Ryujinx/Ryujinx.HLE/HOS/ProgramLoader.cs

313 lines
10 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.Common;
using Ryujinx.Common.Logging;
using Ryujinx.HLE.HOS.Kernel.Common;
using Ryujinx.HLE.HOS.Kernel.Memory;
using Ryujinx.HLE.HOS.Kernel.Process;
using Ryujinx.HLE.Loaders.Executables;
using Ryujinx.HLE.Loaders.Npdm;
namespace Ryujinx.HLE.HOS
{
class ProgramLoader
{
private const bool AslrEnabled = true;
private const int ArgsHeaderSize = 8;
private const int ArgsDataSize = 0x9000;
private const int ArgsTotalSize = ArgsHeaderSize + ArgsDataSize;
public static bool LoadKernelInitalProcess(Horizon system, KernelInitialProcess kip)
{
int endOffset = kip.DataOffset + kip.Data.Length;
if (kip.BssSize != 0)
{
endOffset = kip.BssOffset + kip.BssSize;
}
int codeSize = BitUtils.AlignUp(kip.TextOffset + endOffset, KMemoryManager.PageSize);
int codePagesCount = codeSize / KMemoryManager.PageSize;
ulong codeBaseAddress = kip.Addr39Bits ? 0x8000000UL : 0x200000UL;
ulong codeAddress = codeBaseAddress + (ulong)kip.TextOffset;
int mmuFlags = 0;
if (AslrEnabled)
{
// TODO: Randomization.
mmuFlags |= 0x20;
}
if (kip.Addr39Bits)
{
mmuFlags |= (int)AddressSpaceType.Addr39Bits << 1;
}
if (kip.Is64Bits)
{
mmuFlags |= 1;
}
ProcessCreationInfo creationInfo = new ProcessCreationInfo(
kip.Name,
kip.ProcessCategory,
kip.TitleId,
codeAddress,
codePagesCount,
mmuFlags,
0,
0);
MemoryRegion memoryRegion = kip.IsService
? MemoryRegion.Service
: MemoryRegion.Application;
KMemoryRegionManager region = system.MemoryRegions[(int)memoryRegion];
KernelResult result = region.AllocatePages((ulong)codePagesCount, false, out KPageList pageList);
if (result != KernelResult.Success)
{
Logger.PrintError(LogClass.Loader, $"Process initialization returned error \"{result}\".");
return false;
}
KProcess process = new KProcess(system);
result = process.InitializeKip(
creationInfo,
kip.Capabilities,
pageList,
system.ResourceLimit,
memoryRegion);
if (result != KernelResult.Success)
{
Logger.PrintError(LogClass.Loader, $"Process initialization returned error \"{result}\".");
return false;
}
result = LoadIntoMemory(process, kip, codeBaseAddress);
if (result != KernelResult.Success)
{
Logger.PrintError(LogClass.Loader, $"Process initialization returned error \"{result}\".");
return false;
}
process.DefaultCpuCore = kip.DefaultProcessorId;
result = process.Start(kip.MainThreadPriority, (ulong)kip.MainThreadStackSize);
if (result != KernelResult.Success)
{
Logger.PrintError(LogClass.Loader, $"Process start returned error \"{result}\".");
return false;
}
system.Processes.Add(process.Pid, process);
return true;
}
public static bool LoadStaticObjects(
Horizon system,
Npdm metaData,
IExecutable[] staticObjects,
byte[] arguments = null)
{
if (!metaData.Is64Bits)
{
Logger.PrintWarning(LogClass.Loader, "32-bits application detected.");
}
ulong argsStart = 0;
int argsSize = 0;
ulong codeStart = metaData.Is64Bits ? 0x8000000UL : 0x200000UL;
int codeSize = 0;
ulong[] nsoBase = new ulong[staticObjects.Length];
for (int index = 0; index < staticObjects.Length; index++)
{
IExecutable staticObject = staticObjects[index];
int textEnd = staticObject.TextOffset + staticObject.Text.Length;
int roEnd = staticObject.RoOffset + staticObject.Ro.Length;
int dataEnd = staticObject.DataOffset + staticObject.Data.Length + staticObject.BssSize;
int nsoSize = textEnd;
if ((uint)nsoSize < (uint)roEnd)
{
nsoSize = roEnd;
}
if ((uint)nsoSize < (uint)dataEnd)
{
nsoSize = dataEnd;
}
nsoSize = BitUtils.AlignUp(nsoSize, KMemoryManager.PageSize);
nsoBase[index] = codeStart + (ulong)codeSize;
codeSize += nsoSize;
if (arguments != null && argsSize == 0)
{
argsStart = (ulong)codeSize;
argsSize = BitUtils.AlignDown(arguments.Length * 2 + ArgsTotalSize - 1, KMemoryManager.PageSize);
codeSize += argsSize;
}
}
int codePagesCount = codeSize / KMemoryManager.PageSize;
int personalMmHeapPagesCount = metaData.PersonalMmHeapSize / KMemoryManager.PageSize;
ProcessCreationInfo creationInfo = new ProcessCreationInfo(
metaData.TitleName,
metaData.ProcessCategory,
metaData.Aci0.TitleId,
codeStart,
codePagesCount,
metaData.MmuFlags,
0,
personalMmHeapPagesCount);
KernelResult result;
KResourceLimit resourceLimit = new KResourceLimit(system);
long applicationRgSize = (long)system.MemoryRegions[(int)MemoryRegion.Application].Size;
result = resourceLimit.SetLimitValue(LimitableResource.Memory, applicationRgSize);
result |= resourceLimit.SetLimitValue(LimitableResource.Thread, 608);
result |= resourceLimit.SetLimitValue(LimitableResource.Event, 700);
result |= resourceLimit.SetLimitValue(LimitableResource.TransferMemory, 128);
result |= resourceLimit.SetLimitValue(LimitableResource.Session, 894);
if (result != KernelResult.Success)
{
Logger.PrintError(LogClass.Loader, $"Process initialization failed setting resource limit values.");
return false;
}
KProcess process = new KProcess(system);
MemoryRegion memoryRegion = (MemoryRegion)((metaData.Acid.Flags >> 2) & 0xf);
if (memoryRegion > MemoryRegion.NvServices)
{
Logger.PrintError(LogClass.Loader, $"Process initialization failed due to invalid ACID flags.");
return false;
}
result = process.Initialize(
creationInfo,
metaData.Aci0.KernelAccessControl.Capabilities,
resourceLimit,
memoryRegion);
if (result != KernelResult.Success)
{
Logger.PrintError(LogClass.Loader, $"Process initialization returned error \"{result}\".");
return false;
}
for (int index = 0; index < staticObjects.Length; index++)
{
Logger.PrintInfo(LogClass.Loader, $"Loading image {index} at 0x{nsoBase[index]:x16}...");
result = LoadIntoMemory(process, staticObjects[index], nsoBase[index]);
if (result != KernelResult.Success)
{
Logger.PrintError(LogClass.Loader, $"Process initialization returned error \"{result}\".");
return false;
}
}
process.DefaultCpuCore = metaData.DefaultCpuId;
result = process.Start(metaData.MainThreadPriority, (ulong)metaData.MainThreadStackSize);
if (result != KernelResult.Success)
{
Logger.PrintError(LogClass.Loader, $"Process start returned error \"{result}\".");
return false;
}
system.Processes.Add(process.Pid, process);
return true;
}
private static KernelResult LoadIntoMemory(KProcess process, IExecutable image, ulong baseAddress)
{
ulong textStart = baseAddress + (ulong)image.TextOffset;
ulong roStart = baseAddress + (ulong)image.RoOffset;
ulong dataStart = baseAddress + (ulong)image.DataOffset;
ulong bssStart = baseAddress + (ulong)image.BssOffset;
ulong end = dataStart + (ulong)image.Data.Length;
if (image.BssSize != 0)
{
end = bssStart + (ulong)image.BssSize;
}
process.CpuMemory.WriteBytes((long)textStart, image.Text);
process.CpuMemory.WriteBytes((long)roStart, image.Ro);
process.CpuMemory.WriteBytes((long)dataStart, image.Data);
MemoryHelper.FillWithZeros(process.CpuMemory, (long)bssStart, image.BssSize);
KernelResult SetProcessMemoryPermission(ulong address, ulong size, MemoryPermission permission)
{
if (size == 0)
{
return KernelResult.Success;
}
size = BitUtils.AlignUp(size, KMemoryManager.PageSize);
return process.MemoryManager.SetProcessMemoryPermission(address, size, permission);
}
KernelResult result = SetProcessMemoryPermission(textStart, (ulong)image.Text.Length, MemoryPermission.ReadAndExecute);
if (result != KernelResult.Success)
{
return result;
}
result = SetProcessMemoryPermission(roStart, (ulong)image.Ro.Length, MemoryPermission.Read);
if (result != KernelResult.Success)
{
return result;
}
return SetProcessMemoryPermission(dataStart, end - dataStart, MemoryPermission.ReadAndWrite);
}
}
}