[FFmpeg-devel,v6] avcodec/mfenc: Dynamically load MFPlat.DLL

From 1f6a42a758e9bd7fca49f22ce96c39b59b059dc2 Mon Sep 17 00:00:00 2001
From: Trystan Mata <trystan.mata@tytanium.xyz>
Date: Wed, 25 May 2022 10:58:08 +0200
Subject: [PATCH] avcodec/mfenc: Dynamically load MediaFoundation library

Allows non-UWP builds of FFmpeg with MediaFoundation to work on
N editions of Windows which are without MediaFoundation by default.

On UWP target, FFmpeg is link directly against MediaFoundation since
LoadLibrary is not available.

This commit adresses https://trac.ffmpeg.org/ticket/9788
---
 configure             |  5 ++-
 libavcodec/mf_utils.c | 59 +++++++-------------------
 libavcodec/mf_utils.h | 35 ++++++++++------
 libavcodec/mfenc.c    | 96 +++++++++++++++++++++++++++++++++++++++----
 4 files changed, 128 insertions(+), 67 deletions(-)

diff --git a/configure b/configure
index f115b21064..432a0d163d 100755
--- a/configure
+++ b/configure
@@ -3130,7 +3130,6 @@  wmv3_vdpau_hwaccel_select="vc1_vdpau_hwaccel"
 
 # hardware-accelerated codecs
 mediafoundation_deps="mftransform_h MFCreateAlignedMemoryBuffer"
-mediafoundation_extralibs="-lmfplat -lmfuuid -lole32 -lstrmiids"
 omx_deps="libdl pthreads"
 omx_rpi_select="omx"
 qsv_deps="libmfx"
@@ -6876,6 +6875,10 @@  test_cpp <<EOF && enable uwp && d3d11va_extralibs="-ldxgi -ld3d11"
 #endif
 EOF
 
+# mediafoundation requires linking directly to mfplat and mfuuid if building
+# for uwp target
+enabled uwp && mediafoundation_extralibs="-lmfplat -lmfuuid -lole32 -lstrmiids" || mediafoundation_extralibs="-lole32 -lstrmiids"
+
 enabled libdrm &&
     check_pkg_config libdrm_getfb2 libdrm "xf86drmMode.h" drmModeGetFB2
 
diff --git a/libavcodec/mf_utils.c b/libavcodec/mf_utils.c
index eeabd0ce0b..48e3a63efc 100644
--- a/libavcodec/mf_utils.c
+++ b/libavcodec/mf_utils.c
@@ -47,39 +47,6 @@  HRESULT ff_MFSetAttributeSize(IMFAttributes *pattr, REFGUID guid,
 #define ff_MFSetAttributeRatio ff_MFSetAttributeSize
 #define ff_MFGetAttributeRatio ff_MFGetAttributeSize
 
-// MFTEnumEx was missing from mingw-w64's mfplat import library until
-// mingw-w64 v6.0.0, thus wrap it and load it using GetProcAddress.
-// It's also missing in Windows Vista's mfplat.dll.
-HRESULT ff_MFTEnumEx(GUID guidCategory, UINT32 Flags,
-                     const MFT_REGISTER_TYPE_INFO *pInputType,
-                     const MFT_REGISTER_TYPE_INFO *pOutputType,
-                     IMFActivate ***pppMFTActivate, UINT32 *pnumMFTActivate)
-{
-    HRESULT (WINAPI *MFTEnumEx_ptr)(GUID guidCategory, UINT32 Flags,
-                                    const MFT_REGISTER_TYPE_INFO *pInputType,
-                                    const MFT_REGISTER_TYPE_INFO *pOutputType,
-                                    IMFActivate ***pppMFTActivate,
-                                    UINT32 *pnumMFTActivate) = NULL;
-#if !HAVE_UWP
-    HANDLE lib = GetModuleHandleW(L"mfplat.dll");
-    if (lib)
-        MFTEnumEx_ptr = (void *)GetProcAddress(lib, "MFTEnumEx");
-#else
-    // In UWP (which lacks GetModuleHandle), just link directly against
-    // the functions - this requires building with new/complete enough
-    // import libraries.
-    MFTEnumEx_ptr = MFTEnumEx;
-#endif
-    if (!MFTEnumEx_ptr)
-        return E_FAIL;
-    return MFTEnumEx_ptr(guidCategory,
-                         Flags,
-                         pInputType,
-                         pOutputType,
-                         pppMFTActivate,
-                         pnumMFTActivate);
-}
-
 char *ff_hr_str_buf(char *buf, size_t size, HRESULT hr)
 {
 #define HR(x) case x: return (char *) # x;
@@ -106,19 +73,20 @@  char *ff_hr_str_buf(char *buf, size_t size, HRESULT hr)
 // If fill_data!=NULL, initialize the buffer and set the length. (This is a
 // subtle but important difference: some decoders want CurrentLength==0 on
 // provided output buffers.)
-IMFSample *ff_create_memory_sample(void *fill_data, size_t size, size_t align)
+IMFSample *ff_create_memory_sample(MFFunctions *f,void *fill_data, size_t size,
+                                   size_t align)
 {
     HRESULT hr;
     IMFSample *sample;
     IMFMediaBuffer *buffer;
 
-    hr = MFCreateSample(&sample);
+    hr = f->MFCreateSample(&sample);
     if (FAILED(hr))
         return NULL;
 
     align = FFMAX(align, 16); // 16 is "recommended", even if not required
 
-    hr = MFCreateAlignedMemoryBuffer(size, align - 1, &buffer);
+    hr = f->MFCreateAlignedMemoryBuffer(size, align - 1, &buffer);
     if (FAILED(hr))
         return NULL;
 
@@ -548,7 +516,7 @@  const CLSID *ff_codec_to_mf_subtype(enum AVCodecID codec)
     }
 }
 
-static int init_com_mf(void *log)
+static int init_com_mf(void *log, MFFunctions *f)
 {
     HRESULT hr;
 
@@ -561,7 +529,7 @@  static int init_com_mf(void *log)
         return AVERROR(ENOSYS);
     }
 
-    hr = MFStartup(MF_VERSION, MFSTARTUP_FULL);
+    hr = f->MFStartup(MF_VERSION, MFSTARTUP_FULL);
     if (FAILED(hr)) {
         av_log(log, AV_LOG_ERROR, "could not initialize MediaFoundation\n");
         CoUninitialize();
@@ -571,15 +539,16 @@  static int init_com_mf(void *log)
     return 0;
 }
 
-static void uninit_com_mf(void)
+static void uninit_com_mf(MFFunctions *f)
 {
-    MFShutdown();
+    f->MFShutdown();
     CoUninitialize();
 }
 
 // Find and create a IMFTransform with the given input/output types. When done,
 // you should use ff_free_mf() to destroy it, which will also uninit COM.
 int ff_instantiate_mf(void *log,
+                      MFFunctions *f,
                       GUID category,
                       MFT_REGISTER_TYPE_INFO *in_type,
                       MFT_REGISTER_TYPE_INFO *out_type,
@@ -594,7 +563,7 @@  int ff_instantiate_mf(void *log,
     IMFActivate *winner = 0;
     UINT32 flags;
 
-    ret = init_com_mf(log);
+    ret = init_com_mf(log, f);
     if (ret < 0)
         return ret;
 
@@ -606,7 +575,7 @@  int ff_instantiate_mf(void *log,
         flags |= MFT_ENUM_FLAG_SYNCMFT;
     }
 
-    hr = ff_MFTEnumEx(category, flags, in_type, out_type, &activate,
+    hr = f->MFTEnumEx(category, flags, in_type, out_type, &activate,
                       &num_activate);
     if (FAILED(hr))
         goto error_uninit_mf;
@@ -667,14 +636,14 @@  int ff_instantiate_mf(void *log,
     return 0;
 
 error_uninit_mf:
-    uninit_com_mf();
+    uninit_com_mf(f);
     return AVERROR(ENOSYS);
 }
 
-void ff_free_mf(IMFTransform **mft)
+void ff_free_mf(MFFunctions *f, IMFTransform **mft)
 {
     if (*mft)
         IMFTransform_Release(*mft);
     *mft = NULL;
-    uninit_com_mf();
+    uninit_com_mf(f);
 }
diff --git a/libavcodec/mf_utils.h b/libavcodec/mf_utils.h
index d514723c3b..3b12344f3e 100644
--- a/libavcodec/mf_utils.h
+++ b/libavcodec/mf_utils.h
@@ -41,6 +41,25 @@ 
 
 #include "avcodec.h"
 
+// Windows N editions does not provide MediaFoundation by default.
+// So to avoid DLL loading error, MediaFoundation will be dynamically loaded
+// except on UWP build since LoadLibrary is not available on it.
+typedef struct MFFunctions {
+    HRESULT (WINAPI *MFStartup) (ULONG Version, DWORD dwFlags);
+    HRESULT (WINAPI *MFShutdown) (void);
+    HRESULT (WINAPI *MFCreateAlignedMemoryBuffer) (DWORD cbMaxLength,
+                                                   DWORD cbAligment,
+                                                   IMFMediaBuffer **ppBuffer);
+    HRESULT (WINAPI *MFCreateSample) (IMFSample **ppIMFSample);
+    HRESULT (WINAPI *MFCreateMediaType) (IMFMediaType **ppMFType);
+    // MFTEnumEx is missing in Windows Vista's mfplat.dll.
+    HRESULT (WINAPI *MFTEnumEx)(GUID guidCategory, UINT32 Flags,
+                                const MFT_REGISTER_TYPE_INFO *pInputType,
+                                const MFT_REGISTER_TYPE_INFO *pOutputType,
+                                IMFActivate ***pppMFTActivate,
+                                UINT32 *pnumMFTActivate);
+} MFFunctions;
+
 // These functions do exist in mfapi.h, but are only available within
 // __cplusplus ifdefs.
 HRESULT ff_MFGetAttributeSize(IMFAttributes *pattr, REFGUID guid,
@@ -50,15 +69,6 @@  HRESULT ff_MFSetAttributeSize(IMFAttributes *pattr, REFGUID guid,
 #define ff_MFSetAttributeRatio ff_MFSetAttributeSize
 #define ff_MFGetAttributeRatio ff_MFGetAttributeSize
 
-// MFTEnumEx was missing from mingw-w64's mfplat import library until
-// mingw-w64 v6.0.0, thus wrap it and load it using GetProcAddress.
-// It's also missing in Windows Vista's mfplat.dll.
-HRESULT ff_MFTEnumEx(GUID guidCategory, UINT32 Flags,
-                     const MFT_REGISTER_TYPE_INFO *pInputType,
-                     const MFT_REGISTER_TYPE_INFO *pOutputType,
-                     IMFActivate ***pppMFTActivate, UINT32 *pnumMFTActivate);
-
-
 // These do exist in mingw-w64's codecapi.h, but they aren't properly defined
 // by the header until after mingw-w64 v7.0.0.
 DEFINE_GUID(ff_CODECAPI_AVDecVideoThumbnailGenerationMode, 0x2efd8eee,0x1150,0x4328,0x9c,0xf5,0x66,0xdc,0xe9,0x33,0xfc,0xf4);
@@ -150,7 +160,8 @@  char *ff_hr_str_buf(char *buf, size_t size, HRESULT hr);
 #define FF_VAL_VT_UI4(v) FF_VARIANT_VALUE(VT_UI4, .ulVal = (v))
 #define FF_VAL_VT_BOOL(v) FF_VARIANT_VALUE(VT_BOOL, .boolVal = (v))
 
-IMFSample *ff_create_memory_sample(void *fill_data, size_t size, size_t align);
+IMFSample *ff_create_memory_sample(MFFunctions *f, void *fill_data,
+                                   size_t size, size_t align);
 enum AVSampleFormat ff_media_type_to_sample_fmt(IMFAttributes *type);
 enum AVPixelFormat ff_media_type_to_pix_fmt(IMFAttributes *type);
 const GUID *ff_pix_fmt_to_guid(enum AVPixelFormat pix_fmt);
@@ -160,10 +171,10 @@  char *ff_guid_str_buf(char *buf, size_t buf_size, const GUID *guid);
 void ff_attributes_dump(void *log, IMFAttributes *attrs);
 void ff_media_type_dump(void *log, IMFMediaType *type);
 const CLSID *ff_codec_to_mf_subtype(enum AVCodecID codec);
-int ff_instantiate_mf(void *log, GUID category,
+int ff_instantiate_mf(void *log, MFFunctions *f, GUID category,
                       MFT_REGISTER_TYPE_INFO *in_type,
                       MFT_REGISTER_TYPE_INFO *out_type,
                       int use_hw, IMFTransform **res);
-void ff_free_mf(IMFTransform **mft);
+void ff_free_mf(MFFunctions *f, IMFTransform **mft);
 
 #endif
diff --git a/libavcodec/mfenc.c b/libavcodec/mfenc.c
index 280941cf2e..6eaea429da 100644
--- a/libavcodec/mfenc.c
+++ b/libavcodec/mfenc.c
@@ -29,9 +29,12 @@ 
 #include "libavutil/time.h"
 #include "codec_internal.h"
 #include "internal.h"
+#include "compat/w32dlfcn.h"
 
 typedef struct MFContext {
     AVClass *av_class;
+    HMODULE library;
+    MFFunctions functions;
     AVFrame *frame;
     int is_video, is_audio;
     GUID main_subtype;
@@ -292,7 +295,8 @@  static IMFSample *mf_a_avframe_to_sample(AVCodecContext *avctx, const AVFrame *f
     bps = av_get_bytes_per_sample(avctx->sample_fmt) * avctx->ch_layout.nb_channels;
     len = frame->nb_samples * bps;
 
-    sample = ff_create_memory_sample(frame->data[0], len, c->in_info.cbAlignment);
+    sample = ff_create_memory_sample(&c->functions, frame->data[0], len,
+                                     c->in_info.cbAlignment);
     if (sample)
         IMFSample_SetSampleDuration(sample, mf_to_mf_time(avctx, frame->nb_samples));
     return sample;
@@ -312,7 +316,8 @@  static IMFSample *mf_v_avframe_to_sample(AVCodecContext *avctx, const AVFrame *f
     if (size < 0)
         return NULL;
 
-    sample = ff_create_memory_sample(NULL, size, c->in_info.cbAlignment);
+    sample = ff_create_memory_sample(&c->functions, NULL, size,
+                                     c->in_info.cbAlignment);
     if (!sample)
         return NULL;
 
@@ -422,7 +427,9 @@  static int mf_receive_sample(AVCodecContext *avctx, IMFSample **out_sample)
         }
 
         if (!c->out_stream_provides_samples) {
-            sample = ff_create_memory_sample(NULL, c->out_info.cbSize, c->out_info.cbAlignment);
+            sample = ff_create_memory_sample(&c->functions, NULL,
+                                             c->out_info.cbSize,
+                                             c->out_info.cbAlignment);
             if (!sample)
                 return AVERROR(ENOMEM);
         }
@@ -777,7 +784,7 @@  static int mf_choose_output_type(AVCodecContext *avctx)
     if (out_type) {
         av_log(avctx, AV_LOG_VERBOSE, "picking output type %d.\n", out_type_index);
     } else {
-        hr = MFCreateMediaType(&out_type);
+        hr = c->functions.MFCreateMediaType(&out_type);
         if (FAILED(hr)) {
             ret = AVERROR(ENOMEM);
             goto done;
@@ -1005,7 +1012,8 @@  err:
     return res;
 }
 
-static int mf_create(void *log, IMFTransform **mft, const AVCodec *codec, int use_hw)
+static int mf_create(void *log, MFFunctions *f, IMFTransform **mft,
+                     const AVCodec *codec, int use_hw)
 {
     int is_audio = codec->type == AVMEDIA_TYPE_AUDIO;
     const CLSID *subtype = ff_codec_to_mf_subtype(codec->id);
@@ -1028,13 +1036,13 @@  static int mf_create(void *log, IMFTransform **mft, const AVCodec *codec, int us
         category = MFT_CATEGORY_VIDEO_ENCODER;
     }
 
-    if ((ret = ff_instantiate_mf(log, category, NULL, &reg, use_hw, mft)) < 0)
+    if ((ret = ff_instantiate_mf(log, f, category, NULL, &reg, use_hw, mft)) < 0)
         return ret;
 
     return 0;
 }
 
-static int mf_init(AVCodecContext *avctx)
+static int mf_init_encoder(AVCodecContext *avctx)
 {
     MFContext *c = avctx->priv_data;
     HRESULT hr;
@@ -1058,7 +1066,7 @@  static int mf_init(AVCodecContext *avctx)
 
     c->main_subtype = *subtype;
 
-    if ((ret = mf_create(avctx, &c->mft, avctx->codec, use_hw)) < 0)
+    if ((ret = mf_create(avctx, &c->functions, &c->mft, avctx->codec, use_hw)) < 0)
         return ret;
 
     if ((ret = mf_unlock_async(avctx)) < 0)
@@ -1122,6 +1130,56 @@  static int mf_init(AVCodecContext *avctx)
     return 0;
 }
 
+#if !HAVE_UWP
+#define LOAD_MF_FUNCTION(context, func_name) \
+    context->functions.func_name = (void *)GetProcAddress(context->library, #func_name ""); \
+    if (!context->functions.func_name) \
+    { \
+        av_log(context, AV_LOG_ERROR, "DLL mfplat.dll failed to find function "\
+           #func_name "\n"); \
+        return AVERROR_UNKNOWN; \
+    }
+#else
+// In UWP (which lacks LoadLibrary), just link directly against
+// the functions - this requires building with new/complete enough
+// import libraries.
+#define LOAD_MF_FUNCTION(context, func_name) \
+    context->functions.func_name = func_name; \
+    if (!context->functions.func_name) \
+    { \
+        av_log(context, AV_LOG_ERROR, "Failed to find function " #func_name \
+               "\n"); \
+        return AVERROR_UNKNOWN; \
+    }
+#endif
+
+// Windows N editions does not provide MediaFoundation by default.
+// So to avoid DLL loading error, MediaFoundation is dynamically loaded except
+// on UWP build since LoadLibrary is not available on it.
+static int mf_load_library(AVCodecContext *avctx)
+{
+    MFContext *c = avctx->priv_data;
+
+#if !HAVE_UWP
+    c->library = dlopen("mfplat.dll", 0);
+
+    if (!c->library) {
+        av_log(c, AV_LOG_ERROR, "DLL mfplat.dll failed to open\n");
+        return AVERROR_UNKNOWN;
+    }
+#endif
+
+    LOAD_MF_FUNCTION(c, MFStartup);
+    LOAD_MF_FUNCTION(c, MFShutdown);
+    LOAD_MF_FUNCTION(c, MFCreateAlignedMemoryBuffer);
+    LOAD_MF_FUNCTION(c, MFCreateSample);
+    LOAD_MF_FUNCTION(c, MFCreateMediaType);
+    // MFTEnumEx is missing in Windows Vista's mfplat.dll.
+    LOAD_MF_FUNCTION(c, MFTEnumEx);
+
+    return 0;
+}
+
 static int mf_close(AVCodecContext *avctx)
 {
     MFContext *c = avctx->priv_data;
@@ -1132,7 +1190,15 @@  static int mf_close(AVCodecContext *avctx)
     if (c->async_events)
         IMFMediaEventGenerator_Release(c->async_events);
 
-    ff_free_mf(&c->mft);
+#if !HAVE_UWP
+    if (c->library)
+        ff_free_mf(&c->functions, &c->mft);
+
+    dlclose(c->library);
+    c->library = NULL;
+#else
+    ff_free_mf(&c->functions, &c->mft);
+#endif
 
     av_frame_free(&c->frame);
 
@@ -1142,6 +1208,18 @@  static int mf_close(AVCodecContext *avctx)
     return 0;
 }
 
+static int mf_init(AVCodecContext *avctx)
+{
+    int ret;
+    if ((ret = mf_load_library(avctx)) == 0) {
+           if ((ret = mf_init_encoder(avctx)) == 0) {
+                return 0;
+        }
+    }
+    mf_close(avctx);
+    return ret;
+}
+
 #define OFFSET(x) offsetof(MFContext, x)
 
 #define MF_ENCODER(MEDIATYPE, NAME, ID, OPTS, EXTRA) \
-- 
2.36.1