mirror of
https://github.com/KytyPS5/KytyPS5.git
synced 2026-10-22 20:06:54 +02:00
macOS (Apple Silicon) support: native build running under Rosetta 2 with MoltenVK (#102)
* macos: POSIX platform layer (host fault handler, virtual memory) - hostException: Mach/POSIX signal-based host fault handler mirroring the Windows vectored handler (SIGSEGV/SIGBUS/SIGILL), behind '#elif defined(__APPLE__)'. Windows and Linux branches are untouched. - sysLinuxVirtual: mach_vm_region-based is_mapped (no /proc/self/maps on macOS), PTHREAD_MUTEX_NORMAL, and a MAP_FIXED carve-in-place allocator that never leaves an unmapped hole for dyld/Rosetta/Metal to claim. All __APPLE__-guarded; the original Linux allocator path is preserved verbatim. - sysLinuxDbg/sysLinuxFileIO: libgen.h for basename(), and a POSIX opendir/readdir implementation of SysFileGetDents (previously a stub). * macos: guest kernel backing, threads, and POSIX libs - memory/memoryAddressSpace: anonymous shm_open backing (macOS has no memfd_create) and re-reserve-on-unmap so a guest MAP_FIXED remap never destroys a host mapping (__APPLE__-guarded). Drops host <sys/mman.h> MAP_* macros so the guest's constexpr MAP_* constants compile (no-op on Windows). - pthread: undef the host PTHREAD_STACK_MIN macro; on non-Windows, pin the stack-switch asm's guest rsp/rbp to callee-saved r14/r15 (the template clobbers r12/r13); __APPLE__ no-op for the absent pthread_condattr_setclock. The Windows stack-switch asm is byte-identical. - network: define SOCKET/INVALID_SOCKET for the non-Windows paths (were undefined at 20+ use sites), and rename the non-Windows kernel_clock_* helpers to the CamelCase names the callers already use. Both repair the shared non-Windows build. Integer reinterpret_cast -> static_cast. * loader: pin stack-switch asm operands to callee-saved registers RunEntry switches to the guest stack with an asm template that clobbers r12/r13 before consuming its inputs. With plain "r" constraints the compiler may place func/guest_rsp/guest_rbp into r12/r13, so 'callq *func' jumps through the saved host rsp -- a latent miscompile on every platform that any unrelated codegen change can trigger. Pin the inputs to rbx/r14/r15, which the template never touches and the SysV callee preserves. General correctness fix (not macOS-specific); the same fix is applied to pthread RunOnGuestStack. * macos: Vulkan/MoltenVK graphics enablement - pageManager: GPU write-tracking via Mach VM queries + mprotect (mprotect cannot report the previous protection, so the expected-old check is dropped), thread id via pthread_mach_thread_np, 4 KB page-size check -- __APPLE__-guarded. - shaders/renderDraw/vulkanWindow: MoltenVK lacks VK_EXT_color_write_enable, VK_EXT_depth_clip_enable and depthBounds; fall back to static color-write masks and default depth clipping, request VK_KHR_portability_subset, and reuse the graphics queue for present when only one queue is exposed. Non-Apple pipeline/extension setup is unchanged. - window: optional borderless window (KYTY_BORDERLESS) to sidestep a Rosetta NSException in macOS window chrome. * graphics: macOS thread identity for region tracking Region-ownership locks resolve the current thread via GetCurrentThreadId() on Windows and EXIT elsewhere. Use the Mach thread port on macOS (nonzero per-thread id; 0 stays the no-owner sentinel). * macos: marshal AppKit window operations to the main thread The present worker thread shows the window, updates its icon and title, and recreates a lost Vulkan surface. AppKit traps with 'Must only be used from the main thread' when these run off the main thread. Route them through a small task queue drained by the SDL main loop (an SDL_USEREVENT wakes the loop when it is blocked in SDL_WaitEvent). Title updates are fire-and-forget; showing the window and surface recreation wait for completion. Windows and Linux call the SDL functions directly, as before. * build: ignore the _Build output directory _Build is the conventional out-of-tree build location (only _Build/vscode-clang was ignored); a stray git add could sweep build artifacts into a commit. * macos: isolate stack-switch workaround --------- Co-authored-by: nmzik <Nmzik@mail.ru>
This commit is contained in:
M. Abdullah
@@ -19,6 +19,12 @@
|
||||
#include <windows.h>
|
||||
#undef min
|
||||
#undef max
|
||||
#elif defined(__APPLE__)
|
||||
#include <mach/mach.h>
|
||||
#include <mach/mach_vm.h>
|
||||
#include <pthread.h>
|
||||
#include <sys/mman.h>
|
||||
#include <unistd.h>
|
||||
#endif
|
||||
|
||||
namespace Libs::Graphics {
|
||||
@@ -28,16 +34,55 @@ constexpr uint64_t PAGE_SIZE = TRACKER_PAGE_SIZE;
|
||||
constexpr uint64_t REGION_SIZE = TRACKER_REGION_SIZE;
|
||||
constexpr uint64_t ADDRESS_SIZE = TRACKER_ADDRESS_SIZE;
|
||||
constexpr uint64_t REGION_COUNT = ADDRESS_SIZE / REGION_SIZE;
|
||||
|
||||
#if KYTY_PLATFORM != KYTY_PLATFORM_WINDOWS
|
||||
// The tracker reuses Win32 memory-protection tags as internal page-state values (on
|
||||
// Windows they come from <windows.h> and are what VirtualQuery returns). Mirror the
|
||||
// canonical Win32 numeric values so the shared state-machine logic is identical.
|
||||
constexpr uint32_t PAGE_NOACCESS = 0x01;
|
||||
constexpr uint32_t PAGE_READONLY = 0x02;
|
||||
constexpr uint32_t PAGE_READWRITE = 0x04;
|
||||
#endif
|
||||
constexpr uint64_t REGION_PAGES = REGION_SIZE / PAGE_SIZE;
|
||||
|
||||
#if KYTY_PLATFORM == KYTY_PLATFORM_WINDOWS
|
||||
constexpr uint32_t NO_ACCESS_PROTECTION = PAGE_NOACCESS;
|
||||
constexpr uint32_t READ_ONLY_PROTECTION = PAGE_READONLY;
|
||||
constexpr uint32_t NO_ACCESS_PROTECTION = PAGE_NOACCESS;
|
||||
constexpr uint32_t READ_ONLY_PROTECTION = PAGE_READONLY;
|
||||
constexpr uint32_t READ_WRITE_PROTECTION = PAGE_READWRITE;
|
||||
#else
|
||||
constexpr uint32_t NO_ACCESS_PROTECTION = 0;
|
||||
constexpr uint32_t READ_ONLY_PROTECTION = 1;
|
||||
constexpr uint32_t READ_WRITE_PROTECTION = 2;
|
||||
|
||||
#if defined(__APPLE__)
|
||||
// Map the tracker's Win32-style protection tags to POSIX mprotect flags.
|
||||
static int PageProtToPosix(uint32_t protection) {
|
||||
switch (protection) {
|
||||
case PAGE_NOACCESS: return PROT_NONE;
|
||||
case PAGE_READONLY: return PROT_READ;
|
||||
case PAGE_READWRITE: return PROT_READ | PROT_WRITE;
|
||||
default: return PROT_NONE;
|
||||
}
|
||||
}
|
||||
|
||||
// Query the current protection of the page containing vaddr via the Mach VM map and
|
||||
// collapse it to the tracker's read/write tags (execute is irrelevant to write tracking).
|
||||
static uint32_t MachQueryPageProt(uint64_t vaddr) {
|
||||
auto region_addr = static_cast<mach_vm_address_t>(vaddr);
|
||||
mach_vm_size_t region_size = 0;
|
||||
vm_region_basic_info_data_64_t info {};
|
||||
mach_msg_type_number_t count = VM_REGION_BASIC_INFO_COUNT_64;
|
||||
mach_port_t object_name = MACH_PORT_NULL;
|
||||
|
||||
kern_return_t kr =
|
||||
mach_vm_region(mach_task_self(), ®ion_addr, ®ion_size, VM_REGION_BASIC_INFO_64,
|
||||
reinterpret_cast<vm_region_info_t>(&info), &count, &object_name);
|
||||
if (kr != KERN_SUCCESS || region_addr > vaddr) {
|
||||
return PAGE_NOACCESS; // no region covering vaddr
|
||||
}
|
||||
if ((info.protection & VM_PROT_WRITE) != 0) {
|
||||
return PAGE_READWRITE;
|
||||
}
|
||||
if ((info.protection & VM_PROT_READ) != 0) {
|
||||
return PAGE_READONLY;
|
||||
}
|
||||
return PAGE_NOACCESS;
|
||||
}
|
||||
#endif
|
||||
|
||||
thread_local bool g_in_fault_resolution = false;
|
||||
@@ -78,6 +123,8 @@ thread_local bool g_in_fault_resolution = false;
|
||||
uint32_t CurrentThread() noexcept {
|
||||
#if KYTY_PLATFORM == KYTY_PLATFORM_WINDOWS
|
||||
return GetCurrentThreadId();
|
||||
#elif defined(__APPLE__)
|
||||
return static_cast<uint32_t>(pthread_mach_thread_np(pthread_self()));
|
||||
#else
|
||||
FailFast();
|
||||
#endif
|
||||
@@ -145,6 +192,12 @@ struct PageManager::Impl {
|
||||
Fatal("unsupported host page size 0x%08" PRIx32,
|
||||
static_cast<uint32_t>(info.dwPageSize));
|
||||
}
|
||||
#elif defined(__APPLE__)
|
||||
// Under Rosetta the host page size is 4 KB, matching TRACKER_PAGE_SIZE.
|
||||
if (static_cast<uint64_t>(getpagesize()) != PAGE_SIZE) {
|
||||
Fatal("unsupported host page size 0x%08" PRIx32,
|
||||
static_cast<uint32_t>(getpagesize()));
|
||||
}
|
||||
#else
|
||||
Fatal("page-fault invalidation is not implemented on this platform");
|
||||
#endif
|
||||
@@ -225,6 +278,14 @@ struct PageManager::Impl {
|
||||
vaddr, static_cast<uint32_t>(info.State), static_cast<uint32_t>(info.Protect));
|
||||
}
|
||||
return info.Protect;
|
||||
#elif defined(__APPLE__)
|
||||
const uint32_t protection = MachQueryPageProt(vaddr);
|
||||
if (protection != PAGE_READWRITE) {
|
||||
Fatal("basic path requires PAGE_READWRITE at 0x%016" PRIx64 " (protection=0x%08" PRIx32
|
||||
")",
|
||||
vaddr, protection);
|
||||
}
|
||||
return protection;
|
||||
#else
|
||||
(void)vaddr;
|
||||
Fatal("page query is unsupported on this platform");
|
||||
@@ -245,6 +306,14 @@ struct PageManager::Impl {
|
||||
case PageFaultAccess::Write: return info.Protect == PAGE_READWRITE;
|
||||
default: return false;
|
||||
}
|
||||
#elif defined(__APPLE__)
|
||||
const uint32_t protection = MachQueryPageProt(vaddr);
|
||||
switch (access) {
|
||||
case PageFaultAccess::Read:
|
||||
return protection == PAGE_READONLY || protection == PAGE_READWRITE;
|
||||
case PageFaultAccess::Write: return protection == PAGE_READWRITE;
|
||||
default: return false;
|
||||
}
|
||||
#else
|
||||
(void)vaddr;
|
||||
return false;
|
||||
@@ -265,6 +334,18 @@ struct PageManager::Impl {
|
||||
", expected=0x%08" PRIx32 ", new=0x%08" PRIx32,
|
||||
vaddr, static_cast<uint32_t>(old_protection), expected_old, protection);
|
||||
}
|
||||
#elif defined(__APPLE__)
|
||||
// mprotect cannot report the previous protection, so the expected_old comparison
|
||||
// is dropped; the tracker is the sole mutator of these pages and drives the
|
||||
// transition from its own shadow state.
|
||||
(void)expected_old;
|
||||
if (mprotect(reinterpret_cast<void*>(static_cast<uintptr_t>(vaddr)), PAGE_SIZE,
|
||||
PageProtToPosix(protection)) != 0) {
|
||||
if (fault_path) {
|
||||
FailFast("mprotect fault transition failed");
|
||||
}
|
||||
Fatal("mprotect failed at 0x%016" PRIx64 ", new=0x%08" PRIx32, vaddr, protection);
|
||||
}
|
||||
#else
|
||||
(void)vaddr;
|
||||
(void)protection;
|
||||
|
||||
@@ -16,6 +16,8 @@
|
||||
#include <windows.h>
|
||||
#undef min
|
||||
#undef max
|
||||
#elif defined(__APPLE__)
|
||||
#include <pthread.h>
|
||||
#endif
|
||||
|
||||
namespace Libs::Graphics {
|
||||
@@ -49,6 +51,9 @@ private:
|
||||
static uint32_t CurrentThread() noexcept {
|
||||
#if KYTY_PLATFORM == KYTY_PLATFORM_WINDOWS
|
||||
return GetCurrentThreadId();
|
||||
#elif defined(__APPLE__)
|
||||
// mach thread port is a nonzero per-thread id (0 is the "no owner" sentinel).
|
||||
return static_cast<uint32_t>(pthread_mach_thread_np(pthread_self()));
|
||||
#else
|
||||
EXIT("region tracking thread identity is unsupported on this platform\n");
|
||||
#endif
|
||||
|
||||
@@ -395,6 +395,10 @@ static void SetDynamicParams(const RenderCommandBuffer& buffer, vk::CommandBuffe
|
||||
dynamic_params.stencil_back.reference);
|
||||
}
|
||||
|
||||
#if defined(__APPLE__)
|
||||
// MoltenVK has no VK_EXT_color_write_enable; the pipeline is created without the
|
||||
// eColorWriteEnableEXT dynamic state and relies on the static colorWriteMask instead.
|
||||
#else
|
||||
vk::Bool32 enable[RENDER_COLOR_ATTACHMENTS_MAX] = {};
|
||||
for (uint32_t i = 0; i < dynamic_params.color_write_count; i++) {
|
||||
enable[i] = (dynamic_params.color_write_enable[i] ? VK_TRUE : VK_FALSE);
|
||||
@@ -402,6 +406,7 @@ static void SetDynamicParams(const RenderCommandBuffer& buffer, vk::CommandBuffe
|
||||
if (dynamic_params.color_write_count != 0) {
|
||||
vk_buffer.setColorWriteEnableEXT(dynamic_params.color_write_count, enable);
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
static bool DrawHasValidVertexShader(const HW::Shader& sh_ctx) {
|
||||
|
||||
@@ -729,7 +729,13 @@ void CreatePipelineInternal(GraphicContext& graphics, DescriptorCache& descripto
|
||||
|
||||
vk::PipelineRasterizationStateCreateInfo rasterizer {};
|
||||
rasterizer.sType = vk::StructureType::ePipelineRasterizationStateCreateInfo;
|
||||
// MoltenVK lacks VK_EXT_depth_clip_enable; omit the depth-clip struct on macOS and accept
|
||||
// Vulkan's default depth clipping (enabled) instead of the PS5's clamp behavior.
|
||||
#if defined(__APPLE__)
|
||||
rasterizer.pNext = nullptr;
|
||||
#else
|
||||
rasterizer.pNext = &clip_ext;
|
||||
#endif
|
||||
rasterizer.flags = {};
|
||||
rasterizer.depthClampEnable = VK_FALSE;
|
||||
rasterizer.rasterizerDiscardEnable = VK_FALSE;
|
||||
@@ -807,7 +813,13 @@ void CreatePipelineInternal(GraphicContext& graphics, DescriptorCache& descripto
|
||||
|
||||
vk::PipelineColorBlendStateCreateInfo color_blending {};
|
||||
color_blending.sType = vk::StructureType::ePipelineColorBlendStateCreateInfo;
|
||||
// MoltenVK lacks VK_EXT_color_write_enable; drop the dynamic color-write struct on macOS
|
||||
// and rely on each attachment's static colorWriteMask (all channels enabled by default).
|
||||
#if defined(__APPLE__)
|
||||
color_blending.pNext = nullptr;
|
||||
#else
|
||||
color_blending.pNext = &color_write;
|
||||
#endif
|
||||
color_blending.flags = {};
|
||||
color_blending.logicOpEnable = VK_FALSE;
|
||||
color_blending.logicOp = vk::LogicOp::eCopy;
|
||||
@@ -873,7 +885,11 @@ void CreatePipelineInternal(GraphicContext& graphics, DescriptorCache& descripto
|
||||
depth_stencil_info.depthWriteEnable = (static_params.depth_write_enable ? VK_TRUE : VK_FALSE);
|
||||
depth_stencil_info.depthCompareOp = static_params.depth_compare_op;
|
||||
depth_stencil_info.depthBoundsTestEnable =
|
||||
#if defined(__APPLE__)
|
||||
VK_FALSE; // MoltenVK lacks the depthBounds feature; depth-bounds testing is disabled
|
||||
#else
|
||||
(static_params.depth_bounds_test_enable ? VK_TRUE : VK_FALSE);
|
||||
#endif
|
||||
depth_stencil_info.stencilTestEnable = (static_params.stencil_test_enable ? VK_TRUE : VK_FALSE);
|
||||
depth_stencil_info.front.failOp = static_params.stencil_front.failOp;
|
||||
depth_stencil_info.front.passOp = static_params.stencil_front.passOp;
|
||||
@@ -893,7 +909,9 @@ void CreatePipelineInternal(GraphicContext& graphics, DescriptorCache& descripto
|
||||
vk::DynamicState::eStencilCompareMask,
|
||||
vk::DynamicState::eStencilReference,
|
||||
vk::DynamicState::eStencilWriteMask,
|
||||
vk::DynamicState::eColorWriteEnableEXT,
|
||||
#if !defined(__APPLE__)
|
||||
vk::DynamicState::eColorWriteEnableEXT, // unsupported by MoltenVK; static mask instead
|
||||
#endif
|
||||
};
|
||||
const auto dynamic_states_count =
|
||||
static_cast<uint32_t>(sizeof(dynamic_states) / sizeof(dynamic_states[0]));
|
||||
|
||||
Reference in New Issue
Block a user