Fix the P6 scratch save in R2UR/MATCH/HFMA2.RELU; GPU memory dump tool

The colour cast on title 1 (magenta/cyan, then red/green, changing per
course) came from the sky/atmosphere volume shader (a pixel shader drawing
a 32^3 RGBA16F table slice by slice), which starts with an unguarded R2UR.
R2UR, MATCH and HFMA2.RELU use P6 as scratch and saved/restored it with the
uniform-guard mask, 1 << (6 - 7) for an unguarded instruction: undefined, in
practice bit 31, which shifted into the opcode bits and turned the save into
another instruction. They now always save and restore P6.

Debugging aids used to find it:
- EDEN_NX2_DUMP=<present>:<addr>:<size>,...: flush GPU memory ranges at a
  present (on the GPU thread) and save them next to the frame captures;
  nx2work/vol3d.py untiles Switch 2 3D textures from such dumps.
- GPU::RunOnGpuThread.
- Logs of Switch 2 3D images and descriptors.

1 files changed, 6 insertions, 0 deletions

diff --git a/src/video_core/texture_cache/texture_cache.h b/src/video_core/texture_cache/texture_cache.h
index f3da5684a5..75005f0731 100644
--- a/src/video_core/texture_cache/texture_cache.h
+++ b/src/video_core/texture_cache/texture_cache.h
@@ -1569,6 +1569,12 @@ ImageId TextureCache<P>::InsertImage(const ImageInfo& info, GPUVAddr gpu_addr,
     ASSERT_MSG(cpu_addr, "Tried to insert an image to an invalid gpu_addr={:#x}", gpu_addr);
     ImageInfo storage_info = info;
     storage_info.native_tiling = gpu_memory->UsesNativeTiling();
+    if (storage_info.native_tiling && info.type == ImageType::e3D) {
+        // Switch 2 3D images (lighting/fog volumes) are rare: log each one's shape.
+        LOG_INFO(HW_GPU, "3D image at {:#x}: {}x{}x{} levels {} format {} block {}x{}x{}",
+                 gpu_addr, info.size.width, info.size.height, info.size.depth, info.resources.levels,
+                 static_cast<u32>(info.format), info.block.width, info.block.height, info.block.depth);
+    }
     const ImageId image_id = JoinImages(storage_info, gpu_addr, *cpu_addr);
     const Image& image = slot_images[image_id];
     // Using "image.gpu_addr" instead of "gpu_addr" is important because it might be different