Fixes a Mutex Issue Preventing Some UE Titles From Booting (#451)

* Optimize guest import, memory, and pthread hot paths

* Fix UE adaptive mutex self-lock handling

src/SharpEmu.Core/Cpu/Native/DirectExecutionBackend.Imports.cs

@@ -530,9 +530,12 @@ public sealed partial class DirectExecutionBackend
 			{
 				GuestThreadExecution.RestoreImportCallFrame(previousImportCallFrame);
 			}
-			DeliverPendingGuestExceptionAtSafePoint(
-				cpuContext,
-				CaptureImportBoundaryContinuation(cpuContext, argPackPtr, num7));
+			if (Volatile.Read(ref _pendingGuestExceptionCount) != 0)
+			{
+				DeliverPendingGuestExceptionAtSafePoint(
+					cpuContext,
+					CaptureImportBoundaryContinuation(cpuContext, argPackPtr, num7));
+			}
 			StoreImportVectorReturn(cpuContext, argPackPtr);
 			if (dispatchResolved &&
 				orbisGen2Result == OrbisGen2Result.ORBIS_GEN2_OK &&
@@ -1326,9 +1329,12 @@ public sealed partial class DirectExecutionBackend
 				GuestThreadExecution.RestoreImportCallFrame(previousImportCallFrame);
 			}
 		}
-		DeliverPendingGuestExceptionAtSafePoint(
-			cpuContext,
-			CaptureImportBoundaryContinuation(cpuContext, argPackPtr, returnRip));
+		if (Volatile.Read(ref _pendingGuestExceptionCount) != 0)
+		{
+			DeliverPendingGuestExceptionAtSafePoint(
+				cpuContext,
+				CaptureImportBoundaryContinuation(cpuContext, argPackPtr, returnRip));
+		}
 		StoreImportVectorReturn(cpuContext, argPackPtr);
 
 		if (returnValue != (int)OrbisGen2Result.ORBIS_GEN2_OK)

src/SharpEmu.Core/Cpu/Native/DirectExecutionBackend.cs

@@ -712,6 +712,11 @@ public sealed unsafe partial class DirectExecutionBackend : INativeCpuBackend, I
 
 	private readonly Dictionary<ulong, PendingGuestException> _pendingGuestExceptions = new Dictionary<ulong, PendingGuestException>();
 
+	// Import dispatch is the hottest managed path in UE titles. Most imports do
+	// not have an exception queued, so publish the dictionary population and let
+	// safe points skip _guestThreadGate entirely in the common case.
+	private int _pendingGuestExceptionCount;
+
 	private readonly HashSet<ulong> _activeGuestExceptionDeliveries = new HashSet<ulong>();
 
 	private int _guestThreadPumpDepth;
@@ -3948,10 +3953,10 @@ public sealed unsafe partial class DirectExecutionBackend : INativeCpuBackend, I
 					// unwinding. Unity can begin its next stop-the-world cycle in
 					// that window; treating the new raise as part of the old delivery
 					// strands the collector waiting for an acknowledgement.
-					_pendingGuestExceptions[threadHandle] = new PendingGuestException(
+					QueuePendingGuestExceptionLocked(threadHandle, new PendingGuestException(
 						handler,
 						exceptionType,
-						external.ExceptionStackBase);
+						external.ExceptionStackBase));
 					return true;
 				}
 
@@ -3960,10 +3965,10 @@ public sealed unsafe partial class DirectExecutionBackend : INativeCpuBackend, I
 				// managed thread corrupts the worker's control state. Queue the
 				// request and let that exact executor consume it at its next HLE
 				// boundary, where the original guest thread is safely paused.
-				_pendingGuestExceptions[threadHandle] = new PendingGuestException(
+				QueuePendingGuestExceptionLocked(threadHandle, new PendingGuestException(
 					handler,
 					exceptionType,
-					external.ExceptionStackBase);
+					external.ExceptionStackBase));
 				if (logGuestExceptions)
 				{
 					Console.Error.WriteLine(
@@ -4008,17 +4013,17 @@ public sealed unsafe partial class DirectExecutionBackend : INativeCpuBackend, I
 				}
 				if (target.ExceptionDeliveryActive)
 				{
-					_pendingGuestExceptions[threadHandle] = new PendingGuestException(
+					QueuePendingGuestExceptionLocked(threadHandle, new PendingGuestException(
 						handler,
 						exceptionType,
-						exceptionStackBase);
+						exceptionStackBase));
 					return true;
 				}
 
-				_pendingGuestExceptions[threadHandle] = new PendingGuestException(
+				QueuePendingGuestExceptionLocked(threadHandle, new PendingGuestException(
 					handler,
 					exceptionType,
-					exceptionStackBase);
+					exceptionStackBase));
 				if (logGuestExceptions)
 				{
 					Console.Error.WriteLine(
@@ -4179,7 +4184,7 @@ public sealed unsafe partial class DirectExecutionBackend : INativeCpuBackend, I
 					RestoreInterruptedGuestThread();
 					if (target.State == GuestThreadRunState.Blocked &&
 						!target.ExecutorActive &&
-						_pendingGuestExceptions.Remove(threadHandle, out var queued))
+						TryRemovePendingGuestExceptionLocked(threadHandle, out var queued))
 					{
 						followUp = queued;
 					}
@@ -4265,6 +4270,11 @@ public sealed unsafe partial class DirectExecutionBackend : INativeCpuBackend, I
 		CpuContext currentContext,
 		GuestCpuContinuation interruptedContinuation)
 	{
+		if (Volatile.Read(ref _pendingGuestExceptionCount) == 0)
+		{
+			return;
+		}
+
 		var threadHandle = GuestThreadExecution.CurrentGuestThreadHandle;
 		if (threadHandle == 0)
 		{
@@ -4278,7 +4288,7 @@ public sealed unsafe partial class DirectExecutionBackend : INativeCpuBackend, I
 				return;
 			}
 
-			if (!_pendingGuestExceptions.Remove(threadHandle, out pending))
+			if (!TryRemovePendingGuestExceptionLocked(threadHandle, out pending))
 			{
 				return;
 			}
@@ -4340,6 +4350,27 @@ public sealed unsafe partial class DirectExecutionBackend : INativeCpuBackend, I
 		}
 	}
 
+	private void QueuePendingGuestExceptionLocked(
+		ulong threadHandle,
+		PendingGuestException pending)
+	{
+		_pendingGuestExceptions[threadHandle] = pending;
+		Volatile.Write(ref _pendingGuestExceptionCount, _pendingGuestExceptions.Count);
+	}
+
+	private bool TryRemovePendingGuestExceptionLocked(
+		ulong threadHandle,
+		out PendingGuestException pending)
+	{
+		if (!_pendingGuestExceptions.Remove(threadHandle, out pending))
+		{
+			return false;
+		}
+
+		Volatile.Write(ref _pendingGuestExceptionCount, _pendingGuestExceptions.Count);
+		return true;
+	}
+
 	private static bool TryWriteGuestExceptionContext(
 		CpuContext context,
 		ulong address,
@@ -4434,6 +4465,7 @@ public sealed unsafe partial class DirectExecutionBackend : INativeCpuBackend, I
 			_guestThreads.Clear();
 			_externalGuestThreads.Clear();
 			_pendingGuestExceptions.Clear();
+			Volatile.Write(ref _pendingGuestExceptionCount, 0);
 			_activeGuestExceptionDeliveries.Clear();
 		}
 

src/SharpEmu.Core/Cpu/TrackedCpuMemory.cs

@@ -40,6 +40,9 @@ public sealed class TrackedCpuMemory : ICpuMemory, ITrackedCpuMemory, IGuestMemo
         return result;
     }
 
+    public bool TryCopy(ulong destinationAddress, ulong sourceAddress, ulong length) =>
+        _inner.TryCopy(destinationAddress, sourceAddress, length);
+
     public bool TryAllocateGuestMemory(ulong size, ulong alignment, out ulong address)
     {
         if (_inner is IGuestMemoryAllocator allocator)

src/SharpEmu.Core/Memory/PhysicalVirtualMemory.cs

@@ -20,6 +20,11 @@ public sealed unsafe class PhysicalVirtualMemory : IVirtualMemory, IGuestMemoryA
     private readonly Dictionary<(ulong DesiredAddress, ulong Alignment, bool Executable), ulong> _allocationSearchHints = new();
     private readonly Dictionary<ulong, ProgramHeaderFlags> _pageProtections = new();
     private bool _disposed;
+
+    [ThreadStatic]
+    private static CommittedRangeCache? _committedRangeCache;
+
+    private long _mappingGeneration;
     private const ulong PageSize = 0x1000;
     private const ulong GuestAllocationArenaAddress = 0x00006000_0000_0000;
     private const ulong GuestAllocationArenaSize = 0x0100_0000;
@@ -28,6 +33,77 @@ public sealed unsafe class PhysicalVirtualMemory : IVirtualMemory, IGuestMemoryA
     private const ulong FullCommitRegionLimit = 4UL << 30;
     private const ulong DefaultLazyReservePrimeBytes = 0x0400_0000UL; // 64 MiB
     private const ulong LazyReservePrimeChunkBytes = 0x0200_0000UL; // 32 MiB
+    private const int CommittedRangeCacheCapacity = 4;
+
+    private sealed class CommittedRangeCache
+    {
+        private readonly CommittedRange[] _ranges = new CommittedRange[CommittedRangeCacheCapacity];
+        private PhysicalVirtualMemory? _owner;
+        private long _generation;
+        private int _count;
+        private int _nextReplacement;
+
+        public bool Contains(
+            PhysicalVirtualMemory owner,
+            long generation,
+            ulong start,
+            ulong end)
+        {
+            if (!ReferenceEquals(_owner, owner) || _generation != generation)
+            {
+                return false;
+            }
+
+            for (var index = 0; index < _count; index++)
+            {
+                var range = _ranges[index];
+                if (start >= range.Start && end <= range.End)
+                {
+                    return true;
+                }
+            }
+
+            return false;
+        }
+
+        public void Add(
+            PhysicalVirtualMemory owner,
+            long generation,
+            ulong start,
+            ulong end)
+        {
+            if (!ReferenceEquals(_owner, owner) || _generation != generation)
+            {
+                _owner = owner;
+                _generation = generation;
+                _count = 0;
+                _nextReplacement = 0;
+            }
+
+            for (var index = 0; index < _count; index++)
+            {
+                var range = _ranges[index];
+                if (start <= range.End && end >= range.Start)
+                {
+                    _ranges[index] = new CommittedRange(
+                        Math.Min(start, range.Start),
+                        Math.Max(end, range.End));
+                    return;
+                }
+            }
+
+            if (_count < _ranges.Length)
+            {
+                _ranges[_count++] = new CommittedRange(start, end);
+                return;
+            }
+
+            _ranges[_nextReplacement] = new CommittedRange(start, end);
+            _nextReplacement = (_nextReplacement + 1) % _ranges.Length;
+        }
+    }
+
+    private readonly record struct CommittedRange(ulong Start, ulong End);
 
     // Raw Windows PAGE_* values retained for the internal region/protection
     // bookkeeping: regions and saved old-protection values always carry the raw
@@ -440,6 +516,7 @@ public sealed unsafe class PhysicalVirtualMemory : IVirtualMemory, IGuestMemoryA
             _gate.ExitWriteLock();
         }
 
+        Interlocked.Increment(ref _mappingGeneration);
         _hostMemory.Free(address);
     }
 
@@ -611,6 +688,7 @@ public sealed unsafe class PhysicalVirtualMemory : IVirtualMemory, IGuestMemoryA
                 {
                     _allocationSearchHints.Clear();
                 }
+                Interlocked.Increment(ref _mappingGeneration);
             }
             finally
             {
@@ -953,6 +1031,60 @@ public sealed unsafe class PhysicalVirtualMemory : IVirtualMemory, IGuestMemoryA
         }
     }
 
+    public bool TryCopy(ulong destinationAddress, ulong sourceAddress, ulong length)
+    {
+        if (length == 0)
+        {
+            return true;
+        }
+        if (length > int.MaxValue)
+        {
+            return false;
+        }
+
+        // Match TryWrite's managed-write notification before touching an
+        // identity-mapped guest page protected by the image tracker.
+        GuestImageWriteTracker.NotifyManagedWrite(destinationAddress, length);
+
+        _gate.EnterReadLock();
+        try
+        {
+            var sourceRegion = FindRegion(sourceAddress, length);
+            var destinationRegion = FindRegion(destinationAddress, length);
+            if (sourceRegion is null || destinationRegion is null ||
+                !TryResolveRegionOffset(sourceAddress, length, sourceRegion, out var sourceOffset) ||
+                !TryResolveRegionOffset(destinationAddress, length, destinationRegion, out var destinationOffset))
+            {
+                return false;
+            }
+
+            var sourcePointer = sourceRegion.VirtualAddress + sourceOffset;
+            var destinationPointer = destinationRegion.VirtualAddress + destinationOffset;
+            if ((sourceRegion.IsReservedOnly &&
+                 !EnsureRangeCommitted(sourcePointer, length, sourceRegion)) ||
+                (destinationRegion.IsReservedOnly &&
+                 !EnsureRangeCommitted(destinationPointer, length, destinationRegion)) ||
+                !CanReadWithoutProtectionChange(sourcePointer, length, sourceRegion) ||
+                !CanWriteWithoutProtectionChange(destinationPointer, length, destinationRegion))
+            {
+                return false;
+            }
+
+            // Span.CopyTo has memmove overlap semantics, so this allocation-free
+            // path safely serves both libc memcpy and libc memmove.
+            new ReadOnlySpan<byte>((void*)sourcePointer, checked((int)length)).CopyTo(
+                new Span<byte>((void*)destinationPointer, checked((int)length)));
+            NotifyGuestWriteWatch(
+                destinationAddress,
+                new ReadOnlySpan<byte>((void*)destinationPointer, checked((int)length)));
+            return true;
+        }
+        finally
+        {
+            _gate.ExitReadLock();
+        }
+    }
+
     private bool TryReadExclusive(ulong virtualAddress, Span<byte> destination)
     {
         var region = FindRegion(virtualAddress, (ulong)destination.Length);
@@ -1292,6 +1424,12 @@ public sealed unsafe class PhysicalVirtualMemory : IVirtualMemory, IGuestMemoryA
 
         var startPage = AlignDown(address, PageSize);
         var endPage = AlignUp(address + size, PageSize);
+        var mappingGeneration = Volatile.Read(ref _mappingGeneration);
+        var committedRangeCache = _committedRangeCache ??= new CommittedRangeCache();
+        if (committedRangeCache.Contains(this, mappingGeneration, startPage, endPage))
+        {
+            return true;
+        }
         var commitProtection = GetCommitProtection(region);
 
         var pageAddress = startPage;
@@ -1313,6 +1451,9 @@ public sealed unsafe class PhysicalVirtualMemory : IVirtualMemory, IGuestMemoryA
 
             if (info.State == HostRegionState.Committed)
             {
+                // The host query proved this whole range is committed. Retain
+                // that result instead of caching only the caller's small span.
+                CacheCommittedRange(info.BaseAddress, queriedEnd, mappingGeneration);
                 pageAddress = rangeEnd;
                 continue;
             }
@@ -1328,12 +1469,23 @@ public sealed unsafe class PhysicalVirtualMemory : IVirtualMemory, IGuestMemoryA
                 return false;
             }
 
+            CacheCommittedRange(pageAddress, rangeEnd, mappingGeneration);
             pageAddress = rangeEnd;
         }
 
+        CacheCommittedRange(startPage, endPage, mappingGeneration);
         return true;
     }
 
+    private void CacheCommittedRange(ulong startPage, ulong endPage, long mappingGeneration)
+    {
+        (_committedRangeCache ??= new CommittedRangeCache()).Add(
+            this,
+            mappingGeneration,
+            startPage,
+            endPage);
+    }
+
     private bool TryTemporarilyProtectForRead(
         ulong address,
         ulong size,

src/SharpEmu.HLE/ICpuMemory.cs

@@ -10,4 +10,6 @@ public interface ICpuMemory
     bool TryWrite(ulong virtualAddress, ReadOnlySpan<byte> source);
 
     bool TryCompare(ulong virtualAddress, ReadOnlySpan<byte> expected) => false;
+
+    bool TryCopy(ulong destinationAddress, ulong sourceAddress, ulong length) => false;
 }

src/SharpEmu.Libs/Kernel/KernelMemoryCompatExports.cs

@@ -1105,10 +1105,13 @@ public static partial class KernelMemoryCompatExports
             return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT;
         }
 
-        var payload = GC.AllocateUninitializedArray<byte>(count);
-        if (count > 0 && (!TryReadCompat(ctx, source, payload) || !TryWriteCompat(ctx, destination, payload)))
+        if (count > 0 && !ctx.Memory.TryCopy(destination, source, (ulong)count))
         {
-            return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT;
+            var payload = GC.AllocateUninitializedArray<byte>(count);
+            if (!TryReadCompat(ctx, source, payload) || !TryWriteCompat(ctx, destination, payload))
+            {
+                return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT;
+            }
         }
 
         ctx[CpuRegister.Rax] = destination;

src/SharpEmu.Libs/Kernel/KernelPthreadCompatExports.cs

@@ -41,18 +41,87 @@ public static class KernelPthreadCompatExports
 
     private sealed class PthreadMutexState
     {
-        public ulong OwnerThreadId { get; set; }
-        public int RecursionCount { get; set; }
+        private long _ownerThreadId;
+        private int _recursionCount;
+        private int _queuedWaiterCount;
+
+        public Lock SyncRoot { get; } = new();
+        public ulong OwnerThreadId
+        {
+            get => unchecked((ulong)Volatile.Read(ref _ownerThreadId));
+            set => Volatile.Write(ref _ownerThreadId, unchecked((long)value));
+        }
+
+        public int RecursionCount
+        {
+            get => Volatile.Read(ref _recursionCount);
+            set => Volatile.Write(ref _recursionCount, value);
+        }
+
+        public int QueuedWaiterCount => Volatile.Read(ref _queuedWaiterCount);
         public int Type { get; set; } = MutexTypeErrorCheck;
         public int Protocol { get; set; }
         public LinkedList<PthreadMutexWaiter> Waiters { get; } = new();
+
+        public bool TryAcquireUncontended(ulong threadId, bool allowWaiterBarge)
+        {
+            if (!allowWaiterBarge && QueuedWaiterCount != 0)
+            {
+                return false;
+            }
+
+            return TryAcquireOwner(threadId);
+        }
+
+        public bool TryAcquireOwner(ulong threadId)
+        {
+            if (Interlocked.CompareExchange(
+                    ref _ownerThreadId,
+                    unchecked((long)threadId),
+                    0) != 0)
+            {
+                return false;
+            }
+
+            Volatile.Write(ref _recursionCount, 1);
+            return true;
+        }
+
+        public bool TryReleaseUncontended(ulong threadId)
+        {
+            if (QueuedWaiterCount != 0 || RecursionCount != 1)
+            {
+                return false;
+            }
+
+            Volatile.Write(ref _recursionCount, 0);
+            if (Interlocked.CompareExchange(
+                    ref _ownerThreadId,
+                    0,
+                    unchecked((long)threadId)) == unchecked((long)threadId))
+            {
+                return true;
+            }
+
+            Volatile.Write(ref _recursionCount, 1);
+            return false;
+        }
+
+        public int IncrementRecursion() => Interlocked.Increment(ref _recursionCount);
+
+        public int DecrementRecursion() => Interlocked.Decrement(ref _recursionCount);
+
+        public void WaiterAddedLocked() => Interlocked.Increment(ref _queuedWaiterCount);
+
+        public void WaiterRemovedLocked() => Interlocked.Decrement(ref _queuedWaiterCount);
     }
 
     private sealed class PthreadMutexWaiter
     {
         public required ulong ThreadId { get; init; }
         public required string WakeKey { get; init; }
-        public required bool Cooperative { get; init; }
+        public required bool Cooperative { get; set; }
+        public ManualResetEventSlim? HostSignal { get; set; }
         public LinkedListNode<PthreadMutexWaiter>? Node { get; set; }
         public int Granted;
     }
@@ -94,7 +163,10 @@ public static class KernelPthreadCompatExports
     public static int PthreadSelf(CpuContext ctx)
     {
         var currentThreadHandle = KernelPthreadState.GetCurrentThreadHandle();
-        GuestThreadExecution.Scheduler?.RegisterGuestThreadContext(currentThreadHandle, ctx);
+        if (GuestThreadExecution.CurrentGuestThreadHandle != currentThreadHandle)
+        {
+            GuestThreadExecution.Scheduler?.RegisterGuestThreadContext(currentThreadHandle, ctx);
+        }
         ctx[CpuRegister.Rax] = currentThreadHandle;
         TracePthreadSelf(ctx, currentThreadHandle);
         return (int)OrbisGen2Result.ORBIS_GEN2_OK;
@@ -652,7 +724,7 @@ public static class KernelPthreadCompatExports
             return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_NOT_FOUND;
         }
 
-        lock (state)
+        lock (state.SyncRoot)
         {
             if (state.OwnerThreadId != 0 || state.RecursionCount != 0 || state.Waiters.Count != 0)
             {
@@ -684,11 +756,56 @@ public static class KernelPthreadCompatExports
         }
 
         var currentThreadId = KernelPthreadState.GetCurrentThreadHandle();
+        if (state.TryAcquireUncontended(currentThreadId, allowWaiterBarge: tryOnly))
+        {
+            TracePthreadMutex(ctx, tryOnly ? "trylock" : "lock", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_OK);
+            return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+        }
+
+        if (state.OwnerThreadId == currentThreadId)
+        {
+            if (state.Type == MutexTypeRecursive)
+            {
+                state.IncrementRecursion();
+                TracePthreadMutex(ctx, tryOnly ? "trylock" : "lock", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_OK);
+                return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+            }
+
+            if (state.Type == MutexTypeAdaptiveNp)
+            {
+                var adaptiveResult = tryOnly
+                    ? (int)OrbisGen2Result.ORBIS_GEN2_ERROR_BUSY
+                    : (int)OrbisGen2Result.ORBIS_GEN2_OK;
+                TracePthreadMutex(ctx, tryOnly ? "trylock" : "lock-idempotent", mutexAddress, resolvedAddress, state, currentThreadId, adaptiveResult);
+                return adaptiveResult;
+            }
+
+            if (state.Type == MutexTypeNormal)
+            {
+                if (tryOnly)
+                {
+                    TracePthreadMutex(ctx, "trylock", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_BUSY);
+                    return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_BUSY;
+                }
+
+                state.IncrementRecursion();
+                TracePthreadMutex(ctx, "lock", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_OK);
+                return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+            }
+
+            var ownedResult = tryOnly
+                ? (int)OrbisGen2Result.ORBIS_GEN2_ERROR_BUSY
+                : (int)OrbisGen2Result.ORBIS_GEN2_ERROR_DEADLOCK;
+            TracePthreadMutex(ctx, tryOnly ? "trylock" : "lock", mutexAddress, resolvedAddress, state, currentThreadId, ownedResult);
+            return ownedResult;
+        }
+
         var canCooperativelyBlock = !tryOnly &&
             GuestThreadExecution.IsGuestThread &&
             GuestThreadExecution.TryGetCurrentImportCallFrame(out _);
         PthreadMutexWaiter? waiter = null;
-        lock (state)
+        var acquiredWhileQueueing = false;
+        lock (state.SyncRoot)
         {
             if (state.OwnerThreadId == currentThreadId)
             {
@@ -699,7 +816,23 @@ public static class KernelPthreadCompatExports
                     return (int)OrbisGen2Result.ORBIS_GEN2_OK;
                 }
 
-                if (state.Type is MutexTypeNormal or MutexTypeAdaptiveNp)
+                if (state.Type == MutexTypeAdaptiveNp)
+                {
+                    if (tryOnly)
+                    {
+                        TracePthreadMutex(ctx, "trylock", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_BUSY);
+                        return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_BUSY;
+                    }
+
+                    // Gen5 runtime wrappers can layer an adaptive lock call over
+                    // scePthreadMutexLock for one logical acquisition, followed by
+                    // only one unlock. Keep the duplicate acquisition idempotent so
+                    // the matching unlock fully releases the HLE mutex.
+                    TracePthreadMutex(ctx, "lock-idempotent", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_OK);
+                    return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+                }
+
+                if (state.Type == MutexTypeNormal)
                 {
                     if (tryOnly)
                     {
@@ -708,7 +841,7 @@ public static class KernelPthreadCompatExports
                     }
 
                     // Several Gen5 runtimes layer their own owner/count bookkeeping
-                    // over a NORMAL or ADAPTIVE kernel mutex. Returning EDEADLK here
+                    // over a NORMAL kernel mutex. Returning EDEADLK here
                     // leaves that guest bookkeeping out of sync with the HLE owner and
                     // turns the wrapper into a permanent lock/unlock retry loop. Keep
                     // the compatibility recursion used by the original implementation;
@@ -734,10 +867,10 @@ public static class KernelPthreadCompatExports
             // waiter wedge a spin-on-trylock loop forever even though the mutex
             // is free (owner==0). The blocking lock still honours FIFO so real
             // blocked waiters are not starved by a barging locker.
-            if (state.OwnerThreadId == 0 && (tryOnly || state.Waiters.Count == 0))
+            if (state.OwnerThreadId == 0 &&
+                (tryOnly || state.Waiters.Count == 0) &&
+                state.TryAcquireOwner(currentThreadId))
             {
-                state.OwnerThreadId = currentThreadId;
-                state.RecursionCount = 1;
                 TracePthreadMutex(ctx, tryOnly ? "trylock" : "lock", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_OK);
                 return (int)OrbisGen2Result.ORBIS_GEN2_OK;
             }
@@ -749,6 +882,14 @@ public static class KernelPthreadCompatExports
             }
 
             waiter = EnqueueMutexWaiterLocked(state, currentThreadId, canCooperativelyBlock);
+            acquiredWhileQueueing = TryGrantMutexWaiterLocked(state, waiter);
+        }
+
+        if (acquiredWhileQueueing)
+        {
+            waiter!.HostSignal?.Dispose();
+            TracePthreadMutex(ctx, "lock", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_OK);
+            return (int)OrbisGen2Result.ORBIS_GEN2_OK;
         }
 
         if (canCooperativelyBlock && waiter is not null &&
@@ -782,8 +923,29 @@ public static class KernelPthreadCompatExports
         }
 
         var currentThreadId = KernelPthreadState.GetCurrentThreadHandle();
-        string? nextWakeKey = null;
-        lock (state)
+        if (state.OwnerThreadId == currentThreadId)
+        {
+            if (state.RecursionCount > 1)
+            {
+                state.DecrementRecursion();
+                TracePthreadMutex(ctx, "unlock", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_OK);
+                return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+            }
+
+            if (state.TryReleaseUncontended(currentThreadId))
+            {
+                if (state.QueuedWaiterCount != 0)
+                {
+                    WakeFirstMutexWaiter(state);
+                }
+
+                TracePthreadMutex(ctx, "unlock", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_OK);
+                return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+            }
+        }
+
+        PthreadMutexWaiter? nextWaiter = null;
+        lock (state.SyncRoot)
         {
             if (state.RecursionCount <= 0)
             {
@@ -810,19 +972,20 @@ public static class KernelPthreadCompatExports
                 // later locker — including the game's main thread — then queues
                 // behind a head that never advances and the process wedges.
                 if (state.Waiters.First is { } headNode &&
-                    TryGrantMutexWaiterLocked(state, headNode.Value) &&
-                    headNode.Value.Cooperative)
+                    TryGrantMutexWaiterLocked(state, headNode.Value))
                 {
-                    nextWakeKey = headNode.Value.WakeKey;
+                    nextWaiter = headNode.Value;
+                    if (!nextWaiter.Cooperative)
+                    {
+                        nextWaiter.HostSignal!.Set();
+                    }
                 }
-
-                Monitor.PulseAll(state);
             }
         }
 
-        if (nextWakeKey is not null)
+        if (nextWaiter is { Cooperative: true })
         {
-            _ = GuestThreadExecution.Scheduler?.WakeBlockedThreads(nextWakeKey, 1);
+            _ = GuestThreadExecution.Scheduler?.WakeBlockedThreads(nextWaiter.WakeKey, 1);
         }
 
         TracePthreadMutex(ctx, "unlock", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_OK);
@@ -1282,7 +1445,7 @@ public static class KernelPthreadCompatExports
         }
 
         var currentThreadId = KernelPthreadState.GetCurrentThreadHandle();
-        lock (mutexState)
+        lock (mutexState.SyncRoot)
         {
             if (mutexState.OwnerThreadId == 0 && mutexState.RecursionCount == 0)
             {
@@ -1295,10 +1458,10 @@ public static class KernelPthreadCompatExports
                 // mutex held (the unlock below is skipped), wedging every thread
                 // that later blocks on pthread_mutex_lock. Adopt ownership so the
                 // unlock/wait/re-lock cycle is balanced and releases the mutex.
-                mutexState.OwnerThreadId = currentThreadId;
-                mutexState.RecursionCount = 1;
+                _ = mutexState.TryAcquireOwner(currentThreadId);
             }
-            else if (mutexState.OwnerThreadId != currentThreadId || mutexState.RecursionCount != 1)
+
+            if (mutexState.OwnerThreadId != currentThreadId || mutexState.RecursionCount != 1)
             {
                 return mutexState.OwnerThreadId == currentThreadId
                     ? (int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT
@@ -1467,6 +1630,7 @@ public static class KernelPthreadCompatExports
                 if (node.Value.ThreadId == threadId)
                 {
                     state.Waiters.Remove(node);
+                    state.WaiterRemovedLocked();
                     node.Value.Node = null;
                 }
 
@@ -1481,8 +1645,10 @@ public static class KernelPthreadCompatExports
             WakeKey = cooperative
                 ? wakeKey ?? $"pthread_mutex_waiter:{Interlocked.Increment(ref _nextSynchronizationWaiterId)}"
                 : string.Empty,
+            HostSignal = cooperative ? null : new ManualResetEventSlim(initialState: false),
         };
         waiter.Node = state.Waiters.AddLast(waiter);
+        state.WaiterAddedLocked();
         return waiter;
     }
 
@@ -1492,7 +1658,7 @@ public static class KernelPthreadCompatExports
         var mutex = new PthreadMutexState();
         PthreadMutexWaiter first;
         PthreadMutexWaiter second;
-        lock (mutex)
+        lock (mutex.SyncRoot)
         {
             first = EnqueueMutexWaiterLocked(mutex, 0x101, cooperative: false);
             second = EnqueueMutexWaiterLocked(mutex, 0x202, cooperative: false);
@@ -1536,26 +1702,72 @@ public static class KernelPthreadCompatExports
             return false;
         }
 
+        if (!state.TryAcquireOwner(waiter.ThreadId))
+        {
+            return false;
+        }
+
         state.Waiters.Remove(waiter.Node);
+        state.WaiterRemovedLocked();
         waiter.Node = null;
-        state.OwnerThreadId = waiter.ThreadId;
-        state.RecursionCount = 1;
         Volatile.Write(ref waiter.Granted, 1);
-        Monitor.PulseAll(state);
         return true;
     }
 
+    private static void WakeFirstMutexWaiter(PthreadMutexState state)
+    {
+        PthreadMutexWaiter? nextWaiter;
+        lock (state.SyncRoot)
+        {
+            if (state.OwnerThreadId != 0)
+            {
+                return;
+            }
+
+            nextWaiter = state.Waiters.First?.Value;
+            if (nextWaiter is { Cooperative: false })
+            {
+                nextWaiter.HostSignal!.Set();
+            }
+        }
+
+        if (nextWaiter is { Cooperative: true })
+        {
+            _ = GuestThreadExecution.Scheduler?.WakeBlockedThreads(nextWaiter.WakeKey, 1);
+        }
+    }
+
     private static int WaitForHostMutexLock(PthreadMutexState state, PthreadMutexWaiter waiter)
     {
-        lock (state)
+        ManualResetEventSlim? hostSignal = null;
+        try
         {
-            while (!TryGrantMutexWaiterLocked(state, waiter))
+            while (true)
             {
-                Monitor.Wait(state);
+                lock (state.SyncRoot)
+                {
+                    if (waiter.HostSignal is null)
+                    {
+                        waiter.Cooperative = false;
+                        waiter.HostSignal = new ManualResetEventSlim(initialState: false);
+                    }
+
+                    hostSignal = waiter.HostSignal;
+                    if (TryGrantMutexWaiterLocked(state, waiter))
+                    {
+                        return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+                    }
+
+                    hostSignal.Reset();
+                }
+
+                hostSignal.Wait();
             }
         }
-
-        return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+        finally
+        {
+            hostSignal?.Dispose();
+        }
     }
 
     private static bool TryGrantBlockedMutexLock(
@@ -1566,7 +1778,7 @@ public static class KernelPthreadCompatExports
         PthreadMutexWaiter waiter)
     {
         var granted = false;
-        lock (state)
+        lock (state.SyncRoot)
         {
             granted = TryGrantMutexWaiterLocked(state, waiter);
         }
@@ -1615,7 +1827,7 @@ public static class KernelPthreadCompatExports
         waiter.TimeoutTimer?.Dispose();
         waiter.TimeoutTimer = null;
 
-        lock (waiter.MutexState)
+        lock (waiter.MutexState.SyncRoot)
         {
             waiter.MutexWaiter = EnqueueMutexWaiterLocked(
                 waiter.MutexState,
@@ -1663,7 +1875,7 @@ public static class KernelPthreadCompatExports
             return false;
         }
 
-        lock (waiter.MutexState)
+        lock (waiter.MutexState.SyncRoot)
         {
             return TryGrantMutexWaiterLocked(waiter.MutexState, mutexWaiter);
         }

tests/SharpEmu.Libs.Tests/Memory/PhysicalVirtualMemoryTests.cs

@@ -39,6 +39,60 @@ public sealed class PhysicalVirtualMemoryTests
         Assert.Equal([(page, 0x1000UL, HostPageProtection.ReadWrite)], host.CommitCalls);
     }
 
+    [Fact]
+    public void RepeatedLazyReadUsesCommittedRangeCache()
+    {
+        using var host = new LazyZeroedHostMemory();
+        using var memory = new PhysicalVirtualMemory(host);
+
+        var address = memory.AllocateAt(0, (4UL << 30) + 0x1000, executable: false);
+        host.CommitCalls.Clear();
+
+        Span<byte> buffer = stackalloc byte[16];
+        Assert.True(memory.TryRead(address + 0x100, buffer));
+        var queryCallsAfterFirstRead = host.QueryCalls;
+        Assert.True(memory.TryRead(address + 0x108, buffer[..8]));
+
+        Assert.Equal(queryCallsAfterFirstRead, host.QueryCalls);
+        Assert.Single(host.CommitCalls);
+    }
+
+    [Fact]
+    public void TryCopyHandlesOverlappingIdentityMappedRanges()
+    {
+        using var host = new LazyZeroedHostMemory();
+        using var memory = new PhysicalVirtualMemory(host);
+
+        var address = memory.AllocateAt(0, (4UL << 30) + 0x1000, executable: false);
+        Assert.True(memory.TryWrite(address, new byte[] { 1, 2, 3, 4, 5, 6 }));
+
+        Assert.True(memory.TryCopy(address + 2, address, 4));
+
+        Span<byte> result = stackalloc byte[6];
+        Assert.True(memory.TryRead(address, result));
+        Assert.Equal(new byte[] { 1, 2, 1, 2, 3, 4 }, result.ToArray());
+    }
+
+    [Fact]
+    public void RepeatedTryCopyKeepsSourceAndDestinationCommitRangesCached()
+    {
+        using var host = new LazyZeroedHostMemory();
+        using var memory = new PhysicalVirtualMemory(host);
+
+        var address = memory.AllocateAt(0, (4UL << 30) + 0x1000, executable: false);
+        var source = address + 0x100;
+        var destination = address + 0x1100;
+        Assert.True(memory.TryWrite(source, new byte[] { 1, 2, 3, 4 }));
+        Assert.True(memory.TryWrite(destination, new byte[4]));
+
+        host.CommitCalls.Clear();
+        Assert.True(memory.TryCopy(destination, source, 4));
+        var queryCallsAfterFirstCopy = host.QueryCalls;
+        Assert.True(memory.TryCopy(destination, source, 4));
+
+        Assert.Equal(queryCallsAfterFirstCopy, host.QueryCalls);
+    }
+
     // 2. Reserve-only region: GetPointer commits the page before returning it,
     //    so callers receive a valid (non-null) pointer. An unmapped address yields null.
     [Fact]
@@ -125,12 +179,14 @@ public sealed class PhysicalVirtualMemoryTests
 
         public LazyZeroedHostMemory()
         {
-            _allocation = System.Runtime.InteropServices.NativeMemory.AllocZeroed(0x2000);
+            _allocation = System.Runtime.InteropServices.NativeMemory.AllocZeroed(0x3000);
             _address = ((ulong)_allocation + 0xFFF) & ~0xFFFUL;
         }
 
         public List<(ulong Address, ulong Size, HostPageProtection Protection)> CommitCalls { get; } = [];
 
+        public int QueryCalls { get; private set; }
+
         public ulong Allocate(ulong desiredAddress, ulong size, HostPageProtection protection) => _address;
 
         public ulong Reserve(ulong desiredAddress, ulong size, HostPageProtection protection) => _address;
@@ -162,6 +218,7 @@ public sealed class PhysicalVirtualMemoryTests
 
         public bool Query(ulong address, out HostRegionInfo info)
         {
+            QueryCalls++;
             var pageAddress = address & ~0xFFFUL;
             info = new HostRegionInfo(
                 pageAddress,

tests/SharpEmu.Libs.Tests/Pthread/PthreadMutexSemanticsTests.cs

@@ -10,7 +10,7 @@ namespace SharpEmu.Libs.Tests.Pthread;
 public sealed class PthreadMutexSemanticsTests
 {
     [Fact]
-    public void AdaptiveMutex_SelfLockUsesCompatibilityRecursion()
+    public void AdaptiveMutex_SelfLockIsIdempotent()
     {
         const ulong memoryBase = 0x1_0000_0000;
         const ulong mutexAddress = memoryBase + 0x100;
@@ -22,7 +22,129 @@ public sealed class PthreadMutexSemanticsTests
         Assert.Equal(0, KernelPthreadCompatExports.PthreadMutexLock(context));
         Assert.Equal(0, KernelPthreadCompatExports.PthreadMutexLock(context));
         Assert.Equal(0, KernelPthreadCompatExports.PthreadMutexUnlock(context));
-        Assert.Equal(0, KernelPthreadCompatExports.PthreadMutexUnlock(context));
+        Assert.NotEqual(0, KernelPthreadCompatExports.PthreadMutexUnlock(context));
+    }
+
+    [Fact]
+    public async Task ContendedMutex_HandsOffOneHostWaiterAtATime()
+    {
+        const ulong memoryBase = 0x2_0000_0000;
+        const ulong mutexAddress = memoryBase + 0x100;
+        var memory = new AllocatingCpuMemory(memoryBase, 0x4000);
+        var ownerContext = new CpuContext(memory, Generation.Gen5);
+        Assert.True(ownerContext.TryWriteUInt64(mutexAddress, 1));
+        ownerContext[CpuRegister.Rdi] = mutexAddress;
+        Assert.Equal(0, KernelPthreadCompatExports.PthreadMutexLock(ownerContext));
+
+        using var waitersStarted = new CountdownEvent(2);
+        using var firstAcquired = new ManualResetEventSlim(false);
+        using var secondAcquired = new ManualResetEventSlim(false);
+        using var releaseFirst = new ManualResetEventSlim(false);
+        var acquisitionCount = 0;
+
+        Task<(int LockResult, int UnlockResult)> StartWaiter() =>
+            Task.Factory.StartNew(
+                () =>
+                {
+                    var waiterContext = new CpuContext(memory, Generation.Gen5);
+                    waiterContext[CpuRegister.Rdi] = mutexAddress;
+                    waitersStarted.Signal();
+                    var lockResult = KernelPthreadCompatExports.PthreadMutexLock(waiterContext);
+                    if (lockResult != 0)
+                    {
+                        return (lockResult, int.MinValue);
+                    }
+
+                    if (Interlocked.Increment(ref acquisitionCount) == 1)
+                    {
+                        firstAcquired.Set();
+                        releaseFirst.Wait(TimeSpan.FromSeconds(5));
+                    }
+                    else
+                    {
+                        secondAcquired.Set();
+                    }
+
+                    var unlockResult = KernelPthreadCompatExports.PthreadMutexUnlock(waiterContext);
+                    return (lockResult, unlockResult);
+                },
+                CancellationToken.None,
+                TaskCreationOptions.LongRunning,
+                TaskScheduler.Default);
+
+        var firstWaiter = StartWaiter();
+        var secondWaiter = StartWaiter();
+        Assert.True(waitersStarted.Wait(TimeSpan.FromSeconds(5)));
+        Thread.Sleep(50);
+        Assert.Equal(0, Volatile.Read(ref acquisitionCount));
+
+        Assert.Equal(0, KernelPthreadCompatExports.PthreadMutexUnlock(ownerContext));
+        Assert.True(firstAcquired.Wait(TimeSpan.FromSeconds(5)));
+        Assert.Equal(1, Volatile.Read(ref acquisitionCount));
+        releaseFirst.Set();
+        Assert.True(secondAcquired.Wait(TimeSpan.FromSeconds(5)));
+
+        var results = await Task.WhenAll(firstWaiter, secondWaiter).WaitAsync(TimeSpan.FromSeconds(5));
+        Assert.All(results, result => Assert.Equal((0, 0), result));
+        Assert.Equal(2, Volatile.Read(ref acquisitionCount));
+    }
+
+    [Fact]
+    public async Task ContendedMutex_PreservesMutualExclusionUnderLoad()
+    {
+        const ulong memoryBase = 0x3_0000_0000;
+        const ulong mutexAddress = memoryBase + 0x100;
+        const int workerCount = 4;
+        const int iterationsPerWorker = 250;
+        var memory = new AllocatingCpuMemory(memoryBase, 0x4000);
+        var initializationContext = new CpuContext(memory, Generation.Gen5);
+        Assert.True(initializationContext.TryWriteUInt64(mutexAddress, 1));
+        initializationContext[CpuRegister.Rdi] = mutexAddress;
+        Assert.Equal(0, KernelPthreadCompatExports.PthreadMutexLock(initializationContext));
+        Assert.Equal(0, KernelPthreadCompatExports.PthreadMutexUnlock(initializationContext));
+
+        using var start = new ManualResetEventSlim(false);
+        var insideCriticalSection = 0;
+        var mutualExclusionViolations = 0;
+        var protectedCounter = 0;
+        var workers = Enumerable.Range(0, workerCount)
+            .Select(_ => Task.Factory.StartNew(
+                () =>
+                {
+                    var context = new CpuContext(memory, Generation.Gen5);
+                    context[CpuRegister.Rdi] = mutexAddress;
+                    start.Wait();
+                    for (var iteration = 0; iteration < iterationsPerWorker; iteration++)
+                    {
+                        if (KernelPthreadCompatExports.PthreadMutexLock(context) != 0)
+                        {
+                            throw new InvalidOperationException("pthread mutex lock failed during contention stress.");
+                        }
+
+                        if (Interlocked.Increment(ref insideCriticalSection) != 1)
+                        {
+                            Interlocked.Increment(ref mutualExclusionViolations);
+                        }
+
+                        protectedCounter++;
+                        Thread.SpinWait(20);
+                        Interlocked.Decrement(ref insideCriticalSection);
+
+                        if (KernelPthreadCompatExports.PthreadMutexUnlock(context) != 0)
+                        {
+                            throw new InvalidOperationException("pthread mutex unlock failed during contention stress.");
+                        }
+                    }
+                },
+                CancellationToken.None,
+                TaskCreationOptions.LongRunning,
+                TaskScheduler.Default))
+            .ToArray();
+
+        start.Set();
+        await Task.WhenAll(workers).WaitAsync(TimeSpan.FromSeconds(10));
+        Assert.Equal(0, Volatile.Read(ref mutualExclusionViolations));
+        Assert.Equal(workerCount * iterationsPerWorker, protectedCounter);
     }
 
     private sealed class AllocatingCpuMemory : ICpuMemory, IGuestMemoryAllocator