Files
wz-phone/crates/wzp-native/cpp/oboe_bridge.cpp
Siavash Sameni 8c4d640f89
Some checks failed
Mirror to GitHub / mirror (push) Failing after 40s
Build Release Binaries / build-amd64 (push) Failing after 3m43s
fix(android): playout Usage::Media + relay CallSetup advertises real IP
Three real bugs, one smoke-test session's worth of progress.

1. RELAY: wrong advertised addr in CallSetup
   The direct-call CallSetup computed `relay_addr = addr.ip()` where
   `addr = connection.remote_address()` — i.e. the CLIENT'S IP, not the
   relay's. So the relay was telling both parties "the call room is at
   the answerer's IP:4433", which meant each client dialed either the
   other client (no server listening) or themselves. Both endpoint.connect
   calls hung forever and the call never happened.
   Fix: compute the relay's own advertised IP once at startup. If the
   listen addr is 0.0.0.0, probe the primary outbound interface via the
   classic UDP-bind-and-connect(8.8.8.8:80) trick to discover the LAN
   IP the OS would use to reach external hosts. Thread the resulting
   advertised_addr_str into the CallSetup sender for both parties.

2. RELAY: accept loop serialized QUIC handshakes
   Previously the main accept loop called `wzp_transport::accept` which
   did both `endpoint.accept().await` AND `incoming.await` (the server-
   side QUIC handshake). A single slow handshake therefore blocked every
   subsequent client from being accepted. Unroll the helper here and
   move `incoming.await` into the per-connection spawned task, so every
   handshake runs in parallel. Also log "accept queue: new Incoming",
   "QUIC handshake complete", and "QUIC handshake failed" so we can tell
   immediately whether a client's packets are reaching the relay at all.

3. ANDROID: playout was routed to the silent in-call stream
   The Oboe playout stream was configured with Usage::VoiceCommunication,
   which routes to the Android in-call earpiece stream. That stream is
   silent unless the Activity has called AudioManager.setMode(
   IN_COMMUNICATION) and, even then, only the earpiece/BT headset get
   audio (not the loud speaker). Result: android→mac calls worked
   because mac had a normal media output, but mac→android calls were
   silent even though packets flowed through the relay just fine.
   Switch to Usage::Media + ContentType::Speech so Oboe routes to the
   loud speaker and uses the media volume slider. A later polish step
   will wire setMode + setSpeakerphoneOn from MainActivity.kt so we can
   go back to VoiceCommunication for AEC and proximity-sensor routing.

Plus: heartbeat tracing every 2s in the send/recv tasks — frames_sent,
last_rms, last_pkt_bytes, short_reads on the send side; decoded_frames,
last_decode_n, last_written, decode_errs on the recv side. Will make the
next "no sound" regression trivial to localize.
2026-04-09 20:55:10 +04:00

307 lines
12 KiB
C++

// Full Oboe implementation for Android
// This file is compiled only when targeting Android
#include "oboe_bridge.h"
#ifdef __ANDROID__
#include <oboe/Oboe.h>
#include <android/log.h>
#include <cstring>
#include <atomic>
#define LOG_TAG "wzp-oboe"
#define LOGI(...) __android_log_print(ANDROID_LOG_INFO, LOG_TAG, __VA_ARGS__)
#define LOGW(...) __android_log_print(ANDROID_LOG_WARN, LOG_TAG, __VA_ARGS__)
#define LOGE(...) __android_log_print(ANDROID_LOG_ERROR, LOG_TAG, __VA_ARGS__)
// ---------------------------------------------------------------------------
// Ring buffer helpers (SPSC, lock-free)
// ---------------------------------------------------------------------------
static inline int32_t ring_available_read(const wzp_atomic_int* write_idx,
const wzp_atomic_int* read_idx,
int32_t capacity) {
int32_t w = std::atomic_load_explicit(write_idx, std::memory_order_acquire);
int32_t r = std::atomic_load_explicit(read_idx, std::memory_order_relaxed);
int32_t avail = w - r;
if (avail < 0) avail += capacity;
return avail;
}
static inline int32_t ring_available_write(const wzp_atomic_int* write_idx,
const wzp_atomic_int* read_idx,
int32_t capacity) {
return capacity - 1 - ring_available_read(write_idx, read_idx, capacity);
}
static inline void ring_write(int16_t* buf, int32_t capacity,
wzp_atomic_int* write_idx, const wzp_atomic_int* read_idx,
const int16_t* src, int32_t count) {
int32_t w = std::atomic_load_explicit(write_idx, std::memory_order_relaxed);
for (int32_t i = 0; i < count; i++) {
buf[w] = src[i];
w++;
if (w >= capacity) w = 0;
}
std::atomic_store_explicit(write_idx, w, std::memory_order_release);
}
static inline void ring_read(int16_t* buf, int32_t capacity,
const wzp_atomic_int* write_idx, wzp_atomic_int* read_idx,
int16_t* dst, int32_t count) {
int32_t r = std::atomic_load_explicit(read_idx, std::memory_order_relaxed);
for (int32_t i = 0; i < count; i++) {
dst[i] = buf[r];
r++;
if (r >= capacity) r = 0;
}
std::atomic_store_explicit(read_idx, r, std::memory_order_release);
}
// ---------------------------------------------------------------------------
// Global state
// ---------------------------------------------------------------------------
static std::shared_ptr<oboe::AudioStream> g_capture_stream;
static std::shared_ptr<oboe::AudioStream> g_playout_stream;
// Value copy — the WzpOboeRings the Rust side passes us lives on the caller's
// stack frame and goes away as soon as wzp_oboe_start returns. The raw
// int16/atomic pointers INSIDE the struct point into the Rust-owned, leaked-
// for-the-lifetime-of-the-process AudioBackend singleton, so copying the
// struct by value is safe and keeps the inner pointers valid indefinitely.
// g_rings_valid guards the audio-callback-side read; clearing it in stop()
// signals "no backend" to the callbacks which then return silence + Stop.
static WzpOboeRings g_rings{};
static std::atomic<bool> g_rings_valid{false};
static std::atomic<bool> g_running{false};
static std::atomic<float> g_capture_latency_ms{0.0f};
static std::atomic<float> g_playout_latency_ms{0.0f};
// ---------------------------------------------------------------------------
// Capture callback
// ---------------------------------------------------------------------------
class CaptureCallback : public oboe::AudioStreamDataCallback {
public:
oboe::DataCallbackResult onAudioReady(
oboe::AudioStream* stream,
void* audioData,
int32_t numFrames) override {
if (!g_running.load(std::memory_order_relaxed) ||
!g_rings_valid.load(std::memory_order_acquire)) {
return oboe::DataCallbackResult::Stop;
}
const int16_t* src = static_cast<const int16_t*>(audioData);
int32_t avail = ring_available_write(g_rings.capture_write_idx,
g_rings.capture_read_idx,
g_rings.capture_capacity);
int32_t to_write = (numFrames < avail) ? numFrames : avail;
if (to_write > 0) {
ring_write(g_rings.capture_buf, g_rings.capture_capacity,
g_rings.capture_write_idx, g_rings.capture_read_idx,
src, to_write);
}
// Update latency estimate
auto result = stream->calculateLatencyMillis();
if (result) {
g_capture_latency_ms.store(static_cast<float>(result.value()),
std::memory_order_relaxed);
}
return oboe::DataCallbackResult::Continue;
}
};
// ---------------------------------------------------------------------------
// Playout callback
// ---------------------------------------------------------------------------
class PlayoutCallback : public oboe::AudioStreamDataCallback {
public:
oboe::DataCallbackResult onAudioReady(
oboe::AudioStream* stream,
void* audioData,
int32_t numFrames) override {
if (!g_running.load(std::memory_order_relaxed) ||
!g_rings_valid.load(std::memory_order_acquire)) {
memset(audioData, 0, numFrames * sizeof(int16_t));
return oboe::DataCallbackResult::Stop;
}
int16_t* dst = static_cast<int16_t*>(audioData);
int32_t avail = ring_available_read(g_rings.playout_write_idx,
g_rings.playout_read_idx,
g_rings.playout_capacity);
int32_t to_read = (numFrames < avail) ? numFrames : avail;
if (to_read > 0) {
ring_read(g_rings.playout_buf, g_rings.playout_capacity,
g_rings.playout_write_idx, g_rings.playout_read_idx,
dst, to_read);
}
// Fill remainder with silence on underrun
if (to_read < numFrames) {
memset(dst + to_read, 0, (numFrames - to_read) * sizeof(int16_t));
}
// Update latency estimate
auto result = stream->calculateLatencyMillis();
if (result) {
g_playout_latency_ms.store(static_cast<float>(result.value()),
std::memory_order_relaxed);
}
return oboe::DataCallbackResult::Continue;
}
};
static CaptureCallback g_capture_cb;
static PlayoutCallback g_playout_cb;
// ---------------------------------------------------------------------------
// Public C API
// ---------------------------------------------------------------------------
int wzp_oboe_start(const WzpOboeConfig* config, const WzpOboeRings* rings) {
if (g_running.load(std::memory_order_relaxed)) {
LOGW("wzp_oboe_start: already running");
return -1;
}
// Deep-copy the rings struct into static storage BEFORE we publish it to
// the audio callbacks — `rings` points at the caller's stack frame and
// goes away as soon as this function returns.
g_rings = *rings;
g_rings_valid.store(true, std::memory_order_release);
// Build capture stream
oboe::AudioStreamBuilder captureBuilder;
captureBuilder.setDirection(oboe::Direction::Input)
->setPerformanceMode(oboe::PerformanceMode::LowLatency)
->setSharingMode(oboe::SharingMode::Exclusive)
->setFormat(oboe::AudioFormat::I16)
->setChannelCount(config->channel_count)
->setSampleRate(config->sample_rate)
->setFramesPerDataCallback(config->frames_per_burst)
->setInputPreset(oboe::InputPreset::VoiceCommunication)
->setDataCallback(&g_capture_cb);
oboe::Result result = captureBuilder.openStream(g_capture_stream);
if (result != oboe::Result::OK) {
LOGE("Failed to open capture stream: %s", oboe::convertToText(result));
return -2;
}
// Build playout stream
//
// Usage::Media (NOT VoiceCommunication) routes to the media audio
// stream which plays through the loud speaker and uses the media
// volume slider. VoiceCommunication routes to the in-call earpiece
// stream which is silent unless AudioManager.setMode(IN_COMMUNICATION)
// has been called from the Activity, and even then only the earpiece
// (or a bluetooth headset) gets audio by default. For a debug-friendly
// smoke test we want loud speaker by default. A future polish step
// will wire setMode + setSpeakerphoneOn from MainActivity.kt so we
// can switch back to VoiceCommunication (for AEC benefits etc).
oboe::AudioStreamBuilder playoutBuilder;
playoutBuilder.setDirection(oboe::Direction::Output)
->setPerformanceMode(oboe::PerformanceMode::LowLatency)
->setSharingMode(oboe::SharingMode::Exclusive)
->setFormat(oboe::AudioFormat::I16)
->setChannelCount(config->channel_count)
->setSampleRate(config->sample_rate)
->setFramesPerDataCallback(config->frames_per_burst)
->setUsage(oboe::Usage::Media)
->setContentType(oboe::ContentType::Speech)
->setDataCallback(&g_playout_cb);
result = playoutBuilder.openStream(g_playout_stream);
if (result != oboe::Result::OK) {
LOGE("Failed to open playout stream: %s", oboe::convertToText(result));
g_capture_stream->close();
g_capture_stream.reset();
return -3;
}
g_running.store(true, std::memory_order_release);
// Start both streams
result = g_capture_stream->requestStart();
if (result != oboe::Result::OK) {
LOGE("Failed to start capture: %s", oboe::convertToText(result));
g_running.store(false, std::memory_order_release);
g_capture_stream->close();
g_playout_stream->close();
g_capture_stream.reset();
g_playout_stream.reset();
return -4;
}
result = g_playout_stream->requestStart();
if (result != oboe::Result::OK) {
LOGE("Failed to start playout: %s", oboe::convertToText(result));
g_running.store(false, std::memory_order_release);
g_capture_stream->requestStop();
g_capture_stream->close();
g_playout_stream->close();
g_capture_stream.reset();
g_playout_stream.reset();
return -5;
}
LOGI("Oboe started: sr=%d burst=%d ch=%d",
config->sample_rate, config->frames_per_burst, config->channel_count);
return 0;
}
void wzp_oboe_stop(void) {
g_running.store(false, std::memory_order_release);
// Tell the audio callbacks to stop touching g_rings BEFORE we tear down
// the streams, so any in-flight callback returns Stop instead of reading
// stale pointers.
g_rings_valid.store(false, std::memory_order_release);
if (g_capture_stream) {
g_capture_stream->requestStop();
g_capture_stream->close();
g_capture_stream.reset();
}
if (g_playout_stream) {
g_playout_stream->requestStop();
g_playout_stream->close();
g_playout_stream.reset();
}
LOGI("Oboe stopped");
}
float wzp_oboe_capture_latency_ms(void) {
return g_capture_latency_ms.load(std::memory_order_relaxed);
}
float wzp_oboe_playout_latency_ms(void) {
return g_playout_latency_ms.load(std::memory_order_relaxed);
}
int wzp_oboe_is_running(void) {
return g_running.load(std::memory_order_relaxed) ? 1 : 0;
}
#else
// Non-Android fallback — should not be reached; oboe_stub.cpp is used instead.
// Provide empty implementations just in case.
int wzp_oboe_start(const WzpOboeConfig* config, const WzpOboeRings* rings) {
(void)config; (void)rings;
return -99;
}
void wzp_oboe_stop(void) {}
float wzp_oboe_capture_latency_ms(void) { return 0.0f; }
float wzp_oboe_playout_latency_ms(void) { return 0.0f; }
int wzp_oboe_is_running(void) { return 0; }
#endif // __ANDROID__