[vk] Fast UBO: fix tracking (#2712)

Fixes or mitigates memory errors in TOTK and possibly other games as well.

Credit: Ribbit
Reviewed-on: #2712
Reviewed-by: Lizzie <lizzie@eden-emu.dev>
Reviewed-by: crueter <crueter@eden-emu.dev>
Co-authored-by: MaranBr <maranbr@outlook.com>
Co-committed-by: MaranBr <maranbr@outlook.com>

src/core/hle/service/acc/profile_manager.cpp

@@ -509,6 +509,9 @@ std::vector<std::string> ProfileManager::FindOrphanedProfiles()
         good_uuids.emplace_back(uuid_string);
     }
 
+    // used for acnh, etc
+    good_uuids.emplace_back("00000000000000000000000000000000");
+
     // TODO: fetch save_id programmatically
     const auto path = Common::FS::GetEdenPath(Common::FS::EdenPath::NANDDir)
                       / "user/save/0000000000000000";

src/qt_common/CMakeLists.txt

@@ -45,6 +45,10 @@ if (NOT APPLE AND ENABLE_OPENGL)
     target_compile_definitions(qt_common PUBLIC HAS_OPENGL)
 endif()
 
-if (NOT WIN32)
+if (UNIX AND NOT APPLE)
+    if (TARGET Qt6::GuiPrivate)
+        target_link_libraries(qt_common PRIVATE Qt6::GuiPrivate)
+    else()
         target_include_directories(qt_common PRIVATE ${Qt6Gui_PRIVATE_INCLUDE_DIRS})
     endif()
+endif()

src/video_core/buffer_cache/buffer_cache.h

@@ -386,11 +386,9 @@ void BufferCache<P>::BindHostComputeBuffers() {
 template <class P>
 void BufferCache<P>::SetUniformBuffersState(const std::array<u32, NUM_STAGES>& mask,
                                             const UniformBufferSizes* sizes) {
-    if constexpr (HAS_PERSISTENT_UNIFORM_BUFFER_BINDINGS) {
     if (channel_state->enabled_uniform_buffer_masks != mask) {
-            if constexpr (IS_OPENGL) {
         channel_state->fast_bound_uniform_buffers.fill(0);
-            }
+        if constexpr (HAS_PERSISTENT_UNIFORM_BUFFER_BINDINGS) {
             channel_state->dirty_uniform_buffers.fill(~u32{0});
             channel_state->uniform_buffer_binding_sizes.fill({});
         }
@@ -806,7 +804,7 @@ void BufferCache<P>::BindHostGraphicsUniformBuffer(size_t stage, u32 index, u32
                     channel_state->uniform_buffer_binding_sizes[stage][binding_index] != size;
                 if (should_fast_bind) {
                     // We only have to bind when the currently bound buffer is not the fast version
-                    channel_state->fast_bound_uniform_buffers[stage] |= 1U << binding_index;
+                    channel_state->fast_bound_uniform_buffers[stage] |= 1u << binding_index;
                     channel_state->uniform_buffer_binding_sizes[stage][binding_index] = size;
                     runtime.BindFastUniformBuffer(stage, binding_index, size);
                 }
@@ -815,10 +813,8 @@ void BufferCache<P>::BindHostGraphicsUniformBuffer(size_t stage, u32 index, u32
                 return;
             }
         }
-        if constexpr (IS_OPENGL) {
-            channel_state->fast_bound_uniform_buffers[stage] |= 1U << binding_index;
+        channel_state->fast_bound_uniform_buffers[stage] |= 1u << binding_index;
         channel_state->uniform_buffer_binding_sizes[stage][binding_index] = size;
-        }
         // Stream buffer path to avoid stalling on non-Nvidia drivers or Vulkan
         const std::span<u8> span = runtime.BindMappedUniformBuffer(stage, binding_index, size);
         device_memory.ReadBlockUnsafe(device_addr, span.data(), size);
@@ -839,9 +835,6 @@ void BufferCache<P>::BindHostGraphicsUniformBuffer(size_t stage, u32 index, u32
     }
     const u32 offset = buffer.Offset(device_addr);
     if constexpr (IS_OPENGL) {
-        // Fast buffer will be unbound
-        channel_state->fast_bound_uniform_buffers[stage] &= ~(1U << binding_index);
-
         // Mark the index as dirty if offset doesn't match
         const bool is_copy_bind = offset != 0 && !runtime.SupportsNonZeroUniformOffset();
         channel_state->dirty_uniform_buffers[stage] |= (is_copy_bind ? 1U : 0U) << index;
@@ -855,6 +848,7 @@ void BufferCache<P>::BindHostGraphicsUniformBuffer(size_t stage, u32 index, u32
     } else {
         runtime.BindUniformBuffer(buffer, offset, size);
     }
+    channel_state->fast_bound_uniform_buffers[stage] &= ~(1u << binding_index);
 }
 
 template <class P>
@@ -1789,12 +1783,7 @@ std::span<u8> BufferCache<P>::ImmediateBuffer(size_t wanted_capacity) {
 
 template <class P>
 bool BufferCache<P>::HasFastUniformBufferBound(size_t stage, u32 binding_index) const noexcept {
-    if constexpr (IS_OPENGL) {
-        return ((channel_state->fast_bound_uniform_buffers[stage] >> binding_index) & 1) != 0;
-    } else {
-        // Only OpenGL has fast uniform buffers
-        return false;
-    }
+    return ((channel_state->fast_bound_uniform_buffers[stage] >> binding_index) & 1u) != 0;
 }
 
 template <class P>

src/video_core/buffer_cache/buffer_cache_base.h

@@ -54,6 +54,8 @@ constexpr u32 NUM_STORAGE_BUFFERS = 16;
 constexpr u32 NUM_TEXTURE_BUFFERS = 32;
 constexpr u32 NUM_STAGES = 5;
 
+static_assert(NUM_GRAPHICS_UNIFORM_BUFFERS <= 32, "fast bitmask must fit u32");
+
 using UniformBufferSizes = std::array<std::array<u32, NUM_GRAPHICS_UNIFORM_BUFFERS>, NUM_STAGES>;
 using ComputeUniformBufferSizes = std::array<u32, NUM_COMPUTE_UNIFORM_BUFFERS>;
 
@@ -137,8 +139,8 @@ public:
     u32 written_compute_texture_buffers = 0;
     u32 image_compute_texture_buffers = 0;
 
-    std::array<u32, 16> uniform_cache_hits{};
-    std::array<u32, 16> uniform_cache_shots{};
+    std::array<u32, NUM_GRAPHICS_UNIFORM_BUFFERS> uniform_cache_hits{};
+    std::array<u32, NUM_GRAPHICS_UNIFORM_BUFFERS> uniform_cache_shots{};
 
     u32 uniform_buffer_skip_cache_size = DEFAULT_SKIP_CACHE_SIZE;
 

src/video_core/renderer_vulkan/vk_buffer_cache.cpp

@@ -337,6 +337,11 @@ BufferCacheRuntime::BufferCacheRuntime(const Device& device_, MemoryAllocator& m
         uint8_pass = std::make_unique<Uint8Pass>(device, scheduler, descriptor_pool, staging_pool,
                                                  compute_pass_descriptor_queue);
     }
+    const u32 ubo_align = static_cast<u32>(
+            device.GetUniformBufferAlignment() //check if the device has it
+    );
+    // add the ability to change the size in settings in future
+    uniform_ring.Init(device, memory_allocator, 8 * 1024 * 1024 /* 8 MiB */, ubo_align ? ubo_align : 256);
     quad_array_index_buffer = std::make_shared<QuadArrayIndexBuffer>(device_, memory_allocator_,
                                                                      scheduler_, staging_pool_);
     quad_strip_index_buffer = std::make_shared<QuadStripIndexBuffer>(device_, memory_allocator_,
@@ -355,6 +360,42 @@ void BufferCacheRuntime::FreeDeferredStagingBuffer(StagingBufferRef& ref) {
     staging_pool.FreeDeferred(ref);
 }
 
+void BufferCacheRuntime::UniformRing::Init(const Device& device,
+                                           MemoryAllocator& alloc,
+                                           u64 bytes, u32 alignment) {
+    for (size_t i = 0; i < NUM_FRAMES; ++i) {
+        VkBufferCreateInfo ci{
+            .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
+            .pNext = nullptr,
+            .flags = 0,
+            .size  = bytes,
+            .usage = VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT,
+            .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
+            .queueFamilyIndexCount = 0,
+            .pQueueFamilyIndices = nullptr,
+        };
+        buffers[i] = alloc.CreateBuffer(ci, MemoryUsage::Upload);
+        mapped[i] = buffers[i].Mapped().data();
+    }
+    size   = bytes;
+    align  = alignment ? alignment : 256;
+    head   = 0;
+    current_frame = 0;
+}
+
+std::span<u8> BufferCacheRuntime::UniformRing::Alloc(u32 bytes, u32& out_offset) {
+    const u64 aligned = Common::AlignUp(head, static_cast<u64>(align));
+    u64 end = aligned + bytes;
+
+    if (end > size) {
+       return {}; // Fallback to staging pool
+    }
+
+    out_offset = static_cast<u32>(aligned);
+    head = end;
+    return {mapped[current_frame] + out_offset, bytes};
+}
+
 u64 BufferCacheRuntime::GetDeviceLocalMemory() const {
     return device.GetDeviceLocalMemory();
 }
@@ -375,6 +416,7 @@ void BufferCacheRuntime::TickFrame(Common::SlotVector<Buffer>& slot_buffers) noe
     for (auto it = slot_buffers.begin(); it != slot_buffers.end(); it++) {
         it->ResetUsageTracking();
     }
+    uniform_ring.BeginFrame();
 }
 
 void BufferCacheRuntime::Finish() {

src/video_core/renderer_vulkan/vk_buffer_cache.h

@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2019 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -124,8 +127,15 @@ public:
 
     void BindTransformFeedbackBuffers(VideoCommon::HostBindings<Buffer>& bindings);
 
-    std::span<u8> BindMappedUniformBuffer([[maybe_unused]] size_t stage,
-                                          [[maybe_unused]] u32 binding_index, u32 size) {
+    std::span<u8> BindMappedUniformBuffer([[maybe_unused]] size_t /*stage*/,
+                                          [[maybe_unused]] u32 /*binding_index*/,
+                                          u32 size) {
+        u32 offset = 0;
+        if (auto span = uniform_ring.Alloc(size, offset); !span.empty()) {
+            BindBuffer(*uniform_ring.buffers[uniform_ring.current_frame], offset, size);
+            return span;
+        }
+        // Fallback for giant requests
         const StagingBufferRef ref = staging_pool.Request(size, MemoryUsage::Upload);
         BindBuffer(ref.buffer, static_cast<u32>(ref.offset), size);
         return ref.mapped_span;
@@ -153,6 +163,24 @@ private:
     void ReserveNullBuffer();
     vk::Buffer CreateNullBuffer();
 
+    struct UniformRing {
+        static constexpr size_t NUM_FRAMES = 3;
+        std::array<vk::Buffer, NUM_FRAMES> buffers{};
+        std::array<u8*, NUM_FRAMES> mapped{};
+        u64 size = 0;
+        u64 head = 0;
+        u32 align = 256;
+        size_t current_frame = 0;
+
+        void Init(const Device& device, MemoryAllocator& alloc, u64 bytes, u32 alignment);
+        void BeginFrame() {
+            current_frame = (current_frame + 1) % NUM_FRAMES;
+            head = 0;
+        }
+        std::span<u8> Alloc(u32 bytes, u32& out_offset);
+    };
+    UniformRing uniform_ring;
+
     const Device& device;
     MemoryAllocator& memory_allocator;
     Scheduler& scheduler;

src/yuzu/CMakeLists.txt

@@ -393,16 +393,8 @@ target_link_libraries(yuzu PRIVATE common core input_common frontend_common netw
 target_link_libraries(yuzu PRIVATE Boost::headers glad Qt6::Widgets)
 target_link_libraries(yuzu PRIVATE ${PLATFORM_LIBRARIES} Threads::Threads)
 
-if (NOT WIN32)
-    target_include_directories(yuzu PRIVATE ${Qt6Gui_PRIVATE_INCLUDE_DIRS})
-endif()
-
 if (UNIX AND NOT APPLE)
     target_link_libraries(yuzu PRIVATE Qt6::DBus)
-
-    if (TARGET Qt6::GuiPrivate)
-        target_link_libraries(yuzu PRIVATE Qt6::GuiPrivate)
-    endif()
 endif()
 
 target_compile_definitions(yuzu PRIVATE