[PATCH v2 1/1] winegstreamer: Optimise copy to DXGI buffer.

[Brendan McGrath]

From: Brendan McGrath

Using IMF2DBuffer2_Lock2DSize with LockFlags_Write dramatically improves
performance over IMFMediaBuffer_Lock when using a DXGI buffer.

IMFMediaBuffer_Lock does not know that this buffer will not be read and
therefore performs an unnecessary transfer of the texture from GPU to CPU
before it is overwritten.
---
 dlls/winegstreamer/gst_private.h |  2 +-
 dlls/winegstreamer/media_sink.c  |  2 +-
 dlls/winegstreamer/wg_sample.c   | 31 +++++++++++++++++++++++++------
 3 files changed, 27 insertions(+), 8 deletions(-)

diff --git a/dlls/winegstreamer/gst_private.h b/dlls/winegstreamer/gst_private.h
index 0f7d945ba37..0fa1aa0dac5 100644
--- a/dlls/winegstreamer/gst_private.h
+++ b/dlls/winegstreamer/gst_private.h
@@ -156,7 +156,7 @@ extern HRESULT mfplat_DllRegisterServer(void);
 IMFMediaType *mf_media_type_from_wg_format(const struct wg_format *format);
 void mf_media_type_to_wg_format(IMFMediaType *type, struct wg_format *format);

-HRESULT wg_sample_create_mf(IMFSample *sample, struct wg_sample **out);
+HRESULT wg_sample_create_mf(IMFSample *sample, struct wg_sample **out, MF2DBuffer_LockFlags lockFlags);
 HRESULT wg_sample_create_quartz(IMediaSample *sample, struct wg_sample **out);
 HRESULT wg_sample_create_dmo(IMediaBuffer *media_buffer, struct wg_sample **out);
 void wg_sample_release(struct wg_sample *wg_sample);
diff --git a/dlls/winegstreamer/media_sink.c b/dlls/winegstreamer/media_sink.c
index 5ee2c44dc70..9eb64756ec6 100644
--- a/dlls/winegstreamer/media_sink.c
+++ b/dlls/winegstreamer/media_sink.c
@@ -615,7 +615,7 @@ static HRESULT media_sink_process(struct media_sink *media_sink, IMFSample *samp
     if (FAILED(hr = media_sink_write_stream(media_sink)))
         WARN("Failed to write output samples to stream, hr %#lx.\n", hr);

-    if (FAILED(hr = wg_sample_create_mf(sample, &wg_sample)))
+    if (FAILED(hr = wg_sample_create_mf(sample, &wg_sample, MF2DBuffer_LockFlags_Read)))
         return hr;

if (SUCCEEDED(IMFSample_GetSampleTime(sample, &time)))
diff --git a/dlls/winegstreamer/wg_sample.c b/dlls/winegstreamer/wg_sample.c
index 116dbb1f3ec..03dc7c9de5b 100644
--- a/dlls/winegstreamer/wg_sample.c
+++ b/dlls/winegstreamer/wg_sample.c
@@ -52,6 +52,7 @@ struct sample
         {
             IMFSample *sample;
             IMFMediaBuffer *buffer;
+            IMF2DBuffer2 *buffer2d2;
         } mf;
         struct
         {
@@ -79,7 +80,15 @@ static void mf_sample_destroy(struct wg_sample *wg_sample)

TRACE_(mfplat)("wg_sample %p.\n", wg_sample);

-    IMFMediaBuffer_Unlock(sample->u.mf.buffer);
+    if (sample->u.mf.buffer2d2)
+    {
+        IMF2DBuffer2_Unlock2D(sample->u.mf.buffer2d2);
+        IMF2DBuffer2_Release(sample->u.mf.buffer2d2);
+    }
+    else
+    {
+        IMFMediaBuffer_Unlock(sample->u.mf.buffer);
+    }
     IMFMediaBuffer_Release(sample->u.mf.buffer);
     IMFSample_Release(sample->u.mf.sample);
 }
@@ -89,18 +98,28 @@ static const struct wg_sample_ops mf_sample_ops =
     mf_sample_destroy,
 };

-HRESULT wg_sample_create_mf(IMFSample *mf_sample, struct wg_sample **out)
+HRESULT wg_sample_create_mf(IMFSample *mf_sample, struct wg_sample **out, MF2DBuffer_LockFlags lockFlags)
 {
     DWORD current_length, max_length;
+    LONG pitch;
     struct sample *sample;
-    BYTE *buffer;
+    BYTE *buffer, *scanline;
     HRESULT hr;

if (!(sample = calloc(1, sizeof(*sample))))
         return E_OUTOFMEMORY;
     if (FAILED(hr = IMFSample_ConvertToContiguousBuffer(mf_sample, &sample->u.mf.buffer)))
         goto fail;
-    if (FAILED(hr = IMFMediaBuffer_Lock(sample->u.mf.buffer, &buffer, &max_length, &current_length)))
+    if (SUCCEEDED(hr = IMFMediaBuffer_QueryInterface(sample->u.mf.buffer, &IID_IMF2DBuffer2, (void**)&sample->u.mf.buffer2d2)) &&
+            FAILED(hr = IMF2DBuffer2_Lock2DSize(sample->u.mf.buffer2d2, lockFlags, &scanline, &pitch, &buffer, &max_length)))
+    {
+        IMF2DBuffer2_Release(sample->u.mf.buffer2d2);
+        sample->u.mf.buffer2d2 = NULL;
+    }
+
+    if (SUCCEEDED(hr))
+        current_length = max_length;
+    else if (FAILED(hr = IMFMediaBuffer_Lock(sample->u.mf.buffer, &buffer, &max_length, &current_length)))
         goto fail;

IMFSample_AddRef((sample->u.mf.sample = mf_sample));
@@ -313,7 +332,7 @@ HRESULT wg_transform_push_mf(wg_transform_t transform, IMFSample *sample,

TRACE_(mfplat)("transform %#I64x, sample %p, queue %p.\n", transform, sample, queue);

-    if (FAILED(hr = wg_sample_create_mf(sample, &wg_sample)))
+    if (FAILED(hr = wg_sample_create_mf(sample, &wg_sample, MF2DBuffer_LockFlags_Read)))
         return hr;

if (SUCCEEDED(IMFSample_GetSampleTime(sample, &time)))
@@ -347,7 +366,7 @@ HRESULT wg_transform_read_mf(wg_transform_t transform, IMFSample *sample,

TRACE_(mfplat)("transform %#I64x, sample %p, flags %p.\n", transform, sample, flags);

-    if (FAILED(hr = wg_sample_create_mf(sample, &wg_sample)))
+    if (FAILED(hr = wg_sample_create_mf(sample, &wg_sample, MF2DBuffer_LockFlags_Write)))
         return hr;

wg_sample->size = 0;