在DirectShow中支持DXVA 2.0（Supporting DXVA 2.0 in DirectShow），dxvasupporting

在DirectShow中支持DXVA 2.0（Supporting DXVA 2.0 in DirectShow），dxvasupporting

　　這幾天在做dxva2硬件加速，找不到什麼資料，翻譯了一下微軟的兩篇相關文檔。並准備記錄一下用ffmpeg實現dxva2，將在第三篇寫到。這是第二篇。，英文原址：https://msdn.microsoft.com/en-us/library/aa965245(v=vs.85).aspx 
第一篇翻譯的Direct3D device manager，鏈接：http://www.cnblogs.com/betterwgo/p/6124588.html

　　本主題描述如何在DirectShow的解碼器中支持DirectX Video Acceleration (DXVA) 2.0。具體而言，是描述解碼器與視頻渲染器之間的聯通（communication ）。本主題不描述如何實現DXVA解碼。

1.准備(Prerequisites)

   本主題假定你熟悉如何寫DirectShow過濾器。更多信息請參考DirectShow SDK文檔的Writing DirectShow Filters主題（https://msdn.microsoft.com/en-us/library/dd391013(v=vs.85).aspx ）。代碼簡例假定解碼器繼承自CTransformFilter類，定義如下：

class CDecoder : public CTransformFilter
{
public:
    static CUnknown* WINAPI CreateInstance(IUnknown *pUnk, HRESULT *pHr);

    HRESULT CompleteConnect(PIN_DIRECTION direction, IPin *pPin);

    HRESULT InitAllocator(IMemAllocator **ppAlloc);
    HRESULT DecideBufferSize(IMemAllocator *pAlloc, ALLOCATOR_PROPERTIES *pProp);

    // TODO: The implementations of these methods depend on the specific decoder.
    HRESULT CheckInputType(const CMediaType *mtIn);
    HRESULT CheckTransform(const CMediaType *mtIn, const CMediaType *mtOut);
    HRESULT CTransformFilter::GetMediaType(int,CMediaType *);

private:
    CDecoder(HRESULT *pHr);
    ~CDecoder();

    CBasePin * GetPin(int n);

    HRESULT ConfigureDXVA2(IPin *pPin);
    HRESULT SetEVRForDXVA2(IPin *pPin);

    HRESULT FindDecoderConfiguration(
        /* [in] */  IDirectXVideoDecoderService *pDecoderService,
        /* [in] */  const GUID& guidDecoder, 
        /* [out] */ DXVA2_ConfigPictureDecode *pSelectedConfig,
        /* [out] */ BOOL *pbFoundDXVA2Configuration
        );

private:
    IDirectXVideoDecoderService *m_pDecoderService;

    DXVA2_ConfigPictureDecode m_DecoderConfig;
    GUID                      m_DecoderGuid;
    HANDLE                    m_hDevice;

    FOURCC                    m_fccOutputFormat;
};

本主題中，解碼器是指decoder filter，包括接收壓縮視頻數據到輸出解壓縮的視頻數據的過程。解碼設備指圖形驅動所實現的硬件視頻加速器。

一個解碼器要支持DXVA 2.0必須有以下基本步驟：

（1）確定一個文件類型（個人理解：應該是指根據獲取到的原文件類型，找到DXVA2對應的文件類型。比如ffmpeg獲取到了文件類型，要知道這個文件類型在DXVA2中對應的是什麼文件類型）

（2）找到對應的DXVA解碼器配置

（3）告知視頻渲染設備解碼器用的是DXVA

（4）提供一個客戶分配器來分配Direct3D surfaces.

原文：

HRESULT CDecoder::ConfigureDXVA2(IPin *pPin) { UINT cDecoderGuids = 0; BOOL bFoundDXVA2Configuration = FALSE; GUID guidDecoder = GUID_NULL; DXVA2_ConfigPictureDecode config; ZeroMemory(&config, sizeof(config)); // Variables that follow must be cleaned up at the end. IMFGetService *pGetService = NULL; IDirect3DDeviceManager9 *pDeviceManager = NULL; IDirectXVideoDecoderService *pDecoderService = NULL; GUID *pDecoderGuids = NULL; // size = cDecoderGuids HANDLE hDevice = INVALID_HANDLE_VALUE; // Query the pin for IMFGetService. HRESULT hr = pPin->QueryInterface(IID_PPV_ARGS(&pGetService)); // Get the Direct3D device manager. if (SUCCEEDED(hr)) { hr = pGetService->GetService( MR_VIDEO_ACCELERATION_SERVICE, IID_PPV_ARGS(&pDeviceManager) ); } // Open a new device handle. if (SUCCEEDED(hr)) { hr = pDeviceManager->OpenDeviceHandle(&hDevice); } // Get the video decoder service. if (SUCCEEDED(hr)) { hr = pDeviceManager->GetVideoService( hDevice, IID_PPV_ARGS(&pDecoderService)); } // Get the decoder GUIDs. if (SUCCEEDED(hr)) { hr = pDecoderService->GetDecoderDeviceGuids( &cDecoderGuids, &pDecoderGuids); } if (SUCCEEDED(hr)) { // Look for the decoder GUIDs we want. for (UINT iGuid = 0; iGuid < cDecoderGuids; iGuid++) { // Do we support this mode? if (!IsSupportedDecoderMode(pDecoderGuids[iGuid])) { continue; } // Find a configuration that we support. hr = FindDecoderConfiguration(pDecoderService, pDecoderGuids[iGuid], &config, &bFoundDXVA2Configuration); if (FAILED(hr)) { break; } if (bFoundDXVA2Configuration) { // Found a good configuration. Save the GUID and exit the loop. guidDecoder = pDecoderGuids[iGuid]; break; } } } if (!bFoundDXVA2Configuration) { hr = E_FAIL; // Unable to find a configuration. } if (SUCCEEDED(hr)) { // Store the things we will need later. SafeRelease(&m_pDecoderService); m_pDecoderService = pDecoderService; m_pDecoderService->AddRef(); m_DecoderConfig = config; m_DecoderGuid = guidDecoder; m_hDevice = hDevice; } if (FAILED(hr)) { if (hDevice != INVALID_HANDLE_VALUE) { pDeviceManager->CloseDeviceHandle(hDevice); } } SafeRelease(&pGetService); SafeRelease(&pDeviceManager); SafeRelease(&pDecoderService); return hr; } HRESULT CDecoder::FindDecoderConfiguration( /* [in] */ IDirectXVideoDecoderService *pDecoderService, /* [in] */ const GUID& guidDecoder, /* [out] */ DXVA2_ConfigPictureDecode *pSelectedConfig, /* [out] */ BOOL *pbFoundDXVA2Configuration ) { HRESULT hr = S_OK; UINT cFormats = 0; UINT cConfigurations = 0; D3DFORMAT *pFormats = NULL; // size = cFormats DXVA2_ConfigPictureDecode *pConfig = NULL; // size = cConfigurations // Find the valid render target formats for this decoder GUID. hr = pDecoderService->GetDecoderRenderTargets( guidDecoder, &cFormats, &pFormats ); if (SUCCEEDED(hr)) { // Look for a format that matches our output format. for (UINT iFormat = 0; iFormat < cFormats; iFormat++) { if (pFormats[iFormat] != (D3DFORMAT)m_fccOutputFormat) { continue; } // Fill in the video description. Set the width, height, format, // and frame rate. DXVA2_VideoDesc videoDesc = {0}; FillInVideoDescription(&videoDesc); // Private helper function. videoDesc.Format = pFormats[iFormat]; // Get the available configurations. hr = pDecoderService->GetDecoderConfigurations( guidDecoder, &videoDesc, NULL, // Reserved. &cConfigurations, &pConfig ); if (FAILED(hr)) { break; } // Find a supported configuration. for (UINT iConfig = 0; iConfig < cConfigurations; iConfig++) { if (IsSupportedDecoderConfig(pConfig[iConfig])) { // This configuration is good. *pbFoundDXVA2Configuration = TRUE; *pSelectedConfig = pConfig[iConfig]; break; } } CoTaskMemFree(pConfig); break; } // End of formats loop. } CoTaskMemFree(pFormats); // Note: It is possible to return S_OK without finding a configuration. return hr; }

由於這是個通用的例子，所以有些邏輯就放置在了輔助函數裡面，需要由解碼器來實現。以下是所用到的輔助函數：

// Returns TRUE if the decoder supports a given decoding mode.
BOOL IsSupportedDecoderMode(const GUID& mode);

// Returns TRUE if the decoder supports a given decoding configuration.
BOOL IsSupportedDecoderConfig(const DXVA2_ConfigPictureDecode& config);

// Fills in a DXVA2_VideoDesc structure based on the input format.
void FillInVideoDescription(DXVA2_VideoDesc *pDesc);

4.通知視頻渲染器（Notifying the Video Renderer）

如果解碼器找到了解碼配置，下一步就是通知視頻渲染器將要使用硬件加速來解碼。你可以在CompleteConnect方法中完成這個步驟。這一步必須在選擇分配器之前做，因為它會影響分配器如何選擇。

1）為IMFGetService接口查詢渲染器的輸入Pin（原文：Query the renderer's input pin for the IMFGetService interface.）

2）調用IMFGetService::GetService獲取指向IDirectXVideoMemoryConfiguration接口的指針。該服務的GUID是MR_VIDEO_ACCELERATION_SERVICE。

3）循環調用IDirectXVideoMemoryConfiguration::GetAvailableSurfaceTypeByIndex，從0增長dwTypeIndex 變量。當該方法在pdwType 參數返回DXVA2_SurfaceType_DecoderRenderTarget 時停止循環。這一步確保視頻渲染器支持硬件加速轉碼。對於EVR過濾器而言這一步總是成功的。

4）如果上一步成功，用DXVA2_SurfaceType_DecoderRenderTarget參數調用IDirectXVideoMemoryConfiguration::SetSurfaceType。用這個參數調用SetSurfaceType將視頻渲染器置於DXVA模式。當視頻渲染器處於這種模式時，解碼器必須提供它自己的分配器。

以下代碼展示如何通知視頻渲染器：

HRESULT CDecoder::SetEVRForDXVA2(IPin *pPin)
{
    HRESULT hr = S_OK;

    IMFGetService                       *pGetService = NULL;
    IDirectXVideoMemoryConfiguration    *pVideoConfig = NULL;

    // Query the pin for IMFGetService.
    hr = pPin->QueryInterface(__uuidof(IMFGetService), (void**)&pGetService);

    // Get the IDirectXVideoMemoryConfiguration interface.
    if (SUCCEEDED(hr))
    {
        hr = pGetService->GetService(
            MR_VIDEO_ACCELERATION_SERVICE, IID_PPV_ARGS(&pVideoConfig));
    }

    // Notify the EVR. 
    if (SUCCEEDED(hr))
    {
        DXVA2_SurfaceType surfaceType;

        for (DWORD iTypeIndex = 0; ; iTypeIndex++)
        {
            hr = pVideoConfig->GetAvailableSurfaceTypeByIndex(iTypeIndex, &surfaceType);
            
            if (FAILED(hr))
            {
                break;
            }

            if (surfaceType == DXVA2_SurfaceType_DecoderRenderTarget)
            {
                hr = pVideoConfig->SetSurfaceType(DXVA2_SurfaceType_DecoderRenderTarget);
                break;
            }
        }
    }

    SafeRelease(&pGetService);
    SafeRelease(&pVideoConfig);

    return hr;
}

如果解碼器找到了有效的配置並成功通知了視頻渲染器，解碼器就可以用DXVA來解碼了。解碼器必須給輸出Pin實現客戶分配器（原為：a custom allocator）,如下面一部分描述的。

5.分配解碼數據緩存（Allocating Uncompressed Buffers）

    在DXVA 2.0中，解碼器負責分配作為解壓縮視頻數據緩存的Direct3D surfaces。因此，解碼器必須實現一個創建surfaces的custom allocator（不知道怎麼翻譯，不翻譯了，意思大概是由用戶來實現的分配器）。這個分配器提供的media samples會有一個指向Direct3D surfaces的指針。EVR通過調用這個media sample的IMFGetService::GetService取回這個指向surface的指針。這個服務的標識符是MR_BUFFER_SERVICE。

要實現custom allocator，需執行以下步驟：

1）給media samples定義一個類。這個類繼承自CMediaSample。在這個類中，做以下：

    a)保存一個指向the Direct3D surface的指針；b)實現IMFGetService接口。在GetService方法中，如果service GUID i是MR_BUFFER_SERVICE，query the Direct3D surface for the requested interface。否則，GetService 會返回MF_E_UNSUPPORTED_SERVICE。c)重寫CMediaSample::GetPointer 方法來返回 E_NOTIMPL.

2）給the allocator定義一個類。the allocator可以繼承自CBaseAllocator類。在這個類中，做以下：

    a)重寫CBaseAllocator::Alloc方法。在這個方法中，調用IDirectXVideoAccelerationService::CreateSurface創建surface。（ IDirectXVideoDecoderService 接口從IDirectXVideoAccelerationService繼承這個方法）。b)重寫CBaseAllocator::Free方法釋放surface。

3）在你的過濾器的輸出Pin中，重寫CBaseOutputPin::InitAllocator方法。在這個方法中，創建一個你實現的custom allocator的實例。

4）在你的filter中，實現CTransformFilter::DecideBufferSize方法。pProperties 參數表明EVR所需的surface的數量。把這個值增加的解碼器所需的大小，並在allocator中調用IMemAllocator::SetProperties。

以下代碼展示如何實現media sample類：

class CDecoderSample : public CMediaSample, public IMFGetService
{
    friend class CDecoderAllocator;

public:

    CDecoderSample(CDecoderAllocator *pAlloc, HRESULT *phr)
        : CMediaSample(NAME("DecoderSample"), (CBaseAllocator*)pAlloc, phr, NULL, 0),
          m_pSurface(NULL),
          m_dwSurfaceId(0)
    { 
    }

    // Note: CMediaSample does not derive from CUnknown, so we cannot use the
    //       DECLARE_IUNKNOWN macro that is used by most of the filter classes.

    STDMETHODIMP QueryInterface(REFIID riid, void **ppv)
    {
        CheckPointer(ppv, E_POINTER);

        if (riid == IID_IMFGetService)
        {
            *ppv = static_cast<IMFGetService*>(this);
            AddRef();
            return S_OK;
        }
        else
        {
            return CMediaSample::QueryInterface(riid, ppv);
        }
    }
    STDMETHODIMP_(ULONG) AddRef()
    {
        return CMediaSample::AddRef();
    }

    STDMETHODIMP_(ULONG) Release()
    {
        // Return a temporary variable for thread safety.
        ULONG cRef = CMediaSample::Release();
        return cRef;
    }

    // IMFGetService::GetService
    STDMETHODIMP GetService(REFGUID guidService, REFIID riid, LPVOID *ppv)
    {
        if (guidService != MR_BUFFER_SERVICE)
        {
            return MF_E_UNSUPPORTED_SERVICE;
        }
        else if (m_pSurface == NULL)
        {
            return E_NOINTERFACE;
        }
        else
        {
            return m_pSurface->QueryInterface(riid, ppv);
        }
    }

    // Override GetPointer because this class does not manage a system memory buffer.
    // The EVR uses the MR_BUFFER_SERVICE service to get the Direct3D surface.
    STDMETHODIMP GetPointer(BYTE ** ppBuffer)
    {
        return E_NOTIMPL;
    }

private:

    // Sets the pointer to the Direct3D surface. 
    void SetSurface(DWORD surfaceId, IDirect3DSurface9 *pSurf)
    {
        SafeRelease(&m_pSurface);

        m_pSurface = pSurf;
        if (m_pSurface)
        {
            m_pSurface->AddRef();
        }

        m_dwSurfaceId = surfaceId;
    }

    IDirect3DSurface9   *m_pSurface;
    DWORD               m_dwSurfaceId;
};

以下代碼展示如何在allocator中實現Alloc方法

HRESULT CDecoderAllocator::Alloc()
{
    CAutoLock lock(this);

    HRESULT hr = S_OK;

    if (m_pDXVA2Service == NULL)
    {
        return E_UNEXPECTED;
    }

    hr = CBaseAllocator::Alloc();

    // If the requirements have not changed, do not reallocate.
    if (hr == S_FALSE)
    {
        return S_OK;
    }

    if (SUCCEEDED(hr))
    {
        // Free the old resources.
        Free();

        // Allocate a new array of pointers.
        m_ppRTSurfaceArray = new (std::nothrow) IDirect3DSurface9*[m_lCount];
        if (m_ppRTSurfaceArray == NULL)
        {
            hr = E_OUTOFMEMORY;
        }
        else
        {
            ZeroMemory(m_ppRTSurfaceArray, sizeof(IDirect3DSurface9*) * m_lCount);
        }
    }

    // Allocate the surfaces.
    if (SUCCEEDED(hr))
    {
        hr = m_pDXVA2Service->CreateSurface(
            m_dwWidth,
            m_dwHeight,
            m_lCount - 1,
            (D3DFORMAT)m_dwFormat,
            D3DPOOL_DEFAULT,
            0,
            DXVA2_VideoDecoderRenderTarget,
            m_ppRTSurfaceArray,
            NULL
            );
    }

    if (SUCCEEDED(hr))
    {
        for (m_lAllocated = 0; m_lAllocated < m_lCount; m_lAllocated++)
        {
            CDecoderSample *pSample = new (std::nothrow) CDecoderSample(this, &hr);

            if (pSample == NULL)
            {
                hr = E_OUTOFMEMORY;
                break;
            }
            if (FAILED(hr))
            {
                break;
            }
            // Assign the Direct3D surface pointer and the index.
            pSample->SetSurface(m_lAllocated, m_ppRTSurfaceArray[m_lAllocated]);

            // Add to the sample list.
            m_lFree.Add(pSample);
        }
    }

    if (SUCCEEDED(hr))
    {
        m_bChanged = FALSE;
    }
    return hr;
}

以下代碼是Free方法：

void CDecoderAllocator::Free()
{
    CMediaSample *pSample = NULL;

    do
    {
        pSample = m_lFree.RemoveHead();
        if (pSample)
        {
            delete pSample;
        }
    } while (pSample);

    if (m_ppRTSurfaceArray)
    {
        for (long i = 0; i < m_lAllocated; i++)
        {
            SafeRelease(&m_ppRTSurfaceArray[i]);
        }

        delete [] m_ppRTSurfaceArray;
    }
    m_lAllocated = 0;
}

6.解碼（Decoding）

    調用IDirectXVideoDecoderService::CreateVideoDecoder方法創建解碼器設備，該方法返回一個指向解碼器設備IDirectXVideoDecoder接口的指針。

    對每一幀，調用IDirect3DDeviceManager9::TestDevice來測試設備句柄。如果設備改變了，方法將返回DXVA2_E_NEW_VIDEO_DEVICE。如果這種情況發生，做以下：

1)調用IDirect3DDeviceManager9::CloseDeviceHandle關閉設備句柄

2)釋放IDirectXVideoDecoderService 和IDirectXVideoDecoder 指針

3)打開一個新的設備句柄

4)確定一個新的解碼器配置，如3所述。

5)創建一個新的解碼器設備。

假定設備句柄有效，解碼進程以如下步驟工作：

1)調用IDirectXVideoDecoder::BeginFrame

2)做以下，一次或多次：

    a)調用IDirectXVideoDecoder::GetBuffer獲取一個DXVA解碼器緩存

    b)填充緩存

    c)調用IDirectXVideoDecoder::ReleaseBuffer

3）調用IDirectXVideoDecoder::Execute對該幀執行解碼操作

   DXVA 2.0解碼操作所用數據結構與DXVA 1.0相同。

    在每一對BeginFrame/Execute的調用之間，你可能要多次調用GetBuffer，但每種DXVA緩存類型只能一次。如果你對同一種緩存類型調用兩次，數據將會覆蓋。

    調用Execute之後，調用IMemInputPin::Receive把該幀傳給視頻渲染器，這與軟解一樣。Receive方法是異步的，它返回之後，解碼器可以繼續解碼下一幀。顯示驅動器（display driver）阻止任何解碼命令在緩存使用期間覆寫緩存。解碼器不應該在渲染器釋放sample之前重用surface來解碼另一幀數據。當渲染器釋放sample之後，分配器把sample放回可用sample池中。要獲取下一個可用sample，調用CBaseOutputPin::GetDeliveryBuffer，它轉而調用IMemAllocator::GetBuffer（原文：which in turn calls IMemAllocator::GetBuffer）。