Create python-publish.yml

Replace GLSL as the default OpenGL shader backend

.github/workflows/python-publish.yml

@@ -0,0 +1,39 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python#publishing-to-package-registries
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build
+    - name: Build package
+      run: python -m build
+    - name: Publish package
+      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN }}

externals/CMakeLists.txt

@@ -67,9 +67,6 @@ if (YUZU_USE_EXTERNAL_SDL2)
     endif()
     set(SDL_STATIC ON)
     set(SDL_SHARED OFF)
-    if (APPLE)
-        set(SDL_FILE ON)
-    endif()
 
     add_subdirectory(SDL EXCLUDE_FROM_ALL)
     add_library(SDL2 ALIAS SDL2-static)
@@ -95,10 +92,14 @@ endif()
 add_subdirectory(sirit)
 
 if (ENABLE_WEB_SERVICE)
-    find_package(OpenSSL 1.1)
-    if (OPENSSL_FOUND)
-        set(OPENSSL_LIBRARIES OpenSSL::SSL OpenSSL::Crypto)
-    else()
+    if (NOT WIN32)
+        find_package(OpenSSL 1.1)
+        if (OPENSSL_FOUND)
+            set(OPENSSL_LIBRARIES OpenSSL::SSL OpenSSL::Crypto)
+        endif()
+    endif()
+
+    if (WIN32 OR NOT OPENSSL_FOUND)
         # LibreSSL
         set(LIBRESSL_SKIP_INSTALL ON CACHE BOOL "")
         set(OPENSSLDIR "/etc/ssl/")

src/CMakeLists.txt

@@ -112,8 +112,6 @@ else()
 
         $<$<CXX_COMPILER_ID:Clang>:-Wno-braced-scalar-init>
         $<$<CXX_COMPILER_ID:Clang>:-Wno-unused-private-field>
-        $<$<CXX_COMPILER_ID:AppleClang>:-Wno-braced-scalar-init>
-        $<$<CXX_COMPILER_ID:AppleClang>:-Wno-unused-private-field>
     )
 
     if (ARCHITECTURE_x86_64)

src/audio_core/audio_event.cpp

@@ -3,7 +3,6 @@
 
 #include "audio_core/audio_event.h"
 #include "common/assert.h"
-#include "common/polyfill_ranges.h"
 
 namespace AudioCore {
 

src/audio_core/audio_manager.h

@@ -9,8 +9,6 @@
 #include <mutex>
 #include <thread>
 
-#include "common/polyfill_thread.h"
-
 #include "audio_core/audio_event.h"
 
 union Result;

src/audio_core/audio_render_manager.h

@@ -7,8 +7,6 @@
 #include <memory>
 #include <mutex>
 
-#include "common/polyfill_thread.h"
-
 #include "audio_core/common/common.h"
 #include "audio_core/renderer/system_manager.h"
 #include "core/hle/service/audio/errors.h"

src/audio_core/common/feature_support.h

@@ -10,7 +10,6 @@
 #include "common/assert.h"
 #include "common/common_funcs.h"
 #include "common/common_types.h"
-#include "common/polyfill_ranges.h"
 
 namespace AudioCore {
 constexpr u32 CurrentRevision = 11;

src/audio_core/renderer/command/command_buffer.cpp

@@ -460,21 +460,23 @@ void CommandBuffer::GenerateDeviceSinkCommand(const s32 node_id, const s16 buffe
 
     cmd.session_id = session_id;
 
+    cmd.input_count = parameter.input_count;
+    s16 max_input{0};
+    for (u32 i = 0; i < parameter.input_count; i++) {
+        cmd.inputs[i] = buffer_offset + parameter.inputs[i];
+        max_input = std::max(max_input, cmd.inputs[i]);
+    }
+
     if (state.upsampler_info != nullptr) {
         const auto size_{state.upsampler_info->sample_count * parameter.input_count};
         const auto size_bytes{size_ * sizeof(s32)};
         const auto addr{memory_pool->Translate(state.upsampler_info->samples_pos, size_bytes)};
         cmd.sample_buffer = {reinterpret_cast<s32*>(addr),
-                             parameter.input_count * state.upsampler_info->sample_count};
+                             (max_input + 1) * state.upsampler_info->sample_count};
     } else {
         cmd.sample_buffer = samples_buffer;
     }
 
-    cmd.input_count = parameter.input_count;
-    for (u32 i = 0; i < parameter.input_count; i++) {
-        cmd.inputs[i] = buffer_offset + parameter.inputs[i];
-    }
-
     GenerateEnd<DeviceSinkCommand>(cmd);
 }
 

src/audio_core/renderer/command/effect/i3dl2_reverb.cpp

@@ -5,7 +5,6 @@
 
 #include "audio_core/renderer/adsp/command_list_processor.h"
 #include "audio_core/renderer/command/effect/i3dl2_reverb.h"
-#include "common/polyfill_ranges.h"
 
 namespace AudioCore::AudioRenderer {
 

src/audio_core/renderer/command/effect/reverb.cpp

@@ -6,7 +6,6 @@
 
 #include "audio_core/renderer/adsp/command_list_processor.h"
 #include "audio_core/renderer/command/effect/reverb.h"
-#include "common/polyfill_ranges.h"
 
 namespace AudioCore::AudioRenderer {
 

src/audio_core/renderer/mix/mix_context.cpp

@@ -5,7 +5,6 @@
 
 #include "audio_core/renderer/mix/mix_context.h"
 #include "audio_core/renderer/splitter/splitter_context.h"
-#include "common/polyfill_ranges.h"
 
 namespace AudioCore::AudioRenderer {
 

src/audio_core/renderer/voice/voice_context.cpp

@@ -4,7 +4,6 @@
 #include <ranges>
 
 #include "audio_core/renderer/voice/voice_context.h"
-#include "common/polyfill_ranges.h"
 
 namespace AudioCore::AudioRenderer {
 

src/audio_core/sink/sink_stream.cpp

@@ -170,8 +170,8 @@ void SinkStream::ProcessAudioIn(std::span<const s16> input_buffer, std::size_t n
 
         // Get the minimum frames available between the currently playing buffer, and the
         // amount we have left to fill
-        size_t frames_available{std::min<u64>(playing_buffer.frames - playing_buffer.frames_played,
-                                              num_frames - frames_written)};
+        size_t frames_available{std::min(playing_buffer.frames - playing_buffer.frames_played,
+                                         num_frames - frames_written)};
 
         samples_buffer.Push(&input_buffer[frames_written * frame_size],
                             frames_available * frame_size);
@@ -241,8 +241,8 @@ void SinkStream::ProcessAudioOutAndRender(std::span<s16> output_buffer, std::siz
 
         // Get the minimum frames available between the currently playing buffer, and the
         // amount we have left to fill
-        size_t frames_available{std::min<u64>(playing_buffer.frames - playing_buffer.frames_played,
-                                              num_frames - frames_written)};
+        size_t frames_available{std::min(playing_buffer.frames - playing_buffer.frames_played,
+                                         num_frames - frames_written)};
 
         samples_buffer.Pop(&output_buffer[frames_written * frame_size],
                            frames_available * frame_size);

src/common/fs/file.cpp

@@ -1,8 +1,6 @@
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
-#include <vector>
-
 #include "common/fs/file.h"
 #include "common/fs/fs.h"
 #include "common/logging/log.h"

src/common/fs/fs_util.cpp

@@ -4,7 +4,6 @@
 #include <algorithm>
 
 #include "common/fs/fs_util.h"
-#include "common/polyfill_ranges.h"
 
 namespace Common::FS {
 

src/common/fs/path_util.cpp

@@ -2,7 +2,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 #include <algorithm>
-#include <sstream>
 #include <unordered_map>
 
 #include "common/fs/fs.h"

src/common/input.h

@@ -8,7 +8,6 @@
 #include <string>
 #include <unordered_map>
 #include <utility>
-#include <vector>
 #include "common/logging/log.h"
 #include "common/param_package.h"
 #include "common/uuid.h"

src/common/logging/backend.cpp

@@ -4,6 +4,7 @@
 #include <atomic>
 #include <chrono>
 #include <climits>
+#include <stop_token>
 #include <thread>
 
 #include <fmt/format.h>
@@ -17,7 +18,6 @@
 #include "common/fs/fs_paths.h"
 #include "common/fs/path_util.h"
 #include "common/literals.h"
-#include "common/polyfill_thread.h"
 #include "common/thread.h"
 
 #include "common/logging/backend.h"

src/common/polyfill_ranges.h

@@ -1,530 +0,0 @@
-// SPDX-FileCopyrightText: 2022 yuzu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-//
-// TODO: remove this file when ranges are supported by all compilation targets
-//
-
-#pragma once
-
-#include <algorithm>
-#include <utility>
-#include <version>
-
-#ifndef __cpp_lib_ranges
-
-namespace std {
-namespace ranges {
-
-template <typename T>
-concept range = requires(T& t) {
-    begin(t);
-    end(t);
-};
-
-template <typename T>
-concept input_range = range<T>;
-
-template <typename T>
-concept output_range = range<T>;
-
-template <range R>
-using range_difference_t = ptrdiff_t;
-
-//
-// find, find_if, find_if_not
-//
-
-struct find_fn {
-    template <typename Iterator, typename T, typename Proj = std::identity>
-    constexpr Iterator operator()(Iterator first, Iterator last, const T& value,
-                                  Proj proj = {}) const {
-        for (; first != last; ++first) {
-            if (std::invoke(proj, *first) == value) {
-                return first;
-            }
-        }
-        return first;
-    }
-
-    template <ranges::input_range R, typename T, typename Proj = std::identity>
-    constexpr ranges::iterator_t<R> operator()(R&& r, const T& value, Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), value, std::ref(proj));
-    }
-};
-
-struct find_if_fn {
-    template <typename Iterator, typename Proj = std::identity, typename Pred>
-    constexpr Iterator operator()(Iterator first, Iterator last, Pred pred, Proj proj = {}) const {
-        for (; first != last; ++first) {
-            if (std::invoke(pred, std::invoke(proj, *first))) {
-                return first;
-            }
-        }
-        return first;
-    }
-
-    template <ranges::input_range R, typename Proj = std::identity, typename Pred>
-    constexpr ranges::iterator_t<R> operator()(R&& r, Pred pred, Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), std::ref(pred), std::ref(proj));
-    }
-};
-
-struct find_if_not_fn {
-    template <typename Iterator, typename Proj = std::identity, typename Pred>
-    constexpr Iterator operator()(Iterator first, Iterator last, Pred pred, Proj proj = {}) const {
-        for (; first != last; ++first) {
-            if (!std::invoke(pred, std::invoke(proj, *first))) {
-                return first;
-            }
-        }
-        return first;
-    }
-
-    template <ranges::input_range R, typename Proj = std::identity, typename Pred>
-    constexpr ranges::iterator_t<R> operator()(R&& r, Pred pred, Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), std::ref(pred), std::ref(proj));
-    }
-};
-
-inline constexpr find_fn find;
-inline constexpr find_if_fn find_if;
-inline constexpr find_if_not_fn find_if_not;
-
-//
-// any_of, all_of, none_of
-//
-
-struct all_of_fn {
-    template <typename Iterator, typename Proj = std::identity, typename Pred>
-    constexpr bool operator()(Iterator first, Iterator last, Pred pred, Proj proj = {}) const {
-        return ranges::find_if_not(first, last, std::ref(pred), std::ref(proj)) == last;
-    }
-
-    template <ranges::input_range R, typename Proj = std::identity, typename Pred>
-    constexpr bool operator()(R&& r, Pred pred, Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), std::ref(pred), std::ref(proj));
-    }
-};
-
-struct any_of_fn {
-    template <typename Iterator, typename Proj = std::identity, typename Pred>
-    constexpr bool operator()(Iterator first, Iterator last, Pred pred, Proj proj = {}) const {
-        return ranges::find_if(first, last, std::ref(pred), std::ref(proj)) != last;
-    }
-
-    template <ranges::input_range R, typename Proj = std::identity, typename Pred>
-    constexpr bool operator()(R&& r, Pred pred, Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), std::ref(pred), std::ref(proj));
-    }
-};
-
-struct none_of_fn {
-    template <typename Iterator, typename Proj = std::identity, typename Pred>
-    constexpr bool operator()(Iterator first, Iterator last, Pred pred, Proj proj = {}) const {
-        return ranges::find_if(first, last, std::ref(pred), std::ref(proj)) == last;
-    }
-
-    template <ranges::input_range R, typename Proj = std::identity, typename Pred>
-    constexpr bool operator()(R&& r, Pred pred, Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), std::ref(pred), std::ref(proj));
-    }
-};
-
-inline constexpr any_of_fn any_of;
-inline constexpr all_of_fn all_of;
-inline constexpr none_of_fn none_of;
-
-//
-// count, count_if
-//
-
-struct count_fn {
-    template <typename Iterator, typename T, typename Proj = std::identity>
-    constexpr ptrdiff_t operator()(Iterator first, Iterator last, const T& value,
-                                   Proj proj = {}) const {
-        ptrdiff_t counter = 0;
-        for (; first != last; ++first)
-            if (std::invoke(proj, *first) == value)
-                ++counter;
-        return counter;
-    }
-
-    template <ranges::input_range R, typename T, typename Proj = std::identity>
-    constexpr ptrdiff_t operator()(R&& r, const T& value, Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), value, std::ref(proj));
-    }
-};
-
-struct count_if_fn {
-    template <typename Iterator, typename Proj = std::identity, typename Pred>
-    constexpr ptrdiff_t operator()(Iterator first, Iterator last, Pred pred, Proj proj = {}) const {
-        ptrdiff_t counter = 0;
-        for (; first != last; ++first)
-            if (std::invoke(pred, std::invoke(proj, *first)))
-                ++counter;
-        return counter;
-    }
-
-    template <ranges::input_range R, typename Proj = std::identity, typename Pred>
-    constexpr ptrdiff_t operator()(R&& r, Pred pred, Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), std::ref(pred), std::ref(proj));
-    }
-};
-
-inline constexpr count_fn count;
-inline constexpr count_if_fn count_if;
-
-//
-// transform
-//
-
-struct transform_fn {
-    template <typename InputIterator, typename OutputIterator, typename F,
-              typename Proj = std::identity>
-    constexpr void operator()(InputIterator first1, InputIterator last1, OutputIterator result,
-                              F op, Proj proj = {}) const {
-        for (; first1 != last1; ++first1, (void)++result) {
-            *result = std::invoke(op, std::invoke(proj, *first1));
-        }
-    }
-
-    template <ranges::input_range R, typename OutputIterator, typename F,
-              typename Proj = std::identity>
-    constexpr void operator()(R&& r, OutputIterator result, F op, Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), result, std::ref(op), std::ref(proj));
-    }
-};
-
-inline constexpr transform_fn transform;
-
-//
-// sort
-//
-
-struct sort_fn {
-    template <typename Iterator, typename Comp = ranges::less, typename Proj = std::identity>
-    constexpr void operator()(Iterator first, Iterator last, Comp comp = {}, Proj proj = {}) const {
-        if (first == last)
-            return;
-
-        Iterator last_iter = ranges::next(first, last);
-        std::sort(first, last_iter,
-                  [&](auto& lhs, auto& rhs) { return comp(proj(lhs), proj(rhs)); });
-    }
-
-    template <ranges::input_range R, typename Comp = ranges::less, typename Proj = std::identity>
-    constexpr void operator()(R&& r, Comp comp = {}, Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), std::move(comp), std::move(proj));
-    }
-};
-
-inline constexpr sort_fn sort;
-
-//
-// fill
-//
-
-struct fill_fn {
-    template <typename T, typename OutputIterator>
-    constexpr OutputIterator operator()(OutputIterator first, OutputIterator last,
-                                        const T& value) const {
-        while (first != last) {
-            *first++ = value;
-        }
-
-        return first;
-    }
-
-    template <typename T, ranges::output_range R>
-    constexpr ranges::iterator_t<R> operator()(R&& r, const T& value) const {
-        return operator()(ranges::begin(r), ranges::end(r), value);
-    }
-};
-
-inline constexpr fill_fn fill;
-
-//
-// for_each
-//
-
-struct for_each_fn {
-    template <typename Iterator, typename Proj = std::identity, typename Fun>
-    constexpr void operator()(Iterator first, Iterator last, Fun f, Proj proj = {}) const {
-        for (; first != last; ++first) {
-            std::invoke(f, std::invoke(proj, *first));
-        }
-    }
-
-    template <ranges::input_range R, typename Proj = std::identity, typename Fun>
-    constexpr void operator()(R&& r, Fun f, Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), std::move(f), std::ref(proj));
-    }
-};
-
-inline constexpr for_each_fn for_each;
-
-//
-// min_element, max_element
-//
-
-struct min_element_fn {
-    template <typename Iterator, typename Proj = std::identity, typename Comp = ranges::less>
-    constexpr Iterator operator()(Iterator first, Iterator last, Comp comp = {},
-                                  Proj proj = {}) const {
-        if (first == last) {
-            return last;
-        }
-
-        auto smallest = first;
-        ++first;
-        for (; first != last; ++first) {
-            if (!std::invoke(comp, std::invoke(proj, *smallest), std::invoke(proj, *first))) {
-                smallest = first;
-            }
-        }
-        return smallest;
-    }
-
-    template <ranges::input_range R, typename Proj = std::identity, typename Comp = ranges::less>
-    constexpr ranges::iterator_t<R> operator()(R&& r, Comp comp = {}, Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), std::ref(comp), std::ref(proj));
-    }
-};
-
-struct max_element_fn {
-    template <typename Iterator, typename Proj = std::identity, typename Comp = ranges::less>
-    constexpr Iterator operator()(Iterator first, Iterator last, Comp comp = {},
-                                  Proj proj = {}) const {
-        if (first == last) {
-            return last;
-        }
-
-        auto largest = first;
-        ++first;
-        for (; first != last; ++first) {
-            if (std::invoke(comp, std::invoke(proj, *largest), std::invoke(proj, *first))) {
-                largest = first;
-            }
-        }
-        return largest;
-    }
-
-    template <ranges::input_range R, typename Proj = std::identity, typename Comp = ranges::less>
-    constexpr ranges::iterator_t<R> operator()(R&& r, Comp comp = {}, Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), std::ref(comp), std::ref(proj));
-    }
-};
-
-inline constexpr min_element_fn min_element;
-inline constexpr max_element_fn max_element;
-
-//
-// replace, replace_if
-//
-
-struct replace_fn {
-    template <typename Iterator, typename T1, typename T2, typename Proj = std::identity>
-    constexpr Iterator operator()(Iterator first, Iterator last, const T1& old_value,
-                                  const T2& new_value, Proj proj = {}) const {
-        for (; first != last; ++first) {
-            if (old_value == std::invoke(proj, *first)) {
-                *first = new_value;
-            }
-        }
-        return first;
-    }
-
-    template <ranges::input_range R, typename T1, typename T2, typename Proj = std::identity>
-    constexpr ranges::iterator_t<R> operator()(R&& r, const T1& old_value, const T2& new_value,
-                                               Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), old_value, new_value, std::move(proj));
-    }
-};
-
-struct replace_if_fn {
-    template <typename Iterator, typename T, typename Proj = std::identity, typename Pred>
-    constexpr Iterator operator()(Iterator first, Iterator last, Pred pred, const T& new_value,
-                                  Proj proj = {}) const {
-        for (; first != last; ++first) {
-            if (!!std::invoke(pred, std::invoke(proj, *first))) {
-                *first = new_value;
-            }
-        }
-        return std::move(first);
-    }
-
-    template <ranges::input_range R, typename T, typename Proj = std::identity, typename Pred>
-    constexpr ranges::iterator_t<R> operator()(R&& r, Pred pred, const T& new_value,
-                                               Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), std::move(pred), new_value,
-                          std::move(proj));
-    }
-};
-
-inline constexpr replace_fn replace;
-inline constexpr replace_if_fn replace_if;
-
-//
-// copy, copy_if
-//
-
-struct copy_fn {
-    template <typename InputIterator, typename OutputIterator>
-    constexpr void operator()(InputIterator first, InputIterator last,
-                              OutputIterator result) const {
-        for (; first != last; ++first, (void)++result) {
-            *result = *first;
-        }
-    }
-
-    template <ranges::input_range R, typename OutputIterator>
-    constexpr void operator()(R&& r, OutputIterator result) const {
-        return operator()(ranges::begin(r), ranges::end(r), std::move(result));
-    }
-};
-
-struct copy_if_fn {
-    template <typename InputIterator, typename OutputIterator, typename Proj = std::identity,
-              typename Pred>
-    constexpr void operator()(InputIterator first, InputIterator last, OutputIterator result,
-                              Pred pred, Proj proj = {}) const {
-        for (; first != last; ++first) {
-            if (std::invoke(pred, std::invoke(proj, *first))) {
-                *result = *first;
-                ++result;
-            }
-        }
-    }
-
-    template <ranges::input_range R, typename OutputIterator, typename Proj = std::identity,
-              typename Pred>
-    constexpr void operator()(R&& r, OutputIterator result, Pred pred, Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), std::move(result), std::ref(pred),
-                          std::ref(proj));
-    }
-};
-
-inline constexpr copy_fn copy;
-inline constexpr copy_if_fn copy_if;
-
-//
-// generate
-//
-
-struct generate_fn {
-    template <typename Iterator, typename F>
-    constexpr Iterator operator()(Iterator first, Iterator last, F gen) const {
-        for (; first != last; *first = std::invoke(gen), ++first)
-            ;
-        return first;
-    }
-
-    template <typename R, std::copy_constructible F>
-    requires std::invocable<F&> && ranges::output_range<R>
-    constexpr ranges::iterator_t<R> operator()(R&& r, F gen) const {
-        return operator()(ranges::begin(r), ranges::end(r), std::move(gen));
-    }
-};
-
-inline constexpr generate_fn generate;
-
-//
-// lower_bound, upper_bound
-//
-
-struct lower_bound_fn {
-    template <typename Iterator, typename T, typename Proj = std::identity,
-              typename Comp = ranges::less>
-    constexpr Iterator operator()(Iterator first, Iterator last, const T& value, Comp comp = {},
-                                  Proj proj = {}) const {
-        Iterator it;
-        std::ptrdiff_t _count, _step;
-        _count = std::distance(first, last);
-
-        while (_count > 0) {
-            it = first;
-            _step = _count / 2;
-            ranges::advance(it, _step, last);
-            if (comp(std::invoke(proj, *it), value)) {
-                first = ++it;
-                _count -= _step + 1;
-            } else {
-                _count = _step;
-            }
-        }
-        return first;
-    }
-
-    template <ranges::input_range R, typename T, typename Proj = std::identity,
-              typename Comp = ranges::less>
-    constexpr ranges::iterator_t<R> operator()(R&& r, const T& value, Comp comp = {},
-                                               Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), value, std::ref(comp), std::ref(proj));
-    }
-};
-
-struct upper_bound_fn {
-    template <typename Iterator, typename T, typename Proj = std::identity,
-              typename Comp = ranges::less>
-    constexpr Iterator operator()(Iterator first, Iterator last, const T& value, Comp comp = {},
-                                  Proj proj = {}) const {
-        Iterator it;
-        std::ptrdiff_t _count, _step;
-        _count = std::distance(first, last);
-
-        while (_count > 0) {
-            it = first;
-            _step = _count / 2;
-            ranges::advance(it, _step, last);
-            if (!comp(value, std::invoke(proj, *it))) {
-                first = ++it;
-                _count -= _step + 1;
-            } else {
-                _count = _step;
-            }
-        }
-        return first;
-    }
-
-    template <ranges::input_range R, typename T, typename Proj = std::identity,
-              typename Comp = ranges::less>
-    constexpr ranges::iterator_t<R> operator()(R&& r, const T& value, Comp comp = {},
-                                               Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), value, std::ref(comp), std::ref(proj));
-    }
-};
-
-inline constexpr lower_bound_fn lower_bound;
-inline constexpr upper_bound_fn upper_bound;
-
-//
-// adjacent_find
-//
-
-struct adjacent_find_fn {
-    template <typename Iterator, typename Proj = std::identity, typename Pred = ranges::equal_to>
-    constexpr Iterator operator()(Iterator first, Iterator last, Pred pred = {},
-                                  Proj proj = {}) const {
-        if (first == last)
-            return first;
-        auto _next = ranges::next(first);
-        for (; _next != last; ++_next, ++first)
-            if (std::invoke(pred, std::invoke(proj, *first), std::invoke(proj, *_next)))
-                return first;
-        return _next;
-    }
-
-    template <ranges::input_range R, typename Proj = std::identity,
-              typename Pred = ranges::equal_to>
-    constexpr ranges::iterator_t<R> operator()(R&& r, Pred pred = {}, Proj proj = {}) const {
-        return operator()(ranges::begin(r), ranges::end(r), std::ref(pred), std::ref(proj));
-    }
-};
-
-inline constexpr adjacent_find_fn adjacent_find;
-
-} // namespace ranges
-} // namespace std
-
-#endif

src/common/polyfill_thread.h

@@ -1,323 +0,0 @@
-// SPDX-FileCopyrightText: 2022 yuzu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-//
-// TODO: remove this file when jthread is supported by all compilation targets
-//
-
-#pragma once
-
-#include <version>
-
-#ifdef __cpp_lib_jthread
-
-#include <stop_token>
-#include <thread>
-
-namespace Common {
-
-template <typename Condvar, typename Lock, typename Pred>
-void CondvarWait(Condvar& cv, Lock& lock, std::stop_token token, Pred&& pred) {
-    cv.wait(lock, token, std::move(pred));
-}
-
-} // namespace Common
-
-#else
-
-#include <atomic>
-#include <functional>
-#include <list>
-#include <memory>
-#include <mutex>
-#include <optional>
-#include <thread>
-#include <type_traits>
-
-namespace std {
-namespace polyfill {
-
-using stop_state_callbacks = list<function<void()>>;
-
-class stop_state {
-public:
-    stop_state() = default;
-    ~stop_state() = default;
-
-    bool request_stop() {
-        stop_state_callbacks callbacks;
-
-        {
-            scoped_lock lk{m_lock};
-
-            if (m_stop_requested.load()) {
-                // Already set, nothing to do
-                return false;
-            }
-
-            // Set as requested
-            m_stop_requested = true;
-
-            // Copy callback list
-            callbacks = m_callbacks;
-        }
-
-        for (auto callback : callbacks) {
-            callback();
-        }
-
-        return true;
-    }
-
-    bool stop_requested() const {
-        return m_stop_requested.load();
-    }
-
-    stop_state_callbacks::const_iterator insert_callback(function<void()> f) {
-        stop_state_callbacks::const_iterator ret{};
-        bool should_run{};
-
-        {
-            scoped_lock lk{m_lock};
-            should_run = m_stop_requested.load();
-            m_callbacks.push_front(f);
-            ret = m_callbacks.begin();
-        }
-
-        if (should_run) {
-            f();
-        }
-
-        return ret;
-    }
-
-    void remove_callback(stop_state_callbacks::const_iterator it) {
-        scoped_lock lk{m_lock};
-        m_callbacks.erase(it);
-    }
-
-private:
-    mutex m_lock;
-    atomic<bool> m_stop_requested;
-    stop_state_callbacks m_callbacks;
-};
-
-} // namespace polyfill
-
-class stop_token;
-class stop_source;
-struct nostopstate_t {
-    explicit nostopstate_t() = default;
-};
-inline constexpr nostopstate_t nostopstate{};
-
-template <class Callback>
-class stop_callback;
-
-class stop_token {
-public:
-    stop_token() noexcept = default;
-
-    stop_token(const stop_token&) noexcept = default;
-    stop_token(stop_token&&) noexcept = default;
-    stop_token& operator=(const stop_token&) noexcept = default;
-    stop_token& operator=(stop_token&&) noexcept = default;
-    ~stop_token() = default;
-
-    void swap(stop_token& other) noexcept {
-        m_stop_state.swap(other.m_stop_state);
-    }
-
-    [[nodiscard]] bool stop_requested() const noexcept {
-        return m_stop_state && m_stop_state->stop_requested();
-    }
-    [[nodiscard]] bool stop_possible() const noexcept {
-        return m_stop_state != nullptr;
-    }
-
-private:
-    friend class stop_source;
-    template <typename Callback>
-    friend class stop_callback;
-    stop_token(shared_ptr<polyfill::stop_state> stop_state) : m_stop_state(move(stop_state)) {}
-
-private:
-    shared_ptr<polyfill::stop_state> m_stop_state;
-};
-
-class stop_source {
-public:
-    stop_source() : m_stop_state(make_shared<polyfill::stop_state>()) {}
-    explicit stop_source(nostopstate_t) noexcept {}
-
-    stop_source(const stop_source&) noexcept = default;
-    stop_source(stop_source&&) noexcept = default;
-    stop_source& operator=(const stop_source&) noexcept = default;
-    stop_source& operator=(stop_source&&) noexcept = default;
-    ~stop_source() = default;
-    void swap(stop_source& other) noexcept {
-        m_stop_state.swap(other.m_stop_state);
-    }
-
-    [[nodiscard]] stop_token get_token() const noexcept {
-        return stop_token(m_stop_state);
-    }
-    [[nodiscard]] bool stop_possible() const noexcept {
-        return m_stop_state != nullptr;
-    }
-    [[nodiscard]] bool stop_requested() const noexcept {
-        return m_stop_state && m_stop_state->stop_requested();
-    }
-    bool request_stop() noexcept {
-        return m_stop_state && m_stop_state->request_stop();
-    }
-
-private:
-    friend class jthread;
-    explicit stop_source(shared_ptr<polyfill::stop_state> stop_state)
-        : m_stop_state(move(stop_state)) {}
-
-private:
-    shared_ptr<polyfill::stop_state> m_stop_state;
-};
-
-template <typename Callback>
-class stop_callback {
-    static_assert(is_nothrow_destructible_v<Callback>);
-    static_assert(is_invocable_v<Callback>);
-
-public:
-    using callback_type = Callback;
-
-    template <typename C>
-    requires constructible_from<Callback, C>
-    explicit stop_callback(const stop_token& st,
-                           C&& cb) noexcept(is_nothrow_constructible_v<Callback, C>)
-        : m_stop_state(st.m_stop_state) {
-        if (m_stop_state) {
-            m_callback = m_stop_state->insert_callback(move(cb));
-        }
-    }
-    template <typename C>
-    requires constructible_from<Callback, C>
-    explicit stop_callback(stop_token&& st,
-                           C&& cb) noexcept(is_nothrow_constructible_v<Callback, C>)
-        : m_stop_state(move(st.m_stop_state)) {
-        if (m_stop_state) {
-            m_callback = m_stop_state->insert_callback(move(cb));
-        }
-    }
-    ~stop_callback() {
-        if (m_stop_state && m_callback) {
-            m_stop_state->remove_callback(*m_callback);
-        }
-    }
-
-    stop_callback(const stop_callback&) = delete;
-    stop_callback(stop_callback&&) = delete;
-    stop_callback& operator=(const stop_callback&) = delete;
-    stop_callback& operator=(stop_callback&&) = delete;
-
-private:
-    shared_ptr<polyfill::stop_state> m_stop_state;
-    optional<polyfill::stop_state_callbacks::const_iterator> m_callback;
-};
-
-template <typename Callback>
-stop_callback(stop_token, Callback) -> stop_callback<Callback>;
-
-class jthread {
-public:
-    using id = thread::id;
-    using native_handle_type = thread::native_handle_type;
-
-    jthread() noexcept = default;
-
-    template <typename F, typename... Args,
-              typename = enable_if_t<!is_same_v<remove_cvref_t<F>, jthread>>>
-    explicit jthread(F&& f, Args&&... args)
-        : m_stop_state(make_shared<polyfill::stop_state>()),
-          m_thread(make_thread(move(f), move(args)...)) {}
-
-    ~jthread() {
-        if (joinable()) {
-            request_stop();
-            join();
-        }
-    }
-
-    jthread(const jthread&) = delete;
-    jthread(jthread&&) noexcept = default;
-    jthread& operator=(const jthread&) = delete;
-
-    jthread& operator=(jthread&& other) noexcept {
-        m_thread.swap(other.m_thread);
-        m_stop_state.swap(other.m_stop_state);
-        return *this;
-    }
-
-    void swap(jthread& other) noexcept {
-        m_thread.swap(other.m_thread);
-        m_stop_state.swap(other.m_stop_state);
-    }
-    [[nodiscard]] bool joinable() const noexcept {
-        return m_thread.joinable();
-    }
-    void join() {
-        m_thread.join();
-    }
-    void detach() {
-        m_thread.detach();
-        m_stop_state.reset();
-    }
-
-    [[nodiscard]] id get_id() const noexcept {
-        return m_thread.get_id();
-    }
-    [[nodiscard]] native_handle_type native_handle() {
-        return m_thread.native_handle();
-    }
-    [[nodiscard]] stop_source get_stop_source() noexcept {
-        return stop_source(m_stop_state);
-    }
-    [[nodiscard]] stop_token get_stop_token() const noexcept {
-        return stop_source(m_stop_state).get_token();
-    }
-    bool request_stop() noexcept {
-        return get_stop_source().request_stop();
-    }
-    [[nodiscard]] static unsigned int hardware_concurrency() noexcept {
-        return thread::hardware_concurrency();
-    }
-
-private:
-    template <typename F, typename... Args>
-    thread make_thread(F&& f, Args&&... args) {
-        if constexpr (is_invocable_v<decay_t<F>, stop_token, decay_t<Args>...>) {
-            return thread(move(f), get_stop_token(), move(args)...);
-        } else {
-            return thread(move(f), move(args)...);
-        }
-    }
-
-    shared_ptr<polyfill::stop_state> m_stop_state;
-    thread m_thread;
-};
-
-} // namespace std
-
-namespace Common {
-
-template <typename Condvar, typename Lock, typename Pred>
-void CondvarWait(Condvar& cv, Lock& lock, std::stop_token token, Pred pred) {
-    if (token.stop_requested()) {
-        return;
-    }
-
-    std::stop_callback callback(token, [&] { cv.notify_all(); });
-    cv.wait(lock, [&] { return pred() || token.stop_requested(); });
-}
-
-} // namespace Common
-
-#endif

src/common/settings.h

@@ -442,7 +442,7 @@ struct Values {
     SwitchableSetting<NvdecEmulation> nvdec_emulation{NvdecEmulation::GPU, "nvdec_emulation"};
     SwitchableSetting<bool> accelerate_astc{true, "accelerate_astc"};
     SwitchableSetting<bool> use_vsync{true, "use_vsync"};
-    SwitchableSetting<ShaderBackend, true> shader_backend{ShaderBackend::GLASM, ShaderBackend::GLSL,
+    SwitchableSetting<ShaderBackend, true> shader_backend{ShaderBackend::GLSL, ShaderBackend::GLSL,
                                                           ShaderBackend::SPIRV, "shader_backend"};
     SwitchableSetting<bool> use_asynchronous_shaders{false, "use_asynchronous_shaders"};
     SwitchableSetting<bool> use_fast_gpu_time{true, "use_fast_gpu_time"};

src/common/thread_worker.h

@@ -7,13 +7,13 @@
 #include <condition_variable>
 #include <functional>
 #include <mutex>
+#include <stop_token>
 #include <string>
 #include <thread>
 #include <type_traits>
 #include <vector>
 #include <queue>
 
-#include "common/polyfill_thread.h"
 #include "common/thread.h"
 #include "common/unique_function.h"
 
@@ -47,8 +47,7 @@ public:
                         if (requests.empty()) {
                             wait_condition.notify_all();
                         }
-                        Common::CondvarWait(condition, lock, stop_token,
-                                            [this] { return !requests.empty(); });
+                        condition.wait(lock, stop_token, [this] { return !requests.empty(); });
                         if (stop_token.stop_requested()) {
                             break;
                         }

src/common/threadsafe_queue.h

@@ -12,8 +12,6 @@
 #include <mutex>
 #include <utility>
 
-#include "common/polyfill_thread.h"
-
 namespace Common {
 template <typename T, bool with_stop_token = false>
 class SPSCQueue {
@@ -99,7 +97,7 @@ public:
     T PopWait(std::stop_token stop_token) {
         if (Empty()) {
             std::unique_lock lock{cv_mutex};
-            Common::CondvarWait(cv, lock, stop_token, [this] { return !Empty(); });
+            cv.wait(lock, stop_token, [this] { return !Empty(); });
         }
         if (stop_token.stop_requested()) {
             return T{};

src/core/CMakeLists.txt

@@ -530,6 +530,11 @@ add_library(core STATIC
     hle/service/ncm/ncm.h
     hle/service/nfc/nfc.cpp
     hle/service/nfc/nfc.h
+    hle/service/nfc/nfc_device.cpp
+    hle/service/nfc/nfc_device.h
+    hle/service/nfc/nfc_result.h
+    hle/service/nfc/nfc_user.cpp
+    hle/service/nfc/nfc_user.h
     hle/service/nfp/amiibo_crypto.cpp
     hle/service/nfp/amiibo_crypto.h
     hle/service/nfp/nfp.cpp

src/core/cpu_manager.h

@@ -10,7 +10,6 @@
 #include <thread>
 
 #include "common/fiber.h"
-#include "common/polyfill_thread.h"
 #include "common/thread.h"
 #include "core/hardware_properties.h"
 

src/core/debugger/debugger.cpp

@@ -9,7 +9,6 @@
 #include <boost/process/async_pipe.hpp>
 
 #include "common/logging/log.h"
-#include "common/polyfill_thread.h"
 #include "common/thread.h"
 #include "core/core.h"
 #include "core/debugger/debugger.h"

src/core/file_sys/content_archive.cpp

@@ -7,7 +7,6 @@
 #include <utility>
 
 #include "common/logging/log.h"
-#include "common/polyfill_ranges.h"
 #include "core/crypto/aes_util.h"
 #include "core/crypto/ctr_encryption_layer.h"
 #include "core/crypto/key_manager.h"

src/core/frontend/applets/controller.h

@@ -4,7 +4,6 @@
 #pragma once
 
 #include <functional>
-#include <vector>
 
 #include "common/common_types.h"
 

src/core/hid/emulated_controller.h

@@ -8,7 +8,6 @@
 #include <memory>
 #include <mutex>
 #include <unordered_map>
-#include <vector>
 
 #include "common/common_types.h"
 #include "common/input.h"

src/core/hid/emulated_devices.h

@@ -8,7 +8,6 @@
 #include <memory>
 #include <mutex>
 #include <unordered_map>
-#include <vector>
 
 #include "common/common_types.h"
 #include "common/input.h"

src/core/hle/kernel/hle_ipc.h

@@ -199,7 +199,7 @@ public:
     ~HLERequestContext();
 
     /// Returns a pointer to the IPC command buffer for this request.
-    u32* CommandBuffer() {
+    [[nodiscard]] u32* CommandBuffer() {
         return cmd_buf.data();
     }
 
@@ -207,7 +207,7 @@ public:
      * Returns the session through which this request was made. This can be used as a map key to
      * access per-client data on services.
      */
-    Kernel::KServerSession* Session() {
+    [[nodiscard]] Kernel::KServerSession* Session() {
         return server_session;
     }
 
@@ -217,61 +217,61 @@ public:
     /// Writes data from this context back to the requesting process/thread.
     Result WriteToOutgoingCommandBuffer(KThread& requesting_thread);
 
-    u32_le GetHipcCommand() const {
+    [[nodiscard]] u32_le GetHipcCommand() const {
         return command;
     }
 
-    u32_le GetTipcCommand() const {
+    [[nodiscard]] u32_le GetTipcCommand() const {
         return static_cast<u32_le>(command_header->type.Value()) -
                static_cast<u32_le>(IPC::CommandType::TIPC_CommandRegion);
     }
 
-    u32_le GetCommand() const {
+    [[nodiscard]] u32_le GetCommand() const {
         return command_header->IsTipc() ? GetTipcCommand() : GetHipcCommand();
     }
 
-    bool IsTipc() const {
+    [[nodiscard]] bool IsTipc() const {
         return command_header->IsTipc();
     }
 
-    IPC::CommandType GetCommandType() const {
+    [[nodiscard]] IPC::CommandType GetCommandType() const {
         return command_header->type;
     }
 
-    u64 GetPID() const {
+    [[nodiscard]] u64 GetPID() const {
         return pid;
     }
 
-    u32 GetDataPayloadOffset() const {
+    [[nodiscard]] u32 GetDataPayloadOffset() const {
         return data_payload_offset;
     }
 
-    const std::vector<IPC::BufferDescriptorX>& BufferDescriptorX() const {
+    [[nodiscard]] const std::vector<IPC::BufferDescriptorX>& BufferDescriptorX() const {
         return buffer_x_desciptors;
     }
 
-    const std::vector<IPC::BufferDescriptorABW>& BufferDescriptorA() const {
+    [[nodiscard]] const std::vector<IPC::BufferDescriptorABW>& BufferDescriptorA() const {
         return buffer_a_desciptors;
     }
 
-    const std::vector<IPC::BufferDescriptorABW>& BufferDescriptorB() const {
+    [[nodiscard]] const std::vector<IPC::BufferDescriptorABW>& BufferDescriptorB() const {
         return buffer_b_desciptors;
     }
 
-    const std::vector<IPC::BufferDescriptorC>& BufferDescriptorC() const {
+    [[nodiscard]] const std::vector<IPC::BufferDescriptorC>& BufferDescriptorC() const {
         return buffer_c_desciptors;
     }
 
-    const IPC::DomainMessageHeader& GetDomainMessageHeader() const {
+    [[nodiscard]] const IPC::DomainMessageHeader& GetDomainMessageHeader() const {
         return domain_message_header.value();
     }
 
-    bool HasDomainMessageHeader() const {
+    [[nodiscard]] bool HasDomainMessageHeader() const {
         return domain_message_header.has_value();
     }
 
     /// Helper function to read a buffer using the appropriate buffer descriptor
-    std::vector<u8> ReadBuffer(std::size_t buffer_index = 0) const;
+    [[nodiscard]] std::vector<u8> ReadBuffer(std::size_t buffer_index = 0) const;
 
     /// Helper function to write a buffer using the appropriate buffer descriptor
     std::size_t WriteBuffer(const void* buffer, std::size_t size,
@@ -308,22 +308,34 @@ public:
     }
 
     /// Helper function to get the size of the input buffer
-    std::size_t GetReadBufferSize(std::size_t buffer_index = 0) const;
+    [[nodiscard]] std::size_t GetReadBufferSize(std::size_t buffer_index = 0) const;
 
     /// Helper function to get the size of the output buffer
-    std::size_t GetWriteBufferSize(std::size_t buffer_index = 0) const;
+    [[nodiscard]] std::size_t GetWriteBufferSize(std::size_t buffer_index = 0) const;
+
+    /// Helper function to derive the number of elements able to be contained in the read buffer
+    template <typename T>
+    [[nodiscard]] std::size_t GetReadBufferNumElements(std::size_t buffer_index = 0) const {
+        return GetReadBufferSize(buffer_index) / sizeof(T);
+    }
+
+    /// Helper function to derive the number of elements able to be contained in the write buffer
+    template <typename T>
+    [[nodiscard]] std::size_t GetWriteBufferNumElements(std::size_t buffer_index = 0) const {
+        return GetWriteBufferSize(buffer_index) / sizeof(T);
+    }
 
     /// Helper function to test whether the input buffer at buffer_index can be read
-    bool CanReadBuffer(std::size_t buffer_index = 0) const;
+    [[nodiscard]] bool CanReadBuffer(std::size_t buffer_index = 0) const;
 
     /// Helper function to test whether the output buffer at buffer_index can be written
-    bool CanWriteBuffer(std::size_t buffer_index = 0) const;
+    [[nodiscard]] bool CanWriteBuffer(std::size_t buffer_index = 0) const;
 
-    Handle GetCopyHandle(std::size_t index) const {
+    [[nodiscard]] Handle GetCopyHandle(std::size_t index) const {
         return incoming_copy_handles.at(index);
     }
 
-    Handle GetMoveHandle(std::size_t index) const {
+    [[nodiscard]] Handle GetMoveHandle(std::size_t index) const {
         return incoming_move_handles.at(index);
     }
 
@@ -348,13 +360,13 @@ public:
         manager = manager_;
     }
 
-    std::string Description() const;
+    [[nodiscard]] std::string Description() const;
 
-    KThread& GetThread() {
+    [[nodiscard]] KThread& GetThread() {
         return *thread;
     }
 
-    std::shared_ptr<SessionRequestManager> GetManager() const {
+    [[nodiscard]] std::shared_ptr<SessionRequestManager> GetManager() const {
         return manager.lock();
     }
 

src/core/hle/kernel/k_handle_table.cpp

@@ -2,6 +2,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 #include "core/hle/kernel/k_handle_table.h"
+#include "core/hle/kernel/k_process.h"
 
 namespace Kernel {
 
@@ -82,6 +83,22 @@ Result KHandleTable::Add(Handle* out_handle, KAutoObject* obj) {
     R_SUCCEED();
 }
 
+KScopedAutoObject<KAutoObject> KHandleTable::GetObjectForIpc(Handle handle,
+                                                             KThread* cur_thread) const {
+    // Handle pseudo-handles.
+    ASSERT(cur_thread != nullptr);
+    if (handle == Svc::PseudoHandle::CurrentProcess) {
+        auto* const cur_process = cur_thread->GetOwnerProcess();
+        ASSERT(cur_process != nullptr);
+        return cur_process;
+    }
+    if (handle == Svc::PseudoHandle::CurrentThread) {
+        return cur_thread;
+    }
+
+    return GetObjectForIpcWithoutPseudoHandle(handle);
+}
+
 Result KHandleTable::Reserve(Handle* out_handle) {
     KScopedDisableDispatch dd{m_kernel};
     KScopedSpinLock lk(m_lock);

src/core/hle/kernel/k_handle_table.h

@@ -113,21 +113,7 @@ public:
         return this->GetObjectImpl(handle);
     }
 
-    KScopedAutoObject<KAutoObject> GetObjectForIpc(Handle handle, KThread* cur_thread) const {
-        // Handle pseudo-handles.
-        ASSERT(cur_thread != nullptr);
-        if (handle == Svc::PseudoHandle::CurrentProcess) {
-            auto* const cur_process =
-                static_cast<KAutoObject*>(static_cast<void*>(cur_thread->GetOwnerProcess()));
-            ASSERT(cur_process != nullptr);
-            return cur_process;
-        }
-        if (handle == Svc::PseudoHandle::CurrentThread) {
-            return static_cast<KAutoObject*>(cur_thread);
-        }
-
-        return GetObjectForIpcWithoutPseudoHandle(handle);
-    }
+    KScopedAutoObject<KAutoObject> GetObjectForIpc(Handle handle, KThread* cur_thread) const;
 
     KScopedAutoObject<KAutoObject> GetObjectByIndex(Handle* out_handle, size_t index) const {
         KScopedDisableDispatch dd{m_kernel};

src/core/hle/kernel/k_memory_manager.cpp

@@ -225,8 +225,8 @@ Result KMemoryManager::AllocatePageGroupImpl(KPageGroup* out, size_t num_pages,
     ON_RESULT_FAILURE {
         for (const auto& it : out->Nodes()) {
             auto& manager = this->GetManager(it.GetAddress());
-            const size_t node_num_pages = std::min<u64>(
-                it.GetNumPages(), (manager.GetEndAddress() - it.GetAddress()) / PageSize);
+            const size_t node_num_pages =
+                std::min(it.GetNumPages(), (manager.GetEndAddress() - it.GetAddress()) / PageSize);
             manager.Free(it.GetAddress(), node_num_pages);
         }
         out->Finalize();

src/core/hle/kernel/k_slab_heap.h

@@ -6,7 +6,6 @@
 #include <atomic>
 
 #include "common/assert.h"
-#include "common/atomic_ops.h"
 #include "common/common_funcs.h"
 #include "common/common_types.h"
 #include "common/spin_lock.h"
@@ -83,13 +82,16 @@ private:
 
 private:
     void UpdatePeakImpl(uintptr_t obj) {
+        static_assert(std::atomic_ref<uintptr_t>::is_always_lock_free);
+        std::atomic_ref<uintptr_t> peak_ref(m_peak);
+
         const uintptr_t alloc_peak = obj + this->GetObjectSize();
         uintptr_t cur_peak = m_peak;
         do {
             if (alloc_peak <= cur_peak) {
                 break;
             }
-        } while (!Common::AtomicCompareAndSwap(&m_peak, alloc_peak, cur_peak, cur_peak));
+        } while (!peak_ref.compare_exchange_strong(cur_peak, alloc_peak));
     }
 
 public:

src/core/hle/kernel/k_thread_local_page.h

@@ -10,7 +10,6 @@
 #include "common/assert.h"
 #include "common/common_types.h"
 #include "common/intrusive_red_black_tree.h"
-#include "common/polyfill_ranges.h"
 #include "core/hle/kernel/memory_types.h"
 #include "core/hle/kernel/slab_helpers.h"
 #include "core/hle/result.h"

src/core/hle/kernel/service_thread.cpp

@@ -7,7 +7,6 @@
 #include <thread>
 #include <vector>
 
-#include "common/polyfill_thread.h"
 #include "common/scope_exit.h"
 #include "common/thread.h"
 #include "core/hle/ipc_helpers.h"

src/core/hle/kernel/svc_wrap.h

@@ -82,7 +82,7 @@ void SvcWrap64(Core::System& system) {
 }
 
 // Used by ControlCodeMemory
-template <Result func(Core::System&, Handle, u32, VAddr, size_t, Svc::MemoryPermission)>
+template <Result func(Core::System&, Handle, u32, u64, u64, Svc::MemoryPermission)>
 void SvcWrap64(Core::System& system) {
     FuncReturn(system, func(system, static_cast<Handle>(Param(system, 0)),
                             static_cast<u32>(Param(system, 1)), Param(system, 2), Param(system, 3),
@@ -327,7 +327,7 @@ void SvcWrap64(Core::System& system) {
 }
 
 // Used by CreateCodeMemory
-template <Result func(Core::System&, Handle*, VAddr, size_t)>
+template <Result func(Core::System&, Handle*, u64, u64)>
 void SvcWrap64(Core::System& system) {
     u32 param_1 = 0;
     const u32 retval = func(system, &param_1, Param(system, 1), Param(system, 2)).raw;

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

@@ -7,7 +7,6 @@
 #include "common/fs/file.h"
 #include "common/fs/path_util.h"
 #include "common/logging/log.h"
-#include "common/polyfill_ranges.h"
 #include "common/string_util.h"
 #include "common/swap.h"
 #include "core/constants.h"

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

@@ -9,7 +9,6 @@
 #include "common/fs/file.h"
 #include "common/fs/fs.h"
 #include "common/fs/path_util.h"
-#include "common/polyfill_ranges.h"
 #include "common/settings.h"
 #include "core/hle/service/acc/profile_manager.h"
 

src/core/hle/service/am/am.cpp

@@ -1125,7 +1125,7 @@ void IStorageAccessor::Write(Kernel::HLERequestContext& ctx) {
 
     const u64 offset{rp.Pop<u64>()};
     const std::vector<u8> data{ctx.ReadBuffer()};
-    const std::size_t size{std::min<u64>(data.size(), backing.GetSize() - offset)};
+    const std::size_t size{std::min(data.size(), backing.GetSize() - offset)};
 
     LOG_DEBUG(Service_AM, "called, offset={}, size={}", offset, size);
 
@@ -1149,7 +1149,7 @@ void IStorageAccessor::Read(Kernel::HLERequestContext& ctx) {
     IPC::RequestParser rp{ctx};
 
     const u64 offset{rp.Pop<u64>()};
-    const std::size_t size{std::min<u64>(ctx.GetWriteBufferSize(), backing.GetSize() - offset)};
+    const std::size_t size{std::min(ctx.GetWriteBufferSize(), backing.GetSize() - offset)};
 
     LOG_DEBUG(Service_AM, "called, offset={}, size={}", offset, size);
 

src/core/hle/service/audio/audin_u.cpp

@@ -122,10 +122,10 @@ private:
     }
 
     void GetReleasedAudioInBuffer(Kernel::HLERequestContext& ctx) {
-        auto write_buffer_size = ctx.GetWriteBufferSize() / sizeof(u64);
-        std::vector<u64> released_buffers(write_buffer_size, 0);
+        const auto write_buffer_size = ctx.GetWriteBufferNumElements<u64>();
+        std::vector<u64> released_buffers(write_buffer_size);
 
-        auto count = impl->GetReleasedBuffers(released_buffers);
+        const auto count = impl->GetReleasedBuffers(released_buffers);
 
         [[maybe_unused]] std::string tags{};
         for (u32 i = 0; i < count; i++) {
@@ -228,7 +228,7 @@ void AudInU::ListAudioIns(Kernel::HLERequestContext& ctx) {
     LOG_DEBUG(Service_Audio, "called");
 
     const auto write_count =
-        static_cast<u32>(ctx.GetWriteBufferSize() / sizeof(AudioDevice::AudioDeviceName));
+        static_cast<u32>(ctx.GetWriteBufferNumElements<AudioDevice::AudioDeviceName>());
     std::vector<AudioDevice::AudioDeviceName> device_names{};
 
     u32 out_count{0};
@@ -248,7 +248,7 @@ void AudInU::ListAudioInsAutoFiltered(Kernel::HLERequestContext& ctx) {
     LOG_DEBUG(Service_Audio, "called");
 
     const auto write_count =
-        static_cast<u32>(ctx.GetWriteBufferSize() / sizeof(AudioDevice::AudioDeviceName));
+        static_cast<u32>(ctx.GetWriteBufferNumElements<AudioDevice::AudioDeviceName>());
     std::vector<AudioDevice::AudioDeviceName> device_names{};
 
     u32 out_count{0};

src/core/hle/service/audio/audout_u.cpp

@@ -129,16 +129,16 @@ private:
     }
 
     void GetReleasedAudioOutBuffers(Kernel::HLERequestContext& ctx) {
-        auto write_buffer_size = ctx.GetWriteBufferSize() / sizeof(u64);
-        std::vector<u64> released_buffers(write_buffer_size, 0);
+        const auto write_buffer_size = ctx.GetWriteBufferNumElements<u64>();
+        std::vector<u64> released_buffers(write_buffer_size);
 
-        auto count = impl->GetReleasedBuffers(released_buffers);
+        const auto count = impl->GetReleasedBuffers(released_buffers);
 
         [[maybe_unused]] std::string tags{};
         for (u32 i = 0; i < count; i++) {
             tags += fmt::format("{:08X}, ", released_buffers[i]);
         }
-        [[maybe_unused]] auto sessionid{impl->GetSystem().GetSessionId()};
+        [[maybe_unused]] const auto sessionid{impl->GetSystem().GetSessionId()};
         LOG_TRACE(Service_Audio, "called. Session {} released {} buffers: {}", sessionid, count,
                   tags);
 
@@ -244,7 +244,7 @@ void AudOutU::ListAudioOuts(Kernel::HLERequestContext& ctx) {
     std::scoped_lock l{impl->mutex};
 
     const auto write_count =
-        static_cast<u32>(ctx.GetWriteBufferSize() / sizeof(AudioDevice::AudioDeviceName));
+        static_cast<u32>(ctx.GetWriteBufferNumElements<AudioDevice::AudioDeviceName>());
     std::vector<AudioDevice::AudioDeviceName> device_names{};
     if (write_count > 0) {
         device_names.emplace_back("DeviceOut");

src/core/hle/service/audio/audren_u.cpp

@@ -14,7 +14,6 @@
 #include "common/bit_util.h"
 #include "common/common_funcs.h"
 #include "common/logging/log.h"
-#include "common/polyfill_ranges.h"
 #include "common/string_util.h"
 #include "core/core.h"
 #include "core/hle/ipc_helpers.h"
@@ -275,7 +274,7 @@ public:
 
 private:
     void ListAudioDeviceName(Kernel::HLERequestContext& ctx) {
-        const size_t in_count = ctx.GetWriteBufferSize() / sizeof(AudioDevice::AudioDeviceName);
+        const size_t in_count = ctx.GetWriteBufferNumElements<AudioDevice::AudioDeviceName>();
 
         std::vector<AudioDevice::AudioDeviceName> out_names{};
 
@@ -336,7 +335,7 @@ private:
     }
 
     void GetActiveAudioDeviceName(Kernel::HLERequestContext& ctx) {
-        const auto write_size = ctx.GetWriteBufferSize() / sizeof(char);
+        const auto write_size = ctx.GetWriteBufferSize();
         std::string out_name{"AudioTvOutput"};
 
         LOG_DEBUG(Service_Audio, "(STUBBED) called. Name={}", out_name);
@@ -388,7 +387,7 @@ private:
     }
 
     void ListAudioOutputDeviceName(Kernel::HLERequestContext& ctx) {
-        const size_t in_count = ctx.GetWriteBufferSize() / sizeof(AudioDevice::AudioDeviceName);
+        const size_t in_count = ctx.GetWriteBufferNumElements<AudioDevice::AudioDeviceName>();
 
         std::vector<AudioDevice::AudioDeviceName> out_names{};
 

src/core/hle/service/audio/hwopus.cpp

@@ -68,7 +68,7 @@ private:
                                  ExtraBehavior extra_behavior) {
         u32 consumed = 0;
         u32 sample_count = 0;
-        std::vector<opus_int16> samples(ctx.GetWriteBufferSize() / sizeof(opus_int16));
+        std::vector<opus_int16> samples(ctx.GetWriteBufferNumElements<opus_int16>());
 
         if (extra_behavior == ExtraBehavior::ResetContext) {
             ResetDecoderContext();

src/core/hle/service/bcat/bcat_module.cpp

@@ -443,7 +443,7 @@ private:
     }
 
     void Read(Kernel::HLERequestContext& ctx) {
-        auto write_size = ctx.GetWriteBufferSize() / sizeof(DeliveryCacheDirectoryEntry);
+        auto write_size = ctx.GetWriteBufferNumElements<DeliveryCacheDirectoryEntry>();
 
         LOG_DEBUG(Service_BCAT, "called, write_size={:016X}", write_size);
 
@@ -533,7 +533,7 @@ private:
     }
 
     void EnumerateDeliveryCacheDirectory(Kernel::HLERequestContext& ctx) {
-        auto size = ctx.GetWriteBufferSize() / sizeof(DirectoryName);
+        auto size = ctx.GetWriteBufferNumElements<DirectoryName>();
 
         LOG_DEBUG(Service_BCAT, "called, size={:016X}", size);
 

src/core/hle/service/es/es.cpp

@@ -192,12 +192,10 @@ private:
     }
 
     void ListCommonTicketRightsIds(Kernel::HLERequestContext& ctx) {
-        u32 out_entries;
-        if (keys.GetCommonTickets().empty())
-            out_entries = 0;
-        else
-            out_entries = static_cast<u32>(ctx.GetWriteBufferSize() / sizeof(u128));
-
+        size_t out_entries = 0;
+        if (!keys.GetCommonTickets().empty()) {
+            out_entries = ctx.GetWriteBufferNumElements<u128>();
+        }
         LOG_DEBUG(Service_ETicket, "called, entries={:016X}", out_entries);
 
         keys.PopulateTickets();
@@ -206,20 +204,19 @@ private:
         std::transform(tickets.begin(), tickets.end(), std::back_inserter(ids),
                        [](const auto& pair) { return pair.first; });
 
-        out_entries = static_cast<u32>(std::min<std::size_t>(ids.size(), out_entries));
+        out_entries = std::min(ids.size(), out_entries);
         ctx.WriteBuffer(ids.data(), out_entries * sizeof(u128));
 
         IPC::ResponseBuilder rb{ctx, 3};
         rb.Push(ResultSuccess);
-        rb.Push<u32>(out_entries);
+        rb.Push<u32>(static_cast<u32>(out_entries));
     }
 
     void ListPersonalizedTicketRightsIds(Kernel::HLERequestContext& ctx) {
-        u32 out_entries;
-        if (keys.GetPersonalizedTickets().empty())
-            out_entries = 0;
-        else
-            out_entries = static_cast<u32>(ctx.GetWriteBufferSize() / sizeof(u128));
+        size_t out_entries = 0;
+        if (!keys.GetPersonalizedTickets().empty()) {
+            out_entries = ctx.GetWriteBufferNumElements<u128>();
+        }
 
         LOG_DEBUG(Service_ETicket, "called, entries={:016X}", out_entries);
 
@@ -229,12 +226,12 @@ private:
         std::transform(tickets.begin(), tickets.end(), std::back_inserter(ids),
                        [](const auto& pair) { return pair.first; });
 
-        out_entries = static_cast<u32>(std::min<std::size_t>(ids.size(), out_entries));
+        out_entries = std::min(ids.size(), out_entries);
         ctx.WriteBuffer(ids.data(), out_entries * sizeof(u128));
 
         IPC::ResponseBuilder rb{ctx, 3};
         rb.Push(ResultSuccess);
-        rb.Push<u32>(out_entries);
+        rb.Push<u32>(static_cast<u32>(out_entries));
     }
 
     void GetCommonTicketSize(Kernel::HLERequestContext& ctx) {

src/core/hle/service/filesystem/fsp_srv.cpp

@@ -277,7 +277,7 @@ private:
         LOG_DEBUG(Service_FS, "called.");
 
         // Calculate how many entries we can fit in the output buffer
-        const u64 count_entries = ctx.GetWriteBufferSize() / sizeof(FileSys::Entry);
+        const u64 count_entries = ctx.GetWriteBufferNumElements<FileSys::Entry>();
 
         // Cap at total number of entries.
         const u64 actual_entries = std::min(count_entries, entries.size() - next_entry_index);
@@ -543,7 +543,7 @@ public:
         LOG_DEBUG(Service_FS, "called");
 
         // Calculate how many entries we can fit in the output buffer
-        const u64 count_entries = ctx.GetWriteBufferSize() / sizeof(SaveDataInfo);
+        const u64 count_entries = ctx.GetWriteBufferNumElements<SaveDataInfo>();
 
         // Cap at total number of entries.
         const u64 actual_entries = std::min(count_entries, info.size() - next_entry_index);

src/core/hle/service/ldn/ldn.cpp

@@ -292,7 +292,7 @@ public:
 
     void GetNetworkInfoLatestUpdate(Kernel::HLERequestContext& ctx) {
         const std::size_t network_buffer_size = ctx.GetWriteBufferSize(0);
-        const std::size_t node_buffer_count = ctx.GetWriteBufferSize(1) / sizeof(NodeLatestUpdate);
+        const std::size_t node_buffer_count = ctx.GetWriteBufferNumElements<NodeLatestUpdate>(1);
 
         if (node_buffer_count == 0 || network_buffer_size != sizeof(NetworkInfo)) {
             LOG_ERROR(Service_LDN, "Invalid buffer, size = {}, count = {}", network_buffer_size,
@@ -333,7 +333,7 @@ public:
         const auto channel{rp.PopEnum<WifiChannel>()};
         const auto scan_filter{rp.PopRaw<ScanFilter>()};
 
-        const std::size_t network_info_size = ctx.GetWriteBufferSize() / sizeof(NetworkInfo);
+        const std::size_t network_info_size = ctx.GetWriteBufferNumElements<NetworkInfo>();
 
         if (network_info_size == 0) {
             LOG_ERROR(Service_LDN, "Invalid buffer size {}", network_info_size);

src/core/hle/service/nfc/nfc.cpp

@@ -7,6 +7,7 @@
 #include "common/settings.h"
 #include "core/hle/ipc_helpers.h"
 #include "core/hle/service/nfc/nfc.h"
+#include "core/hle/service/nfc/nfc_user.h"
 #include "core/hle/service/service.h"
 #include "core/hle/service/sm/sm.h"
 
@@ -97,76 +98,6 @@ private:
     }
 };
 
-class IUser final : public ServiceFramework<IUser> {
-public:
-    explicit IUser(Core::System& system_) : ServiceFramework{system_, "NFC::IUser"} {
-        // clang-format off
-        static const FunctionInfo functions[] = {
-            {0, &IUser::InitializeOld, "InitializeOld"},
-            {1, &IUser::FinalizeOld, "FinalizeOld"},
-            {2, &IUser::GetStateOld, "GetStateOld"},
-            {3, &IUser::IsNfcEnabledOld, "IsNfcEnabledOld"},
-            {400, &IUser::InitializeOld, "Initialize"},
-            {401, &IUser::FinalizeOld, "Finalize"},
-            {402, &IUser::GetStateOld, "GetState"},
-            {403, &IUser::IsNfcEnabledOld, "IsNfcEnabled"},
-            {404, nullptr, "ListDevices"},
-            {405, nullptr, "GetDeviceState"},
-            {406, nullptr, "GetNpadId"},
-            {407, nullptr, "AttachAvailabilityChangeEvent"},
-            {408, nullptr, "StartDetection"},
-            {409, nullptr, "StopDetection"},
-            {410, nullptr, "GetTagInfo"},
-            {411, nullptr, "AttachActivateEvent"},
-            {412, nullptr, "AttachDeactivateEvent"},
-            {1000, nullptr, "ReadMifare"},
-            {1001, nullptr, "WriteMifare"},
-            {1300, nullptr, "SendCommandByPassThrough"},
-            {1301, nullptr, "KeepPassThroughSession"},
-            {1302, nullptr, "ReleasePassThroughSession"},
-        };
-        // clang-format on
-
-        RegisterHandlers(functions);
-    }
-
-private:
-    enum class NfcStates : u32 {
-        Finalized = 6,
-    };
-
-    void InitializeOld(Kernel::HLERequestContext& ctx) {
-        LOG_DEBUG(Service_NFC, "called");
-
-        IPC::ResponseBuilder rb{ctx, 2, 0};
-        rb.Push(ResultSuccess);
-        // We don't deal with hardware initialization so we can just stub this.
-    }
-
-    void IsNfcEnabledOld(Kernel::HLERequestContext& ctx) {
-        LOG_DEBUG(Service_NFC, "IsNfcEnabledOld");
-
-        IPC::ResponseBuilder rb{ctx, 3};
-        rb.Push(ResultSuccess);
-        rb.PushRaw<u8>(true);
-    }
-
-    void GetStateOld(Kernel::HLERequestContext& ctx) {
-        LOG_WARNING(Service_NFC, "(STUBBED) called");
-
-        IPC::ResponseBuilder rb{ctx, 3};
-        rb.Push(ResultSuccess);
-        rb.PushEnum(NfcStates::Finalized); // TODO(ogniK): Figure out if this matches nfp
-    }
-
-    void FinalizeOld(Kernel::HLERequestContext& ctx) {
-        LOG_WARNING(Service_NFC, "(STUBBED) called");
-
-        IPC::ResponseBuilder rb{ctx, 2};
-        rb.Push(ResultSuccess);
-    }
-};
-
 class NFC_U final : public ServiceFramework<NFC_U> {
 public:
     explicit NFC_U(Core::System& system_) : ServiceFramework{system_, "nfc:user"} {

src/core/hle/service/nfc/nfc_device.cpp

@@ -0,0 +1,197 @@
+// SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include "common/input.h"
+#include "common/logging/log.h"
+#include "core/core.h"
+#include "core/hid/emulated_controller.h"
+#include "core/hid/hid_core.h"
+#include "core/hid/hid_types.h"
+#include "core/hle/ipc_helpers.h"
+#include "core/hle/kernel/k_event.h"
+#include "core/hle/service/nfc/nfc_device.h"
+#include "core/hle/service/nfc/nfc_result.h"
+#include "core/hle/service/nfc/nfc_user.h"
+
+namespace Service::NFC {
+NfcDevice::NfcDevice(Core::HID::NpadIdType npad_id_, Core::System& system_,
+                     KernelHelpers::ServiceContext& service_context_,
+                     Kernel::KEvent* availability_change_event_)
+    : npad_id{npad_id_}, system{system_}, service_context{service_context_},
+      availability_change_event{availability_change_event_} {
+    activate_event = service_context.CreateEvent("IUser:NFCActivateEvent");
+    deactivate_event = service_context.CreateEvent("IUser:NFCDeactivateEvent");
+    npad_device = system.HIDCore().GetEmulatedController(npad_id);
+
+    Core::HID::ControllerUpdateCallback engine_callback{
+        .on_change = [this](Core::HID::ControllerTriggerType type) { NpadUpdate(type); },
+        .is_npad_service = false,
+    };
+    is_controller_set = true;
+    callback_key = npad_device->SetCallback(engine_callback);
+}
+
+NfcDevice::~NfcDevice() {
+    activate_event->Close();
+    deactivate_event->Close();
+    if (!is_controller_set) {
+        return;
+    }
+    npad_device->DeleteCallback(callback_key);
+    is_controller_set = false;
+};
+
+void NfcDevice::NpadUpdate(Core::HID::ControllerTriggerType type) {
+    if (type == Core::HID::ControllerTriggerType::Connected ||
+        type == Core::HID::ControllerTriggerType::Disconnected) {
+        availability_change_event->Signal();
+        return;
+    }
+
+    if (type != Core::HID::ControllerTriggerType::Nfc) {
+        return;
+    }
+
+    if (!npad_device->IsConnected()) {
+        return;
+    }
+
+    const auto nfc_status = npad_device->GetNfc();
+    switch (nfc_status.state) {
+    case Common::Input::NfcState::NewAmiibo:
+        LoadNfcTag(nfc_status.data);
+        break;
+    case Common::Input::NfcState::AmiiboRemoved:
+        if (device_state != NFP::DeviceState::SearchingForTag) {
+            CloseNfcTag();
+        }
+        break;
+    default:
+        break;
+    }
+}
+
+bool NfcDevice::LoadNfcTag(std::span<const u8> data) {
+    if (device_state != NFP::DeviceState::SearchingForTag) {
+        LOG_ERROR(Service_NFC, "Game is not looking for nfc tag, current state {}", device_state);
+        return false;
+    }
+
+    if (data.size() != sizeof(NFP::EncryptedNTAG215File)) {
+        LOG_ERROR(Service_NFC, "Not an amiibo, size={}", data.size());
+        return false;
+    }
+
+    memcpy(&encrypted_tag_data, data.data(), sizeof(NFP::EncryptedNTAG215File));
+
+    device_state = NFP::DeviceState::TagFound;
+    deactivate_event->GetReadableEvent().Clear();
+    activate_event->Signal();
+    return true;
+}
+
+void NfcDevice::CloseNfcTag() {
+    LOG_INFO(Service_NFC, "Remove nfc tag");
+
+    device_state = NFP::DeviceState::TagRemoved;
+    encrypted_tag_data = {};
+    activate_event->GetReadableEvent().Clear();
+    deactivate_event->Signal();
+}
+
+Kernel::KReadableEvent& NfcDevice::GetActivateEvent() const {
+    return activate_event->GetReadableEvent();
+}
+
+Kernel::KReadableEvent& NfcDevice::GetDeactivateEvent() const {
+    return deactivate_event->GetReadableEvent();
+}
+
+void NfcDevice::Initialize() {
+    device_state =
+        npad_device->HasNfc() ? NFP::DeviceState::Initialized : NFP::DeviceState::Unavailable;
+    encrypted_tag_data = {};
+}
+
+void NfcDevice::Finalize() {
+    if (device_state == NFP::DeviceState::SearchingForTag ||
+        device_state == NFP::DeviceState::TagRemoved) {
+        StopDetection();
+    }
+    device_state = NFP::DeviceState::Unavailable;
+}
+
+Result NfcDevice::StartDetection(s32 protocol_) {
+    if (device_state != NFP::DeviceState::Initialized &&
+        device_state != NFP::DeviceState::TagRemoved) {
+        LOG_ERROR(Service_NFC, "Wrong device state {}", device_state);
+        return WrongDeviceState;
+    }
+
+    if (!npad_device->SetPollingMode(Common::Input::PollingMode::NFC)) {
+        LOG_ERROR(Service_NFC, "Nfc not supported");
+        return NfcDisabled;
+    }
+
+    device_state = NFP::DeviceState::SearchingForTag;
+    protocol = protocol_;
+    return ResultSuccess;
+}
+
+Result NfcDevice::StopDetection() {
+    npad_device->SetPollingMode(Common::Input::PollingMode::Active);
+
+    if (device_state == NFP::DeviceState::Initialized) {
+        return ResultSuccess;
+    }
+
+    if (device_state == NFP::DeviceState::TagFound ||
+        device_state == NFP::DeviceState::TagMounted) {
+        CloseNfcTag();
+        return ResultSuccess;
+    }
+    if (device_state == NFP::DeviceState::SearchingForTag ||
+        device_state == NFP::DeviceState::TagRemoved) {
+        device_state = NFP::DeviceState::Initialized;
+        return ResultSuccess;
+    }
+
+    LOG_ERROR(Service_NFC, "Wrong device state {}", device_state);
+    return WrongDeviceState;
+}
+
+Result NfcDevice::GetTagInfo(NFP::TagInfo& tag_info) const {
+    if (device_state != NFP::DeviceState::TagFound &&
+        device_state != NFP::DeviceState::TagMounted) {
+        LOG_ERROR(Service_NFC, "Wrong device state {}", device_state);
+        if (device_state == NFP::DeviceState::TagRemoved) {
+            return TagRemoved;
+        }
+        return WrongDeviceState;
+    }
+
+    // Protocol and tag type may change here
+    tag_info = {
+        .uuid = encrypted_tag_data.uuid.uid,
+        .uuid_length = static_cast<u8>(encrypted_tag_data.uuid.uid.size()),
+        .protocol = NFP::TagProtocol::TypeA,
+        .tag_type = NFP::TagType::Type2,
+    };
+
+    return ResultSuccess;
+}
+
+u64 NfcDevice::GetHandle() const {
+    // Generate a handle based of the npad id
+    return static_cast<u64>(npad_id);
+}
+
+NFP::DeviceState NfcDevice::GetCurrentState() const {
+    return device_state;
+}
+
+Core::HID::NpadIdType NfcDevice::GetNpadId() const {
+    return npad_id;
+}
+
+} // namespace Service::NFC

src/core/hle/service/nfc/nfc_device.h

@@ -0,0 +1,70 @@
+// SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#pragma once
+
+#include "common/common_types.h"
+#include "core/hle/service/kernel_helpers.h"
+#include "core/hle/service/nfp/nfp_types.h"
+#include "core/hle/service/service.h"
+
+namespace Kernel {
+class KEvent;
+class KReadableEvent;
+} // namespace Kernel
+
+namespace Core {
+class System;
+} // namespace Core
+
+namespace Core::HID {
+class EmulatedController;
+enum class ControllerTriggerType;
+enum class NpadIdType : u32;
+} // namespace Core::HID
+
+namespace Service::NFC {
+class NfcDevice {
+public:
+    NfcDevice(Core::HID::NpadIdType npad_id_, Core::System& system_,
+              KernelHelpers::ServiceContext& service_context_,
+              Kernel::KEvent* availability_change_event_);
+    ~NfcDevice();
+
+    void Initialize();
+    void Finalize();
+
+    Result StartDetection(s32 protocol_);
+    Result StopDetection();
+
+    Result GetTagInfo(NFP::TagInfo& tag_info) const;
+
+    u64 GetHandle() const;
+    NFP::DeviceState GetCurrentState() const;
+    Core::HID::NpadIdType GetNpadId() const;
+
+    Kernel::KReadableEvent& GetActivateEvent() const;
+    Kernel::KReadableEvent& GetDeactivateEvent() const;
+
+private:
+    void NpadUpdate(Core::HID::ControllerTriggerType type);
+    bool LoadNfcTag(std::span<const u8> data);
+    void CloseNfcTag();
+
+    bool is_controller_set{};
+    int callback_key;
+    const Core::HID::NpadIdType npad_id;
+    Core::System& system;
+    Core::HID::EmulatedController* npad_device = nullptr;
+    KernelHelpers::ServiceContext& service_context;
+    Kernel::KEvent* activate_event = nullptr;
+    Kernel::KEvent* deactivate_event = nullptr;
+    Kernel::KEvent* availability_change_event = nullptr;
+
+    s32 protocol{};
+    NFP::DeviceState device_state{NFP::DeviceState::Unavailable};
+
+    NFP::EncryptedNTAG215File encrypted_tag_data{};
+};
+
+} // namespace Service::NFC

src/core/hle/service/nfc/nfc_result.h

@@ -0,0 +1,17 @@
+// SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#pragma once
+
+#include "core/hle/result.h"
+
+namespace Service::NFC {
+
+constexpr Result DeviceNotFound(ErrorModule::NFC, 64);
+constexpr Result InvalidArgument(ErrorModule::NFC, 65);
+constexpr Result WrongDeviceState(ErrorModule::NFC, 73);
+constexpr Result NfcDisabled(ErrorModule::NFC, 80);
+constexpr Result TagRemoved(ErrorModule::NFC, 97);
+constexpr Result CorruptedData(ErrorModule::NFC, 144);
+
+} // namespace Service::NFC

src/core/hle/service/nfc/nfc_user.cpp

@@ -0,0 +1,365 @@
+// SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include "common/logging/log.h"
+#include "core/core.h"
+#include "core/hid/hid_types.h"
+#include "core/hle/ipc_helpers.h"
+#include "core/hle/kernel/k_event.h"
+#include "core/hle/service/nfc/nfc_device.h"
+#include "core/hle/service/nfc/nfc_result.h"
+#include "core/hle/service/nfc/nfc_user.h"
+#include "core/hle/service/time/clock_types.h"
+
+namespace Service::NFC {
+
+IUser::IUser(Core::System& system_)
+    : ServiceFramework{system_, "NFC::IUser"}, service_context{system_, service_name} {
+    static const FunctionInfo functions[] = {
+        {0, &IUser::Initialize, "InitializeOld"},
+        {1, &IUser::Finalize, "FinalizeOld"},
+        {2, &IUser::GetState, "GetStateOld"},
+        {3, &IUser::IsNfcEnabled, "IsNfcEnabledOld"},
+        {400, &IUser::Initialize, "Initialize"},
+        {401, &IUser::Finalize, "Finalize"},
+        {402, &IUser::GetState, "GetState"},
+        {403, &IUser::IsNfcEnabled, "IsNfcEnabled"},
+        {404, &IUser::ListDevices, "ListDevices"},
+        {405, &IUser::GetDeviceState, "GetDeviceState"},
+        {406, &IUser::GetNpadId, "GetNpadId"},
+        {407, &IUser::AttachAvailabilityChangeEvent, "AttachAvailabilityChangeEvent"},
+        {408, &IUser::StartDetection, "StartDetection"},
+        {409, &IUser::StopDetection, "StopDetection"},
+        {410, &IUser::GetTagInfo, "GetTagInfo"},
+        {411, &IUser::AttachActivateEvent, "AttachActivateEvent"},
+        {412, &IUser::AttachDeactivateEvent, "AttachDeactivateEvent"},
+        {1000, nullptr, "ReadMifare"},
+        {1001, nullptr, "WriteMifare"},
+        {1300, &IUser::SendCommandByPassThrough, "SendCommandByPassThrough"},
+        {1301, nullptr, "KeepPassThroughSession"},
+        {1302, nullptr, "ReleasePassThroughSession"},
+    };
+    RegisterHandlers(functions);
+
+    availability_change_event = service_context.CreateEvent("IUser:AvailabilityChangeEvent");
+
+    for (u32 device_index = 0; device_index < 10; device_index++) {
+        devices[device_index] =
+            std::make_shared<NfcDevice>(Core::HID::IndexToNpadIdType(device_index), system,
+                                        service_context, availability_change_event);
+    }
+}
+
+IUser ::~IUser() {
+    availability_change_event->Close();
+}
+
+void IUser::Initialize(Kernel::HLERequestContext& ctx) {
+    LOG_INFO(Service_NFC, "called");
+
+    state = State::Initialized;
+
+    for (auto& device : devices) {
+        device->Initialize();
+    }
+
+    IPC::ResponseBuilder rb{ctx, 2, 0};
+    rb.Push(ResultSuccess);
+}
+
+void IUser::Finalize(Kernel::HLERequestContext& ctx) {
+    LOG_INFO(Service_NFC, "called");
+
+    state = State::NonInitialized;
+
+    for (auto& device : devices) {
+        device->Finalize();
+    }
+
+    IPC::ResponseBuilder rb{ctx, 2};
+    rb.Push(ResultSuccess);
+}
+
+void IUser::GetState(Kernel::HLERequestContext& ctx) {
+    LOG_DEBUG(Service_NFC, "called");
+
+    IPC::ResponseBuilder rb{ctx, 3};
+    rb.Push(ResultSuccess);
+    rb.PushEnum(state);
+}
+
+void IUser::IsNfcEnabled(Kernel::HLERequestContext& ctx) {
+    LOG_DEBUG(Service_NFC, "called");
+
+    IPC::ResponseBuilder rb{ctx, 3};
+    rb.Push(ResultSuccess);
+    rb.Push(state != State::NonInitialized);
+}
+
+void IUser::ListDevices(Kernel::HLERequestContext& ctx) {
+    LOG_INFO(Service_NFC, "called");
+
+    if (state == State::NonInitialized) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(NfcDisabled);
+        return;
+    }
+
+    if (!ctx.CanWriteBuffer()) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(InvalidArgument);
+        return;
+    }
+
+    if (ctx.GetWriteBufferSize() == 0) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(InvalidArgument);
+        return;
+    }
+
+    std::vector<u64> nfp_devices;
+    const std::size_t max_allowed_devices = ctx.GetWriteBufferNumElements<u64>();
+
+    for (auto& device : devices) {
+        if (nfp_devices.size() >= max_allowed_devices) {
+            continue;
+        }
+        if (device->GetCurrentState() != NFP::DeviceState::Unavailable) {
+            nfp_devices.push_back(device->GetHandle());
+        }
+    }
+
+    if (nfp_devices.empty()) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(DeviceNotFound);
+        return;
+    }
+
+    ctx.WriteBuffer(nfp_devices);
+
+    IPC::ResponseBuilder rb{ctx, 3};
+    rb.Push(ResultSuccess);
+    rb.Push(static_cast<s32>(nfp_devices.size()));
+}
+
+void IUser::GetDeviceState(Kernel::HLERequestContext& ctx) {
+    IPC::RequestParser rp{ctx};
+    const auto device_handle{rp.Pop<u64>()};
+    LOG_DEBUG(Service_NFC, "called, device_handle={}", device_handle);
+
+    auto device = GetNfcDevice(device_handle);
+
+    if (!device.has_value()) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(DeviceNotFound);
+        return;
+    }
+
+    IPC::ResponseBuilder rb{ctx, 3};
+    rb.Push(ResultSuccess);
+    rb.PushEnum(device.value()->GetCurrentState());
+}
+
+void IUser::GetNpadId(Kernel::HLERequestContext& ctx) {
+    IPC::RequestParser rp{ctx};
+    const auto device_handle{rp.Pop<u64>()};
+    LOG_DEBUG(Service_NFC, "called, device_handle={}", device_handle);
+
+    if (state == State::NonInitialized) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(NfcDisabled);
+        return;
+    }
+
+    auto device = GetNfcDevice(device_handle);
+
+    if (!device.has_value()) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(DeviceNotFound);
+        return;
+    }
+
+    IPC::ResponseBuilder rb{ctx, 3};
+    rb.Push(ResultSuccess);
+    rb.PushEnum(device.value()->GetNpadId());
+}
+
+void IUser::AttachAvailabilityChangeEvent(Kernel::HLERequestContext& ctx) {
+    LOG_INFO(Service_NFC, "called");
+
+    if (state == State::NonInitialized) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(NfcDisabled);
+        return;
+    }
+
+    IPC::ResponseBuilder rb{ctx, 2, 1};
+    rb.Push(ResultSuccess);
+    rb.PushCopyObjects(availability_change_event->GetReadableEvent());
+}
+
+void IUser::StartDetection(Kernel::HLERequestContext& ctx) {
+    IPC::RequestParser rp{ctx};
+    const auto device_handle{rp.Pop<u64>()};
+    const auto nfp_protocol{rp.Pop<s32>()};
+    LOG_INFO(Service_NFC, "called, device_handle={}, nfp_protocol={}", device_handle, nfp_protocol);
+
+    if (state == State::NonInitialized) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(NfcDisabled);
+        return;
+    }
+
+    auto device = GetNfcDevice(device_handle);
+
+    if (!device.has_value()) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(DeviceNotFound);
+        return;
+    }
+
+    const auto result = device.value()->StartDetection(nfp_protocol);
+    IPC::ResponseBuilder rb{ctx, 2};
+    rb.Push(result);
+}
+
+void IUser::StopDetection(Kernel::HLERequestContext& ctx) {
+    IPC::RequestParser rp{ctx};
+    const auto device_handle{rp.Pop<u64>()};
+    LOG_INFO(Service_NFC, "called, device_handle={}", device_handle);
+
+    if (state == State::NonInitialized) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(NfcDisabled);
+        return;
+    }
+
+    auto device = GetNfcDevice(device_handle);
+
+    if (!device.has_value()) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(DeviceNotFound);
+        return;
+    }
+
+    const auto result = device.value()->StopDetection();
+    IPC::ResponseBuilder rb{ctx, 2};
+    rb.Push(result);
+}
+
+void IUser::GetTagInfo(Kernel::HLERequestContext& ctx) {
+    IPC::RequestParser rp{ctx};
+    const auto device_handle{rp.Pop<u64>()};
+    LOG_INFO(Service_NFC, "called, device_handle={}", device_handle);
+
+    if (state == State::NonInitialized) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(NfcDisabled);
+        return;
+    }
+
+    auto device = GetNfcDevice(device_handle);
+
+    if (!device.has_value()) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(DeviceNotFound);
+        return;
+    }
+
+    NFP::TagInfo tag_info{};
+    const auto result = device.value()->GetTagInfo(tag_info);
+    ctx.WriteBuffer(tag_info);
+    IPC::ResponseBuilder rb{ctx, 2};
+    rb.Push(result);
+}
+
+void IUser::AttachActivateEvent(Kernel::HLERequestContext& ctx) {
+    IPC::RequestParser rp{ctx};
+    const auto device_handle{rp.Pop<u64>()};
+    LOG_DEBUG(Service_NFC, "called, device_handle={}", device_handle);
+
+    if (state == State::NonInitialized) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(NfcDisabled);
+        return;
+    }
+
+    auto device = GetNfcDevice(device_handle);
+
+    if (!device.has_value()) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(DeviceNotFound);
+        return;
+    }
+
+    IPC::ResponseBuilder rb{ctx, 2, 1};
+    rb.Push(ResultSuccess);
+    rb.PushCopyObjects(device.value()->GetActivateEvent());
+}
+
+void IUser::AttachDeactivateEvent(Kernel::HLERequestContext& ctx) {
+    IPC::RequestParser rp{ctx};
+    const auto device_handle{rp.Pop<u64>()};
+    LOG_DEBUG(Service_NFC, "called, device_handle={}", device_handle);
+
+    if (state == State::NonInitialized) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(NfcDisabled);
+        return;
+    }
+
+    auto device = GetNfcDevice(device_handle);
+
+    if (!device.has_value()) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(DeviceNotFound);
+        return;
+    }
+
+    IPC::ResponseBuilder rb{ctx, 2, 1};
+    rb.Push(ResultSuccess);
+    rb.PushCopyObjects(device.value()->GetDeactivateEvent());
+}
+
+void IUser::SendCommandByPassThrough(Kernel::HLERequestContext& ctx) {
+    IPC::RequestParser rp{ctx};
+    const auto device_handle{rp.Pop<u64>()};
+    const auto timeout{rp.PopRaw<Time::Clock::TimeSpanType>()};
+    const auto command_data{ctx.ReadBuffer()};
+
+    LOG_INFO(Service_NFC, "(STUBBED) called, device_handle={}, timeout={}, data_size={}",
+             device_handle, timeout.ToSeconds(), command_data.size());
+
+    if (state == State::NonInitialized) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(NfcDisabled);
+        return;
+    }
+
+    auto device = GetNfcDevice(device_handle);
+
+    if (!device.has_value()) {
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(DeviceNotFound);
+        return;
+    }
+
+    std::vector<u8> out_data(1);
+    // TODO: Request data from nfc device
+    ctx.WriteBuffer(out_data);
+
+    IPC::ResponseBuilder rb{ctx, 3};
+    rb.Push(ResultSuccess);
+    rb.Push(static_cast<u32>(out_data.size()));
+}
+
+std::optional<std::shared_ptr<NfcDevice>> IUser::GetNfcDevice(u64 handle) {
+    for (auto& device : devices) {
+        if (device->GetHandle() == handle) {
+            return device;
+        }
+    }
+    return std::nullopt;
+}
+
+} // namespace Service::NFC

src/core/hle/service/nfc/nfc_user.h

@@ -0,0 +1,52 @@
+// SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#pragma once
+
+#include <array>
+#include <memory>
+#include <optional>
+
+#include "core/hle/service/kernel_helpers.h"
+#include "core/hle/service/service.h"
+
+namespace Service::NFC {
+class NfcDevice;
+
+class IUser final : public ServiceFramework<IUser> {
+public:
+    explicit IUser(Core::System& system_);
+    ~IUser();
+
+private:
+    enum class State : u32 {
+        NonInitialized,
+        Initialized,
+    };
+
+    void Initialize(Kernel::HLERequestContext& ctx);
+    void Finalize(Kernel::HLERequestContext& ctx);
+    void GetState(Kernel::HLERequestContext& ctx);
+    void IsNfcEnabled(Kernel::HLERequestContext& ctx);
+    void ListDevices(Kernel::HLERequestContext& ctx);
+    void GetDeviceState(Kernel::HLERequestContext& ctx);
+    void GetNpadId(Kernel::HLERequestContext& ctx);
+    void AttachAvailabilityChangeEvent(Kernel::HLERequestContext& ctx);
+    void StartDetection(Kernel::HLERequestContext& ctx);
+    void StopDetection(Kernel::HLERequestContext& ctx);
+    void GetTagInfo(Kernel::HLERequestContext& ctx);
+    void AttachActivateEvent(Kernel::HLERequestContext& ctx);
+    void AttachDeactivateEvent(Kernel::HLERequestContext& ctx);
+    void SendCommandByPassThrough(Kernel::HLERequestContext& ctx);
+
+    std::optional<std::shared_ptr<NfcDevice>> GetNfcDevice(u64 handle);
+
+    KernelHelpers::ServiceContext service_context;
+
+    std::array<std::shared_ptr<NfcDevice>, 10> devices{};
+
+    State state{State::NonInitialized};
+    Kernel::KEvent* availability_change_event;
+};
+
+} // namespace Service::NFC

src/core/hle/service/nfp/amiibo_crypto.cpp

@@ -12,7 +12,6 @@
 #include "common/fs/fs.h"
 #include "common/fs/path_util.h"
 #include "common/logging/log.h"
-#include "core/hle/service/mii/mii_manager.h"
 #include "core/hle/service/nfp/amiibo_crypto.h"
 
 namespace Service::NFP::AmiiboCrypto {

src/core/hle/service/nfp/nfp_device.cpp

@@ -2,10 +2,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 #include <array>
-#include <atomic>
 
-#include "common/fs/file.h"
-#include "common/fs/path_util.h"
 #include "common/input.h"
 #include "common/logging/log.h"
 #include "common/string_util.h"
@@ -19,7 +16,6 @@
 #include "core/hle/service/mii/mii_manager.h"
 #include "core/hle/service/mii/types.h"
 #include "core/hle/service/nfp/amiibo_crypto.h"
-#include "core/hle/service/nfp/nfp.h"
 #include "core/hle/service/nfp/nfp_device.h"
 #include "core/hle/service/nfp/nfp_result.h"
 #include "core/hle/service/nfp/nfp_user.h"
@@ -49,6 +45,8 @@ NfpDevice::NfpDevice(Core::HID::NpadIdType npad_id_, Core::System& system_,
 }
 
 NfpDevice::~NfpDevice() {
+    activate_event->Close();
+    deactivate_event->Close();
     if (!is_controller_set) {
         return;
     }

src/core/hle/service/nfp/nfp_device.h

@@ -3,11 +3,10 @@
 
 #pragma once
 
-#include <array>
 #include <span>
 #include <vector>
 
-#include "common/common_funcs.h"
+#include "common/common_types.h"
 #include "core/hle/service/kernel_helpers.h"
 #include "core/hle/service/nfp/nfp_types.h"
 #include "core/hle/service/service.h"

src/core/hle/service/nfp/nfp_user.cpp

@@ -1,9 +1,6 @@
 // SPDX-FileCopyrightText: Copyright 2018 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
-#include <array>
-#include <atomic>
-
 #include "common/logging/log.h"
 #include "core/core.h"
 #include "core/hid/hid_types.h"
@@ -55,8 +52,12 @@ IUser::IUser(Core::System& system_)
     }
 }
 
+IUser ::~IUser() {
+    availability_change_event->Close();
+}
+
 void IUser::Initialize(Kernel::HLERequestContext& ctx) {
-    LOG_INFO(Service_NFC, "called");
+    LOG_INFO(Service_NFP, "called");
 
     state = State::Initialized;
 
@@ -64,7 +65,7 @@ void IUser::Initialize(Kernel::HLERequestContext& ctx) {
         device->Initialize();
     }
 
-    IPC::ResponseBuilder rb{ctx, 2, 0};
+    IPC::ResponseBuilder rb{ctx, 2};
     rb.Push(ResultSuccess);
 }
 
@@ -103,9 +104,9 @@ void IUser::ListDevices(Kernel::HLERequestContext& ctx) {
     }
 
     std::vector<u64> nfp_devices;
-    const std::size_t max_allowed_devices = ctx.GetWriteBufferSize() / sizeof(u64);
+    const std::size_t max_allowed_devices = ctx.GetWriteBufferNumElements<u64>();
 
-    for (auto& device : devices) {
+    for (const auto& device : devices) {
         if (nfp_devices.size() >= max_allowed_devices) {
             continue;
         }
@@ -114,7 +115,7 @@ void IUser::ListDevices(Kernel::HLERequestContext& ctx) {
         }
     }
 
-    if (nfp_devices.size() == 0) {
+    if (nfp_devices.empty()) {
         IPC::ResponseBuilder rb{ctx, 2};
         rb.Push(DeviceNotFound);
         return;
@@ -551,9 +552,9 @@ void IUser::AttachDeactivateEvent(Kernel::HLERequestContext& ctx) {
 }
 
 void IUser::GetState(Kernel::HLERequestContext& ctx) {
-    LOG_DEBUG(Service_NFC, "called");
+    LOG_DEBUG(Service_NFP, "called");
 
-    IPC::ResponseBuilder rb{ctx, 3, 0};
+    IPC::ResponseBuilder rb{ctx, 3};
     rb.Push(ResultSuccess);
     rb.PushEnum(state);
 }

src/core/hle/service/nfp/nfp_user.h

@@ -3,6 +3,10 @@
 
 #pragma once
 
+#include <array>
+#include <memory>
+#include <optional>
+
 #include "core/hle/service/kernel_helpers.h"
 #include "core/hle/service/service.h"
 
@@ -12,6 +16,7 @@ class NfpDevice;
 class IUser final : public ServiceFramework<IUser> {
 public:
     explicit IUser(Core::System& system_);
+    ~IUser();
 
 private:
     enum class State : u32 {

src/core/hle/service/ns/iplatform_service_manager.cpp

@@ -279,13 +279,10 @@ void IPlatformServiceManager::GetSharedFontInOrderOfPriority(Kernel::HLERequestC
         font_sizes.push_back(region.size);
     }
 
-    // Resize buffers if game requests smaller size output.
-    font_codes.resize(
-        std::min<std::size_t>(font_codes.size(), ctx.GetWriteBufferSize(0) / sizeof(u32)));
-    font_offsets.resize(
-        std::min<std::size_t>(font_offsets.size(), ctx.GetWriteBufferSize(1) / sizeof(u32)));
-    font_sizes.resize(
-        std::min<std::size_t>(font_sizes.size(), ctx.GetWriteBufferSize(2) / sizeof(u32)));
+    // Resize buffers if game requests smaller size output
+    font_codes.resize(std::min(font_codes.size(), ctx.GetWriteBufferNumElements<u32>(0)));
+    font_offsets.resize(std::min(font_offsets.size(), ctx.GetWriteBufferNumElements<u32>(1)));
+    font_sizes.resize(std::min(font_sizes.size(), ctx.GetWriteBufferNumElements<u32>(2)));
 
     ctx.WriteBuffer(font_codes, 0);
     ctx.WriteBuffer(font_offsets, 1);

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

@@ -11,7 +11,6 @@
 #include <vector>
 
 #include "common/common_types.h"
-#include "common/polyfill_thread.h"
 #include "core/hle/result.h"
 #include "core/hle/service/kernel_helpers.h"
 

src/core/hle/service/set/set.cpp

@@ -83,7 +83,7 @@ void PushResponseLanguageCode(Kernel::HLERequestContext& ctx, std::size_t num_la
 }
 
 void GetAvailableLanguageCodesImpl(Kernel::HLERequestContext& ctx, std::size_t max_entries) {
-    const std::size_t requested_amount = ctx.GetWriteBufferSize() / sizeof(LanguageCode);
+    const std::size_t requested_amount = ctx.GetWriteBufferNumElements<LanguageCode>();
     const std::size_t max_amount = std::min(requested_amount, max_entries);
     const std::size_t copy_amount = std::min(available_language_codes.size(), max_amount);
     const std::size_t copy_size = copy_amount * sizeof(LanguageCode);

src/core/internal_network/network_interface.cpp

@@ -9,7 +9,6 @@
 #include "common/bit_cast.h"
 #include "common/common_types.h"
 #include "common/logging/log.h"
-#include "common/polyfill_ranges.h"
 #include "common/settings.h"
 #include "common/string_util.h"
 #include "core/internal_network/network_interface.h"

src/input_common/drivers/gc_adapter.h

@@ -5,10 +5,10 @@
 
 #include <array>
 #include <memory>
+#include <stop_token>
 #include <string>
 #include <thread>
 
-#include "common/polyfill_thread.h"
 #include "input_common/input_engine.h"
 
 struct libusb_context;

src/input_common/drivers/mouse.cpp

@@ -1,6 +1,7 @@
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include <stop_token>
 #include <thread>
 #include <fmt/format.h>
 

src/input_common/drivers/mouse.h

@@ -3,9 +3,9 @@
 
 #pragma once
 
+#include <stop_token>
 #include <thread>
 
-#include "common/polyfill_thread.h"
 #include "common/vector_math.h"
 #include "input_common/input_engine.h"
 

src/input_common/drivers/tas_input.cpp

@@ -2,7 +2,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 #include <cstring>
-#include <sstream>
 #include <fmt/format.h>
 
 #include "common/fs/file.h"

src/shader_recompiler/CMakeLists.txt

@@ -254,7 +254,6 @@ else()
         # Bracket depth determines maximum size of a fold expression in Clang since 9c9974c3ccb6.
         # And this in turns limits the size of a std::array.
         $<$<CXX_COMPILER_ID:Clang>:-fbracket-depth=1024>
-        $<$<CXX_COMPILER_ID:AppleClang>:-fbracket-depth=1024>
     )
 endif()
 

src/shader_recompiler/frontend/ir/opcodes.h

@@ -8,7 +8,6 @@
 
 #include <fmt/format.h>
 
-#include "common/polyfill_ranges.h"
 #include "shader_recompiler/frontend/ir/type.h"
 
 namespace Shader::IR {

src/shader_recompiler/frontend/maxwell/control_flow.cpp

@@ -9,7 +9,6 @@
 
 #include <fmt/format.h>
 
-#include "common/polyfill_ranges.h"
 #include "shader_recompiler/exception.h"
 #include "shader_recompiler/frontend/maxwell/control_flow.h"
 #include "shader_recompiler/frontend/maxwell/decode.h"

src/shader_recompiler/frontend/maxwell/decode.cpp

@@ -7,7 +7,6 @@
 #include <memory>
 
 #include "common/common_types.h"
-#include "common/polyfill_ranges.h"
 #include "shader_recompiler/exception.h"
 #include "shader_recompiler/frontend/maxwell/decode.h"
 #include "shader_recompiler/frontend/maxwell/opcodes.h"

src/shader_recompiler/frontend/maxwell/structured_control_flow.cpp

@@ -12,7 +12,6 @@
 
 #include <boost/intrusive/list.hpp>
 
-#include "common/polyfill_ranges.h"
 #include "shader_recompiler/environment.h"
 #include "shader_recompiler/frontend/ir/basic_block.h"
 #include "shader_recompiler/frontend/ir/ir_emitter.h"

src/shader_recompiler/frontend/maxwell/translate/impl/floating_point_conversion_integer.cpp

@@ -176,13 +176,12 @@ void TranslateF2I(TranslatorVisitor& v, u64 insn, const IR::F16F32F64& src_a) {
         (f2i.src_format == SrcFormat::F64) != (f2i.dest_format == DestFormat::I64);
     if (special_nan_cases) {
         if (f2i.dest_format == DestFormat::I32) {
-            constexpr u32 nan_value = 0x8000'0000U;
             handled_special_case = true;
-            result = IR::U32{v.ir.Select(v.ir.FPIsNan(op_a), v.ir.Imm32(nan_value), result)};
+            result = IR::U32{v.ir.Select(v.ir.FPIsNan(op_a), v.ir.Imm32(0x8000'0000U), result)};
         } else if (f2i.dest_format == DestFormat::I64) {
-            constexpr u64 nan_value = 0x8000'0000'0000'0000ULL;
             handled_special_case = true;
-            result = IR::U64{v.ir.Select(v.ir.FPIsNan(op_a), v.ir.Imm64(nan_value), result)};
+            result = IR::U64{
+                v.ir.Select(v.ir.FPIsNan(op_a), v.ir.Imm64(0x8000'0000'0000'0000UL), result)};
         }
     }
     if (!handled_special_case && is_signed) {

src/video_core/CMakeLists.txt

@@ -28,6 +28,10 @@ add_library(video_core STATIC
     dirty_flags.h
     dma_pusher.cpp
     dma_pusher.h
+    engines/sw_blitter/blitter.cpp
+    engines/sw_blitter/blitter.h
+    engines/sw_blitter/converter.cpp
+    engines/sw_blitter/converter.h
     engines/const_buffer_info.h
     engines/engine_interface.h
     engines/engine_upload.cpp

src/video_core/buffer_cache/buffer_base.h

@@ -535,7 +535,7 @@ private:
         const u64* const state_words = Array<type>();
         const u64 num_query_words = size / BYTES_PER_WORD + 1;
         const u64 word_begin = offset / BYTES_PER_WORD;
-        const u64 word_end = std::min<u64>(word_begin + num_query_words, NumWords());
+        const u64 word_end = std::min(word_begin + num_query_words, NumWords());
         const u64 page_limit = Common::DivCeil(offset + size, BYTES_PER_PAGE);
         u64 page_index = (offset / BYTES_PER_PAGE) % PAGES_PER_WORD;
         for (u64 word_index = word_begin; word_index < word_end; ++word_index, page_index = 0) {

src/video_core/buffer_cache/buffer_cache.h

@@ -19,7 +19,6 @@
 #include "common/literals.h"
 #include "common/lru_cache.h"
 #include "common/microprofile.h"
-#include "common/polyfill_ranges.h"
 #include "common/settings.h"
 #include "core/memory.h"
 #include "video_core/buffer_cache/buffer_base.h"
@@ -1743,12 +1742,12 @@ bool BufferCache<P>::InlineMemory(VAddr dest_address, size_t copy_size,
     SynchronizeBuffer(buffer, dest_address, static_cast<u32>(copy_size));
 
     if constexpr (USE_MEMORY_MAPS) {
+        auto upload_staging = runtime.UploadStagingBuffer(copy_size);
         std::array copies{BufferCopy{
-            .src_offset = 0,
+            .src_offset = upload_staging.offset,
             .dst_offset = buffer.Offset(dest_address),
             .size = copy_size,
         }};
-        auto upload_staging = runtime.UploadStagingBuffer(copy_size);
         u8* const src_pointer = upload_staging.mapped_span.data();
         std::memcpy(src_pointer, inlined_buffer.data(), copy_size);
         runtime.CopyBuffer(buffer, upload_staging.buffer, copies);

src/video_core/control/channel_state.cpp

@@ -20,7 +20,7 @@ void ChannelState::Init(Core::System& system, GPU& gpu) {
     ASSERT(memory_manager);
     dma_pusher = std::make_unique<Tegra::DmaPusher>(system, gpu, *memory_manager, *this);
     maxwell_3d = std::make_unique<Engines::Maxwell3D>(system, *memory_manager);
-    fermi_2d = std::make_unique<Engines::Fermi2D>();
+    fermi_2d = std::make_unique<Engines::Fermi2D>(*memory_manager);
     kepler_compute = std::make_unique<Engines::KeplerCompute>(system, *memory_manager);
     maxwell_dma = std::make_unique<Engines::MaxwellDMA>(system, *memory_manager);
     kepler_memory = std::make_unique<Engines::KeplerMemory>(system, *memory_manager);

src/video_core/control/channel_state_cache.h

@@ -35,6 +35,8 @@ public:
     explicit ChannelInfo(Tegra::Control::ChannelState& state);
     ChannelInfo(const ChannelInfo& state) = delete;
     ChannelInfo& operator=(const ChannelInfo&) = delete;
+    ChannelInfo(ChannelInfo&& other) = default;
+    ChannelInfo& operator=(ChannelInfo&& other) = default;
 
     Tegra::Engines::Maxwell3D& maxwell3d;
     Tegra::Engines::KeplerCompute& kepler_compute;

src/video_core/engines/engine_upload.cpp

@@ -51,11 +51,11 @@ void State::ProcessData(std::span<const u8> read_buffer) {
         } else {
             for (u32 line = 0; line < regs.line_count; ++line) {
                 const GPUVAddr dest_line = address + static_cast<size_t>(line) * regs.dest.pitch;
-                memory_manager.WriteBlockUnsafe(
-                    dest_line, read_buffer.data() + static_cast<size_t>(line) * regs.line_length_in,
-                    regs.line_length_in);
+                std::span<const u8> buffer(read_buffer.data() +
+                                               static_cast<size_t>(line) * regs.line_length_in,
+                                           regs.line_length_in);
+                rasterizer->AccelerateInlineToMemory(dest_line, regs.line_length_in, buffer);
             }
-            memory_manager.InvalidateRegion(address, regs.dest.pitch * regs.line_count);
         }
     } else {
         u32 width = regs.dest.width;

src/video_core/engines/fermi_2d.cpp

@@ -3,17 +3,25 @@
 
 #include "common/assert.h"
 #include "common/logging/log.h"
+#include "common/microprofile.h"
 #include "video_core/engines/fermi_2d.h"
-#include "video_core/memory_manager.h"
+#include "video_core/engines/sw_blitter/blitter.h"
 #include "video_core/rasterizer_interface.h"
 #include "video_core/surface.h"
+#include "video_core/textures/decoders.h"
+
+MICROPROFILE_DECLARE(GPU_BlitEngine);
+MICROPROFILE_DEFINE(GPU_BlitEngine, "GPU", "Blit Engine", MP_RGB(224, 224, 128));
 
 using VideoCore::Surface::BytesPerBlock;
 using VideoCore::Surface::PixelFormatFromRenderTargetFormat;
 
 namespace Tegra::Engines {
 
-Fermi2D::Fermi2D() {
+using namespace Texture;
+
+Fermi2D::Fermi2D(MemoryManager& memory_manager_) {
+    sw_blitter = std::make_unique<Blitter::SoftwareBlitEngine>(memory_manager_);
     // Nvidia's OpenGL driver seems to assume these values
     regs.src.depth = 1;
     regs.dst.depth = 1;
@@ -42,6 +50,7 @@ void Fermi2D::CallMultiMethod(u32 method, const u32* base_start, u32 amount, u32
 }
 
 void Fermi2D::Blit() {
+    MICROPROFILE_SCOPE(GPU_BlitEngine);
     LOG_DEBUG(HW_GPU, "called. source address=0x{:x}, destination address=0x{:x}",
               regs.src.Address(), regs.dst.Address());
 
@@ -52,9 +61,16 @@ void Fermi2D::Blit() {
     UNIMPLEMENTED_IF_MSG(regs.clip_enable != 0, "Clipped blit enabled");
 
     const auto& args = regs.pixels_from_memory;
+    constexpr s64 null_derivate = 1ULL << 32;
+    Surface src = regs.src;
+    const auto bytes_per_pixel = BytesPerBlock(PixelFormatFromRenderTargetFormat(src.format));
+    const bool delegate_to_gpu = src.width > 512 && src.height > 512 && bytes_per_pixel <= 8 &&
+                                 src.format != regs.dst.format;
     Config config{
         .operation = regs.operation,
         .filter = args.sample_mode.filter,
+        .must_accelerate =
+            args.du_dx != null_derivate || args.dv_dy != null_derivate || delegate_to_gpu,
         .dst_x0 = args.dst_x0,
         .dst_y0 = args.dst_y0,
         .dst_x1 = args.dst_x0 + args.dst_width,
@@ -64,8 +80,7 @@ void Fermi2D::Blit() {
         .src_x1 = static_cast<s32>((args.du_dx * args.dst_width + args.src_x0) >> 32),
         .src_y1 = static_cast<s32>((args.dv_dy * args.dst_height + args.src_y0) >> 32),
     };
-    Surface src = regs.src;
-    const auto bytes_per_pixel = BytesPerBlock(PixelFormatFromRenderTargetFormat(src.format));
+
     const auto need_align_to_pitch =
         src.linear == Tegra::Engines::Fermi2D::MemoryLayout::Pitch &&
         static_cast<s32>(src.width) == config.src_x1 &&
@@ -78,8 +93,9 @@ void Fermi2D::Blit() {
         config.src_x1 -= config.src_x0;
         config.src_x0 = 0;
     }
+
     if (!rasterizer->AccelerateSurfaceCopy(src, regs.dst, config)) {
-        UNIMPLEMENTED();
+        sw_blitter->Blit(src, regs.dst, config);
     }
 }
 

src/video_core/engines/fermi_2d.h

@@ -5,6 +5,7 @@
 
 #include <array>
 #include <cstddef>
+#include <memory>
 #include "common/bit_field.h"
 #include "common/common_funcs.h"
 #include "common/common_types.h"
@@ -21,6 +22,10 @@ class RasterizerInterface;
 
 namespace Tegra::Engines {
 
+namespace Blitter {
+class SoftwareBlitEngine;
+}
+
 /**
  * This Engine is known as G80_2D. Documentation can be found in:
  * https://github.com/envytools/envytools/blob/master/rnndb/graph/g80_2d.xml
@@ -32,7 +37,7 @@ namespace Tegra::Engines {
 
 class Fermi2D final : public EngineInterface {
 public:
-    explicit Fermi2D();
+    explicit Fermi2D(MemoryManager& memory_manager_);
     ~Fermi2D() override;
 
     /// Binds a rasterizer to this engine.
@@ -286,6 +291,7 @@ public:
     struct Config {
         Operation operation;
         Filter filter;
+        bool must_accelerate;
         s32 dst_x0;
         s32 dst_y0;
         s32 dst_x1;
@@ -298,6 +304,7 @@ public:
 
 private:
     VideoCore::RasterizerInterface* rasterizer = nullptr;
+    std::unique_ptr<Blitter::SoftwareBlitEngine> sw_blitter;
 
     /// Performs the copy from the source surface to the destination surface as configured in the
     /// registers.

src/video_core/engines/maxwell_3d.cpp

@@ -126,6 +126,7 @@ void Maxwell3D::InitializeRegisterDefaults() {
     draw_command[MAXWELL3D_REG_INDEX(draw_inline_index)] = true;
     draw_command[MAXWELL3D_REG_INDEX(inline_index_2x16.even)] = true;
     draw_command[MAXWELL3D_REG_INDEX(inline_index_4x8.index0)] = true;
+    draw_command[MAXWELL3D_REG_INDEX(draw.instance_id)] = true;
 }
 
 void Maxwell3D::ProcessMacro(u32 method, const u32* base_start, u32 amount, bool is_last_call) {
@@ -249,9 +250,6 @@ void Maxwell3D::ProcessMethodCall(u32 method, u32 argument, u32 nonshadow_argume
         return;
     case MAXWELL3D_REG_INDEX(fragment_barrier):
         return rasterizer->FragmentBarrier();
-    case MAXWELL3D_REG_INDEX(invalidate_texture_data_cache):
-        rasterizer->InvalidateGPUCache();
-        return rasterizer->WaitForIdle();
     case MAXWELL3D_REG_INDEX(tiled_cache_barrier):
         return rasterizer->TiledCacheBarrier();
     }
@@ -288,31 +286,58 @@ void Maxwell3D::CallMethod(u32 method, u32 method_argument, bool is_last_call) {
     ASSERT_MSG(method < Regs::NUM_REGS,
                "Invalid Maxwell3D register, increase the size of the Regs structure");
 
+    const u32 argument = ProcessShadowRam(method, method_argument);
+    ProcessDirtyRegisters(method, argument);
+
     if (draw_command[method]) {
         regs.reg_array[method] = method_argument;
         deferred_draw_method.push_back(method);
-        auto u32_to_u8 = [&](const u32 argument) {
-            inline_index_draw_indexes.push_back(static_cast<u8>(argument & 0x000000ff));
-            inline_index_draw_indexes.push_back(static_cast<u8>((argument & 0x0000ff00) >> 8));
-            inline_index_draw_indexes.push_back(static_cast<u8>((argument & 0x00ff0000) >> 16));
-            inline_index_draw_indexes.push_back(static_cast<u8>((argument & 0xff000000) >> 24));
+        auto update_inline_index = [&](const u32 index) {
+            inline_index_draw_indexes.push_back(static_cast<u8>(index & 0x000000ff));
+            inline_index_draw_indexes.push_back(static_cast<u8>((index & 0x0000ff00) >> 8));
+            inline_index_draw_indexes.push_back(static_cast<u8>((index & 0x00ff0000) >> 16));
+            inline_index_draw_indexes.push_back(static_cast<u8>((index & 0xff000000) >> 24));
+            draw_mode = DrawMode::InlineIndex;
         };
-        if (MAXWELL3D_REG_INDEX(draw_inline_index) == method) {
-            u32_to_u8(method_argument);
-        } else if (MAXWELL3D_REG_INDEX(inline_index_2x16.even) == method) {
-            u32_to_u8(regs.inline_index_2x16.even);
-            u32_to_u8(regs.inline_index_2x16.odd);
-        } else if (MAXWELL3D_REG_INDEX(inline_index_4x8.index0) == method) {
-            u32_to_u8(regs.inline_index_4x8.index0);
-            u32_to_u8(regs.inline_index_4x8.index1);
-            u32_to_u8(regs.inline_index_4x8.index2);
-            u32_to_u8(regs.inline_index_4x8.index3);
+        switch (method) {
+        case MAXWELL3D_REG_INDEX(draw.end):
+            switch (draw_mode) {
+            case DrawMode::General:
+                ProcessDraw(1);
+                break;
+            case DrawMode::InlineIndex:
+                regs.index_buffer.count = static_cast<u32>(inline_index_draw_indexes.size() / 4);
+                regs.index_buffer.format = Regs::IndexFormat::UnsignedInt;
+                ProcessDraw(1);
+                inline_index_draw_indexes.clear();
+                break;
+            case DrawMode::Instance:
+                break;
+            }
+            break;
+        case MAXWELL3D_REG_INDEX(draw_inline_index):
+            update_inline_index(method_argument);
+            break;
+        case MAXWELL3D_REG_INDEX(inline_index_2x16.even):
+            update_inline_index(regs.inline_index_2x16.even);
+            update_inline_index(regs.inline_index_2x16.odd);
+            break;
+        case MAXWELL3D_REG_INDEX(inline_index_4x8.index0):
+            update_inline_index(regs.inline_index_4x8.index0);
+            update_inline_index(regs.inline_index_4x8.index1);
+            update_inline_index(regs.inline_index_4x8.index2);
+            update_inline_index(regs.inline_index_4x8.index3);
+            break;
+        case MAXWELL3D_REG_INDEX(draw.instance_id):
+            draw_mode =
+                (regs.draw.instance_id == Maxwell3D::Regs::Draw::InstanceId::Subsequent) ||
+                        (regs.draw.instance_id == Maxwell3D::Regs::Draw::InstanceId::Unchanged)
+                    ? DrawMode::Instance
+                    : DrawMode::General;
+            break;
         }
     } else {
         ProcessDeferredDraw();
-
-        const u32 argument = ProcessShadowRam(method, method_argument);
-        ProcessDirtyRegisters(method, argument);
         ProcessMethodCall(method, argument, method_argument, is_last_call);
     }
 }
@@ -511,10 +536,7 @@ void Maxwell3D::ProcessCounterReset() {
 
 void Maxwell3D::ProcessSyncPoint() {
     const u32 sync_point = regs.sync_info.sync_point.Value();
-    const u32 cache_flush = regs.sync_info.clean_l2.Value();
-    if (cache_flush != 0) {
-        rasterizer->InvalidateGPUCache();
-    }
+    [[maybe_unused]] const u32 cache_flush = regs.sync_info.clean_l2.Value();
     rasterizer->SignalSyncPoint(sync_point);
 }
 
@@ -626,57 +648,27 @@ void Maxwell3D::ProcessDraw(u32 instance_count) {
 }
 
 void Maxwell3D::ProcessDeferredDraw() {
-    if (deferred_draw_method.empty()) {
+    if (draw_mode != DrawMode::Instance || deferred_draw_method.empty()) {
         return;
     }
 
-    enum class DrawMode {
-        Undefined,
-        General,
-        Instance,
-    };
-    DrawMode draw_mode{DrawMode::Undefined};
     u32 method_count = static_cast<u32>(deferred_draw_method.size());
-    u32 method = deferred_draw_method[method_count - 1];
-    if (MAXWELL3D_REG_INDEX(draw.end) != method) {
-        return;
-    }
-    draw_mode = (regs.draw.instance_id == Maxwell3D::Regs::Draw::InstanceId::Subsequent) ||
-                        (regs.draw.instance_id == Maxwell3D::Regs::Draw::InstanceId::Unchanged)
-                    ? DrawMode::Instance
-                    : DrawMode::General;
-    u32 instance_count = 0;
-    if (draw_mode == DrawMode::Instance) {
-        u32 vertex_buffer_count = 0;
-        u32 index_buffer_count = 0;
-        for (u32 index = 0; index < method_count; ++index) {
-            method = deferred_draw_method[index];
-            if (method == MAXWELL3D_REG_INDEX(vertex_buffer.count)) {
-                instance_count = ++vertex_buffer_count;
-            } else if (method == MAXWELL3D_REG_INDEX(index_buffer.count)) {
-                instance_count = ++index_buffer_count;
-            }
-        }
-        ASSERT_MSG(!(vertex_buffer_count && index_buffer_count),
-                   "Instance both indexed and direct?");
-    } else {
-        instance_count = 1;
-        for (u32 index = 0; index < method_count; ++index) {
-            method = deferred_draw_method[index];
-            if (MAXWELL3D_REG_INDEX(draw_inline_index) == method ||
-                MAXWELL3D_REG_INDEX(inline_index_2x16.even) == method ||
-                MAXWELL3D_REG_INDEX(inline_index_4x8.index0) == method) {
-                regs.index_buffer.count = static_cast<u32>(inline_index_draw_indexes.size() / 4);
-                regs.index_buffer.format = Regs::IndexFormat::UnsignedInt;
-                break;
-            }
+    u32 instance_count = 1;
+    u32 vertex_buffer_count = 0;
+    u32 index_buffer_count = 0;
+    for (u32 index = 0; index < method_count; ++index) {
+        u32 method = deferred_draw_method[index];
+        if (method == MAXWELL3D_REG_INDEX(vertex_buffer.count)) {
+            instance_count = ++vertex_buffer_count;
+        } else if (method == MAXWELL3D_REG_INDEX(index_buffer.count)) {
+            instance_count = ++index_buffer_count;
         }
     }
+    ASSERT_MSG(!(vertex_buffer_count && index_buffer_count), "Instance both indexed and direct?");
 
     ProcessDraw(instance_count);
 
     deferred_draw_method.clear();
-    inline_index_draw_indexes.clear();
 }
 
 } // namespace Tegra::Engines

src/video_core/engines/maxwell_3d.h

@@ -3148,10 +3148,12 @@ private:
     /// Handles use of topology overrides (e.g., to avoid using a topology assigned from a macro)
     void ProcessTopologyOverride();
 
-    void ProcessDraw(u32 instance_count = 1);
-
+    /// Handles deferred draw(e.g., instance draw).
     void ProcessDeferredDraw();
 
+    /// Handles a draw.
+    void ProcessDraw(u32 instance_count = 1);
+
     /// Returns a query's value or an empty object if the value will be deferred through a cache.
     std::optional<u64> GetQueryResult();
 
@@ -3178,6 +3180,8 @@ private:
 
     std::array<bool, Regs::NUM_REGS> draw_command{};
     std::vector<u32> deferred_draw_method;
+    enum class DrawMode : u32 { General = 0, Instance, InlineIndex };
+    DrawMode draw_mode{DrawMode::General};
 };
 
 #define ASSERT_REG_POSITION(field_name, position)                                                  \

src/video_core/engines/maxwell_dma.cpp

@@ -62,7 +62,8 @@ void MaxwellDMA::Launch() {
 
         if (!is_src_pitch && !is_dst_pitch) {
             // If both the source and the destination are in block layout, assert.
-            UNIMPLEMENTED_MSG("Tiled->Tiled DMA transfers are not yet implemented");
+            CopyBlockLinearToBlockLinear();
+            ReleaseSemaphore();
             return;
         }
 
@@ -291,6 +292,70 @@ void MaxwellDMA::FastCopyBlockLinearToPitch() {
     memory_manager.WriteBlock(regs.offset_out, write_buffer.data(), dst_size);
 }
 
+void MaxwellDMA::CopyBlockLinearToBlockLinear() {
+    UNIMPLEMENTED_IF(regs.src_params.block_size.width != 0);
+
+    const bool is_remapping = regs.launch_dma.remap_enable != 0;
+
+    // Deswizzle the input and copy it over.
+    const Parameters& src = regs.src_params;
+    const Parameters& dst = regs.dst_params;
+
+    const u32 num_remap_components = regs.remap_const.num_dst_components_minus_one + 1;
+    const u32 remap_components_size = regs.remap_const.component_size_minus_one + 1;
+
+    const u32 base_bpp = !is_remapping ? 1U : num_remap_components * remap_components_size;
+
+    u32 src_width = src.width;
+    u32 dst_width = dst.width;
+    u32 x_elements = regs.line_length_in;
+    u32 src_x_offset = src.origin.x;
+    u32 dst_x_offset = dst.origin.x;
+    u32 bpp_shift = 0U;
+    if (!is_remapping) {
+        bpp_shift = Common::FoldRight(
+            4U, [](u32 x, u32 y) { return std::min(x, static_cast<u32>(std::countr_zero(y))); },
+            src_width, dst_width, x_elements, src_x_offset, dst_x_offset,
+            static_cast<u32>(regs.offset_in), static_cast<u32>(regs.offset_out));
+        src_width >>= bpp_shift;
+        dst_width >>= bpp_shift;
+        x_elements >>= bpp_shift;
+        src_x_offset >>= bpp_shift;
+        dst_x_offset >>= bpp_shift;
+    }
+
+    const u32 bytes_per_pixel = base_bpp << bpp_shift;
+    const size_t src_size = CalculateSize(true, bytes_per_pixel, src_width, src.height, src.depth,
+                                          src.block_size.height, src.block_size.depth);
+    const size_t dst_size = CalculateSize(true, bytes_per_pixel, dst_width, dst.height, dst.depth,
+                                          dst.block_size.height, dst.block_size.depth);
+
+    const u32 pitch = x_elements * bytes_per_pixel;
+    const size_t mid_buffer_size = pitch * regs.line_count;
+
+    if (read_buffer.size() < src_size) {
+        read_buffer.resize(src_size);
+    }
+    if (write_buffer.size() < dst_size) {
+        write_buffer.resize(dst_size);
+    }
+
+    intermediate_buffer.resize(mid_buffer_size);
+
+    memory_manager.ReadBlock(regs.offset_in, read_buffer.data(), src_size);
+    memory_manager.ReadBlock(regs.offset_out, write_buffer.data(), dst_size);
+
+    UnswizzleSubrect(intermediate_buffer, read_buffer, bytes_per_pixel, src_width, src.height,
+                     src.depth, src_x_offset, src.origin.y, x_elements, regs.line_count,
+                     src.block_size.height, src.block_size.depth, pitch);
+
+    SwizzleSubrect(write_buffer, intermediate_buffer, bytes_per_pixel, dst_width, dst.height,
+                   dst.depth, dst_x_offset, dst.origin.y, x_elements, regs.line_count,
+                   dst.block_size.height, dst.block_size.depth, pitch);
+
+    memory_manager.WriteBlock(regs.offset_out, write_buffer.data(), dst_size);
+}
+
 void MaxwellDMA::ReleaseSemaphore() {
     const auto type = regs.launch_dma.semaphore_type;
     const GPUVAddr address = regs.semaphore.address;

src/video_core/engines/maxwell_dma.h

@@ -223,6 +223,8 @@ private:
 
     void CopyPitchToBlockLinear();
 
+    void CopyBlockLinearToBlockLinear();
+
     void FastCopyBlockLinearToPitch();
 
     void ReleaseSemaphore();
@@ -234,6 +236,7 @@ private:
 
     std::vector<u8> read_buffer;
     std::vector<u8> write_buffer;
+    std::vector<u8> intermediate_buffer;
 
     static constexpr std::size_t NUM_REGS = 0x800;
     struct Regs {

src/video_core/engines/puller.cpp

@@ -118,7 +118,7 @@ void Puller::ProcessSemaphoreRelease() {
     std::function<void()> operation([this, sequence_address, payload] {
         memory_manager.Write<u32>(sequence_address, payload);
     });
-    rasterizer->SyncOperation(std::move(operation));
+    rasterizer->SignalFence(std::move(operation));
 }
 
 void Puller::ProcessSemaphoreAcquire() {
@@ -151,8 +151,8 @@ void Puller::CallPullerMethod(const MethodCall& method_call) {
     case BufferMethods::SemaphoreAddressLow:
     case BufferMethods::SemaphoreSequencePayload:
     case BufferMethods::SyncpointPayload:
-        break;
     case BufferMethods::WrcacheFlush:
+        break;
     case BufferMethods::RefCnt:
         rasterizer->SignalReference();
         break;

src/video_core/engines/sw_blitter/blitter.cpp

@@ -0,0 +1,238 @@
+// SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
+#include <algorithm>
+#include <cmath>
+#include <vector>
+
+#include "video_core/engines/sw_blitter/blitter.h"
+#include "video_core/engines/sw_blitter/converter.h"
+#include "video_core/memory_manager.h"
+#include "video_core/surface.h"
+#include "video_core/textures/decoders.h"
+
+namespace Tegra {
+class MemoryManager;
+}
+
+using VideoCore::Surface::BytesPerBlock;
+using VideoCore::Surface::PixelFormatFromRenderTargetFormat;
+
+namespace Tegra::Engines::Blitter {
+
+using namespace Texture;
+
+namespace {
+
+constexpr size_t ir_components = 4;
+
+void NearestNeighbor(std::span<const u8> input, std::span<u8> output, u32 src_width, u32 src_height,
+                     u32 dst_width, u32 dst_height, size_t bpp) {
+    const size_t dx_du = std::llround((static_cast<f64>(src_width) / dst_width) * (1ULL << 32));
+    const size_t dy_dv = std::llround((static_cast<f64>(src_height) / dst_height) * (1ULL << 32));
+    size_t src_y = 0;
+    for (u32 y = 0; y < dst_height; y++) {
+        size_t src_x = 0;
+        for (u32 x = 0; x < dst_width; x++) {
+            const size_t read_from = ((src_y * src_width + src_x) >> 32) * bpp;
+            const size_t write_to = (y * dst_width + x) * bpp;
+
+            std::memcpy(&output[write_to], &input[read_from], bpp);
+            src_x += dx_du;
+        }
+        src_y += dy_dv;
+    }
+}
+
+void NearestNeighborFast(std::span<const f32> input, std::span<f32> output, u32 src_width,
+                         u32 src_height, u32 dst_width, u32 dst_height) {
+    const size_t dx_du = std::llround((static_cast<f64>(src_width) / dst_width) * (1ULL << 32));
+    const size_t dy_dv = std::llround((static_cast<f64>(src_height) / dst_height) * (1ULL << 32));
+    size_t src_y = 0;
+    for (u32 y = 0; y < dst_height; y++) {
+        size_t src_x = 0;
+        for (u32 x = 0; x < dst_width; x++) {
+            const size_t read_from = ((src_y * src_width + src_x) >> 32) * ir_components;
+            const size_t write_to = (y * dst_width + x) * ir_components;
+
+            std::memcpy(&output[write_to], &input[read_from], sizeof(f32) * ir_components);
+            src_x += dx_du;
+        }
+        src_y += dy_dv;
+    }
+}
+
+void Bilinear(std::span<const f32> input, std::span<f32> output, size_t src_width,
+              size_t src_height, size_t dst_width, size_t dst_height) {
+    const auto bilinear_sample = [](std::span<const f32> x0_y0, std::span<const f32> x1_y0,
+                                    std::span<const f32> x0_y1, std::span<const f32> x1_y1,
+                                    f32 weight_x, f32 weight_y) {
+        std::array<f32, ir_components> result{};
+        for (size_t i = 0; i < ir_components; i++) {
+            const f32 a = std::lerp(x0_y0[i], x1_y0[i], weight_x);
+            const f32 b = std::lerp(x0_y1[i], x1_y1[i], weight_x);
+            result[i] = std::lerp(a, b, weight_y);
+        }
+        return result;
+    };
+    const f32 dx_du =
+        dst_width > 1 ? static_cast<f32>(src_width - 1) / static_cast<f32>(dst_width - 1) : 0.f;
+    const f32 dy_dv =
+        dst_height > 1 ? static_cast<f32>(src_height - 1) / static_cast<f32>(dst_height - 1) : 0.f;
+    for (u32 y = 0; y < dst_height; y++) {
+        for (u32 x = 0; x < dst_width; x++) {
+            const f32 x_low = std::floor(static_cast<f32>(x) * dx_du);
+            const f32 y_low = std::floor(static_cast<f32>(y) * dy_dv);
+            const f32 x_high = std::ceil(static_cast<f32>(x) * dx_du);
+            const f32 y_high = std::ceil(static_cast<f32>(y) * dy_dv);
+            const f32 weight_x = (static_cast<f32>(x) * dx_du) - x_low;
+            const f32 weight_y = (static_cast<f32>(y) * dy_dv) - y_low;
+
+            const auto read_src = [&](f32 in_x, f32 in_y) {
+                const size_t read_from =
+                    ((static_cast<size_t>(in_x) * src_width + static_cast<size_t>(in_y)) >> 32) *
+                    ir_components;
+                return std::span<const f32>(&input[read_from], ir_components);
+            };
+
+            auto x0_y0 = read_src(x_low, y_low);
+            auto x1_y0 = read_src(x_high, y_low);
+            auto x0_y1 = read_src(x_low, y_high);
+            auto x1_y1 = read_src(x_high, y_high);
+
+            const auto result = bilinear_sample(x0_y0, x1_y0, x0_y1, x1_y1, weight_x, weight_y);
+
+            const size_t write_to = (y * dst_width + x) * ir_components;
+
+            std::memcpy(&output[write_to], &result, sizeof(f32) * ir_components);
+        }
+    }
+}
+
+} // namespace
+
+struct SoftwareBlitEngine::BlitEngineImpl {
+    std::vector<u8> tmp_buffer;
+    std::vector<u8> src_buffer;
+    std::vector<u8> dst_buffer;
+    std::vector<f32> intermediate_src;
+    std::vector<f32> intermediate_dst;
+    ConverterFactory converter_factory;
+};
+
+SoftwareBlitEngine::SoftwareBlitEngine(MemoryManager& memory_manager_)
+    : memory_manager{memory_manager_} {
+    impl = std::make_unique<BlitEngineImpl>();
+}
+
+SoftwareBlitEngine::~SoftwareBlitEngine() = default;
+
+bool SoftwareBlitEngine::Blit(Fermi2D::Surface& src, Fermi2D::Surface& dst,
+                              Fermi2D::Config& config) {
+    const auto get_surface_size = [](Fermi2D::Surface& surface, u32 bytes_per_pixel) {
+        if (surface.linear == Fermi2D::MemoryLayout::BlockLinear) {
+            return CalculateSize(true, bytes_per_pixel, surface.width, surface.height,
+                                 surface.depth, surface.block_height, surface.block_depth);
+        }
+        return static_cast<size_t>(surface.pitch * surface.height);
+    };
+    const auto process_pitch_linear = [](bool unpack, std::span<const u8> input,
+                                         std::span<u8> output, u32 extent_x, u32 extent_y,
+                                         u32 pitch, u32 x0, u32 y0, size_t bpp) {
+        const size_t base_offset = x0 * bpp;
+        const size_t copy_size = extent_x * bpp;
+        for (u32 y = y0; y < extent_y; y++) {
+            const size_t first_offset = y * pitch + base_offset;
+            const size_t second_offset = y * extent_x * bpp;
+            u8* write_to = unpack ? &output[first_offset] : &output[second_offset];
+            const u8* read_from = unpack ? &input[second_offset] : &input[first_offset];
+            std::memcpy(write_to, read_from, copy_size);
+        }
+    };
+
+    const u32 src_extent_x = config.src_x1 - config.src_x0;
+    const u32 src_extent_y = config.src_y1 - config.src_y0;
+
+    const u32 dst_extent_x = config.dst_x1 - config.dst_x0;
+    const u32 dst_extent_y = config.dst_y1 - config.dst_y0;
+    const auto src_bytes_per_pixel = BytesPerBlock(PixelFormatFromRenderTargetFormat(src.format));
+    const auto dst_bytes_per_pixel = BytesPerBlock(PixelFormatFromRenderTargetFormat(dst.format));
+    const size_t src_size = get_surface_size(src, src_bytes_per_pixel);
+    impl->tmp_buffer.resize(src_size);
+    memory_manager.ReadBlock(src.Address(), impl->tmp_buffer.data(), src_size);
+
+    const size_t src_copy_size = src_extent_x * src_extent_y * src_bytes_per_pixel;
+
+    const size_t dst_copy_size = dst_extent_x * dst_extent_y * dst_bytes_per_pixel;
+
+    impl->src_buffer.resize(src_copy_size);
+
+    const bool no_passthrough =
+        src.format != dst.format || src_extent_x != dst_extent_x || src_extent_y != dst_extent_y;
+
+    const auto convertion_phase_same_format = [&]() {
+        NearestNeighbor(impl->src_buffer, impl->dst_buffer, src_extent_x, src_extent_y,
+                        dst_extent_x, dst_extent_y, dst_bytes_per_pixel);
+    };
+
+    const auto convertion_phase_ir = [&]() {
+        auto* input_converter = impl->converter_factory.GetFormatConverter(src.format);
+        impl->intermediate_src.resize((src_copy_size / src_bytes_per_pixel) * ir_components);
+        impl->intermediate_dst.resize((dst_copy_size / dst_bytes_per_pixel) * ir_components);
+        input_converter->ConvertTo(impl->src_buffer, impl->intermediate_src);
+
+        if (config.filter != Fermi2D::Filter::Bilinear) {
+            NearestNeighborFast(impl->intermediate_src, impl->intermediate_dst, src_extent_x,
+                                src_extent_y, dst_extent_x, dst_extent_y);
+        } else {
+            Bilinear(impl->intermediate_src, impl->intermediate_dst, src_extent_x, src_extent_y,
+                     dst_extent_x, dst_extent_y);
+        }
+
+        auto* output_converter = impl->converter_factory.GetFormatConverter(dst.format);
+        output_converter->ConvertFrom(impl->intermediate_dst, impl->dst_buffer);
+    };
+
+    // Do actuall Blit
+
+    impl->dst_buffer.resize(dst_copy_size);
+    if (src.linear == Fermi2D::MemoryLayout::BlockLinear) {
+        UnswizzleSubrect(impl->src_buffer, impl->tmp_buffer, src_bytes_per_pixel, src.width,
+                         src.height, src.depth, config.src_x0, config.src_y0, src_extent_x,
+                         src_extent_y, src.block_height, src.block_depth,
+                         src_extent_x * src_bytes_per_pixel);
+    } else {
+        process_pitch_linear(false, impl->tmp_buffer, impl->src_buffer, src_extent_x, src_extent_y,
+                             src.pitch, config.src_x0, config.src_y0, src_bytes_per_pixel);
+    }
+
+    // Conversion Phase
+    if (no_passthrough) {
+        if (src.format != dst.format || config.filter == Fermi2D::Filter::Bilinear) {
+            convertion_phase_ir();
+        } else {
+            convertion_phase_same_format();
+        }
+    } else {
+        impl->dst_buffer.swap(impl->src_buffer);
+    }
+
+    const size_t dst_size = get_surface_size(dst, dst_bytes_per_pixel);
+    impl->tmp_buffer.resize(dst_size);
+    memory_manager.ReadBlock(dst.Address(), impl->tmp_buffer.data(), dst_size);
+
+    if (dst.linear == Fermi2D::MemoryLayout::BlockLinear) {
+        SwizzleSubrect(impl->tmp_buffer, impl->dst_buffer, dst_bytes_per_pixel, dst.width,
+                       dst.height, dst.depth, config.dst_x0, config.dst_y0, dst_extent_x,
+                       dst_extent_y, dst.block_height, dst.block_depth,
+                       dst_extent_x * dst_bytes_per_pixel);
+    } else {
+        process_pitch_linear(true, impl->dst_buffer, impl->tmp_buffer, dst_extent_x, dst_extent_y,
+                             dst.pitch, config.dst_x0, config.dst_y0,
+                             static_cast<size_t>(dst_bytes_per_pixel));
+    }
+    memory_manager.WriteBlock(dst.Address(), impl->tmp_buffer.data(), dst_size);
+    return true;
+}
+
+} // namespace Tegra::Engines::Blitter

src/video_core/engines/sw_blitter/blitter.h

@@ -0,0 +1,27 @@
+// SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
+#pragma once
+
+#include "video_core/engines/fermi_2d.h"
+
+namespace Tegra {
+class MemoryManager;
+}
+
+namespace Tegra::Engines::Blitter {
+
+class SoftwareBlitEngine {
+public:
+    explicit SoftwareBlitEngine(MemoryManager& memory_manager_);
+    ~SoftwareBlitEngine();
+
+    bool Blit(Fermi2D::Surface& src, Fermi2D::Surface& dst, Fermi2D::Config& copy_config);
+
+private:
+    MemoryManager& memory_manager;
+    struct BlitEngineImpl;
+    std::unique_ptr<BlitEngineImpl> impl;
+};
+
+} // namespace Tegra::Engines::Blitter

src/video_core/engines/sw_blitter/converter.h

@@ -0,0 +1,36 @@
+// SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
+#pragma once
+
+#include <memory>
+#include <span>
+
+#include "common/common_types.h"
+
+#include "video_core/gpu.h"
+
+namespace Tegra::Engines::Blitter {
+
+class Converter {
+public:
+    virtual void ConvertTo(std::span<const u8> input, std::span<f32> output) = 0;
+    virtual void ConvertFrom(std::span<const f32> input, std::span<u8> output) = 0;
+    virtual ~Converter() = default;
+};
+
+class ConverterFactory {
+public:
+    ConverterFactory();
+    ~ConverterFactory();
+
+    Converter* GetFormatConverter(RenderTargetFormat format);
+
+private:
+    Converter* BuildConverter(RenderTargetFormat format);
+
+    struct ConverterFactoryImpl;
+    std::unique_ptr<ConverterFactoryImpl> impl;
+};
+
+} // namespace Tegra::Engines::Blitter

src/video_core/engines/sw_blitter/generate_converters.py

@@ -0,0 +1,136 @@
+# SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
+# SPDX-License-Identifier: GPL-3.0-or-later
+
+import re
+
+class Format:
+    def __init__(self, string_value):
+        self.name = string_value
+        tmp = string_value.split('_')
+        self.component_type = tmp[1]
+        component_data = re.findall(r"\w\d+", tmp[0])
+        self.num_components = len(component_data)
+        sizes = []
+        swizzle = []
+        for data in component_data:
+            swizzle.append(data[0])
+            sizes.append(int(data[1:]))
+        self.sizes = sizes
+        self.swizzle = swizzle
+
+    def build_component_type_array(self):
+        result = "{ "
+        b = False
+        for i in range(0, self.num_components):
+            if b:
+                result += ", "
+            b = True
+            result += "ComponentType::" + self.component_type
+        result += " }"
+        return result
+
+    def build_component_sizes_array(self):
+        result = "{ "
+        b = False
+        for i in range(0, self.num_components):
+            if b:
+                result += ", "
+            b = True
+            result += str(self.sizes[i])
+        result += " }"
+        return result
+
+    def build_component_swizzle_array(self):
+        result = "{ "
+        b = False
+        for i in range(0, self.num_components):
+            if b:
+                result += ", "
+            b = True
+            swizzle = self.swizzle[i]
+            if swizzle == "X":
+                swizzle = "None"
+            result += "Swizzle::" + swizzle
+        result += " }"
+        return result
+
+    def print_declaration(self):
+        print("struct " + self.name + "Traits {")
+        print("  static constexpr size_t num_components = " + str(self.num_components) + ";")
+        print("  static constexpr std::array<ComponentType, num_components> component_types = " + self.build_component_type_array() + ";")
+        print("  static constexpr std::array<size_t, num_components> component_sizes = " + self.build_component_sizes_array() + ";")
+        print("  static constexpr std::array<Swizzle, num_components> component_swizzle = " + self.build_component_swizzle_array() + ";")
+        print("};\n")
+
+    def print_case(self):
+        print("case RenderTargetFormat::" + self.name + ":")
+        print("  return impl->converters_cache")
+        print("    .emplace(format, std::make_unique<ConverterImpl<" + self.name + "Traits>>())")
+        print("    .first->second.get();")
+        print("  break;")
+
+txt = """
+R32G32B32A32_FLOAT
+R32G32B32A32_SINT
+R32G32B32A32_UINT
+R32G32B32X32_FLOAT
+R32G32B32X32_SINT
+R32G32B32X32_UINT
+R16G16B16A16_UNORM
+R16G16B16A16_SNORM
+R16G16B16A16_SINT
+R16G16B16A16_UINT
+R16G16B16A16_FLOAT
+R32G32_FLOAT
+R32G32_SINT
+R32G32_UINT
+R16G16B16X16_FLOAT
+A8R8G8B8_UNORM
+A8R8G8B8_SRGB
+A2B10G10R10_UNORM
+A2B10G10R10_UINT
+A2R10G10B10_UNORM
+A8B8G8R8_UNORM
+A8B8G8R8_SRGB
+A8B8G8R8_SNORM
+A8B8G8R8_SINT
+A8B8G8R8_UINT
+R16G16_UNORM
+R16G16_SNORM
+R16G16_SINT
+R16G16_UINT
+R16G16_FLOAT
+B10G11R11_FLOAT
+R32_SINT
+R32_UINT
+R32_FLOAT
+X8R8G8B8_UNORM
+X8R8G8B8_SRGB
+R5G6B5_UNORM
+A1R5G5B5_UNORM
+R8G8_UNORM
+R8G8_SNORM
+R8G8_SINT
+R8G8_UINT
+R16_UNORM
+R16_SNORM
+R16_SINT
+R16_UINT
+R16_FLOAT
+R8_UNORM
+R8_SNORM
+R8_SINT
+R8_UINT
+X1R5G5B5_UNORM
+X8B8G8R8_UNORM
+X8B8G8R8_SRGB
+"""
+
+x = txt.split()
+y = list(map(lambda a: Format(a), x))
+formats = list(y)
+for format in formats:
+  format.print_declaration()
+
+for format in formats:
+  format.print_case()

src/video_core/gpu.h

@@ -27,12 +27,12 @@ struct CommandList;
 // TODO: Implement the commented ones
 enum class RenderTargetFormat : u32 {
     NONE = 0x0,
-    R32B32G32A32_FLOAT = 0xC0,
+    R32G32B32A32_FLOAT = 0xC0,
     R32G32B32A32_SINT = 0xC1,
     R32G32B32A32_UINT = 0xC2,
-    // R32G32B32X32_FLOAT = 0xC3,
-    // R32G32B32X32_SINT = 0xC4,
-    // R32G32B32X32_UINT = 0xC5,
+    R32G32B32X32_FLOAT = 0xC3,
+    R32G32B32X32_SINT = 0xC4,
+    R32G32B32X32_UINT = 0xC5,
     R16G16B16A16_UNORM = 0xC6,
     R16G16B16A16_SNORM = 0xC7,
     R16G16B16A16_SINT = 0xC8,
@@ -56,13 +56,13 @@ enum class RenderTargetFormat : u32 {
     R16G16_SINT = 0xDC,
     R16G16_UINT = 0xDD,
     R16G16_FLOAT = 0xDE,
-    // A2R10G10B10_UNORM = 0xDF,
+    A2R10G10B10_UNORM = 0xDF,
     B10G11R11_FLOAT = 0xE0,
     R32_SINT = 0xE3,
     R32_UINT = 0xE4,
     R32_FLOAT = 0xE5,
-    // X8R8G8B8_UNORM = 0xE6,
-    // X8R8G8B8_SRGB = 0xE7,
+    X8R8G8B8_UNORM = 0xE6,
+    X8R8G8B8_SRGB = 0xE7,
     R5G6B5_UNORM = 0xE8,
     A1R5G5B5_UNORM = 0xE9,
     R8G8_UNORM = 0xEA,
@@ -79,11 +79,11 @@ enum class RenderTargetFormat : u32 {
     R8_SINT = 0xF5,
     R8_UINT = 0xF6,
 
-    /*
-    A8_UNORM = 0xF7,
+    // A8_UNORM = 0xF7,
     X1R5G5B5_UNORM = 0xF8,
     X8B8G8R8_UNORM = 0xF9,
     X8B8G8R8_SRGB = 0xFA,
+    /*
     Z1R5G5B5_UNORM = 0xFB,
     O1R5G5B5_UNORM = 0xFC,
     Z8R8G8B8_UNORM = 0xFD,

src/video_core/gpu_thread.cpp

@@ -125,7 +125,7 @@ u64 ThreadManager::PushCommand(CommandData&& command_data, bool block) {
     state.queue.Push(CommandDataContainer(std::move(command_data), fence, block));
 
     if (block) {
-        Common::CondvarWait(state.cv, lk, thread.get_stop_token(), [this, fence] {
+        state.cv.wait(lk, thread.get_stop_token(), [this, fence] {
             return fence <= state.signaled_fence.load(std::memory_order_relaxed);
         });
     }

src/video_core/gpu_thread.h

@@ -10,7 +10,6 @@
 #include <thread>
 #include <variant>
 
-#include "common/polyfill_thread.h"
 #include "common/threadsafe_queue.h"
 #include "video_core/framebuffer_config.h"
 

src/video_core/rasterizer_interface.h

@@ -6,8 +6,8 @@
 #include <functional>
 #include <optional>
 #include <span>
+#include <stop_token>
 #include "common/common_types.h"
-#include "common/polyfill_thread.h"
 #include "video_core/engines/fermi_2d.h"
 #include "video_core/gpu.h"
 

src/video_core/renderer_opengl/gl_device.cpp

@@ -14,7 +14,6 @@
 
 #include "common/literals.h"
 #include "common/logging/log.h"
-#include "common/polyfill_ranges.h"
 #include "common/settings.h"
 #include "shader_recompiler/stage.h"
 #include "video_core/renderer_opengl/gl_device.h"

src/video_core/renderer_opengl/gl_rasterizer.cpp

@@ -466,8 +466,7 @@ bool RasterizerOpenGL::AccelerateSurfaceCopy(const Tegra::Engines::Fermi2D::Surf
                                              const Tegra::Engines::Fermi2D::Config& copy_config) {
     MICROPROFILE_SCOPE(OpenGL_Blits);
     std::scoped_lock lock{texture_cache.mutex};
-    texture_cache.BlitImage(dst, src, copy_config);
-    return true;
+    return texture_cache.BlitImage(dst, src, copy_config);
 }
 
 Tegra::Engines::AccelerateDMAInterface& RasterizerOpenGL::AccessAccelerateDMA() {

src/video_core/renderer_opengl/gl_shader_cache.h

@@ -4,6 +4,7 @@
 #pragma once
 
 #include <filesystem>
+#include <stop_token>
 #include <unordered_map>
 
 #include "common/common_types.h"

src/video_core/renderer_opengl/maxwell_to_gl.h

@@ -28,6 +28,7 @@ constexpr std::array<FormatTuple, VideoCore::Surface::MaxPixelFormat> FORMAT_TAB
     {GL_RGB5_A1, GL_BGRA, GL_UNSIGNED_SHORT_1_5_5_5_REV},             // A1R5G5B5_UNORM
     {GL_RGB10_A2, GL_RGBA, GL_UNSIGNED_INT_2_10_10_10_REV},           // A2B10G10R10_UNORM
     {GL_RGB10_A2UI, GL_RGBA_INTEGER, GL_UNSIGNED_INT_2_10_10_10_REV}, // A2B10G10R10_UINT
+    {GL_RGB10_A2, GL_BGRA, GL_UNSIGNED_INT_2_10_10_10_REV},           // A2R10G10B10_UNORM
     {GL_RGB5_A1, GL_RGBA, GL_UNSIGNED_SHORT_1_5_5_5_REV},             // A1B5G5R5_UNORM
     {GL_RGB5_A1, GL_RGBA, GL_UNSIGNED_SHORT_5_5_5_1},                 // A5B5G5R1_UNORM
     {GL_R8, GL_RED, GL_UNSIGNED_BYTE},                                // R8_UNORM