Add multi-level function table (#2228)

* Add AddressTable<T>

* Use AddressTable<T> for dispatch

* Remove JumpTable & co.

* Add fallback for out of range addresses

* Add PPTC support

* Add documentation to `AddressTable<T>`

* Make AddressTable<T> configurable

* Fix table walk

* Fix IsMapped check

* Remove CountTableCapacity

* Add PPTC support for fast path

* Rename IsMapped to IsValid

* Remove stale comment

* Change format of address in exception message

* Add TranslatorStubs

* Split DispatchStub

Avoids recompilation of stubs during tests.

* Add hint for 64bit or 32bit

* Add documentation to `Symbol`

* Add documentation to `TranslatorStubs`

Make `TranslatorStubs` disposable as well.

* Add documentation to `SymbolType`

* Add `AddressTableEventSource` to monitor function table size

Add an EventSource which measures the amount of unmanaged bytes
allocated by AddressTable<T> instances.

 dotnet-counters monitor -n Ryujinx --counters ARMeilleure

* Add `AllowLcqInFunctionTable` optimization toggle

This is to reduce the impact this change has on the test duration.
Before everytime a test was ran, the FunctionTable would be initialized
and populated so that the newly compiled test would get registered to
it.

* Implement unmanaged dispatcher

Uses the DispatchStub to dispatch into the next translation, which
allows execution to stay in unmanaged for longer and skips a
ConcurrentDictionary look up when the target translation has been
registered to the FunctionTable.

* Remove redundant null check

* Tune levels of FunctionTable

Uses 5 levels instead of 4 and change unit of AddressTableEventSource
from KB to MB.

* Use 64-bit function table

Improves codegen for direct branches:

    mov qword [rax+0x408],0x10603560
 -  mov rcx,sub_10603560_OFFSET
 -  mov ecx,[rcx]
 -  mov ecx,ecx
 -  mov rdx,JIT_CACHE_BASE
 -  add rdx,rcx
 +  mov rcx,sub_10603560
 +  mov rdx,[rcx]
    mov rcx,rax

Improves codegen for dispatch stub:

    and rax,byte +0x1f
 -  mov eax,[rcx+rax*4]
 -  mov eax,eax
 -  mov rcx,JIT_CACHE_BASE
 -  lea rax,[rcx+rax]
 +  mov rax,[rcx+rax*8]
    mov rcx,rbx

* Remove `JitCacheSymbol` & `JitCache.Offset`

* Turn `Translator.Translate` into an instance method

We do not have to add more parameter to this method and related ones as
new structures are added & needed for translation.

* Add symbol only when PTC is enabled

Address LDj3SNuD's feedback

* Change `NativeContext.Running` to a 32-bit integer

* Fix PageTable symbol for host mapped

5 files changed, 12 insertions, 13 deletions

diff --git a/Ryujinx.HLE/HOS/ArmProcessContext.cs b/Ryujinx.HLE/HOS/ArmProcessContext.cs
index ae5fe601..457d1218 100644
--- a/Ryujinx.HLE/HOS/ArmProcessContext.cs
+++ b/Ryujinx.HLE/HOS/ArmProcessContext.cs
@@ -3,7 +3,6 @@ using ARMeilleure.State;
 using Ryujinx.Cpu;
 using Ryujinx.HLE.HOS.Kernel.Process;
 using Ryujinx.Memory;
-using System;
 
 namespace Ryujinx.HLE.HOS
 {
@@ -14,7 +13,7 @@ namespace Ryujinx.HLE.HOS
 
         public IVirtualMemoryManager AddressSpace => _memoryManager;
 
-        public ArmProcessContext(T memoryManager)
+        public ArmProcessContext(T memoryManager, bool for64Bit)
         {
             if (memoryManager is IRefCounted rc)
             {
@@ -22,7 +21,7 @@ namespace Ryujinx.HLE.HOS
             }
 
             _memoryManager = memoryManager;
-            _cpuContext = new CpuContext(memoryManager);
+            _cpuContext = new CpuContext(memoryManager, for64Bit);
         }
 
         public void Execute(ExecutionContext context, ulong codeAddress)
diff --git a/Ryujinx.HLE/HOS/ArmProcessContextFactory.cs b/Ryujinx.HLE/HOS/ArmProcessContextFactory.cs
index 14617cf2..04d06e1f 100644
--- a/Ryujinx.HLE/HOS/ArmProcessContextFactory.cs
+++ b/Ryujinx.HLE/HOS/ArmProcessContextFactory.cs
@@ -9,19 +9,19 @@ namespace Ryujinx.HLE.HOS
 {
     class ArmProcessContextFactory : IProcessContextFactory
     {
-        public IProcessContext Create(KernelContext context, ulong addressSpaceSize, InvalidAccessHandler invalidAccessHandler)
+        public IProcessContext Create(KernelContext context, ulong addressSpaceSize, InvalidAccessHandler invalidAccessHandler, bool for64Bit)
         {
             MemoryManagerMode mode = context.Device.Configuration.MemoryManagerMode;
 
             switch (mode)
             {
                 case MemoryManagerMode.SoftwarePageTable:
-                    return new ArmProcessContext<MemoryManager>(new MemoryManager(addressSpaceSize, invalidAccessHandler));
+                    return new ArmProcessContext<MemoryManager>(new MemoryManager(addressSpaceSize, invalidAccessHandler), for64Bit);
 
                 case MemoryManagerMode.HostMapped:
                 case MemoryManagerMode.HostMappedUnsafe:
                     bool unsafeMode = mode == MemoryManagerMode.HostMappedUnsafe;
-                    return new ArmProcessContext<MemoryManagerHostMapped>(new MemoryManagerHostMapped(addressSpaceSize, unsafeMode, invalidAccessHandler));
+                    return new ArmProcessContext<MemoryManagerHostMapped>(new MemoryManagerHostMapped(addressSpaceSize, unsafeMode, invalidAccessHandler), for64Bit);
 
                 default:
                     throw new ArgumentOutOfRangeException();
diff --git a/Ryujinx.HLE/HOS/Kernel/Process/IProcessContextFactory.cs b/Ryujinx.HLE/HOS/Kernel/Process/IProcessContextFactory.cs
index e9fbf618..fbd6c139 100644
--- a/Ryujinx.HLE/HOS/Kernel/Process/IProcessContextFactory.cs
+++ b/Ryujinx.HLE/HOS/Kernel/Process/IProcessContextFactory.cs
@@ -1,10 +1,9 @@
-using Ryujinx.Cpu;
-using Ryujinx.Memory;
+using Ryujinx.Memory;
 
 namespace Ryujinx.HLE.HOS.Kernel.Process
 {
     interface IProcessContextFactory
     {
-        IProcessContext Create(KernelContext context, ulong addressSpaceSize, InvalidAccessHandler invalidAccessHandler);
+        IProcessContext Create(KernelContext context, ulong addressSpaceSize, InvalidAccessHandler invalidAccessHandler, bool for64Bit);
     }
 }
diff --git a/Ryujinx.HLE/HOS/Kernel/Process/KProcess.cs b/Ryujinx.HLE/HOS/Kernel/Process/KProcess.cs
index f2ba675f..90cd01f0 100644
--- a/Ryujinx.HLE/HOS/Kernel/Process/KProcess.cs
+++ b/Ryujinx.HLE/HOS/Kernel/Process/KProcess.cs
@@ -1049,7 +1049,9 @@ namespace Ryujinx.HLE.HOS.Kernel.Process
                 _ => 39
             };
 
-            Context = _contextFactory.Create(KernelContext, 1UL << addrSpaceBits, InvalidAccessHandler);
+            bool for64Bit = flags.HasFlag(ProcessCreationFlags.Is64Bit);
+
+            Context = _contextFactory.Create(KernelContext, 1UL << addrSpaceBits, InvalidAccessHandler, for64Bit);
 
             // TODO: This should eventually be removed.
             // The GPU shouldn't depend on the CPU memory manager at all.
diff --git a/Ryujinx.HLE/HOS/Kernel/Process/ProcessContextFactory.cs b/Ryujinx.HLE/HOS/Kernel/Process/ProcessContextFactory.cs
index 29860b3b..5920fe44 100644
--- a/Ryujinx.HLE/HOS/Kernel/Process/ProcessContextFactory.cs
+++ b/Ryujinx.HLE/HOS/Kernel/Process/ProcessContextFactory.cs
@@ -1,11 +1,10 @@
-using Ryujinx.Cpu;
-using Ryujinx.Memory;
+using Ryujinx.Memory;
 
 namespace Ryujinx.HLE.HOS.Kernel.Process
 {
     class ProcessContextFactory : IProcessContextFactory
     {
-        public IProcessContext Create(KernelContext context, ulong addressSpaceSize, InvalidAccessHandler invalidAccessHandler)
+        public IProcessContext Create(KernelContext context, ulong addressSpaceSize, InvalidAccessHandler invalidAccessHandler, bool for64Bit)
         {
             return new ProcessContext(new AddressSpaceManager(addressSpaceSize));
         }