Ryujinx/Ryujinx.HLE/HOS/Services/Nv/NvHostChannel/NvHostChannelIoctl.cs

371 lines
13 KiB
C#
Raw Normal View History

Add a new JIT compiler for CPU code (#693) * 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
2019-08-08 18:56:22 +00:00
using ARMeilleure.Memory;
using Ryujinx.Common.Logging;
using Ryujinx.Graphics.Memory;
using Ryujinx.HLE.HOS.Kernel.Process;
using Ryujinx.HLE.HOS.Services.Nv.NvGpuAS;
using Ryujinx.HLE.HOS.Services.Nv.NvMap;
using System;
using System.Collections.Concurrent;
namespace Ryujinx.HLE.HOS.Services.Nv.NvHostChannel
{
class NvHostChannelIoctl
{
private static ConcurrentDictionary<KProcess, NvChannel> _channels;
static NvHostChannelIoctl()
{
_channels = new ConcurrentDictionary<KProcess, NvChannel>();
}
public static int ProcessIoctl(ServiceCtx context, int cmd)
{
switch (cmd & 0xffff)
{
case 0x0001: return Submit (context);
case 0x0002: return GetSyncpoint (context);
case 0x0003: return GetWaitBase (context);
case 0x0007: return SetSubmitTimeout (context);
case 0x0009: return MapBuffer (context);
case 0x000a: return UnmapBuffer (context);
case 0x4714: return SetUserData (context);
case 0x4801: return SetNvMap (context);
case 0x4803: return SetTimeout (context);
case 0x4808: return SubmitGpfifo (context);
case 0x4809: return AllocObjCtx (context);
case 0x480b: return ZcullBind (context);
case 0x480c: return SetErrorNotifier (context);
case 0x480d: return SetPriority (context);
case 0x481a: return AllocGpfifoEx2 (context);
case 0x481b: return KickoffPbWithAttr(context);
case 0x481d: return SetTimeslice (context);
}
throw new NotImplementedException(cmd.ToString("x8"));
}
private static int Submit(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
long outputPosition = context.Request.GetBufferType0x22().Position;
NvHostChannelSubmit args = MemoryHelper.Read<NvHostChannelSubmit>(context.Memory, inputPosition);
NvGpuVmm vmm = NvGpuASIoctl.GetASCtx(context).Vmm;
for (int index = 0; index < args.CmdBufsCount; index++)
{
long cmdBufOffset = inputPosition + 0x10 + index * 0xc;
NvHostChannelCmdBuf cmdBuf = MemoryHelper.Read<NvHostChannelCmdBuf>(context.Memory, cmdBufOffset);
NvMapHandle map = NvMapIoctl.GetNvMap(context, cmdBuf.MemoryId);
int[] cmdBufData = new int[cmdBuf.WordsCount];
for (int offset = 0; offset < cmdBufData.Length; offset++)
{
cmdBufData[offset] = context.Memory.ReadInt32(map.Address + cmdBuf.Offset + offset * 4);
}
context.Device.Gpu.PushCommandBuffer(vmm, cmdBufData);
}
// TODO: Relocation, waitchecks, etc.
return NvResult.Success;
}
private static int GetSyncpoint(ServiceCtx context)
{
// TODO
long inputPosition = context.Request.GetBufferType0x21().Position;
long outputPosition = context.Request.GetBufferType0x22().Position;
NvHostChannelGetParamArg args = MemoryHelper.Read<NvHostChannelGetParamArg>(context.Memory, inputPosition);
args.Value = 0;
MemoryHelper.Write(context.Memory, outputPosition, args);
return NvResult.Success;
}
private static int GetWaitBase(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
long outputPosition = context.Request.GetBufferType0x22().Position;
NvHostChannelGetParamArg args = MemoryHelper.Read<NvHostChannelGetParamArg>(context.Memory, inputPosition);
args.Value = 0;
MemoryHelper.Write(context.Memory, outputPosition, args);
return NvResult.Success;
}
private static int SetSubmitTimeout(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
GetChannel(context).SubmitTimeout = context.Memory.ReadInt32(inputPosition);
// TODO: Handle the timeout in the submit method.
Logger.PrintStub(LogClass.ServiceNv);
return NvResult.Success;
}
private static int MapBuffer(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
long outputPosition = context.Request.GetBufferType0x22().Position;
NvHostChannelMapBuffer args = MemoryHelper.Read<NvHostChannelMapBuffer>(context.Memory, inputPosition);
NvGpuVmm vmm = NvGpuASIoctl.GetASCtx(context).Vmm;
for (int index = 0; index < args.NumEntries; index++)
{
int handle = context.Memory.ReadInt32(inputPosition + 0xc + index * 8);
NvMapHandle map = NvMapIoctl.GetNvMap(context, handle);
if (map == null)
{
Logger.PrintWarning(LogClass.ServiceNv, $"Invalid handle 0x{handle:x8}!");
return NvResult.InvalidInput;
}
lock (map)
{
if (map.DmaMapAddress == 0)
{
map.DmaMapAddress = vmm.MapLow(map.Address, map.Size);
}
context.Memory.WriteInt32(outputPosition + 0xc + 4 + index * 8, (int)map.DmaMapAddress);
}
}
return NvResult.Success;
}
private static int UnmapBuffer(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
NvHostChannelMapBuffer args = MemoryHelper.Read<NvHostChannelMapBuffer>(context.Memory, inputPosition);
NvGpuVmm vmm = NvGpuASIoctl.GetASCtx(context).Vmm;
for (int index = 0; index < args.NumEntries; index++)
{
int handle = context.Memory.ReadInt32(inputPosition + 0xc + index * 8);
NvMapHandle map = NvMapIoctl.GetNvMap(context, handle);
if (map == null)
{
Logger.PrintWarning(LogClass.ServiceNv, $"Invalid handle 0x{handle:x8}!");
return NvResult.InvalidInput;
}
lock (map)
{
if (map.DmaMapAddress != 0)
{
vmm.Free(map.DmaMapAddress, map.Size);
map.DmaMapAddress = 0;
}
}
}
return NvResult.Success;
}
private static int SetUserData(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
long outputPosition = context.Request.GetBufferType0x22().Position;
Logger.PrintStub(LogClass.ServiceNv);
return NvResult.Success;
}
private static int SetNvMap(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
long outputPosition = context.Request.GetBufferType0x22().Position;
Logger.PrintStub(LogClass.ServiceNv);
return NvResult.Success;
}
private static int SetTimeout(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
GetChannel(context).Timeout = context.Memory.ReadInt32(inputPosition);
Logger.PrintStub(LogClass.ServiceNv);
return NvResult.Success;
}
private static int SubmitGpfifo(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
long outputPosition = context.Request.GetBufferType0x22().Position;
NvHostChannelSubmitGpfifo args = MemoryHelper.Read<NvHostChannelSubmitGpfifo>(context.Memory, inputPosition);
NvGpuVmm vmm = NvGpuASIoctl.GetASCtx(context).Vmm;
for (int index = 0; index < args.NumEntries; index++)
{
long gpfifo = context.Memory.ReadInt64(inputPosition + 0x18 + index * 8);
PushGpfifo(context, vmm, gpfifo);
}
args.SyncptId = 0;
args.SyncptValue = 0;
MemoryHelper.Write(context.Memory, outputPosition, args);
return NvResult.Success;
}
private static int AllocObjCtx(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
long outputPosition = context.Request.GetBufferType0x22().Position;
Logger.PrintStub(LogClass.ServiceNv);
return NvResult.Success;
}
private static int ZcullBind(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
long outputPosition = context.Request.GetBufferType0x22().Position;
Logger.PrintStub(LogClass.ServiceNv);
return NvResult.Success;
}
private static int SetErrorNotifier(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
long outputPosition = context.Request.GetBufferType0x22().Position;
Logger.PrintStub(LogClass.ServiceNv);
return NvResult.Success;
}
private static int SetPriority(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
switch ((NvChannelPriority)context.Memory.ReadInt32(inputPosition))
{
case NvChannelPriority.Low:
GetChannel(context).Timeslice = 1300; // Timeslice low priority in micro-seconds
break;
case NvChannelPriority.Medium:
GetChannel(context).Timeslice = 2600; // Timeslice medium priority in micro-seconds
break;
case NvChannelPriority.High:
GetChannel(context).Timeslice = 5200; // Timeslice high priority in micro-seconds
break;
default:
return NvResult.InvalidInput;
}
Logger.PrintStub(LogClass.ServiceNv);
// TODO: disable and preempt channel when GPU scheduler will be implemented.
return NvResult.Success;
}
private static int AllocGpfifoEx2(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
long outputPosition = context.Request.GetBufferType0x22().Position;
Logger.PrintStub(LogClass.ServiceNv);
return NvResult.Success;
}
private static int KickoffPbWithAttr(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
long outputPosition = context.Request.GetBufferType0x22().Position;
NvHostChannelSubmitGpfifo args = MemoryHelper.Read<NvHostChannelSubmitGpfifo>(context.Memory, inputPosition);
NvGpuVmm vmm = NvGpuASIoctl.GetASCtx(context).Vmm;
for (int index = 0; index < args.NumEntries; index++)
{
long gpfifo = context.Memory.ReadInt64(args.Address + index * 8);
PushGpfifo(context, vmm, gpfifo);
}
args.SyncptId = 0;
args.SyncptValue = 0;
MemoryHelper.Write(context.Memory, outputPosition, args);
return NvResult.Success;
}
private static int SetTimeslice(ServiceCtx context)
{
long inputPosition = context.Request.GetBufferType0x21().Position;
int timeslice = context.Memory.ReadInt32(inputPosition);
if (timeslice < 1000 || timeslice > 50000)
{
return NvResult.InvalidInput;
}
GetChannel(context).Timeslice = timeslice; // in micro-seconds
Logger.PrintStub(LogClass.ServiceNv);
// TODO: disable and preempt channel when GPU scheduler will be implemented.
return NvResult.Success;
}
private static void PushGpfifo(ServiceCtx context, NvGpuVmm vmm, long gpfifo)
{
context.Device.Gpu.Pusher.Push(vmm, gpfifo);
}
public static NvChannel GetChannel(ServiceCtx context)
{
return _channels.GetOrAdd(context.Process, (key) => new NvChannel());
}
public static void UnloadProcess(KProcess process)
{
_channels.TryRemove(process, out _);
}
}
}