mirror of
https://github.com/par274/sharpemu.git
synced 2026-08-09 11:15:41 +08:00
Astro Bot stack: VEH/TBB, title clear, swapchain fallback, Psml MFSR (#528)
* Cpu/Kernel: harden VEH trampoline and keep TBB on native workers Route FastFail/CLR/stack-overflow around managed VEH, serialize managed entry with a recursive spinlock, require native workers for tbb_thead, and abandon pthread mutexes when a guest thread is torn down by worker abort so splash waiters are not left holding locks forever. * Cpu: soft-fail TBB native worker storms and cap concurrent Runs Throwing on worker/prologue faults killed the process mid tbb_thead burst (FailFast 0xC0000409). Soft-return 0x80020012, limit in-flight native Runs (default 2), and keep prewarm small so back-to-back boots do not need an artificial settle delay. * Agc/VideoOut: poison-only empty-SRT reject and clear procedural ES/PS Skip QueueSubmit only when Address-0 image slots remain; run the Astro title clear pair via CmdClearColorImage so the pass executes without descriptors that lose the device. * VideoOut: recreate swapchain with fallback extent on 0x0 surface Minimized Win32 surfaces report 0x0 / MaxImageExtent=0; deferring recreate forever left an OutOfDate swapchain with no presents. Clamp to last/default size and recreate instead of early-return. * Psml: stub MFSR init/shared/context and dispatch packet size Astro Bot asserts in GfxRenderStagePSSR when scePsmlMfsrInit is unresolved (Mfsr initialized failed). Soft HLE for the MFSR shared-resource and 800M3_2 context path plus dispatch packet size lets boot pass splash to first frame without claiming real upscaling. * Psml: stub MFSR GetDispatchMfsrPacket900 for logo PSSR Astro StartLevel ps_logo asserted GfxRenderStagePSSR.cpp:266 when GetDispatchMfsrPacket900 (RUNLFro+qok) was unresolved. Return SCE_OK from SizeInDwords so the 900 fill runs, soft-clear the guest packet buffer, and register 1000/1100 siblings for the same ABI.
This commit is contained in:
Mike Saito
@@ -24,7 +24,7 @@ internal sealed unsafe partial class WindowsFaultHandling : IHostFaultHandling
|
||||
|
||||
public nint CreateHandlerThunk(nint managedCallback, uint hostRspSwitchTlsSlot, nint tlsGetValueAddress)
|
||||
{
|
||||
const uint stubSize = 256u;
|
||||
const uint stubSize = 1024u;
|
||||
void* ptr = (void*)_memory.Allocate(0, stubSize, HostPageProtection.ReadWriteExecute);
|
||||
if (ptr == null)
|
||||
{
|
||||
@@ -43,11 +43,15 @@ internal sealed unsafe partial class WindowsFaultHandling : IHostFaultHandling
|
||||
// managed code; the CLR's own VEH handles its exceptions. MSVC C++ exceptions
|
||||
// (Vulkan drivers, host CRT) are excluded too: the managed handler only ever
|
||||
// returned CONTINUE_SEARCH for them.
|
||||
//
|
||||
// FastFail (0xC0000409) is logged from this native path only: managed VEH never
|
||||
// sees it (tLT18–21 silent exits after TBB AV recovery).
|
||||
ReadOnlySpan<uint> nonManagedExceptionCodes =
|
||||
[WindowsFaultCodes.ClrManagedException, 0xE06D7363u, WindowsFaultCodes.FastFail, WindowsFaultCodes.StackOverflow];
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0x8B); EmitByte(code, ref offset, 0x01); // mov rax, [rcx] (ExceptionRecord*)
|
||||
EmitByte(code, ref offset, 0x8B); EmitByte(code, ref offset, 0x00); // mov eax, [rax] (ExceptionCode)
|
||||
var passJumpOffsets = stackalloc int[nonManagedExceptionCodes.Length];
|
||||
int fastFailJumpSlot = -1;
|
||||
for (int i = 0; i < nonManagedExceptionCodes.Length; i++)
|
||||
{
|
||||
EmitByte(code, ref offset, 0x3D); // cmp eax, imm32
|
||||
@@ -55,13 +59,162 @@ internal sealed unsafe partial class WindowsFaultHandling : IHostFaultHandling
|
||||
EmitByte(code, ref offset, 0x74); // je pass
|
||||
passJumpOffsets[i] = offset;
|
||||
EmitByte(code, ref offset, 0x00);
|
||||
if (nonManagedExceptionCodes[i] == WindowsFaultCodes.FastFail)
|
||||
{
|
||||
fastFailJumpSlot = i;
|
||||
}
|
||||
}
|
||||
EmitByte(code, ref offset, 0xEB); EmitByte(code, ref offset, 0x03); // jmp over pass block
|
||||
EmitByte(code, ref offset, 0xE9); // jmp mainBody rel32 (FastFail breadcrumb sits between)
|
||||
var mainBodyJumpSlot = offset;
|
||||
EmitUInt32(code, ref offset, 0u);
|
||||
|
||||
int passOffset = offset;
|
||||
EmitByte(code, ref offset, 0x31); EmitByte(code, ref offset, 0xC0); // pass: xor eax, eax (EXCEPTION_CONTINUE_SEARCH)
|
||||
EmitByte(code, ref offset, 0xC3); // ret
|
||||
|
||||
// FastFail: native stderr breadcrumb with Context.Rip (no managed entry), then CONTINUE_SEARCH.
|
||||
// Keep in sync with DirectExecutionBackend.CreateExceptionHandlerTrampoline.
|
||||
int fastFailPassOffset = offset;
|
||||
var fastFailLogInstalled = false;
|
||||
if (fastFailJumpSlot >= 0 &&
|
||||
NativeLibrary.TryLoad("kernel32.dll", out var kernel32) &&
|
||||
NativeLibrary.TryGetExport(kernel32, "GetStdHandle", out var getStdHandle) &&
|
||||
NativeLibrary.TryGetExport(kernel32, "WriteFile", out var writeFile))
|
||||
{
|
||||
ReadOnlySpan<byte> msg =
|
||||
"[LOADER][FATAL] VEH_PASS FastFail 0xC0000409 (native; no managed VEH) rip=0x"u8;
|
||||
ReadOnlySpan<byte> hexDigits = "0123456789ABCDEF"u8;
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0x8B); EmitByte(code, ref offset, 0x41);
|
||||
EmitByte(code, ref offset, 0x08); // mov rax, [rcx+8]
|
||||
EmitByte(code, ref offset, 0x4C); EmitByte(code, ref offset, 0x8B); EmitByte(code, ref offset, 0x90);
|
||||
EmitUInt32(code, ref offset, 0xF8u); // mov r10, [rax+0xF8]
|
||||
EmitByte(code, ref offset, 0x50); // push rax
|
||||
EmitByte(code, ref offset, 0x51); // push rcx
|
||||
EmitByte(code, ref offset, 0x52); // push rdx
|
||||
EmitByte(code, ref offset, 0x41); EmitByte(code, ref offset, 0x50); // push r8
|
||||
EmitByte(code, ref offset, 0x41); EmitByte(code, ref offset, 0x51); // push r9
|
||||
EmitByte(code, ref offset, 0x41); EmitByte(code, ref offset, 0x52); // push r10
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0x83);
|
||||
EmitByte(code, ref offset, 0xEC); EmitByte(code, ref offset, 0x40); // sub rsp, 0x40
|
||||
EmitByte(code, ref offset, 0xB9); EmitUInt32(code, ref offset, unchecked((uint)-12));
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0xB8);
|
||||
*(nint*)(code + offset) = getStdHandle;
|
||||
offset += sizeof(nint);
|
||||
EmitByte(code, ref offset, 0xFF); EmitByte(code, ref offset, 0xD0);
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0x89);
|
||||
EmitByte(code, ref offset, 0x44); EmitByte(code, ref offset, 0x24);
|
||||
EmitByte(code, ref offset, 0x28); // mov [rsp+0x28], rax
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0x89); EmitByte(code, ref offset, 0xC1);
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0xB8);
|
||||
var msgAbsSlot = offset;
|
||||
*(nint*)(code + offset) = 0;
|
||||
offset += sizeof(nint);
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0x89); EmitByte(code, ref offset, 0xC2);
|
||||
EmitByte(code, ref offset, 0x41); EmitByte(code, ref offset, 0xB8);
|
||||
EmitUInt32(code, ref offset, (uint)msg.Length);
|
||||
EmitByte(code, ref offset, 0x4C); EmitByte(code, ref offset, 0x8D);
|
||||
EmitByte(code, ref offset, 0x4C); EmitByte(code, ref offset, 0x24);
|
||||
EmitByte(code, ref offset, 0x20);
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0xC7);
|
||||
EmitByte(code, ref offset, 0x44); EmitByte(code, ref offset, 0x24);
|
||||
EmitByte(code, ref offset, 0x20); EmitUInt32(code, ref offset, 0);
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0xC7);
|
||||
EmitByte(code, ref offset, 0x44); EmitByte(code, ref offset, 0x24);
|
||||
EmitByte(code, ref offset, 0x38); EmitUInt32(code, ref offset, 0);
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0xB8);
|
||||
*(nint*)(code + offset) = writeFile;
|
||||
offset += sizeof(nint);
|
||||
EmitByte(code, ref offset, 0xFF); EmitByte(code, ref offset, 0xD0);
|
||||
|
||||
EmitByte(code, ref offset, 0x4C); EmitByte(code, ref offset, 0x8B);
|
||||
EmitByte(code, ref offset, 0x54); EmitByte(code, ref offset, 0x24);
|
||||
EmitByte(code, ref offset, 0x40); // mov r10, [rsp+0x40]
|
||||
EmitByte(code, ref offset, 0x49); EmitByte(code, ref offset, 0xB8);
|
||||
var hexDigitsAbsSlot = offset;
|
||||
*(nint*)(code + offset) = 0;
|
||||
offset += sizeof(nint);
|
||||
EmitByte(code, ref offset, 0x4C); EmitByte(code, ref offset, 0x8D);
|
||||
EmitByte(code, ref offset, 0x5C); EmitByte(code, ref offset, 0x24);
|
||||
EmitByte(code, ref offset, 0x30); // lea r11, [rsp+0x30]
|
||||
EmitByte(code, ref offset, 0xB9); EmitUInt32(code, ref offset, 16u);
|
||||
EmitByte(code, ref offset, 0x4C); EmitByte(code, ref offset, 0x89); EmitByte(code, ref offset, 0xD0);
|
||||
int hexLoopOffset = offset;
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0xC1); EmitByte(code, ref offset, 0xC0);
|
||||
EmitByte(code, ref offset, 0x04);
|
||||
EmitByte(code, ref offset, 0x89); EmitByte(code, ref offset, 0xC2);
|
||||
EmitByte(code, ref offset, 0x83); EmitByte(code, ref offset, 0xE2); EmitByte(code, ref offset, 0x0F);
|
||||
EmitByte(code, ref offset, 0x41); EmitByte(code, ref offset, 0x0F); EmitByte(code, ref offset, 0xB6);
|
||||
EmitByte(code, ref offset, 0x14); EmitByte(code, ref offset, 0x10);
|
||||
EmitByte(code, ref offset, 0x41); EmitByte(code, ref offset, 0x88); EmitByte(code, ref offset, 0x13);
|
||||
EmitByte(code, ref offset, 0x49); EmitByte(code, ref offset, 0xFF); EmitByte(code, ref offset, 0xC3);
|
||||
EmitByte(code, ref offset, 0xFF); EmitByte(code, ref offset, 0xC9);
|
||||
EmitByte(code, ref offset, 0x75);
|
||||
EmitByte(code, ref offset, unchecked((byte)(hexLoopOffset - (offset + 1)))); // jnz rel8
|
||||
EmitByte(code, ref offset, 0x41); EmitByte(code, ref offset, 0xC6); EmitByte(code, ref offset, 0x03);
|
||||
EmitByte(code, ref offset, 0x0A);
|
||||
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0x8B);
|
||||
EmitByte(code, ref offset, 0x4C); EmitByte(code, ref offset, 0x24);
|
||||
EmitByte(code, ref offset, 0x28);
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0x8D);
|
||||
EmitByte(code, ref offset, 0x54); EmitByte(code, ref offset, 0x24);
|
||||
EmitByte(code, ref offset, 0x30);
|
||||
EmitByte(code, ref offset, 0x41); EmitByte(code, ref offset, 0xB8);
|
||||
EmitUInt32(code, ref offset, 17u);
|
||||
EmitByte(code, ref offset, 0x4C); EmitByte(code, ref offset, 0x8D);
|
||||
EmitByte(code, ref offset, 0x4C); EmitByte(code, ref offset, 0x24);
|
||||
EmitByte(code, ref offset, 0x20);
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0xC7);
|
||||
EmitByte(code, ref offset, 0x44); EmitByte(code, ref offset, 0x24);
|
||||
EmitByte(code, ref offset, 0x20); EmitUInt32(code, ref offset, 0);
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0xC7);
|
||||
EmitByte(code, ref offset, 0x44); EmitByte(code, ref offset, 0x24);
|
||||
EmitByte(code, ref offset, 0x38); EmitUInt32(code, ref offset, 0);
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0xB8);
|
||||
*(nint*)(code + offset) = writeFile;
|
||||
offset += sizeof(nint);
|
||||
EmitByte(code, ref offset, 0xFF); EmitByte(code, ref offset, 0xD0);
|
||||
|
||||
EmitByte(code, ref offset, 0x48); EmitByte(code, ref offset, 0x83);
|
||||
EmitByte(code, ref offset, 0xC4); EmitByte(code, ref offset, 0x40);
|
||||
EmitByte(code, ref offset, 0x41); EmitByte(code, ref offset, 0x5A);
|
||||
EmitByte(code, ref offset, 0x41); EmitByte(code, ref offset, 0x59);
|
||||
EmitByte(code, ref offset, 0x41); EmitByte(code, ref offset, 0x58);
|
||||
EmitByte(code, ref offset, 0x5A);
|
||||
EmitByte(code, ref offset, 0x59);
|
||||
EmitByte(code, ref offset, 0x58);
|
||||
EmitByte(code, ref offset, 0x31); EmitByte(code, ref offset, 0xC0);
|
||||
EmitByte(code, ref offset, 0xC3);
|
||||
|
||||
var msgOffset = offset;
|
||||
for (int i = 0; i < msg.Length; i++)
|
||||
{
|
||||
EmitByte(code, ref offset, msg[i]);
|
||||
}
|
||||
|
||||
var hexDigitsOffset = offset;
|
||||
for (int i = 0; i < hexDigits.Length; i++)
|
||||
{
|
||||
EmitByte(code, ref offset, hexDigits[i]);
|
||||
}
|
||||
|
||||
*(nint*)(code + msgAbsSlot) = (nint)ptr + msgOffset;
|
||||
*(nint*)(code + hexDigitsAbsSlot) = (nint)ptr + hexDigitsOffset;
|
||||
code[passJumpOffsets[fastFailJumpSlot]] =
|
||||
checked((byte)(fastFailPassOffset - (passJumpOffsets[fastFailJumpSlot] + 1)));
|
||||
fastFailLogInstalled = true;
|
||||
}
|
||||
|
||||
int mainBodyOffset = offset;
|
||||
*(int*)(code + mainBodyJumpSlot) = mainBodyOffset - (mainBodyJumpSlot + sizeof(int));
|
||||
|
||||
for (int i = 0; i < nonManagedExceptionCodes.Length; i++)
|
||||
{
|
||||
if (i == fastFailJumpSlot && fastFailLogInstalled)
|
||||
{
|
||||
continue;
|
||||
}
|
||||
|
||||
code[passJumpOffsets[i]] = checked((byte)(passOffset - (passJumpOffsets[i] + 1)));
|
||||
}
|
||||
EmitByte(code, ref offset, 0x41); EmitByte(code, ref offset, 0x54); // push r12
|
||||
|
||||
Reference in New Issue
Block a user