Corrections, documenting and fixes.

src/audio_core/buffer.h

@@ -21,7 +21,7 @@ public:
     Buffer(Tag tag, std::vector<s16>&& samples) : tag{tag}, samples{std::move(samples)} {}
 
     /// Returns the raw audio data for the buffer
-    std::vector<s16>& GetSamples() {
+    std::vector<s16>& Samples() {
         return samples;
     }
 

src/audio_core/stream.cpp

@@ -95,7 +95,7 @@ void Stream::PlayNextBuffer() {
     active_buffer = queued_buffers.front();
     queued_buffers.pop();
 
-    VolumeAdjustSamples(active_buffer->GetSamples());
+    VolumeAdjustSamples(active_buffer->Samples());
 
     sink_stream.EnqueueSamples(GetNumChannels(), active_buffer->GetSamples());
 

src/common/CMakeLists.txt

@@ -113,6 +113,8 @@ add_library(common STATIC
     threadsafe_queue.h
     timer.cpp
     timer.h
+    uint128.cpp
+    uint128.h
     vector_math.h
     web_result.h
 )

src/common/logging/backend.cpp

@@ -40,7 +40,9 @@ public:
     const Impl& operator=(Impl const&) = delete;
 
     void PushEntry(Entry e) {
+        std::lock_guard<std::mutex> lock(message_mutex);
         message_queue.Push(std::move(e));
+        message_cv.notify_one();
     }
 
     void AddBackend(std::unique_ptr<Backend> backend) {
@@ -84,13 +86,15 @@ private:
                 }
             };
             while (true) {
-                entry = message_queue.PopWait();
-                if (entry.final_entry) {
+                {
+                    std::unique_lock<std::mutex> lock(message_mutex);
+                    message_cv.wait(lock, [&] { return !running || message_queue.Pop(entry); });
+                }
+                if (!running) {
                     break;
                 }
                 write_logs(entry);
             }
-
             // Drain the logging queue. Only writes out up to MAX_LOGS_TO_WRITE to prevent a case
             // where a system is repeatedly spamming logs even on close.
             const int MAX_LOGS_TO_WRITE = filter.IsDebug() ? INT_MAX : 100;
@@ -102,13 +106,14 @@ private:
     }
 
     ~Impl() {
-        Entry entry;
-        entry.final_entry = true;
-        message_queue.Push(entry);
+        running = false;
+        message_cv.notify_one();
         backend_thread.join();
     }
 
-    std::mutex writing_mutex;
+    std::atomic_bool running{true};
+    std::mutex message_mutex, writing_mutex;
+    std::condition_variable message_cv;
     std::thread backend_thread;
     std::vector<std::unique_ptr<Backend>> backends;
     Common::MPSCQueue<Log::Entry> message_queue;

src/common/logging/backend.h

@@ -27,7 +27,6 @@ struct Entry {
     unsigned int line_num;
     std::string function;
     std::string message;
-    bool final_entry = false;
 
     Entry() = default;
     Entry(Entry&& o) = default;

src/common/threadsafe_queue.h

@@ -8,7 +8,6 @@
 // single reader, single writer queue
 
 #include <atomic>
-#include <condition_variable>
 #include <cstddef>
 #include <mutex>
 #include <utility>
@@ -46,7 +45,6 @@ public:
         ElementPtr* new_ptr = new ElementPtr();
         write_ptr->next.store(new_ptr, std::memory_order_release);
         write_ptr = new_ptr;
-        cv.notify_one();
 
         ++size;
     }
@@ -76,16 +74,6 @@ public:
         return true;
     }
 
-    T PopWait() {
-        if (Empty()) {
-            std::unique_lock<std::mutex> lock(cv_mutex);
-            cv.wait(lock, [this]() { return !Empty(); });
-        }
-        T t;
-        Pop(t);
-        return t;
-    }
-
     // not thread-safe
     void Clear() {
         size.store(0);
@@ -113,8 +101,6 @@ private:
     ElementPtr* write_ptr;
     ElementPtr* read_ptr;
     std::atomic_size_t size{0};
-    std::mutex cv_mutex;
-    std::condition_variable cv;
 };
 
 // a simple thread-safe,
@@ -149,10 +135,6 @@ public:
         return spsc_queue.Pop(t);
     }
 
-    T PopWait() {
-        return spsc_queue.PopWait();
-    }
-
     // not thread-safe
     void Clear() {
         spsc_queue.Clear();

src/common/uint128.cpp

@@ -0,0 +1,41 @@
+#ifdef _MSC_VER
+#include <intrin.h>
+
+#pragma intrinsic(_umul128)
+#endif
+#include <cstring>
+#include "common/uint128.h"
+
+namespace Common {
+
+u128 Multiply64Into128(u64 a, u64 b) {
+    u128 result;
+#ifdef _MSC_VER
+    result[0] = _umul128(a, b, &result[1]);
+#else
+    unsigned __int128 tmp = a;
+    tmp *= b;
+    std::memcpy(&result, &tmp, sizeof(u128));
+#endif
+    return result;
+}
+
+std::pair<u64, u64> Divide128On32(u128 dividend, u32 divisor) {
+    u64 remainder = dividend[0] % divisor;
+    u64 accum = dividend[0] / divisor;
+    if (dividend[1] == 0)
+        return {accum, remainder};
+    // We ignore dividend[1] / divisor as that overflows
+    const u64 first_segment = (dividend[1] % divisor) << 32;
+    accum += (first_segment / divisor) << 32;
+    const u64 second_segment = (first_segment % divisor) << 32;
+    accum += (second_segment / divisor);
+    remainder += second_segment % divisor;
+    if (remainder >= divisor) {
+        accum++;
+        remainder -= divisor;
+    }
+    return {accum, remainder};
+}
+
+} // namespace Common

src/common/uint128.h

@@ -0,0 +1,14 @@
+
+#include <utility>
+#include "common/common_types.h"
+
+namespace Common {
+
+// This function multiplies 2 u64 values and produces a u128 value;
+u128 Multiply64Into128(u64 a, u64 b);
+
+// This function divides a u128 by a u32 value and produces two u64 values:
+// the result of division and the remainder
+std::pair<u64, u64> Divide128On32(u128 dividend, u32 divisor);
+
+} // namespace Common

src/core/CMakeLists.txt

@@ -400,10 +400,6 @@ add_library(core STATIC
     hle/service/time/time.h
     hle/service/usb/usb.cpp
     hle/service/usb/usb.h
-    hle/service/vi/display/vi_display.cpp
-    hle/service/vi/display/vi_display.h
-    hle/service/vi/layer/vi_layer.cpp
-    hle/service/vi/layer/vi_layer.h
     hle/service/vi/vi.cpp
     hle/service/vi/vi.h
     hle/service/vi/vi_m.cpp

src/core/arm/dynarmic/arm_dynarmic.cpp

@@ -12,6 +12,7 @@
 #include "core/core.h"
 #include "core/core_cpu.h"
 #include "core/core_timing.h"
+#include "core/core_timing_util.h"
 #include "core/gdbstub/gdbstub.h"
 #include "core/hle/kernel/process.h"
 #include "core/hle/kernel/svc.h"
@@ -119,7 +120,7 @@ public:
         return std::max(parent.core_timing.GetDowncount(), 0);
     }
     u64 GetCNTPCT() override {
-        return parent.core_timing.GetTicks();
+        return Timing::CpuCyclesToClockCycles(parent.core_timing.GetTicks());
     }
 
     ARM_Dynarmic& parent;
@@ -151,7 +152,7 @@ std::unique_ptr<Dynarmic::A64::Jit> ARM_Dynarmic::MakeJit() const {
     config.tpidr_el0 = &cb->tpidr_el0;
     config.dczid_el0 = 4;
     config.ctr_el0 = 0x8444c004;
-    config.cntfrq_el0 = 19200000; // Value from fusee.
+    config.cntfrq_el0 = Timing::CNTFREQ;
 
     // Unpredictable instructions
     config.define_unpredictable_behaviour = true;

src/core/core.cpp

@@ -128,7 +128,7 @@ struct System::Impl {
             return ResultStatus::ErrorVideoCore;
         }
 
-        gpu_core = std::make_unique<Tegra::GPU>(system, renderer->Rasterizer());
+        gpu_core = std::make_unique<Tegra::GPU>(renderer->Rasterizer());
 
         cpu_core_manager.Initialize(system);
         is_powered_on = true;

src/core/core_timing_util.cpp

@@ -7,6 +7,7 @@
 #include <cinttypes>
 #include <limits>
 #include "common/logging/log.h"
+#include "common/uint128.h"
 
 namespace Core::Timing {
 
@@ -60,4 +61,9 @@ s64 nsToCycles(u64 ns) {
     return (BASE_CLOCK_RATE * static_cast<s64>(ns)) / 1000000000;
 }
 
+u64 CpuCyclesToClockCycles(u64 ticks) {
+    const u128 temporal = Common::Multiply64Into128(ticks, CNTFREQ);
+    return Common::Divide128On32(temporal, static_cast<u32>(BASE_CLOCK_RATE)).first;
+}
+
 } // namespace Core::Timing

src/core/core_timing_util.h

@@ -11,6 +11,7 @@ namespace Core::Timing {
 // The below clock rate is based on Switch's clockspeed being widely known as 1.020GHz
 // The exact value used is of course unverified.
 constexpr u64 BASE_CLOCK_RATE = 1019215872; // Switch clock speed is 1020MHz un/docked
+constexpr u64 CNTFREQ = 19200000;           // Value from fusee.
 
 inline s64 msToCycles(int ms) {
     // since ms is int there is no way to overflow
@@ -61,4 +62,6 @@ inline u64 cyclesToMs(s64 cycles) {
     return cycles * 1000 / BASE_CLOCK_RATE;
 }
 
+u64 CpuCyclesToClockCycles(u64 ticks);
+
 } // namespace Core::Timing

src/core/crypto/key_manager.cpp

@@ -398,8 +398,7 @@ static bool ValidCryptoRevisionString(std::string_view base, size_t begin, size_
 }
 
 void KeyManager::LoadFromFile(const std::string& filename, bool is_title_keys) {
-    std::ifstream file;
-    OpenFStream(file, filename, std::ios_base::in);
+    std::ifstream file(filename);
     if (!file.is_open())
         return;
 

src/core/file_sys/vfs_vector.cpp

@@ -47,7 +47,7 @@ std::size_t VectorVfsFile::Write(const u8* data_, std::size_t length, std::size_
     if (offset + length > data.size())
         data.resize(offset + length);
     const auto write = std::min(length, data.size() - offset);
-    std::memcpy(data.data() + offset, data_, write);
+    std::memcpy(data.data(), data_, write);
     return write;
 }
 

src/core/hle/kernel/address_arbiter.cpp

@@ -17,7 +17,8 @@
 #include "core/hle/result.h"
 #include "core/memory.h"
 
-namespace Kernel::AddressArbiter {
+namespace Kernel {
+namespace AddressArbiter {
 
 // Performs actual address waiting logic.
 static ResultCode WaitForAddress(VAddr address, s64 timeout) {
@@ -175,4 +176,5 @@ ResultCode WaitForAddressIfEqual(VAddr address, s32 value, s64 timeout) {
 
     return WaitForAddress(address, timeout);
 }
-} // namespace Kernel::AddressArbiter
+} // namespace AddressArbiter
+} // namespace Kernel

src/core/hle/kernel/address_arbiter.h

@@ -8,8 +8,9 @@
 
 union ResultCode;
 
-namespace Kernel::AddressArbiter {
+namespace Kernel {
 
+namespace AddressArbiter {
 enum class ArbitrationType {
     WaitIfLessThan = 0,
     DecrementAndWaitIfLessThan = 1,
@@ -28,5 +29,6 @@ ResultCode ModifyByWaitingCountAndSignalToAddressIfEqual(VAddr address, s32 valu
 
 ResultCode WaitForAddressIfLessThan(VAddr address, s32 value, s64 timeout, bool should_decrement);
 ResultCode WaitForAddressIfEqual(VAddr address, s32 value, s64 timeout);
+} // namespace AddressArbiter
 
-} // namespace Kernel::AddressArbiter
+} // namespace Kernel

src/core/hle/service/nvflinger/nvflinger.cpp

@@ -14,12 +14,11 @@
 #include "core/core_timing_util.h"
 #include "core/hle/kernel/kernel.h"
 #include "core/hle/kernel/readable_event.h"
+#include "core/hle/kernel/writable_event.h"
 #include "core/hle/service/nvdrv/devices/nvdisp_disp0.h"
 #include "core/hle/service/nvdrv/nvdrv.h"
 #include "core/hle/service/nvflinger/buffer_queue.h"
 #include "core/hle/service/nvflinger/nvflinger.h"
-#include "core/hle/service/vi/display/vi_display.h"
-#include "core/hle/service/vi/layer/vi_layer.h"
 #include "core/perf_stats.h"
 #include "video_core/renderer_base.h"
 
@@ -28,9 +27,7 @@ namespace Service::NVFlinger {
 constexpr std::size_t SCREEN_REFRESH_RATE = 60;
 constexpr u64 frame_ticks = static_cast<u64>(Core::Timing::BASE_CLOCK_RATE / SCREEN_REFRESH_RATE);
 
-NVFlinger::NVFlinger(Core::Timing::CoreTiming& core_timing)
-    : displays{{0, "Default"}, {1, "External"}, {2, "Edid"}, {3, "Internal"}, {4, "Null"}},
-      core_timing{core_timing} {
+NVFlinger::NVFlinger(Core::Timing::CoreTiming& core_timing) : core_timing{core_timing} {
     // Schedule the screen composition events
     composition_event =
         core_timing.RegisterEvent("ScreenComposition", [this](u64 userdata, int cycles_late) {
@@ -56,7 +53,7 @@ std::optional<u64> NVFlinger::OpenDisplay(std::string_view name) {
     ASSERT(name == "Default");
 
     const auto itr = std::find_if(displays.begin(), displays.end(),
-                                  [&](const VI::Display& display) { return display.name == name; });
+                                  [&](const Display& display) { return display.name == name; });
     if (itr == displays.end()) {
         return {};
     }
@@ -109,10 +106,9 @@ std::shared_ptr<BufferQueue> NVFlinger::FindBufferQueue(u32 id) const {
     return *itr;
 }
 
-VI::Display* NVFlinger::FindDisplay(u64 display_id) {
-    const auto itr =
-        std::find_if(displays.begin(), displays.end(),
-                     [&](const VI::Display& display) { return display.id == display_id; });
+Display* NVFlinger::FindDisplay(u64 display_id) {
+    const auto itr = std::find_if(displays.begin(), displays.end(),
+                                  [&](const Display& display) { return display.id == display_id; });
 
     if (itr == displays.end()) {
         return nullptr;
@@ -121,10 +117,9 @@ VI::Display* NVFlinger::FindDisplay(u64 display_id) {
     return &*itr;
 }
 
-const VI::Display* NVFlinger::FindDisplay(u64 display_id) const {
-    const auto itr =
-        std::find_if(displays.begin(), displays.end(),
-                     [&](const VI::Display& display) { return display.id == display_id; });
+const Display* NVFlinger::FindDisplay(u64 display_id) const {
+    const auto itr = std::find_if(displays.begin(), displays.end(),
+                                  [&](const Display& display) { return display.id == display_id; });
 
     if (itr == displays.end()) {
         return nullptr;
@@ -133,7 +128,7 @@ const VI::Display* NVFlinger::FindDisplay(u64 display_id) const {
     return &*itr;
 }
 
-VI::Layer* NVFlinger::FindLayer(u64 display_id, u64 layer_id) {
+Layer* NVFlinger::FindLayer(u64 display_id, u64 layer_id) {
     auto* const display = FindDisplay(display_id);
 
     if (display == nullptr) {
@@ -141,7 +136,7 @@ VI::Layer* NVFlinger::FindLayer(u64 display_id, u64 layer_id) {
     }
 
     const auto itr = std::find_if(display->layers.begin(), display->layers.end(),
-                                  [&](const VI::Layer& layer) { return layer.id == layer_id; });
+                                  [&](const Layer& layer) { return layer.id == layer_id; });
 
     if (itr == display->layers.end()) {
         return nullptr;
@@ -150,7 +145,7 @@ VI::Layer* NVFlinger::FindLayer(u64 display_id, u64 layer_id) {
     return &*itr;
 }
 
-const VI::Layer* NVFlinger::FindLayer(u64 display_id, u64 layer_id) const {
+const Layer* NVFlinger::FindLayer(u64 display_id, u64 layer_id) const {
     const auto* const display = FindDisplay(display_id);
 
     if (display == nullptr) {
@@ -158,7 +153,7 @@ const VI::Layer* NVFlinger::FindLayer(u64 display_id, u64 layer_id) const {
     }
 
     const auto itr = std::find_if(display->layers.begin(), display->layers.end(),
-                                  [&](const VI::Layer& layer) { return layer.id == layer_id; });
+                                  [&](const Layer& layer) { return layer.id == layer_id; });
 
     if (itr == display->layers.end()) {
         return nullptr;
@@ -179,7 +174,7 @@ void NVFlinger::Compose() {
         // TODO(Subv): Support more than 1 layer.
         ASSERT_MSG(display.layers.size() == 1, "Max 1 layer per display is supported");
 
-        VI::Layer& layer = display.layers[0];
+        Layer& layer = display.layers[0];
         auto& buffer_queue = layer.buffer_queue;
 
         // Search for a queued buffer and acquire it
@@ -212,4 +207,15 @@ void NVFlinger::Compose() {
     }
 }
 
+Layer::Layer(u64 id, std::shared_ptr<BufferQueue> queue) : id(id), buffer_queue(std::move(queue)) {}
+Layer::~Layer() = default;
+
+Display::Display(u64 id, std::string name) : id(id), name(std::move(name)) {
+    auto& kernel = Core::System::GetInstance().Kernel();
+    vsync_event = Kernel::WritableEvent::CreateEventPair(kernel, Kernel::ResetType::Sticky,
+                                                         fmt::format("Display VSync Event {}", id));
+}
+
+Display::~Display() = default;
+
 } // namespace Service::NVFlinger

src/core/hle/service/nvflinger/nvflinger.h

@@ -4,6 +4,7 @@
 
 #pragma once
 
+#include <array>
 #include <memory>
 #include <optional>
 #include <string>
@@ -25,17 +26,31 @@ class WritableEvent;
 
 namespace Service::Nvidia {
 class Module;
-} // namespace Service::Nvidia
-
-namespace Service::VI {
-struct Display;
-struct Layer;
-} // namespace Service::VI
+}
 
 namespace Service::NVFlinger {
 
 class BufferQueue;
 
+struct Layer {
+    Layer(u64 id, std::shared_ptr<BufferQueue> queue);
+    ~Layer();
+
+    u64 id;
+    std::shared_ptr<BufferQueue> buffer_queue;
+};
+
+struct Display {
+    Display(u64 id, std::string name);
+    ~Display();
+
+    u64 id;
+    std::string name;
+
+    std::vector<Layer> layers;
+    Kernel::EventPair vsync_event;
+};
+
 class NVFlinger final {
 public:
     explicit NVFlinger(Core::Timing::CoreTiming& core_timing);
@@ -73,20 +88,26 @@ public:
 
 private:
     /// Finds the display identified by the specified ID.
-    VI::Display* FindDisplay(u64 display_id);
+    Display* FindDisplay(u64 display_id);
 
     /// Finds the display identified by the specified ID.
-    const VI::Display* FindDisplay(u64 display_id) const;
+    const Display* FindDisplay(u64 display_id) const;
 
     /// Finds the layer identified by the specified ID in the desired display.
-    VI::Layer* FindLayer(u64 display_id, u64 layer_id);
+    Layer* FindLayer(u64 display_id, u64 layer_id);
 
     /// Finds the layer identified by the specified ID in the desired display.
-    const VI::Layer* FindLayer(u64 display_id, u64 layer_id) const;
+    const Layer* FindLayer(u64 display_id, u64 layer_id) const;
 
     std::shared_ptr<Nvidia::Module> nvdrv;
 
-    std::vector<VI::Display> displays;
+    std::array<Display, 5> displays{{
+        {0, "Default"},
+        {1, "External"},
+        {2, "Edid"},
+        {3, "Internal"},
+        {4, "Null"},
+    }};
     std::vector<std::shared_ptr<BufferQueue>> buffer_queues;
 
     /// Id to use for the next layer that is created, this counter is shared among all displays.

src/core/hle/service/vi/display/vi_display.cpp

@@ -1,22 +0,0 @@
-// Copyright 2019 yuzu emulator team
-// Licensed under GPLv2 or any later version
-// Refer to the license.txt file included.
-
-#include <fmt/format.h>
-
-#include "core/core.h"
-#include "core/hle/kernel/readable_event.h"
-#include "core/hle/service/vi/display/vi_display.h"
-#include "core/hle/service/vi/layer/vi_layer.h"
-
-namespace Service::VI {
-
-Display::Display(u64 id, std::string name) : id{id}, name{std::move(name)} {
-    auto& kernel = Core::System::GetInstance().Kernel();
-    vsync_event = Kernel::WritableEvent::CreateEventPair(kernel, Kernel::ResetType::Sticky,
-                                                         fmt::format("Display VSync Event {}", id));
-}
-
-Display::~Display() = default;
-
-} // namespace Service::VI

src/core/hle/service/vi/display/vi_display.h

@@ -1,28 +0,0 @@
-// Copyright 2019 yuzu emulator team
-// Licensed under GPLv2 or any later version
-// Refer to the license.txt file included.
-
-#pragma once
-
-#include <string>
-#include <vector>
-
-#include "common/common_types.h"
-#include "core/hle/kernel/writable_event.h"
-
-namespace Service::VI {
-
-struct Layer;
-
-struct Display {
-    Display(u64 id, std::string name);
-    ~Display();
-
-    u64 id;
-    std::string name;
-
-    std::vector<Layer> layers;
-    Kernel::EventPair vsync_event;
-};
-
-} // namespace Service::VI

src/core/hle/service/vi/layer/vi_layer.cpp

@@ -1,14 +0,0 @@
-// Copyright 2019 yuzu emulator team
-// Licensed under GPLv2 or any later version
-// Refer to the license.txt file included.
-
-#include "core/hle/service/vi/layer/vi_layer.h"
-
-namespace Service::VI {
-
-Layer::Layer(u64 id, std::shared_ptr<NVFlinger::BufferQueue> queue)
-    : id{id}, buffer_queue{std::move(queue)} {}
-
-Layer::~Layer() = default;
-
-} // namespace Service::VI

src/core/hle/service/vi/layer/vi_layer.h

@@ -1,25 +0,0 @@
-// Copyright 2019 yuzu emulator team
-// Licensed under GPLv2 or any later version
-// Refer to the license.txt file included.
-
-#pragma once
-
-#include <memory>
-
-#include "common/common_types.h"
-
-namespace Service::NVFlinger {
-class BufferQueue;
-}
-
-namespace Service::VI {
-
-struct Layer {
-    Layer(u64 id, std::shared_ptr<NVFlinger::BufferQueue> queue);
-    ~Layer();
-
-    u64 id;
-    std::shared_ptr<NVFlinger::BufferQueue> buffer_queue;
-};
-
-} // namespace Service::VI

src/video_core/CMakeLists.txt

@@ -105,13 +105,7 @@ if (ENABLE_VULKAN)
     target_sources(video_core PRIVATE
         renderer_vulkan/declarations.h
         renderer_vulkan/vk_device.cpp
-        renderer_vulkan/vk_device.h
-        renderer_vulkan/vk_memory_manager.cpp
-        renderer_vulkan/vk_memory_manager.h
-        renderer_vulkan/vk_resource_manager.cpp
-        renderer_vulkan/vk_resource_manager.h
-        renderer_vulkan/vk_scheduler.cpp
-        renderer_vulkan/vk_scheduler.h)
+        renderer_vulkan/vk_device.h)
 
     target_include_directories(video_core PRIVATE ../../externals/Vulkan-Headers/include)
     target_compile_definitions(video_core PRIVATE HAS_VULKAN)

src/video_core/dma_pusher.cpp

@@ -33,36 +33,18 @@ void DmaPusher::DispatchCalls() {
 }
 
 bool DmaPusher::Step() {
-    if (!ib_enable || dma_pushbuffer.empty()) {
-        // pushbuffer empty and IB empty or nonexistent - nothing to do
-        return false;
-    }
+    if (dma_get != dma_put) {
+        // Push buffer non-empty, read a word
+        const auto address = gpu.MemoryManager().GpuToCpuAddress(dma_get);
+        ASSERT_MSG(address, "Invalid GPU address");
 
-    const CommandList& command_list{dma_pushbuffer.front()};
-    const CommandListHeader& command_list_header{command_list[dma_pushbuffer_subindex++]};
-    GPUVAddr dma_get = command_list_header.addr;
-    GPUVAddr dma_put = dma_get + command_list_header.size * sizeof(u32);
-    bool non_main = command_list_header.is_non_main;
+        const CommandHeader command_header{Memory::Read32(*address)};
 
-    if (dma_pushbuffer_subindex >= command_list.size()) {
-        // We've gone through the current list, remove it from the queue
-        dma_pushbuffer.pop();
-        dma_pushbuffer_subindex = 0;
-    }
+        dma_get += sizeof(u32);
 
-    if (command_list_header.size == 0) {
-        return true;
-    }
-
-    // Push buffer non-empty, read a word
-    const auto address = gpu.MemoryManager().GpuToCpuAddress(dma_get);
-    ASSERT_MSG(address, "Invalid GPU address");
-
-    command_headers.resize(command_list_header.size);
-
-    Memory::ReadBlock(*address, command_headers.data(), command_list_header.size * sizeof(u32));
-
-    for (const CommandHeader& command_header : command_headers) {
+        if (!non_main) {
+            dma_mget = dma_get;
+        }
 
         // now, see if we're in the middle of a command
         if (dma_state.length_pending) {
@@ -109,11 +91,22 @@ bool DmaPusher::Step() {
                 break;
             }
         }
-    }
+    } else if (ib_enable && !dma_pushbuffer.empty()) {
+        // Current pushbuffer empty, but we have more IB entries to read
+        const CommandList& command_list{dma_pushbuffer.front()};
+        const CommandListHeader& command_list_header{command_list[dma_pushbuffer_subindex++]};
+        dma_get = command_list_header.addr;
+        dma_put = dma_get + command_list_header.size * sizeof(u32);
+        non_main = command_list_header.is_non_main;
 
-    if (!non_main) {
-        // TODO (degasus): This is dead code, as dma_mget is never read.
-        dma_mget = dma_put;
+        if (dma_pushbuffer_subindex >= command_list.size()) {
+            // We've gone through the current list, remove it from the queue
+            dma_pushbuffer.pop();
+            dma_pushbuffer_subindex = 0;
+        }
+    } else {
+        // Otherwise, pushbuffer empty and IB empty or nonexistent - nothing to do
+        return {};
     }
 
     return true;

src/video_core/dma_pusher.h

@@ -75,8 +75,6 @@ private:
 
     GPU& gpu;
 
-    std::vector<CommandHeader> command_headers; ///< Buffer for list of commands fetched at once
-
     std::queue<CommandList> dma_pushbuffer; ///< Queue of command lists to be processed
     std::size_t dma_pushbuffer_subindex{};  ///< Index within a command list within the pushbuffer
 
@@ -91,8 +89,11 @@ private:
     DmaState dma_state{};
     bool dma_increment_once{};
 
+    GPUVAddr dma_put{};   ///< pushbuffer current end address
+    GPUVAddr dma_get{};   ///< pushbuffer current read address
     GPUVAddr dma_mget{};  ///< main pushbuffer last read address
     bool ib_enable{true}; ///< IB mode enabled
+    bool non_main{};      ///< non-main pushbuffer active
 };
 
 } // namespace Tegra

src/video_core/engines/kepler_memory.cpp

@@ -2,7 +2,6 @@
 // Licensed under GPLv2 or any later version
 // Refer to the license.txt file included.
 
-#include "common/assert.h"
 #include "common/logging/log.h"
 #include "core/core.h"
 #include "core/memory.h"
@@ -12,9 +11,9 @@
 
 namespace Tegra::Engines {
 
-KeplerMemory::KeplerMemory(Core::System& system, VideoCore::RasterizerInterface& rasterizer,
+KeplerMemory::KeplerMemory(VideoCore::RasterizerInterface& rasterizer,
                            MemoryManager& memory_manager)
-    : system{system}, memory_manager(memory_manager), rasterizer{rasterizer} {}
+    : memory_manager(memory_manager), rasterizer{rasterizer} {}
 
 KeplerMemory::~KeplerMemory() = default;
 
@@ -51,7 +50,7 @@ void KeplerMemory::ProcessData(u32 data) {
     rasterizer.InvalidateRegion(*dest_address, sizeof(u32));
 
     Memory::Write32(*dest_address, data);
-    system.GPU().Maxwell3D().dirty_flags.OnMemoryWrite();
+    Core::System::GetInstance().GPU().Maxwell3D().dirty_flags.OnMemoryWrite();
 
     state.write_offset++;
 }

src/video_core/engines/kepler_memory.h

@@ -5,16 +5,13 @@
 #pragma once
 
 #include <array>
+#include "common/assert.h"
 #include "common/bit_field.h"
 #include "common/common_funcs.h"
 #include "common/common_types.h"
 #include "video_core/gpu.h"
 #include "video_core/memory_manager.h"
 
-namespace Core {
-class System;
-}
-
 namespace VideoCore {
 class RasterizerInterface;
 }
@@ -26,8 +23,7 @@ namespace Tegra::Engines {
 
 class KeplerMemory final {
 public:
-    KeplerMemory(Core::System& system, VideoCore::RasterizerInterface& rasterizer,
-                 MemoryManager& memory_manager);
+    KeplerMemory(VideoCore::RasterizerInterface& rasterizer, MemoryManager& memory_manager);
     ~KeplerMemory();
 
     /// Write the value to the register identified by method.
@@ -80,7 +76,6 @@ public:
     } state{};
 
 private:
-    Core::System& system;
     MemoryManager& memory_manager;
     VideoCore::RasterizerInterface& rasterizer;
 

src/video_core/engines/maxwell_3d.cpp

@@ -19,10 +19,8 @@ namespace Tegra::Engines {
 /// First register id that is actually a Macro call.
 constexpr u32 MacroRegistersStart = 0xE00;
 
-Maxwell3D::Maxwell3D(Core::System& system, VideoCore::RasterizerInterface& rasterizer,
-                     MemoryManager& memory_manager)
-    : memory_manager(memory_manager), system{system}, rasterizer{rasterizer},
-      macro_interpreter(*this) {
+Maxwell3D::Maxwell3D(VideoCore::RasterizerInterface& rasterizer, MemoryManager& memory_manager)
+    : memory_manager(memory_manager), rasterizer{rasterizer}, macro_interpreter(*this) {
     InitializeRegisterDefaults();
 }
 
@@ -105,7 +103,7 @@ void Maxwell3D::CallMacroMethod(u32 method, std::vector<u32> parameters) {
 }
 
 void Maxwell3D::CallMethod(const GPU::MethodCall& method_call) {
-    auto debug_context = system.GetGPUDebugContext();
+    auto debug_context = Core::System::GetInstance().GetGPUDebugContext();
 
     // It is an error to write to a register other than the current macro's ARG register before it
     // has finished execution.
@@ -319,7 +317,7 @@ void Maxwell3D::ProcessQueryGet() {
             LongQueryResult query_result{};
             query_result.value = result;
             // TODO(Subv): Generate a real GPU timestamp and write it here instead of CoreTiming
-            query_result.timestamp = system.CoreTiming().GetTicks();
+            query_result.timestamp = Core::System::GetInstance().CoreTiming().GetTicks();
             Memory::WriteBlock(*address, &query_result, sizeof(query_result));
         }
         dirty_flags.OnMemoryWrite();
@@ -336,7 +334,7 @@ void Maxwell3D::DrawArrays() {
               regs.vertex_buffer.count);
     ASSERT_MSG(!(regs.index_array.count && regs.vertex_buffer.count), "Both indexed and direct?");
 
-    auto debug_context = system.GetGPUDebugContext();
+    auto debug_context = Core::System::GetInstance().GetGPUDebugContext();
 
     if (debug_context) {
         debug_context->OnEvent(Tegra::DebugContext::Event::IncomingPrimitiveBatch, nullptr);

src/video_core/engines/maxwell_3d.h

@@ -17,10 +17,6 @@
 #include "video_core/memory_manager.h"
 #include "video_core/textures/texture.h"
 
-namespace Core {
-class System;
-}
-
 namespace VideoCore {
 class RasterizerInterface;
 }
@@ -32,8 +28,7 @@ namespace Tegra::Engines {
 
 class Maxwell3D final {
 public:
-    explicit Maxwell3D(Core::System& system, VideoCore::RasterizerInterface& rasterizer,
-                       MemoryManager& memory_manager);
+    explicit Maxwell3D(VideoCore::RasterizerInterface& rasterizer, MemoryManager& memory_manager);
     ~Maxwell3D() = default;
 
     /// Register structure of the Maxwell3D engine.
@@ -1136,8 +1131,6 @@ public:
 private:
     void InitializeRegisterDefaults();
 
-    Core::System& system;
-
     VideoCore::RasterizerInterface& rasterizer;
 
     /// Start offsets of each macro in macro_memory

src/video_core/engines/maxwell_dma.cpp

@@ -2,7 +2,6 @@
 // Licensed under GPLv2 or any later version
 // Refer to the license.txt file included.
 
-#include "common/assert.h"
 #include "core/core.h"
 #include "core/memory.h"
 #include "video_core/engines/maxwell_3d.h"
@@ -12,9 +11,8 @@
 
 namespace Tegra::Engines {
 
-MaxwellDMA::MaxwellDMA(Core::System& system, VideoCore::RasterizerInterface& rasterizer,
-                       MemoryManager& memory_manager)
-    : memory_manager(memory_manager), system{system}, rasterizer{rasterizer} {}
+MaxwellDMA::MaxwellDMA(VideoCore::RasterizerInterface& rasterizer, MemoryManager& memory_manager)
+    : memory_manager(memory_manager), rasterizer{rasterizer} {}
 
 void MaxwellDMA::CallMethod(const GPU::MethodCall& method_call) {
     ASSERT_MSG(method_call.method < Regs::NUM_REGS,
@@ -61,7 +59,7 @@ void MaxwellDMA::HandleCopy() {
     }
 
     // All copies here update the main memory, so mark all rasterizer states as invalid.
-    system.GPU().Maxwell3D().dirty_flags.OnMemoryWrite();
+    Core::System::GetInstance().GPU().Maxwell3D().dirty_flags.OnMemoryWrite();
 
     if (regs.exec.is_dst_linear && regs.exec.is_src_linear) {
         // When the enable_2d bit is disabled, the copy is performed as if we were copying a 1D

src/video_core/engines/maxwell_dma.h

@@ -5,16 +5,13 @@
 #pragma once
 
 #include <array>
+#include "common/assert.h"
 #include "common/bit_field.h"
 #include "common/common_funcs.h"
 #include "common/common_types.h"
 #include "video_core/gpu.h"
 #include "video_core/memory_manager.h"
 
-namespace Core {
-class System;
-}
-
 namespace VideoCore {
 class RasterizerInterface;
 }
@@ -23,8 +20,7 @@ namespace Tegra::Engines {
 
 class MaxwellDMA final {
 public:
-    explicit MaxwellDMA(Core::System& system, VideoCore::RasterizerInterface& rasterizer,
-                        MemoryManager& memory_manager);
+    explicit MaxwellDMA(VideoCore::RasterizerInterface& rasterizer, MemoryManager& memory_manager);
     ~MaxwellDMA() = default;
 
     /// Write the value to the register identified by method.
@@ -141,8 +137,6 @@ public:
     MemoryManager& memory_manager;
 
 private:
-    Core::System& system;
-
     VideoCore::RasterizerInterface& rasterizer;
 
     /// Performs the copy from the source buffer to the destination buffer as configured in the

src/video_core/gpu.cpp

@@ -28,14 +28,14 @@ u32 FramebufferConfig::BytesPerPixel(PixelFormat format) {
     UNREACHABLE();
 }
 
-GPU::GPU(Core::System& system, VideoCore::RasterizerInterface& rasterizer) {
+GPU::GPU(VideoCore::RasterizerInterface& rasterizer) {
     memory_manager = std::make_unique<Tegra::MemoryManager>();
     dma_pusher = std::make_unique<Tegra::DmaPusher>(*this);
-    maxwell_3d = std::make_unique<Engines::Maxwell3D>(system, rasterizer, *memory_manager);
+    maxwell_3d = std::make_unique<Engines::Maxwell3D>(rasterizer, *memory_manager);
     fermi_2d = std::make_unique<Engines::Fermi2D>(rasterizer, *memory_manager);
     kepler_compute = std::make_unique<Engines::KeplerCompute>(*memory_manager);
-    maxwell_dma = std::make_unique<Engines::MaxwellDMA>(system, rasterizer, *memory_manager);
-    kepler_memory = std::make_unique<Engines::KeplerMemory>(system, rasterizer, *memory_manager);
+    maxwell_dma = std::make_unique<Engines::MaxwellDMA>(rasterizer, *memory_manager);
+    kepler_memory = std::make_unique<Engines::KeplerMemory>(rasterizer, *memory_manager);
 }
 
 GPU::~GPU() = default;

src/video_core/gpu.h

@@ -6,15 +6,12 @@
 
 #include <array>
 #include <memory>
+#include <vector>
 #include "common/common_types.h"
 #include "core/hle/service/nvflinger/buffer_queue.h"
 #include "video_core/dma_pusher.h"
 #include "video_core/memory_manager.h"
 
-namespace Core {
-class System;
-}
-
 namespace VideoCore {
 class RasterizerInterface;
 }
@@ -121,7 +118,7 @@ enum class EngineID {
 
 class GPU final {
 public:
-    explicit GPU(Core::System& system, VideoCore::RasterizerInterface& rasterizer);
+    explicit GPU(VideoCore::RasterizerInterface& rasterizer);
     ~GPU();
 
     struct MethodCall {

src/video_core/renderer_opengl/gl_rasterizer_cache.cpp

@@ -423,7 +423,7 @@ void SwizzleFunc(const MortonSwizzleMode& mode, const SurfaceParams& params,
         for (u32 i = 0; i < params.depth; i++) {
             MortonSwizzle(mode, params.pixel_format, params.MipWidth(mip_level),
                           params.MipBlockHeight(mip_level), params.MipHeight(mip_level),
-                          params.MipBlockDepth(mip_level), 1, params.tile_width_spacing,
+                          params.MipBlockDepth(mip_level), params.tile_width_spacing, 1,
                           gl_buffer.data() + offset_gl, gl_size, params.addr + offset);
             offset += layer_size;
             offset_gl += gl_size;

src/video_core/renderer_opengl/gl_state.cpp

@@ -11,9 +11,7 @@
 namespace OpenGL {
 
 OpenGLState OpenGLState::cur_state;
-
 bool OpenGLState::s_rgb_used;
-
 OpenGLState::OpenGLState() {
     // These all match default OpenGL values
     geometry_shaders.enabled = false;
@@ -114,6 +112,7 @@ void OpenGLState::ApplyDefaultState() {
 }
 
 void OpenGLState::ApplySRgb() const {
+    // sRGB
     if (framebuffer_srgb.enabled != cur_state.framebuffer_srgb.enabled) {
         if (framebuffer_srgb.enabled) {
             // Track if sRGB is used
@@ -126,20 +125,23 @@ void OpenGLState::ApplySRgb() const {
 }
 
 void OpenGLState::ApplyCulling() const {
-    if (cull.enabled != cur_state.cull.enabled) {
+    // Culling
+    const bool cull_changed = cull.enabled != cur_state.cull.enabled;
+    if (cull_changed) {
         if (cull.enabled) {
             glEnable(GL_CULL_FACE);
         } else {
             glDisable(GL_CULL_FACE);
         }
     }
+    if (cull.enabled) {
+        if (cull_changed || cull.mode != cur_state.cull.mode) {
+            glCullFace(cull.mode);
+        }
 
-    if (cull.mode != cur_state.cull.mode) {
-        glCullFace(cull.mode);
-    }
-
-    if (cull.front_face != cur_state.cull.front_face) {
-        glFrontFace(cull.front_face);
+        if (cull_changed || cull.front_face != cur_state.cull.front_face) {
+            glFrontFace(cull.front_face);
+        }
     }
 }
 
@@ -170,63 +172,72 @@ void OpenGLState::ApplyColorMask() const {
 }
 
 void OpenGLState::ApplyDepth() const {
-    if (depth.test_enabled != cur_state.depth.test_enabled) {
+    // Depth test
+    const bool depth_test_changed = depth.test_enabled != cur_state.depth.test_enabled;
+    if (depth_test_changed) {
         if (depth.test_enabled) {
             glEnable(GL_DEPTH_TEST);
         } else {
             glDisable(GL_DEPTH_TEST);
         }
     }
-
-    if (depth.test_func != cur_state.depth.test_func) {
+    if (depth.test_enabled &&
+        (depth_test_changed || depth.test_func != cur_state.depth.test_func)) {
         glDepthFunc(depth.test_func);
     }
-
+    // Depth mask
     if (depth.write_mask != cur_state.depth.write_mask) {
         glDepthMask(depth.write_mask);
     }
 }
 
 void OpenGLState::ApplyPrimitiveRestart() const {
-    if (primitive_restart.enabled != cur_state.primitive_restart.enabled) {
+    const bool primitive_restart_changed =
+        primitive_restart.enabled != cur_state.primitive_restart.enabled;
+    if (primitive_restart_changed) {
         if (primitive_restart.enabled) {
             glEnable(GL_PRIMITIVE_RESTART);
         } else {
             glDisable(GL_PRIMITIVE_RESTART);
         }
     }
-
-    if (primitive_restart.index != cur_state.primitive_restart.index) {
+    if (primitive_restart_changed ||
+        (primitive_restart.enabled &&
+         primitive_restart.index != cur_state.primitive_restart.index)) {
         glPrimitiveRestartIndex(primitive_restart.index);
     }
 }
 
 void OpenGLState::ApplyStencilTest() const {
-    if (stencil.test_enabled != cur_state.stencil.test_enabled) {
+    const bool stencil_test_changed = stencil.test_enabled != cur_state.stencil.test_enabled;
+    if (stencil_test_changed) {
         if (stencil.test_enabled) {
             glEnable(GL_STENCIL_TEST);
         } else {
             glDisable(GL_STENCIL_TEST);
         }
     }
-
-    const auto ConfigStencil = [](GLenum face, const auto& config, const auto& prev_config) {
-        if (config.test_func != prev_config.test_func || config.test_ref != prev_config.test_ref ||
-            config.test_mask != prev_config.test_mask) {
-            glStencilFuncSeparate(face, config.test_func, config.test_ref, config.test_mask);
-        }
-        if (config.action_depth_fail != prev_config.action_depth_fail ||
-            config.action_depth_pass != prev_config.action_depth_pass ||
-            config.action_stencil_fail != prev_config.action_stencil_fail) {
-            glStencilOpSeparate(face, config.action_stencil_fail, config.action_depth_fail,
-                                config.action_depth_pass);
-        }
-        if (config.write_mask != prev_config.write_mask) {
-            glStencilMaskSeparate(face, config.write_mask);
-        }
-    };
-    ConfigStencil(GL_FRONT, stencil.front, cur_state.stencil.front);
-    ConfigStencil(GL_BACK, stencil.back, cur_state.stencil.back);
+    if (stencil.test_enabled) {
+        auto config_stencil = [stencil_test_changed](GLenum face, const auto& config,
+                                                     const auto& prev_config) {
+            if (stencil_test_changed || config.test_func != prev_config.test_func ||
+                config.test_ref != prev_config.test_ref ||
+                config.test_mask != prev_config.test_mask) {
+                glStencilFuncSeparate(face, config.test_func, config.test_ref, config.test_mask);
+            }
+            if (stencil_test_changed || config.action_depth_fail != prev_config.action_depth_fail ||
+                config.action_depth_pass != prev_config.action_depth_pass ||
+                config.action_stencil_fail != prev_config.action_stencil_fail) {
+                glStencilOpSeparate(face, config.action_stencil_fail, config.action_depth_fail,
+                                    config.action_depth_pass);
+            }
+            if (config.write_mask != prev_config.write_mask) {
+                glStencilMaskSeparate(face, config.write_mask);
+            }
+        };
+        config_stencil(GL_FRONT, stencil.front, cur_state.stencil.front);
+        config_stencil(GL_BACK, stencil.back, cur_state.stencil.back);
+    }
 }
 // Viewport does not affects glClearBuffer so emulate viewport using scissor test
 void OpenGLState::EmulateViewportWithScissor() {
@@ -267,18 +278,19 @@ void OpenGLState::ApplyViewport() const {
                 updated.depth_range_far != current.depth_range_far) {
                 glDepthRangeIndexed(i, updated.depth_range_near, updated.depth_range_far);
             }
-
-            if (updated.scissor.enabled != current.scissor.enabled) {
+            const bool scissor_changed = updated.scissor.enabled != current.scissor.enabled;
+            if (scissor_changed) {
                 if (updated.scissor.enabled) {
                     glEnablei(GL_SCISSOR_TEST, i);
                 } else {
                     glDisablei(GL_SCISSOR_TEST, i);
                 }
             }
-
-            if (updated.scissor.x != current.scissor.x || updated.scissor.y != current.scissor.y ||
-                updated.scissor.width != current.scissor.width ||
-                updated.scissor.height != current.scissor.height) {
+            if (updated.scissor.enabled &&
+                (scissor_changed || updated.scissor.x != current.scissor.x ||
+                 updated.scissor.y != current.scissor.y ||
+                 updated.scissor.width != current.scissor.width ||
+                 updated.scissor.height != current.scissor.height)) {
                 glScissorIndexed(i, updated.scissor.x, updated.scissor.y, updated.scissor.width,
                                  updated.scissor.height);
             }
@@ -290,23 +302,22 @@ void OpenGLState::ApplyViewport() const {
             updated.height != current.height) {
             glViewport(updated.x, updated.y, updated.width, updated.height);
         }
-
         if (updated.depth_range_near != current.depth_range_near ||
             updated.depth_range_far != current.depth_range_far) {
             glDepthRange(updated.depth_range_near, updated.depth_range_far);
         }
-
-        if (updated.scissor.enabled != current.scissor.enabled) {
+        const bool scissor_changed = updated.scissor.enabled != current.scissor.enabled;
+        if (scissor_changed) {
             if (updated.scissor.enabled) {
                 glEnable(GL_SCISSOR_TEST);
             } else {
                 glDisable(GL_SCISSOR_TEST);
             }
         }
-
-        if (updated.scissor.x != current.scissor.x || updated.scissor.y != current.scissor.y ||
-            updated.scissor.width != current.scissor.width ||
-            updated.scissor.height != current.scissor.height) {
+        if (updated.scissor.enabled && (scissor_changed || updated.scissor.x != current.scissor.x ||
+                                        updated.scissor.y != current.scissor.y ||
+                                        updated.scissor.width != current.scissor.width ||
+                                        updated.scissor.height != current.scissor.height)) {
             glScissor(updated.scissor.x, updated.scissor.y, updated.scissor.width,
                       updated.scissor.height);
         }
@@ -316,7 +327,8 @@ void OpenGLState::ApplyViewport() const {
 void OpenGLState::ApplyGlobalBlending() const {
     const Blend& current = cur_state.blend[0];
     const Blend& updated = blend[0];
-    if (updated.enabled != current.enabled) {
+    const bool blend_changed = updated.enabled != current.enabled;
+    if (blend_changed) {
         if (updated.enabled) {
             glEnable(GL_BLEND);
         } else {
@@ -326,14 +338,15 @@ void OpenGLState::ApplyGlobalBlending() const {
     if (!updated.enabled) {
         return;
     }
-    if (updated.src_rgb_func != current.src_rgb_func ||
+    if (blend_changed || updated.src_rgb_func != current.src_rgb_func ||
         updated.dst_rgb_func != current.dst_rgb_func || updated.src_a_func != current.src_a_func ||
         updated.dst_a_func != current.dst_a_func) {
         glBlendFuncSeparate(updated.src_rgb_func, updated.dst_rgb_func, updated.src_a_func,
                             updated.dst_a_func);
     }
 
-    if (updated.rgb_equation != current.rgb_equation || updated.a_equation != current.a_equation) {
+    if (blend_changed || updated.rgb_equation != current.rgb_equation ||
+        updated.a_equation != current.a_equation) {
         glBlendEquationSeparate(updated.rgb_equation, updated.a_equation);
     }
 }
@@ -341,22 +354,26 @@ void OpenGLState::ApplyGlobalBlending() const {
 void OpenGLState::ApplyTargetBlending(std::size_t target, bool force) const {
     const Blend& updated = blend[target];
     const Blend& current = cur_state.blend[target];
-    if (updated.enabled != current.enabled || force) {
+    const bool blend_changed = updated.enabled != current.enabled || force;
+    if (blend_changed) {
         if (updated.enabled) {
             glEnablei(GL_BLEND, static_cast<GLuint>(target));
         } else {
             glDisablei(GL_BLEND, static_cast<GLuint>(target));
         }
     }
-
-    if (updated.src_rgb_func != current.src_rgb_func ||
+    if (!updated.enabled) {
+        return;
+    }
+    if (blend_changed || updated.src_rgb_func != current.src_rgb_func ||
         updated.dst_rgb_func != current.dst_rgb_func || updated.src_a_func != current.src_a_func ||
         updated.dst_a_func != current.dst_a_func) {
         glBlendFuncSeparatei(static_cast<GLuint>(target), updated.src_rgb_func,
                              updated.dst_rgb_func, updated.src_a_func, updated.dst_a_func);
     }
 
-    if (updated.rgb_equation != current.rgb_equation || updated.a_equation != current.a_equation) {
+    if (blend_changed || updated.rgb_equation != current.rgb_equation ||
+        updated.a_equation != current.a_equation) {
         glBlendEquationSeparatei(static_cast<GLuint>(target), updated.rgb_equation,
                                  updated.a_equation);
     }
@@ -380,7 +397,8 @@ void OpenGLState::ApplyBlending() const {
 }
 
 void OpenGLState::ApplyLogicOp() const {
-    if (logic_op.enabled != cur_state.logic_op.enabled) {
+    const bool logic_op_changed = logic_op.enabled != cur_state.logic_op.enabled;
+    if (logic_op_changed) {
         if (logic_op.enabled) {
             glEnable(GL_COLOR_LOGIC_OP);
         } else {
@@ -388,12 +406,14 @@ void OpenGLState::ApplyLogicOp() const {
         }
     }
 
-    if (logic_op.operation != cur_state.logic_op.operation) {
+    if (logic_op.enabled &&
+        (logic_op_changed || logic_op.operation != cur_state.logic_op.operation)) {
         glLogicOp(logic_op.operation);
     }
 }
 
 void OpenGLState::ApplyPolygonOffset() const {
+
     const bool fill_enable_changed =
         polygon_offset.fill_enable != cur_state.polygon_offset.fill_enable;
     const bool line_enable_changed =
@@ -428,7 +448,9 @@ void OpenGLState::ApplyPolygonOffset() const {
         }
     }
 
-    if (factor_changed || units_changed || clamp_changed) {
+    if ((polygon_offset.fill_enable || polygon_offset.line_enable || polygon_offset.point_enable) &&
+        (factor_changed || units_changed || clamp_changed)) {
+
         if (GLAD_GL_EXT_polygon_offset_clamp && polygon_offset.clamp != 0) {
             glPolygonOffsetClamp(polygon_offset.factor, polygon_offset.units, polygon_offset.clamp);
         } else {
@@ -506,9 +528,9 @@ void OpenGLState::ApplyDepthClamp() const {
         depth_clamp.near_plane == cur_state.depth_clamp.near_plane) {
         return;
     }
-    UNIMPLEMENTED_IF_MSG(depth_clamp.far_plane != depth_clamp.near_plane,
-                         "Unimplemented Depth Clamp Separation!");
-
+    if (depth_clamp.far_plane != depth_clamp.near_plane) {
+        UNIMPLEMENTED_MSG("Unimplemented Depth Clamp Separation!");
+    }
     if (depth_clamp.far_plane || depth_clamp.near_plane) {
         glEnable(GL_DEPTH_CLAMP);
     } else {

src/video_core/renderer_opengl/renderer_opengl.cpp

@@ -380,8 +380,7 @@ void RendererOpenGL::CaptureScreenshot() {
     GLuint renderbuffer;
     glGenRenderbuffers(1, &renderbuffer);
     glBindRenderbuffer(GL_RENDERBUFFER, renderbuffer);
-    glRenderbufferStorage(GL_RENDERBUFFER, state.GetsRGBUsed() ? GL_SRGB8 : GL_RGB8, layout.width,
-                          layout.height);
+    glRenderbufferStorage(GL_RENDERBUFFER, GL_RGB8, layout.width, layout.height);
     glFramebufferRenderbuffer(GL_FRAMEBUFFER, GL_COLOR_ATTACHMENT0, GL_RENDERBUFFER, renderbuffer);
 
     DrawScreen(layout);

src/video_core/renderer_vulkan/vk_memory_manager.cpp

@@ -1,252 +0,0 @@
-// Copyright 2018 yuzu Emulator Project
-// Licensed under GPLv2 or any later version
-// Refer to the license.txt file included.
-
-#include <algorithm>
-#include <optional>
-#include <tuple>
-#include <vector>
-#include "common/alignment.h"
-#include "common/assert.h"
-#include "common/common_types.h"
-#include "common/logging/log.h"
-#include "video_core/renderer_vulkan/declarations.h"
-#include "video_core/renderer_vulkan/vk_device.h"
-#include "video_core/renderer_vulkan/vk_memory_manager.h"
-
-namespace Vulkan {
-
-// TODO(Rodrigo): Fine tune this number
-constexpr u64 ALLOC_CHUNK_SIZE = 64 * 1024 * 1024;
-
-class VKMemoryAllocation final {
-public:
-    explicit VKMemoryAllocation(const VKDevice& device, vk::DeviceMemory memory,
-                                vk::MemoryPropertyFlags properties, u64 alloc_size, u32 type)
-        : device{device}, memory{memory}, properties{properties}, alloc_size{alloc_size},
-          shifted_type{ShiftType(type)}, is_mappable{properties &
-                                                     vk::MemoryPropertyFlagBits::eHostVisible} {
-        if (is_mappable) {
-            const auto dev = device.GetLogical();
-            const auto& dld = device.GetDispatchLoader();
-            base_address = static_cast<u8*>(dev.mapMemory(memory, 0, alloc_size, {}, dld));
-        }
-    }
-
-    ~VKMemoryAllocation() {
-        const auto dev = device.GetLogical();
-        const auto& dld = device.GetDispatchLoader();
-        if (is_mappable)
-            dev.unmapMemory(memory, dld);
-        dev.free(memory, nullptr, dld);
-    }
-
-    VKMemoryCommit Commit(vk::DeviceSize commit_size, vk::DeviceSize alignment) {
-        auto found = TryFindFreeSection(free_iterator, alloc_size, static_cast<u64>(commit_size),
-                                        static_cast<u64>(alignment));
-        if (!found) {
-            found = TryFindFreeSection(0, free_iterator, static_cast<u64>(commit_size),
-                                       static_cast<u64>(alignment));
-            if (!found) {
-                // Signal out of memory, it'll try to do more allocations.
-                return nullptr;
-            }
-        }
-        u8* address = is_mappable ? base_address + *found : nullptr;
-        auto commit = std::make_unique<VKMemoryCommitImpl>(this, memory, address, *found,
-                                                           *found + commit_size);
-        commits.push_back(commit.get());
-
-        // Last commit's address is highly probable to be free.
-        free_iterator = *found + commit_size;
-
-        return commit;
-    }
-
-    void Free(const VKMemoryCommitImpl* commit) {
-        ASSERT(commit);
-        const auto it =
-            std::find_if(commits.begin(), commits.end(),
-                         [&](const auto& stored_commit) { return stored_commit == commit; });
-        if (it == commits.end()) {
-            LOG_CRITICAL(Render_Vulkan, "Freeing unallocated commit!");
-            UNREACHABLE();
-            return;
-        }
-        commits.erase(it);
-    }
-
-    /// Returns whether this allocation is compatible with the arguments.
-    bool IsCompatible(vk::MemoryPropertyFlags wanted_properties, u32 type_mask) const {
-        return (wanted_properties & properties) != vk::MemoryPropertyFlagBits(0) &&
-               (type_mask & shifted_type) != 0;
-    }
-
-private:
-    static constexpr u32 ShiftType(u32 type) {
-        return 1U << type;
-    }
-
-    /// A memory allocator, it may return a free region between "start" and "end" with the solicited
-    /// requeriments.
-    std::optional<u64> TryFindFreeSection(u64 start, u64 end, u64 size, u64 alignment) const {
-        u64 iterator = start;
-        while (iterator + size < end) {
-            const u64 try_left = Common::AlignUp(iterator, alignment);
-            const u64 try_right = try_left + size;
-
-            bool overlap = false;
-            for (const auto& commit : commits) {
-                const auto [commit_left, commit_right] = commit->interval;
-                if (try_left < commit_right && commit_left < try_right) {
-                    // There's an overlap, continue the search where the overlapping commit ends.
-                    iterator = commit_right;
-                    overlap = true;
-                    break;
-                }
-            }
-            if (!overlap) {
-                // A free address has been found.
-                return try_left;
-            }
-        }
-        // No free regions where found, return an empty optional.
-        return std::nullopt;
-    }
-
-    const VKDevice& device;                   ///< Vulkan device.
-    const vk::DeviceMemory memory;            ///< Vulkan memory allocation handler.
-    const vk::MemoryPropertyFlags properties; ///< Vulkan properties.
-    const u64 alloc_size;                     ///< Size of this allocation.
-    const u32 shifted_type;                   ///< Stored Vulkan type of this allocation, shifted.
-    const bool is_mappable;                   ///< Whether the allocation is mappable.
-
-    /// Base address of the mapped pointer.
-    u8* base_address{};
-
-    /// Hints where the next free region is likely going to be.
-    u64 free_iterator{};
-
-    /// Stores all commits done from this allocation.
-    std::vector<const VKMemoryCommitImpl*> commits;
-};
-
-VKMemoryManager::VKMemoryManager(const VKDevice& device)
-    : device{device}, props{device.GetPhysical().getMemoryProperties(device.GetDispatchLoader())},
-      is_memory_unified{GetMemoryUnified(props)} {}
-
-VKMemoryManager::~VKMemoryManager() = default;
-
-VKMemoryCommit VKMemoryManager::Commit(const vk::MemoryRequirements& reqs, bool host_visible) {
-    ASSERT(reqs.size < ALLOC_CHUNK_SIZE);
-
-    // When a host visible commit is asked, search for host visible and coherent, otherwise search
-    // for a fast device local type.
-    const vk::MemoryPropertyFlags wanted_properties =
-        host_visible
-            ? vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent
-            : vk::MemoryPropertyFlagBits::eDeviceLocal;
-
-    const auto TryCommit = [&]() -> VKMemoryCommit {
-        for (auto& alloc : allocs) {
-            if (!alloc->IsCompatible(wanted_properties, reqs.memoryTypeBits))
-                continue;
-
-            if (auto commit = alloc->Commit(reqs.size, reqs.alignment); commit) {
-                return commit;
-            }
-        }
-        return {};
-    };
-
-    if (auto commit = TryCommit(); commit) {
-        return commit;
-    }
-
-    // Commit has failed, allocate more memory.
-    if (!AllocMemory(wanted_properties, reqs.memoryTypeBits, ALLOC_CHUNK_SIZE)) {
-        // TODO(Rodrigo): Try to use host memory.
-        LOG_CRITICAL(Render_Vulkan, "Ran out of memory!");
-        UNREACHABLE();
-    }
-
-    // Commit again, this time it won't fail since there's a fresh allocation above. If it does,
-    // there's a bug.
-    auto commit = TryCommit();
-    ASSERT(commit);
-    return commit;
-}
-
-VKMemoryCommit VKMemoryManager::Commit(vk::Buffer buffer, bool host_visible) {
-    const auto dev = device.GetLogical();
-    const auto& dld = device.GetDispatchLoader();
-    const auto requeriments = dev.getBufferMemoryRequirements(buffer, dld);
-    auto commit = Commit(requeriments, host_visible);
-    dev.bindBufferMemory(buffer, commit->GetMemory(), commit->GetOffset(), dld);
-    return commit;
-}
-
-VKMemoryCommit VKMemoryManager::Commit(vk::Image image, bool host_visible) {
-    const auto dev = device.GetLogical();
-    const auto& dld = device.GetDispatchLoader();
-    const auto requeriments = dev.getImageMemoryRequirements(image, dld);
-    auto commit = Commit(requeriments, host_visible);
-    dev.bindImageMemory(image, commit->GetMemory(), commit->GetOffset(), dld);
-    return commit;
-}
-
-bool VKMemoryManager::AllocMemory(vk::MemoryPropertyFlags wanted_properties, u32 type_mask,
-                                  u64 size) {
-    const u32 type = [&]() {
-        for (u32 type_index = 0; type_index < props.memoryTypeCount; ++type_index) {
-            const auto flags = props.memoryTypes[type_index].propertyFlags;
-            if ((type_mask & (1U << type_index)) && (flags & wanted_properties)) {
-                // The type matches in type and in the wanted properties.
-                return type_index;
-            }
-        }
-        LOG_CRITICAL(Render_Vulkan, "Couldn't find a compatible memory type!");
-        UNREACHABLE();
-        return 0u;
-    }();
-
-    const auto dev = device.GetLogical();
-    const auto& dld = device.GetDispatchLoader();
-
-    // Try to allocate found type.
-    const vk::MemoryAllocateInfo memory_ai(size, type);
-    vk::DeviceMemory memory;
-    if (const vk::Result res = dev.allocateMemory(&memory_ai, nullptr, &memory, dld);
-        res != vk::Result::eSuccess) {
-        LOG_CRITICAL(Render_Vulkan, "Device allocation failed with code {}!", vk::to_string(res));
-        return false;
-    }
-    allocs.push_back(
-        std::make_unique<VKMemoryAllocation>(device, memory, wanted_properties, size, type));
-    return true;
-}
-
-/*static*/ bool VKMemoryManager::GetMemoryUnified(const vk::PhysicalDeviceMemoryProperties& props) {
-    for (u32 heap_index = 0; heap_index < props.memoryHeapCount; ++heap_index) {
-        if (!(props.memoryHeaps[heap_index].flags & vk::MemoryHeapFlagBits::eDeviceLocal)) {
-            // Memory is considered unified when heaps are device local only.
-            return false;
-        }
-    }
-    return true;
-}
-
-VKMemoryCommitImpl::VKMemoryCommitImpl(VKMemoryAllocation* allocation, vk::DeviceMemory memory,
-                                       u8* data, u64 begin, u64 end)
-    : allocation{allocation}, memory{memory}, data{data}, interval(std::make_pair(begin, end)) {}
-
-VKMemoryCommitImpl::~VKMemoryCommitImpl() {
-    allocation->Free(this);
-}
-
-u8* VKMemoryCommitImpl::GetData() const {
-    ASSERT_MSG(data != nullptr, "Trying to access an unmapped commit.");
-    return data;
-}
-
-} // namespace Vulkan

src/video_core/renderer_vulkan/vk_memory_manager.h

@@ -1,87 +0,0 @@
-// Copyright 2019 yuzu Emulator Project
-// Licensed under GPLv2 or any later version
-// Refer to the license.txt file included.
-
-#pragma once
-
-#include <memory>
-#include <utility>
-#include <vector>
-#include "common/common_types.h"
-#include "video_core/renderer_vulkan/declarations.h"
-
-namespace Vulkan {
-
-class VKDevice;
-class VKMemoryAllocation;
-class VKMemoryCommitImpl;
-
-using VKMemoryCommit = std::unique_ptr<VKMemoryCommitImpl>;
-
-class VKMemoryManager final {
-public:
-    explicit VKMemoryManager(const VKDevice& device);
-    ~VKMemoryManager();
-
-    /**
-     * Commits a memory with the specified requeriments.
-     * @param reqs Requeriments returned from a Vulkan call.
-     * @param host_visible Signals the allocator that it *must* use host visible and coherent
-     * memory. When passing false, it will try to allocate device local memory.
-     * @returns A memory commit.
-     */
-    VKMemoryCommit Commit(const vk::MemoryRequirements& reqs, bool host_visible);
-
-    /// Commits memory required by the buffer and binds it.
-    VKMemoryCommit Commit(vk::Buffer buffer, bool host_visible);
-
-    /// Commits memory required by the image and binds it.
-    VKMemoryCommit Commit(vk::Image image, bool host_visible);
-
-    /// Returns true if the memory allocations are done always in host visible and coherent memory.
-    bool IsMemoryUnified() const {
-        return is_memory_unified;
-    }
-
-private:
-    /// Allocates a chunk of memory.
-    bool AllocMemory(vk::MemoryPropertyFlags wanted_properties, u32 type_mask, u64 size);
-
-    /// Returns true if the device uses an unified memory model.
-    static bool GetMemoryUnified(const vk::PhysicalDeviceMemoryProperties& props);
-
-    const VKDevice& device;                                  ///< Device handler.
-    const vk::PhysicalDeviceMemoryProperties props;          ///< Physical device properties.
-    const bool is_memory_unified;                            ///< True if memory model is unified.
-    std::vector<std::unique_ptr<VKMemoryAllocation>> allocs; ///< Current allocations.
-};
-
-class VKMemoryCommitImpl final {
-    friend VKMemoryAllocation;
-
-public:
-    explicit VKMemoryCommitImpl(VKMemoryAllocation* allocation, vk::DeviceMemory memory, u8* data,
-                                u64 begin, u64 end);
-    ~VKMemoryCommitImpl();
-
-    /// Returns the writeable memory map. The commit has to be mappable.
-    u8* GetData() const;
-
-    /// Returns the Vulkan memory handler.
-    vk::DeviceMemory GetMemory() const {
-        return memory;
-    }
-
-    /// Returns the start position of the commit relative to the allocation.
-    vk::DeviceSize GetOffset() const {
-        return static_cast<vk::DeviceSize>(interval.first);
-    }
-
-private:
-    std::pair<u64, u64> interval{};   ///< Interval where the commit exists.
-    vk::DeviceMemory memory;          ///< Vulkan device memory handler.
-    VKMemoryAllocation* allocation{}; ///< Pointer to the large memory allocation.
-    u8* data{}; ///< Pointer to the host mapped memory, it has the commit offset included.
-};
-
-} // namespace Vulkan

src/video_core/renderer_vulkan/vk_resource_manager.cpp

@@ -1,285 +0,0 @@
-// Copyright 2018 yuzu Emulator Project
-// Licensed under GPLv2 or any later version
-// Refer to the license.txt file included.
-
-#include <algorithm>
-#include <optional>
-#include "common/assert.h"
-#include "common/logging/log.h"
-#include "video_core/renderer_vulkan/declarations.h"
-#include "video_core/renderer_vulkan/vk_device.h"
-#include "video_core/renderer_vulkan/vk_resource_manager.h"
-
-namespace Vulkan {
-
-// TODO(Rodrigo): Fine tune these numbers.
-constexpr std::size_t COMMAND_BUFFER_POOL_SIZE = 0x1000;
-constexpr std::size_t FENCES_GROW_STEP = 0x40;
-
-class CommandBufferPool final : public VKFencedPool {
-public:
-    CommandBufferPool(const VKDevice& device)
-        : VKFencedPool(COMMAND_BUFFER_POOL_SIZE), device{device} {}
-
-    void Allocate(std::size_t begin, std::size_t end) {
-        const auto dev = device.GetLogical();
-        const auto& dld = device.GetDispatchLoader();
-        const u32 graphics_family = device.GetGraphicsFamily();
-
-        auto pool = std::make_unique<Pool>();
-
-        // Command buffers are going to be commited, recorded, executed every single usage cycle.
-        // They are also going to be reseted when commited.
-        const auto pool_flags = vk::CommandPoolCreateFlagBits::eTransient |
-                                vk::CommandPoolCreateFlagBits::eResetCommandBuffer;
-        const vk::CommandPoolCreateInfo cmdbuf_pool_ci(pool_flags, graphics_family);
-        pool->handle = dev.createCommandPoolUnique(cmdbuf_pool_ci, nullptr, dld);
-
-        const vk::CommandBufferAllocateInfo cmdbuf_ai(*pool->handle,
-                                                      vk::CommandBufferLevel::ePrimary,
-                                                      static_cast<u32>(COMMAND_BUFFER_POOL_SIZE));
-        pool->cmdbufs =
-            dev.allocateCommandBuffersUnique<std::allocator<UniqueCommandBuffer>>(cmdbuf_ai, dld);
-
-        pools.push_back(std::move(pool));
-    }
-
-    vk::CommandBuffer Commit(VKFence& fence) {
-        const std::size_t index = CommitResource(fence);
-        const auto pool_index = index / COMMAND_BUFFER_POOL_SIZE;
-        const auto sub_index = index % COMMAND_BUFFER_POOL_SIZE;
-        return *pools[pool_index]->cmdbufs[sub_index];
-    }
-
-private:
-    struct Pool {
-        UniqueCommandPool handle;
-        std::vector<UniqueCommandBuffer> cmdbufs;
-    };
-
-    const VKDevice& device;
-
-    std::vector<std::unique_ptr<Pool>> pools;
-};
-
-VKResource::VKResource() = default;
-
-VKResource::~VKResource() = default;
-
-VKFence::VKFence(const VKDevice& device, UniqueFence handle)
-    : device{device}, handle{std::move(handle)} {}
-
-VKFence::~VKFence() = default;
-
-void VKFence::Wait() {
-    const auto dev = device.GetLogical();
-    const auto& dld = device.GetDispatchLoader();
-    dev.waitForFences({*handle}, true, std::numeric_limits<u64>::max(), dld);
-}
-
-void VKFence::Release() {
-    is_owned = false;
-}
-
-void VKFence::Commit() {
-    is_owned = true;
-    is_used = true;
-}
-
-bool VKFence::Tick(bool gpu_wait, bool owner_wait) {
-    if (!is_used) {
-        // If a fence is not used it's always free.
-        return true;
-    }
-    if (is_owned && !owner_wait) {
-        // The fence is still being owned (Release has not been called) and ownership wait has
-        // not been asked.
-        return false;
-    }
-
-    const auto dev = device.GetLogical();
-    const auto& dld = device.GetDispatchLoader();
-    if (gpu_wait) {
-        // Wait for the fence if it has been requested.
-        dev.waitForFences({*handle}, true, std::numeric_limits<u64>::max(), dld);
-    } else {
-        if (dev.getFenceStatus(*handle, dld) != vk::Result::eSuccess) {
-            // Vulkan fence is not ready, not much it can do here
-            return false;
-        }
-    }
-
-    // Broadcast resources their free state.
-    for (auto* resource : protected_resources) {
-        resource->OnFenceRemoval(this);
-    }
-    protected_resources.clear();
-
-    // Prepare fence for reusage.
-    dev.resetFences({*handle}, dld);
-    is_used = false;
-    return true;
-}
-
-void VKFence::Protect(VKResource* resource) {
-    protected_resources.push_back(resource);
-}
-
-void VKFence::Unprotect(const VKResource* resource) {
-    const auto it = std::find(protected_resources.begin(), protected_resources.end(), resource);
-    if (it != protected_resources.end()) {
-        protected_resources.erase(it);
-    }
-}
-
-VKFenceWatch::VKFenceWatch() = default;
-
-VKFenceWatch::~VKFenceWatch() {
-    if (fence) {
-        fence->Unprotect(this);
-    }
-}
-
-void VKFenceWatch::Wait() {
-    if (!fence) {
-        return;
-    }
-    fence->Wait();
-    fence->Unprotect(this);
-    fence = nullptr;
-}
-
-void VKFenceWatch::Watch(VKFence& new_fence) {
-    Wait();
-    fence = &new_fence;
-    fence->Protect(this);
-}
-
-bool VKFenceWatch::TryWatch(VKFence& new_fence) {
-    if (fence) {
-        return false;
-    }
-    fence = &new_fence;
-    fence->Protect(this);
-    return true;
-}
-
-void VKFenceWatch::OnFenceRemoval(VKFence* signaling_fence) {
-    ASSERT_MSG(signaling_fence == fence, "Removing the wrong fence");
-    fence = nullptr;
-}
-
-VKFencedPool::VKFencedPool(std::size_t grow_step) : grow_step{grow_step} {}
-
-VKFencedPool::~VKFencedPool() = default;
-
-std::size_t VKFencedPool::CommitResource(VKFence& fence) {
-    const auto Search = [&](std::size_t begin, std::size_t end) -> std::optional<std::size_t> {
-        for (std::size_t iterator = begin; iterator < end; ++iterator) {
-            if (watches[iterator]->TryWatch(fence)) {
-                // The resource is now being watched, a free resource was successfully found.
-                return iterator;
-            }
-        }
-        return {};
-    };
-    // Try to find a free resource from the hinted position to the end.
-    auto found = Search(free_iterator, watches.size());
-    if (!found) {
-        // Search from beginning to the hinted position.
-        found = Search(0, free_iterator);
-        if (!found) {
-            // Both searches failed, the pool is full; handle it.
-            const std::size_t free_resource = ManageOverflow();
-
-            // Watch will wait for the resource to be free.
-            watches[free_resource]->Watch(fence);
-            found = free_resource;
-        }
-    }
-    // Free iterator is hinted to the resource after the one that's been commited.
-    free_iterator = (*found + 1) % watches.size();
-    return *found;
-}
-
-std::size_t VKFencedPool::ManageOverflow() {
-    const std::size_t old_capacity = watches.size();
-    Grow();
-
-    // The last entry is guaranted to be free, since it's the first element of the freshly
-    // allocated resources.
-    return old_capacity;
-}
-
-void VKFencedPool::Grow() {
-    const std::size_t old_capacity = watches.size();
-    watches.resize(old_capacity + grow_step);
-    std::generate(watches.begin() + old_capacity, watches.end(),
-                  []() { return std::make_unique<VKFenceWatch>(); });
-    Allocate(old_capacity, old_capacity + grow_step);
-}
-
-VKResourceManager::VKResourceManager(const VKDevice& device) : device{device} {
-    GrowFences(FENCES_GROW_STEP);
-    command_buffer_pool = std::make_unique<CommandBufferPool>(device);
-}
-
-VKResourceManager::~VKResourceManager() = default;
-
-VKFence& VKResourceManager::CommitFence() {
-    const auto StepFences = [&](bool gpu_wait, bool owner_wait) -> VKFence* {
-        const auto Tick = [=](auto& fence) { return fence->Tick(gpu_wait, owner_wait); };
-        const auto hinted = fences.begin() + fences_iterator;
-
-        auto it = std::find_if(hinted, fences.end(), Tick);
-        if (it == fences.end()) {
-            it = std::find_if(fences.begin(), hinted, Tick);
-            if (it == hinted) {
-                return nullptr;
-            }
-        }
-        fences_iterator = std::distance(fences.begin(), it) + 1;
-        if (fences_iterator >= fences.size())
-            fences_iterator = 0;
-
-        auto& fence = *it;
-        fence->Commit();
-        return fence.get();
-    };
-
-    VKFence* found_fence = StepFences(false, false);
-    if (!found_fence) {
-        // Try again, this time waiting.
-        found_fence = StepFences(true, false);
-
-        if (!found_fence) {
-            // Allocate new fences and try again.
-            LOG_INFO(Render_Vulkan, "Allocating new fences {} -> {}", fences.size(),
-                     fences.size() + FENCES_GROW_STEP);
-
-            GrowFences(FENCES_GROW_STEP);
-            found_fence = StepFences(true, false);
-            ASSERT(found_fence != nullptr);
-        }
-    }
-    return *found_fence;
-}
-
-vk::CommandBuffer VKResourceManager::CommitCommandBuffer(VKFence& fence) {
-    return command_buffer_pool->Commit(fence);
-}
-
-void VKResourceManager::GrowFences(std::size_t new_fences_count) {
-    const auto dev = device.GetLogical();
-    const auto& dld = device.GetDispatchLoader();
-    const vk::FenceCreateInfo fence_ci;
-
-    const std::size_t previous_size = fences.size();
-    fences.resize(previous_size + new_fences_count);
-
-    std::generate(fences.begin() + previous_size, fences.end(), [&]() {
-        return std::make_unique<VKFence>(device, dev.createFenceUnique(fence_ci, nullptr, dld));
-    });
-}
-
-} // namespace Vulkan

src/video_core/renderer_vulkan/vk_resource_manager.h

@@ -1,180 +0,0 @@
-// Copyright 2018 yuzu Emulator Project
-// Licensed under GPLv2 or any later version
-// Refer to the license.txt file included.
-
-#pragma once
-
-#include <cstddef>
-#include <memory>
-#include <vector>
-#include "video_core/renderer_vulkan/declarations.h"
-
-namespace Vulkan {
-
-class VKDevice;
-class VKFence;
-class VKResourceManager;
-
-class CommandBufferPool;
-
-/// Interface for a Vulkan resource
-class VKResource {
-public:
-    explicit VKResource();
-    virtual ~VKResource();
-
-    /**
-     * Signals the object that an owning fence has been signaled.
-     * @param signaling_fence Fence that signals its usage end.
-     */
-    virtual void OnFenceRemoval(VKFence* signaling_fence) = 0;
-};
-
-/**
- * Fences take ownership of objects, protecting them from GPU-side or driver-side concurrent access.
- * They must be commited from the resource manager. Their usage flow is: commit the fence from the
- * resource manager, protect resources with it and use them, send the fence to an execution queue
- * and Wait for it if needed and then call Release. Used resources will automatically be signaled
- * when they are free to be reused.
- * @brief Protects resources for concurrent usage and signals its release.
- */
-class VKFence {
-    friend class VKResourceManager;
-
-public:
-    explicit VKFence(const VKDevice& device, UniqueFence handle);
-    ~VKFence();
-
-    /**
-     * Waits for the fence to be signaled.
-     * @warning You must have ownership of the fence and it has to be previously sent to a queue to
-     * call this function.
-     */
-    void Wait();
-
-    /**
-     * Releases ownership of the fence. Pass after it has been sent to an execution queue.
-     * Unmanaged usage of the fence after the call will result in undefined behavior because it may
-     * be being used for something else.
-     */
-    void Release();
-
-    /// Protects a resource with this fence.
-    void Protect(VKResource* resource);
-
-    /// Removes protection for a resource.
-    void Unprotect(const VKResource* resource);
-
-    /// Retreives the fence.
-    operator vk::Fence() const {
-        return *handle;
-    }
-
-private:
-    /// Take ownership of the fence.
-    void Commit();
-
-    /**
-     * Updates the fence status.
-     * @warning Waiting for the owner might soft lock the execution.
-     * @param gpu_wait Wait for the fence to be signaled by the driver.
-     * @param owner_wait Wait for the owner to signal its freedom.
-     * @returns True if the fence is free. Waiting for gpu and owner will always return true.
-     */
-    bool Tick(bool gpu_wait, bool owner_wait);
-
-    const VKDevice& device;                       ///< Device handler
-    UniqueFence handle;                           ///< Vulkan fence
-    std::vector<VKResource*> protected_resources; ///< List of resources protected by this fence
-    bool is_owned = false; ///< The fence has been commited but not released yet.
-    bool is_used = false;  ///< The fence has been commited but it has not been checked to be free.
-};
-
-/**
- * A fence watch is used to keep track of the usage of a fence and protect a resource or set of
- * resources without having to inherit VKResource from their handlers.
- */
-class VKFenceWatch final : public VKResource {
-public:
-    explicit VKFenceWatch();
-    ~VKFenceWatch();
-
-    /// Waits for the fence to be released.
-    void Wait();
-
-    /**
-     * Waits for a previous fence and watches a new one.
-     * @param new_fence New fence to wait to.
-     */
-    void Watch(VKFence& new_fence);
-
-    /**
-     * Checks if it's currently being watched and starts watching it if it's available.
-     * @returns True if a watch has started, false if it's being watched.
-     */
-    bool TryWatch(VKFence& new_fence);
-
-    void OnFenceRemoval(VKFence* signaling_fence) override;
-
-private:
-    VKFence* fence{}; ///< Fence watching this resource. nullptr when the watch is free.
-};
-
-/**
- * Handles a pool of resources protected by fences. Manages resource overflow allocating more
- * resources.
- */
-class VKFencedPool {
-public:
-    explicit VKFencedPool(std::size_t grow_step);
-    virtual ~VKFencedPool();
-
-protected:
-    /**
-     * Commits a free resource and protects it with a fence. It may allocate new resources.
-     * @param fence Fence that protects the commited resource.
-     * @returns Index of the resource commited.
-     */
-    std::size_t CommitResource(VKFence& fence);
-
-    /// Called when a chunk of resources have to be allocated.
-    virtual void Allocate(std::size_t begin, std::size_t end) = 0;
-
-private:
-    /// Manages pool overflow allocating new resources.
-    std::size_t ManageOverflow();
-
-    /// Allocates a new page of resources.
-    void Grow();
-
-    std::size_t grow_step = 0;     ///< Number of new resources created after an overflow
-    std::size_t free_iterator = 0; ///< Hint to where the next free resources is likely to be found
-    std::vector<std::unique_ptr<VKFenceWatch>> watches; ///< Set of watched resources
-};
-
-/**
- * The resource manager handles all resources that can be protected with a fence avoiding
- * driver-side or GPU-side concurrent usage. Usage is documented in VKFence.
- */
-class VKResourceManager final {
-public:
-    explicit VKResourceManager(const VKDevice& device);
-    ~VKResourceManager();
-
-    /// Commits a fence. It has to be sent to a queue and released.
-    VKFence& CommitFence();
-
-    /// Commits an unused command buffer and protects it with a fence.
-    vk::CommandBuffer CommitCommandBuffer(VKFence& fence);
-
-private:
-    /// Allocates new fences.
-    void GrowFences(std::size_t new_fences_count);
-
-    const VKDevice& device;          ///< Device handler.
-    std::size_t fences_iterator = 0; ///< Index where a free fence is likely to be found.
-    std::vector<std::unique_ptr<VKFence>> fences;           ///< Pool of fences.
-    std::unique_ptr<CommandBufferPool> command_buffer_pool; ///< Pool of command buffers.
-};
-
-} // namespace Vulkan

src/video_core/renderer_vulkan/vk_scheduler.cpp

@@ -1,60 +0,0 @@
-// Copyright 2019 yuzu Emulator Project
-// Licensed under GPLv2 or any later version
-// Refer to the license.txt file included.
-
-#include "common/assert.h"
-#include "common/logging/log.h"
-#include "video_core/renderer_vulkan/declarations.h"
-#include "video_core/renderer_vulkan/vk_device.h"
-#include "video_core/renderer_vulkan/vk_resource_manager.h"
-#include "video_core/renderer_vulkan/vk_scheduler.h"
-
-namespace Vulkan {
-
-VKScheduler::VKScheduler(const VKDevice& device, VKResourceManager& resource_manager)
-    : device{device}, resource_manager{resource_manager} {
-    next_fence = &resource_manager.CommitFence();
-    AllocateNewContext();
-}
-
-VKScheduler::~VKScheduler() = default;
-
-VKExecutionContext VKScheduler::GetExecutionContext() const {
-    return VKExecutionContext(current_fence, current_cmdbuf);
-}
-
-VKExecutionContext VKScheduler::Flush(vk::Semaphore semaphore) {
-    SubmitExecution(semaphore);
-    current_fence->Release();
-    AllocateNewContext();
-    return GetExecutionContext();
-}
-
-VKExecutionContext VKScheduler::Finish(vk::Semaphore semaphore) {
-    SubmitExecution(semaphore);
-    current_fence->Wait();
-    current_fence->Release();
-    AllocateNewContext();
-    return GetExecutionContext();
-}
-
-void VKScheduler::SubmitExecution(vk::Semaphore semaphore) {
-    const auto& dld = device.GetDispatchLoader();
-    current_cmdbuf.end(dld);
-
-    const auto queue = device.GetGraphicsQueue();
-    const vk::SubmitInfo submit_info(0, nullptr, nullptr, 1, &current_cmdbuf, semaphore ? 1u : 0u,
-                                     &semaphore);
-    queue.submit({submit_info}, *current_fence, dld);
-}
-
-void VKScheduler::AllocateNewContext() {
-    current_fence = next_fence;
-    current_cmdbuf = resource_manager.CommitCommandBuffer(*current_fence);
-    next_fence = &resource_manager.CommitFence();
-
-    const auto& dld = device.GetDispatchLoader();
-    current_cmdbuf.begin({vk::CommandBufferUsageFlagBits::eOneTimeSubmit}, dld);
-}
-
-} // namespace Vulkan

src/video_core/renderer_vulkan/vk_scheduler.h

@@ -1,69 +0,0 @@
-// Copyright 2019 yuzu Emulator Project
-// Licensed under GPLv2 or any later version
-// Refer to the license.txt file included.
-
-#pragma once
-
-#include "common/common_types.h"
-#include "video_core/renderer_vulkan/declarations.h"
-
-namespace Vulkan {
-
-class VKDevice;
-class VKExecutionContext;
-class VKFence;
-class VKResourceManager;
-
-/// The scheduler abstracts command buffer and fence management with an interface that's able to do
-/// OpenGL-like operations on Vulkan command buffers.
-class VKScheduler {
-public:
-    explicit VKScheduler(const VKDevice& device, VKResourceManager& resource_manager);
-    ~VKScheduler();
-
-    /// Gets the current execution context.
-    [[nodiscard]] VKExecutionContext GetExecutionContext() const;
-
-    /// Sends the current execution context to the GPU. It invalidates the current execution context
-    /// and returns a new one.
-    VKExecutionContext Flush(vk::Semaphore semaphore = nullptr);
-
-    /// Sends the current execution context to the GPU and waits for it to complete. It invalidates
-    /// the current execution context and returns a new one.
-    VKExecutionContext Finish(vk::Semaphore semaphore = nullptr);
-
-private:
-    void SubmitExecution(vk::Semaphore semaphore);
-
-    void AllocateNewContext();
-
-    const VKDevice& device;
-    VKResourceManager& resource_manager;
-    vk::CommandBuffer current_cmdbuf;
-    VKFence* current_fence = nullptr;
-    VKFence* next_fence = nullptr;
-};
-
-class VKExecutionContext {
-    friend class VKScheduler;
-
-public:
-    VKExecutionContext() = default;
-
-    VKFence& GetFence() const {
-        return *fence;
-    }
-
-    vk::CommandBuffer GetCommandBuffer() const {
-        return cmdbuf;
-    }
-
-private:
-    explicit VKExecutionContext(VKFence* fence, vk::CommandBuffer cmdbuf)
-        : fence{fence}, cmdbuf{cmdbuf} {}
-
-    VKFence* fence{};
-    vk::CommandBuffer cmdbuf;
-};
-
-} // namespace Vulkan