From 002007c323c3c17d69068e5ff729c2675aa7f477 Mon Sep 17 00:00:00 2001
From: ParantezTech <12572227+par274@users.noreply.github.com>
Date: Sun, 11 Oct 2026 06:11:55 +0300
Subject: [PATCH] [GPU] Fill metadata-shaped bounded fills on the host

---
 .../Gpu/Buffers/GuestBufferCache.cs           | 23 +++++++++++--------
 .../VulkanVideoPresenter.Rendering.cs         | 12 +++++++++-
 2 files changed, 24 insertions(+), 11 deletions(-)

diff --git a/src/SharpEmu.Libs/Gpu/Buffers/GuestBufferCache.cs b/src/SharpEmu.Libs/Gpu/Buffers/GuestBufferCache.cs
index 1fc7ad5..1a77b94 100644
--- a/src/SharpEmu.Libs/Gpu/Buffers/GuestBufferCache.cs
+++ b/src/SharpEmu.Libs/Gpu/Buffers/GuestBufferCache.cs
@@ -361,7 +361,10 @@ public sealed unsafe class GuestBufferCache : IGuestBufferStore, IDisposable
         }
     }
 
-    public void FillBuffer(ulong guestAddress, ulong size, uint value, bool isGds)
+    public void FillBuffer(ulong guestAddress, ulong size, uint value, bool isGds) =>
+        FillBuffer(guestAddress, size, value, isGds, publishFill: false);
+
+    private void FillBuffer(ulong guestAddress, ulong size, uint value, bool isGds, bool publishFill)
     {
         if ((guestAddress & 3) != 0 || size == 0 || (size & 3) != 0 || size > ulong.MaxValue - guestAddress)
         {
@@ -410,14 +413,14 @@ public sealed unsafe class GuestBufferCache : IGuestBufferStore, IDisposable
 
         images.InvalidateMemoryFromGpu(guestAddress, size);
         var bufferIdentifier = FindBuffer(guestAddress, size);
-        var (destination, destinationOffset) = ObtainBuffer(guestAddress, size, true, true, bufferIdentifier);
-        destination.Fill(destinationOffset, size, value);
-        if (images.OverlapsDccMetadata(guestAddress, size) && TryWriteFillToBacking(guestAddress, size, value))
         if (Diagnostics.DccWriterTrace.Enabled)
         {
             Diagnostics.DccWriterTrace.CurrentKind = "fill";
         }
 
+        var (destination, destinationOffset) = ObtainBuffer(guestAddress, size, true, true, bufferIdentifier);
+        destination.Fill(destinationOffset, size, value);
+        if ((publishFill || images.OverlapsDccMetadata(guestAddress, size)) && TryWriteFillToBacking(guestAddress, size, value))
         {
             _gpuModifiedRanges.Remove(guestAddress, size);
             Interlocked.Increment(ref _gpuModifiedVersion);
@@ -466,7 +469,7 @@ public sealed unsafe class GuestBufferCache : IGuestBufferStore, IDisposable
         if (guestAddress == 0 || (guestAddress & 3) != 0 || size == 0 || (size & 3) != 0 || size > ulong.MaxValue - guestAddress ||
             HasGpuDirtyBytes(guestAddress, size))
         {
-            FillBuffer(guestAddress, size, value, false);
+            FillBuffer(guestAddress, size, value, false, publishFill: true);
             return;
         }
 
@@ -476,7 +479,7 @@ public sealed unsafe class GuestBufferCache : IGuestBufferStore, IDisposable
         var region = images.QueryRegion(guestAddress, size);
         if (region.GpuImageBytes)
         {
-            FillBuffer(guestAddress, size, value, false);
+            FillBuffer(guestAddress, size, value, false, publishFill: true);
             return;
         }
 
@@ -489,7 +492,7 @@ public sealed unsafe class GuestBufferCache : IGuestBufferStore, IDisposable
         destination.Fill(destinationOffset, size, value);
         if (!TryWriteFillToBacking(guestAddress, size, value))
         {
-            FillBuffer(guestAddress, size, value, false);
+            FillBuffer(guestAddress, size, value, false, publishFill: true);
         }
     }
 
@@ -645,14 +648,14 @@ public sealed unsafe class GuestBufferCache : IGuestBufferStore, IDisposable
         var srcId = srcMemory ? FindBuffer(srcVaddr, size) : default;
         var dstId = dstMemory ? FindBuffer(dstVaddr, size) : default;
         var (src, srcOffset) = srcMemory ? ObtainBuffer(srcVaddr, size, false, true, srcId) : (_gds, srcVaddr);
-        var (dst, dstOffset) = dstMemory ? ObtainBuffer(dstVaddr, size, true, true, dstId) : (_gds, dstVaddr);
-        if (ReferenceEquals(src, dst) && srcOffset < dstOffset + size && dstOffset < srcOffset + size)
-        {
         if (Diagnostics.DccWriterTrace.Enabled)
         {
             Diagnostics.DccWriterTrace.CurrentKind = $"copy_from_0x{srcVaddr:X}";
         }
 
+        var (dst, dstOffset) = dstMemory ? ObtainBuffer(dstVaddr, size, true, true, dstId) : (_gds, dstVaddr);
+        if (ReferenceEquals(src, dst) && srcOffset < dstOffset + size && dstOffset < srcOffset + size)
+        {
             throw SubmissionScheduler.Fatal("The resolved Vulkan copy ranges overlap.");
         }
 
diff --git a/src/SharpEmu.Libs/VideoOut/VulkanVideoPresenter.Rendering.cs b/src/SharpEmu.Libs/VideoOut/VulkanVideoPresenter.Rendering.cs
index 61d3317..e602ca2 100644
--- a/src/SharpEmu.Libs/VideoOut/VulkanVideoPresenter.Rendering.cs
+++ b/src/SharpEmu.Libs/VideoOut/VulkanVideoPresenter.Rendering.cs
@@ -1299,7 +1299,7 @@ internal static unsafe partial class VulkanVideoPresenter
 
         public bool TryFillDccMetadata(ulong address, ulong size, uint fillValue)
         {
-            if (!_imageCache.OverlapsDccMetadata(address, size))
+            if (!_imageCache.OverlapsDccMetadata(address, size) && !IsMetadataShapedFill(address, size, fillValue))
             {
                 return false;
             }
@@ -1308,6 +1308,16 @@ internal static unsafe partial class VulkanVideoPresenter
             return true;
         }
 
+        private bool IsMetadataShapedFill(ulong address, ulong size, uint fillValue)
+        {
+            const ulong metadataBlockSize = 0x1000;
+            const ulong maxMetadataFill = 0x100000;
+            return address != 0 && size != 0 && size <= maxMetadataFill &&
+                   address % metadataBlockSize == 0 && size % metadataBlockSize == 0 &&
+                   fillValue == (fillValue & 0xFF) * 0x01010101u &&
+                   !_imageCache.QueryRegion(address, size).ImageBytes;
+        }
+
         public bool TryCopyWordsOnHost(ulong destination, ulong source, ulong sourceWords, ulong words) =>
             _bufferCache.TryCopyWordsOnHost(destination, source, sourceWords, words);
     }