libavutil/hwcontext_d3d11va: adding more texture information to the D3D11 hwcontext API

Microsoft VideoProcessor requires texture with D3DUSAGE_RENDERTARGET flag as output.
There is no way to allocate array of textures with D3D11_BIND_RENDER_TARGET flag
and .ArraySize > 2 by ID3D11Device_CreateTexture2D due to the Microsoft limitation.
Adding AVD3D11FrameDescriptors array to store array of single textures
instead of texture with multiple slices resolves this.

Signed-off-by: Artem Galin <artem.galin@intel.com>

doc/APIchanges

@@ -14,6 +14,9 @@ libavutil:     2021-04-27
 
 API changes, most recent first:
 
+2021-09-08 - xxxxxxxxxx - lavu 57.5.100 - hwcontext_d3d11va.h
+  Add AVD3D11VAFramesContext.texture_infos
+
 2021-09-06 - xxxxxxxxxx - lsws 6.1.100 - swscale.h
   Add AVFrame-based scaling API:
     - sws_scale_frame()

libavutil/hwcontext_d3d11va.c

@@ -72,6 +72,7 @@ static av_cold void load_functions(void)
 }
 
 typedef struct D3D11VAFramesContext {
+    int nb_surfaces;
     int nb_surfaces_used;
 
     DXGI_FORMAT format;
@@ -112,6 +113,8 @@ static void d3d11va_frames_uninit(AVHWFramesContext *ctx)
     if (s->staging_texture)
         ID3D11Texture2D_Release(s->staging_texture);
     s->staging_texture = NULL;
+
+    av_freep(&frames_hwctx->texture_infos);
 }
 
 static int d3d11va_frames_get_constraints(AVHWDeviceContext *ctx,
@@ -152,15 +155,21 @@ static void free_texture(void *opaque, uint8_t *data)
     av_free(data);
 }
 
-static AVBufferRef *wrap_texture_buf(ID3D11Texture2D *tex, int index)
+static AVBufferRef *wrap_texture_buf(AVHWFramesContext *ctx, ID3D11Texture2D *tex, int index)
 {
     AVBufferRef *buf;
     AVD3D11FrameDescriptor         *desc = av_mallocz(sizeof(*desc));
+    D3D11VAFramesContext              *s = ctx->internal->priv;
+    AVD3D11VAFramesContext *frames_hwctx = ctx->hwctx;
     if (!desc) {
         ID3D11Texture2D_Release(tex);
         return NULL;
     }
 
+    frames_hwctx->texture_infos[s->nb_surfaces_used].texture = tex;
+    frames_hwctx->texture_infos[s->nb_surfaces_used].index = index;
+    s->nb_surfaces_used++;
+
     desc->texture = tex;
     desc->index   = index;
 
@@ -199,7 +208,7 @@ static AVBufferRef *d3d11va_alloc_single(AVHWFramesContext *ctx)
         return NULL;
     }
 
-    return wrap_texture_buf(tex, 0);
+    return wrap_texture_buf(ctx, tex, 0);
 }
 
 static AVBufferRef *d3d11va_pool_alloc(void *opaque, size_t size)
@@ -220,7 +229,7 @@ static AVBufferRef *d3d11va_pool_alloc(void *opaque, size_t size)
     }
 
     ID3D11Texture2D_AddRef(hwctx->texture);
-    return wrap_texture_buf(hwctx->texture, s->nb_surfaces_used++);
+    return wrap_texture_buf(ctx, hwctx->texture, s->nb_surfaces_used);
 }
 
 static int d3d11va_frames_init(AVHWFramesContext *ctx)
@@ -267,7 +276,7 @@ static int d3d11va_frames_init(AVHWFramesContext *ctx)
             av_log(ctx, AV_LOG_ERROR, "User-provided texture has mismatching parameters\n");
             return AVERROR(EINVAL);
         }
-    } else if (texDesc.ArraySize > 0) {
+    } else if (!(texDesc.BindFlags & D3D11_BIND_RENDER_TARGET) && texDesc.ArraySize > 0) {
         hr = ID3D11Device_CreateTexture2D(device_hwctx->device, &texDesc, NULL, &hwctx->texture);
         if (FAILED(hr)) {
             av_log(ctx, AV_LOG_ERROR, "Could not create the texture (%lx)\n", (long)hr);
@@ -275,6 +284,11 @@ static int d3d11va_frames_init(AVHWFramesContext *ctx)
         }
     }
 
+    hwctx->texture_infos = av_mallocz_array(ctx->initial_pool_size, sizeof(*hwctx->texture_infos));
+    if (!hwctx->texture_infos)
+        return AVERROR(ENOMEM);
+    s->nb_surfaces = ctx->initial_pool_size;
+
     ctx->internal->pool_internal = av_buffer_pool_init2(sizeof(AVD3D11FrameDescriptor),
                                                         ctx, d3d11va_pool_alloc, NULL);
     if (!ctx->internal->pool_internal)

libavutil/hwcontext_d3d11va.h

@@ -164,6 +164,15 @@ typedef struct AVD3D11VAFramesContext {
      * This field is ignored/invalid if a user-allocated texture is provided.
      */
     UINT MiscFlags;
+
+    /**
+     * In case if texture structure member above is not NULL contains the same texture
+     * pointer for all elements and different indexes into the array texture.
+     * In case if texture structure member above is NULL, all elements contains
+     * pointers to separate non-array textures and 0 indexes.
+     * This field is ignored/invalid if a user-allocated texture is provided.
+    */
+    AVD3D11FrameDescriptor *texture_infos;
 } AVD3D11VAFramesContext;
 
 #endif /* AVUTIL_HWCONTEXT_D3D11VA_H */

libavutil/hwcontext_qsv.c

@@ -120,6 +120,23 @@ static uint32_t qsv_fourcc_from_pix_fmt(enum AVPixelFormat pix_fmt)
     return 0;
 }
 
+#if CONFIG_D3D11VA
+static uint32_t qsv_get_d3d11va_bind_flags(int mem_type)
+{
+    uint32_t bind_flags = 0;
+
+    if ((mem_type & MFX_MEMTYPE_VIDEO_MEMORY_ENCODER_TARGET) && (mem_type & MFX_MEMTYPE_INTERNAL_FRAME))
+        bind_flags = D3D11_BIND_DECODER | D3D11_BIND_VIDEO_ENCODER;
+    else
+        bind_flags = D3D11_BIND_DECODER;
+
+    if ((MFX_MEMTYPE_FROM_VPPOUT & mem_type) || (MFX_MEMTYPE_VIDEO_MEMORY_PROCESSOR_TARGET & mem_type))
+        bind_flags = D3D11_BIND_RENDER_TARGET;
+
+    return bind_flags;
+}
+#endif
+
 static int qsv_device_init(AVHWDeviceContext *ctx)
 {
     AVQSVDeviceContext *hwctx = ctx->hwctx;
@@ -295,12 +312,11 @@ static int qsv_init_child_ctx(AVHWFramesContext *ctx)
 #if CONFIG_D3D11VA
     if (child_device_ctx->type == AV_HWDEVICE_TYPE_D3D11VA) {
         AVD3D11VAFramesContext *child_frames_hwctx = child_frames_ctx->hwctx;
-        if (hwctx->frame_type & MFX_MEMTYPE_VIDEO_MEMORY_PROCESSOR_TARGET)
+        if (hwctx->frame_type == 0)
-            child_frames_hwctx->BindFlags = D3D11_BIND_RENDER_TARGET;
+            hwctx->frame_type = MFX_MEMTYPE_VIDEO_MEMORY_PROCESSOR_TARGET;
-        else
-            child_frames_hwctx->BindFlags = D3D11_BIND_DECODER;
         if (hwctx->frame_type & MFX_MEMTYPE_SHARED_RESOURCE)
             child_frames_hwctx->MiscFlags = D3D11_RESOURCE_MISC_SHARED;
+        child_frames_hwctx->BindFlags = qsv_get_d3d11va_bind_flags(hwctx->frame_type);
     }
 #endif
 #if CONFIG_DXVA2
@@ -334,11 +350,11 @@ static int qsv_init_child_ctx(AVHWFramesContext *ctx)
     if (child_device_ctx->type == AV_HWDEVICE_TYPE_D3D11VA) {
         AVD3D11VAFramesContext *child_frames_hwctx = child_frames_ctx->hwctx;
         for (i = 0; i < ctx->initial_pool_size; i++) {
-            s->handle_pairs_internal[i].first = (mfxMemId)child_frames_hwctx->texture;
+            s->handle_pairs_internal[i].first = (mfxMemId)child_frames_hwctx->texture_infos[i].texture;
             if(child_frames_hwctx->BindFlags & D3D11_BIND_RENDER_TARGET) {
                 s->handle_pairs_internal[i].second = (mfxMemId)MFX_INFINITE;
             } else {
-                s->handle_pairs_internal[i].second = (mfxMemId)i;
+                s->handle_pairs_internal[i].second = (mfxMemId)child_frames_hwctx->texture_infos[i].index;
             }
             s->surfaces_internal[i].Data.MemId = (mfxMemId)&s->handle_pairs_internal[i];
         }
@@ -714,10 +730,7 @@ static int qsv_frames_derive_from(AVHWFramesContext *dst_ctx,
             dst_hwctx->texture = (ID3D11Texture2D*)pair->first;
             if (src_hwctx->frame_type & MFX_MEMTYPE_SHARED_RESOURCE)
                 dst_hwctx->MiscFlags = D3D11_RESOURCE_MISC_SHARED;
-            if (src_hwctx->frame_type == MFX_MEMTYPE_VIDEO_MEMORY_DECODER_TARGET)
+            dst_hwctx->BindFlags = qsv_get_d3d11va_bind_flags(src_hwctx->frame_type);
-                dst_hwctx->BindFlags = D3D11_BIND_DECODER;
-            else
-                dst_hwctx->BindFlags = D3D11_BIND_RENDER_TARGET;
         }
         break;
 #endif
@@ -1137,11 +1150,11 @@ static int qsv_frames_derive_to(AVHWFramesContext *dst_ctx,
                 return AVERROR(ENOMEM);
             for (i = 0; i < src_ctx->initial_pool_size; i++) {
                 qsv_init_surface(dst_ctx, &s->surfaces_internal[i]);
-                s->handle_pairs_internal[i].first = (mfxMemId)src_hwctx->texture;
+                s->handle_pairs_internal[i].first = (mfxMemId)src_hwctx->texture_infos[i].texture;
                 if (src_hwctx->BindFlags & D3D11_BIND_RENDER_TARGET) {
                     s->handle_pairs_internal[i].second = (mfxMemId)MFX_INFINITE;
                 } else {
-                    s->handle_pairs_internal[i].second = (mfxMemId)i;
+                    s->handle_pairs_internal[i].second = (mfxMemId)src_hwctx->texture_infos[i].index;
                 }
                 s->surfaces_internal[i].Data.MemId = (mfxMemId)&s->handle_pairs_internal[i];
             }

libavutil/version.h

@@ -79,8 +79,8 @@
  */
 
 #define LIBAVUTIL_VERSION_MAJOR  57
-#define LIBAVUTIL_VERSION_MINOR   4
+#define LIBAVUTIL_VERSION_MINOR   5
-#define LIBAVUTIL_VERSION_MICRO 101
+#define LIBAVUTIL_VERSION_MICRO 100
 
 #define LIBAVUTIL_VERSION_INT   AV_VERSION_INT(LIBAVUTIL_VERSION_MAJOR, \
                                                LIBAVUTIL_VERSION_MINOR, \