2026-09-06 21:26:09

Signed-off-by: lizzie <lizzie@eden-emu.dev>

src/dynarmic/CMakeLists.txt

@@ -11,34 +11,15 @@ set(dynarmic_VERSION ${dynarmic_VERSION_MAJOR}.${dynarmic_VERSION_MINOR}.${dynar
 
 project(dynarmic LANGUAGES C CXX ASM VERSION ${dynarmic_VERSION})
 
-# Determine if we're built as a subproject (using add_subdirectory)
-# or if this is the master project.
-set(MASTER_PROJECT OFF)
-if (CMAKE_CURRENT_SOURCE_DIR STREQUAL CMAKE_SOURCE_DIR)
-  set(MASTER_PROJECT ON)
-endif()
-
-if (MASTER_PROJECT)
-    include(CTest)
-endif()
-
-# Dynarmic project options
-option(DYNARMIC_ENABLE_CPU_FEATURE_DETECTION "Turning this off causes dynarmic to assume the host CPU doesn't support anything later than SSE3" ON)
-
 if (OPENBSD OR DRAGONFLY OR NETBSD)
     set(REQUIRE_WX ON)
 else()
     set(REQUIRE_WX OFF)
 endif()
 option(DYNARMIC_ENABLE_NO_EXECUTE_SUPPORT "Enables support for systems that require W^X" ${REQUIRE_WX})
-
-option(DYNARMIC_IGNORE_ASSERTS "Ignore asserts" ON)
 option(DYNARMIC_TESTS_USE_UNICORN "Enable fuzzing tests against unicorn" OFF)
 CMAKE_DEPENDENT_OPTION(DYNARMIC_USE_LLVM "Support disassembly of jitted x86_64 code using LLVM" OFF "NOT YUZU_DISABLE_LLVM" OFF)
 
-option(DYNARMIC_INSTALL "Install dynarmic headers and CMake files" OFF)
-option(DYNARMIC_USE_BUNDLED_EXTERNALS "Use all bundled externals (useful when e.g. cross-compiling)" OFF)
-
 # Set hard requirements for C++
 set(CMAKE_CXX_STANDARD 20)
 set(CMAKE_CXX_STANDARD_REQUIRED ON)
@@ -88,7 +69,7 @@ if (MSVC)
              -Wno-missing-braces)
     endif()
 else()
-    set(DYNARMIC_CXX_FLAGS
+    list(APPEND DYNARMIC_CXX_FLAGS
         -Wall
         -Wextra
         -Wcast-qual
@@ -103,37 +84,35 @@ else()
         # to Address& after first checking isMEM(), and that code is inlined in a situation where
         # GCC knows that the variable is actually a Reg64.  isMEM() will never return true for a
         # Reg64, but GCC doesn't know that.
-        list(APPEND DYNARMIC_CXX_FLAGS -Wno-array-bounds)
-        list(APPEND DYNARMIC_CXX_FLAGS -Wstack-usage=4096)
+        list(APPEND DYNARMIC_CXX_FLAGS
+            -Wno-array-bounds
+            -Wstack-usage=4096)
     endif()
     if (CXX_CLANG)
-        # Bracket depth determines maximum size of a fold expression in Clang since 9c9974c3ccb6.
-        # And this in turns limits the size of a std::array.
-        list(APPEND DYNARMIC_CXX_FLAGS -fbracket-depth=1024)
-        # Clang mistakenly blames CMake for using unused arguments during compilation
-        list(APPEND DYNARMIC_CXX_FLAGS -Wno-unused-command-line-argument)
+        list(APPEND DYNARMIC_CXX_FLAGS
+            # Bracket depth determines maximum size of a fold expression in Clang since 9c9974c3ccb6.
+            # And this in turns limits the size of a std::array.
+            -fbracket-depth=1024
+            # Clang mistakenly blames CMake for using unused arguments during compilation
+            -Wno-unused-command-line-argument)
     endif()
 endif()
 
 if (NOT Boost_FOUND)
     find_package(Boost 1.57 REQUIRED)
 endif()
-
 find_package(fmt 8 CONFIG)
 
-if ("arm64" IN_LIST ARCHITECTURE OR DYNARMIC_TESTS)
+if (ARCHITECTURE_arm64)
     find_package(oaknut 2.0.1 CONFIG)
 endif()
-
-if ("riscv64" IN_LIST ARCHITECTURE)
+if (ARCHITECTURE_riscv64)
     find_package(biscuit 0.9.1 REQUIRED)
 endif()
-
-if ("loongarch64" IN_LIST ARCHITECTURE)
+if (ARCHITECTURE_loongarch64)
     find_package(lagoon REQUIRED)
 endif()
-
-if ("x86_64" IN_LIST ARCHITECTURE)
+if (ARCHITECTURE_x86_64)
     find_package(xbyak 7 CONFIG)
 endif()
 
@@ -142,44 +121,12 @@ if (DYNARMIC_USE_LLVM)
     separate_arguments(LLVM_DEFINITIONS)
 endif()
 
+# Dynarmic project files
+add_subdirectory(src/dynarmic)
 if (DYNARMIC_TESTS)
     find_package(Catch2 3 CONFIG)
     if (DYNARMIC_TESTS_USE_UNICORN)
         find_package(Unicorn REQUIRED)
     endif()
-endif()
-
-# Dynarmic project files
-add_subdirectory(src/dynarmic)
-if (DYNARMIC_TESTS)
     add_subdirectory(tests)
 endif()
-
-#
-# Install
-#
-if (DYNARMIC_INSTALL)
-    include(GNUInstallDirs)
-    include(CMakePackageConfigHelpers)
-
-    install(TARGETS dynarmic EXPORT dynarmicTargets)
-    install(EXPORT dynarmicTargets
-        NAMESPACE dynarmic::
-        DESTINATION "${CMAKE_INSTALL_LIBDIR}/cmake/dynarmic"
-    )
-
-    configure_package_config_file(CMakeModules/dynarmicConfig.cmake.in
-        dynarmicConfig.cmake
-        INSTALL_DESTINATION "${CMAKE_INSTALL_LIBDIR}/cmake/dynarmic"
-    )
-    write_basic_package_version_file(dynarmicConfigVersion.cmake
-        COMPATIBILITY SameMajorVersion
-    )
-    install(FILES
-        "${CMAKE_CURRENT_BINARY_DIR}/dynarmicConfig.cmake"
-        "${CMAKE_CURRENT_BINARY_DIR}/dynarmicConfigVersion.cmake"
-        DESTINATION "${CMAKE_INSTALL_LIBDIR}/cmake/dynarmic"
-    )
-
-    install(DIRECTORY src/dynarmic TYPE INCLUDE FILES_MATCHING PATTERN "*.h")
-endif()

src/dynarmic/CMakeModules/TargetArchitectureSpecificSources.cmake

@@ -1,29 +0,0 @@
-# SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
-# SPDX-License-Identifier: GPL-3.0-or-later
-
-function(target_architecture_specific_sources project arch)
-    if (NOT MULTIARCH_BUILD)
-        target_sources("${project}" PRIVATE ${ARGN})
-        return()
-    endif()
-
-    foreach(input_file IN LISTS ARGN)
-        if(input_file MATCHES ".cpp$")
-            if(NOT IS_ABSOLUTE ${input_file})
-                set(input_file "${CMAKE_CURRENT_SOURCE_DIR}/${input_file}")
-            endif()
-
-            set(output_file "${CMAKE_CURRENT_BINARY_DIR}/arch_gen/${input_file}")
-            add_custom_command(
-                OUTPUT "${output_file}"
-                COMMAND ${CMAKE_COMMAND} "-Darch=${arch}"
-                                         "-Dinput_file=${input_file}"
-                                         "-Doutput_file=${output_file}"
-                                         -P "${CMAKE_CURRENT_FUNCTION_LIST_DIR}/impl/TargetArchitectureSpecificSourcesWrapFile.cmake"
-                DEPENDS "${input_file}"
-                VERBATIM
-            )
-            target_sources(${project} PRIVATE "${output_file}")
-        endif()
-    endforeach()
-endfunction()

src/dynarmic/CMakeModules/dynarmicConfig.cmake.in

@@ -1,31 +0,0 @@
-@PACKAGE_INIT@
-
-include(CMakeFindDependencyMacro)
-
-set(ARCHITECTURE "@ARCHITECTURE@")
-
-if (NOT @BUILD_SHARED_LIBS@)
-    find_dependency(Boost 1.57)
-    find_dependency(fmt 9)
-    find_dependency(mcl 0.1.12 EXACT)
-
-    if ("arm64" IN_LIST ARCHITECTURE)
-        find_dependency(oaknut 2.0.1)
-    endif()
-
-    if ("riscv" IN_LIST ARCHITECTURE)
-        find_dependency(biscuit 0.9.1)
-    endif()
-
-    if ("x86_64" IN_LIST ARCHITECTURE)
-        find_dependency(xbyak 7)
-    endif()
-
-    if (@DYNARMIC_USE_LLVM@)
-        find_dependency(LLVM)
-    endif()
-endif()
-
-include("${CMAKE_CURRENT_LIST_DIR}/@PROJECT_NAME@Targets.cmake")
-
-check_required_components(@PROJECT_NAME@)

src/dynarmic/CMakeModules/impl/TargetArchitectureSpecificSourcesWrapFile.cmake

@@ -1,6 +0,0 @@
-# SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
-# SPDX-License-Identifier: GPL-3.0-or-later
-
-string(TOUPPER "${arch}" arch)
-file(READ "${input_file}" f_contents)
-file(WRITE "${output_file}" "#if defined(ARCHITECTURE_${arch})\n${f_contents}\n#endif\n")

src/dynarmic/src/dynarmic/CMakeLists.txt

@@ -1,7 +1,5 @@
 # SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
 # SPDX-License-Identifier: GPL-3.0-or-later
-include(TargetArchitectureSpecificSources)
-
 add_library(dynarmic STATIC
     mcl/bit.hpp
     mcl/function_info.hpp
@@ -135,7 +133,7 @@ add_library(dynarmic STATIC
     interface/A64/config.h
 )
 
-if ("x86_64" IN_LIST ARCHITECTURE)
+if (ARCHITECTURE_x86_64)
     # Newer versions of xbyak (>= 7.25.0) have stricter checks that currently
     # fail in dynarmic
     target_compile_definitions(dynarmic PRIVATE XBYAK_STRICT_CHECK_MEM_REG_SIZE=0)
@@ -143,7 +141,7 @@ if ("x86_64" IN_LIST ARCHITECTURE)
     target_compile_definitions(dynarmic PRIVATE XBYAK_OLD_DISP_CHECK=1)
     target_link_libraries(dynarmic PRIVATE xbyak::xbyak)
 
-    target_architecture_specific_sources(dynarmic "x86_64"
+    target_sources(dynarmic PRIVATE
         backend/x64/abi.cpp
         backend/x64/abi.h
         backend/x64/block_of_code.cpp
@@ -201,10 +199,10 @@ if ("x86_64" IN_LIST ARCHITECTURE)
     )
 endif()
 
-if ("arm64" IN_LIST ARCHITECTURE)
+if (ARCHITECTURE_arm64)
     target_link_libraries(dynarmic PRIVATE merry::oaknut)
 
-    target_architecture_specific_sources(dynarmic "arm64"
+    target_sources(dynarmic PRIVATE
         backend/arm64/a32_jitstate.cpp
         backend/arm64/a32_jitstate.h
         backend/arm64/a64_jitstate.h
@@ -255,7 +253,7 @@ if ("arm64" IN_LIST ARCHITECTURE)
     )
 endif()
 
-if ("riscv64" IN_LIST ARCHITECTURE)
+if (ARCHITECTURE_riscv64)
     target_link_libraries(dynarmic PRIVATE biscuit::biscuit)
 
     target_sources(dynarmic PRIVATE
@@ -295,7 +293,7 @@ if ("riscv64" IN_LIST ARCHITECTURE)
     message(WARNING "TODO: Incomplete frontend for this host architecture")
 endif()
 
-if ("loongarch64" IN_LIST ARCHITECTURE)
+if (ARCHITECTURE_loongarch64)
     target_link_libraries(dynarmic PRIVATE lagoon::lagoon)
 
     target_sources(dynarmic PRIVATE
@@ -400,15 +398,9 @@ if (DYNARMIC_USE_LLVM)
     target_compile_definitions(dynarmic PRIVATE DYNARMIC_USE_LLVM=1 ${LLVM_DEFINITIONS})
     llvm_config(dynarmic USE_SHARED armdesc armdisassembler aarch64desc aarch64disassembler x86desc x86disassembler)
 endif()
-if (DYNARMIC_ENABLE_CPU_FEATURE_DETECTION)
-    target_compile_definitions(dynarmic PRIVATE DYNARMIC_ENABLE_CPU_FEATURE_DETECTION=1)
-endif()
 if (DYNARMIC_ENABLE_NO_EXECUTE_SUPPORT)
     target_compile_definitions(dynarmic PRIVATE DYNARMIC_ENABLE_NO_EXECUTE_SUPPORT=1)
 endif()
-if (DYNARMIC_IGNORE_ASSERTS)
-    target_compile_definitions(dynarmic PRIVATE MCL_IGNORE_ASSERTS=1)
-endif()
 if (CMAKE_SYSTEM_NAME STREQUAL "Windows")
     target_compile_definitions(dynarmic PRIVATE FMT_USE_WINDOWS_H=0)
 endif()

src/dynarmic/src/dynarmic/backend/x64/block_of_code.cpp

@@ -78,7 +78,6 @@ void ProtectMemory(const void* base, size_t size, bool is_executable) {
 
 static const HostFeature features = []() {
     HostFeature f{};
-#ifdef DYNARMIC_ENABLE_CPU_FEATURE_DETECTION
     using Cpu = Xbyak::util::Cpu;
     Xbyak::util::Cpu cpu_info{};
     if (cpu_info.has(Cpu::tSSSE3)) f |= HostFeature::SSSE3;
@@ -121,7 +120,6 @@ static const HostFeature features = []() {
         }
     }
     return f;
-#endif
 }();
 HostFeature GetHostFeatures() {
     return features;

src/dynarmic/src/dynarmic/backend/x64/emit_x64_memory.h

@@ -235,6 +235,7 @@ const void* EmitReadMemoryMov(BlockOfCode& code, int value_idx, const Xbyak::Reg
             code.xadd(qword[addr], Xbyak::Reg64(value_idx));
             break;
         case 128:
+            ASSERT(Xbyak::Xmm(value_idx) != xmm0);
             code.lock();
             code.cmpxchg16b(xword[addr]);
             if (code.HasHostFeature(HostFeature::SSE41)) {

src/dynarmic/src/dynarmic/backend/x64/emit_x64_vector.cpp

@@ -6226,9 +6226,7 @@ void EmitX64::EmitVectorZeroExtend64(EmitContext& ctx, IR::Inst* inst) {
 void EmitX64::EmitVectorZeroUpper(EmitContext& ctx, IR::Inst* inst) {
     auto args = ctx.reg_alloc.GetArgumentInfo(inst);
     auto const a = ctx.reg_alloc.UseScratchXmm(code, args[0]);
-
     code.movq(a, a);  // TODO: !IsLastUse
-
     ctx.reg_alloc.DefineValue(code, inst, a);
 }
 

src/dynarmic/src/dynarmic/common/spin_lock_x64.cpp

@@ -14,12 +14,6 @@
 #include "dynarmic/backend/x64/hostloc.h"
 #include "dynarmic/common/spin_lock.h"
 
-#ifdef DYNARMIC_ENABLE_NO_EXECUTE_SUPPORT
-static const auto default_cg_mode = Xbyak::DontSetProtectRWE;
-#else
-static const auto default_cg_mode = nullptr; //Allow RWE
-#endif
-
 namespace Dynarmic {
 
 void EmitSpinLockLock(Xbyak::CodeGenerator& code, Xbyak::Reg64 ptr, Xbyak::Reg32 tmp, bool waitpkg) {
@@ -78,7 +72,13 @@ namespace {
 struct SpinLockImpl {
     void Initialize() noexcept;
     static void GlobalInitialize() noexcept;
-    Xbyak::CodeGenerator code = Xbyak::CodeGenerator(4096, default_cg_mode);
+    Xbyak::CodeGenerator code = Xbyak::CodeGenerator(4096
+#ifdef DYNARMIC_ENABLE_NO_EXECUTE_SUPPORT
+        , Xbyak::DontSetProtectRWE
+#else
+        , nullptr //Allow RWE
+#endif
+    );
     void (*lock)(volatile int*) = nullptr;
     void (*unlock)(volatile int*) = nullptr;
 };

src/dynarmic/src/dynarmic/frontend/decoder/decoder_detail.h

@@ -91,7 +91,7 @@ struct detail {
                 shifts[arg_index] = bit_position;
             }
         }
-#if !defined(DYNARMIC_IGNORE_ASSERTS) && !defined(__ANDROID__)
+#if !defined(__ANDROID__)
         // Avoids a MSVC ICE, and avoids Android NDK issue.
         DEBUG_ASSERT(std::all_of(masks.begin(), masks.end(), [](auto m) { return m != 0; }));
 #endif

src/dynarmic/tests/CMakeLists.txt

@@ -1,7 +1,5 @@
 # SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
 # SPDX-License-Identifier: GPL-3.0-or-later
-include(TargetArchitectureSpecificSources)
-
 add_executable(dynarmic_tests
     fp/FPToFixed.cpp
     fp/FPValue.cpp
@@ -44,13 +42,13 @@ if (DYNARMIC_TESTS_USE_UNICORN)
     )
 endif()
 
-if ("riscv" IN_LIST ARCHITECTURE)
+if (ARCHITECTURE_riscv64)
     target_link_libraries(dynarmic_tests PRIVATE biscuit::biscuit)
 endif()
 
-if ("x86_64" IN_LIST ARCHITECTURE)
+if (ARCHITECTURE_x86_64)
     target_link_libraries(dynarmic_tests PRIVATE xbyak::xbyak)
-    target_architecture_specific_sources(dynarmic_tests "x86_64"
+    target_sources(dynarmic_tests PRIVATE
         x64_cpu_info.cpp
         native/preserve_xmm.cpp
     )

src/video_core/renderer_vulkan/vk_buffer_cache.cpp

@@ -192,7 +192,7 @@ public:
             if (host_visible) {
                 return StagingBufferRef{};
             }
-            return staging_pool.Request(device, size_bytes, MemoryUsage::Upload);
+            return staging_pool.Request(size_bytes, MemoryUsage::Upload);
         }();
 
         u8* staging_data = host_visible ? buffer.Mapped().data() : staging.mapped_span.data();
@@ -366,11 +366,11 @@ BufferCacheRuntime::BufferCacheRuntime(const Device& device_, MemoryAllocator& m
 }
 
 StagingBufferRef BufferCacheRuntime::UploadStagingBuffer(size_t size) {
-    return staging_pool.Request(device, size, MemoryUsage::Upload);
+    return staging_pool.Request(size, MemoryUsage::Upload);
 }
 
 StagingBufferRef BufferCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) {
-    return staging_pool.Request(device, size, MemoryUsage::Download, deferred);
+    return staging_pool.Request(size, MemoryUsage::Download, deferred);
 }
 
 VkFormat BufferCacheRuntime::TexelBufferFormat(VideoCore::Surface::PixelFormat format) const {

src/video_core/renderer_vulkan/vk_buffer_cache.h

@@ -149,7 +149,7 @@ public:
     std::span<u8> BindMappedUniformBuffer([[maybe_unused]] size_t stage,
                                           [[maybe_unused]] u32 binding_index,
                                           u32 size) {
-        const StagingBufferRef ref = staging_pool.Request(device, size, MemoryUsage::Upload);
+        const StagingBufferRef ref = staging_pool.Request(size, MemoryUsage::Upload);
         guest_descriptor_queue.AddBuffer(ref.buffer, ref.device_address,
                                          static_cast<u32>(ref.offset), size);
         return ref.mapped_span;

src/video_core/renderer_vulkan/vk_compute_pass.cpp

@@ -287,7 +287,7 @@ Uint8Pass::~Uint8Pass() = default;
 std::pair<VkBuffer, VkDeviceSize> Uint8Pass::Assemble(u32 num_vertices, VkBuffer src_buffer,
                                                       u32 src_offset) {
     const u32 staging_size = static_cast<u32>(num_vertices * sizeof(u16));
-    const auto staging = staging_buffer_pool.Request(device, staging_size, MemoryUsage::DeviceLocal);
+    const auto staging = staging_buffer_pool.Request(staging_size, MemoryUsage::DeviceLocal);
 
     compute_pass_descriptor_queue.Acquire(scheduler, 2);
     compute_pass_descriptor_queue.AddBuffer(src_buffer, src_offset, num_vertices);
@@ -345,7 +345,7 @@ std::pair<VkBuffer, VkDeviceSize> QuadIndexedPass::Assemble(
     const u32 num_tri_vertices = (is_strip ? (num_vertices - 2) / 2 : num_vertices / 4) * 6;
 
     const std::size_t staging_size = num_tri_vertices * sizeof(u32);
-    const auto staging = staging_buffer_pool.Request(device, staging_size, MemoryUsage::DeviceLocal);
+    const auto staging = staging_buffer_pool.Request(staging_size, MemoryUsage::DeviceLocal);
 
     compute_pass_descriptor_queue.Acquire(scheduler, 2);
     compute_pass_descriptor_queue.AddBuffer(src_buffer, src_offset, input_size);

src/video_core/renderer_vulkan/vk_query_cache.cpp

@@ -852,7 +852,7 @@ public:
 
     void PushUnsyncedQueries() override {
         CloseCounter();
-        auto staging_ref = staging_pool.Request(device,
+        auto staging_ref = staging_pool.Request(
             pending_flush_queries.size() * TFBQueryBank::QUERY_SIZE, MemoryUsage::Download, true);
         size_t offset_base = staging_ref.offset;
         for (auto q : pending_flush_queries) {
@@ -1657,7 +1657,7 @@ void QueryCacheRuntime::SyncValues(std::span<SyncValuesType> values, VkBuffer ba
     impl->copies_setup.clear();
     impl->copies_setup.resize(impl->little_cache.size());
     if constexpr (SyncValuesType::GeneratesBaseBuffer) {
-        ref = impl->staging_pool.Request(impl->device, total_size, MemoryUsage::Upload);
+        ref = impl->staging_pool.Request(total_size, MemoryUsage::Upload);
         size_t current_offset = ref.offset;
         size_t accumulated_size = 0;
         for (size_t i = 0; i < values.size(); i++) {

src/video_core/renderer_vulkan/vk_staging_buffer_pool.cpp

@@ -28,14 +28,26 @@ using namespace Common::Literals;
 // Maximum potential alignment of a Vulkan buffer
 constexpr VkDeviceSize MAX_ALIGNMENT = 256;
 
-size_t GetStreamBufferSize(const Device& device, size_t max_stream_buffer_size, size_t max_alignment) {
+// Stream buffer size in bytes
+// *NIX drivers are more sensitive to increased buffers for streaming.
+// Windows ones however, can intake bigger buffers and generally do not OOM.
+// - GTX 960 on Windows will not OOM with 256mib
+// - GT 1030 on ^NIX will OOM with 256mib
+#if defined(__FreeBSD__)
+constexpr VkDeviceSize MAX_STREAM_BUFFER_SIZE = 128_MiB;
+#else
+constexpr VkDeviceSize MAX_STREAM_BUFFER_SIZE = 256_MiB;
+#endif
+
+size_t GetStreamBufferSize(const Device& device) {
     if (!device.HasDebuggingToolAttached()) {
-        return max_stream_buffer_size;
+        return MAX_STREAM_BUFFER_SIZE;
     }
 
     VkDeviceSize size{0};
     bool has_device_local_host_visible_heap{};
-    ForEachDeviceLocalHostVisibleHeap(device, [&size, &has_device_local_host_visible_heap](size_t index, VkMemoryHeap& heap) {
+    ForEachDeviceLocalHostVisibleHeap(device, [&size, &has_device_local_host_visible_heap](
+                                                  size_t index, VkMemoryHeap& heap) {
         has_device_local_host_visible_heap = true;
         size = (std::max)(size, heap.size);
     });
@@ -43,27 +55,28 @@ size_t GetStreamBufferSize(const Device& device, size_t max_stream_buffer_size,
         // If rebar is not supported, cut the max heap size to 40%. This will allow 2 captures to be
         // loaded at the same time in RenderDoc. If rebar is supported, this shouldn't be an issue
         // as the heap will be much larger.
-        if (size <= max_stream_buffer_size) {
+        if (size <= MAX_STREAM_BUFFER_SIZE) {
             size = size * 40 / 100;
         }
     } else {
-        size = max_stream_buffer_size;
+        size = MAX_STREAM_BUFFER_SIZE;
     }
-    return (std::min)(Common::AlignUp(size, max_alignment), max_stream_buffer_size);
+    return (std::min)(Common::AlignUp(size, MAX_ALIGNMENT), MAX_STREAM_BUFFER_SIZE);
 }
 } // Anonymous namespace
 
-StagingBufferPool::StagingBufferPool(const Device& device, MemoryAllocator& memory_allocator_, Scheduler& scheduler_)
-    : memory_allocator{memory_allocator_}, scheduler{scheduler_}
-    , stream_buffer_size{GetStreamBufferSize(device, 256_MiB, MAX_ALIGNMENT)}
-{
+StagingBufferPool::StagingBufferPool(const Device& device_, MemoryAllocator& memory_allocator_,
+                                     Scheduler& scheduler_)
+    : device{device_}, memory_allocator{memory_allocator_}, scheduler{scheduler_},
+      stream_buffer_size{GetStreamBufferSize(device)}, region_size{stream_buffer_size /
+                                                                   StagingBufferPool::NUM_SYNCS} {
     VkBufferCreateInfo stream_ci = {
         .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
         .pNext = nullptr,
         .flags = 0,
         .size = stream_buffer_size,
-        .usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT
-            | VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT,
+        .usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT |
+                 VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT,
         .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
         .queueFamilyIndexCount = 0,
         .pQueueFamilyIndices = nullptr,
@@ -74,20 +87,7 @@ StagingBufferPool::StagingBufferPool(const Device& device, MemoryAllocator& memo
     if (device.IsBufferDeviceAddressSupported()) {
         stream_ci.usage |= VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT;
     }
-    // *BSD drivers are more sensitive to increased buffers for streaming.
-    // Windows ones however, can intake bigger buffers and generally do not OOM.
-    // - GTX 960 on Windows will not OOM with 256mib
-    // - GT 1030 on ^BSD will OOM with 256mib
-    // This doesn't seem to be, however, universally true
-    try {
-        stream_buffer = memory_allocator.CreateBuffer(stream_ci, MemoryUsage::Stream);
-    } catch (vk::Exception& e) {
-        LOG_ERROR(Render_Vulkan, "Can't fit {} bytes buffer, halving", stream_ci.size);
-        stream_buffer_size = GetStreamBufferSize(device, 128_MiB, MAX_ALIGNMENT);
-        stream_ci.size = stream_buffer_size;
-        stream_buffer = memory_allocator.CreateBuffer(stream_ci, MemoryUsage::Stream);
-    }
-    region_size = stream_buffer_size / StagingBufferPool::NUM_SYNCS;
+    stream_buffer = memory_allocator.CreateBuffer(stream_ci, MemoryUsage::Stream);
     if (device.HasDebuggingToolAttached()) {
         stream_buffer.SetObjectNameEXT("Stream Buffer");
     }
@@ -100,10 +100,11 @@ StagingBufferPool::StagingBufferPool(const Device& device, MemoryAllocator& memo
 
 StagingBufferPool::~StagingBufferPool() = default;
 
-StagingBufferRef StagingBufferPool::Request(const Device& device, size_t size, MemoryUsage usage, bool deferred) {
-    return (!deferred && usage == MemoryUsage::Upload && size <= region_size)
-        ? GetStreamBuffer(device, size)
-        : GetStagingBuffer(device, size, usage, deferred);
+StagingBufferRef StagingBufferPool::Request(size_t size, MemoryUsage usage, bool deferred) {
+    if (!deferred && usage == MemoryUsage::Upload && size <= region_size) {
+        return GetStreamBuffer(size);
+    }
+    return GetStagingBuffer(size, usage, deferred);
 }
 
 void StagingBufferPool::FreeDeferred(StagingBufferRef& ref) {
@@ -126,10 +127,11 @@ void StagingBufferPool::TickFrame() {
     ReleaseCache(MemoryUsage::Download);
 }
 
-StagingBufferRef StagingBufferPool::GetStreamBuffer(const Device& device, size_t size) {
-    if (AreRegionsActive(Region(free_iterator) + 1, (std::min)(Region(iterator + size) + 1, NUM_SYNCS))) {
+StagingBufferRef StagingBufferPool::GetStreamBuffer(size_t size) {
+    if (AreRegionsActive(Region(free_iterator) + 1,
+                         (std::min)(Region(iterator + size) + 1, NUM_SYNCS))) {
         // Avoid waiting for the previous usages to be free
-        return GetStagingBuffer(device, size, MemoryUsage::Upload);
+        return GetStagingBuffer(size, MemoryUsage::Upload);
     }
     const u64 current_tick = scheduler.CurrentTick();
     std::fill(sync_ticks.begin() + Region(used_iterator), sync_ticks.begin() + Region(iterator),
@@ -138,14 +140,15 @@ StagingBufferRef StagingBufferPool::GetStreamBuffer(const Device& device, size_t
     free_iterator = (std::max)(free_iterator, iterator + size);
 
     if (iterator + size >= stream_buffer_size) {
-        std::fill(sync_ticks.begin() + Region(used_iterator), sync_ticks.begin() + NUM_SYNCS, current_tick);
+        std::fill(sync_ticks.begin() + Region(used_iterator), sync_ticks.begin() + NUM_SYNCS,
+                  current_tick);
         used_iterator = 0;
         iterator = 0;
         free_iterator = size;
 
         if (AreRegionsActive(0, Region(size) + 1)) {
             // Avoid waiting for the previous usages to be free
-            return GetStagingBuffer(device, size, MemoryUsage::Upload);
+            return GetStagingBuffer(size, MemoryUsage::Upload);
         }
     }
     const size_t offset = iterator;
@@ -153,7 +156,7 @@ StagingBufferRef StagingBufferPool::GetStreamBuffer(const Device& device, size_t
     return StagingBufferRef{
         .buffer = *stream_buffer,
         .device_address = stream_buffer_address,
-        .offset = VkDeviceSize(offset),
+        .offset = static_cast<VkDeviceSize>(offset),
         .mapped_span = stream_pointer.subspan(offset, size),
         .usage{},
         .log2_level{},
@@ -163,18 +166,21 @@ StagingBufferRef StagingBufferPool::GetStreamBuffer(const Device& device, size_t
 
 bool StagingBufferPool::AreRegionsActive(size_t region_begin, size_t region_end) const {
     const u64 gpu_tick = scheduler.GetMasterSemaphore().KnownGpuTick();
-    return std::any_of(sync_ticks.begin() + region_begin, sync_ticks.begin() + region_end, [gpu_tick](u64 sync_tick) {
-        return gpu_tick < sync_tick;
-    });
+    return std::any_of(sync_ticks.begin() + region_begin, sync_ticks.begin() + region_end,
+                       [gpu_tick](u64 sync_tick) { return gpu_tick < sync_tick; });
 };
 
-StagingBufferRef StagingBufferPool::GetStagingBuffer(const Device& device, size_t size, MemoryUsage usage, bool deferred) {
-    if (const std::optional<StagingBufferRef> ref = TryGetReservedBuffer(size, usage, deferred))
+StagingBufferRef StagingBufferPool::GetStagingBuffer(size_t size, MemoryUsage usage,
+                                                     bool deferred) {
+    if (const std::optional<StagingBufferRef> ref = TryGetReservedBuffer(size, usage, deferred)) {
         return *ref;
-    return CreateStagingBuffer(device, size, usage, deferred);
+    }
+    return CreateStagingBuffer(size, usage, deferred);
 }
 
-std::optional<StagingBufferRef> StagingBufferPool::TryGetReservedBuffer(size_t size, MemoryUsage usage, bool deferred) {
+std::optional<StagingBufferRef> StagingBufferPool::TryGetReservedBuffer(size_t size,
+                                                                        MemoryUsage usage,
+                                                                        bool deferred) {
     StagingBuffers& cache_level = GetCache(usage)[Common::Log2Ceil(size)];
 
     const auto is_free = [this](const StagingBuffer& entry) {
@@ -196,7 +202,7 @@ std::optional<StagingBufferRef> StagingBufferPool::TryGetReservedBuffer(size_t s
     return it->Ref();
 }
 
-StagingBufferRef StagingBufferPool::CreateStagingBuffer(const Device& device, size_t size, MemoryUsage usage, bool deferred) {
+StagingBufferRef StagingBufferPool::CreateStagingBuffer(size_t size, MemoryUsage usage, bool deferred) {
     auto const log2_size = Common::Log2Ceil<u32>(u32(size));
     VkBufferCreateInfo buffer_ci = {
         .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,

src/video_core/renderer_vulkan/vk_staging_buffer_pool.h

@@ -33,10 +33,11 @@ class StagingBufferPool {
 public:
     static constexpr size_t NUM_SYNCS = 16;
 
-    explicit StagingBufferPool(const Device& device, MemoryAllocator& memory_allocator, Scheduler& scheduler);
+    explicit StagingBufferPool(const Device& device, MemoryAllocator& memory_allocator,
+                               Scheduler& scheduler);
     ~StagingBufferPool();
 
-    StagingBufferRef Request(const Device& device, size_t size, MemoryUsage usage, bool deferred = false);
+    StagingBufferRef Request(size_t size, MemoryUsage usage, bool deferred = false);
     void FreeDeferred(StagingBufferRef& ref);
 
     [[nodiscard]] VkBuffer StreamBuf() const noexcept {
@@ -83,18 +84,27 @@ private:
     static constexpr size_t NUM_LEVELS = sizeof(size_t) * CHAR_BIT;
     using StagingBuffersCache = std::array<StagingBuffers, NUM_LEVELS>;
 
-    StagingBufferRef GetStreamBuffer(const Device& device, size_t size);
+    StagingBufferRef GetStreamBuffer(size_t size);
+
     bool AreRegionsActive(size_t region_begin, size_t region_end) const;
-    StagingBufferRef GetStagingBuffer(const Device& device, size_t size, MemoryUsage usage, bool deferred = false);
-    std::optional<StagingBufferRef> TryGetReservedBuffer(size_t size, MemoryUsage usage, bool deferred);
-    StagingBufferRef CreateStagingBuffer(const Device& device, size_t size, MemoryUsage usage, bool deferred);
+
+    StagingBufferRef GetStagingBuffer(size_t size, MemoryUsage usage, bool deferred = false);
+
+    std::optional<StagingBufferRef> TryGetReservedBuffer(size_t size, MemoryUsage usage,
+                                                         bool deferred);
+
+    StagingBufferRef CreateStagingBuffer(size_t size, MemoryUsage usage, bool deferred);
+
     StagingBuffersCache& GetCache(MemoryUsage usage);
+
     void ReleaseCache(MemoryUsage usage);
+
     void ReleaseLevel(StagingBuffersCache& cache, size_t log2);
     size_t Region(size_t iter) const noexcept {
         return iter / region_size;
     }
 
+    const Device& device;
     MemoryAllocator& memory_allocator;
     Scheduler& scheduler;
 

src/video_core/renderer_vulkan/vk_texture_cache.cpp

@@ -975,11 +975,11 @@ void TextureCacheRuntime::Finish() {
 }
 
 StagingBufferRef TextureCacheRuntime::UploadStagingBuffer(size_t size, bool deferred) {
-    return staging_buffer_pool.Request(device, size, MemoryUsage::Upload, deferred);
+    return staging_buffer_pool.Request(size, MemoryUsage::Upload, deferred);
 }
 
 StagingBufferRef TextureCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) {
-    return staging_buffer_pool.Request(device, size, MemoryUsage::Download, deferred);
+    return staging_buffer_pool.Request(size, MemoryUsage::Download, deferred);
 }
 
 void TextureCacheRuntime::FreeDeferredStagingBuffer(StagingBufferRef& ref) {