Add a new JIT compiler for CPU code (#693)
* Start of the ARMeilleure project * Refactoring around the old IRAdapter, now renamed to PreAllocator * Optimize the LowestBitSet method * Add CLZ support and fix CLS implementation * Add missing Equals and GetHashCode overrides on some structs, misc small tweaks * Implement the ByteSwap IR instruction, and some refactoring on the assembler * Implement the DivideUI IR instruction and fix 64-bits IDIV * Correct constant operand type on CSINC * Move division instructions implementation to InstEmitDiv * Fix destination type for the ConditionalSelect IR instruction * Implement UMULH and SMULH, with new IR instructions * Fix some issues with shift instructions * Fix constant types for BFM instructions * Fix up new tests using the new V128 struct * Update tests * Move DIV tests to a separate file * Add support for calls, and some instructions that depends on them * Start adding support for SIMD & FP types, along with some of the related ARM instructions * Fix some typos and the divide instruction with FP operands * Fix wrong method call on Clz_V * Implement ARM FP & SIMD move instructions, Saddlv_V, and misc. fixes * Implement SIMD logical instructions and more misc. fixes * Fix PSRAD x86 instruction encoding, TRN, UABD and UABDL implementations * Implement float conversion instruction, merge in LDj3SNuD fixes, and some other misc. fixes * Implement SIMD shift instruction and fix Dup_V * Add SCVTF and UCVTF (vector, fixed-point) variants to the opcode table * Fix check with tolerance on tester * Implement FP & SIMD comparison instructions, and some fixes * Update FCVT (Scalar) encoding on the table to support the Half-float variants * Support passing V128 structs, some cleanup on the register allocator, merge LDj3SNuD fixes * Use old memory access methods, made a start on SIMD memory insts support, some fixes * Fix float constant passed to functions, save and restore non-volatile XMM registers, other fixes * Fix arguments count with struct return values, other fixes * More instructions * Misc. fixes and integrate LDj3SNuD fixes * Update tests * Add a faster linear scan allocator, unwinding support on windows, and other changes * Update Ryujinx.HLE * Update Ryujinx.Graphics * Fix V128 return pointer passing, RCX is clobbered * Update Ryujinx.Tests * Update ITimeZoneService * Stop using GetFunctionPointer as that can't be called from native code, misc. fixes and tweaks * Use generic GetFunctionPointerForDelegate method and other tweaks * Some refactoring on the code generator, assert on invalid operations and use a separate enum for intrinsics * Remove some unused code on the assembler * Fix REX.W prefix regression on float conversion instructions, add some sort of profiler * Add hardware capability detection * Fix regression on Sha1h and revert Fcm** changes * Add SSE2-only paths on vector extract and insert, some refactoring on the pre-allocator * Fix silly mistake introduced on last commit on CpuId * Generate inline stack probes when the stack allocation is too large * Initial support for the System-V ABI * Support multiple destination operands * Fix SSE2 VectorInsert8 path, and other fixes * Change placement of XMM callee save and restore code to match other compilers * Rename Dest to Destination and Inst to Instruction * Fix a regression related to calls and the V128 type * Add an extra space on comments to match code style * Some refactoring * Fix vector insert FP32 SSE2 path * Port over the ARM32 instructions * Avoid memory protection races on JIT Cache * Another fix on VectorInsert FP32 (thanks to LDj3SNuD * Float operands don't need to use the same register when VEX is supported * Add a new register allocator, higher quality code for hot code (tier up), and other tweaks * Some nits, small improvements on the pre allocator * CpuThreadState is gone * Allow changing CPU emulators with a config entry * Add runtime identifiers on the ARMeilleure project * Allow switching between CPUs through a config entry (pt. 2) * Change win10-x64 to win-x64 on projects * Update the Ryujinx project to use ARMeilleure * Ensure that the selected register is valid on the hybrid allocator * Allow exiting on returns to 0 (should fix test regression) * Remove register assignments for most used variables on the hybrid allocator * Do not use fixed registers as spill temp * Add missing namespace and remove unneeded using * Address PR feedback * Fix types, etc * Enable AssumeStrictAbiCompliance by default * Ensure that Spill and Fill don't load or store any more than necessary
This commit is contained in:
gdkchan
emmauss
parent
1ba58e9942
commit
a731ab3a2a
310 changed files with 37389 additions and 2086 deletions
164
ARMeilleure/Translation/JitUnwindWindows.cs
Normal file
164
ARMeilleure/Translation/JitUnwindWindows.cs
Normal file
|
|
@ -0,0 +1,164 @@
|
|||
using ARMeilleure.IntermediateRepresentation;
|
||||
using System;
|
||||
using System.Runtime.InteropServices;
|
||||
|
||||
namespace ARMeilleure.Translation
|
||||
{
|
||||
static class JitUnwindWindows
|
||||
{
|
||||
private const int MaxUnwindCodesArraySize = 9 + 10 * 2 + 3;
|
||||
|
||||
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 UnwindOperation
|
||||
{
|
||||
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))
|
||||
{
|
||||
// Not found.
|
||||
return null;
|
||||
}
|
||||
|
||||
var unwindInfo = funcEntry.UnwindInfo;
|
||||
|
||||
int codeIndex = 0;
|
||||
|
||||
int spOffset = unwindInfo.FixedAllocSize;
|
||||
|
||||
foreach (var entry in unwindInfo.PushEntries)
|
||||
{
|
||||
if (entry.Type == RegisterType.Vector)
|
||||
{
|
||||
spOffset -= 16;
|
||||
}
|
||||
}
|
||||
|
||||
for (int index = unwindInfo.PushEntries.Length - 1; index >= 0; index--)
|
||||
{
|
||||
var entry = unwindInfo.PushEntries[index];
|
||||
|
||||
if (entry.Type == RegisterType.Vector)
|
||||
{
|
||||
ushort uwop = PackUwop(UnwindOperation.SaveXmm128, entry.StreamEndOffset, entry.Index);
|
||||
|
||||
_unwindInfo->UnwindCodes[codeIndex++] = uwop;
|
||||
_unwindInfo->UnwindCodes[codeIndex++] = (ushort)spOffset;
|
||||
|
||||
spOffset += 16;
|
||||
}
|
||||
}
|
||||
|
||||
_unwindInfo->UnwindCodes[0] = PackUwop(UnwindOperation.AllocLarge, unwindInfo.PrologueSize, 1);
|
||||
_unwindInfo->UnwindCodes[1] = (ushort)(unwindInfo.FixedAllocSize >> 0);
|
||||
_unwindInfo->UnwindCodes[2] = (ushort)(unwindInfo.FixedAllocSize >> 16);
|
||||
|
||||
codeIndex += 3;
|
||||
|
||||
for (int index = unwindInfo.PushEntries.Length - 1; index >= 0; index--)
|
||||
{
|
||||
var entry = unwindInfo.PushEntries[index];
|
||||
|
||||
if (entry.Type == RegisterType.Integer)
|
||||
{
|
||||
ushort uwop = PackUwop(UnwindOperation.PushNonvol, entry.StreamEndOffset, entry.Index);
|
||||
|
||||
_unwindInfo->UnwindCodes[codeIndex++] = uwop;
|
||||
}
|
||||
}
|
||||
|
||||
_unwindInfo->VersionAndFlags = 1;
|
||||
_unwindInfo->SizeOfProlog = (byte)unwindInfo.PrologueSize;
|
||||
_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 PackUwop(UnwindOperation uwop, int prologOffset, int opInfo)
|
||||
{
|
||||
return (ushort)(prologOffset | ((int)uwop << 8) | (opInfo << 12));
|
||||
}
|
||||
}
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue