2026-09-05 17:42:18

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

CONTRIBUTING.md

@@ -83,16 +83,3 @@ Once your request is processed, you will receive a confirmation email with your
 Alongside the other contribution methods listed up top, you can also choose to contribute through documentation, organization, or community guides. These can be done either through the code contribution methods described above, or created externally and shared via our Discord community.
 
 If you have an external tool/page that you believe would be handy to integrate/link into Eden, please additionally email our developers at [`developers@eden-emu.dev`](mailto:developers@eden-emu.dev). **Do not submit vibe-coded or AI generated tools or applications**.
-
-### Non-English Contributions
-
-If you can't speak English or find more comfortable speaking in your native tongue, you may submit PR, commits, comments, and reviews in other languages. There is no restriction what languages are allowed, but maintainers will use translators if they're unable to understand.
-
-Triage can speak:
-
-- Chinese
-- Portuguese
-- Russian
-- Spanish
-
-Documentation must be in American English, we don't have the capacity to support multilingual manuals. Code comments must remain in English for future referral.

src/video_core/renderer_opengl/gl_buffer_cache.cpp

@@ -148,11 +148,11 @@ BufferCacheRuntime::BufferCacheRuntime(const Device& device_,
 }
 
 StagingBufferMap BufferCacheRuntime::UploadStagingBuffer(size_t size) {
-    return staging_buffer_pool.RequestUploadBuffer(size);
+    return staging_buffer_pool.RequestUploadBuffer(device, size);
 }
 
 StagingBufferMap BufferCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) {
-    return staging_buffer_pool.RequestDownloadBuffer(size, deferred);
+    return staging_buffer_pool.RequestDownloadBuffer(device, size, deferred);
 }
 
 void BufferCacheRuntime::FreeDeferredStagingBuffer(StagingBufferMap& buffer) {

src/video_core/renderer_opengl/gl_texture_cache.cpp

@@ -557,11 +557,11 @@ void TextureCacheRuntime::Finish() {
 }
 
 StagingBufferMap TextureCacheRuntime::UploadStagingBuffer(size_t size, bool deferred) {
-    return staging_buffer_pool.RequestUploadBuffer(size);
+    return staging_buffer_pool.RequestUploadBuffer(device, size);
 }
 
 StagingBufferMap TextureCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) {
-    return staging_buffer_pool.RequestDownloadBuffer(size, deferred);
+    return staging_buffer_pool.RequestDownloadBuffer(device, size, deferred);
 }
 
 void TextureCacheRuntime::FreeDeferredStagingBuffer(StagingBufferMap& buffer) {

src/video_core/renderer_vulkan/vk_buffer_cache.cpp

@@ -192,7 +192,7 @@ 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();
@@ -366,11 +366,11 @@ 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

@@ -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(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

@@ -25,29 +25,14 @@ namespace {
 
 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);
     });
@@ -55,28 +40,27 @@ size_t GetStreamBufferSize(const Device& device) {
         // 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_)
-    : 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, 256)}
+{
     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 +71,20 @@ 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);
+    // *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, 256);
+        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 +97,10 @@ 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 +123,10 @@ 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 +135,14 @@ 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 +150,7 @@ 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 +160,18 @@ 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 +193,7 @@ 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) {