Ryujinx/ARMeilleure/Translation/JitUnwindWindows.cs
LDj3SNuD 5e724cf24e
Add Profiled Persistent Translation Cache. (#769)
* Delete DelegateTypes.cs

* Delete DelegateCache.cs

* Add files via upload

* Update Horizon.cs

* Update Program.cs

* Update MainWindow.cs

* Update Aot.cs

* Update RelocEntry.cs

* Update Translator.cs

* Update MemoryManager.cs

* Update InstEmitMemoryHelper.cs

* Update Delegates.cs

* Nit.

* Nit.

* Nit.

* 10 fewer MSIL bytes for us

* Add comment. Nits.

* Update Translator.cs

* Update Aot.cs

* Nits.

* Opt..

* Opt..

* Opt..

* Opt..

* Allow to change compression level.

* Update MemoryManager.cs

* Update Translator.cs

* Manage corner cases during the save phase. Nits.

* Update Aot.cs

* Translator response tweak for Aot disabled. Nit.

* Nit.

* Nits.

* Create DelegateHelpers.cs

* Update Delegates.cs

* Nit.

* Nit.

* Nits.

* Fix due to #784.

* Fixes due to #757 & #841.

* Fix due to #846.

* Fix due to #847.

* Use MethodInfo for managed method calls.

Use IR methods instead of managed methods about Max/Min (S/U).
Follow-ups & Nits.

* Add missing exception messages.

Reintroduce slow path for Fmov_Vi.
Implement slow path for Fmov_Si.

* Switch to the new folder structure.

Nits.

* Impl. index-based relocation information. Impl. cache file version field.

* Nit.

* Address gdkchan comments.

Mainly:
- fixed cache file corruption issue on exit; - exposed a way to disable AOT on the GUI.

* Address AcK77 comment.

* Address Thealexbarney, jduncanator & emmauss comments.

Header magic, CpuId (FI) & Aot -> Ptc.

* Adaptation to the new application reloading system.

Improvements to the call system of managed methods.
Follow-ups.
Nits.

* Get the same boot times as on master when PTC is disabled.

* Profiled Aot.

* A32 support (#897).

* #975 support (1 of 2).

* #975 support (2 of 2).

* Rebase fix & nits.

* Some fixes and nits (still one bug left).

* One fix & nits.

* Tests fix (by gdk) & nits.

* Support translations not only in high quality and rejit.

Nits.

* Added possibility to skip translations and continue execution, using `ESC` key.

* Update SettingsWindow.cs

* Update GLRenderer.cs

* Update Ptc.cs

* Disabled Profiled PTC by default as requested in the past by gdk.

* Fix rejit bug. Increased number of parallel translations. Add stack unwinding stuffs support (1 of 2).

Nits.

* Add stack unwinding stuffs support (2 of 2). Tuned number of parallel translations.

* Restored the ability to assemble jumps with 8-bit offset when Profiled PTC is disabled or during profiling.

Modifications due to rebase.
Nits.

* Limited profiling of the functions to be translated to the addresses belonging to the range of static objects only.

* Nits.

* Nits.

* Update Delegates.cs

* Nit.

* Update InstEmitSimdArithmetic.cs

* Address riperiperi comments.

* Fixed the issue of unjustifiably longer boot times at the second boot than at the first boot, measured at the same time or reference point and with the same number of translated functions.

* Implemented a simple redundant load/save mechanism.

Halved the value of Decoder.MaxInstsPerFunction more appropriate for the current performance of the Translator.
Replaced by Logger.PrintError to Logger.PrintDebug in TexturePool.cs about the supposed invalid texture format to avoid the spawn of the log.
Nits.

* Nit.

Improved Logger.PrintError in TexturePool.cs to avoid log spawn.
Added missing code for FZ handling (in output) for fp max/min instructions (slow paths).

* Add configuration migration for PTC

Co-authored-by: Thog <me@thog.eu>
2020-06-16 20:28:02 +02:00

188 lines
6.8 KiB
C#

// https://github.com/MicrosoftDocs/cpp-docs/blob/master/docs/build/exception-handling-x64.md
using ARMeilleure.CodeGen.Unwinding;
using System;
using System.Diagnostics;
using System.Runtime.InteropServices;
namespace ARMeilleure.Translation
{
static class JitUnwindWindows
{
private const int MaxUnwindCodesArraySize = 32; // Must be an even value.
private struct RuntimeFunction
{
public uint BeginAddress;
public uint EndAddress;
public uint UnwindData;
}
private struct UnwindInfo
{
public byte VersionAndFlags;
public byte SizeOfProlog;
public byte CountOfUnwindCodes;
public byte FrameRegister;
public unsafe fixed ushort UnwindCodes[MaxUnwindCodesArraySize];
}
private enum UnwindOp
{
PushNonvol = 0,
AllocLarge = 1,
AllocSmall = 2,
SetFpreg = 3,
SaveNonvol = 4,
SaveNonvolFar = 5,
SaveXmm128 = 8,
SaveXmm128Far = 9,
PushMachframe = 10
}
private unsafe delegate RuntimeFunction* GetRuntimeFunctionCallback(ulong controlPc, IntPtr context);
[DllImport("kernel32.dll", CharSet = CharSet.Unicode)]
private static unsafe extern bool RtlInstallFunctionTableCallback(
ulong tableIdentifier,
ulong baseAddress,
uint length,
GetRuntimeFunctionCallback callback,
IntPtr context,
string outOfProcessCallbackDll);
private static GetRuntimeFunctionCallback _getRuntimeFunctionCallback;
private static int _sizeOfRuntimeFunction;
private unsafe static RuntimeFunction* _runtimeFunction;
private unsafe static UnwindInfo* _unwindInfo;
public static void InstallFunctionTableHandler(IntPtr codeCachePointer, uint codeCacheLength)
{
ulong codeCachePtr = (ulong)codeCachePointer.ToInt64();
_sizeOfRuntimeFunction = Marshal.SizeOf<RuntimeFunction>();
bool result;
unsafe
{
_runtimeFunction = (RuntimeFunction*)codeCachePointer;
_unwindInfo = (UnwindInfo*)(codeCachePointer + _sizeOfRuntimeFunction);
_getRuntimeFunctionCallback = new GetRuntimeFunctionCallback(FunctionTableHandler);
result = RtlInstallFunctionTableCallback(
codeCachePtr | 3,
codeCachePtr,
codeCacheLength,
_getRuntimeFunctionCallback,
codeCachePointer,
null);
}
if (!result)
{
throw new InvalidOperationException("Failure installing function table callback.");
}
}
private static unsafe RuntimeFunction* FunctionTableHandler(ulong controlPc, IntPtr context)
{
int offset = (int)((long)controlPc - context.ToInt64());
if (!JitCache.TryFind(offset, out JitCacheEntry funcEntry))
{
return null; // Not found.
}
var unwindInfo = funcEntry.UnwindInfo;
int codeIndex = 0;
for (int index = unwindInfo.PushEntries.Length - 1; index >= 0; index--)
{
var entry = unwindInfo.PushEntries[index];
switch (entry.PseudoOp)
{
case UnwindPseudoOp.SaveXmm128:
{
int stackOffset = entry.StackOffsetOrAllocSize;
Debug.Assert(stackOffset % 16 == 0);
if (stackOffset <= 0xFFFF0)
{
_unwindInfo->UnwindCodes[codeIndex++] = PackUnwindOp(UnwindOp.SaveXmm128, entry.PrologOffset, entry.RegIndex);
_unwindInfo->UnwindCodes[codeIndex++] = (ushort)(stackOffset / 16);
}
else
{
_unwindInfo->UnwindCodes[codeIndex++] = PackUnwindOp(UnwindOp.SaveXmm128Far, entry.PrologOffset, entry.RegIndex);
_unwindInfo->UnwindCodes[codeIndex++] = (ushort)(stackOffset >> 0);
_unwindInfo->UnwindCodes[codeIndex++] = (ushort)(stackOffset >> 16);
}
break;
}
case UnwindPseudoOp.AllocStack:
{
int allocSize = entry.StackOffsetOrAllocSize;
Debug.Assert(allocSize % 8 == 0);
if (allocSize <= 128)
{
_unwindInfo->UnwindCodes[codeIndex++] = PackUnwindOp(UnwindOp.AllocSmall, entry.PrologOffset, (allocSize / 8) - 1);
}
else if (allocSize <= 0x7FFF8)
{
_unwindInfo->UnwindCodes[codeIndex++] = PackUnwindOp(UnwindOp.AllocLarge, entry.PrologOffset, 0);
_unwindInfo->UnwindCodes[codeIndex++] = (ushort)(allocSize / 8);
}
else
{
_unwindInfo->UnwindCodes[codeIndex++] = PackUnwindOp(UnwindOp.AllocLarge, entry.PrologOffset, 1);
_unwindInfo->UnwindCodes[codeIndex++] = (ushort)(allocSize >> 0);
_unwindInfo->UnwindCodes[codeIndex++] = (ushort)(allocSize >> 16);
}
break;
}
case UnwindPseudoOp.PushReg:
{
_unwindInfo->UnwindCodes[codeIndex++] = PackUnwindOp(UnwindOp.PushNonvol, entry.PrologOffset, entry.RegIndex);
break;
}
default: throw new NotImplementedException($"({nameof(entry.PseudoOp)} = {entry.PseudoOp})");
}
}
Debug.Assert(codeIndex <= MaxUnwindCodesArraySize);
_unwindInfo->VersionAndFlags = 1; // Flags: The function has no handler.
_unwindInfo->SizeOfProlog = (byte)unwindInfo.PrologSize;
_unwindInfo->CountOfUnwindCodes = (byte)codeIndex;
_unwindInfo->FrameRegister = 0;
_runtimeFunction->BeginAddress = (uint)funcEntry.Offset;
_runtimeFunction->EndAddress = (uint)(funcEntry.Offset + funcEntry.Size);
_runtimeFunction->UnwindData = (uint)_sizeOfRuntimeFunction;
return _runtimeFunction;
}
private static ushort PackUnwindOp(UnwindOp op, int prologOffset, int opInfo)
{
return (ushort)(prologOffset | ((int)op << 8) | (opInfo << 12));
}
}
}