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
This commit is contained in:
Spooks
2026-07-19 13:20:05 -06:00
committed by GitHub
parent 8ef5a54ee4
commit 90c72ebecf
9 changed files with 647 additions and 58 deletions
@@ -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)
@@ -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();
}
@@ -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)
@@ -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,