Ryujinx/Ryujinx.HLE/HOS/Kernel/Process/HleProcessDebugger.cs

309 lines
8.9 KiB
C#
Raw Normal View History

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
2019-08-08 20:56:22 +02:00
using ARMeilleure.Memory;
using Ryujinx.HLE.HOS.Diagnostics.Demangler;
using Ryujinx.HLE.HOS.Kernel.Memory;
using Ryujinx.HLE.Loaders.Elf;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Threading;
namespace Ryujinx.HLE.HOS.Kernel.Process
{
class HleProcessDebugger
{
private const int Mod0 = 'M' << 0 | 'O' << 8 | 'D' << 16 | '0' << 24;
private KProcess _owner;
private class Image
{
public long BaseAddress { get; private set; }
public ElfSymbol[] Symbols { get; private set; }
public Image(long baseAddress, ElfSymbol[] symbols)
{
BaseAddress = baseAddress;
Symbols = symbols;
}
}
private List<Image> _images;
private int _loaded;
public HleProcessDebugger(KProcess owner)
{
_owner = owner;
_images = new List<Image>();
}
public string GetGuestStackTrace(ARMeilleure.State.ExecutionContext context)
{
EnsureLoaded();
StringBuilder trace = new StringBuilder();
void AppendTrace(long address)
{
Image image = GetImage(address, out int imageIndex);
if (image == null || !TryGetSubName(image, address, out string subName))
{
subName = $"Sub{address:x16}";
}
else if (subName.StartsWith("_Z"))
{
subName = Demangler.Parse(subName);
}
if (image != null)
{
long offset = address - image.BaseAddress;
string imageName = GetGuessedNsoNameFromIndex(imageIndex);
trace.AppendLine($" {imageName}:0x{offset:x8} {subName}");
}
else
{
trace.AppendLine($" ??? {subName}");
}
}
// TODO: ARM32.
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
2019-08-08 20:56:22 +02:00
long framePointer = (long)context.GetX(29);
trace.AppendLine($"Process: {_owner.Name}, PID: {_owner.Pid}");
while (framePointer != 0)
{
if ((framePointer & 7) != 0 ||
!_owner.CpuMemory.IsMapped(framePointer) ||
!_owner.CpuMemory.IsMapped(framePointer + 8))
{
break;
}
// Note: This is the return address, we need to subtract one instruction
// worth of bytes to get the branch instruction address.
AppendTrace(_owner.CpuMemory.ReadInt64(framePointer + 8) - 4);
framePointer = _owner.CpuMemory.ReadInt64(framePointer);
}
return trace.ToString();
}
private bool TryGetSubName(Image image, long address, out string name)
{
address -= image.BaseAddress;
int left = 0;
int right = image.Symbols.Length - 1;
while (left <= right)
{
int size = right - left;
int middle = left + (size >> 1);
ElfSymbol symbol = image.Symbols[middle];
long endAddr = symbol.Value + symbol.Size;
if ((ulong)address >= (ulong)symbol.Value && (ulong)address < (ulong)endAddr)
{
name = symbol.Name;
return true;
}
if ((ulong)address < (ulong)symbol.Value)
{
right = middle - 1;
}
else
{
left = middle + 1;
}
}
name = null;
return false;
}
private Image GetImage(long address, out int index)
{
lock (_images)
{
for (index = _images.Count - 1; index >= 0; index--)
{
if ((ulong)address >= (ulong)_images[index].BaseAddress)
{
return _images[index];
}
}
}
return null;
}
private string GetGuessedNsoNameFromIndex(int index)
{
if ((uint)index > 11)
{
return "???";
}
if (index == 0)
{
return "rtld";
}
else if (index == 1)
{
return "main";
}
else if (index == GetImagesCount() - 1)
{
return "sdk";
}
else
{
return "subsdk" + (index - 2);
}
}
private int GetImagesCount()
{
lock (_images)
{
return _images.Count;
}
}
private void EnsureLoaded()
{
if (Interlocked.CompareExchange(ref _loaded, 1, 0) == 0)
{
ScanMemoryForTextSegments();
}
}
private void ScanMemoryForTextSegments()
{
ulong oldAddress = 0;
ulong address = 0;
while (address >= oldAddress)
{
KMemoryInfo info = _owner.MemoryManager.QueryMemory(address);
if (info.State == MemoryState.Reserved)
{
break;
}
if (info.State == MemoryState.CodeStatic && info.Permission == MemoryPermission.ReadAndExecute)
{
LoadMod0Symbols(_owner.CpuMemory, (long)info.Address);
}
oldAddress = address;
address = info.Address + info.Size;
}
}
private void LoadMod0Symbols(MemoryManager memory, long textOffset)
{
long mod0Offset = textOffset + memory.ReadUInt32(textOffset + 4);
if (mod0Offset < textOffset || !memory.IsMapped(mod0Offset) || (mod0Offset & 3) != 0)
{
return;
}
Dictionary<ElfDynamicTag, long> dynamic = new Dictionary<ElfDynamicTag, long>();
int mod0Magic = memory.ReadInt32(mod0Offset + 0x0);
if (mod0Magic != Mod0)
{
return;
}
long dynamicOffset = memory.ReadInt32(mod0Offset + 0x4) + mod0Offset;
long bssStartOffset = memory.ReadInt32(mod0Offset + 0x8) + mod0Offset;
long bssEndOffset = memory.ReadInt32(mod0Offset + 0xc) + mod0Offset;
long ehHdrStartOffset = memory.ReadInt32(mod0Offset + 0x10) + mod0Offset;
long ehHdrEndOffset = memory.ReadInt32(mod0Offset + 0x14) + mod0Offset;
long modObjOffset = memory.ReadInt32(mod0Offset + 0x18) + mod0Offset;
// TODO: Elf32.
while (true)
{
long tagVal = memory.ReadInt64(dynamicOffset + 0);
long value = memory.ReadInt64(dynamicOffset + 8);
dynamicOffset += 0x10;
ElfDynamicTag tag = (ElfDynamicTag)tagVal;
if (tag == ElfDynamicTag.DT_NULL)
{
break;
}
dynamic[tag] = value;
}
if (!dynamic.TryGetValue(ElfDynamicTag.DT_STRTAB, out long strTab) ||
!dynamic.TryGetValue(ElfDynamicTag.DT_SYMTAB, out long symTab) ||
!dynamic.TryGetValue(ElfDynamicTag.DT_SYMENT, out long symEntSize))
{
return;
}
long strTblAddr = textOffset + strTab;
long symTblAddr = textOffset + symTab;
List<ElfSymbol> symbols = new List<ElfSymbol>();
while ((ulong)symTblAddr < (ulong)strTblAddr)
{
ElfSymbol sym = GetSymbol(memory, symTblAddr, strTblAddr);
symbols.Add(sym);
symTblAddr += symEntSize;
}
lock (_images)
{
_images.Add(new Image(textOffset, symbols.OrderBy(x => x.Value).ToArray()));
}
}
private ElfSymbol GetSymbol(MemoryManager memory, long address, long strTblAddr)
{
int nameIndex = memory.ReadInt32(address + 0);
int info = memory.ReadByte (address + 4);
int other = memory.ReadByte (address + 5);
int shIdx = memory.ReadInt16(address + 6);
long value = memory.ReadInt64(address + 8);
long size = memory.ReadInt64(address + 16);
string name = string.Empty;
for (int chr; (chr = memory.ReadByte(strTblAddr + nameIndex++)) != 0;)
{
name += (char)chr;
}
return new ElfSymbol(name, info, other, shIdx, value, size);
}
}
}