Port AVX512 support from TitanEngine

https://github.com/x64dbg/TitanEngine/pull/22

GleeBug/GleeBug.vcxproj

@@ -21,31 +21,32 @@
   <PropertyGroup Label="Globals">
     <ProjectGuid>{B65A3680-9B6B-44E6-A046-649F94DF9F56}</ProjectGuid>
     <RootNamespace>GleeBug</RootNamespace>
+    <WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
     <ConfigurationType>StaticLibrary</ConfigurationType>
     <UseDebugLibraries>true</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
     <ConfigurationType>StaticLibrary</ConfigurationType>
     <UseDebugLibraries>true</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
     <ConfigurationType>StaticLibrary</ConfigurationType>
     <UseDebugLibraries>false</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <WholeProgramOptimization>true</WholeProgramOptimization>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
     <ConfigurationType>StaticLibrary</ConfigurationType>
     <UseDebugLibraries>false</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <WholeProgramOptimization>true</WholeProgramOptimization>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>

GleeBug/ntdll.h

@@ -2511,7 +2511,7 @@ typedef ULONG GDI_HANDLE_BUFFER32[GDI_HANDLE_BUFFER_SIZE32];
 typedef ULONG GDI_HANDLE_BUFFER64[GDI_HANDLE_BUFFER_SIZE64];
 typedef ULONG GDI_HANDLE_BUFFER[GDI_HANDLE_BUFFER_SIZE];
 
-#define FLS_MAXIMUM_AVAILABLE 128
+#define NTDLL_FLS_MAXIMUM_AVAILABLE 128
 #define TLS_MINIMUM_AVAILABLE 64
 #define TLS_EXPANSION_SLOTS 1024
 
@@ -2656,7 +2656,7 @@ typedef struct _PEB
     PVOID* FlsCallback;
     LIST_ENTRY FlsListHead;
     PVOID FlsBitmap;
-    ULONG FlsBitmapBits[FLS_MAXIMUM_AVAILABLE / (sizeof(ULONG) * 8)];
+    ULONG FlsBitmapBits[NTDLL_FLS_MAXIMUM_AVAILABLE / (sizeof(ULONG) * 8)];
     ULONG FlsHighIndex;
 
     PVOID WerRegistrationData;

MyDebugger/MyDebugger.vcxproj

@@ -21,31 +21,32 @@
   <PropertyGroup Label="Globals">
     <ProjectGuid>{4083DE5A-582F-4B15-B6F0-CB866E66F8C4}</ProjectGuid>
     <RootNamespace>MyDebugger</RootNamespace>
+    <WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
     <ConfigurationType>Application</ConfigurationType>
     <UseDebugLibraries>true</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
     <ConfigurationType>Application</ConfigurationType>
     <UseDebugLibraries>true</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
     <ConfigurationType>Application</ConfigurationType>
     <UseDebugLibraries>false</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <WholeProgramOptimization>true</WholeProgramOptimization>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
     <ConfigurationType>Application</ConfigurationType>
     <UseDebugLibraries>false</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <WholeProgramOptimization>true</WholeProgramOptimization>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>

StaticEngine/StaticEngine.vcxproj

@@ -21,31 +21,32 @@
   <PropertyGroup Label="Globals">
     <ProjectGuid>{8E0C7F46-89CC-4510-BC17-07513A31BC7E}</ProjectGuid>
     <RootNamespace>StaticEngine</RootNamespace>
+    <WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
     <ConfigurationType>DynamicLibrary</ConfigurationType>
     <UseDebugLibraries>true</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
     <ConfigurationType>DynamicLibrary</ConfigurationType>
     <UseDebugLibraries>true</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
     <ConfigurationType>DynamicLibrary</ConfigurationType>
     <UseDebugLibraries>false</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <WholeProgramOptimization>true</WholeProgramOptimization>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
     <ConfigurationType>DynamicLibrary</ConfigurationType>
     <UseDebugLibraries>false</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <WholeProgramOptimization>true</WholeProgramOptimization>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>

StaticEngine/TitanEngine.h

@@ -599,6 +599,12 @@ typedef struct
     XmmRegister_t High; //AVX part
 } YmmRegister_t;
 
+typedef struct
+{
+	YmmRegister_t Low; //AVX part
+	YmmRegister_t High; //AVX-512 part
+} ZmmRegister_t;
+
 typedef struct
 {
     BYTE    data[10];
@@ -664,6 +670,16 @@ typedef struct
 #endif
 } TITAN_ENGINE_CONTEXT_t;
 
+typedef struct
+{
+#ifdef _WIN64
+    ZmmRegister_t ZmmRegisters[32];
+#else // x86
+    ZmmRegister_t ZmmRegisters[8];
+#endif
+    ULONGLONG Opmask[8];
+} TITAN_ENGINE_CONTEXT_AVX512_t;
+
 #ifdef __cplusplus
 extern "C"
 {
@@ -853,6 +869,8 @@ __declspec(dllexport) bool TITCALL SetContextDataEx(HANDLE hActiveThread, DWORD
 __declspec(dllexport) bool TITCALL SetContextData(DWORD IndexOfRegister, ULONG_PTR NewRegisterValue);
 __declspec(dllexport) bool TITCALL GetAVXContext(HANDLE hActiveThread, TITAN_ENGINE_CONTEXT_t* titcontext);
 __declspec(dllexport) bool TITCALL SetAVXContext(HANDLE hActiveThread, TITAN_ENGINE_CONTEXT_t* titcontext);
+__declspec(dllexport) bool TITCALL GetAVX512Context(HANDLE hActiveThread, TITAN_ENGINE_CONTEXT_AVX512_t* titcontext);
+__declspec(dllexport) bool TITCALL SetAVX512Context(HANDLE hActiveThread, TITAN_ENGINE_CONTEXT_AVX512_t* titcontext);
 __declspec(dllexport) void TITCALL ClearExceptionNumber();
 __declspec(dllexport) long TITCALL CurrentExceptionNumber();
 __declspec(dllexport) bool TITCALL MatchPatternEx(HANDLE hProcess, void* MemoryToCheck, int SizeOfMemoryToCheck, void* PatternToMatch, int SizeOfPatternToMatch, PBYTE WildCard);

StaticEngine/TitanEngineEmulator.cpp

@@ -171,6 +171,16 @@ __declspec(dllexport) void TITCALL Getx87FPURegisters(x87FPURegister_t x87FPUReg
     emu.Getx87FPURegisters(x87FPURegisters, titcontext);
 }
 
+__declspec(dllexport) bool TITCALL GetAVX512Context(HANDLE hActiveThread, TITAN_ENGINE_CONTEXT_AVX512_t* titcontext)
+{
+    return false;
+}
+
+__declspec(dllexport) bool TITCALL SetAVX512Context(HANDLE hActiveThread, TITAN_ENGINE_CONTEXT_AVX512_t* titcontext)
+{
+    return false;
+}
+
 //PE
 __declspec(dllexport) bool TITCALL StaticFileLoad(const char* szFileName, DWORD DesiredAccess, bool SimulateLoad, LPHANDLE FileHandle, LPDWORD LoadedSize, LPHANDLE FileMap, PULONG_PTR FileMapVA)
 {

TitanEngineEmulator/Emulator.h

@@ -1170,18 +1170,32 @@ private: //functions
         return dwLastError;
     }
 
+    static DWORD GetNtBuildNumberWindows7()
+    {
+        auto p_RtlGetVersion = (NTSTATUS(WINAPI*)(PRTL_OSVERSIONINFOW))GetProcAddress(GetModuleHandleW(L"ntdll.dll"), "RtlGetVersion");
+        RTL_OSVERSIONINFOW info = { sizeof(info) };
+        if (p_RtlGetVersion && p_RtlGetVersion(&info) == 0)
+            return info.dwBuildNumber;
+        else
+            return 0;
+    }
+
+    static DWORD GetNtBuildNumber()
+    {
+        // https://www.vergiliusproject.com/kernels/x64/Windows%2010%20%7C%202016/1507%20Threshold%201/_KUSER_SHARED_DATA
+        auto NtBuildNumber = *(DWORD*)(0x7FFE0000 + 0x260);
+        if (NtBuildNumber == 0)
+        {
+            // Older versions of Windows
+            static DWORD NtBuildNumber7 = GetNtBuildNumberWindows7();
+            NtBuildNumber = NtBuildNumber7;
+        }
+        return NtBuildNumber;
+    }
+
     static bool isAtleastVista()
     {
-        static bool isAtleastVista = false;
+        return GetNtBuildNumber() >= 6000;
-        static bool isSet = false;
-        if(isSet)
-            return isAtleastVista;
-        OSVERSIONINFO versionInfo = { 0 };
-        versionInfo.dwOSVersionInfoSize = sizeof(OSVERSIONINFO);
-        GetVersionEx(&versionInfo);
-        isAtleastVista = versionInfo.dwMajorVersion >= 6;
-        isSet = true;
-        return isAtleastVista;
     }
 
     //Quote from The Ultimate Anti-Debugging Reference by Peter Ferrie

TitanEngineEmulator/TitanEngine.h

@@ -603,6 +603,12 @@ typedef struct
     XmmRegister_t High; //AVX part
 } YmmRegister_t;
 
+typedef struct
+{
+    YmmRegister_t Low; //AVX part
+    YmmRegister_t High; //AVX-512 part
+} ZmmRegister_t;
+
 typedef struct
 {
     BYTE    data[10];
@@ -668,6 +674,16 @@ typedef struct
 #endif
 } TITAN_ENGINE_CONTEXT_t;
 
+typedef struct
+{
+#ifdef _WIN64
+    ZmmRegister_t ZmmRegisters[32];
+#else // x86
+    ZmmRegister_t ZmmRegisters[8];
+#endif
+    ULONGLONG Opmask[8];
+} TITAN_ENGINE_CONTEXT_AVX512_t;
+
 #ifdef __cplusplus
 extern "C"
 {
@@ -859,6 +875,8 @@ __declspec(dllexport) bool TITCALL SetContextDataEx(HANDLE hActiveThread, DWORD
 __declspec(dllexport) bool TITCALL SetContextData(DWORD IndexOfRegister, ULONG_PTR NewRegisterValue);
 __declspec(dllexport) bool TITCALL GetAVXContext(HANDLE hActiveThread, TITAN_ENGINE_CONTEXT_t* titcontext);
 __declspec(dllexport) bool TITCALL SetAVXContext(HANDLE hActiveThread, TITAN_ENGINE_CONTEXT_t* titcontext);
+__declspec(dllexport) bool TITCALL GetAVX512Context(HANDLE hActiveThread, TITAN_ENGINE_CONTEXT_AVX512_t* titcontext);
+__declspec(dllexport) bool TITCALL SetAVX512Context(HANDLE hActiveThread, TITAN_ENGINE_CONTEXT_AVX512_t* titcontext);
 __declspec(dllexport) void TITCALL ClearExceptionNumber();
 __declspec(dllexport) long TITCALL CurrentExceptionNumber();
 __declspec(dllexport) bool TITCALL MatchPatternEx(HANDLE hProcess, void* MemoryToCheck, int SizeOfMemoryToCheck, void* PatternToMatch, int SizeOfPatternToMatch, PBYTE WildCard);

TitanEngineEmulator/TitanEngineEmulator.cpp

@@ -184,6 +184,203 @@ __declspec(dllexport) void TITCALL Getx87FPURegisters(x87FPURegister_t x87FPUReg
     emu.Getx87FPURegisters(x87FPURegisters, titcontext);
 }
 
+// AVX-512 constants
+#ifndef XSTATE_MASK_AVX512
+#define XSTATE_AVX512_KMASK                 (5)
+#define XSTATE_AVX512_ZMM_H                 (6)
+#define XSTATE_AVX512_ZMM                   (7)
+#define XSTATE_MASK_AVX512                  ((1ui64 << (XSTATE_AVX512_KMASK)) | \
+                                             (1ui64 << (XSTATE_AVX512_ZMM_H)) | \
+                                             (1ui64 << (XSTATE_AVX512_ZMM)))
+#endif
+
+static bool SetAVX512ContextFallbackToAVX(HANDLE hActiveThread, TITAN_ENGINE_CONTEXT_AVX512_t* titcontext) {
+	// Fall back to using AVX and ignore the rest
+	TITAN_ENGINE_CONTEXT_t Avx;
+	memset(&Avx, 0, sizeof(Avx));
+	for (int i = 0; i < _countof(Avx.YmmRegisters); i++) {
+		Avx.YmmRegisters[i] = titcontext->ZmmRegisters[i].Low;
+	}
+	return SetAVXContext(hActiveThread, &Avx);
+}
+
+__declspec(dllexport) bool TITCALL SetAVX512Context(HANDLE hActiveThread, TITAN_ENGINE_CONTEXT_AVX512_t* titcontext)
+{
+	if (InitXState() == false)
+		return false;
+
+	DWORD64 FeatureMask = _GetEnabledXStateFeatures();
+	if ((FeatureMask & XSTATE_MASK_AVX512) == 0)
+		return SetAVX512ContextFallbackToAVX(hActiveThread, titcontext);
+
+	DWORD ContextSize = 0;
+	BOOL Success = _InitializeContext(NULL,
+		CONTEXT_ALL | CONTEXT_XSTATE,
+		NULL,
+		&ContextSize);
+
+	if ((Success == TRUE) || (GetLastError() != ERROR_INSUFFICIENT_BUFFER))
+		return false;
+
+    std::vector<uint8_t> dataBuffer(ContextSize);
+
+	PCONTEXT Context;
+	Success = _InitializeContext(dataBuffer.data(),
+		CONTEXT_ALL | CONTEXT_XSTATE,
+		&Context,
+		&ContextSize);
+	if (Success == FALSE)
+		return false;
+
+	if (_SetXStateFeaturesMask(Context, XSTATE_MASK_AVX | XSTATE_MASK_AVX512) == FALSE)
+		return SetAVX512ContextFallbackToAVX(hActiveThread, titcontext);
+
+	if (GetThreadContext(hActiveThread, Context) == FALSE)
+		return false;
+
+	if (_GetXStateFeaturesMask(Context, &FeatureMask) == FALSE)
+		return false;
+
+	DWORD FeatureLengthSse;
+	DWORD FeatureLengthAvx;
+	DWORD FeatureLengthAvx512_KMASK;
+	DWORD FeatureLengthAvx512_ZMM_H;
+	DWORD FeatureLengthAvx512_ZMM;
+	XmmRegister_t* Sse = (XmmRegister_t*)_LocateXStateFeature(Context, XSTATE_LEGACY_SSE, &FeatureLengthSse);
+	XmmRegister_t* Avx = (XmmRegister_t*)_LocateXStateFeature(Context, XSTATE_AVX, &FeatureLengthAvx);
+	ULONGLONG* Avx512_KMASK = (ULONGLONG*)_LocateXStateFeature(Context, XSTATE_AVX512_KMASK, &FeatureLengthAvx512_KMASK);
+	ZmmRegister_t* Avx512_ZMM = (ZmmRegister_t *)_LocateXStateFeature(Context, XSTATE_AVX512_ZMM, &FeatureLengthAvx512_ZMM);
+	YmmRegister_t* Avx512_ZMM_H = (YmmRegister_t *)_LocateXStateFeature(Context, XSTATE_AVX512_ZMM_H, &FeatureLengthAvx512_ZMM_H);
+
+	if (Sse != NULL) //If the feature is unsupported by the processor it will return NULL
+	{
+		for (size_t i = 0; i < MIN(FeatureLengthSse / sizeof(XmmRegister_t), _countof(titcontext->ZmmRegisters)); i++)
+			Sse[i] = titcontext->ZmmRegisters[i].Low.Low;
+	}
+
+	if (Avx != NULL) //If the feature is unsupported by the processor it will return NULL
+	{
+		for (size_t i = 0; i < MIN(FeatureLengthAvx / sizeof(XmmRegister_t), _countof(titcontext->ZmmRegisters)); i++)
+			Avx[i] = titcontext->ZmmRegisters[i].Low.High;
+	}
+
+	if (Avx512_ZMM_H != NULL) //If the feature is unsupported by the processor it will return NULL
+	{
+		for (size_t i = 0; i < MIN(FeatureLengthAvx512_ZMM_H / sizeof(YmmRegister_t), _countof(titcontext->ZmmRegisters)); i++)
+			Avx512_ZMM_H[i] = titcontext->ZmmRegisters[i].High;
+	}
+
+	if (Avx512_ZMM != NULL) //If the feature is unsupported by the processor it will return NULL
+	{
+		for (size_t i = 0; i < MIN(FeatureLengthAvx512_ZMM / sizeof(ZmmRegister_t), _countof(titcontext->ZmmRegisters) - FeatureLengthAvx / sizeof(XmmRegister_t)); i++)
+			Avx512_ZMM[i] = titcontext->ZmmRegisters[i + FeatureLengthAvx / sizeof(XmmRegister_t)];
+	}
+
+	if (Avx512_KMASK != NULL) //If the feature is unsupported by the processor it will return NULL
+	{
+		for (size_t i = 0; i < MIN(FeatureLengthAvx512_KMASK / sizeof(ULONGLONG), _countof(titcontext->Opmask)); i++)
+			Avx512_KMASK[i] = titcontext->Opmask[i];
+	}
+
+	return (SetThreadContext(hActiveThread, Context) == TRUE);
+}
+
+static bool GetAVX512ContextFallbackToAVX(HANDLE hActiveThread, TITAN_ENGINE_CONTEXT_AVX512_t* titcontext)
+{
+	// Fall back to using AVX and fill the rest with 0
+	TITAN_ENGINE_CONTEXT_t Avx;
+	memset(&Avx, 0, sizeof(Avx));
+	if (GetAVXContext(hActiveThread, &Avx)) {
+		for (int i = 0; i < _countof(Avx.YmmRegisters); i++)
+			titcontext->ZmmRegisters[i].Low = Avx.YmmRegisters[i];
+		return true;
+	}
+	else {
+		return false;
+	}
+}
+
+__declspec(dllexport) bool TITCALL GetAVX512Context(HANDLE hActiveThread, TITAN_ENGINE_CONTEXT_AVX512_t* titcontext)
+{
+	if (InitXState() == false)
+		return false;
+
+	DWORD64 FeatureMask = _GetEnabledXStateFeatures();
+	if ((FeatureMask & XSTATE_MASK_AVX512) == 0) //XSTATE_MASK_AVX512
+		return GetAVX512ContextFallbackToAVX(hActiveThread, titcontext);
+
+	DWORD ContextSize = 0;
+	BOOL Success = _InitializeContext(NULL,
+		CONTEXT_ALL | CONTEXT_XSTATE,
+		NULL,
+		&ContextSize);
+
+	if ((Success == TRUE) || (GetLastError() != ERROR_INSUFFICIENT_BUFFER))
+		return false;
+
+    std::vector<uint8_t> dataBuffer(ContextSize);
+
+	PCONTEXT Context;
+	Success = _InitializeContext(dataBuffer.data(),
+		CONTEXT_ALL | CONTEXT_XSTATE,
+		&Context,
+		&ContextSize);
+	if (Success == FALSE)
+		return false;
+
+	if (_SetXStateFeaturesMask(Context, XSTATE_MASK_AVX | XSTATE_MASK_AVX512) == FALSE)
+		return GetAVX512ContextFallbackToAVX(hActiveThread, titcontext);
+
+	if (GetThreadContext(hActiveThread, Context) == FALSE)
+		return false;
+
+	if (_GetXStateFeaturesMask(Context, &FeatureMask) == FALSE)
+		return false;
+
+	DWORD FeatureLengthSse;
+	DWORD FeatureLengthAvx;
+	DWORD FeatureLengthAvx512_KMASK;
+	DWORD FeatureLengthAvx512_ZMM_H;
+	DWORD FeatureLengthAvx512_ZMM;
+	XmmRegister_t* Sse = (XmmRegister_t*)_LocateXStateFeature(Context, XSTATE_LEGACY_SSE, &FeatureLengthSse);
+	XmmRegister_t* Avx = (XmmRegister_t*)_LocateXStateFeature(Context, XSTATE_AVX, &FeatureLengthAvx);
+	ULONGLONG* Avx512_KMASK = (ULONGLONG*)_LocateXStateFeature(Context, XSTATE_AVX512_KMASK, &FeatureLengthAvx512_KMASK);
+	ZmmRegister_t* Avx512_ZMM = (ZmmRegister_t *)_LocateXStateFeature(Context, XSTATE_AVX512_ZMM, &FeatureLengthAvx512_ZMM);
+	YmmRegister_t* Avx512_ZMM_H = (YmmRegister_t *)_LocateXStateFeature(Context, XSTATE_AVX512_ZMM_H, &FeatureLengthAvx512_ZMM_H);
+
+	if (Sse != NULL) //If the feature is unsupported by the processor it will return NULL
+	{
+		for (size_t i = 0; i < MIN(FeatureLengthSse / sizeof(XmmRegister_t), _countof(titcontext->ZmmRegisters)); i++)
+			titcontext->ZmmRegisters[i].Low.Low = Sse[i];
+	}
+
+	if (Avx != NULL) //If the feature is unsupported by the processor it will return NULL
+	{
+		for (size_t i = 0; i < MIN(FeatureLengthAvx / sizeof(XmmRegister_t), _countof(titcontext->ZmmRegisters)); i++)
+			titcontext->ZmmRegisters[i].Low.High = Avx[i];
+	}
+
+	if (Avx512_ZMM_H != NULL) //If the feature is unsupported by the processor it will return NULL
+	{
+		for (size_t i = 0; i < MIN(FeatureLengthAvx512_ZMM_H / sizeof(YmmRegister_t), _countof(titcontext->ZmmRegisters)); i++)
+			titcontext->ZmmRegisters[i].High = Avx512_ZMM_H[i];
+	}
+
+	if (Avx512_ZMM != NULL) //If the feature is unsupported by the processor it will return NULL
+	{
+		for (size_t i = 0; i < MIN(FeatureLengthAvx512_ZMM / sizeof(ZmmRegister_t), _countof(titcontext->ZmmRegisters) - FeatureLengthAvx / sizeof(XmmRegister_t)); i++)
+			titcontext->ZmmRegisters[i + FeatureLengthAvx / sizeof(XmmRegister_t)] = Avx512_ZMM[i];
+	}
+
+	if (Avx512_KMASK != NULL) //If the feature is unsupported by the processor it will return NULL
+	{
+		for (size_t i = 0; i < MIN(FeatureLengthAvx512_KMASK / sizeof(ULONGLONG), _countof(titcontext->Opmask)); i++)
+			titcontext->Opmask[i] = Avx512_KMASK[i];
+	}
+
+	return true;
+}
+
 //PE
 __declspec(dllexport) bool TITCALL StaticFileLoad(const char* szFileName, DWORD DesiredAccess, bool SimulateLoad, LPHANDLE FileHandle, LPDWORD LoadedSize, LPHANDLE FileMap, PULONG_PTR FileMapVA)
 {

TitanEngineEmulator/TitanEngineEmulator.vcxproj

@@ -21,31 +21,32 @@
   <PropertyGroup Label="Globals">
     <ProjectGuid>{2790D540-B51E-48F1-B8E9-F14F2EEAA676}</ProjectGuid>
     <RootNamespace>TitanEngineEmulator</RootNamespace>
+    <WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
     <ConfigurationType>DynamicLibrary</ConfigurationType>
     <UseDebugLibraries>true</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
     <ConfigurationType>DynamicLibrary</ConfigurationType>
     <UseDebugLibraries>true</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
     <ConfigurationType>DynamicLibrary</ConfigurationType>
     <UseDebugLibraries>false</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <WholeProgramOptimization>true</WholeProgramOptimization>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
     <ConfigurationType>DynamicLibrary</ConfigurationType>
     <UseDebugLibraries>false</UseDebugLibraries>
-    <PlatformToolset>v140_xp</PlatformToolset>
+    <PlatformToolset>v141_xp</PlatformToolset>
     <WholeProgramOptimization>true</WholeProgramOptimization>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>

TitanEngineEmulator/ntdll.h

@@ -2511,9 +2511,9 @@ typedef ULONG GDI_HANDLE_BUFFER32[GDI_HANDLE_BUFFER_SIZE32];
 typedef ULONG GDI_HANDLE_BUFFER64[GDI_HANDLE_BUFFER_SIZE64];
 typedef ULONG GDI_HANDLE_BUFFER[GDI_HANDLE_BUFFER_SIZE];
 
-#define FLS_MAXIMUM_AVAILABLE 128
+#define NTDLL_FLS_MAXIMUM_AVAILABLE 128
-#define TLS_MINIMUM_AVAILABLE 64
+#define NTDLL_TLS_MINIMUM_AVAILABLE 64
-#define TLS_EXPANSION_SLOTS 1024
+#define NTDLL_TLS_EXPANSION_SLOTS 1024
 
 typedef struct _PEB_LDR_DATA
 {
@@ -2656,7 +2656,7 @@ typedef struct _PEB
     PVOID* FlsCallback;
     LIST_ENTRY FlsListHead;
     PVOID FlsBitmap;
-    ULONG FlsBitmapBits[FLS_MAXIMUM_AVAILABLE / (sizeof(ULONG) * 8)];
+    ULONG FlsBitmapBits[NTDLL_FLS_MAXIMUM_AVAILABLE / (sizeof(ULONG) * 8)];
     ULONG FlsHighIndex;
 
     PVOID WerRegistrationData;