fix(audioout2): wire skipped-submit trace counter (#761)

ObserveComputeDispatch only returned evaluation's pooled arrays when
evaluationHandledByCpu was set. Dispatches rejected before submission
(empty resource tables, oversized workgroup, compile failure) or a
compute submit that got dropped instead of enqueued (workSequence == 0)
never handed those buffers to a consumer that would return them,
leaking one lease per occurrence and growing GuestDataPool.Shared
without bound over a long session.

Adds GuestDataPool.DiagnosticStats() (outstanding lease count, idle
cached bytes) surfaced in the periodic [LOADER][PERF] line, to catch
this class of regression going forward.

Verified on Ghost of Yotei and Demon's Souls: pool_leases grew
unbounded before the fix (525 in 5 min on Demon's Souls, 1114 in 180s
on Yotei) and stays flat/bounded after (0-6 and 2-18 respectively),
with no behavioral regression observed.

Directory.Build.props

@@ -9,7 +9,7 @@ SPDX-License-Identifier: GPL-2.0-or-later
     <ImplicitUsings>enable</ImplicitUsings>
     <Nullable>enable</Nullable>
     <GenerateDocumentationFile>true</GenerateDocumentationFile>
-    <SharpEmuVersion>0.0.3-hotfix-2</SharpEmuVersion>
+    <SharpEmuVersion>0.0.3-release.2</SharpEmuVersion>
     <Version>$(SharpEmuVersion)</Version>
 
     <RepoRoot>$([MSBuild]::NormalizeDirectory('$(MSBuildThisFileDirectory)'))</RepoRoot>

src/SharpEmu.Libs/Agc/AgcExports.cs

@@ -11307,7 +11307,9 @@ public static partial class AgcExports
             }
         }
 
-        if (evaluationHandledByCpu)
+        // Rejected/CPU-handled dispatches never hand evaluation's pooled buffers to a
+        // consumer that would return them; reclaim here to keep GuestDataPool.Shared bounded.
+        if (evaluationHandledByCpu || !gpuDispatch)
         {
             ReturnPooledEvaluationArrays(evaluation);
         }

src/SharpEmu.Libs/Audio/AudioOut2Exports.cs

@@ -921,6 +921,7 @@ public static class AudioOut2Exports
 
                 if (mixedPorts == 0)
                 {
+                    TraceSubmitSkipped(context, frames, "no-ports");
                     return false;
                 }
 
@@ -942,6 +943,7 @@ public static class AudioOut2Exports
                 var backend = ResolveContextBackend(context, out var backendName);
                 if (backend is null)
                 {
+                    TraceSubmitSkipped(context, frames, "no-backend");
                     return false;
                 }
 
@@ -1212,4 +1214,14 @@ public static class AudioOut2Exports
             Console.Error.WriteLine($"[LOADER][TRACE] audio_out2.{message}");
         }
     }
+
+    private static void TraceSubmitSkipped(ContextState context, int frames, string reason)
+    {
+        var n = Interlocked.Increment(ref _submitSkipTraceCount);
+        if (n <= 8 || n % 500 == 0)
+        {
+            TraceAudioOut2(
+                $"context-submit-skip#{n} handle=0x{context.Handle:X} frames={frames} reason={reason}");
+        }
+    }
 }

src/SharpEmu.Libs/Gpu/GuestDataPool.cs

@@ -23,6 +23,10 @@ internal static class GuestDataPool
 
     public static void Trim() => ((BoundedByteArrayPool)Shared).Trim();
 
+    /// <summary>Outstanding lease count and idle cached bytes, for leak diagnostics.</summary>
+    public static (int LeaseCount, ulong CachedBytes) DiagnosticStats() =>
+        ((BoundedByteArrayPool)Shared).Stats();
+
     private sealed class BoundedByteArrayPool : ArrayPool<byte>
     {
         private readonly object _gate = new();
@@ -119,6 +123,14 @@ internal static class GuestDataPool
             }
         }
 
+        public (int LeaseCount, ulong CachedBytes) Stats()
+        {
+            lock (_gate)
+            {
+                return (_leases.Count, _cachedBytes);
+            }
+        }
+
         private int GetAllocationLength(int minimumLength)
         {
             if (minimumLength <= 16)

src/SharpEmu.Libs/Kernel/KernelExports.cs

@@ -466,4 +466,45 @@ public static class KernelExports
         ctx[CpuRegister.Rax] = unchecked((ulong)(-1L));
         return (int)OrbisGen2Result.ORBIS_GEN2_OK;
     }
+
+    [SysAbiExport(
+    Nid = "tU5e3f9gSiU",
+    ExportName = "sceKernelIsTrinityMode",
+    Target = Generation.Gen4 | Generation.Gen5,
+    LibraryName = "libKernel")]
+    public static int KernelIsTrinityMode(CpuContext ctx)
+    {
+        ctx[CpuRegister.Rax] = 0;
+
+        return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+    }
+
+    [SysAbiExport(
+    Nid = "DLORcroUqbc",
+    ExportName = "sceKernelGetOpenPsId",
+    Target = Generation.Gen4 | Generation.Gen5,
+    LibraryName = "libKernel")]
+    public static int KernelGetOpenPsId(CpuContext ctx)
+    {
+        ulong bufferPtr = ctx[CpuRegister.Rdi];
+
+        if (bufferPtr == 0)
+        {
+            ctx[CpuRegister.Rax] = unchecked((ulong)(int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT);
+
+            return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT;
+        }
+
+        Span<byte> openPsId = stackalloc byte[16];
+
+        if (!ctx.Memory.TryWrite(bufferPtr, openPsId))
+        {
+            ctx[CpuRegister.Rax] = unchecked((ulong)(int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
+            return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT;
+        }
+
+        ctx[CpuRegister.Rax] = 0;
+
+        return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+    }
 }

src/SharpEmu.Libs/Np/NpTrophy2Exports.cs

@@ -99,6 +99,15 @@ public static class NpTrophy2Exports
     public static int NpTrophy2GetTrophyInfo(CpuContext ctx) =>
         SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_NOT_FOUND);
 
+    [SysAbiExport(
+        Nid = "y3zHpdZO6ME",
+        ExportName = "sceNpTrophy2GetTrophyInfoArray",
+        Target = Generation.Gen5,
+        LibraryName = "libSceNpTrophy2")]
+    public static int NpTrophy2GetTrophyInfoArray(CpuContext ctx) =>
+        SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_NOT_FOUND);
+
+
     private static int WriteIdAndReturn(CpuContext ctx, ulong outAddress, ref int nextId)
     {
         if (outAddress == 0)

src/SharpEmu.Libs/VideoOut/VideoOutExports.cs

@@ -1300,10 +1300,12 @@ public static class VideoOutExports
         var submitted = Interlocked.Exchange(ref _submittedFrameCount, 0);
         var presentedCount = Interlocked.Exchange(ref _presentedFrameCount, 0);
         var (draws, drawMs, pipelines, spirvCompiles) = GuestGpu.Current.ReadAndResetPerfCounters();
+        var (poolLeases, poolCachedBytes) = SharpEmu.Libs.Gpu.GuestDataPool.DiagnosticStats();
         Console.Error.WriteLine(
             $"[LOADER][PERF] videoout submitted_fps={submitted / elapsedSeconds:F1} " +
             $"presented_fps={presentedCount / elapsedSeconds:F1} " +
-            $"draws={draws} draw_ms={drawMs:F0} pipelines={pipelines} spirv={spirvCompiles}");
+            $"draws={draws} draw_ms={drawMs:F0} pipelines={pipelines} spirv={spirvCompiles} " +
+            $"pool_leases={poolLeases} pool_cached_mb={poolCachedBytes / 1024.0 / 1024.0:F1}");
     }
 
     private static readonly bool _flipPacingDisabled = string.Equals(