Ryujinx/Ryujinx.Memory/Tracking/SmartMultiRegionHandle.cs
riperiperi 54ea2285f0
POWER - Performance Optimizations With Extensive Ramifications (#2286)
* Refactoring of KMemoryManager class

* Replace some trivial uses of DRAM address with VA

* Get rid of GetDramAddressFromVa

* Abstracting more operations on derived page table class

* Run auto-format on KPageTableBase

* Managed to make TryConvertVaToPa private, few uses remains now

* Implement guest physical pages ref counting, remove manual freeing

* Make DoMmuOperation private and call new abstract methods only from the base class

* Pass pages count rather than size on Map/UnmapMemory

* Change memory managers to take host pointers

* Fix a guest memory leak and simplify KPageTable

* Expose new methods for host range query and mapping

* Some refactoring of MapPagesFromClientProcess to allow proper page ref counting and mapping without KPageLists

* Remove more uses of AddVaRangeToPageList, now only one remains (shared memory page checking)

* Add a SharedMemoryStorage class, will be useful for host mapping

* Sayonara AddVaRangeToPageList, you served us well

* Start to implement host memory mapping (WIP)

* Support memory tracking through host exception handling

* Fix some access violations from HLE service guest memory access and CPU

* Fix memory tracking

* Fix mapping list bugs, including a race and a error adding mapping ranges

* Simple page table for memory tracking

* Simple "volatile" region handle mode

* Update UBOs directly (experimental, rough)

* Fix the overlap check

* Only set non-modified buffers as volatile

* Fix some memory tracking issues

* Fix possible race in MapBufferFromClientProcess (block list updates were not locked)

* Write uniform update to memory immediately, only defer the buffer set.

* Fix some memory tracking issues

* Pass correct pages count on shared memory unmap

* Armeilleure Signal Handler v1 + Unix changes

Unix currently behaves like windows, rather than remapping physical

* Actually check if the host platform is unix

* Fix decommit on linux.

* Implement windows 10 placeholder shared memory, fix a buffer issue.

* Make PTC version something that will never match with master

* Remove testing variable for block count

* Add reference count for memory manager, fix dispose

Can still deadlock with OpenAL

* Add address validation, use page table for mapped check, add docs

Might clean up the page table traversing routines.

* Implement batched mapping/tracking.

* Move documentation, fix tests.

* Cleanup uniform buffer update stuff.

* Remove unnecessary assignment.

* Add unsafe host mapped memory switch

On by default. Would be good to turn this off for untrusted code (homebrew, exefs mods) and give the user the option to turn it on manually, though that requires some UI work.

* Remove C# exception handlers

They have issues due to current .NET limitations, so the meilleure one fully replaces them for now.

* Fix MapPhysicalMemory on the software MemoryManager.

* Null check for GetHostAddress, docs

* Add configuration for setting memory manager mode (not in UI yet)

* Add config to UI

* Fix type mismatch on Unix signal handler code emit

* Fix 6GB DRAM mode.

The size can be greater than `uint.MaxValue` when the DRAM is >4GB.

* Address some feedback.

* More detailed error if backing memory cannot be mapped.

* SetLastError on all OS functions for consistency

* Force pages dirty with UBO update instead of setting them directly.

Seems to be much faster across a few games. Need retesting.

* Rebase, configuration rework, fix mem tracking regression

* Fix race in FreePages

* Set memory managers null after decrementing ref count

* Remove readonly keyword, as this is now modified.

* Use a local variable for the signal handler rather than a register.

* Fix bug with buffer resize, and index/uniform buffer binding.

Should fix flickering in games.

* Add InvalidAccessHandler to MemoryTracking

Doesn't do anything yet

* Call invalid access handler on unmapped read/write.

Same rules as the regular memory manager.

* Make unsafe mapped memory its own MemoryManagerType

* Move FlushUboDirty into UpdateState.

* Buffer dirty cache, rather than ubo cache

Much cleaner, may be reusable for Inline2Memory updates.

* This doesn't return anything anymore.

* Add sigaction remove methods, correct a few function signatures.

* Return empty list of physical regions for size 0.

* Also on AddressSpaceManager

Co-authored-by: gdkchan <gab.dark.100@gmail.com>
2021-05-24 22:52:44 +02:00

268 lines
8.9 KiB
C#

using System;
using System.Runtime.CompilerServices;
namespace Ryujinx.Memory.Tracking
{
/// <summary>
/// A MultiRegionHandle that attempts to segment a region's handles into the regions requested
/// to avoid iterating over granular chunks for canonically large regions.
/// If minimum granularity is to be expected, use MultiRegionHandle.
/// </summary>
public class SmartMultiRegionHandle : IMultiRegionHandle
{
/// <summary>
/// A list of region handles starting at each granularity size increment.
/// </summary>
private readonly RegionHandle[] _handles;
private readonly ulong _address;
private readonly ulong _granularity;
private readonly ulong _size;
private MemoryTracking _tracking;
public bool Dirty { get; private set; } = true;
internal SmartMultiRegionHandle(MemoryTracking tracking, ulong address, ulong size, ulong granularity)
{
// For this multi-region handle, the handle list starts empty.
// As regions are queried, they are added to the _handles array at their start index.
// When a region being added overlaps another, the existing region is split.
// A query can therefore scan multiple regions, though with no overlaps they can cover a large area.
_tracking = tracking;
_handles = new RegionHandle[size / granularity];
_granularity = granularity;
_address = address;
_size = size;
}
public void SignalWrite()
{
Dirty = true;
}
public void ForceDirty(ulong address, ulong size)
{
foreach (var handle in _handles)
{
if (handle != null && handle.OverlapsWith(address, size))
{
handle.ForceDirty();
}
}
}
public void RegisterAction(RegionSignal action)
{
foreach (var handle in _handles)
{
if (handle != null)
{
handle?.RegisterAction((address, size) => action(handle.Address, handle.Size));
}
}
}
public void QueryModified(Action<ulong, ulong> modifiedAction)
{
if (!Dirty)
{
return;
}
Dirty = false;
QueryModified(_address, _size, modifiedAction);
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private ulong HandlesToBytes(int handles)
{
return (ulong)handles * _granularity;
}
private void SplitHandle(int handleIndex, int splitIndex)
{
RegionHandle handle = _handles[handleIndex];
ulong address = _address + HandlesToBytes(handleIndex);
ulong size = HandlesToBytes(splitIndex - handleIndex);
// First, the target handle must be removed. Its data can still be used to determine the new handles.
RegionSignal signal = handle.PreAction;
handle.Dispose();
RegionHandle splitLow = _tracking.BeginTracking(address, size);
splitLow.Parent = this;
if (signal != null)
{
splitLow.RegisterAction(signal);
}
_handles[handleIndex] = splitLow;
RegionHandle splitHigh = _tracking.BeginTracking(address + size, handle.Size - size);
splitHigh.Parent = this;
if (signal != null)
{
splitHigh.RegisterAction(signal);
}
_handles[splitIndex] = splitHigh;
}
private void CreateHandle(int startHandle, int lastHandle)
{
ulong startAddress = _address + HandlesToBytes(startHandle);
// Scan for the first handle before us. If it's overlapping us, it must be split.
for (int i = startHandle - 1; i >= 0; i--)
{
RegionHandle handle = _handles[i];
if (handle != null)
{
if (handle.EndAddress > startAddress)
{
SplitHandle(i, startHandle);
return; // The remainer of this handle should be filled in later on.
}
break;
}
}
// Scan for handles after us. We should create a handle that goes up to this handle's start point, if present.
for (int i = startHandle + 1; i <= lastHandle; i++)
{
RegionHandle handle = _handles[i];
if (handle != null)
{
// Fill up to the found handle.
handle = _tracking.BeginTracking(startAddress, HandlesToBytes(i - startHandle));
handle.Parent = this;
_handles[startHandle] = handle;
return;
}
}
// Can fill the whole range.
_handles[startHandle] = _tracking.BeginTracking(startAddress, HandlesToBytes(1 + lastHandle - startHandle));
_handles[startHandle].Parent = this;
}
public void QueryModified(ulong address, ulong size, Action<ulong, ulong> modifiedAction)
{
int startHandle = (int)((address - _address) / _granularity);
int lastHandle = (int)((address + (size - 1) - _address) / _granularity);
ulong rgStart = _address + (ulong)startHandle * _granularity;
ulong rgSize = 0;
ulong endAddress = _address + ((ulong)lastHandle + 1) * _granularity;
int i = startHandle;
while (i <= lastHandle)
{
RegionHandle handle = _handles[i];
if (handle == null)
{
// Missing handle. A new handle must be created.
CreateHandle(i, lastHandle);
handle = _handles[i];
}
if (handle.EndAddress > endAddress)
{
// End address of handle is beyond the end of the search. Force a split.
SplitHandle(i, lastHandle + 1);
handle = _handles[i];
}
if (handle.Dirty)
{
rgSize += handle.Size;
handle.Reprotect();
}
else
{
// Submit the region scanned so far as dirty
if (rgSize != 0)
{
modifiedAction(rgStart, rgSize);
rgSize = 0;
}
rgStart = handle.EndAddress;
}
i += (int)(handle.Size / _granularity);
}
if (rgSize != 0)
{
modifiedAction(rgStart, rgSize);
}
}
public void QueryModified(ulong address, ulong size, Action<ulong, ulong> modifiedAction, int sequenceNumber)
{
int startHandle = (int)((address - _address) / _granularity);
int lastHandle = (int)((address + (size - 1) - _address) / _granularity);
ulong rgStart = _address + (ulong)startHandle * _granularity;
ulong rgSize = 0;
ulong endAddress = _address + ((ulong)lastHandle + 1) * _granularity;
int i = startHandle;
while (i <= lastHandle)
{
RegionHandle handle = _handles[i];
if (handle == null)
{
// Missing handle. A new handle must be created.
CreateHandle(i, lastHandle);
handle = _handles[i];
}
if (handle.EndAddress > endAddress)
{
// End address of handle is beyond the end of the search. Force a split.
SplitHandle(i, lastHandle + 1);
handle = _handles[i];
}
if (handle.Dirty && sequenceNumber != handle.SequenceNumber)
{
rgSize += handle.Size;
handle.Reprotect();
}
else
{
// Submit the region scanned so far as dirty
if (rgSize != 0)
{
modifiedAction(rgStart, rgSize);
rgSize = 0;
}
rgStart = handle.EndAddress;
}
handle.SequenceNumber = sequenceNumber;
i += (int)(handle.Size / _granularity);
}
if (rgSize != 0)
{
modifiedAction(rgStart, rgSize);
}
}
public void Dispose()
{
foreach (var handle in _handles)
{
handle?.Dispose();
}
}
}
}