mirror of
https://github.com/par274/sharpemu.git
synced 2026-07-26 12:48:39 +08:00
3d2c30b151
* fix(core): implement 4-tier lazy dlsym stub materialization and argument normalization Enforce transactional and thread-safe resolution for standalone ELF bootstrapper pipelines. - Implement a 4-tier additive fallback cascade (T0: runtime symbols, T1: import entries scan, T2: Aerolib mapping, T3: runtime slack-pool lazy stub allocation at 0x7000_0000_0000). - Fix UnmanagedCallersOnly CLR runtime crashes on second bootstrap by adding NormalizeKernelDynlibDlsymArguments to detect and swap mirrored (symbol, handle) register inputs via rigorous pointer bounds verification. - Protect failure paths via CompleteKernelDynlibDlsymFailure, cleanly zero-filling target outputAddress buffers and returns Rax = -1 with zero managed logging execution in hot native paths. * fix(core): harden lazy-stub diagnostics with COW snapshots and deferred bootstrap logging Follow-up to lazy stub pool copy-on-write publishing in TryGetOrCreateLazyImportStub. - Snapshot _importEntries in ProbeReturnRip before near-call and PLT import lookup loops to prevent torn iteration during concurrent array replacement. - Defer SHARPEMU_LOG_BOOTSTRAP output: hot path records raw register slots in a ring buffer under lock; TryReadAsciiZ and Console.Error run only after import handler completion via DrainDeferredBootstrapTraces. - Normalize bootstrap dynlib register order at DispatchImport gateway entry before any logging or trace reads, so swapped RDI/RSI on Import#2 cannot fault the native gateway when bootstrap tracing is enabled. - Resolve lazy stub pool bounds from the full SelfLoader-mapped import region via VirtualQuery instead of a hardcoded 4 KiB cap. - Use ConcurrentDictionary for runtime symbol registration during concurrent dlsym. - Emit distinct [LOADER][WARN] reasons when import stub region resolution fails versus lazy stub pool exhaustion.
432 lines
12 KiB
C#
432 lines
12 KiB
C#
// Copyright (C) 2026 SharpEmu Emulator Project
|
|
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
|
|
using System;
|
|
using System.Collections.Concurrent;
|
|
using System.Collections.Generic;
|
|
using System.Linq;
|
|
using System.Runtime.InteropServices;
|
|
using System.Threading;
|
|
using SharpEmu.HLE;
|
|
using SharpEmu.Logging;
|
|
|
|
namespace SharpEmu.Core.Cpu.Native;
|
|
|
|
public sealed partial class DirectExecutionBackend
|
|
{
|
|
private static readonly ConcurrentDictionary<ulong, byte> _knownExecutablePages = new();
|
|
|
|
private void RecordRecentImportTrace(
|
|
long dispatchIndex,
|
|
string nid,
|
|
ulong returnRip,
|
|
ulong arg0,
|
|
ulong arg1,
|
|
ulong arg2)
|
|
{
|
|
_recentImportTrace[_recentImportTraceWriteIndex] = new RecentImportTraceEntry(
|
|
dispatchIndex,
|
|
nid,
|
|
returnRip,
|
|
arg0,
|
|
arg1,
|
|
arg2);
|
|
_recentImportTraceWriteIndex = (_recentImportTraceWriteIndex + 1) % _recentImportTrace.Length;
|
|
if (_recentImportTraceCount < _recentImportTrace.Length)
|
|
{
|
|
_recentImportTraceCount++;
|
|
}
|
|
}
|
|
|
|
private void RecordDeferredBootstrapTrace(
|
|
long dispatchIndex,
|
|
ulong op,
|
|
ulong symbolPointer,
|
|
ulong outputPointer,
|
|
ulong returnRip)
|
|
{
|
|
lock (_deferredBootstrapTraceGate)
|
|
{
|
|
_deferredBootstrapTrace[_deferredBootstrapTraceWriteIndex] = new DeferredBootstrapTraceEntry(
|
|
dispatchIndex,
|
|
op,
|
|
symbolPointer,
|
|
outputPointer,
|
|
returnRip);
|
|
_deferredBootstrapTraceWriteIndex =
|
|
(_deferredBootstrapTraceWriteIndex + 1) % _deferredBootstrapTrace.Length;
|
|
if (_deferredBootstrapTraceCount < _deferredBootstrapTrace.Length)
|
|
{
|
|
_deferredBootstrapTraceCount++;
|
|
}
|
|
}
|
|
}
|
|
|
|
private void DrainDeferredBootstrapTraces()
|
|
{
|
|
if (!_logBootstrap)
|
|
{
|
|
return;
|
|
}
|
|
|
|
DeferredBootstrapTraceEntry[] pending;
|
|
lock (_deferredBootstrapTraceGate)
|
|
{
|
|
if (_deferredBootstrapTraceCount == 0)
|
|
{
|
|
return;
|
|
}
|
|
|
|
pending = new DeferredBootstrapTraceEntry[_deferredBootstrapTraceCount];
|
|
var readIndex = (_deferredBootstrapTraceWriteIndex - _deferredBootstrapTraceCount +
|
|
_deferredBootstrapTrace.Length) % _deferredBootstrapTrace.Length;
|
|
for (var i = 0; i < _deferredBootstrapTraceCount; i++)
|
|
{
|
|
pending[i] = _deferredBootstrapTrace[(readIndex + i) % _deferredBootstrapTrace.Length];
|
|
}
|
|
|
|
_deferredBootstrapTraceCount = 0;
|
|
}
|
|
|
|
foreach (var entry in pending)
|
|
{
|
|
var symbolText = "<unreadable>";
|
|
if (TryReadAsciiZ(entry.SymbolPointer, 256, out var sym))
|
|
{
|
|
symbolText = sym;
|
|
}
|
|
|
|
Console.Error.WriteLine(
|
|
$"[LOADER][TRACE] bootstrap_call#{entry.DispatchIndex}: op=0x{entry.Op:X16} " +
|
|
$"sym_ptr=0x{entry.SymbolPointer:X16} sym='{symbolText}' " +
|
|
$"out_ptr=0x{entry.OutputPointer:X16} ret=0x{entry.ReturnRip:X16}");
|
|
}
|
|
}
|
|
|
|
private void DumpRecentImportTrace()
|
|
{
|
|
if (_recentImportTraceCount == 0)
|
|
{
|
|
return;
|
|
}
|
|
Log.Info($" Recent import calls ({_recentImportTraceCount}):");
|
|
int num = (_recentImportTraceWriteIndex - _recentImportTraceCount + _recentImportTrace.Length) % _recentImportTrace.Length;
|
|
for (int i = 0; i < _recentImportTraceCount; i++)
|
|
{
|
|
int num2 = (num + i) % _recentImportTrace.Length;
|
|
var entry = _recentImportTrace[num2];
|
|
if (!string.IsNullOrEmpty(entry.Nid))
|
|
{
|
|
Log.Info(
|
|
$" #{entry.DispatchIndex} nid={entry.Nid} ret=0x{entry.ReturnRip:X16} " +
|
|
$"rdi=0x{entry.Arg0:X16} rsi=0x{entry.Arg1:X16} rdx=0x{entry.Arg2:X16}");
|
|
}
|
|
}
|
|
}
|
|
|
|
private unsafe static List<ulong> ScanSuspiciousResolverPointers(ulong scanStart, ulong scanEnd)
|
|
{
|
|
if (scanEnd <= scanStart)
|
|
{
|
|
return new List<ulong>(0);
|
|
}
|
|
int num = 0;
|
|
int num2 = 0;
|
|
List<ulong> list = new List<ulong>(16);
|
|
ulong num3 = scanStart;
|
|
MEMORY_BASIC_INFORMATION64 lpBuffer;
|
|
while (num3 < scanEnd && VirtualQuery((void*)num3, out lpBuffer, (nuint)sizeof(MEMORY_BASIC_INFORMATION64)) != 0)
|
|
{
|
|
ulong baseAddress = lpBuffer.BaseAddress;
|
|
ulong num4 = baseAddress + lpBuffer.RegionSize;
|
|
if (num4 <= num3)
|
|
{
|
|
break;
|
|
}
|
|
ulong value = Math.Max(num3, baseAddress);
|
|
ulong num5 = Math.Min(num4, scanEnd);
|
|
if (lpBuffer.State == 4096 && IsReadableProtection(lpBuffer.Protect) && !IsExecutableProtection(lpBuffer.Protect))
|
|
{
|
|
ulong num6 = AlignUp(value, 8uL);
|
|
for (ulong num7 = num6; num7 + 8 <= num5; num7 += 8)
|
|
{
|
|
ulong value2 = *(ulong*)num7;
|
|
if (IsUnresolvedSentinel(value2))
|
|
{
|
|
num++;
|
|
list.Add(num7);
|
|
if (num2 < 32)
|
|
{
|
|
Log.Info($"Suspicious unresolved pointer: slot=0x{num7:X16} value=0x{value2:X16}");
|
|
num2++;
|
|
}
|
|
if (num >= 16384)
|
|
{
|
|
Log.Warning($"Suspicious unresolved pointer scan reached cap ({16384}); truncating.");
|
|
return list;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
num3 = num5;
|
|
}
|
|
if (num != 0)
|
|
{
|
|
Log.Warning($"Suspicious unresolved pointer hits: {num}");
|
|
}
|
|
return list;
|
|
}
|
|
|
|
private void ProbeReturnRip(ulong returnRip, long dispatchIndex)
|
|
{
|
|
var cpuContext = ActiveCpuContext;
|
|
if (cpuContext == null || returnRip == 0)
|
|
{
|
|
return;
|
|
}
|
|
Span<byte> destination = stackalloc byte[128];
|
|
if (!cpuContext.Memory.TryRead(returnRip, destination))
|
|
{
|
|
Log.Debug($"Import#{dispatchIndex} return-rip probe: unreadable @0x{returnRip:X16}");
|
|
return;
|
|
}
|
|
string value = BitConverter.ToString(destination.ToArray()).Replace("-", " ");
|
|
Log.Debug($"Import#{dispatchIndex} return-rip bytes @0x{returnRip:X16}: {value}");
|
|
if (destination[0] == byte.MaxValue && (destination[1] == 21 || destination[1] == 37))
|
|
{
|
|
int num = BitConverter.ToInt32(destination.Slice(2, 4));
|
|
ulong num2 = returnRip + 6 + (ulong)num;
|
|
if (cpuContext.TryReadUInt64(num2, out var value2))
|
|
{
|
|
Log.Debug($"Import#{dispatchIndex} return-rip slot: [0x{num2:X16}] = 0x{value2:X16}");
|
|
}
|
|
}
|
|
if (destination[0] == 72 && destination[1] == 139 && destination[2] == 5)
|
|
{
|
|
int num3 = BitConverter.ToInt32(destination.Slice(3, 4));
|
|
ulong num4 = returnRip + 7 + (ulong)num3;
|
|
if (cpuContext.TryReadUInt64(num4, out var value3))
|
|
{
|
|
Log.Debug($"Import#{dispatchIndex} return-rip mov-slot: [0x{num4:X16}] = 0x{value3:X16}");
|
|
}
|
|
}
|
|
for (int i = 0; i + 6 <= destination.Length; i++)
|
|
{
|
|
if (destination[i] == byte.MaxValue && (destination[i + 1] == 21 || destination[i + 1] == 37))
|
|
{
|
|
int num5 = BitConverter.ToInt32(destination.Slice(i + 2, 4));
|
|
ulong num6 = returnRip + (ulong)i;
|
|
ulong num7 = num6 + 6 + (ulong)num5;
|
|
if (cpuContext.TryReadUInt64(num7, out var value4))
|
|
{
|
|
Log.Debug($"Import#{dispatchIndex} near-indirect @{num6:X16}: slot=0x{num7:X16} val=0x{value4:X16}");
|
|
}
|
|
}
|
|
}
|
|
Span<byte> targetBytes = stackalloc byte[32];
|
|
for (int i = 0; i + 5 <= destination.Length; i++)
|
|
{
|
|
if (destination[i] != 0xE8)
|
|
{
|
|
continue;
|
|
}
|
|
|
|
int rel32 = BitConverter.ToInt32(destination.Slice(i + 1, 4));
|
|
ulong callRip = returnRip + (ulong)i;
|
|
ulong target = unchecked((ulong)((long)(callRip + 5) + rel32));
|
|
Log.Debug($"Import#{dispatchIndex} near-call @{callRip:X16}: target=0x{target:X16}");
|
|
var importEntries = _importEntries;
|
|
for (int importIndex = 0; importIndex < importEntries.Length; importIndex++)
|
|
{
|
|
if (importEntries[importIndex].Address != target)
|
|
{
|
|
continue;
|
|
}
|
|
|
|
string nid = importEntries[importIndex].Nid;
|
|
if (_moduleManager.TryGetExport(nid, out var export))
|
|
{
|
|
Log.Debug(
|
|
$"Import#{dispatchIndex} near-call import: index={importIndex} {export.LibraryName}:{export.Name} ({nid})");
|
|
}
|
|
else
|
|
{
|
|
Log.Debug(
|
|
$"Import#{dispatchIndex} near-call import: index={importIndex} nid={nid}");
|
|
}
|
|
break;
|
|
}
|
|
|
|
if (cpuContext.Memory.TryRead(target, targetBytes))
|
|
{
|
|
Log.Debug(
|
|
$"Import#{dispatchIndex} near-call target bytes @0x{target:X16}: " +
|
|
BitConverter.ToString(targetBytes.ToArray()).Replace("-", " "));
|
|
if (targetBytes[0] == 0xFF && targetBytes[1] == 0x25)
|
|
{
|
|
int slotRel32 = BitConverter.ToInt32(targetBytes.Slice(2, 4));
|
|
ulong slot = unchecked((ulong)((long)(target + 6) + slotRel32));
|
|
if (cpuContext.TryReadUInt64(slot, out var slotTarget))
|
|
{
|
|
Log.Debug(
|
|
$"Import#{dispatchIndex} near-call PLT slot: [0x{slot:X16}] = 0x{slotTarget:X16}");
|
|
for (int importIndex = 0; importIndex < importEntries.Length; importIndex++)
|
|
{
|
|
if (importEntries[importIndex].Address != slotTarget)
|
|
{
|
|
continue;
|
|
}
|
|
|
|
string nid = importEntries[importIndex].Nid;
|
|
if (_moduleManager.TryGetExport(nid, out var export))
|
|
{
|
|
Log.Debug(
|
|
$"Import#{dispatchIndex} near-call PLT import: index={importIndex} {export.LibraryName}:{export.Name} ({nid})");
|
|
}
|
|
else
|
|
{
|
|
Log.Debug(
|
|
$"Import#{dispatchIndex} near-call PLT import: index={importIndex} nid={nid}");
|
|
}
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
private static bool IsUnresolvedSentinel(ulong value)
|
|
{
|
|
return value == 65534 || value == 4294967294u || value == 18446744073709551614uL;
|
|
}
|
|
|
|
private static bool IsPlausibleReturnAddress(ulong address)
|
|
{
|
|
return address >= 12884901888L && address < 17592186044416L && !IsUnresolvedSentinel(address);
|
|
}
|
|
|
|
private static bool TryGetPlausibleReturnFromStack(ulong rsp, out ulong returnRip, out ulong nextRsp)
|
|
{
|
|
returnRip = 0uL;
|
|
nextRsp = rsp;
|
|
if (rsp <= 65536 || rsp >= 140737488355328L)
|
|
{
|
|
return false;
|
|
}
|
|
ulong num = rsp & 0xFFFFFFFFFFFFFFF8uL;
|
|
ulong num2 = ((num >= 8) ? (num - 8) : num);
|
|
for (int i = 0; i < 24; i++)
|
|
{
|
|
ulong num3 = num2 + (ulong)((long)i * 8L);
|
|
if (TryReadStackU64(num3, out var value) && IsLikelyReturnAddress(value))
|
|
{
|
|
returnRip = value;
|
|
nextRsp = num3 + 8;
|
|
return true;
|
|
}
|
|
}
|
|
for (ulong num4 = 1uL; num4 < 8; num4++)
|
|
{
|
|
for (int j = 0; j < 24; j++)
|
|
{
|
|
ulong num5 = rsp + num4 + (ulong)((long)j * 8L);
|
|
if (TryReadStackU64(num5, out var value2) && IsLikelyReturnAddress(value2))
|
|
{
|
|
returnRip = value2;
|
|
ulong num6 = num5 + 8;
|
|
nextRsp = (num6 + 7) & 0xFFFFFFFFFFFFFFF8uL;
|
|
return true;
|
|
}
|
|
}
|
|
}
|
|
return false;
|
|
}
|
|
|
|
private unsafe static bool TryReadStackU64(ulong address, out ulong value)
|
|
{
|
|
value = 0uL;
|
|
if (address <= 65536 || address >= 140737488355328L)
|
|
{
|
|
return false;
|
|
}
|
|
if (VirtualQuery((void*)address, out var lpBuffer, (nuint)sizeof(MEMORY_BASIC_INFORMATION64)) == 0)
|
|
{
|
|
return false;
|
|
}
|
|
ulong num = lpBuffer.BaseAddress + lpBuffer.RegionSize;
|
|
if (num < lpBuffer.BaseAddress || address > num - 8)
|
|
{
|
|
return false;
|
|
}
|
|
if (lpBuffer.State != 4096 || !IsReadableProtection(lpBuffer.Protect))
|
|
{
|
|
return false;
|
|
}
|
|
try
|
|
{
|
|
value = *(ulong*)address;
|
|
return true;
|
|
}
|
|
catch
|
|
{
|
|
return false;
|
|
}
|
|
}
|
|
|
|
private static bool IsLikelyReturnAddress(ulong address)
|
|
{
|
|
if (!IsPlausibleReturnAddress(address))
|
|
{
|
|
return false;
|
|
}
|
|
return IsExecutableAddress(address);
|
|
}
|
|
|
|
private unsafe static bool IsExecutableAddress(ulong address)
|
|
{
|
|
var pageAddress = address & ~0xFFFUL;
|
|
if (_knownExecutablePages.ContainsKey(pageAddress))
|
|
{
|
|
return true;
|
|
}
|
|
|
|
if (VirtualQuery((void*)address, out var lpBuffer, (nuint)sizeof(MEMORY_BASIC_INFORMATION64)) == 0)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
var executable = lpBuffer.State == 4096 && IsExecutableProtection(lpBuffer.Protect);
|
|
if (executable)
|
|
{
|
|
_knownExecutablePages.TryAdd(pageAddress, 0);
|
|
}
|
|
|
|
return executable;
|
|
}
|
|
|
|
private static ulong AlignUp(ulong value, ulong alignment)
|
|
{
|
|
if (alignment == 0)
|
|
{
|
|
return value;
|
|
}
|
|
ulong num = alignment - 1;
|
|
return (value + num) & ~num;
|
|
}
|
|
|
|
private static bool IsReadableProtection(uint protect)
|
|
{
|
|
if ((protect & 0x100) != 0 || (protect & 1) != 0)
|
|
{
|
|
return false;
|
|
}
|
|
return (protect & 0xEE) != 0;
|
|
}
|
|
|
|
private static bool IsExecutableProtection(uint protect)
|
|
{
|
|
return (protect & 0xF0) != 0;
|
|
}
|
|
}
|