2026-09-25 09:06:19

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

src/dynarmic/src/dynarmic/backend/x64/a32_jitstate.cpp

@@ -69,8 +69,8 @@ u32 A32JitState::Cpsr() const {
     cpsr |= mcl::bit::get_bit<1>(upper_location_descriptor) ? 1 << 9 : 0;
     cpsr |= mcl::bit::get_bit<0>(upper_location_descriptor) ? 1 << 5 : 0;
     // IT state
-    cpsr |= u32(upper_location_descriptor & 0b11111100'00000000);
-    cpsr |= u32(upper_location_descriptor & 0b00000011'00000000) << 17;
+    cpsr |= static_cast<u32>(upper_location_descriptor & 0b11111100'00000000);
+    cpsr |= static_cast<u32>(upper_location_descriptor & 0b00000011'00000000) << 17;
     // Other flags
     cpsr |= cpsr_jaifm;
 
@@ -169,36 +169,39 @@ constexpr u32 FPSCR_NZCV_MASK = 0xF0000000;
 u32 A32JitState::Fpscr() const {
     DEBUG_ASSERT((fpsr_nzcv & ~FPSCR_NZCV_MASK) == 0);
 
-    const u32 fpcr_mode = u32(upper_location_descriptor) & FPSCR_MODE_MASK;
+    const u32 fpcr_mode = static_cast<u32>(upper_location_descriptor) & FPSCR_MODE_MASK;
     const u32 mxcsr = guest_MXCSR | asimd_MXCSR;
-    u32 fpscr = fpcr_mode | fpsr_nzcv;
-    fpscr |= (mxcsr & 0b0000000000001);       // IOC = IE
-    fpscr |= (mxcsr & 0b0000000111100) >> 1;  // IXC, UFC, OFC, DZC = PE, UE, OE, ZE
-    fpscr |= fpsr_exc;
-    fpscr |= fpsr_qc != 0 ? 1 << 27 : 0;
-    return fpscr;
+
+    u32 FPSCR = fpcr_mode | fpsr_nzcv;
+    FPSCR |= (mxcsr & 0b0000000000001);       // IOC = IE
+    FPSCR |= (mxcsr & 0b0000000111100) >> 1;  // IXC, UFC, OFC, DZC = PE, UE, OE, ZE
+    FPSCR |= fpsr_exc;
+    FPSCR |= fpsr_qc != 0 ? 1 << 27 : 0;
+
+    return FPSCR;
 }
 
-void A32JitState::SetFpscr(u32 value) {
+void A32JitState::SetFpscr(u32 FPSCR) {
     // Ensure that only upper half of upper_location_descriptor is used for FPSCR bits.
     static_assert((FPSCR_MODE_MASK & 0xFFFF0000) == FPSCR_MODE_MASK);
 
     upper_location_descriptor &= 0x0000FFFF;
-    upper_location_descriptor |= value & FPSCR_MODE_MASK;
+    upper_location_descriptor |= FPSCR & FPSCR_MODE_MASK;
 
-    fpsr_nzcv = value & FPSCR_NZCV_MASK;
-    fpsr_qc = (value >> 27) & 1;
+    fpsr_nzcv = FPSCR & FPSCR_NZCV_MASK;
+    fpsr_qc = (FPSCR >> 27) & 1;
 
     guest_MXCSR = 0x00001f80;
     asimd_MXCSR = 0x00009fc0;
 
     // RMode
-    guest_MXCSR |= ((0x6000200040000000 >> (((value >> 18) & (0x3 << 4)))) & 0xf000);
+    const std::array<u32, 4> MXCSR_RMode{0x0, 0x4000, 0x2000, 0x6000};
+    guest_MXCSR |= MXCSR_RMode[(FPSCR >> 22) & 0x3];
 
     // Cumulative flags IDC, IOC, IXC, UFC, OFC, DZC
-    fpsr_exc = value & 0x9F;
+    fpsr_exc = FPSCR & 0x9F;
 
-    if (mcl::bit::get_bit<24>(value)) {
+    if (mcl::bit::get_bit<24>(FPSCR)) {
         // VFP Flush to Zero
         guest_MXCSR |= (1 << 15);  // SSE Flush to Zero
         guest_MXCSR |= (1 << 6);   // SSE Denormals are Zero

src/dynarmic/src/dynarmic/backend/x64/a64_jitstate.cpp

@@ -59,16 +59,16 @@ u32 A64JitState::GetFpcr() const {
 
 void A64JitState::SetFpcr(u32 value) {
     fpcr = value & FPCR_MASK;
+
     asimd_MXCSR &= 0x0000003D;
     guest_MXCSR &= 0x0000003D;
     asimd_MXCSR |= 0x00001f80;
     guest_MXCSR |= 0x00001f80;  // Mask all exceptions
+
     // RMode
-    // 0 -> 0x0000
-    // 1 -> 0x4000
-    // 2 -> 0x2000
-    // 3 -> 0x6000
-    guest_MXCSR |= ((0x6000200040000000 >> (((value >> 18) & (0x3 << 4)))) & 0xf000);
+    const std::array<u32, 4> MXCSR_RMode{0x0, 0x4000, 0x2000, 0x6000};
+    guest_MXCSR |= MXCSR_RMode[(value >> 22) & 0x3];
+
     if (mcl::bit::get_bit<24>(value)) {
         guest_MXCSR |= (1 << 15);  // SSE Flush to Zero
         guest_MXCSR |= (1 << 6);   // SSE Denormals are Zero

src/video_core/renderer_vulkan/vk_buffer_cache.cpp

@@ -200,7 +200,7 @@ public:
             if (host_visible) {
                 return StagingBufferRef{};
             }
-            return staging_pool.Request(size_bytes, MemoryUsage::Upload);
+            return staging_pool.Request(device, size_bytes, MemoryUsage::Upload);
         }();
 
         u8* staging_data = host_visible ? buffer.Mapped().data() : staging.mapped_span.data();
@@ -375,11 +375,11 @@ BufferCacheRuntime::BufferCacheRuntime(const Device& device_, MemoryAllocator& m
 }
 
 StagingBufferRef BufferCacheRuntime::UploadStagingBuffer(size_t size) {
-    return staging_pool.Request(size, MemoryUsage::Upload);
+    return staging_pool.Request(device, size, MemoryUsage::Upload);
 }
 
 StagingBufferRef BufferCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) {
-    return staging_pool.Request(size, MemoryUsage::Download, deferred);
+    return staging_pool.Request(device, size, MemoryUsage::Download, deferred);
 }
 
 VkFormat BufferCacheRuntime::TexelBufferFormat(VideoCore::Surface::PixelFormat format) const {

src/video_core/renderer_vulkan/vk_buffer_cache.h

@@ -162,7 +162,7 @@ public:
     std::span<u8> BindMappedUniformBuffer([[maybe_unused]] size_t stage,
                                           [[maybe_unused]] u32 binding_index,
                                           u32 size) {
-        const StagingBufferRef ref = staging_pool.Request(size, MemoryUsage::Upload);
+        const StagingBufferRef ref = staging_pool.Request(device, 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(staging_size, MemoryUsage::DeviceLocal);
+    const auto staging = staging_buffer_pool.Request(device, 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(staging_size, MemoryUsage::DeviceLocal);
+    const auto staging = staging_buffer_pool.Request(device, 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(
+        auto staging_ref = staging_pool.Request(device,
             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(total_size, MemoryUsage::Upload);
+        ref = impl->staging_pool.Request(impl->device, 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

@@ -28,55 +28,42 @@ using namespace Common::Literals;
 // Maximum potential alignment of a Vulkan buffer
 constexpr VkDeviceSize MAX_ALIGNMENT = 256;
 
-// 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) {
+size_t GetStreamBufferSize(const Device& device, size_t max_stream_buffer_size, size_t max_alignment) {
     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);
+        size = std::max<size_t>(size, heap.size);
     });
     if (has_device_local_host_visible_heap) {
         // 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<size_t>(Common::AlignUp(size, max_alignment), max_stream_buffer_size);
 }
 } // Anonymous namespace
 
-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} {
+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)}
+{
     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,
@@ -87,7 +74,16 @@ StagingBufferPool::StagingBufferPool(const Device& device_, MemoryAllocator& mem
     if (device.IsBufferDeviceAddressSupported()) {
         stream_ci.usage |= VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT;
     }
-    stream_buffer = memory_allocator.CreateBuffer(stream_ci, MemoryUsage::Stream);
+    // Some drivers are more sensitive to increased buffer sizes
+    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;
     if (device.HasDebuggingToolAttached()) {
         stream_buffer.SetObjectNameEXT("Stream Buffer");
     }
@@ -100,11 +96,10 @@ StagingBufferPool::StagingBufferPool(const Device& device_, MemoryAllocator& mem
 
 StagingBufferPool::~StagingBufferPool() = default;
 
-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);
+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);
 }
 
 void StagingBufferPool::FreeDeferred(StagingBufferRef& ref) {
@@ -127,11 +122,10 @@ void StagingBufferPool::TickFrame() {
     ReleaseCache(MemoryUsage::Download);
 }
 
-StagingBufferRef StagingBufferPool::GetStreamBuffer(size_t size) {
-    if (AreRegionsActive(Region(free_iterator) + 1,
-                         (std::min)(Region(iterator + size) + 1, NUM_SYNCS))) {
+StagingBufferRef StagingBufferPool::GetStreamBuffer(const Device& device, 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(size, MemoryUsage::Upload);
+        return GetStagingBuffer(device, size, MemoryUsage::Upload);
     }
     const u64 current_tick = scheduler.CurrentTick();
     std::fill(sync_ticks.begin() + Region(used_iterator), sync_ticks.begin() + Region(iterator),
@@ -140,15 +134,14 @@ StagingBufferRef StagingBufferPool::GetStreamBuffer(size_t size) {
     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(size, MemoryUsage::Upload);
+            return GetStagingBuffer(device, size, MemoryUsage::Upload);
         }
     }
     const size_t offset = iterator;
@@ -156,7 +149,7 @@ StagingBufferRef StagingBufferPool::GetStreamBuffer(size_t size) {
     return StagingBufferRef{
         .buffer = *stream_buffer,
         .device_address = stream_buffer_address,
-        .offset = static_cast<VkDeviceSize>(offset),
+        .offset = VkDeviceSize(offset),
         .mapped_span = stream_pointer.subspan(offset, size),
         .usage{},
         .log2_level{},
@@ -166,21 +159,18 @@ StagingBufferRef StagingBufferPool::GetStreamBuffer(size_t size) {
 
 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(size_t size, MemoryUsage usage,
-                                                     bool deferred) {
-    if (const std::optional<StagingBufferRef> ref = TryGetReservedBuffer(size, usage, deferred)) {
+StagingBufferRef StagingBufferPool::GetStagingBuffer(const Device& device, size_t size, MemoryUsage usage, bool deferred) {
+    if (const std::optional<StagingBufferRef> ref = TryGetReservedBuffer(size, usage, deferred))
         return *ref;
-    }
-    return CreateStagingBuffer(size, usage, deferred);
+    return CreateStagingBuffer(device, 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) {
@@ -202,7 +192,7 @@ std::optional<StagingBufferRef> StagingBufferPool::TryGetReservedBuffer(size_t s
     return it->Ref();
 }
 
-StagingBufferRef StagingBufferPool::CreateStagingBuffer(size_t size, MemoryUsage usage, bool deferred) {
+StagingBufferRef StagingBufferPool::CreateStagingBuffer(const Device& device, 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

@@ -33,11 +33,10 @@ 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(size_t size, MemoryUsage usage, bool deferred = false);
+    StagingBufferRef Request(const Device& device, size_t size, MemoryUsage usage, bool deferred = false);
     void FreeDeferred(StagingBufferRef& ref);
 
     [[nodiscard]] VkBuffer StreamBuf() const noexcept {
@@ -84,27 +83,18 @@ private:
     static constexpr size_t NUM_LEVELS = sizeof(size_t) * CHAR_BIT;
     using StagingBuffersCache = std::array<StagingBuffers, NUM_LEVELS>;
 
-    StagingBufferRef GetStreamBuffer(size_t size);
-
+    StagingBufferRef GetStreamBuffer(const Device& device, size_t size);
     bool AreRegionsActive(size_t region_begin, size_t region_end) const;
-
-    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);
-
+    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);
     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(size, MemoryUsage::Upload, deferred);
+    return staging_buffer_pool.Request(device, size, MemoryUsage::Upload, deferred);
 }
 
 StagingBufferRef TextureCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) {
-    return staging_buffer_pool.Request(size, MemoryUsage::Download, deferred);
+    return staging_buffer_pool.Request(device, size, MemoryUsage::Download, deferred);
 }
 
 void TextureCacheRuntime::FreeDeferredStagingBuffer(StagingBufferRef& ref) {