[loader] external zbic + code tweaks (#4484)

- [x] I have read and followed the [Contribution Guidelines](https://git.eden-emu.dev/eden-emu/eden/src/branch/master/CONTRIBUTING.md#code-contributions).
- [x] I have read and followed the [AI Policy](https://git.eden-emu.dev/eden-emu/eden/src/branch/master/docs/policies/AI.md)
- [x] I have read and followed the [Coding Guidelines](https://git.eden-emu.dev/eden-emu/eden/src/branch/master/docs/policies/Coding.md) to the best of my ability.

-------------------

zstd repo changed from atmosphere to kinnay's

Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4484

cpmfile.json

@@ -5,6 +5,11 @@
         "repo": "lioncash/biscuit",
         "version": "v0.19.0"
     },
+    "atmosphere_zstd_bic": {
+        "hash": "204f7573ea40de2878759c7ff5b2c016111fc29ae8574df50a3a0db9018c3b012f9040ea7466559130424d4335f2dfd6d7abfdc4d4d67e8a34531b8284f0cc6a",
+        "repo": "Atmosphere-NX/Atmosphere",
+        "version": "3ace80cc7b87e1837fccca1522801bbf6fddc6aa"
+    },
     "boost": {
         "artifact": "boost-%VERSION%.tar.zst",
         "find_args": "CONFIG OPTIONAL_COMPONENTS headers context system fiber filesystem",
@@ -333,6 +338,11 @@
         "repo": "herumi/xbyak",
         "version": "v7.40.1"
     },
+    "zbic": {
+        "hash": "fbe2f37986377d7f0d96ae3224c80b5971df6e8b6961f68061f1975ebb2e8cb78f07b90f014b007be4023dbf5513581504e7f7d61a5237cb2a8a7a61ae11e482",
+        "repo": "kinnay/zbic",
+        "version": "11b08f2712264bbed731545085cbd9702096ceb7"
+    },
     "zlib": {
         "hash": "16fea4df307a68cf0035858abe2fd550250618a97590e202037acd18a666f57afc10f8836cbbd472d54a0e76539d0e558cb26f059d53de52ff90634bbf4f47d4",
         "min_version": "1.2",

externals/CMakeLists.txt

@@ -48,6 +48,11 @@ if (NOT TARGET stb::headers)
     add_library(stb::headers ALIAS stb)
 endif()
 
+AddJsonPackage(NAME zbic DOWNLOAD_ONLY)
+set(ZBIC_INCLUDE_DIR
+    "${zbic_SOURCE_DIR}/src"
+    PARENT_SCOPE)
+
 # ItaniumDemangle (Windows only)
 if (WIN32 AND NOT TARGET LLVM::Demangle)
     add_library(demangle demangle/ItaniumDemangle.cpp)

src/common/CMakeLists.txt

@@ -137,6 +137,8 @@ add_library(
     uuid.cpp
     uuid.h
     vector_math.h
+    zbic_compression.cpp
+    zbic_compression.h
     zstd_compression.cpp
     zstd_compression.h
     fs/ryujinx_compat.h fs/ryujinx_compat.cpp
@@ -147,6 +149,10 @@ add_library(
     net/net.h net/net.cpp
     container/unordered_map.h container/unordered_set.h)
 
+set_source_files_properties(zbic_compression.cpp PROPERTIES
+    INCLUDE_DIRECTORIES "${ZBIC_INCLUDE_DIR}"
+    COMPILE_OPTIONS "$<$<CXX_COMPILER_ID:Clang,GNU>:-Wno-unused-function>")
+
 if(WIN32)
     target_sources(common PRIVATE windows/timer_resolution.cpp
         windows/timer_resolution.h)

src/common/zbic_compression.cpp

@@ -0,0 +1,40 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
+#include <cstring>
+
+#include "common/zbic_compression.h"
+
+#define ZSTD_ZBIC_SUPPORT 1
+#define ZSTDLIB_VISIBLE static
+#define ZSTDLIB_HIDDEN static
+#define ZSTDERRORLIB_VISIBLE static
+#define ZSTDERRORLIB_HIDDEN static
+#undef ZSTD_MULTITHREAD
+
+#include "zstd.h"
+#include "zstd.c"
+
+namespace Common::Compression {
+
+bool IsZBIC(std::span<const u8> src) {
+    if (src.size() < sizeof(u32)) {
+        return false;
+    }
+    u32 magic = 0;
+    std::memcpy(&magic, src.data(), sizeof(u32));
+    return magic == ZSTD_MAGICNUMBER; // 0x4349425A ("ZBIC")
+}
+
+int DecompressDataZBIC(std::span<u8> dst, std::span<const u8> src) {
+    if (dst.empty() || src.empty()) {
+        return -1;
+    }
+    const size_t res = ZSTD_decompress(dst.data(), dst.size(), src.data(), src.size());
+    if (ZSTD_isError(res)) {
+        return -1;
+    }
+    return static_cast<int>(res);
+}
+
+} // namespace Common::Compression

src/common/zbic_compression.h

@@ -0,0 +1,15 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
+#pragma once
+
+#include <span>
+#include "common/common_types.h"
+
+namespace Common::Compression {
+
+[[nodiscard]] bool IsZBIC(std::span<const u8> src);
+
+[[nodiscard]] int DecompressDataZBIC(std::span<u8> dst, std::span<const u8> src);
+
+} // namespace Common::Compression

src/core/loader/nso.cpp

@@ -7,12 +7,14 @@
 #include <algorithm>
 #include <cinttypes>
 #include <cstring>
+#include <span>
 #include <vector>
 
 #include "common/common_funcs.h"
 #include "common/hex_util.h"
 #include "common/logging.h"
 #include "common/lz4_compression.h"
+#include "common/zbic_compression.h"
 #include "common/settings.h"
 #include "common/swap.h"
 #include "core/core.h"
@@ -104,11 +106,36 @@ std::optional<VAddr> AppLoader_NSO::LoadModule(Kernel::KProcess& process, Core::
         for (std::size_t i = 0; i < nso_header.segments.size(); ++i) {
             nso_file.Read(compressed_data.data(), nso_header.segments_compressed_size[i], nso_header.segments[i].offset);
             if (nso_header.IsSegmentCompressed(i)) {
-                int r = Common::Compression::DecompressDataLZ4(decompressed_size.data(), nso_header.segments[i].size, compressed_data.data(), nso_header.segments_compressed_size[i]);
-                ASSERT(r == int(nso_header.segments[i].size));
-                std::memcpy(codeset.memory.data() + module_start + nso_header.segments[i].location, decompressed_size.data(), nso_header.segments[i].size);
+                if (nso_header.IsZBICCompressed()) {
+                    // ZBIC compression
+                    const int r = Common::Compression::DecompressDataZBIC(
+                        std::span<u8>{decompressed_size}.first(nso_header.segments[i].size),
+                        std::span<const u8>{compressed_data}.first(nso_header.segments_compressed_size[i])
+                    );
+                    ASSERT(r > 0);
+                } else {
+                    // LZ4 compression
+                    int r = Common::Compression::DecompressDataLZ4(
+                        decompressed_size.data(),
+                        nso_header.segments[i].size,
+                        compressed_data.data(),
+                        nso_header.segments_compressed_size[i]
+                    );
+                    ASSERT(r == int(nso_header.segments[i].size));
+                }
+
+                std::memcpy(
+                    codeset.memory.data() + module_start + nso_header.segments[i].location,
+                    decompressed_size.data(),
+                    nso_header.segments[i].size
+                );
             } else {
-                std::memcpy(codeset.memory.data() + module_start + nso_header.segments[i].location, compressed_data.data(), nso_header.segments[i].size);
+                // Not compressed
+                std::memcpy(
+                    codeset.memory.data() + module_start + nso_header.segments[i].location,
+                    compressed_data.data(),
+                    nso_header.segments[i].size
+                );
             }
             codeset.segments[i].addr = module_start + nso_header.segments[i].location;
             codeset.segments[i].offset = module_start + nso_header.segments[i].location;

src/core/loader/nso.h

@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2018 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -58,6 +61,9 @@ struct NSOHeader {
     std::array<SHA256Hash, 3> segment_hashes;
 
     bool IsSegmentCompressed(size_t segment_num) const;
+    bool IsZBICCompressed() const {
+        return ((flags >> 7) & 1) != 0;
+    }
 };
 static_assert(sizeof(NSOHeader) == 0x100, "NSOHeader has incorrect size.");
 static_assert(std::is_trivially_copyable_v<NSOHeader>, "NSOHeader must be trivially copyable.");

src/video_core/renderer_vulkan/vk_buffer_cache.cpp

@@ -200,7 +200,7 @@ 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();
@@ -375,11 +375,11 @@ 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

@@ -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(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

@@ -28,42 +28,55 @@ 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_t>(size, heap.size);
+        size = (std::max)(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<size_t>(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,
@@ -74,16 +87,7 @@ StagingBufferPool::StagingBufferPool(const Device& device, MemoryAllocator& memo
     if (device.IsBufferDeviceAddressSupported()) {
         stream_ci.usage |= VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT;
     }
-    // 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;
+    stream_buffer = memory_allocator.CreateBuffer(stream_ci, MemoryUsage::Stream);
     if (device.HasDebuggingToolAttached()) {
         stream_buffer.SetObjectNameEXT("Stream Buffer");
     }
@@ -96,10 +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) {
@@ -122,10 +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),
@@ -134,14 +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;
@@ -149,7 +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{},
@@ -159,18 +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) {
@@ -192,7 +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) {