Ryujinx/ARMeilleure/Instructions/NativeInterface.cs
riperiperi b4d8d893a4
Memory Read/Write Tracking using Region Handles (#1272)
* WIP Range Tracking

- Texture invalidation seems to have large problems
- Buffer/Pool invalidation may have problems
- Mirror memory tracking puts an additional `add` in compiled code, we likely just want to make HLE access slower if this is the final solution.
- Native project is in the messiest possible location.
- [HACK] JIT memory access always uses native "fast" path
- [HACK] Trying some things with texture invalidation and views.

It works :)

Still a few hacks, messy things, slow things

More work in progress stuff (also move to memory project)

Quite a bit faster now.
- Unmapping GPU VA and CPU VA will now correctly update write tracking regions, and invalidate textures for the former.
- The Virtual range list is now non-overlapping like the physical one.
- Fixed some bugs where regions could leak.
- Introduced a weird bug that I still need to track down (consistent invalid buffer in MK8 ribbon road)

Move some stuff.

I think we'll eventually just put the dll and so for this in a nuget package.

Fix rebase.

[WIP] MultiRegionHandle variable size ranges

- Avoid reprotecting regions that change often (needs some tweaking)
- There's still a bug in buffers, somehow.
- Might want different api for minimum granularity

Fix rebase issue

Commit everything needed for software only tracking.

Remove native components.

Remove more native stuff.

Cleanup

Use a separate window for the background context, update opentk. (fixes linux)

Some experimental changes

Should get things working up to scratch - still need to try some things with flush/modification and res scale.

Include address with the region action.

Initial work to make range tracking work

Still a ton of bugs

Fix some issues with the new stuff.

* Fix texture flush instability

There's still some weird behaviour, but it's much improved without this. (textures with cpu modified data were flushing over it)

* Find the destination texture for Buffer->Texture full copy

Greatly improves performance for nvdec videos (with range tracking)

* Further improve texture tracking

* Disable Memory Tracking for view parents

This is a temporary approach to better match behaviour on master (where invalidations would be soaked up by views, rather than trigger twice)

The assumption is that when views are created to a texture, they will cover all of its data anyways. Of course, this can easily be improved in future.

* Introduce some tracking tests.

WIP

* Complete base tests.

* Add more tests for multiregion, fix existing test.

* Cleanup Part 1

* Remove unnecessary code from memory tracking

* Fix some inconsistencies with 3D texture rule.

* Add dispose tests.

* Use a background thread for the background context.

Rather than setting and unsetting a context as current, doing the work on a dedicated thread with signals seems to be a bit faster.

Also nerf the multithreading test a bit.

* Copy to texture with matching alignment

This extends the copy to work for some videos with unusual size, such as tutorial videos in SMO. It will only occur if the destination texture already exists at XCount size.

* Track reads for buffer copies. Synchronize new buffers before copying overlaps.

* Remove old texture flushing mechanisms.

Range tracking all the way, baby.

* Wake the background thread when disposing.

Avoids a deadlock when games are closed.

* Address Feedback 1

* Separate TextureCopy instance for background thread

Also `BackgroundContextWorker.InBackground` for a more sensible idenfifier for if we're in a background thread.

* Add missing XML docs.

* Address Feedback

* Maybe I should start drinking coffee.

* Some more feedback.

* Remove flush warning, Refocus window after making background context
2020-10-16 17:18:35 -03:00

272 lines
6.9 KiB
C#

using ARMeilleure.Memory;
using ARMeilleure.State;
using ARMeilleure.Translation;
using System;
using System.Runtime.InteropServices;
namespace ARMeilleure.Instructions
{
static class NativeInterface
{
private class ThreadContext
{
public ExecutionContext Context { get; }
public IMemoryManager Memory { get; }
public Translator Translator { get; }
public ThreadContext(ExecutionContext context, IMemoryManager memory, Translator translator)
{
Context = context;
Memory = memory;
Translator = translator;
}
}
[ThreadStatic]
private static ThreadContext _context;
public static void RegisterThread(ExecutionContext context, IMemoryManager memory, Translator translator)
{
_context = new ThreadContext(context, memory, translator);
}
public static void UnregisterThread()
{
_context = null;
}
public static void Break(ulong address, int imm)
{
Statistics.PauseTimer();
GetContext().OnBreak(address, imm);
Statistics.ResumeTimer();
}
public static void SupervisorCall(ulong address, int imm)
{
Statistics.PauseTimer();
GetContext().OnSupervisorCall(address, imm);
Statistics.ResumeTimer();
}
public static void Undefined(ulong address, int opCode)
{
Statistics.PauseTimer();
GetContext().OnUndefined(address, opCode);
Statistics.ResumeTimer();
}
#region "System registers"
public static ulong GetCtrEl0()
{
return (ulong)GetContext().CtrEl0;
}
public static ulong GetDczidEl0()
{
return (ulong)GetContext().DczidEl0;
}
public static ulong GetFpcr()
{
return (ulong)GetContext().Fpcr;
}
public static ulong GetFpsr()
{
return (ulong)GetContext().Fpsr;
}
public static uint GetFpscr()
{
var context = GetContext();
return (uint)(context.Fpsr & FPSR.A32Mask & ~FPSR.Nzcv) |
(uint)(context.Fpcr & FPCR.A32Mask);
}
public static ulong GetTpidrEl0()
{
return (ulong)GetContext().TpidrEl0;
}
public static uint GetTpidrEl032()
{
return (uint)GetContext().TpidrEl0;
}
public static ulong GetTpidr()
{
return (ulong)GetContext().Tpidr;
}
public static uint GetTpidr32()
{
return (uint)GetContext().Tpidr;
}
public static ulong GetCntfrqEl0()
{
return GetContext().CntfrqEl0;
}
public static ulong GetCntpctEl0()
{
return GetContext().CntpctEl0;
}
public static ulong GetCntvctEl0()
{
return GetContext().CntvctEl0;
}
public static void SetFpcr(ulong value)
{
GetContext().Fpcr = (FPCR)value;
}
public static void SetFpsr(ulong value)
{
GetContext().Fpsr = (FPSR)value;
}
public static void SetFpsrQc()
{
GetContext().Fpsr |= FPSR.Qc;
}
public static void SetFpscr(uint fpscr)
{
var context = GetContext();
context.Fpsr = FPSR.A32Mask & (FPSR)fpscr;
context.Fpcr = FPCR.A32Mask & (FPCR)fpscr;
}
public static void SetTpidrEl0(ulong value)
{
GetContext().TpidrEl0 = (long)value;
}
public static void SetTpidrEl032(uint value)
{
GetContext().TpidrEl0 = (long)value;
}
#endregion
#region "Read"
public static byte ReadByte(ulong address)
{
return GetMemoryManager().ReadTracked<byte>(address);
}
public static ushort ReadUInt16(ulong address)
{
return GetMemoryManager().ReadTracked<ushort>(address);
}
public static uint ReadUInt32(ulong address)
{
return GetMemoryManager().ReadTracked<uint>(address);
}
public static ulong ReadUInt64(ulong address)
{
return GetMemoryManager().ReadTracked<ulong>(address);
}
public static V128 ReadVector128(ulong address)
{
return GetMemoryManager().ReadTracked<V128>(address);
}
#endregion
#region "Write"
public static void WriteByte(ulong address, byte value)
{
GetMemoryManager().Write(address, value);
}
public static void WriteUInt16(ulong address, ushort value)
{
GetMemoryManager().Write(address, value);
}
public static void WriteUInt32(ulong address, uint value)
{
GetMemoryManager().Write(address, value);
}
public static void WriteUInt64(ulong address, ulong value)
{
GetMemoryManager().Write(address, value);
}
public static void WriteVector128(ulong address, V128 value)
{
GetMemoryManager().Write(address, value);
}
#endregion
public static void SignalMemoryTracking(ulong address, ulong size, bool write)
{
GetMemoryManager().SignalMemoryTracking(address, size, write);
}
public static void ThrowInvalidMemoryAccess(ulong address)
{
throw new InvalidAccessException(address);
}
public static ulong GetFunctionAddress(ulong address)
{
TranslatedFunction function = _context.Translator.GetOrTranslate(address, GetContext().ExecutionMode);
return (ulong)function.FuncPtr.ToInt64();
}
public static ulong GetIndirectFunctionAddress(ulong address, ulong entryAddress)
{
TranslatedFunction function = _context.Translator.GetOrTranslate(address, GetContext().ExecutionMode);
ulong ptr = (ulong)function.FuncPtr.ToInt64();
if (function.HighCq)
{
// Rewrite the host function address in the table to point to the highCq function.
Marshal.WriteInt64((IntPtr)entryAddress, 8, (long)ptr);
}
return ptr;
}
public static bool CheckSynchronization()
{
Statistics.PauseTimer();
var context = GetContext();
context.CheckInterrupt();
Statistics.ResumeTimer();
return context.Running;
}
public static ExecutionContext GetContext()
{
return _context.Context;
}
public static IMemoryManager GetMemoryManager()
{
return _context.Memory;
}
}
}