Vulkan: Migrate buffers between memory types to improve GPU performance (#4540)

* Initial implementation of migration between memory heaps

- Missing OOM handling
- Missing `_map` data safety when remapping
  - Copy may not have completed yet (needs some kind of fence)
  - Map may be unmapped before it is done being used. (needs scoped access)
- SSBO accesses are all "writes" - maybe pass info in another way.
- Missing keeping map type when resizing buffers (should this be done?)

* Ensure migrated data is in place before flushing.

* Fix issue where old waitable would be signalled.

- There is a real issue where existing Auto<> references need to be replaced.

* Swap bound Auto<> instances when swapping buffer backing

* Fix conversion buffers

* Don't try move buffers if the host has shared memory.

* Make GPU methods return PinnedSpan with scope

* Storage Hint

* Fix stupidity

* Fix rebase

* Tweak rules

Attempt to sidestep BOTW slowdown

* Remove line

* Migrate only when command buffers flush

* Change backing swap log to debug

* Address some feedback

* Disallow backing swap when the flush lock is held by the current thread

* Make PinnedSpan from ReadOnlySpan explicitly unsafe

* Fix some small issues

- Index buffer swap fixed
- Allocate DeviceLocal buffers using a separate block list to images.

* Remove alternative flags

* Address feedback

Ryujinx.Graphics.Gpu/Image/Texture.cs

@@ -1022,13 +1022,12 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// This method should be used to retrieve data that was modified by the host GPU.
         /// This is not cheap, avoid doing that unless strictly needed.
         /// </remarks>
-        /// <param name="output">An output span to place the texture data into. If empty, one is generated</param>
+        /// <param name="output">An output span to place the texture data into</param>
         /// <param name="blacklist">True if the texture should be blacklisted, false otherwise</param>
         /// <param name="texture">The specific host texture to flush. Defaults to this texture</param>
-        /// <returns>The span containing the texture data</returns>
-        private ReadOnlySpan<byte> GetTextureDataFromGpu(Span<byte> output, bool blacklist, ITexture texture = null)
+        private void GetTextureDataFromGpu(Span<byte> output, bool blacklist, ITexture texture = null)
         {
-            ReadOnlySpan<byte> data;
+            PinnedSpan<byte> data;
 
             if (texture != null)
             {
@@ -1054,9 +1053,9 @@ namespace Ryujinx.Graphics.Gpu.Image
                 }
             }
 
-            data = ConvertFromHostCompatibleFormat(output, data);
+            ConvertFromHostCompatibleFormat(output, data.Get());
 
-            return data;
+            data.Dispose();
         }
 
         /// <summary>
@@ -1071,10 +1070,9 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// <param name="level">The level of the texture to flush</param>
         /// <param name="blacklist">True if the texture should be blacklisted, false otherwise</param>
         /// <param name="texture">The specific host texture to flush. Defaults to this texture</param>
-        /// <returns>The span containing the texture data</returns>
-        public ReadOnlySpan<byte> GetTextureDataSliceFromGpu(Span<byte> output, int layer, int level, bool blacklist, ITexture texture = null)
+        public void GetTextureDataSliceFromGpu(Span<byte> output, int layer, int level, bool blacklist, ITexture texture = null)
         {
-            ReadOnlySpan<byte> data;
+            PinnedSpan<byte> data;
 
             if (texture != null)
             {
@@ -1100,9 +1098,9 @@ namespace Ryujinx.Graphics.Gpu.Image
                 }
             }
 
-            data = ConvertFromHostCompatibleFormat(output, data, level, true);
+            ConvertFromHostCompatibleFormat(output, data.Get(), level, true);
 
-            return data;
+            data.Dispose();
         }
 
         /// <summary>

Ryujinx.Graphics.Gpu/Memory/Buffer.cs

@@ -82,7 +82,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
             Address         = address;
             Size            = size;
 
-            Handle = context.Renderer.CreateBuffer((int)size);
+            Handle = context.Renderer.CreateBuffer((int)size, baseBuffers?.MaxBy(x => x.Size).Handle ?? BufferHandle.Null);
 
             _useGranular = size > GranularBufferThreshold;
 
@@ -415,10 +415,10 @@ namespace Ryujinx.Graphics.Gpu.Memory
         {
             int offset = (int)(address - Address);
 
-            ReadOnlySpan<byte> data = _context.Renderer.GetBufferData(Handle, offset, (int)size);
+            using PinnedSpan<byte> data = _context.Renderer.GetBufferData(Handle, offset, (int)size);
 
             // TODO: When write tracking shaders, they will need to be aware of changes in overlapping buffers.
-            _physicalMemory.WriteUntracked(address, data);
+            _physicalMemory.WriteUntracked(address, data.Get());
         }
 
         /// <summary>