting = 1;
EnterCriticalSection(&awe_lock);
awe_render_waiting = 0;
awe_render_chunk(&awe_front, 0, AWE_SLOT_FRAMES);
awe_render_chunk(&awe_rear, 1, AWE_SLOT_FRAMES);
QueryPerformanceCounter(&now);
awe_last_render_qpc = now.QuadPart;
LeaveCriticalSection(&awe_lock);
int16_t *out = awe_slotbuf[free_slot];
for (unsigned i = 0; i < AWE_SLOT_FRAMES; i++) {
@@ -496,6 +580,8 @@ void VWEAWE_Init(void) {
LARGE_INTEGER f;
QueryPerformanceFrequency(&f);
awe_qpc_freq = f.QuadPart ? f.QuadPart : 1;
QueryPerformanceCounter(&f);
awe_wc_origin_qpc = f.QuadPart; /* WC free-runs from power-on */
emu8k_init(&awe_front, 0x620, ram_kb);
emu8k_init(&awe_rear, 0x640, ram_kb);