rjx-mirror/ARMeilleure/Translation/JitCache.cs
riperiperi d904706fc0
Use a Jump Table for direct and indirect calls/jumps, removing transitions to managed (#975)
* Implement Jump Table for Native Calls

NOTE: this slows down rejit considerably! Not recommended to be used
without codegen optimisation or AOT.

- Does not work on Linux
- A32 needs an additional commit.

* A32 Support

(WIP)

* Actually write Direct Call pointers to the table

That would help.

* Direct Calls: Rather than returning to the translator, attempt to keep within the native stack frame.

A return to the translator can still happen, but only by exceptionally
bubbling up to it.

Also:
- Always translate lowCq as a function. Faster interop with the direct
jumps, and this will be useful in future if we want to do speculative
translation.
- Tail Call Detection: after the decoding stage, detect if we do a tail
call, and avoid translating into it. Detected if a jump is made to an
address outwith the contiguous sequence of blocks surrounding the entry
point. The goal is to reduce code touched by jit and rejit.

* A32 Support

* Use smaller max function size for lowCq, fix exceptional returns

When a return has an unexpected value and there is no code block
following this one, we now return the value rather than continuing.

* CompareAndSwap (buggy)

* Ensure CompareAndSwap does not get optimized away.

* Use CompareAndSwap to make the dynamic table thread safe.

* Tail call for linux, throw on too many arguments.

* Combine CompareAndSwap 128 and 32/64.

They emit different IR instructions since their PreAllocator behaviour
is different, but now they just have one function on EmitterContext.

* Fix issues separating from optimisations.

* Use a stub to find and execute missing functions.

This allows us to skip doing many runtime comparisons and branches, and reduces the amount of code we need to emit significantly.

For the indirect call table, this stub also does the work of moving in the highCq address to the table when one is found.

* Make Jump Tables and Jit Cache dynmically resize

Reserve virtual memory, commit as needed.

* Move TailCallRemover to its own class.

* Multithreaded Translation (based on heuristic)

A poor one, at that. Need to get core count for a better one, which
means a lot of OS specific garbage.

* Better priority management for background threads.

* Bound core limit a bit more

Past a certain point the load is not paralellizable and starts stealing from the main thread. Likely due to GC, memory, heap allocation thread contention. Reduce by one core til optimisations come to improve the situation.

* Fix memory management on linux.

* Temporary solution to some sync problems.

This will make sure threads exit correctly, most of the time. There is a potential race where setting the sync counter to 0 does nothing (counter stays at what it was before, thread could take too long to exit), but we need to find a better way to do this anyways. Synchronization frequency has been tightened as we never enter blockwise segments of code. Essentially this means, check every x functions or loop iterations, before lowcq blocks existed and were worth just as much. Ideally it should be done in a better way, since functions can be anywhere from 1 to 5000 instructions. (maybe based on host timer, or an interrupt flag from a scheduler thread)

* Address feedback minus CompareAndSwap change.

* Use default ReservedRegion granularity.

* Merge CompareAndSwap with its V128 variant.

* We already got the source, no need to do it again.

* Make sure all background translation threads exit.

* Fix CompareAndSwap128

Detection criteria was a bit scuffed.

* Address Comments.
2020-03-12 14:20:55 +11:00

140 lines
No EOL
3.8 KiB
C#

using ARMeilleure.CodeGen;
using ARMeilleure.Memory;
using System;
using System.Collections.Generic;
using System.Runtime.InteropServices;
namespace ARMeilleure.Translation
{
static class JitCache
{
private const int PageSize = 4 * 1024;
private const int PageMask = PageSize - 1;
private const int CodeAlignment = 4; // Bytes
private const int CacheSize = 2047 * 1024 * 1024;
private static ReservedRegion _jitRegion;
private static IntPtr _basePointer => _jitRegion.Pointer;
private static int _offset;
private static List<JitCacheEntry> _cacheEntries;
private static object _lock;
static JitCache()
{
_jitRegion = new ReservedRegion(CacheSize);
if (RuntimeInformation.IsOSPlatform(OSPlatform.Windows))
{
_jitRegion.ExpandIfNeeded(PageSize);
JitUnwindWindows.InstallFunctionTableHandler(_basePointer, CacheSize);
// The first page is used for the table based SEH structs.
_offset = PageSize;
}
_cacheEntries = new List<JitCacheEntry>();
_lock = new object();
}
public static IntPtr Map(CompiledFunction func)
{
byte[] code = func.Code;
lock (_lock)
{
int funcOffset = Allocate(code.Length);
IntPtr funcPtr = _basePointer + funcOffset;
Marshal.Copy(code, 0, funcPtr, code.Length);
ReprotectRange(funcOffset, code.Length);
Add(new JitCacheEntry(funcOffset, code.Length, func.UnwindInfo));
return funcPtr;
}
}
private static void ReprotectRange(int offset, int size)
{
// Map pages that are already full as RX.
// Map pages that are not full yet as RWX.
// On unix, the address must be page aligned.
int endOffs = offset + size;
int pageStart = offset & ~PageMask;
int pageEnd = endOffs & ~PageMask;
int fullPagesSize = pageEnd - pageStart;
if (fullPagesSize != 0)
{
IntPtr funcPtr = _basePointer + pageStart;
MemoryManagement.Reprotect(funcPtr, (ulong)fullPagesSize, MemoryProtection.ReadAndExecute);
}
int remaining = endOffs - pageEnd;
if (remaining != 0)
{
IntPtr funcPtr = _basePointer + pageEnd;
MemoryManagement.Reprotect(funcPtr, (ulong)remaining, MemoryProtection.ReadWriteExecute);
}
}
private static int Allocate(int codeSize)
{
codeSize = checked(codeSize + (CodeAlignment - 1)) & ~(CodeAlignment - 1);
int allocOffset = _offset;
_offset += codeSize;
_jitRegion.ExpandIfNeeded((ulong)_offset);
if ((ulong)(uint)_offset > CacheSize)
{
throw new OutOfMemoryException();
}
return allocOffset;
}
private static void Add(JitCacheEntry entry)
{
_cacheEntries.Add(entry);
}
public static bool TryFind(int offset, out JitCacheEntry entry)
{
lock (_lock)
{
foreach (JitCacheEntry cacheEntry in _cacheEntries)
{
int endOffset = cacheEntry.Offset + cacheEntry.Size;
if (offset >= cacheEntry.Offset && offset < endOffset)
{
entry = cacheEntry;
return true;
}
}
}
entry = default(JitCacheEntry);
return false;
}
}
}