Gpu runtime stalls (#410)

* [runtime] restore default GC mode

* [cpu] add string leaf stubs

* [ampr] allow concurrent reads

* [bink] keep guest decode path

* [kernel] streamline host memory access

* [shader] add scalar memory fallback

* [gpu] bound guest data pool

* [gpu] reduce queue stalls

* [video] stabilize guest resources

* revert lock file

src/SharpEmu.Libs/Gpu/GuestDataPool.cs

@@ -2,6 +2,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 using System.Buffers;
+using System.Numerics;
 
 namespace SharpEmu.Libs.Gpu;
 
@@ -15,7 +16,125 @@ namespace SharpEmu.Libs.Gpu;
 /// </summary>
 internal static class GuestDataPool
 {
-    public static ArrayPool<byte> Shared { get; } = ArrayPool<byte>.Create(
+    public static ArrayPool<byte> Shared { get; } = new BoundedByteArrayPool(
         maxArrayLength: 16 * 1024 * 1024,
-        maxArraysPerBucket: 96);
+        maxCachedBytes: 256UL * 1024 * 1024,
+        maxArraysPerBucket: 8);
+
+    public static void Trim() => ((BoundedByteArrayPool)Shared).Trim();
+
+    private sealed class BoundedByteArrayPool : ArrayPool<byte>
+    {
+        private readonly object _gate = new();
+        private readonly int _maxArrayLength;
+        private readonly ulong _maxCachedBytes;
+        private readonly int _maxArraysPerBucket;
+        private readonly Dictionary<int, Stack<byte[]>> _cachedByBucket = [];
+        private readonly HashSet<byte[]> _leases =
+            new(System.Collections.Generic.ReferenceEqualityComparer.Instance);
+        private ulong _cachedBytes;
+
+        public BoundedByteArrayPool(
+            int maxArrayLength,
+            ulong maxCachedBytes,
+            int maxArraysPerBucket)
+        {
+            ArgumentOutOfRangeException.ThrowIfNegativeOrZero(maxArrayLength);
+            ArgumentOutOfRangeException.ThrowIfZero(maxCachedBytes);
+            ArgumentOutOfRangeException.ThrowIfNegativeOrZero(maxArraysPerBucket);
+            _maxArrayLength = maxArrayLength;
+            _maxCachedBytes = maxCachedBytes;
+            _maxArraysPerBucket = maxArraysPerBucket;
+        }
+
+        public override byte[] Rent(int minimumLength)
+        {
+            ArgumentOutOfRangeException.ThrowIfNegative(minimumLength);
+            var length = GetAllocationLength(minimumLength);
+            byte[]? array = null;
+            lock (_gate)
+            {
+                if (length <= _maxArrayLength &&
+                    _cachedByBucket.TryGetValue(length, out var bucket) &&
+                    bucket.TryPop(out array))
+                {
+                    _cachedBytes -= (ulong)array.LongLength;
+                }
+
+                array ??= new byte[length];
+                _leases.Add(array);
+            }
+
+            return array;
+        }
+
+        public override void Return(byte[] array, bool clearArray = false)
+        {
+            ArgumentNullException.ThrowIfNull(array);
+            lock (_gate)
+            {
+                if (!_leases.Remove(array))
+                {
+                    return;
+                }
+            }
+
+            if (clearArray)
+            {
+                Array.Clear(array);
+            }
+
+            lock (_gate)
+            {
+                if (array.Length > _maxArrayLength ||
+                    !IsBucketLength(array.Length) ||
+                    (ulong)array.LongLength > _maxCachedBytes -
+                        Math.Min(_cachedBytes, _maxCachedBytes))
+                {
+                    return;
+                }
+
+                if (!_cachedByBucket.TryGetValue(array.Length, out var bucket))
+                {
+                    bucket = new Stack<byte[]>();
+                    _cachedByBucket.Add(array.Length, bucket);
+                }
+
+                if (bucket.Count >= _maxArraysPerBucket)
+                {
+                    return;
+                }
+
+                bucket.Push(array);
+                _cachedBytes += (ulong)array.LongLength;
+            }
+        }
+
+        public void Trim()
+        {
+            lock (_gate)
+            {
+                _cachedByBucket.Clear();
+                _cachedBytes = 0;
+            }
+        }
+
+        private int GetAllocationLength(int minimumLength)
+        {
+            if (minimumLength <= 16)
+            {
+                return 16;
+            }
+
+            if (minimumLength > _maxArrayLength)
+            {
+                return minimumLength;
+            }
+
+            return checked((int)BitOperations.RoundUpToPowerOf2((uint)minimumLength));
+        }
+
+        private static bool IsBucketLength(int length) =>
+            length >= 16 && (length & (length - 1)) == 0;
+    }
 }