Run clang-format (the repo's .clang-format: LLVM base, 120 cols, tabs, Allman functions) over every source file so the tree is formatter-clean. Whitespace only -- no behavior change; full x64 + x86 suites pass. Also set SortIncludes: false in .clang-format. Windows include order is load-bearing (windows.h must precede tlhelp32.h / mmreg.h / xinput.h / dinput.h; winsock2.h must precede windows.h), and the default alphabetical sort reorders tlhelp32.h ahead of windows.h -- a build break. Leaving order alone keeps the manual, correct grouping.
310 lines
12 KiB
C++
310 lines
12 KiB
C++
// In-process self-test for the WASAPI render-hook (hook/src/audio_hook.cpp), focused on
|
|
// audio-format detection. This process plays both "game" and "hook": it installs the
|
|
// audio hooks and renders sine tones through WASAPI at a matrix of common formats,
|
|
// exercising both code paths the hook uses to learn a stream's format:
|
|
//
|
|
// - SEE-INIT: hooks installed before the render client is created, so the hook sees
|
|
// IAudioClient::Initialize and records the *exact* format.
|
|
// - GUESS: the render client already exists when the hook installs (the real case --
|
|
// we inject into a running game), so the hook never saw Initialize and assumes the
|
|
// device mix format, then measures the stream's true sample rate from its cadence.
|
|
//
|
|
// For each format it asserts the hook published the right rate/channels/bits and the
|
|
// right provenance state. No game, no second Steam account. Exits 0 on pass, 1 on fail;
|
|
// SKIPs cleanly (exit 0) on a machine with no render endpoint, mirroring the other tests.
|
|
|
|
#include <cstdint>
|
|
#include <cstdio>
|
|
#include <vector>
|
|
|
|
#include <windows.h>
|
|
|
|
#include <audioclient.h>
|
|
#include <mmdeviceapi.h>
|
|
#include <mmreg.h>
|
|
|
|
#include "audio_hook.hpp"
|
|
#include "coop/audio_ring.hpp"
|
|
#include "coop/protocol.hpp"
|
|
#include "coop/shared_memory.hpp"
|
|
#include "ipc_client.hpp"
|
|
#include "tone_source.hpp"
|
|
|
|
using namespace coop;
|
|
using coop::tone::ToneFormat;
|
|
using coop::tone::ToneSource;
|
|
|
|
namespace {
|
|
|
|
int g_failures = 0;
|
|
|
|
// Returns 1 (and logs) on failure, 0 on success -- so callers can sum a tally.
|
|
int expect(bool ok, const char* what)
|
|
{
|
|
if (!ok) {
|
|
std::printf(" FAIL: %s\n", what);
|
|
++g_failures;
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
void reset_ring(AudioRingHeader* ring, SharedBlock* block)
|
|
{
|
|
audio_ring_init(*ring, kAudioRingCapacity);
|
|
ring->capture_enabled.store(1, std::memory_order_release);
|
|
block->status.audio_streams[0] = AudioStreamInfo{}; // clear stale provenance from the last case
|
|
}
|
|
|
|
// Drain the ring and report whether any non-silent sample landed in it (capture path).
|
|
bool ring_has_nonsilent(AudioRingHeader* ring)
|
|
{
|
|
std::vector<std::uint8_t> buf(128 * 1024, 0);
|
|
const std::uint32_t got = audio_ring_pop(*ring, buf.data(), static_cast<std::uint32_t>(buf.size()));
|
|
for (std::uint32_t i = 0; i < got; ++i) {
|
|
if (buf[i] != 0) {
|
|
return true;
|
|
}
|
|
}
|
|
return false;
|
|
}
|
|
|
|
const char* fmt_desc(const ToneFormat& f, char* buf, size_t n)
|
|
{
|
|
std::snprintf(buf, n, "%u Hz %u ch %u-bit %s", f.rate, f.channels, f.bits, f.is_float ? "float" : "pcm");
|
|
return buf;
|
|
}
|
|
|
|
// SEE-INIT: install hooks first, then create the render client so the hook records the
|
|
// exact Initialize format. Verifies the full format and the Exact provenance.
|
|
void test_see_init(hook::IpcClient& ipc, AudioRingHeader* ring, SharedBlock* block, const ToneFormat& want)
|
|
{
|
|
char d[64];
|
|
reset_ring(ring, block);
|
|
if (!hook::install_audio_hooks(ipc, ring)) {
|
|
std::printf(" SKIP see-init (audio hooks unavailable)\n");
|
|
return;
|
|
}
|
|
|
|
ToneSource tone;
|
|
if (!tone.open(want)) {
|
|
std::printf(" SKIP see-init %s (format unavailable here)\n", fmt_desc(want, d, sizeof(d)));
|
|
hook::remove_audio_hooks();
|
|
return;
|
|
}
|
|
const ToneFormat& f = tone.format();
|
|
|
|
// Exact format publishes at registration; render briefly so capture fills the ring.
|
|
const std::uint64_t silenced_before = hook::audio_frames_silenced();
|
|
const DWORD end = GetTickCount() + 300;
|
|
while (GetTickCount() < end) {
|
|
tone.render_step(50);
|
|
}
|
|
|
|
const AudioStreamInfo& s = block->status.audio_streams[0];
|
|
int fail = 0;
|
|
fail += expect(audio_ring_format_ready(*ring), "see-init: format published to ring");
|
|
fail += expect(ring->sample_rate == f.rate, "see-init: ring rate == exact rate");
|
|
fail += expect(ring->channels == f.channels, "see-init: ring channels == exact channels");
|
|
fail += expect(ring->bits == f.bits, "see-init: ring bits == exact bits");
|
|
fail += expect(s.sample_rate == f.rate, "see-init: HookStatus rate == exact rate");
|
|
fail += expect(s.format_state == AudioFormat_Exact, "see-init: provenance == Exact");
|
|
fail += expect(ring_has_nonsilent(ring), "see-init: non-silent audio captured");
|
|
fail += expect(hook::audio_frames_silenced() > silenced_before, "see-init: local playback muted (no echo)");
|
|
std::printf(" %s see-init %s -> ring %uHz/%uch/%ubit state=%u\n", fail == 0 ? "PASS" : "FAIL",
|
|
fmt_desc(f, d, sizeof(d)), ring->sample_rate, ring->channels, ring->bits, s.format_state);
|
|
|
|
tone.close();
|
|
hook::remove_audio_hooks();
|
|
}
|
|
|
|
// GUESS: create the render client first (its Initialize is unseen), then install hooks so
|
|
// the stream is discovered lazily and assigned the device mix format -- whose rate is then
|
|
// measured/corrected. Rendered with the device channels/bits (only the rate differs from
|
|
// the device) so the test isolates the rate-measurement logic the real bug needed.
|
|
void test_guess(hook::IpcClient& ipc, AudioRingHeader* ring, SharedBlock* block, unsigned rate)
|
|
{
|
|
reset_ring(ring, block);
|
|
|
|
ToneSource tone;
|
|
ToneFormat want;
|
|
want.rate = rate; // channels/bits resolve to the device's
|
|
if (!tone.open(want)) {
|
|
std::printf(" SKIP guess %u Hz (format unavailable here)\n", rate);
|
|
return;
|
|
}
|
|
const ToneFormat& f = tone.format();
|
|
|
|
// Let the stream reach steady state before attaching, like a game already running when
|
|
// we inject (the real case) -- not a stream we caught at its first buffer.
|
|
const DWORD warm = GetTickCount() + 300;
|
|
while (GetTickCount() < warm) {
|
|
tone.render_step(30);
|
|
}
|
|
|
|
// Hooks install *after* the client exists -> the lazy-discovery (guess) path.
|
|
if (!hook::install_audio_hooks(ipc, ring)) {
|
|
std::printf(" SKIP guess (audio hooks unavailable)\n");
|
|
tone.close();
|
|
return;
|
|
}
|
|
|
|
// Render while driving republish (the DLL's worker does this each tick) until the
|
|
// measured rate is published, then render a bit more so capture fills the ring.
|
|
const DWORD measure_deadline = GetTickCount() + 2000;
|
|
while (GetTickCount() < measure_deadline && !audio_ring_format_ready(*ring)) {
|
|
tone.render_step(30);
|
|
hook::republish_audio_format();
|
|
}
|
|
// Format is published; from here the hook must capture AND mute (the no-echo path).
|
|
const std::uint64_t silenced_before = hook::audio_frames_silenced();
|
|
const DWORD cap_end = GetTickCount() + 200;
|
|
while (GetTickCount() < cap_end) {
|
|
tone.render_step(30);
|
|
}
|
|
|
|
const AudioStreamInfo& s = block->status.audio_streams[0];
|
|
int fail = 0;
|
|
fail += expect(audio_ring_format_ready(*ring), "guess: format published after measuring");
|
|
fail += expect(ring->sample_rate == f.rate, "guess: measured rate == rendered rate");
|
|
fail += expect(s.sample_rate == f.rate, "guess: HookStatus rate == rendered rate");
|
|
fail += expect(s.format_state == AudioFormat_Measured, "guess: provenance == Measured");
|
|
fail += expect(ring_has_nonsilent(ring), "guess: non-silent audio captured");
|
|
// THE BROTATO BUG: a guessed (late-attach) stream is byte-compatible here (device
|
|
// channels/bits), so the hook must mute the game's local playback too -- otherwise the
|
|
// game plays locally AND the mirror re-renders it, slightly delayed = a metallic double.
|
|
fail += expect(hook::audio_frames_silenced() > silenced_before,
|
|
"guess: local playback muted (no echo) -- the Brotato double-audio bug");
|
|
std::printf(" %s guess %u Hz (device %uch/%ubit) -> measured %uHz state=%u\n", fail == 0 ? "PASS" : "FAIL", rate,
|
|
f.channels, f.bits, ring->sample_rate, s.format_state);
|
|
|
|
tone.close();
|
|
hook::remove_audio_hooks();
|
|
}
|
|
|
|
// GUESS-MISMATCH: the device channels/bits guess is *wrong* for this stream (its bytes/frame
|
|
// differ). We can't recover the true channels/bits, but the capture must stay safe -- the
|
|
// VirtualQuery clamp must stop the copy reading past the source buffer. We can't assert a
|
|
// "correct" format here (it's fundamentally undetectable); we assert the hook survives and
|
|
// doesn't read absurd amounts, i.e. the unit test completes without an access violation.
|
|
void test_guess_mismatch_safe(hook::IpcClient& ipc, AudioRingHeader* ring, SharedBlock* block, const ToneFormat& want,
|
|
const char* label)
|
|
{
|
|
char d[64];
|
|
reset_ring(ring, block);
|
|
|
|
ToneSource tone;
|
|
if (!tone.open(want)) {
|
|
std::printf(" SKIP guess-mismatch %s (%s unavailable here)\n", label, fmt_desc(want, d, sizeof(d)));
|
|
return;
|
|
}
|
|
const ToneFormat& f = tone.format();
|
|
const DWORD warm = GetTickCount() + 300; // steady state before attaching
|
|
while (GetTickCount() < warm) {
|
|
tone.render_step(30);
|
|
}
|
|
if (!hook::install_audio_hooks(ipc, ring)) {
|
|
std::printf(" SKIP guess-mismatch (audio hooks unavailable)\n");
|
|
tone.close();
|
|
return;
|
|
}
|
|
|
|
// Render and capture through the guessed (too-large) block. The clamp must keep this
|
|
// from over-reading; reaching the end of the loop is the pass (no AV).
|
|
const DWORD end = GetTickCount() + 600;
|
|
while (GetTickCount() < end) {
|
|
tone.render_step(30);
|
|
hook::republish_audio_format();
|
|
}
|
|
std::printf(" PASS guess-mismatch %s (%s) survived capture with a too-large guessed block (no over-read)\n",
|
|
fmt_desc(f, d, sizeof(d)), label);
|
|
|
|
tone.close();
|
|
hook::remove_audio_hooks();
|
|
}
|
|
|
|
} // namespace
|
|
|
|
int main()
|
|
{
|
|
if (FAILED(CoInitializeEx(nullptr, COINIT_MULTITHREADED))) {
|
|
std::printf("FAIL: CoInitializeEx\n");
|
|
return 1;
|
|
}
|
|
|
|
// Host side: the IPC SharedBlock (named by our pid) the hook's IpcClient connects to,
|
|
// plus one producer ring with capture enabled.
|
|
SharedMemory shm;
|
|
if (!shm.create(shared_memory_name(GetCurrentProcessId()), sizeof(SharedBlock))) {
|
|
std::printf("FAIL: create shared memory\n");
|
|
return 1;
|
|
}
|
|
auto* block = shm.as<SharedBlock>(); // OS zero-inits the mapping
|
|
block->version = kProtocolVersion;
|
|
block->sequence.store(0, std::memory_order_relaxed);
|
|
block->magic = kProtocolMagic;
|
|
|
|
std::vector<std::uint8_t> ring_storage(audio_ring_total_size(kAudioRingCapacity), 0);
|
|
auto* ring = new (ring_storage.data()) AudioRingHeader();
|
|
audio_ring_init(*ring, kAudioRingCapacity);
|
|
|
|
hook::IpcClient ipc;
|
|
expect(ipc.connect(10, 5), "IPC client connect");
|
|
|
|
// Probe the endpoint once; SKIP cleanly on a headless machine (no render device).
|
|
// Capture the device mix format so the guess-mismatch cases can pick formats whose
|
|
// bytes/frame are guaranteed to differ from the device's.
|
|
ToneFormat dev;
|
|
{
|
|
ToneSource probe;
|
|
if (!probe.open(ToneFormat{})) {
|
|
std::printf("SKIP: no default render endpoint (no audio device?)\n");
|
|
CoUninitialize();
|
|
return 0;
|
|
}
|
|
dev = probe.format();
|
|
probe.close();
|
|
}
|
|
std::printf("Device mix format: %u Hz %u ch %u-bit %s\n", dev.rate, dev.channels, dev.bits,
|
|
dev.is_float ? "float" : "pcm");
|
|
|
|
// SEE-INIT: exact full-format detection across common rate/channel/bit-depth combos.
|
|
std::printf("== SEE-INIT (hook sees Initialize -> exact format) ==\n");
|
|
const ToneFormat see_init[] = {
|
|
{44100, 2, 16, false}, // CD-quality stereo PCM
|
|
{48000, 2, 32, true}, // common float stereo
|
|
{96000, 2, 32, true}, // hi-res stereo float
|
|
{44100, 1, 16, false}, // mono PCM
|
|
{48000, 6, 32, true}, // 5.1 float
|
|
};
|
|
for (const ToneFormat& f : see_init) {
|
|
test_see_init(ipc, ring, block, f);
|
|
}
|
|
|
|
// GUESS (match): the lazy-discovery path with the device channels/bits, so only the
|
|
// rate differs -- the hook measures + corrects it to the true rate (the Brotato/Godot
|
|
// case). Rendered at the device's channel/bit layout, so the bytes/frame match.
|
|
std::printf("== GUESS, byte-compatible (pre-existing client -> measure the true rate) ==\n");
|
|
for (unsigned rate : {44100u, 48000u, 96000u}) {
|
|
test_guess(ipc, ring, block, rate);
|
|
}
|
|
|
|
// GUESS (byte-incompatible): a pre-existing client whose channels/bits differ from the
|
|
// device. The hook can't recover them (so it can't be pitch/format-correct here -- that's
|
|
// a documented limitation), but the VirtualQuery clamp must keep the capture safe rather
|
|
// than over-reading the source buffer.
|
|
std::printf("== GUESS, byte-incompatible (channels/bits differ -> capture must stay safe) ==\n");
|
|
if (dev.channels >= 2) {
|
|
test_guess_mismatch_safe(ipc, ring, block, {dev.rate, 1, dev.bits, dev.is_float}, "mono");
|
|
}
|
|
{
|
|
const unsigned alt_bits = (dev.bits == 32) ? 16u : 32u;
|
|
const bool alt_float = (alt_bits == 32);
|
|
test_guess_mismatch_safe(ipc, ring, block, {dev.rate, dev.channels, alt_bits, alt_float}, "alt bit depth");
|
|
}
|
|
|
|
CoUninitialize();
|
|
std::printf(g_failures == 0 ? "AUDIO HOOK TEST PASS\n" : "AUDIO HOOK TEST FAILED (%d)\n", g_failures);
|
|
return g_failures == 0 ? 0 : 1;
|
|
}
|