在上一节有提到，音频数据会通过共享内存传到播放线程播放，如果是混音，则音频数据传入到MixerThread进行处理。当调用output打开输出流后会根据output_flag创建对应的播放线程。
thread = new MixerThread(this, outputStream, *output, mSystemReady);
创建MixerThread对象时，会创建混音器AudioMixer，实现了混音的主要逻辑。
mAudioMixer = new AudioMixer(mNormalFrameCount, mSampleRate);
mNormalFrameCount:AudioMixer会根据传进来的mNormalFrameCount作为一次输送数据的长度，把源buffer的音频数据写入目的buffer
mSampleRate:AudioMixer会把传进来的mSampleRate作为音频数据输出的采样率
MixerThread继承于PlaybackThread，当PlaybackThread的核心方法threadLoop被唤醒时，就开始拿到音频数据进行混音处理。
混音关键的三个步骤有
(1)prepareTracks_l
将需要混音的Track赋值到AudioMixer中，并配置相关混音参数Paramter
(2)threadLoop_mix
开始混音
(3)threadLoop_write
将混音后的数据写入到HAL中去
1.混音准备
准备工作主要做了3件事情：
(1)查看音频数据是否充足
(2)计算音量
(3)将外部Track属性、参数等工作设置到AudioMixer内部的Track中
设置的内容包含format、sampleRate、音量volume、音频数据输入地址mainBuffer、重采样器等等，通过setParameter设置
prepareTracks函数就是混音之前做好准备工作，为AudioMixer混音前创建一一对应的内部Track，并为Track赋值音量、buffer、format、重采样管理器等参数，为混音前做好准备工作，具体看的不是很明白，以后再补充。
2.混音
在上一节提到，PlaybackThread的threadLoop中调用了threadLoop_mix()， 其中调用了AudioMixer->process,我们先来看下process具体实现：
AudioMixer继承于AudioMixerBase， process在AudioMixerBase.h中定义如下：
void process() {
preProcess();
(this->*mHook)();
postProcess();
}
重点就是执行mHook函数指针指向的函数，下面分析下具体指向了哪个函数。
在第一步时调用AudioMixer的setParameter()时会调用 invalidate()方法，该方法在AudioMixerBase.h中定义了hook的实现。
void invalidate() {
mHook = &AudioMixerBase::process__validate;
}
再具体看下process__validate，该方法主要做了两件事情，一是为当前Track指定hook函数，即对应的混音函数；二是为AudioMixer指定mHook函数指针成员，处理当前混音器下面所有Track逻辑。
cpp
void AudioMixerBase::process__validate()
{
......
for (const auto &pair : mTracks) {
const int name = pair.first;
const std::shared_ptr<TrackBase> &t = pair.second;
if (!t->enabled) continue;
mEnabled.emplace_back(name); // we add to mEnabled in order of name.
mGroups[t->mainBuffer].emplace_back(name); // mGroups also in order of name.
uint32_t n = 0;
// FIXME can overflow (mask is only 3 bits)
n |= NEEDS_CHANNEL_1 + t->channelCount - 1;
if (t->doesResample()) {
n |= NEEDS_RESAMPLE;
}
if (t->auxLevel != 0 && t->auxBuffer != NULL) {
n |= NEEDS_AUX;
}
if (t->volumeInc[0]|t->volumeInc[1]) {
volumeRamp = true;
} else if (!t->doesResample() && t->volumeRL == 0) {
n |= NEEDS_MUTE;
}
t->needs = n;
if (n & NEEDS_MUTE) {
t->hook = &TrackBase::track__nop;
} else {
if (n & NEEDS_AUX) {
all16BitsStereoNoResample = false;
}
if (n & NEEDS_RESAMPLE) {
all16BitsStereoNoResample = false;
resampling = true;
if ((n & NEEDS_CHANNEL_COUNT__MASK) == NEEDS_CHANNEL_1
&& t->channelMask == AUDIO_CHANNEL_OUT_MONO // MONO_HACK
&& isAudioChannelPositionMask(t->mMixerChannelMask)) {
t->hook = TrackBase::getTrackHook(
TRACKTYPE_RESAMPLEMONO, t->mMixerChannelCount,
t->mMixerInFormat, t->mMixerFormat);
} else if ((n & NEEDS_CHANNEL_COUNT__MASK) >= NEEDS_CHANNEL_2
&& t->useStereoVolume()) {
t->hook = TrackBase::getTrackHook(
TRACKTYPE_RESAMPLESTEREO, t->mMixerChannelCount,
t->mMixerInFormat, t->mMixerFormat);
} else {
t->hook = TrackBase::getTrackHook(
TRACKTYPE_RESAMPLE, t->mMixerChannelCount,
t->mMixerInFormat, t->mMixerFormat);
}
ALOGV_IF((n & NEEDS_CHANNEL_COUNT__MASK) > NEEDS_CHANNEL_2,
"Track %d needs downmix + resample", name);
} else {
if ((n & NEEDS_CHANNEL_COUNT__MASK) == NEEDS_CHANNEL_1){
t->hook = TrackBase::getTrackHook(
(isAudioChannelPositionMask(t->mMixerChannelMask) // TODO: MONO_HACK
&& t->channelMask == AUDIO_CHANNEL_OUT_MONO)
? TRACKTYPE_NORESAMPLEMONO : TRACKTYPE_NORESAMPLE,
t->mMixerChannelCount,
t->mMixerInFormat, t->mMixerFormat);
all16BitsStereoNoResample = false;
}
if ((n & NEEDS_CHANNEL_COUNT__MASK) >= NEEDS_CHANNEL_2){
t->hook = TrackBase::getTrackHook(
t->useStereoVolume() ? TRACKTYPE_NORESAMPLESTEREO
: TRACKTYPE_NORESAMPLE,
t->mMixerChannelCount, t->mMixerInFormat,
t->mMixerFormat);
ALOGV_IF((n & NEEDS_CHANNEL_COUNT__MASK) > NEEDS_CHANNEL_2,
"Track %d needs downmix", name);
}
}
}
}
// select the processing hooks
mHook = &AudioMixerBase::process__nop;
if (mEnabled.size() > 0) {
if (resampling) {
if (mOutputTemp.get() == nullptr) {
mOutputTemp.reset(new int32_t[MAX_NUM_CHANNELS * mFrameCount]);
}
if (mResampleTemp.get() == nullptr) {
mResampleTemp.reset(new int32_t[MAX_NUM_CHANNELS * mFrameCount]);
}
mHook = &AudioMixerBase::process__genericResampling;
} else {
// we keep temp arrays around.
mHook = &AudioMixerBase::process__genericNoResampling;
if (all16BitsStereoNoResample && !volumeRamp) {
if (mEnabled.size() == 1) {
const std::shared_ptr<TrackBase> &t = mTracks[mEnabled[0]];
if ((t->needs & NEEDS_MUTE) == 0) {
// The check prevents a muted track from acquiring a process hook.
//
// This is dangerous if the track is MONO as that requires
// special case handling due to implicit channel duplication.
// Stereo or Multichannel should actually be fine here.
mHook = getProcessHook(PROCESSTYPE_NORESAMPLEONETRACK,
t->mMixerChannelCount, t->mMixerInFormat, t->mMixerFormat,
t->useStereoVolume());
}
}
}
}
}
ALOGV("mixer configuration change: %zu "
"all16BitsStereoNoResample=%d, resampling=%d, volumeRamp=%d",
mEnabled.size(), all16BitsStereoNoResample, resampling, volumeRamp);
process();
// Now that the volume ramp has been done, set optimal state and
// track hooks for subsequent mixer process
if (mEnabled.size() > 0) {
bool allMuted = true;
for (const int name : mEnabled) {
const std::shared_ptr<TrackBase> &t = mTracks[name];
if (!t->doesResample() && t->volumeRL == 0) {
t->needs |= NEEDS_MUTE;
t->hook = &TrackBase::track__nop;
} else {
allMuted = false;
}
}
if (allMuted) {
mHook = &AudioMixerBase::process__nop;
} else if (all16BitsStereoNoResample) {
if (mEnabled.size() == 1) {
//const int i = 31 - __builtin_clz(enabledTracks);
const std::shared_ptr<TrackBase> &t = mTracks[mEnabled[0]];
// Muted single tracks handled by allMuted above.
mHook = getProcessHook(PROCESSTYPE_NORESAMPLEONETRACK,
t->mMixerChannelCount, t->mMixerInFormat, t->mMixerFormat,
t->useStereoVolume());
}
}
}
}调用getTrackHook根据tracktype指定混音的hook函数：
cpp
AudioMixerBase::hook_t AudioMixerBase::TrackBase::getTrackHook(int trackType, uint32_t channelCount,
audio_format_t mixerInFormat, audio_format_t mixerOutFormat __unused)
{
if (!kUseNewMixer && channelCount == FCC_2 && mixerInFormat == AUDIO_FORMAT_PCM_16_BIT) {
switch (trackType) {
case TRACKTYPE_NOP:
return &TrackBase::track__nop;
case TRACKTYPE_RESAMPLE:
return &TrackBase::track__genericResample;
case TRACKTYPE_NORESAMPLEMONO:
return &TrackBase::track__16BitsMono;
case TRACKTYPE_NORESAMPLE:
return &TrackBase::track__16BitsStereo;
default:
LOG_ALWAYS_FATAL("bad trackType: %d", trackType);
break;
}
}
LOG_ALWAYS_FATAL_IF(channelCount > MAX_NUM_CHANNELS);
switch (trackType) {
case TRACKTYPE_NOP:
return &TrackBase::track__nop;
case TRACKTYPE_RESAMPLE:
switch (mixerInFormat) {
case AUDIO_FORMAT_PCM_FLOAT:
return (AudioMixerBase::hook_t) &TrackBase::track__Resample<
MIXTYPE_MULTI, float /*TO*/, float /*TI*/, TYPE_AUX>;
case AUDIO_FORMAT_PCM_16_BIT:
return (AudioMixerBase::hook_t) &TrackBase::track__Resample<
MIXTYPE_MULTI, int32_t /*TO*/, int16_t /*TI*/, TYPE_AUX>;
default:
LOG_ALWAYS_FATAL("bad mixerInFormat: %#x", mixerInFormat);
break;
}
break;
case TRACKTYPE_RESAMPLESTEREO:
switch (mixerInFormat) {
case AUDIO_FORMAT_PCM_FLOAT:
return (AudioMixerBase::hook_t) &TrackBase::track__Resample<
MIXTYPE_MULTI_STEREOVOL, float /*TO*/, float /*TI*/,
TYPE_AUX>;
case AUDIO_FORMAT_PCM_16_BIT:
return (AudioMixerBase::hook_t) &TrackBase::track__Resample<
MIXTYPE_MULTI_STEREOVOL, int32_t /*TO*/, int16_t /*TI*/,
TYPE_AUX>;
default:
LOG_ALWAYS_FATAL("bad mixerInFormat: %#x", mixerInFormat);
break;
}
break;
// RESAMPLEMONO needs MIXTYPE_STEREOEXPAND since resampler will upmix mono
// track to stereo track
case TRACKTYPE_RESAMPLEMONO:
switch (mixerInFormat) {
case AUDIO_FORMAT_PCM_FLOAT:
return (AudioMixerBase::hook_t) &TrackBase::track__Resample<
MIXTYPE_STEREOEXPAND, float /*TO*/, float /*TI*/,
TYPE_AUX>;
case AUDIO_FORMAT_PCM_16_BIT:
return (AudioMixerBase::hook_t) &TrackBase::track__Resample<
MIXTYPE_STEREOEXPAND, int32_t /*TO*/, int16_t /*TI*/,
TYPE_AUX>;
default:
LOG_ALWAYS_FATAL("bad mixerInFormat: %#x", mixerInFormat);
break;
}
break;
case TRACKTYPE_NORESAMPLEMONO:
switch (mixerInFormat) {
case AUDIO_FORMAT_PCM_FLOAT:
return (AudioMixerBase::hook_t) &TrackBase::track__NoResample<
MIXTYPE_MONOEXPAND, float /*TO*/, float /*TI*/, TYPE_AUX>;
case AUDIO_FORMAT_PCM_16_BIT:
return (AudioMixerBase::hook_t) &TrackBase::track__NoResample<
MIXTYPE_MONOEXPAND, int32_t /*TO*/, int16_t /*TI*/, TYPE_AUX>;
default:
LOG_ALWAYS_FATAL("bad mixerInFormat: %#x", mixerInFormat);
break;
}
break;
case TRACKTYPE_NORESAMPLE:
switch (mixerInFormat) {
case AUDIO_FORMAT_PCM_FLOAT:
return (AudioMixerBase::hook_t) &TrackBase::track__NoResample<
MIXTYPE_MULTI, float /*TO*/, float /*TI*/, TYPE_AUX>;
case AUDIO_FORMAT_PCM_16_BIT:
return (AudioMixerBase::hook_t) &TrackBase::track__NoResample<
MIXTYPE_MULTI, int32_t /*TO*/, int16_t /*TI*/, TYPE_AUX>;
default:
LOG_ALWAYS_FATAL("bad mixerInFormat: %#x", mixerInFormat);
break;
}
break;
case TRACKTYPE_NORESAMPLESTEREO:
switch (mixerInFormat) {
case AUDIO_FORMAT_PCM_FLOAT:
return (AudioMixerBase::hook_t) &TrackBase::track__NoResample<
MIXTYPE_MULTI_STEREOVOL, float /*TO*/, float /*TI*/,
TYPE_AUX>;
case AUDIO_FORMAT_PCM_16_BIT:
return (AudioMixerBase::hook_t) &TrackBase::track__NoResample<
MIXTYPE_MULTI_STEREOVOL, int32_t /*TO*/, int16_t /*TI*/,
TYPE_AUX>;
default:
LOG_ALWAYS_FATAL("bad mixerInFormat: %#x", mixerInFormat);
break;
}
break;
default:
LOG_ALWAYS_FATAL("bad trackType: %d", trackType);
break;
}
return NULL;
}调用getProcessHook，根据音频格式返回对应的process函数，例如AUDIO_FORMAT_PCM_16_BIT,返回process_noResampleOneTrack
cpp
AudioMixerBase::process_hook_t AudioMixerBase::getProcessHook(
int processType, uint32_t channelCount,
audio_format_t mixerInFormat, audio_format_t mixerOutFormat,
bool stereoVolume)
{
if (processType != PROCESSTYPE_NORESAMPLEONETRACK) { // Only NORESAMPLEONETRACK
LOG_ALWAYS_FATAL("bad processType: %d", processType);
return NULL;
}
if (!kUseNewMixer && channelCount == FCC_2 && mixerInFormat == AUDIO_FORMAT_PCM_16_BIT) {
return &AudioMixerBase::process__oneTrack16BitsStereoNoResampling;
}
LOG_ALWAYS_FATAL_IF(channelCount > MAX_NUM_CHANNELS);
if (stereoVolume) { // templated arguments require explicit values.
switch (mixerInFormat) {
case AUDIO_FORMAT_PCM_FLOAT:
switch (mixerOutFormat) {
case AUDIO_FORMAT_PCM_FLOAT:
return &AudioMixerBase::process__noResampleOneTrack<
MIXTYPE_MULTI_SAVEONLY_STEREOVOL, float /*TO*/,
float /*TI*/, TYPE_AUX>;
case AUDIO_FORMAT_PCM_16_BIT:
return &AudioMixerBase::process__noResampleOneTrack<
MIXTYPE_MULTI_SAVEONLY_STEREOVOL, int16_t /*TO*/,
float /*TI*/, TYPE_AUX>;
default:
LOG_ALWAYS_FATAL("bad mixerOutFormat: %#x", mixerOutFormat);
break;
}
break;
case AUDIO_FORMAT_PCM_16_BIT:
switch (mixerOutFormat) {
case AUDIO_FORMAT_PCM_FLOAT:
return &AudioMixerBase::process__noResampleOneTrack<
MIXTYPE_MULTI_SAVEONLY_STEREOVOL, float /*TO*/,
int16_t /*TI*/, TYPE_AUX>;
case AUDIO_FORMAT_PCM_16_BIT:
return &AudioMixerBase::process__noResampleOneTrack<
MIXTYPE_MULTI_SAVEONLY_STEREOVOL, int16_t /*TO*/,
int16_t /*TI*/, TYPE_AUX>;
default:
LOG_ALWAYS_FATAL("bad mixerOutFormat: %#x", mixerOutFormat);
break;
}
break;
default:
LOG_ALWAYS_FATAL("bad mixerInFormat: %#x", mixerInFormat);
break;
}
} else {
switch (mixerInFormat) {
case AUDIO_FORMAT_PCM_FLOAT:
switch (mixerOutFormat) {
case AUDIO_FORMAT_PCM_FLOAT:
return &AudioMixerBase::process__noResampleOneTrack<
MIXTYPE_MULTI_SAVEONLY, float /*TO*/,
float /*TI*/, TYPE_AUX>;
case AUDIO_FORMAT_PCM_16_BIT:
return &AudioMixerBase::process__noResampleOneTrack<
MIXTYPE_MULTI_SAVEONLY, int16_t /*TO*/,
float /*TI*/, TYPE_AUX>;
default:
LOG_ALWAYS_FATAL("bad mixerOutFormat: %#x", mixerOutFormat);
break;
}
break;
case AUDIO_FORMAT_PCM_16_BIT:
switch (mixerOutFormat) {
case AUDIO_FORMAT_PCM_FLOAT:
return &AudioMixerBase::process__noResampleOneTrack<
MIXTYPE_MULTI_SAVEONLY, float /*TO*/,
int16_t /*TI*/, TYPE_AUX>;
case AUDIO_FORMAT_PCM_16_BIT:
return &AudioMixerBase::process__noResampleOneTrack<
MIXTYPE_MULTI_SAVEONLY, int16_t /*TO*/,
int16_t /*TI*/, TYPE_AUX>;
default:
LOG_ALWAYS_FATAL("bad mixerOutFormat: %#x", mixerOutFormat);
break;
}
break;
default:
LOG_ALWAYS_FATAL("bad mixerInFormat: %#x", mixerInFormat);
break;
}
}
return NULL;
}有两种hook函数，一种是需要重采样的，一种是不需要重采样：
需要重采样：process__genericResampling
cpp
void AudioMixerBase::process__genericResampling()
{
ALOGVV("process__genericResampling\n");
int32_t * const outTemp = mOutputTemp.get(); // naked ptr
size_t numFrames = mFrameCount;
for (const auto &pair : mGroups) {
const auto &group = pair.second;
const std::shared_ptr<TrackBase> &t1 = mTracks[group[0]];
// clear temp buffer
memset(outTemp, 0, sizeof(*outTemp) * t1->mMixerChannelCount * mFrameCount);
for (const int name : group) {
const std::shared_ptr<TrackBase> &t = mTracks[name];
int32_t *aux = NULL;
if (CC_UNLIKELY(t->needs & NEEDS_AUX)) {
aux = t->auxBuffer;
}
// this is a little goofy, on the resampling case we don't
// acquire/release the buffers because it's done by
// the resampler.
if (t->needs & NEEDS_RESAMPLE) {
(t.get()->*t->hook)(outTemp, numFrames, mResampleTemp.get() /* naked ptr */, aux);
} else {
size_t outFrames = 0;
while (outFrames < numFrames) {
t->buffer.frameCount = numFrames - outFrames;
t->bufferProvider->getNextBuffer(&t->buffer);
t->mIn = t->buffer.raw;
// t->mIn == nullptr can happen if the track was flushed just after having
// been enabled for mixing.
if (t->mIn == nullptr) break;
(t.get()->*t->hook)(
outTemp + outFrames * t->mMixerChannelCount, t->buffer.frameCount,
mResampleTemp.get() /* naked ptr */,
aux != nullptr ? aux + outFrames : nullptr);
outFrames += t->buffer.frameCount;
t->bufferProvider->releaseBuffer(&t->buffer);
}
}
}
convertMixerFormat(t1->mainBuffer, t1->mMixerFormat,
outTemp, t1->mMixerInFormat, numFrames * t1->mMixerChannelCount);
}
}该函数中，会遍历所有的Track，如果Track需要重采样则不需要获取额外的buffer，调用track的重采样函数并进行混音。如果不需要重采样了则需要获取buffer，并进行混音后把数据拷贝到输出buffer中，
不需要混音的hook函数：process__genericNoResampling也是类似的，需要获取到buffer，混音后把数据拷贝到输出buffer中。
在设置参数或enable时会调用到invalidate，会重新指定mhook函数，从而刷新track，在调用process__validate会调用一次process()函数，后续都是在threadLoop_mix中调用。
混音以track为源，mainBuffer为目标，frameCount为一次混音长度。AudioMixer最多能维护32个track。track可以对应不同mainBuffer，尽管一般情况下他们的mainBuffer都是同一个。