Fixes and workarounds to make UBSan happier on macOS

There are still some other issues not addressed here, but it's a start.

Workarounds for false-positive reports:

- `RasterizerAccelerated`: Put a gigantic array behind a `unique_ptr`,
  because UBSan has a [hardcoded limit](https://stackoverflow.com/questions/64531383/c-runtime-error-using-fsanitize-undefined-object-has-a-possibly-invalid-vp)
  of how big it thinks objects can be, specifically when dealing with
  offset-to-top values used with multiple inheritance.  Hopefully this
  doesn't have a performance impact.

- `QueryCacheBase::QueryCacheBase`: Avoid an operation that UBSan thinks
  is UB even though it at least arguably isn't.  See the link in the
  comment for more information.

Fixes for correct reports:

- `PageTable`, `Memory`: Use `uintptr_t` values instead of pointers to
  avoid UB from pointer overflow (when pointer arithmetic wraps around
  the address space).

- `KScheduler::Reload`: `thread->GetOwnerProcess()` can be `nullptr`;
  avoid calling methods on it in this case.  (The existing code returns
  a garbage reference to a field, which is then passed into
  `LoadWatchpointArray`, and apparently it's never used, so it's
  harmless in practice but still triggers UBSan.)

- `KAutoObject::Close`: This function calls `this->Destroy()`, which
  overwrites the beginning of the object with junk (specifically a free
  list pointer).  Then it calls `this->UnregisterWithKernel()`.  UBSan
  complains about a type mismatch because the vtable has been
  overwritten, and I believe this is indeed UB.  `UnregisterWithKernel`
  also loads `m_kernel` from the 'freed' object, which seems to be
  technically safe (the overwriting doesn't extend as far as that
  field), but seems dubious.  Switch to a `static` method and load
  `m_kernel` in advance.

src/common/page_table.h

@@ -51,7 +51,7 @@ struct PageTable {
     class PageInfo {
     public:
         /// Returns the page pointer
-        [[nodiscard]] u8* Pointer() const noexcept {
+        [[nodiscard]] uintptr_t Pointer() const noexcept {
             return ExtractPointer(raw.load(std::memory_order_relaxed));
         }
 
@@ -61,7 +61,7 @@ struct PageTable {
         }
 
         /// Returns the page pointer and attribute pair, extracted from the same atomic read
-        [[nodiscard]] std::pair<u8*, PageType> PointerType() const noexcept {
+        [[nodiscard]] std::pair<uintptr_t, PageType> PointerType() const noexcept {
             const uintptr_t non_atomic_raw = raw.load(std::memory_order_relaxed);
             return {ExtractPointer(non_atomic_raw), ExtractType(non_atomic_raw)};
         }
@@ -73,13 +73,13 @@ struct PageTable {
         }
 
         /// Write a page pointer and type pair atomically
-        void Store(u8* pointer, PageType type) noexcept {
-            raw.store(reinterpret_cast<uintptr_t>(pointer) | static_cast<uintptr_t>(type));
+        void Store(uintptr_t pointer, PageType type) noexcept {
+            raw.store(pointer | static_cast<uintptr_t>(type));
         }
 
         /// Unpack a pointer from a page info raw representation
-        [[nodiscard]] static u8* ExtractPointer(uintptr_t raw) noexcept {
-            return reinterpret_cast<u8*>(raw & (~uintptr_t{0} << ATTRIBUTE_BITS));
+        [[nodiscard]] static uintptr_t ExtractPointer(uintptr_t raw) noexcept {
+            return raw & (~uintptr_t{0} << ATTRIBUTE_BITS);
         }
 
         /// Unpack a page type from a page info raw representation

src/core/arm/arm_interface.cpp

@@ -217,8 +217,8 @@ void ARM_Interface::Run() {
     }
 }
 
-void ARM_Interface::LoadWatchpointArray(const WatchpointArray& wp) {
-    watchpoints = ℘
+void ARM_Interface::LoadWatchpointArray(const WatchpointArray* wp) {
+    watchpoints = wp;
 }
 
 const Kernel::DebugWatchpoint* ARM_Interface::MatchingWatchpoint(

src/core/arm/arm_interface.h

@@ -186,7 +186,7 @@ public:
     virtual void SaveContext(ThreadContext64& ctx) const = 0;
     virtual void LoadContext(const ThreadContext32& ctx) = 0;
     virtual void LoadContext(const ThreadContext64& ctx) = 0;
-    void LoadWatchpointArray(const WatchpointArray& wp);
+    void LoadWatchpointArray(const WatchpointArray* wp);
 
     /// Clears the exclusive monitor's state.
     virtual void ClearExclusiveState() = 0;

src/core/hle/kernel/k_auto_object.cpp

@@ -15,8 +15,8 @@ void KAutoObject::RegisterWithKernel() {
     m_kernel.RegisterKernelObject(this);
 }
 
-void KAutoObject::UnregisterWithKernel() {
-    m_kernel.UnregisterKernelObject(this);
+void KAutoObject::UnregisterWithKernel(KernelCore& kernel, KAutoObject* self) {
+    kernel.UnregisterKernelObject(self);
 }
 
 } // namespace Kernel

src/core/hle/kernel/k_auto_object.h

@@ -159,14 +159,15 @@ public:
 
         // If ref count hits zero, destroy the object.
         if (cur_ref_count - 1 == 0) {
+            KernelCore& kernel = m_kernel;
             this->Destroy();
-            this->UnregisterWithKernel();
+            KAutoObject::UnregisterWithKernel(kernel, this);
         }
     }
 
 private:
     void RegisterWithKernel();
-    void UnregisterWithKernel();
+    static void UnregisterWithKernel(KernelCore& kernel, KAutoObject* self);
 
 protected:
     KernelCore& m_kernel;

src/core/hle/kernel/k_scheduler.cpp

@@ -510,11 +510,12 @@ void KScheduler::Unload(KThread* thread) {
 
 void KScheduler::Reload(KThread* thread) {
     auto& cpu_core = m_kernel.System().ArmInterface(m_core_id);
+    auto* process = thread->GetOwnerProcess();
     cpu_core.LoadContext(thread->GetContext32());
     cpu_core.LoadContext(thread->GetContext64());
     cpu_core.SetTlsAddress(GetInteger(thread->GetTlsAddress()));
     cpu_core.SetTPIDR_EL0(thread->GetTpidrEl0());
-    cpu_core.LoadWatchpointArray(thread->GetOwnerProcess()->GetWatchpoints());
+    cpu_core.LoadWatchpointArray(process ? &process->GetWatchpoints() : nullptr);
     cpu_core.ClearExclusiveState();
 }
 

src/core/hle/kernel/k_thread.cpp

@@ -129,7 +129,7 @@ Result KThread::Initialize(KThreadFunction func, uintptr_t arg, KProcessAddress
     case ThreadType::User:
         ASSERT(((owner == nullptr) ||
                 (owner->GetCoreMask() | (1ULL << virt_core)) == owner->GetCoreMask()));
-        ASSERT(((owner == nullptr) ||
+        ASSERT(((owner == nullptr) || (prio > Svc::LowestThreadPriority) ||
                 (owner->GetPriorityMask() | (1ULL << prio)) == owner->GetPriorityMask()));
         break;
     case ThreadType::Kernel:

src/core/memory.cpp

@@ -73,7 +73,7 @@ struct Memory::Impl {
             return {};
         }
 
-        return system.DeviceMemory().GetPointer<u8>(paddr) + vaddr;
+        return system.DeviceMemory().GetPointer<u8>(paddr + vaddr);
     }
 
     [[nodiscard]] u8* GetPointerFromDebugMemory(u64 vaddr) const {
@@ -84,7 +84,7 @@ struct Memory::Impl {
             return {};
         }
 
-        return system.DeviceMemory().GetPointer<u8>(paddr) + vaddr;
+        return system.DeviceMemory().GetPointer<u8>(paddr + vaddr);
     }
 
     u8 Read8(const Common::ProcessAddress addr) {
@@ -204,7 +204,8 @@ struct Memory::Impl {
                 break;
             }
             case Common::PageType::Memory: {
-                u8* mem_ptr = pointer + page_offset + (page_index << YUZU_PAGEBITS);
+                u8* mem_ptr =
+                    reinterpret_cast<u8*>(pointer + page_offset + (page_index << YUZU_PAGEBITS));
                 on_memory(copy_amount, mem_ptr);
                 break;
             }
@@ -448,7 +449,7 @@ struct Memory::Impl {
                     break;
                 case Common::PageType::Memory:
                     current_page_table->pointers[vaddr >> YUZU_PAGEBITS].Store(
-                        nullptr, Common::PageType::DebugMemory);
+                        0, Common::PageType::DebugMemory);
                     break;
                 default:
                     UNREACHABLE();
@@ -466,7 +467,8 @@ struct Memory::Impl {
                 case Common::PageType::DebugMemory: {
                     u8* const pointer{GetPointerFromDebugMemory(vaddr & ~YUZU_PAGEMASK)};
                     current_page_table->pointers[vaddr >> YUZU_PAGEBITS].Store(
-                        pointer - (vaddr & ~YUZU_PAGEMASK), Common::PageType::Memory);
+                        reinterpret_cast<uintptr_t>(pointer) - (vaddr & ~YUZU_PAGEMASK),
+                        Common::PageType::Memory);
                     break;
                 }
                 default:
@@ -506,7 +508,7 @@ struct Memory::Impl {
                 case Common::PageType::DebugMemory:
                 case Common::PageType::Memory:
                     current_page_table->pointers[vaddr >> YUZU_PAGEBITS].Store(
-                        nullptr, Common::PageType::RasterizerCachedMemory);
+                        0, Common::PageType::RasterizerCachedMemory);
                     break;
                 case Common::PageType::RasterizerCachedMemory:
                     // There can be more than one GPU region mapped per CPU region, so it's common
@@ -534,10 +536,11 @@ struct Memory::Impl {
                         // pagetable after unmapping a VMA. In that case the underlying VMA will no
                         // longer exist, and we should just leave the pagetable entry blank.
                         current_page_table->pointers[vaddr >> YUZU_PAGEBITS].Store(
-                            nullptr, Common::PageType::Unmapped);
+                            0, Common::PageType::Unmapped);
                     } else {
                         current_page_table->pointers[vaddr >> YUZU_PAGEBITS].Store(
-                            pointer - (vaddr & ~YUZU_PAGEMASK), Common::PageType::Memory);
+                            reinterpret_cast<uintptr_t>(pointer) - (vaddr & ~YUZU_PAGEMASK),
+                            Common::PageType::Memory);
                     }
                     break;
                 }
@@ -584,7 +587,7 @@ struct Memory::Impl {
                        "Mapping memory page without a pointer @ {:016x}", base * YUZU_PAGESIZE);
 
             while (base != end) {
-                page_table.pointers[base].Store(nullptr, type);
+                page_table.pointers[base].Store(0, type);
                 page_table.backing_addr[base] = 0;
                 page_table.blocks[base] = 0;
                 base += 1;
@@ -593,7 +596,8 @@ struct Memory::Impl {
             auto orig_base = base;
             while (base != end) {
                 auto host_ptr =
-                    system.DeviceMemory().GetPointer<u8>(target) - (base << YUZU_PAGEBITS);
+                    reinterpret_cast<uintptr_t>(system.DeviceMemory().GetPointer<u8>(target)) -
+                    (base << YUZU_PAGEBITS);
                 auto backing = GetInteger(target) - (base << YUZU_PAGEBITS);
                 page_table.pointers[base].Store(host_ptr, type);
                 page_table.backing_addr[base] = backing;
@@ -619,8 +623,8 @@ struct Memory::Impl {
 
         // Avoid adding any extra logic to this fast-path block
         const uintptr_t raw_pointer = current_page_table->pointers[vaddr >> YUZU_PAGEBITS].Raw();
-        if (u8* const pointer = Common::PageTable::PageInfo::ExtractPointer(raw_pointer)) {
-            return &pointer[vaddr];
+        if (const uintptr_t pointer = Common::PageTable::PageInfo::ExtractPointer(raw_pointer)) {
+            return reinterpret_cast<u8*>(pointer + vaddr);
         }
         switch (Common::PageTable::PageInfo::ExtractType(raw_pointer)) {
         case Common::PageType::Unmapped:
@@ -814,7 +818,7 @@ bool Memory::IsValidVirtualAddress(const Common::ProcessAddress vaddr) const {
         return false;
     }
     const auto [pointer, type] = page_table.pointers[page].PointerType();
-    return pointer != nullptr || type == Common::PageType::RasterizerCachedMemory ||
+    return pointer != 0 || type == Common::PageType::RasterizerCachedMemory ||
            type == Common::PageType::DebugMemory;
 }
 

src/video_core/query_cache.h

@@ -103,7 +103,9 @@ public:
     explicit QueryCacheBase(VideoCore::RasterizerInterface& rasterizer_,
                             Core::Memory::Memory& cpu_memory_)
         : rasterizer{rasterizer_},
-          cpu_memory{cpu_memory_}, streams{{CounterStream{static_cast<QueryCache&>(*this),
+          // Use reinterpret_cast instead of static_cast as workaround for
+          // UBSan bug (https://github.com/llvm/llvm-project/issues/59060)
+          cpu_memory{cpu_memory_}, streams{{CounterStream{reinterpret_cast<QueryCache&>(*this),
                                                           VideoCore::QueryType::SamplesPassed}}} {
         (void)slot_async_jobs.insert(); // Null value
     }

src/video_core/rasterizer_accelerated.cpp

@@ -13,7 +13,8 @@ namespace VideoCore {
 
 using namespace Core::Memory;
 
-RasterizerAccelerated::RasterizerAccelerated(Memory& cpu_memory_) : cpu_memory{cpu_memory_} {}
+RasterizerAccelerated::RasterizerAccelerated(Memory& cpu_memory_)
+    : cached_pages(std::make_unique<CachedPages>()), cpu_memory{cpu_memory_} {}
 
 RasterizerAccelerated::~RasterizerAccelerated() = default;
 
@@ -26,7 +27,7 @@ void RasterizerAccelerated::UpdatePagesCachedCount(VAddr addr, u64 size, int del
     std::atomic_thread_fence(std::memory_order_acquire);
     const u64 page_end = Common::DivCeil(addr + size, YUZU_PAGESIZE);
     for (u64 page = addr >> YUZU_PAGEBITS; page != page_end; ++page) {
-        std::atomic_uint16_t& count = cached_pages.at(page >> 2).Count(page);
+        std::atomic_uint16_t& count = cached_pages->at(page >> 2).Count(page);
 
         if (delta > 0) {
             ASSERT_MSG(count.load(std::memory_order::relaxed) < UINT16_MAX, "Count may overflow!");

src/video_core/rasterizer_accelerated.h

@@ -41,7 +41,8 @@ private:
     };
     static_assert(sizeof(CacheEntry) == 8, "CacheEntry should be 8 bytes!");
 
-    std::array<CacheEntry, 0x2000000> cached_pages;
+    using CachedPages = std::array<CacheEntry, 0x2000000>;
+    std::unique_ptr<CachedPages> cached_pages;
     Core::Memory::Memory& cpu_memory;
 };