vulkan_av1: add workaround for NVIDIA drivers tested on broken CTS

The first release of the CTS for AV1 decoding had incorrect
offsets for the OrderHints values.
The CTS will be fixed, and eventually, the drivers will be
updated to the proper spec-conforming behaviour, but we still
need to add a workaround as this will take months.

Only NVIDIA use these values at all, so limit the workaround
to only NVIDIA. Also, other vendors don't tend to provide accurate
CTS information.

libavcodec/vulkan_av1.c

@@ -97,9 +97,14 @@ static int vk_av1_fill_pict(AVCodecContext *avctx, const AV1Frame **ref_src,
         .RefFrameSignBias = hp->ref_frame_sign_bias_mask,
     };
 
-    if (saved_order_hints)
-        for (int i = 0; i < AV1_TOTAL_REFS_PER_FRAME; i++)
-            vkav1_std_ref->SavedOrderHints[i] = saved_order_hints[i];
+    if (saved_order_hints) {
+        if (dec->quirk_av1_offset)
+            for (int i = 1; i < STD_VIDEO_AV1_TOTAL_REFS_PER_FRAME; i++)
+                vkav1_std_ref->SavedOrderHints[i - 1] = saved_order_hints[i];
+        else
+            for (int i = 0; i < STD_VIDEO_AV1_TOTAL_REFS_PER_FRAME; i++)
+                vkav1_std_ref->SavedOrderHints[i] = saved_order_hints[i];
+    }
 
     *vkav1_ref = (VkVideoDecodeAV1DpbSlotInfoKHR) {
         .sType = VK_STRUCTURE_TYPE_VIDEO_DECODE_AV1_DPB_SLOT_INFO_KHR,
@@ -490,8 +495,14 @@ static int vk_av1_start_frame(AVCodecContext          *avctx,
         }
     }
 
+    if (dec->quirk_av1_offset)
+        for (int i = 1; i < STD_VIDEO_AV1_TOTAL_REFS_PER_FRAME; i++)
+            ap->std_pic_info.OrderHints[i - 1] = pic->order_hints[i];
+    else
+        for (int i = 0; i < STD_VIDEO_AV1_TOTAL_REFS_PER_FRAME; i++)
+            ap->std_pic_info.OrderHints[i] = pic->order_hints[i];
+
     for (int i = 0; i < STD_VIDEO_AV1_TOTAL_REFS_PER_FRAME; i++) {
-        ap->std_pic_info.OrderHints[i] = pic->order_hints[i];
         ap->loop_filter.loop_filter_ref_deltas[i] = frame_header->loop_filter_ref_deltas[i];
         ap->global_motion.GmType[i] = s->cur_frame.gm_type[i];
         for (int j = 0; j < STD_VIDEO_AV1_GLOBAL_MOTION_PARAMS; j++) {

libavcodec/vulkan_decode.c

@@ -1115,6 +1115,7 @@ int ff_vk_decode_init(AVCodecContext *avctx)
     FFVulkanFunctions *vk;
     const VkVideoProfileInfoKHR *profile;
     const FFVulkanDecodeDescriptor *vk_desc;
+    const VkPhysicalDeviceDriverProperties *driver_props;
 
     VkVideoDecodeH264SessionParametersCreateInfoKHR h264_params = {
         .sType = VK_STRUCTURE_TYPE_VIDEO_DECODE_H264_SESSION_PARAMETERS_CREATE_INFO_KHR,
@@ -1276,6 +1277,14 @@ int ff_vk_decode_init(AVCodecContext *avctx)
         return AVERROR_EXTERNAL;
     }
 
+    driver_props = &dec->shared_ctx->s.driver_props;
+    if (driver_props->driverID == VK_DRIVER_ID_NVIDIA_PROPRIETARY &&
+        driver_props->conformanceVersion.major == 1 &&
+        driver_props->conformanceVersion.minor == 3 &&
+        driver_props->conformanceVersion.subminor == 8 &&
+        driver_props->conformanceVersion.patch < 3)
+        dec->quirk_av1_offset = 1;
+
     ff_vk_decode_flush(avctx);
 
     av_log(avctx, AV_LOG_VERBOSE, "Vulkan decoder initialization sucessful\n");

libavcodec/vulkan_decode.h

@@ -72,6 +72,10 @@ typedef struct FFVulkanDecodeContext {
     int external_fg;   /* Oddity  #2 - hardware can't apply film grain */
     uint32_t frame_id_alloc_mask; /* For AV1 only */
 
+    /* Workaround for NVIDIA drivers tested with CTS version 1.3.8 for AV1.
+     * The tests were incorrect as the OrderHints were offset by 1. */
+    int quirk_av1_offset;
+
     /* Thread-local state below */
     struct HEVCHeaderSet *hevc_headers;
     size_t hevc_headers_size;