a731ab3a2a
* 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
254 lines
8.3 KiB
C#
254 lines
8.3 KiB
C#
using Ryujinx.HLE.HOS.Kernel.Process;
|
|
using System;
|
|
using System.Collections.Generic;
|
|
using System.Linq;
|
|
|
|
namespace Ryujinx.HLE.HOS.Kernel.Threading
|
|
{
|
|
partial class KScheduler : IDisposable
|
|
{
|
|
public const int PrioritiesCount = 64;
|
|
public const int CpuCoresCount = 4;
|
|
|
|
private const int PreemptionPriorityCores012 = 59;
|
|
private const int PreemptionPriorityCore3 = 63;
|
|
|
|
private Horizon _system;
|
|
|
|
public KSchedulingData SchedulingData { get; private set; }
|
|
|
|
public KCoreContext[] CoreContexts { get; private set; }
|
|
|
|
public bool ThreadReselectionRequested { get; set; }
|
|
|
|
public KScheduler(Horizon system)
|
|
{
|
|
_system = system;
|
|
|
|
SchedulingData = new KSchedulingData();
|
|
|
|
CoreManager = new HleCoreManager();
|
|
|
|
CoreContexts = new KCoreContext[CpuCoresCount];
|
|
|
|
for (int core = 0; core < CpuCoresCount; core++)
|
|
{
|
|
CoreContexts[core] = new KCoreContext(this, CoreManager);
|
|
}
|
|
}
|
|
|
|
private void PreemptThreads()
|
|
{
|
|
_system.CriticalSection.Enter();
|
|
|
|
PreemptThread(PreemptionPriorityCores012, 0);
|
|
PreemptThread(PreemptionPriorityCores012, 1);
|
|
PreemptThread(PreemptionPriorityCores012, 2);
|
|
PreemptThread(PreemptionPriorityCore3, 3);
|
|
|
|
_system.CriticalSection.Leave();
|
|
}
|
|
|
|
private void PreemptThread(int prio, int core)
|
|
{
|
|
IEnumerable<KThread> scheduledThreads = SchedulingData.ScheduledThreads(core);
|
|
|
|
KThread selectedThread = scheduledThreads.FirstOrDefault(x => x.DynamicPriority == prio);
|
|
|
|
// Yield priority queue.
|
|
if (selectedThread != null)
|
|
{
|
|
SchedulingData.Reschedule(prio, core, selectedThread);
|
|
}
|
|
|
|
IEnumerable<KThread> SuitableCandidates()
|
|
{
|
|
foreach (KThread thread in SchedulingData.SuggestedThreads(core))
|
|
{
|
|
int srcCore = thread.CurrentCore;
|
|
|
|
if (srcCore >= 0)
|
|
{
|
|
KThread highestPrioSrcCore = SchedulingData.ScheduledThreads(srcCore).FirstOrDefault();
|
|
|
|
if (highestPrioSrcCore != null && highestPrioSrcCore.DynamicPriority < 2)
|
|
{
|
|
break;
|
|
}
|
|
|
|
if (highestPrioSrcCore == thread)
|
|
{
|
|
continue;
|
|
}
|
|
}
|
|
|
|
// If the candidate was scheduled after the current thread, then it's not worth it.
|
|
if (selectedThread == null || selectedThread.LastScheduledTime >= thread.LastScheduledTime)
|
|
{
|
|
yield return thread;
|
|
}
|
|
}
|
|
}
|
|
|
|
// Select candidate threads that could run on this core.
|
|
// Only take into account threads that are not yet selected.
|
|
KThread dst = SuitableCandidates().FirstOrDefault(x => x.DynamicPriority == prio);
|
|
|
|
if (dst != null)
|
|
{
|
|
SchedulingData.TransferToCore(prio, core, dst);
|
|
|
|
selectedThread = dst;
|
|
}
|
|
|
|
// If the priority of the currently selected thread is lower than preemption priority,
|
|
// then allow threads with lower priorities to be selected aswell.
|
|
if (selectedThread != null && selectedThread.DynamicPriority > prio)
|
|
{
|
|
Func<KThread, bool> predicate = x => x.DynamicPriority >= selectedThread.DynamicPriority;
|
|
|
|
dst = SuitableCandidates().FirstOrDefault(predicate);
|
|
|
|
if (dst != null)
|
|
{
|
|
SchedulingData.TransferToCore(dst.DynamicPriority, core, dst);
|
|
}
|
|
}
|
|
|
|
ThreadReselectionRequested = true;
|
|
}
|
|
|
|
public void SelectThreads()
|
|
{
|
|
ThreadReselectionRequested = false;
|
|
|
|
for (int core = 0; core < CpuCoresCount; core++)
|
|
{
|
|
KThread thread = SchedulingData.ScheduledThreads(core).FirstOrDefault();
|
|
|
|
CoreContexts[core].SelectThread(thread);
|
|
}
|
|
|
|
for (int core = 0; core < CpuCoresCount; core++)
|
|
{
|
|
// If the core is not idle (there's already a thread running on it),
|
|
// then we don't need to attempt load balancing.
|
|
if (SchedulingData.ScheduledThreads(core).Any())
|
|
{
|
|
continue;
|
|
}
|
|
|
|
int[] srcCoresHighestPrioThreads = new int[CpuCoresCount];
|
|
|
|
int srcCoresHighestPrioThreadsCount = 0;
|
|
|
|
KThread dst = null;
|
|
|
|
// Select candidate threads that could run on this core.
|
|
// Give preference to threads that are not yet selected.
|
|
foreach (KThread thread in SchedulingData.SuggestedThreads(core))
|
|
{
|
|
if (thread.CurrentCore < 0 || thread != CoreContexts[thread.CurrentCore].SelectedThread)
|
|
{
|
|
dst = thread;
|
|
|
|
break;
|
|
}
|
|
|
|
srcCoresHighestPrioThreads[srcCoresHighestPrioThreadsCount++] = thread.CurrentCore;
|
|
}
|
|
|
|
// Not yet selected candidate found.
|
|
if (dst != null)
|
|
{
|
|
// Priorities < 2 are used for the kernel message dispatching
|
|
// threads, we should skip load balancing entirely.
|
|
if (dst.DynamicPriority >= 2)
|
|
{
|
|
SchedulingData.TransferToCore(dst.DynamicPriority, core, dst);
|
|
|
|
CoreContexts[core].SelectThread(dst);
|
|
}
|
|
|
|
continue;
|
|
}
|
|
|
|
// All candidates are already selected, choose the best one
|
|
// (the first one that doesn't make the source core idle if moved).
|
|
for (int index = 0; index < srcCoresHighestPrioThreadsCount; index++)
|
|
{
|
|
int srcCore = srcCoresHighestPrioThreads[index];
|
|
|
|
KThread src = SchedulingData.ScheduledThreads(srcCore).ElementAtOrDefault(1);
|
|
|
|
if (src != null)
|
|
{
|
|
// Run the second thread on the queue on the source core,
|
|
// move the first one to the current core.
|
|
KThread origSelectedCoreSrc = CoreContexts[srcCore].SelectedThread;
|
|
|
|
CoreContexts[srcCore].SelectThread(src);
|
|
|
|
SchedulingData.TransferToCore(origSelectedCoreSrc.DynamicPriority, core, origSelectedCoreSrc);
|
|
|
|
CoreContexts[core].SelectThread(origSelectedCoreSrc);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
public KThread GetCurrentThread()
|
|
{
|
|
lock (CoreContexts)
|
|
{
|
|
for (int core = 0; core < CpuCoresCount; core++)
|
|
{
|
|
if (CoreContexts[core].CurrentThread?.IsCurrentHostThread() ?? false)
|
|
{
|
|
return CoreContexts[core].CurrentThread;
|
|
}
|
|
}
|
|
}
|
|
|
|
return GetDummyThread();
|
|
|
|
throw new InvalidOperationException("Current thread is not scheduled!");
|
|
}
|
|
|
|
private KThread _dummyThread;
|
|
|
|
private KThread GetDummyThread()
|
|
{
|
|
if (_dummyThread != null)
|
|
{
|
|
return _dummyThread;
|
|
}
|
|
|
|
KProcess dummyProcess = new KProcess(_system);
|
|
|
|
KThread dummyThread = new KThread(_system);
|
|
|
|
dummyThread.Initialize(0, 0, 0, 44, 0, dummyProcess, ThreadType.Dummy);
|
|
|
|
return _dummyThread = dummyThread;
|
|
}
|
|
|
|
public KProcess GetCurrentProcess()
|
|
{
|
|
return GetCurrentThread().Owner;
|
|
}
|
|
|
|
public void Dispose()
|
|
{
|
|
Dispose(true);
|
|
}
|
|
|
|
protected virtual void Dispose(bool disposing)
|
|
{
|
|
if (disposing)
|
|
{
|
|
_keepPreempting = false;
|
|
}
|
|
}
|
|
}
|
|
} |