Merge pull request #1 from cemu-project/main

Update

.clang-format

@@ -15,6 +15,7 @@ BinPackArguments: true
 BinPackParameters: true
 BraceWrapping:
   AfterCaseLabel: true
+  AfterClass: true
   AfterControlStatement: Always
   AfterEnum: true
   AfterExternBlock: true

.github/ISSUE_TEMPLATE/bug-report-feature-request.md

@@ -1,34 +0,0 @@
----
-name: Bug Report / Feature Request
-about: Tech support does not belong here. You should only file an issue here if you think you have experienced an actual bug with Cemu or you are requesting a feature you believe would make Cemu better.
-title: ''
-labels: ''
-assignees: ''
-
----
-
-<!---
-Please keep in mind Cemu is EXPERIMENTAL SOFTWARE.
-
-Please read the FAQ:
-https://cemu.info/faq.html
-
-THIS IS NOT A SUPPORT FORUM, FOR SUPPORT GO TO:
-https://discord.com/invite/5psYsup
-
-If the FAQ does not answer your question, please go to:
-https://discord.com/invite/5psYsup
-
-When submitting an issue, please check the following:
-
-- You have read the above.
-- You have provided the version (commit hash) of Cemu you are using.
-- You have provided sufficient detail for the issue to be reproduced.
-- You have provided system specs (if relevant).
-- Please also provide:
-  - For any issues, a log file
-  - For crashes, a backtrace.
-  - For graphical issues, comparison screenshots with real hardware.
-  - For emulation inaccuracies, a test-case (if able).
-
--->

.github/ISSUE_TEMPLATE/config.yml

@@ -2,4 +2,4 @@ blank_issues_enabled: false
 contact_links:
   - name: Cemu Discord
     url: https://discord.com/invite/5psYsup
-    about: If you are experiencing an issue with Cemu, and you need tech support, or if you have a general question, try asking in the official Cemu Discord linked here. Piracy is not allowed.
+    about: If you need technical support with Cemu or have other questions the best place to ask is on the official Cemu Discord linked here

.github/ISSUE_TEMPLATE/emulation_bug_report.yaml

@@ -0,0 +1,69 @@
+# Docs - https://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema
+name: Bug Report
+description: Report an issue with Cemu emulator
+title: "Enter a title for the bug report here"
+labels: bug
+body:
+  - type: markdown
+    id: md_readme
+    attributes:
+      value: |
+        ## Important: Read First
+        
+        If you discovered a bug you can report it here. Please make sure of the following first:
+        - That you are using the latest version of Cemu
+        - Only report something if you are sure it's a bug and not any technical issue on your end. For troubleshooting help see the [links page](https://github.com/cemu-project/Cemu#links)
+        - Problems specific to a single game should be reported on the [compatibility wiki](https://wiki.cemu.info/wiki/Main_Page) instead
+        - Verify that your problem isn't already mentioned on the [issue tracker](https://github.com/cemu-project/Cemu/issues)
+        
+        Additionally, be aware that graphic packs can also causes issues. There is a separate issue tracker for graphic pack bugs over at the [graphic pack repository](https://github.com/cemu-project/cemu_graphic_packs)
+  - type: textarea
+    id: current_behavior
+    attributes:
+      label: Current Behavior
+      description: "What the bug is, in a brief description"
+    validations:
+      required: true
+  - type: textarea
+    id: expected_behavior
+    attributes:
+      label: Expected Behavior
+      description: "What did you expect to happen?"
+    validations:
+      required: true
+
+  - type: textarea
+    id: steps_to_reproduce
+    attributes:
+      label: Steps to Reproduce
+      description: "How to reproduce the issue"
+    validations:
+      required: true
+  - type: textarea
+    id: sys_info
+    attributes:
+      label: System Info (Optional)
+      description: "Your PC specifications. Usually only the operating system and graphics card is important. But feel free to add more info."
+      placeholder: |
+        Info        
+        OS: Windows 10
+        GPU: NVIDIA GeForce RTX 4090
+      value: |
+        OS: 
+        GPU: 
+  - type: textarea
+    id: emulation_settings
+    attributes:
+      label: Emulation Settings (Optional)
+      description: |
+        Any non-default settings. You can leave this empty if you didn't change anything other than input settings.
+    validations:
+      required: false
+  - type: textarea
+    id: logs_files
+    attributes:
+      label: "Logs (Optional)"
+      description: |
+        "Attach `log.txt` from your Cemu folder (*File > Open Cemu folder*)".
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/feature_report.yaml

@@ -0,0 +1,28 @@
+# Docs - https://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema
+name: Feature suggestion
+description: Suggest a new feature
+title: "Enter a title for the suggestion here"
+labels: feature request
+body:
+  - type: markdown
+    id: md_readme
+    attributes:
+      value: |
+        ## Important: Read First
+        
+        While we appreciate suggestions, it is important to note that we are a very small team and there are already many more ideas than we could ever implement in the near future. Therefore, please only suggest something if you believe it is a great addition and the idea is reasonably unique.
+        
+        *Avoid* to create suggestions for:
+        - Overly obvious features ("Game xyz does not work and should be fixed", "Wiimote support should be improved", "You should add an Android port", "Copy feature xyz from another emulator", "A button to pause/stop emulation")
+        - Niche features which are only interesting to a tiny percentage of users
+        - Large scale features ("Add a Metal backend for MacOS", "Add ARM support", "Add savestates")
+         
+        Note that this doesn't mean we aren't interested in these ideas, but rather we likely have them planned anyway and it's mostly up to finding the time to implement them.
+        If you believe your idea is worthwhile even if it doesn't meet all the criteria above, you can still try suggesting it but we might close it.        
+  - type: textarea
+    id: idea_suggestion
+    attributes:
+      label: Your suggestion
+      description: "Describe what your suggestion is in as much detail as possible"
+    validations:
+      required: true

.github/getversion.cpp

@@ -1,9 +0,0 @@
-#include <stdio.h>
-#include "./../src/Common/version.h"
-
-// output current Cemu version for CI workflow. Do not modify
-int main()
-{
-   printf("%d.%d", EMULATOR_VERSION_LEAD, EMULATOR_VERSION_MAJOR);
-   return 0;
-}

.github/workflows/build.yml

@@ -3,10 +3,10 @@ name: Build Cemu
 on:
   workflow_call:
     inputs:
-      deploymode:
+      next_version_major:
         required: false
         type: string
-      experimentalversion:
+      next_version_minor:
         required: false
         type: string
 
@@ -19,41 +19,32 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
     - name: "Checkout repo"
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
       with:
         submodules: "recursive"
         fetch-depth: 0
 
-    - name: "Fetch full history for vcpkg submodule"
-      run: |
-        cd dependencies/vcpkg
-        git fetch --unshallow
-        git pull --all
-
-    - name: Setup release mode parameters (for deploy)
-      if: ${{ inputs.deploymode == 'release' }}
+    - name: Setup release mode parameters
       run: |
         echo "BUILD_MODE=release" >> $GITHUB_ENV
         echo "BUILD_FLAGS=" >> $GITHUB_ENV
         echo "Build mode is release"
 
-    - name: Setup debug mode parameters (for continous build)
-      if: ${{ inputs.deploymode != 'release' }}
+    - name: Setup build flags for version
+      if: ${{ inputs.next_version_major != '' }}
       run: |
-        echo "BUILD_MODE=debug" >> $GITHUB_ENV
-        echo "BUILD_FLAGS=" >> $GITHUB_ENV
-        echo "Build mode is debug"
-
-    - name: Setup version for experimental
-      if: ${{ inputs.experimentalversion != '' }}
-      run: |
-        echo "[INFO] Experimental version ${{ inputs.experimentalversion }}"
-        echo "BUILD_FLAGS=${{ env.BUILD_FLAGS }} -DEXPERIMENTAL_VERSION=${{ inputs.experimentalversion }}" >> $GITHUB_ENV
+        echo "[INFO] Version ${{ inputs.next_version_major }}.${{ inputs.next_version_minor }}"
+        echo "BUILD_FLAGS=${{ env.BUILD_FLAGS }} -DEMULATOR_VERSION_MAJOR=${{ inputs.next_version_major }} -DEMULATOR_VERSION_MINOR=${{ inputs.next_version_minor }}" >> $GITHUB_ENV
 
     - name: "Install system dependencies"
       run: |
         sudo apt update -qq
-        sudo apt install -y clang-15 cmake freeglut3-dev libgcrypt20-dev libglm-dev libgtk-3-dev libpulse-dev libsecret-1-dev libsystemd-dev libudev-dev nasm ninja-build
+        sudo apt install -y clang-15 cmake freeglut3-dev libgcrypt20-dev libglm-dev libgtk-3-dev libpulse-dev libsecret-1-dev libsystemd-dev libudev-dev nasm ninja-build libbluetooth-dev
+
+    - name: "Setup cmake"
+      uses: jwlawson/actions-setup-cmake@v2
+      with:
+        cmake-version: '3.29.0'
 
     - name: "Bootstrap vcpkg"
       run: |
@@ -75,19 +66,17 @@ jobs:
         
     - name: "cmake"
       run: |
-        cmake -S . -B build ${{ env.BUILD_FLAGS }} -DCMAKE_BUILD_TYPE=${{ env.BUILD_MODE }} -DPORTABLE=OFF -DCMAKE_C_COMPILER=/usr/bin/clang-15 -DCMAKE_CXX_COMPILER=/usr/bin/clang++-15 -G Ninja -DCMAKE_MAKE_PROGRAM=/usr/bin/ninja
+        cmake -S . -B build ${{ env.BUILD_FLAGS }} -DCMAKE_BUILD_TYPE=${{ env.BUILD_MODE }} -DCMAKE_C_COMPILER=/usr/bin/clang-15 -DCMAKE_CXX_COMPILER=/usr/bin/clang++-15 -G Ninja -DCMAKE_MAKE_PROGRAM=/usr/bin/ninja
         
     - name: "Build Cemu"
       run: |
         cmake --build build
         
     - name: Prepare artifact
-      if: ${{ inputs.deploymode == 'release' }}
       run: mv bin/Cemu_release bin/Cemu
               
     - name: Upload artifact
-      uses: actions/upload-artifact@v3
-      if: ${{ inputs.deploymode == 'release' }}
+      uses: actions/upload-artifact@v4
       with:
         name: cemu-bin-linux-x64
         path: ./bin/Cemu
@@ -97,9 +86,9 @@ jobs:
     needs: build-ubuntu
     steps:
     - name: Checkout Upstream Repo
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
 
-    - uses: actions/download-artifact@v3
+    - uses: actions/download-artifact@v4
       with:
         name: cemu-bin-linux-x64
         path: bin
@@ -107,7 +96,7 @@ jobs:
     - name: "Install system dependencies"
       run: |
         sudo apt update -qq
-        sudo apt install -y clang-15 cmake freeglut3-dev libgcrypt20-dev libglm-dev libgtk-3-dev libpulse-dev libsecret-1-dev libsystemd-dev nasm ninja-build appstream
+        sudo apt install -y clang-15 cmake freeglut3-dev libgcrypt20-dev libglm-dev libgtk-3-dev libpulse-dev libsecret-1-dev libsystemd-dev nasm ninja-build appstream libbluetooth-dev
 
     - name: "Build AppImage"
       run: |
@@ -116,7 +105,7 @@ jobs:
         dist/linux/appimage.sh
 
     - name: Upload artifact
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v4
       with:
         name: cemu-appimage-x64
         path: artifacts
@@ -125,34 +114,26 @@ jobs:
     runs-on: windows-2022
     steps:
     - name: "Checkout repo"
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
       with:
         submodules: "recursive"
 
-    - name: "Fetch full history for vcpkg submodule"
-      run: |
-        cd dependencies/vcpkg
-        git fetch --unshallow
-        git pull --all        
-        
-    - name: Setup release mode parameters (for deploy)
-      if: ${{ inputs.deploymode == 'release' }}
+    - name: Setup release mode parameters
       run: |
         echo "BUILD_MODE=release" | Out-File -FilePath $Env:GITHUB_ENV -Encoding utf8 -Append
         echo "BUILD_FLAGS=" | Out-File -FilePath $Env:GITHUB_ENV -Encoding utf8 -Append
         echo "Build mode is release"
 
-    - name: Setup debug mode parameters (for continous build)
-      if: ${{ inputs.deploymode != 'release' }}
+    - name: Setup build flags for version
+      if: ${{ inputs.next_version_major != '' }}
       run: |
-        echo "BUILD_MODE=debug" | Out-File -FilePath $Env:GITHUB_ENV -Encoding utf8 -Append
-        echo "BUILD_FLAGS=" | Out-File -FilePath $Env:GITHUB_ENV -Encoding utf8 -Append
-        echo "Build mode is debug"
-    - name: Setup version for experimental
-      if: ${{ inputs.experimentalversion != '' }}
-      run: |
-        echo "[INFO] Experimental version ${{ inputs.experimentalversion }}"
-        echo "BUILD_FLAGS=${{ env.BUILD_FLAGS }} -DEXPERIMENTAL_VERSION=${{ inputs.experimentalversion }}" | Out-File -FilePath $Env:GITHUB_ENV -Encoding utf8 -Append
+        echo "[INFO] Version ${{ inputs.next_version_major }}.${{ inputs.next_version_minor }}"
+        echo "BUILD_FLAGS=${{ env.BUILD_FLAGS }} -DEMULATOR_VERSION_MAJOR=${{ inputs.next_version_major }} -DEMULATOR_VERSION_MINOR=${{ inputs.next_version_minor }}" | Out-File -FilePath $Env:GITHUB_ENV -Encoding utf8 -Append
+
+    - name: "Setup cmake"
+      uses: jwlawson/actions-setup-cmake@v2
+      with:
+        cmake-version: '3.29.0'
 
     - name: "Bootstrap vcpkg"
       run: |
@@ -183,56 +164,53 @@ jobs:
     - name: "Build Cemu"
       run: |
         cd build
-        cmake --build . --config ${{ env.BUILD_MODE }} -j 2
+        cmake --build . --config ${{ env.BUILD_MODE }}
 
     - name: Prepare artifact
-      if: ${{ inputs.deploymode == 'release' }}
       run: Rename-Item bin/Cemu_release.exe Cemu.exe
       
     - name: Upload artifact
-      uses: actions/upload-artifact@v3
-      if: ${{ inputs.deploymode == 'release' }}
+      uses: actions/upload-artifact@v4
       with:
         name: cemu-bin-windows-x64
         path: ./bin/Cemu.exe
 
   build-macos:
-    runs-on: macos-12
+    runs-on: macos-14
     steps:
     - name: "Checkout repo"
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
       with:
         submodules: "recursive"
         
-    - name: "Fetch full history for vcpkg submodule"
-      run: |
-        cd dependencies/vcpkg
-        git fetch --unshallow
-        git pull --all        
-        
-    - name: Setup release mode parameters (for deploy)
-      if: ${{ inputs.deploymode == 'release' }}
+    - name: Setup release mode parameters
       run: |
         echo "BUILD_MODE=release" >> $GITHUB_ENV
         echo "BUILD_FLAGS=" >> $GITHUB_ENV
         echo "Build mode is release"
-    - name: Setup debug mode parameters (for continous build)
-      if: ${{ inputs.deploymode != 'release' }}
-      run: |
-        echo "BUILD_MODE=debug" >> $GITHUB_ENV
-        echo "BUILD_FLAGS=" >> $GITHUB_ENV
-        echo "Build mode is debug"
 
-    - name: Setup version for experimental
-      if: ${{ inputs.experimentalversion != '' }}
+    - name: Setup build flags for version
+      if: ${{ inputs.next_version_major != '' }}
       run: |
-        echo "[INFO] Experimental version ${{ inputs.experimentalversion }}"
-        echo "BUILD_FLAGS=${{ env.BUILD_FLAGS }} -DEXPERIMENTAL_VERSION=${{ inputs.experimentalversion }}" >> $GITHUB_ENV
+        echo "[INFO] Version ${{ inputs.next_version_major }}.${{ inputs.next_version_minor }}"
+        echo "BUILD_FLAGS=${{ env.BUILD_FLAGS }} -DEMULATOR_VERSION_MAJOR=${{ inputs.next_version_major }} -DEMULATOR_VERSION_MINOR=${{ inputs.next_version_minor }}" >> $GITHUB_ENV
         
     - name: "Install system dependencies"
       run: |
         brew update
-        brew install llvm@15 ninja nasm molten-vk automake libtool
+        brew install ninja nasm automake libtool
+
+    - name: "Install molten-vk"
+      run: |
+        curl -L -O https://github.com/KhronosGroup/MoltenVK/releases/download/v1.2.9/MoltenVK-macos.tar
+        tar xf MoltenVK-macos.tar
+        sudo mkdir -p /usr/local/lib
+        sudo cp MoltenVK/MoltenVK/dynamic/dylib/macOS/libMoltenVK.dylib /usr/local/lib
+
+    - name: "Setup cmake"
+      uses: jwlawson/actions-setup-cmake@v2
+      with:
+        cmake-version: '3.29.0'
 
     - name: "Bootstrap vcpkg"
       run: |
@@ -258,10 +236,8 @@ jobs:
         cd build
         cmake .. ${{ env.BUILD_FLAGS }} \
         -DCMAKE_BUILD_TYPE=${{ env.BUILD_MODE }} \
-        -DPORTABLE=OFF \
+        -DCMAKE_OSX_ARCHITECTURES=x86_64 \
         -DMACOS_BUNDLE=ON \
-        -DCMAKE_C_COMPILER=/usr/local/opt/llvm@15/bin/clang \
-        -DCMAKE_CXX_COMPILER=/usr/local/opt/llvm@15/bin/clang++ \
         -G Ninja
         
     - name: "Build Cemu"
@@ -269,21 +245,19 @@ jobs:
         cmake --build build
 
     - name: Prepare artifact
-      if: ${{ inputs.deploymode == 'release' }}
       run: |
         mkdir bin/Cemu_app
         mv bin/Cemu_release.app bin/Cemu_app/Cemu.app
         mv bin/Cemu_app/Cemu.app/Contents/MacOS/Cemu_release bin/Cemu_app/Cemu.app/Contents/MacOS/Cemu
         sed -i '' 's/Cemu_release/Cemu/g' bin/Cemu_app/Cemu.app/Contents/Info.plist
-        chmod a+x bin/Cemu_app/Cemu.app/Contents/MacOS/Cemu
+        chmod a+x bin/Cemu_app/Cemu.app/Contents/MacOS/{Cemu,update.sh}
         ln -s /Applications bin/Cemu_app/Applications
         hdiutil create ./bin/tmp.dmg -ov -volname "Cemu" -fs HFS+ -srcfolder "./bin/Cemu_app"
         hdiutil convert ./bin/tmp.dmg -format UDZO -o bin/Cemu.dmg
         rm bin/tmp.dmg
               
     - name: Upload artifact
-      uses: actions/upload-artifact@v3
-      if: ${{ inputs.deploymode == 'release' }}
+      uses: actions/upload-artifact@v4
       with:
         name: cemu-bin-macos-x64
         path: ./bin/Cemu.dmg

.github/workflows/build_check.yml

@@ -16,6 +16,3 @@ on:
 jobs:
   build:
     uses: ./.github/workflows/build.yml
-    with:
-      deploymode: release
-      experimentalversion: 999999

.github/workflows/deploy_experimental_release.yml

@@ -1,86 +0,0 @@
-name: Deploy experimental release
-on: 
-  workflow_dispatch:
-
-jobs:
-  call-release-build:
-    uses: ./.github/workflows/build.yml
-    with:
-      deploymode: release
-      experimentalversion: ${{ github.run_number }}
-  deploy:
-    name: Deploy experimental release
-    runs-on: ubuntu-22.04
-    needs: call-release-build
-    steps:
-      - uses: actions/checkout@v3
- 
-      - uses: actions/download-artifact@v3
-        with:
-          name: cemu-bin-linux-x64
-          path: cemu-bin-linux-x64
-
-      - uses: actions/download-artifact@v3
-        with:
-          name: cemu-appimage-x64
-          path: cemu-appimage-x64
-
-      - uses: actions/download-artifact@v3
-        with:
-          name: cemu-bin-windows-x64
-          path: cemu-bin-windows-x64
-
-      - uses: actions/download-artifact@v3
-        with:
-          name: cemu-bin-macos-x64
-          path: cemu-bin-macos-x64
-
-      - name: Initialize
-        run: |
-          mkdir upload
-          sudo apt install zip
-          
-      - name: Get version
-        run: |
-          echo "Experimental version: ${{ github.run_number }}"
-          ls
-          gcc -o getversion .github/getversion.cpp
-          ./getversion
-          echo "Cemu CI version: $(./getversion)"
-          echo "CEMU_FOLDER_NAME=Cemu_$(./getversion)-${{ github.run_number }}" >> $GITHUB_ENV
-          echo "CEMU_VERSION=$(./getversion)-${{ github.run_number }}" >> $GITHUB_ENV
-
-      - name: Create release from windows-bin
-        run: |
-          ls ./
-          ls ./bin/
-          cp -R ./bin ./${{ env.CEMU_FOLDER_NAME }}
-          mv cemu-bin-windows-x64/Cemu.exe ./${{ env.CEMU_FOLDER_NAME }}/Cemu.exe
-          zip -9 -r upload/cemu-${{ env.CEMU_VERSION }}-windows-x64.zip ${{ env.CEMU_FOLDER_NAME }}
-          rm -r ./${{ env.CEMU_FOLDER_NAME }}
-
-      - name: Create appimage
-        run: |
-          VERSION=${{ env.CEMU_VERSION }}
-          echo "Cemu Version is $VERSION"
-          ls cemu-appimage-x64
-          mv cemu-appimage-x64/Cemu-*-x86_64.AppImage upload/Cemu-$VERSION-x86_64.AppImage
-        
-      - name: Create release from linux-bin
-        run: |
-          ls ./
-          ls ./bin/
-          cp -R ./bin ./${{ env.CEMU_FOLDER_NAME }}
-          mv cemu-bin-linux-x64/Cemu ./${{ env.CEMU_FOLDER_NAME }}/Cemu
-          zip -9 -r upload/cemu-${{ env.CEMU_VERSION }}-ubuntu-22.04-x64.zip ${{ env.CEMU_FOLDER_NAME }}
-          rm -r ./${{ env.CEMU_FOLDER_NAME }}
-          
-      - name: Create release from macos-bin
-        run: cp cemu-bin-macos-x64/Cemu.dmg upload/cemu-${{ env.CEMU_VERSION }}-macos-12-x64.dmg
-
-      - name: Create release
-        run: |
-          wget -O ghr.tar.gz https://github.com/tcnksm/ghr/releases/download/v0.15.0/ghr_v0.15.0_linux_amd64.tar.gz
-          tar xvzf ghr.tar.gz; rm ghr.tar.gz
-          echo "[INFO] Release tag: v${{ env.CEMU_VERSION }}"
-          ghr_v0.15.0_linux_amd64/ghr -prerelease -t ${{ secrets.GITHUB_TOKEN }} -n "Cemu ${{ env.CEMU_VERSION }} (Experimental)" -b "Cemu experimental release" "v${{ env.CEMU_VERSION }}" ./upload

.github/workflows/deploy_release.yml

@@ -0,0 +1,151 @@
+name: Deploy release
+on: 
+  workflow_dispatch:
+    inputs:
+      changelog0:
+        description: 'Enter the changelog lines for this release. Each line is a feature / bullet point. Do not use dash.'
+        required: true
+        type: string
+      changelog1:
+        description: 'Feature 2'
+        required: false
+        type: string
+      changelog2:
+        description: 'Feature 3'
+        required: false
+        type: string
+      changelog3:
+        description: 'Feature 4'
+        required: false
+        type: string
+      changelog4:
+        description: 'Feature 5'
+        required: false
+        type: string
+      changelog5:
+        description: 'Feature 6'
+        required: false
+        type: string
+      changelog6:
+        description: 'Feature 7'
+        required: false
+        type: string
+      changelog7:
+        description: 'Feature 8'
+        required: false
+        type: string
+      changelog8:
+        description: 'Feature 9'
+        required: false
+        type: string
+      changelog9:
+        description: 'Feature 10'
+        required: false
+        type: string
+
+jobs:
+  calculate-version:
+    name: Calculate Version
+    uses: ./.github/workflows/determine_release_version.yml
+  call-release-build:
+    uses: ./.github/workflows/build.yml
+    needs: calculate-version
+    with:
+      next_version_major: ${{ needs.calculate-version.outputs.next_version_major }}
+      next_version_minor: ${{ needs.calculate-version.outputs.next_version_minor }}
+  deploy:
+    name: Deploy release
+    runs-on: ubuntu-22.04
+    needs: [call-release-build, calculate-version]
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Generate changelog
+        id: generate_changelog
+        run: |
+          CHANGELOG=""
+          if [ -n "${{ github.event.inputs.changelog0 }}" ]; then CHANGELOG="$CHANGELOG- ${{ github.event.inputs.changelog0 }}\n"; fi
+          if [ -n "${{ github.event.inputs.changelog1 }}" ]; then CHANGELOG="$CHANGELOG- ${{ github.event.inputs.changelog1 }}\n"; fi
+          if [ -n "${{ github.event.inputs.changelog2 }}" ]; then CHANGELOG="$CHANGELOG- ${{ github.event.inputs.changelog2 }}\n"; fi
+          if [ -n "${{ github.event.inputs.changelog3 }}" ]; then CHANGELOG="$CHANGELOG- ${{ github.event.inputs.changelog3 }}\n"; fi
+          if [ -n "${{ github.event.inputs.changelog4 }}" ]; then CHANGELOG="$CHANGELOG- ${{ github.event.inputs.changelog4 }}\n"; fi
+          if [ -n "${{ github.event.inputs.changelog5 }}" ]; then CHANGELOG="$CHANGELOG- ${{ github.event.inputs.changelog5 }}\n"; fi
+          if [ -n "${{ github.event.inputs.changelog6 }}" ]; then CHANGELOG="$CHANGELOG- ${{ github.event.inputs.changelog6 }}\n"; fi
+          if [ -n "${{ github.event.inputs.changelog7 }}" ]; then CHANGELOG="$CHANGELOG- ${{ github.event.inputs.changelog7 }}\n"; fi
+          if [ -n "${{ github.event.inputs.changelog8 }}" ]; then CHANGELOG="$CHANGELOG- ${{ github.event.inputs.changelog8 }}\n"; fi
+          if [ -n "${{ github.event.inputs.changelog9 }}" ]; then CHANGELOG="$CHANGELOG- ${{ github.event.inputs.changelog9 }}\n"; fi
+          echo -e "$CHANGELOG"
+          echo "RELEASE_BODY=$CHANGELOG" >> $GITHUB_ENV
+      - uses: actions/download-artifact@v4
+        with:
+          name: cemu-bin-linux-x64
+          path: cemu-bin-linux-x64
+
+      - uses: actions/download-artifact@v4
+        with:
+          name: cemu-appimage-x64
+          path: cemu-appimage-x64
+
+      - uses: actions/download-artifact@v4
+        with:
+          name: cemu-bin-windows-x64
+          path: cemu-bin-windows-x64
+
+      - uses: actions/download-artifact@v4
+        with:
+          name: cemu-bin-macos-x64
+          path: cemu-bin-macos-x64
+
+      - name: Initialize
+        run: |
+          mkdir upload
+          sudo apt install zip
+          
+      - name: Set version dependent vars
+        run: |
+          echo "Version: ${{ needs.calculate-version.outputs.next_version }}"
+          echo "CEMU_FOLDER_NAME=Cemu_${{ needs.calculate-version.outputs.next_version }}"
+          echo "CEMU_VERSION=${{ needs.calculate-version.outputs.next_version }}"
+          echo "CEMU_FOLDER_NAME=Cemu_${{ needs.calculate-version.outputs.next_version }}" >> $GITHUB_ENV
+          echo "CEMU_VERSION=${{ needs.calculate-version.outputs.next_version }}" >> $GITHUB_ENV
+
+      - name: Create release from windows-bin
+        run: |
+          ls ./
+          ls ./bin/
+          cp -R ./bin ./${{ env.CEMU_FOLDER_NAME }}
+          mv cemu-bin-windows-x64/Cemu.exe ./${{ env.CEMU_FOLDER_NAME }}/Cemu.exe
+          zip -9 -r upload/cemu-${{ env.CEMU_VERSION }}-windows-x64.zip ${{ env.CEMU_FOLDER_NAME }}
+          rm -r ./${{ env.CEMU_FOLDER_NAME }}
+
+      - name: Create appimage
+        run: |
+          VERSION=${{ env.CEMU_VERSION }}
+          echo "Cemu Version is $VERSION"
+          ls cemu-appimage-x64
+          mv cemu-appimage-x64/Cemu-*-x86_64.AppImage upload/Cemu-$VERSION-x86_64.AppImage
+        
+      - name: Create release from linux-bin
+        run: |
+          ls ./
+          ls ./bin/
+          cp -R ./bin ./${{ env.CEMU_FOLDER_NAME }}
+          mv cemu-bin-linux-x64/Cemu ./${{ env.CEMU_FOLDER_NAME }}/Cemu
+          zip -9 -r upload/cemu-${{ env.CEMU_VERSION }}-ubuntu-22.04-x64.zip ${{ env.CEMU_FOLDER_NAME }}
+          rm -r ./${{ env.CEMU_FOLDER_NAME }}
+          
+      - name: Create release from macos-bin
+        run: cp cemu-bin-macos-x64/Cemu.dmg upload/cemu-${{ env.CEMU_VERSION }}-macos-12-x64.dmg
+
+      - name: Create release
+        run: |
+          wget -O ghr.tar.gz https://github.com/tcnksm/ghr/releases/download/v0.15.0/ghr_v0.15.0_linux_amd64.tar.gz
+          tar xvzf ghr.tar.gz; rm ghr.tar.gz
+          echo "[INFO] Release tag: v${{ env.CEMU_VERSION }}"
+          CHANGELOG_UNESCAPED=$(printf "%s\n" "${{ env.RELEASE_BODY }}" | sed 's/\\n/\n/g')          
+          RELEASE_BODY=$(printf "%s\n%s" \
+            "**Changelog:**" \
+            "$CHANGELOG_UNESCAPED")
+          ghr_v0.15.0_linux_amd64/ghr -draft -t ${{ secrets.GITHUB_TOKEN }} -n "Cemu ${{ env.CEMU_VERSION }}" -b "$RELEASE_BODY" "v${{ env.CEMU_VERSION }}" ./upload

.github/workflows/deploy_stable_release.yml

@@ -1,85 +0,0 @@
-name: Create new release
-on: 
-  workflow_dispatch:
-    inputs:
-      PlaceholderInput:
-        description: PlaceholderInput
-        required: false
-jobs:
-  call-release-build:
-    uses: ./.github/workflows/build.yml
-    with:
-      deploymode: release
-  deploy:
-    name: Deploy release
-    runs-on: ubuntu-20.04
-    needs: call-release-build
-    steps:
-      - uses: actions/checkout@v3
- 
-      - uses: actions/download-artifact@v3
-        with:
-          name: cemu-bin-linux-x64
-          path: cemu-bin-linux-x64
-
-      - uses: actions/download-artifact@v3
-        with:
-          name: cemu-appimage-x64
-          path: cemu-appimage-x64
-          
-      - uses: actions/download-artifact@v3
-        with:
-          name: cemu-bin-windows-x64
-          path: cemu-bin-windows-x64
-
-      - uses: actions/download-artifact@v3
-        with:
-          name: cemu-bin-macos-x64
-          path: cemu-bin-macos-x64
-
-      - name: Initialize
-        run: |
-          mkdir upload
-          sudo apt update -qq
-          sudo apt install -y zip
-          
-      - name: Get Cemu release version
-        run: |
-          gcc -o getversion .github/getversion.cpp
-          echo "Cemu CI version: $(./getversion)"
-          echo "CEMU_FOLDER_NAME=Cemu_$(./getversion)" >> $GITHUB_ENV
-          echo "CEMU_VERSION=$(./getversion)" >> $GITHUB_ENV
-          
-      - name: Create release from windows-bin
-        run: |
-          ls ./
-          ls ./bin/
-          cp -R ./bin ./${{ env.CEMU_FOLDER_NAME }}
-          mv cemu-bin-windows-x64/Cemu.exe ./${{ env.CEMU_FOLDER_NAME }}/Cemu.exe
-          zip -9 -r upload/cemu-${{ env.CEMU_VERSION }}-windows-x64.zip ${{ env.CEMU_FOLDER_NAME }}
-          rm -r ./${{ env.CEMU_FOLDER_NAME }}
-
-      - name: Create appimage
-        run: |
-          VERSION=${{ env.CEMU_VERSION }}
-          echo "Cemu Version is $VERSION"
-          ls cemu-appimage-x64
-          mv cemu-appimage-x64/Cemu-*-x86_64.AppImage upload/Cemu-$VERSION-x86_64.AppImage
-          
-      - name: Create release from ubuntu-bin
-        run: |
-          ls ./
-          ls ./bin/
-          cp -R ./bin ./${{ env.CEMU_FOLDER_NAME }}
-          mv cemu-bin-linux-x64/Cemu ./${{ env.CEMU_FOLDER_NAME }}/Cemu
-          zip -9 -r upload/cemu-${{ env.CEMU_VERSION }}-ubuntu-20.04-x64.zip ${{ env.CEMU_FOLDER_NAME }}
-          rm -r ./${{ env.CEMU_FOLDER_NAME }}
-          
-      - name: Create release from macos-bin
-        run: cp cemu-bin-macos-x64/Cemu.dmg upload/cemu-${{ env.CEMU_VERSION }}-macos-12-x64.dmg
-          
-      - name: Create release
-        run: |
-          wget -O ghr.tar.gz https://github.com/tcnksm/ghr/releases/download/v0.15.0/ghr_v0.15.0_linux_amd64.tar.gz
-          tar xvzf ghr.tar.gz; rm ghr.tar.gz
-          ghr_v0.15.0_linux_amd64/ghr -t ${{ secrets.GITHUB_TOKEN }} -n "Cemu ${{ env.CEMU_VERSION }}" -b "Changelog:" v${{ env.CEMU_VERSION }} ./upload

.github/workflows/determine_release_version.yml

@@ -0,0 +1,74 @@
+name: Calculate Next Version from release history
+
+on:
+  workflow_dispatch:
+  workflow_call:
+    outputs:
+      next_version:
+        description: "The next semantic version"
+        value: ${{ jobs.calculate-version.outputs.next_version }}
+      next_version_major:
+        description: "The next semantic version (major)"
+        value: ${{ jobs.calculate-version.outputs.next_version_major }}
+      next_version_minor:
+        description: "The next semantic version (minor)"
+        value: ${{ jobs.calculate-version.outputs.next_version_minor }}
+
+jobs:
+  calculate-version:
+    runs-on: ubuntu-latest
+    outputs:
+      next_version: ${{ steps.calculate_next_version.outputs.next_version }}
+      next_version_major: ${{ steps.calculate_next_version.outputs.next_version_major }}
+      next_version_minor: ${{ steps.calculate_next_version.outputs.next_version_minor }}      
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+
+      - name: Get all releases
+        id: get_all_releases
+        run: |
+          # Fetch all releases and check for API errors
+          RESPONSE=$(curl -s -o response.json -w "%{http_code}" "https://api.github.com/repos/${{ github.repository }}/releases?per_page=100")
+          if [ "$RESPONSE" -ne 200 ]; then
+            echo "Failed to fetch releases. HTTP status: $RESPONSE"
+            cat response.json
+            exit 1
+          fi
+          
+          # Extract and sort tags
+          ALL_TAGS=$(jq -r '.[].tag_name' response.json | grep -E '^v[0-9]+\.[0-9]+(-[0-9]+)?$' | sed 's/-.*//' | sort -V | tail -n 1)
+
+          # Exit if no tags were found
+          if [ -z "$ALL_TAGS" ]; then
+            echo "No valid tags found."
+            exit 1
+          fi
+
+          echo "::set-output name=tag::$ALL_TAGS"
+          # echo "tag=$ALL_TAGS" >> $GITHUB_STATE
+
+      - name: Calculate next semver minor
+        id: calculate_next_version
+        run: |
+          LATEST_VERSION=${{ steps.get_all_releases.outputs.tag }}
+
+          # strip 'v' prefix and split into major.minor
+          LATEST_VERSION=${LATEST_VERSION//v/}
+          IFS='.' read -r -a VERSION_PARTS <<< "$LATEST_VERSION"
+
+          MAJOR=${VERSION_PARTS[0]}
+          MINOR=${VERSION_PARTS[1]}
+
+          # increment the minor version
+          MINOR=$((MINOR + 1))
+
+          NEXT_VERSION="${MAJOR}.${MINOR}"
+
+          echo "Major: $MAJOR"
+          echo "Minor: $MINOR"
+
+          echo "Next version: $NEXT_VERSION"
+          echo "::set-output name=next_version::$NEXT_VERSION"
+          echo "::set-output name=next_version_major::$MAJOR"
+          echo "::set-output name=next_version_minor::$MINOR"          

.github/workflows/generate_pot.yml

@@ -35,7 +35,7 @@ jobs:
           -o cemu.pot
 
       - name: Upload artifact
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: POT file
           path: ./cemu.pot

.gitignore

@@ -39,6 +39,8 @@ bin/sdcard/*
 bin/screenshots/*
 bin/dump/*
 bin/cafeLibs/*
+bin/portable/*
+bin/keys.txt
 
 !bin/shaderCache/info.txt
 bin/shaderCache/*

.gitmodules

@@ -9,10 +9,12 @@
 [submodule "dependencies/vcpkg"]
 	path = dependencies/vcpkg
 	url = https://github.com/microsoft/vcpkg
-	shallow = true
+	shallow = false
 [submodule "dependencies/Vulkan-Headers"]
 	path = dependencies/Vulkan-Headers
 	url = https://github.com/KhronosGroup/Vulkan-Headers
+	shallow = true
 [submodule "dependencies/imgui"]
 	path = dependencies/imgui
 	url = https://github.com/ocornut/imgui
+	shallow = true

BUILD.md

@@ -1,4 +1,26 @@
-# Build instructions
+# Build Instructions
+
+## Table of Contents
+
+- [Windows](#windows)
+- [Linux](#linux)
+   - [Dependencies](#dependencies)
+      - [For Arch and derivatives:](#for-arch-and-derivatives)
+      - [For Debian, Ubuntu and derivatives](#for-debian-ubuntu-and-derivatives)
+      - [For Fedora and derivatives:](#for-fedora-and-derivatives)
+   - [Build Cemu](#build-cemu)
+      - [CMake and Clang](#cmake-and-clang)
+      - [GCC](#gcc)
+      - [Debug Build](#debug-build)
+      - [Troubleshooting Steps](#troubleshooting-steps)
+         - [Compiling Errors](#compiling-errors)
+         - [Building Errors](#building-errors)
+- [macOS](#macos)
+   - [Installing brew](#installing-brew)
+   - [Installing Tool Dependencies](#installing-tool-dependencies)
+   - [Installing Library Dependencies](#installing-library-dependencies)
+   - [Build Cemu using CMake](#build-cemu-using-cmake)
+- [Updating Cemu and source code](#updating-cemu-and-source-code)
 
 ## Windows
 
@@ -19,79 +41,144 @@ Any other IDE should also work as long as it has CMake and MSVC support. CLion a
 
 ## Linux
 
-To compile Cemu, a recent enough compiler and STL with C++20 support is required! clang-15 or higher is what we recommend.
+To compile Cemu, a recent enough compiler and STL with C++20 support is required! Clang-15 or higher is what we recommend.
 
-### Installing dependencies
+### Dependencies
 
-#### For Ubuntu and derivatives:
-`sudo apt install -y cmake curl clang-15 freeglut3-dev git libgcrypt20-dev libglm-dev libgtk-3-dev libpulse-dev libsecret-1-dev libsystemd-dev nasm ninja-build`
+#### For Arch and derivatives:
+`sudo pacman -S --needed base-devel bluez-libs clang cmake freeglut git glm gtk3 libgcrypt libpulse libsecret linux-headers llvm nasm ninja systemd unzip zip`
+
+#### For Debian, Ubuntu and derivatives:
+`sudo apt install -y cmake curl clang-15 freeglut3-dev git libbluetooth-dev libgcrypt20-dev libglm-dev libgtk-3-dev libpulse-dev libsecret-1-dev libsystemd-dev libtool nasm ninja-build`
 
 You may also need to install `libusb-1.0-0-dev` as a workaround for an issue with the vcpkg hidapi package.
 
-At step 3 while building, use:
+At Step 3 in [Build Cemu using cmake and clang](#build-cemu-using-cmake-and-clang), use the following command instead:
    `cmake -S . -B build -DCMAKE_BUILD_TYPE=release -DCMAKE_C_COMPILER=/usr/bin/clang-15 -DCMAKE_CXX_COMPILER=/usr/bin/clang++-15 -G Ninja -DCMAKE_MAKE_PROGRAM=/usr/bin/ninja`
 
-#### For Arch and derivatives:
-`sudo pacman -S --needed base-devel clang cmake freeglut git glm gtk3 libgcrypt libpulse libsecret linux-headers llvm nasm ninja systemd unzip zip`
-
 #### For Fedora and derivatives:
-`sudo dnf install clang cmake cubeb-devel freeglut-devel git glm-devel gtk3-devel kernel-headers libgcrypt-devel libsecret-devel libtool libusb1-devel nasm ninja-build perl-core systemd-devel zlib-devel`
+`sudo dnf install bluez-libs-devel clang cmake cubeb-devel freeglut-devel git glm-devel gtk3-devel kernel-headers libgcrypt-devel libsecret-devel libtool libusb1-devel llvm nasm ninja-build perl-core systemd-devel wayland-protocols-devel zlib-devel zlib-static`
 
-### Build Cemu using cmake and clang
-1. `git clone --recursive https://github.com/cemu-project/Cemu`
-2. `cd Cemu`
-3. `cmake -S . -B build -DCMAKE_BUILD_TYPE=release -DCMAKE_C_COMPILER=/usr/bin/clang -DCMAKE_CXX_COMPILER=/usr/bin/clang++ -G Ninja`
-4. `cmake --build build`
-5. You should now have a Cemu executable file in the /bin folder, which you can run using `./bin/Cemu_release`.
+### Build Cemu
 
-#### Using GCC
-While we build and test Cemu using clang, using GCC might work better with your distro (they should be fairly similar performance/issues wise and should only be considered if compilation is the issue).
+#### CMake and Clang
 
-You can use GCC by doing the following:
-- make sure you have g++ installed in your system
-  - installation for Ubuntu and derivatives: `sudo apt install g++`
-  - installation for Fedora and derivatives: `sudo dnf install gcc-c++`
-- replace the step 3 with the following:
-`cmake -S . -B build -DCMAKE_BUILD_TYPE=release -DCMAKE_C_COMPILER=/usr/bin/gcc -DCMAKE_CXX_COMPILER=/usr/bin/g++ -G Ninja`
+```
+git clone --recursive https://github.com/cemu-project/Cemu
+cd Cemu
+cmake -S . -B build -DCMAKE_BUILD_TYPE=release -DCMAKE_C_COMPILER=/usr/bin/clang -DCMAKE_CXX_COMPILER=/usr/bin/clang++ -G Ninja
+cmake --build build
+```
 
-#### Troubleshooting steps
- - If step 3 gives you an error about not being able to find ninja, try appending `-DCMAKE_MAKE_PROGRAM=/usr/bin/ninja` to the command and running it again.
- - If step 3 fails while compiling the boost-build dependency, it means you don't have a working/good standard library installation. Check the integrity of your system headers and making sure that C++ related packages are installed and intact.
- - If step 3 gives a random error, read the `[package-name-and-platform]-out.log` and `[package-name-and-platform]-err.log` for the actual reason to see if you might be lacking the headers from a dependency.
- - If step 3 is still failing or if you're not able to find the cause, please make an issue on our Github about it!
- - If step 3 fails during rebuild after `git pull` with an error that mentions RPATH, add this to the end of step 3: `-DCMAKE_BUILD_WITH_INSTALL_RPATH=ON`
- - If step 4 gives you an error that contains something like `main.cpp.o: in function 'std::__cxx11::basic_string...`, you likely are experiencing a clang-14 issue. This can only be fixed by either lowering the clang version or using GCC, see below.
- - If step 4 gives you a different error, you could report it to this repo or try using GCC. Just make sure your standard library and compilers are updated since Cemu uses a lot of modern features!
- - If step 4 gives you undefined libdecor_xx, you are likely experiencing an issue with sdl2 package that comes with vcpkg. Delete sdl2 from vcpkg.json in source file and recompile.
- - If step 4 gives you `fatal error: 'span' file not found`, then you're either missing `libstdc++` or are using a version that's too old. Install at least v10 with your package manager, eg `sudo apt install libstdc++-10-dev`. See #644.
+#### GCC
+
+If you are building using GCC, make sure you have g++ installed:
+- Installation for Arch and derivatives: `sudo pacman -S gcc`
+- Installation for Debian, Ubuntu and derivatives: `sudo apt install g++`
+- Installation for Fedora and derivatives: `sudo dnf install gcc-c++`
+
+```
+git clone --recursive https://github.com/cemu-project/Cemu
+cd Cemu
+cmake -S . -B build -DCMAKE_BUILD_TYPE=release -DCMAKE_C_COMPILER=/usr/bin/gcc -DCMAKE_CXX_COMPILER=/usr/bin/g++ -G Ninja
+cmake --build build
+```
+
+#### Debug Build
+
+```
+git clone --recursive https://github.com/cemu-project/Cemu
+cd Cemu
+cmake -S . -B build -DCMAKE_BUILD_TYPE=debug -DCMAKE_C_COMPILER=/usr/bin/clang -DCMAKE_CXX_COMPILER=/usr/bin/clang++ -G Ninja
+cmake --build build
+```
+
+If you are using GCC, replace `cmake -S . -B build -DCMAKE_BUILD_TYPE=debug -DCMAKE_C_COMPILER=/usr/bin/clang -DCMAKE_CXX_COMPILER=/usr/bin/clang++ -G Ninja` with `cmake -S . -B build -DCMAKE_BUILD_TYPE=debug -DCMAKE_C_COMPILER=/usr/bin/gcc -DCMAKE_CXX_COMPILER=/usr/bin/g++ -G Ninja`
+
+#### Troubleshooting Steps
+
+##### Compiling Errors
+
+This section refers to running `cmake -S...` (truncated).
+
+* `vcpkg install failed`
+   * Run the following in the root directory and try running the command again (don't forget to change directories afterwards):
+      * `cd dependencies/vcpkg && git fetch --unshallow`
+* `Please ensure you're using the latest port files with git pull and vcpkg update.`
+   * Either:
+      * Update vcpkg by running by the following command:
+         * `git submodule update --remote dependencies/vcpkg`
+      * If you are sure vcpkg is up to date, check the following logs:
+         * `Cemu/dependencies/vcpkg/buildtrees/wxwidgets/config-x64-linux-out.log`
+         * `Cemu/dependencies/vcpkg/buildtrees/libsystemd/config-x64-linux-dbg-meson-log.txt.log`
+         * `Cemu/dependencies/vcpkg/buildtrees/libsystemd/config-x64-linux-dbg-out.log`
+* Not able to find Ninja.
+   * Add the following and try running the command again:
+      * `-DCMAKE_MAKE_PROGRAM=/usr/bin/ninja`
+* Compiling failed during the boost-build dependency.
+   * It means you don't have a working/good standard library installation. Check the integrity of your system headers and making sure that C++ related packages are installed and intact.
+* Compiling failed during rebuild after `git pull` with an error that mentions RPATH
+   * Add the following and try running the command again:
+      * `-DCMAKE_BUILD_WITH_INSTALL_RPATH=ON`
+* Environment variable `VCPKG_FORCE_SYSTEM_BINARIES` must be set.
+   * Execute the folowing and then try running the command again:
+      * `export VCPKG_FORCE_SYSTEM_BINARIES=1`
+* If you are getting a random error, read the [package-name-and-platform]-out.log and [package-name-and-platform]-err.log for the actual reason to see if you might be lacking the headers from a dependency.
+
+
+If you are getting a different error than any of the errors listed above, you may either open an issue in this repo or try using [GCC](#gcc). Make sure your standard library and compilers are updated since Cemu uses a lot of modern features!
+
+
+##### Building Errors
+
+This section refers to running `cmake --build build`.
+
+* `main.cpp.o: in function 'std::__cxx11::basic_string...`
+   * You likely are experiencing a clang-14 issue. This can only be fixed by either lowering the clang version or using GCC, see [GCC](#gcc).
+* `fatal error: 'span' file not found`
+   *  You're either missing `libstdc++` or are using a version that's too old. Install at least v10 with your package manager, eg `sudo apt install libstdc++-10-dev`. See [#644](https://github.com/cemu-project/Cemu/issues/644).
+* `undefined libdecor_xx`
+   * You are likely experiencing an issue with sdl2 package that comes with vcpkg. Delete sdl2 from vcpkg.json in source file and recompile.
+
+If you are getting a different error than any of the errors listed above, you may either open an issue in this repo or try using [GCC](#gcc). Make sure your standard library and compilers are updated since Cemu uses a lot of modern features!
 
 ## macOS
 
-To compile Cemu, a recent enough compiler and STL with C++20 support is required! LLVM 13 and 
-below, built in LLVM, and Xcode LLVM don't support the C++20 feature set required. The OpenGL graphics
-API isn't support on macOS, Vulkan must be used. Additionally Vulkan must be used through the 
-Molten-VK compatibility layer
-
-### On Apple Silicon Macs, Rosetta 2 and the x86_64 version of Homebrew must be used
-
-You can skip this section if you have an Intel Mac. Every time you compile, you need to perform steps 2.
-
-1. `softwareupdate --install-rosetta` # Install Rosetta 2 if you don't have it. This only has to be done once
-2. `arch -x86_64 zsh` # run an x64 shell
+To compile Cemu, a recent enough compiler and STL with C++20 support is required! LLVM 13 and below
+don't support the C++20 feature set required, so either install LLVM from Homebrew or make sure that
+you have a recent enough version of Xcode. Xcode 15 is known to work. The OpenGL graphics API isn't
+supported on macOS, so Vulkan must be used through the Molten-VK compatibility layer.
 
 ### Installing brew
 
 1. `/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"`
-2. `eval "$(/usr/local/Homebrew/bin/brew shellenv)"` # set x86_64 brew env
+2. Set up the Homebrew shell environment:
+   1. **On an Intel Mac:** `eval "$(/usr/local/Homebrew/bin/brew shellenv)"`
+   2. **On an Apple Silicon Mac:** eval `"$(/opt/homebrew/bin/brew shellenv)"`
 
-### Installing dependencies
+### Installing Tool Dependencies
 
-`brew install boost git cmake llvm ninja nasm molten-vk automake libtool`
+The native versions of these can be used regardless of what type of Mac you have.
+
+`brew install git cmake ninja nasm automake libtool`
+
+### Installing Library Dependencies
+
+**On Apple Silicon Macs, Rosetta 2 and the x86_64 version of Homebrew must be used to install these dependencies:**
+1. `softwareupdate --install-rosetta` # Install Rosetta 2 if you don't have it. This only has to be done once
+2. `arch -x86_64 zsh` # run an x64 shell
+3. `/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"`
+4. `eval "$(/usr/local/Homebrew/bin/brew shellenv)"`
+
+Then install the dependencies:
+
+`brew install boost molten-vk`
+
+### Build Cemu using CMake
 
-### Build Cemu using cmake and clang
 1. `git clone --recursive https://github.com/cemu-project/Cemu`
 2. `cd Cemu`
-3. `cmake -S . -B build -DCMAKE_BUILD_TYPE=release -DCMAKE_C_COMPILER=/usr/local/opt/llvm/bin/clang -DCMAKE_CXX_COMPILER=/usr/local/opt/llvm/bin/clang++ -G Ninja`
+3. `cmake -S . -B build -DCMAKE_BUILD_TYPE=release -DCMAKE_OSX_ARCHITECTURES=x86_64 -G Ninja`
 4. `cmake --build build`
 5. You should now have a Cemu executable file in the /bin folder, which you can run using `./bin/Cemu_release`.
 
@@ -104,3 +191,42 @@ You can skip this section if you have an Intel Mac. Every time you compile, you
 2. Then, you can rebuild Cemu using the steps listed above, according to whether you use Linux or Windows.
 
 If CMake complains about Cemu already being compiled or another similar error, try deleting the `CMakeCache.txt` file inside the `build` folder and retry building.
+
+## CMake configure flags
+Some flags can be passed during CMake configure to customise which features are enabled on build.
+
+Example usage: `cmake -S . -B build -DCMAKE_BUILD_TYPE=release -DENABLE_SDL=ON -DENABLE_VULKAN=OFF`
+
+### All platforms
+| Flag               |   | Description                                                                 | Default | Note               |
+|--------------------|:--|-----------------------------------------------------------------------------|---------|--------------------|
+| ALLOW_PORTABLE     |   | Allow Cemu to use the `portable` directory to store configs and data        | ON      |                    |
+| CEMU_CXX_FLAGS     |   | Flags passed straight to the compiler, e.g. `-march=native`, `-Wall`, `/W3` | ""      |                    |
+| ENABLE_CUBEB       |   | Enable cubeb audio backend                                                  | ON      |                    |
+| ENABLE_DISCORD_RPC |   | Enable Discord Rich presence support                                        | ON      |                    |
+| ENABLE_OPENGL      |   | Enable OpenGL graphics backend                                              | ON      | Currently required |
+| ENABLE_HIDAPI      |   | Enable HIDAPI (used for Wiimote controller API)                             | ON      |                    |
+| ENABLE_SDL         |   | Enable SDLController controller API                                         | ON      | Currently required |
+| ENABLE_VCPKG       |   | Use VCPKG package manager to obtain dependencies                            | ON      |                    |
+| ENABLE_VULKAN      |   | Enable the Vulkan graphics backend                                          | ON      |                    |
+| ENABLE_WXWIDGETS   |   | Enable wxWidgets UI                                                         | ON      | Currently required |
+
+### Windows
+| Flag               | Description                       | Default | Note               |
+|--------------------|-----------------------------------|---------|--------------------|
+| ENABLE_DIRECTAUDIO | Enable DirectAudio audio backend  | ON      | Currently required |
+| ENABLE_DIRECTINPUT | Enable DirectInput controller API | ON      | Currently required |
+| ENABLE_XAUDIO      | Enable XAudio audio backend       | ON      |                    |
+| ENABLE_XINPUT      | Enable XInput controller API      | ON      |                    |
+
+### Linux
+| Flag                  | Description                                        | Default |
+|-----------------------|----------------------------------------------------|---------|
+| ENABLE_BLUEZ          | Build with Bluez (used for Wiimote controller API) | ON      |
+| ENABLE_FERAL_GAMEMODE | Enable Feral Interactive GameMode support          | ON      |
+| ENABLE_WAYLAND        | Enable Wayland support                             | ON      |
+
+### macOS
+| Flag         | Description                                    | Default |
+|--------------|------------------------------------------------|---------|
+| MACOS_BUNDLE | MacOS executable will be an application bundle | OFF     |

CMakeLists.txt

@@ -1,12 +1,14 @@
 cmake_minimum_required(VERSION 3.21.1)
 
 option(ENABLE_VCPKG "Enable the vcpkg package manager" ON)
-option(PORTABLE "All data created and maintained by Cemu will be in the directory where the executable file is located" ON)
 option(MACOS_BUNDLE "The executable when built on macOS will be created as an application bundle" OFF)
-set(EXPERIMENTAL_VERSION "" CACHE STRING "") # used by CI script to set experimental version
+option(ALLOW_PORTABLE "Allow Cemu to be run in portable mode" ON)
+
+# used by CI script to set version:
+set(EMULATOR_VERSION_MAJOR "0" CACHE STRING "")
+set(EMULATOR_VERSION_MINOR "0" CACHE STRING "")
+set(EMULATOR_VERSION_PATCH "0" CACHE STRING "")
 
-if (EXPERIMENTAL_VERSION)
-	add_definitions(-DEMULATOR_VERSION_MINOR=${EXPERIMENTAL_VERSION})
 execute_process(
 		COMMAND git log --format=%h -1
 		WORKING_DIRECTORY ${CMAKE_CURRENT_LIST_DIR}
@@ -14,11 +16,30 @@ if (EXPERIMENTAL_VERSION)
 		OUTPUT_STRIP_TRAILING_WHITESPACE
 )
 add_definitions(-DEMULATOR_HASH=${GIT_HASH})
-endif()
 
 if (ENABLE_VCPKG)
+	# check if vcpkg is shallow and unshallow it if necessary
+	execute_process(
+	COMMAND git rev-parse --is-shallow-repository
+	WORKING_DIRECTORY ${CMAKE_SOURCE_DIR}/dependencies/vcpkg
+	OUTPUT_VARIABLE is_vcpkg_shallow
+	OUTPUT_STRIP_TRAILING_WHITESPACE
+    )
+	
+	if(is_vcpkg_shallow STREQUAL "true")
+		message(STATUS "vcpkg is shallow. Unshallowing it now...")
+		execute_process(
+			COMMAND git fetch --unshallow
+			WORKING_DIRECTORY "${CMAKE_SOURCE_DIR}/dependencies/vcpkg"
+			RESULT_VARIABLE result
+			OUTPUT_VARIABLE output
+		)
+	endif()
+
 	if(UNIX AND NOT APPLE)
 		set(VCPKG_OVERLAY_PORTS "${CMAKE_CURRENT_LIST_DIR}/dependencies/vcpkg_overlay_ports_linux")
+	elseif(APPLE)
+		set(VCPKG_OVERLAY_PORTS "${CMAKE_CURRENT_LIST_DIR}/dependencies/vcpkg_overlay_ports_mac")
 	else()
 		set(VCPKG_OVERLAY_PORTS "${CMAKE_CURRENT_LIST_DIR}/dependencies/vcpkg_overlay_ports")
 	endif()
@@ -43,9 +64,9 @@ set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
 
 add_compile_definitions($<$<CONFIG:Debug>:CEMU_DEBUG_ASSERT>) # if build type is debug, set CEMU_DEBUG_ASSERT
 
-if(PORTABLE)
-	add_compile_definitions(PORTABLE)
-endif()
+add_definitions(-DEMULATOR_VERSION_MAJOR=${EMULATOR_VERSION_MAJOR})
+add_definitions(-DEMULATOR_VERSION_MINOR=${EMULATOR_VERSION_MINOR})
+add_definitions(-DEMULATOR_VERSION_PATCH=${EMULATOR_VERSION_PATCH})
 
 set_property(GLOBAL PROPERTY USE_FOLDERS ON)
 
@@ -72,11 +93,13 @@ endif()
 
 if (APPLE)
     enable_language(OBJC OBJCXX)
+    set(CMAKE_OSX_DEPLOYMENT_TARGET "12.0")
 endif()
 
 if (UNIX AND NOT APPLE)
 	option(ENABLE_WAYLAND "Build with Wayland support" ON)
 	option(ENABLE_FERAL_GAMEMODE "Enables Feral Interactive GameMode Support" ON)
+	option(ENABLE_BLUEZ "Build with Bluez support" ON)
 endif()
 
 option(ENABLE_OPENGL "Enables the OpenGL backend" ON)
@@ -89,10 +112,9 @@ if (WIN32)
 	option(ENABLE_XINPUT "Enables the usage of XInput" ON)
 	option(ENABLE_DIRECTINPUT "Enables the usage of DirectInput" ON)
 	add_compile_definitions(HAS_DIRECTINPUT)
-	set(ENABLE_WIIMOTE ON)
-elseif (UNIX)
-	option(ENABLE_HIDAPI "Build with HIDAPI" ON)
 endif()
+
+option(ENABLE_HIDAPI "Build with HIDAPI" ON)
 option(ENABLE_SDL "Enables the SDLController backend" ON)
 
 # audio backends
@@ -102,23 +124,6 @@ if (WIN32)
 endif()
 option(ENABLE_CUBEB "Enabled cubeb backend" ON)
 
-# usb hid backends
-if (WIN32)
-	option(ENABLE_NSYSHID_WINDOWS_HID "Enables the native Windows HID backend for nsyshid" ON)
-endif ()
-# libusb and windows hid backends shouldn't be active at the same time; otherwise we'd see all devices twice!
-if (NOT ENABLE_NSYSHID_WINDOWS_HID)
-	option(ENABLE_NSYSHID_LIBUSB "Enables the libusb backend for nsyshid" ON)
-else ()
-	set(ENABLE_NSYSHID_LIBUSB OFF CACHE BOOL "" FORCE)
-endif ()
-if (ENABLE_NSYSHID_WINDOWS_HID)
-	add_compile_definitions(NSYSHID_ENABLE_BACKEND_WINDOWS_HID)
-endif ()
-if (ENABLE_NSYSHID_LIBUSB)
-	add_compile_definitions(NSYSHID_ENABLE_BACKEND_LIBUSB)
-endif ()
-
 option(ENABLE_WXWIDGETS "Build with wxWidgets UI (Currently required)" ON)
 
 set(THREADS_PREFER_PTHREAD_FLAG true)
@@ -159,6 +164,12 @@ if (UNIX AND NOT APPLE)
 	endif()
 	find_package(GTK3 REQUIRED)
 
+	if(ENABLE_BLUEZ)
+		find_package(bluez REQUIRED)
+		set(ENABLE_WIIMOTE ON)
+		add_compile_definitions(HAS_BLUEZ)
+	endif()
+
 endif()
 
 if (ENABLE_VULKAN)
@@ -202,7 +213,7 @@ if (ENABLE_CUBEB)
 		option(BUILD_TOOLS "" OFF)
 		option(BUNDLE_SPEEX "" OFF)
 		set(USE_WINMM OFF CACHE BOOL "")
-		add_subdirectory("dependencies/cubeb" EXCLUDE_FROM_ALL)
+		add_subdirectory("dependencies/cubeb" EXCLUDE_FROM_ALL SYSTEM)
 		set_property(TARGET cubeb PROPERTY MSVC_RUNTIME_LIBRARY "MultiThreaded$<$<CONFIG:Debug>:Debug>")
 		add_library(cubeb::cubeb ALIAS cubeb)
 	endif()

README.md

@@ -48,7 +48,7 @@ Before submitting a pull request, please read and follow our code style guidelin
 
 If coding isn't your thing, testing games and making detailed bug reports or updating the (usually outdated) compatibility wiki is also appreciated!
 
-Questions about Cemu's software architecture can also be answered on Discord (through the Matrix bridge).
+Questions about Cemu's software architecture can also be answered on Discord (or through the Matrix bridge).
 
 ## License
 Cemu is licensed under [Mozilla Public License 2.0](/LICENSE.txt). Exempt from this are all files in the dependencies directory for which the licenses of the original code apply as well as some individual files in the src folder, as specified in those file headers respectively.

bin/shaderCache/info.txt

@@ -1 +0,0 @@
-If you plan to transfer the shader cache to a different PC or Cemu installation you only need to copy the 'transferable' directory.

cmake/Findbluez.cmake

@@ -0,0 +1,20 @@
+# SPDX-FileCopyrightText: 2022 Andrea Pappacoda <andrea@pappacoda.it>
+# SPDX-License-Identifier: ISC
+
+find_package(bluez CONFIG)
+if (NOT bluez_FOUND)
+  find_package(PkgConfig)
+  if (PKG_CONFIG_FOUND)
+    pkg_search_module(bluez IMPORTED_TARGET GLOBAL bluez-1.0 bluez)
+    if (bluez_FOUND)
+      add_library(bluez::bluez ALIAS PkgConfig::bluez)
+    endif ()
+  endif ()
+endif ()
+
+find_package_handle_standard_args(bluez
+    REQUIRED_VARS
+    bluez_LINK_LIBRARIES
+    bluez_FOUND
+    VERSION_VAR bluez_VERSION
+)

dependencies/ih264d/CMakeLists.txt

@@ -117,7 +117,13 @@ add_library (ih264d
 "decoder/ivd.h"
 )
 
-if (CMAKE_SYSTEM_PROCESSOR STREQUAL "x86_64" OR CMAKE_SYSTEM_PROCESSOR STREQUAL "amd64" OR CMAKE_SYSTEM_PROCESSOR STREQUAL "AMD64")
+if (CMAKE_OSX_ARCHITECTURES)
+set(IH264D_ARCHITECTURE ${CMAKE_OSX_ARCHITECTURES})
+else()
+set(IH264D_ARCHITECTURE ${CMAKE_SYSTEM_PROCESSOR})
+endif()
+
+if (IH264D_ARCHITECTURE STREQUAL "x86_64" OR IH264D_ARCHITECTURE STREQUAL "amd64" OR IH264D_ARCHITECTURE STREQUAL "AMD64")
 set(LIBAVCDEC_X86_INCLUDES "common/x86" "decoder/x86")
 include_directories("common/" "decoder/" ${LIBAVCDEC_X86_INCLUDES})
 target_sources(ih264d PRIVATE
@@ -140,7 +146,7 @@ target_sources(ih264d PRIVATE
 "decoder/x86/ih264d_function_selector_sse42.c"
 "decoder/x86/ih264d_function_selector_ssse3.c"
 )
-elseif(CMAKE_SYSTEM_PROCESSOR STREQUAL "aarch64")
+elseif(IH264D_ARCHITECTURE STREQUAL "aarch64" OR IH264D_ARCHITECTURE STREQUAL "arm64")
 enable_language( C CXX ASM )
 set(LIBAVCDEC_ARM_INCLUDES "common/armv8" "decoder/arm")
 include_directories("common/" "decoder/" ${LIBAVCDEC_ARM_INCLUDES})
@@ -178,7 +184,7 @@ target_sources(ih264d PRIVATE
 )
 target_compile_options(ih264d PRIVATE -DARMV8)
 else()
-message(FATAL_ERROR "ih264d unknown architecture: ${CMAKE_SYSTEM_PROCESSOR}")
+message(FATAL_ERROR "ih264d unknown architecture: ${IH264D_ARCHITECTURE}")
 endif()
 
 if(MSVC)

dependencies/vcpkg

@@ -1 +1 @@
-Subproject commit b81bc3a83fdbdffe80325eeabb2ec735a1f3c29d
+Subproject commit 533a5fda5c0646d1771345fb572e759283444d5f

dependencies/vcpkg_overlay_ports/sdl2/deps.patch

@@ -1,13 +0,0 @@
-diff --git a/cmake/sdlchecks.cmake b/cmake/sdlchecks.cmake
-index 65a98efbe..2f99f28f1 100644
---- a/cmake/sdlchecks.cmake
-+++ b/cmake/sdlchecks.cmake
-@@ -352,7 +352,7 @@ endmacro()
- # - HAVE_SDL_LOADSO opt
- macro(CheckLibSampleRate)
-   if(SDL_LIBSAMPLERATE)
--    find_package(SampleRate QUIET)
-+    find_package(SampleRate CONFIG REQUIRED)
-     if(SampleRate_FOUND AND TARGET SampleRate::samplerate)
-       set(HAVE_LIBSAMPLERATE TRUE)
-       set(HAVE_LIBSAMPLERATE_H TRUE)

dependencies/vcpkg_overlay_ports/sdl2/portfile.cmake

@@ -1,130 +0,0 @@
-vcpkg_from_github(
-    OUT_SOURCE_PATH SOURCE_PATH
-    REPO libsdl-org/SDL
-    REF "release-${VERSION}"
-    SHA512 90858ae8c5fdddd5e13724e05ad0970e11bbab1df8a0201c3f4ce354dc6018e5d4ab7279402a263c716aacdaa52745f78531dc225d48d790ee9307e2f6198695
-    HEAD_REF main
-    PATCHES
-        deps.patch
-)
-
-string(COMPARE EQUAL "${VCPKG_LIBRARY_LINKAGE}" "static" SDL_STATIC)
-string(COMPARE EQUAL "${VCPKG_LIBRARY_LINKAGE}" "dynamic" SDL_SHARED)
-string(COMPARE EQUAL "${VCPKG_CRT_LINKAGE}" "static" FORCE_STATIC_VCRT)
-
-vcpkg_check_features(OUT_FEATURE_OPTIONS FEATURE_OPTIONS
-    FEATURES
-        vulkan   SDL_VULKAN
-        x11      SDL_X11
-        wayland  SDL_WAYLAND
-        samplerate SDL_LIBSAMPLERATE
-        ibus     SDL_IBUS
-)
-
-if ("x11" IN_LIST FEATURES)
-    message(WARNING "You will need to install Xorg dependencies to use feature x11:\nsudo apt install libx11-dev libxft-dev libxext-dev\n")
-endif()
-if ("wayland" IN_LIST FEATURES)
-    message(WARNING "You will need to install Wayland dependencies to use feature wayland:\nsudo apt install libwayland-dev libxkbcommon-dev libegl1-mesa-dev\n")
-endif()
-if ("ibus" IN_LIST FEATURES)
-    message(WARNING "You will need to install ibus dependencies to use feature ibus:\nsudo apt install libibus-1.0-dev\n")
-endif()
-
-if(VCPKG_TARGET_IS_UWP)
-    set(configure_opts WINDOWS_USE_MSBUILD)
-endif()
-
-vcpkg_cmake_configure(
-    SOURCE_PATH "${SOURCE_PATH}"
-    ${configure_opts}
-    OPTIONS ${FEATURE_OPTIONS}
-        -DSDL_STATIC=${SDL_STATIC}
-        -DSDL_SHARED=${SDL_SHARED}
-        -DSDL_FORCE_STATIC_VCRT=${FORCE_STATIC_VCRT}
-        -DSDL_LIBC=ON
-        -DSDL_TEST=OFF
-        -DSDL_INSTALL_CMAKEDIR="cmake"
-        -DCMAKE_DISABLE_FIND_PACKAGE_Git=ON
-        -DSDL_LIBSAMPLERATE_SHARED=OFF
-    MAYBE_UNUSED_VARIABLES
-        SDL_FORCE_STATIC_VCRT
-)
-
-vcpkg_cmake_install()
-vcpkg_cmake_config_fixup(CONFIG_PATH cmake)
-
-file(REMOVE_RECURSE
-    "${CURRENT_PACKAGES_DIR}/debug/include"
-    "${CURRENT_PACKAGES_DIR}/debug/share"
-    "${CURRENT_PACKAGES_DIR}/bin/sdl2-config"
-    "${CURRENT_PACKAGES_DIR}/debug/bin/sdl2-config"
-    "${CURRENT_PACKAGES_DIR}/SDL2.framework"
-    "${CURRENT_PACKAGES_DIR}/debug/SDL2.framework"
-    "${CURRENT_PACKAGES_DIR}/share/licenses"
-    "${CURRENT_PACKAGES_DIR}/share/aclocal"
-)
-
-file(GLOB BINS "${CURRENT_PACKAGES_DIR}/debug/bin/*" "${CURRENT_PACKAGES_DIR}/bin/*")
-if(NOT BINS)
-    file(REMOVE_RECURSE
-        "${CURRENT_PACKAGES_DIR}/bin"
-        "${CURRENT_PACKAGES_DIR}/debug/bin"
-    )
-endif()
-
-if(VCPKG_TARGET_IS_WINDOWS AND NOT VCPKG_TARGET_IS_UWP AND NOT VCPKG_TARGET_IS_MINGW)
-    if(NOT DEFINED VCPKG_BUILD_TYPE OR VCPKG_BUILD_TYPE STREQUAL "release")
-        file(MAKE_DIRECTORY "${CURRENT_PACKAGES_DIR}/lib/manual-link")
-        file(RENAME "${CURRENT_PACKAGES_DIR}/lib/SDL2main.lib" "${CURRENT_PACKAGES_DIR}/lib/manual-link/SDL2main.lib")
-    endif()
-    if(NOT DEFINED VCPKG_BUILD_TYPE OR VCPKG_BUILD_TYPE STREQUAL "debug")
-        file(MAKE_DIRECTORY "${CURRENT_PACKAGES_DIR}/debug/lib/manual-link")
-        file(RENAME "${CURRENT_PACKAGES_DIR}/debug/lib/SDL2maind.lib" "${CURRENT_PACKAGES_DIR}/debug/lib/manual-link/SDL2maind.lib")
-    endif()
-
-    file(GLOB SHARE_FILES "${CURRENT_PACKAGES_DIR}/share/sdl2/*.cmake")
-    foreach(SHARE_FILE ${SHARE_FILES})
-        vcpkg_replace_string("${SHARE_FILE}" "lib/SDL2main" "lib/manual-link/SDL2main")
-    endforeach()
-endif()
-
-vcpkg_copy_pdbs()
-
-set(DYLIB_COMPATIBILITY_VERSION_REGEX "set\\(DYLIB_COMPATIBILITY_VERSION (.+)\\)")
-set(DYLIB_CURRENT_VERSION_REGEX "set\\(DYLIB_CURRENT_VERSION (.+)\\)")
-file(STRINGS "${SOURCE_PATH}/CMakeLists.txt" DYLIB_COMPATIBILITY_VERSION REGEX ${DYLIB_COMPATIBILITY_VERSION_REGEX})
-file(STRINGS "${SOURCE_PATH}/CMakeLists.txt" DYLIB_CURRENT_VERSION REGEX ${DYLIB_CURRENT_VERSION_REGEX})
-string(REGEX REPLACE ${DYLIB_COMPATIBILITY_VERSION_REGEX} "\\1" DYLIB_COMPATIBILITY_VERSION "${DYLIB_COMPATIBILITY_VERSION}")
-string(REGEX REPLACE ${DYLIB_CURRENT_VERSION_REGEX} "\\1" DYLIB_CURRENT_VERSION "${DYLIB_CURRENT_VERSION}")
-
-if(NOT DEFINED VCPKG_BUILD_TYPE OR VCPKG_BUILD_TYPE STREQUAL "debug")
-    vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/debug/lib/pkgconfig/sdl2.pc" "-lSDL2main" "-lSDL2maind")
-    vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/debug/lib/pkgconfig/sdl2.pc" "-lSDL2 " "-lSDL2d ")
-    vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/debug/lib/pkgconfig/sdl2.pc" "-lSDL2-static " "-lSDL2-staticd ")
-endif()
-
-if(VCPKG_LIBRARY_LINKAGE STREQUAL "dynamic" AND VCPKG_TARGET_IS_WINDOWS AND NOT VCPKG_TARGET_IS_MINGW)
-    if(NOT DEFINED VCPKG_BUILD_TYPE OR VCPKG_BUILD_TYPE STREQUAL "release")
-        vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/lib/pkgconfig/sdl2.pc" "-lSDL2-static " " ")
-    endif()
-    if(NOT DEFINED VCPKG_BUILD_TYPE OR VCPKG_BUILD_TYPE STREQUAL "debug")
-        vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/debug/lib/pkgconfig/sdl2.pc" "-lSDL2-staticd " " ")
-    endif()
-endif()
-
-if(VCPKG_TARGET_IS_UWP)
-    if(NOT DEFINED VCPKG_BUILD_TYPE OR VCPKG_BUILD_TYPE STREQUAL "release")
-        vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/lib/pkgconfig/sdl2.pc" "$<$<CONFIG:Debug>:d>.lib" "")
-        vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/lib/pkgconfig/sdl2.pc" "-l-nodefaultlib:" "-nodefaultlib:")
-    endif()
-    if(NOT DEFINED VCPKG_BUILD_TYPE OR VCPKG_BUILD_TYPE STREQUAL "debug")
-        vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/debug/lib/pkgconfig/sdl2.pc" "$<$<CONFIG:Debug>:d>.lib" "d")
-        vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/debug/lib/pkgconfig/sdl2.pc" "-l-nodefaultlib:" "-nodefaultlib:")
-    endif()
-endif()
-
-vcpkg_fixup_pkgconfig()
-
-file(INSTALL "${CMAKE_CURRENT_LIST_DIR}/usage" DESTINATION "${CURRENT_PACKAGES_DIR}/share/${PORT}")
-vcpkg_install_copyright(FILE_LIST "${SOURCE_PATH}/LICENSE.txt")

dependencies/vcpkg_overlay_ports/sdl2/usage

@@ -1,8 +0,0 @@
-sdl2 provides CMake targets:
-
-    find_package(SDL2 CONFIG REQUIRED)
-    target_link_libraries(main
-        PRIVATE
-        $<TARGET_NAME_IF_EXISTS:SDL2::SDL2main>
-        $<IF:$<TARGET_EXISTS:SDL2::SDL2>,SDL2::SDL2,SDL2::SDL2-static>
-    )

dependencies/vcpkg_overlay_ports/sdl2/vcpkg.json

@@ -1,58 +0,0 @@
-{
-  "name": "sdl2",
-  "version": "2.26.5",
-  "description": "Simple DirectMedia Layer is a cross-platform development library designed to provide low level access to audio, keyboard, mouse, joystick, and graphics hardware via OpenGL and Direct3D.",
-  "homepage": "https://www.libsdl.org/download-2.0.php",
-  "license": "Zlib",
-  "dependencies": [
-    {
-      "name": "vcpkg-cmake",
-      "host": true
-    },
-    {
-      "name": "vcpkg-cmake-config",
-      "host": true
-    }
-  ],
-  "default-features": [
-    "base"
-  ],
-  "features": {
-    "base": {
-      "description": "Base functionality for SDL",
-      "dependencies": [
-        {
-          "name": "sdl2",
-          "default-features": false,
-          "features": [
-            "ibus",
-            "wayland",
-            "x11"
-          ],
-          "platform": "linux"
-        }
-      ]
-    },
-    "ibus": {
-      "description": "Build with ibus IME support",
-      "supports": "linux"
-    },
-    "samplerate": {
-      "description": "Use libsamplerate for audio rate conversion",
-      "dependencies": [
-        "libsamplerate"
-      ]
-    },
-    "vulkan": {
-      "description": "Vulkan functionality for SDL"
-    },
-    "wayland": {
-      "description": "Build with Wayland support",
-      "supports": "linux"
-    },
-    "x11": {
-      "description": "Build with X11 support",
-      "supports": "!windows"
-    }
-  }
-}

dependencies/vcpkg_overlay_ports_linux/sdl2/deps.patch

@@ -1,13 +0,0 @@
-diff --git a/cmake/sdlchecks.cmake b/cmake/sdlchecks.cmake
-index 65a98efbe..2f99f28f1 100644
---- a/cmake/sdlchecks.cmake
-+++ b/cmake/sdlchecks.cmake
-@@ -352,7 +352,7 @@ endmacro()
- # - HAVE_SDL_LOADSO opt
- macro(CheckLibSampleRate)
-   if(SDL_LIBSAMPLERATE)
--    find_package(SampleRate QUIET)
-+    find_package(SampleRate CONFIG REQUIRED)
-     if(SampleRate_FOUND AND TARGET SampleRate::samplerate)
-       set(HAVE_LIBSAMPLERATE TRUE)
-       set(HAVE_LIBSAMPLERATE_H TRUE)

dependencies/vcpkg_overlay_ports_linux/sdl2/portfile.cmake

@@ -1,130 +0,0 @@
-vcpkg_from_github(
-    OUT_SOURCE_PATH SOURCE_PATH
-    REPO libsdl-org/SDL
-    REF "release-${VERSION}"
-    SHA512 90858ae8c5fdddd5e13724e05ad0970e11bbab1df8a0201c3f4ce354dc6018e5d4ab7279402a263c716aacdaa52745f78531dc225d48d790ee9307e2f6198695
-    HEAD_REF main
-    PATCHES
-        deps.patch
-)
-
-string(COMPARE EQUAL "${VCPKG_LIBRARY_LINKAGE}" "static" SDL_STATIC)
-string(COMPARE EQUAL "${VCPKG_LIBRARY_LINKAGE}" "dynamic" SDL_SHARED)
-string(COMPARE EQUAL "${VCPKG_CRT_LINKAGE}" "static" FORCE_STATIC_VCRT)
-
-vcpkg_check_features(OUT_FEATURE_OPTIONS FEATURE_OPTIONS
-    FEATURES
-        vulkan   SDL_VULKAN
-        x11      SDL_X11
-        wayland  SDL_WAYLAND
-        samplerate SDL_LIBSAMPLERATE
-        ibus     SDL_IBUS
-)
-
-if ("x11" IN_LIST FEATURES)
-    message(WARNING "You will need to install Xorg dependencies to use feature x11:\nsudo apt install libx11-dev libxft-dev libxext-dev\n")
-endif()
-if ("wayland" IN_LIST FEATURES)
-    message(WARNING "You will need to install Wayland dependencies to use feature wayland:\nsudo apt install libwayland-dev libxkbcommon-dev libegl1-mesa-dev\n")
-endif()
-if ("ibus" IN_LIST FEATURES)
-    message(WARNING "You will need to install ibus dependencies to use feature ibus:\nsudo apt install libibus-1.0-dev\n")
-endif()
-
-if(VCPKG_TARGET_IS_UWP)
-    set(configure_opts WINDOWS_USE_MSBUILD)
-endif()
-
-vcpkg_cmake_configure(
-    SOURCE_PATH "${SOURCE_PATH}"
-    ${configure_opts}
-    OPTIONS ${FEATURE_OPTIONS}
-        -DSDL_STATIC=${SDL_STATIC}
-        -DSDL_SHARED=${SDL_SHARED}
-        -DSDL_FORCE_STATIC_VCRT=${FORCE_STATIC_VCRT}
-        -DSDL_LIBC=ON
-        -DSDL_TEST=OFF
-        -DSDL_INSTALL_CMAKEDIR="cmake"
-        -DCMAKE_DISABLE_FIND_PACKAGE_Git=ON
-        -DSDL_LIBSAMPLERATE_SHARED=OFF
-    MAYBE_UNUSED_VARIABLES
-        SDL_FORCE_STATIC_VCRT
-)
-
-vcpkg_cmake_install()
-vcpkg_cmake_config_fixup(CONFIG_PATH cmake)
-
-file(REMOVE_RECURSE
-    "${CURRENT_PACKAGES_DIR}/debug/include"
-    "${CURRENT_PACKAGES_DIR}/debug/share"
-    "${CURRENT_PACKAGES_DIR}/bin/sdl2-config"
-    "${CURRENT_PACKAGES_DIR}/debug/bin/sdl2-config"
-    "${CURRENT_PACKAGES_DIR}/SDL2.framework"
-    "${CURRENT_PACKAGES_DIR}/debug/SDL2.framework"
-    "${CURRENT_PACKAGES_DIR}/share/licenses"
-    "${CURRENT_PACKAGES_DIR}/share/aclocal"
-)
-
-file(GLOB BINS "${CURRENT_PACKAGES_DIR}/debug/bin/*" "${CURRENT_PACKAGES_DIR}/bin/*")
-if(NOT BINS)
-    file(REMOVE_RECURSE
-        "${CURRENT_PACKAGES_DIR}/bin"
-        "${CURRENT_PACKAGES_DIR}/debug/bin"
-    )
-endif()
-
-if(VCPKG_TARGET_IS_WINDOWS AND NOT VCPKG_TARGET_IS_UWP AND NOT VCPKG_TARGET_IS_MINGW)
-    if(NOT DEFINED VCPKG_BUILD_TYPE OR VCPKG_BUILD_TYPE STREQUAL "release")
-        file(MAKE_DIRECTORY "${CURRENT_PACKAGES_DIR}/lib/manual-link")
-        file(RENAME "${CURRENT_PACKAGES_DIR}/lib/SDL2main.lib" "${CURRENT_PACKAGES_DIR}/lib/manual-link/SDL2main.lib")
-    endif()
-    if(NOT DEFINED VCPKG_BUILD_TYPE OR VCPKG_BUILD_TYPE STREQUAL "debug")
-        file(MAKE_DIRECTORY "${CURRENT_PACKAGES_DIR}/debug/lib/manual-link")
-        file(RENAME "${CURRENT_PACKAGES_DIR}/debug/lib/SDL2maind.lib" "${CURRENT_PACKAGES_DIR}/debug/lib/manual-link/SDL2maind.lib")
-    endif()
-
-    file(GLOB SHARE_FILES "${CURRENT_PACKAGES_DIR}/share/sdl2/*.cmake")
-    foreach(SHARE_FILE ${SHARE_FILES})
-        vcpkg_replace_string("${SHARE_FILE}" "lib/SDL2main" "lib/manual-link/SDL2main")
-    endforeach()
-endif()
-
-vcpkg_copy_pdbs()
-
-set(DYLIB_COMPATIBILITY_VERSION_REGEX "set\\(DYLIB_COMPATIBILITY_VERSION (.+)\\)")
-set(DYLIB_CURRENT_VERSION_REGEX "set\\(DYLIB_CURRENT_VERSION (.+)\\)")
-file(STRINGS "${SOURCE_PATH}/CMakeLists.txt" DYLIB_COMPATIBILITY_VERSION REGEX ${DYLIB_COMPATIBILITY_VERSION_REGEX})
-file(STRINGS "${SOURCE_PATH}/CMakeLists.txt" DYLIB_CURRENT_VERSION REGEX ${DYLIB_CURRENT_VERSION_REGEX})
-string(REGEX REPLACE ${DYLIB_COMPATIBILITY_VERSION_REGEX} "\\1" DYLIB_COMPATIBILITY_VERSION "${DYLIB_COMPATIBILITY_VERSION}")
-string(REGEX REPLACE ${DYLIB_CURRENT_VERSION_REGEX} "\\1" DYLIB_CURRENT_VERSION "${DYLIB_CURRENT_VERSION}")
-
-if(NOT DEFINED VCPKG_BUILD_TYPE OR VCPKG_BUILD_TYPE STREQUAL "debug")
-    vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/debug/lib/pkgconfig/sdl2.pc" "-lSDL2main" "-lSDL2maind")
-    vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/debug/lib/pkgconfig/sdl2.pc" "-lSDL2 " "-lSDL2d ")
-    vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/debug/lib/pkgconfig/sdl2.pc" "-lSDL2-static " "-lSDL2-staticd ")
-endif()
-
-if(VCPKG_LIBRARY_LINKAGE STREQUAL "dynamic" AND VCPKG_TARGET_IS_WINDOWS AND NOT VCPKG_TARGET_IS_MINGW)
-    if(NOT DEFINED VCPKG_BUILD_TYPE OR VCPKG_BUILD_TYPE STREQUAL "release")
-        vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/lib/pkgconfig/sdl2.pc" "-lSDL2-static " " ")
-    endif()
-    if(NOT DEFINED VCPKG_BUILD_TYPE OR VCPKG_BUILD_TYPE STREQUAL "debug")
-        vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/debug/lib/pkgconfig/sdl2.pc" "-lSDL2-staticd " " ")
-    endif()
-endif()
-
-if(VCPKG_TARGET_IS_UWP)
-    if(NOT DEFINED VCPKG_BUILD_TYPE OR VCPKG_BUILD_TYPE STREQUAL "release")
-        vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/lib/pkgconfig/sdl2.pc" "$<$<CONFIG:Debug>:d>.lib" "")
-        vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/lib/pkgconfig/sdl2.pc" "-l-nodefaultlib:" "-nodefaultlib:")
-    endif()
-    if(NOT DEFINED VCPKG_BUILD_TYPE OR VCPKG_BUILD_TYPE STREQUAL "debug")
-        vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/debug/lib/pkgconfig/sdl2.pc" "$<$<CONFIG:Debug>:d>.lib" "d")
-        vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/debug/lib/pkgconfig/sdl2.pc" "-l-nodefaultlib:" "-nodefaultlib:")
-    endif()
-endif()
-
-vcpkg_fixup_pkgconfig()
-
-file(INSTALL "${CMAKE_CURRENT_LIST_DIR}/usage" DESTINATION "${CURRENT_PACKAGES_DIR}/share/${PORT}")
-vcpkg_install_copyright(FILE_LIST "${SOURCE_PATH}/LICENSE.txt")

dependencies/vcpkg_overlay_ports_linux/sdl2/usage

@@ -1,8 +0,0 @@
-sdl2 provides CMake targets:
-
-    find_package(SDL2 CONFIG REQUIRED)
-    target_link_libraries(main
-        PRIVATE
-        $<TARGET_NAME_IF_EXISTS:SDL2::SDL2main>
-        $<IF:$<TARGET_EXISTS:SDL2::SDL2>,SDL2::SDL2,SDL2::SDL2-static>
-    )

dependencies/vcpkg_overlay_ports_linux/sdl2/vcpkg.json

@@ -1,58 +0,0 @@
-{
-  "name": "sdl2",
-  "version": "2.26.5",
-  "description": "Simple DirectMedia Layer is a cross-platform development library designed to provide low level access to audio, keyboard, mouse, joystick, and graphics hardware via OpenGL and Direct3D.",
-  "homepage": "https://www.libsdl.org/download-2.0.php",
-  "license": "Zlib",
-  "dependencies": [
-    {
-      "name": "vcpkg-cmake",
-      "host": true
-    },
-    {
-      "name": "vcpkg-cmake-config",
-      "host": true
-    }
-  ],
-  "default-features": [
-    "base"
-  ],
-  "features": {
-    "base": {
-      "description": "Base functionality for SDL",
-      "dependencies": [
-        {
-          "name": "sdl2",
-          "default-features": false,
-          "features": [
-            "ibus",
-            "wayland",
-            "x11"
-          ],
-          "platform": "linux"
-        }
-      ]
-    },
-    "ibus": {
-      "description": "Build with ibus IME support",
-      "supports": "linux"
-    },
-    "samplerate": {
-      "description": "Use libsamplerate for audio rate conversion",
-      "dependencies": [
-        "libsamplerate"
-      ]
-    },
-    "vulkan": {
-      "description": "Vulkan functionality for SDL"
-    },
-    "wayland": {
-      "description": "Build with Wayland support",
-      "supports": "linux"
-    },
-    "x11": {
-      "description": "Build with X11 support",
-      "supports": "!windows"
-    }
-  }
-}

dependencies/vcpkg_overlay_ports_mac/libusb/portfile.cmake

@@ -0,0 +1,71 @@
+set(VCPKG_LIBRARY_LINKAGE dynamic)
+
+if(VCPKG_TARGET_IS_LINUX)
+    message("${PORT} currently requires the following tools and libraries from the system package manager:\n    autoreconf\n    libudev\n\nThese can be installed on Ubuntu systems via apt-get install autoconf libudev-dev")
+endif()
+
+set(VERSION 1.0.26)
+vcpkg_from_github(
+    OUT_SOURCE_PATH SOURCE_PATH
+    REPO libusb/libusb
+    REF fcf0c710ef5911ae37fbbf1b39d48a89f6f14e8a # v1.0.26.11791 2023-03-12
+    SHA512 0aa6439f7988487adf2a3bff473fec80b5c722a47f117a60696d2aa25c87cc3f20fb6aaca7c66e49be25db6a35eb0bb5f71ed7b211d1b8ee064c5d7f1b985c73
+    HEAD_REF master
+)
+
+if(VCPKG_TARGET_IS_WINDOWS AND NOT VCPKG_TARGET_IS_MINGW)
+
+  if(VCPKG_LIBRARY_LINKAGE STREQUAL "dynamic")
+      set(LIBUSB_PROJECT_TYPE dll)
+  else()
+      set(LIBUSB_PROJECT_TYPE static)
+  endif()
+
+  # The README.md file in the archive is a symlink to README
+  # which causes issues with the windows MSBUILD process
+  file(REMOVE "${SOURCE_PATH}/README.md")
+
+  vcpkg_msbuild_install(
+      SOURCE_PATH "${SOURCE_PATH}"
+      PROJECT_SUBPATH msvc/libusb_${LIBUSB_PROJECT_TYPE}.vcxproj
+  )
+
+  file(INSTALL "${SOURCE_PATH}/libusb/libusb.h"  DESTINATION "${CURRENT_PACKAGES_DIR}/include/libusb-1.0")
+  set(prefix "")
+  set(exec_prefix [[${prefix}]])
+  set(libdir [[${prefix}/lib]])
+  set(includedir [[${prefix}/include]])  
+  configure_file("${SOURCE_PATH}/libusb-1.0.pc.in" "${CURRENT_PACKAGES_DIR}/lib/pkgconfig/libusb-1.0.pc" @ONLY)
+  vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/lib/pkgconfig/libusb-1.0.pc" " -lusb-1.0" " -llibusb-1.0")
+  if(NOT VCPKG_BUILD_TYPE)
+      set(includedir [[${prefix}/../include]])  
+      configure_file("${SOURCE_PATH}/libusb-1.0.pc.in" "${CURRENT_PACKAGES_DIR}/debug/lib/pkgconfig/libusb-1.0.pc" @ONLY)
+      vcpkg_replace_string("${CURRENT_PACKAGES_DIR}/debug/lib/pkgconfig/libusb-1.0.pc" " -lusb-1.0" " -llibusb-1.0")
+  endif()
+else()
+    vcpkg_list(SET MAKE_OPTIONS)
+    vcpkg_list(SET LIBUSB_LINK_LIBRARIES)
+    if(VCPKG_TARGET_IS_EMSCRIPTEN)
+        vcpkg_list(APPEND MAKE_OPTIONS BUILD_TRIPLET --host=wasm32)
+    endif()
+    if("udev" IN_LIST FEATURES)
+        vcpkg_list(APPEND MAKE_OPTIONS "--enable-udev")
+        vcpkg_list(APPEND LIBUSB_LINK_LIBRARIES udev)
+    else()
+        vcpkg_list(APPEND MAKE_OPTIONS "--disable-udev")
+    endif()
+    vcpkg_configure_make(
+        SOURCE_PATH "${SOURCE_PATH}"
+        AUTOCONFIG
+        OPTIONS 
+            ${MAKE_OPTIONS}
+            "--enable-examples-build=no"
+            "--enable-tests-build=no"
+    )
+    vcpkg_install_make()
+endif()
+
+vcpkg_fixup_pkgconfig()
+
+file(INSTALL "${CMAKE_CURRENT_LIST_DIR}/usage" DESTINATION "${CURRENT_PACKAGES_DIR}/share/${PORT}")
+vcpkg_install_copyright(FILE_LIST "${SOURCE_PATH}/COPYING")

dependencies/vcpkg_overlay_ports_mac/libusb/usage

@@ -0,0 +1,5 @@
+libusb can be imported via CMake FindPkgConfig module:
+    find_package(PkgConfig REQUIRED)
+    pkg_check_modules(libusb REQUIRED IMPORTED_TARGET libusb-1.0)
+
+    target_link_libraries(main PRIVATE PkgConfig::libusb)

dependencies/vcpkg_overlay_ports_mac/libusb/vcpkg.json

@@ -0,0 +1,8 @@
+{
+  "name": "libusb",
+  "version": "1.0.26.11791",
+  "port-version": 7,
+  "description": "a cross-platform library to access USB devices",
+  "homepage": "https://github.com/libusb/libusb",
+  "license": "LGPL-2.1-or-later"
+}

dist/linux/appimage.sh

@@ -10,6 +10,8 @@ curl -sSfL https://github.com"$(curl https://github.com/probonopd/go-appimage/re
 chmod a+x mkappimage.AppImage
 curl -sSfLO "https://raw.githubusercontent.com/linuxdeploy/linuxdeploy-plugin-gtk/master/linuxdeploy-plugin-gtk.sh"
 chmod a+x linuxdeploy-plugin-gtk.sh
+curl -sSfLO "https://github.com/darealshinji/linuxdeploy-plugin-checkrt/releases/download/continuous/linuxdeploy-plugin-checkrt.sh"
+chmod a+x linuxdeploy-plugin-checkrt.sh
 
 if [[ ! -e /usr/lib/x86_64-linux-gnu ]]; then
 	sed -i 's#lib\/x86_64-linux-gnu#lib64#g' linuxdeploy-plugin-gtk.sh
@@ -33,12 +35,14 @@ chmod +x AppDir/usr/bin/Cemu
 cp /usr/lib/x86_64-linux-gnu/{libsepol.so.1,libffi.so.7,libpcre.so.3,libGLU.so.1,libthai.so.0} AppDir/usr/lib
 
 export UPD_INFO="gh-releases-zsync|cemu-project|Cemu|ci|Cemu.AppImage.zsync"
+export NO_STRIP=1
 ./linuxdeploy-x86_64.AppImage --appimage-extract-and-run \
   --appdir="${GITHUB_WORKSPACE}"/AppDir/ \
   -d "${GITHUB_WORKSPACE}"/AppDir/info.cemu.Cemu.desktop \
   -i "${GITHUB_WORKSPACE}"/AppDir/info.cemu.Cemu.png \
   -e "${GITHUB_WORKSPACE}"/AppDir/usr/bin/Cemu \
-  --plugin gtk
+  --plugin gtk \
+  --plugin checkrt
 
 if ! GITVERSION="$(git rev-parse --short HEAD 2>/dev/null)"; then
 	GITVERSION=experimental

dist/network_services.xml

@@ -0,0 +1,17 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<content>
+    <networkname>CustomExample</networkname>
+    <disablesslverification>0</disablesslverification>
+    <urls>
+        <act>https://account.nintendo.net</act>
+        <ecs>https://ecs.wup.shop.nintendo.net/ecs/services/ECommerceSOAP</ecs>
+        <nus>https://nus.wup.shop.nintendo.net/nus/services/NetUpdateSOAP</nus>
+        <ias>https://ias.wup.shop.nintendo.net/ias/services/IdentityAuthenticationSOAP</ias>
+        <ccsu>https://ccs.wup.shop.nintendo.net/ccs/download</ccsu>
+        <ccs>http://ccs.cdn.wup.shop.nintendo.net/ccs/download</ccs>
+        <idbe>https://idbe-wup.cdn.nintendo.net/icondata</idbe>
+        <boss>https://npts.app.nintendo.net/p01/tasksheet</boss>
+        <tagaya>https://tagaya.wup.shop.nintendo.net/tagaya/versionlist</tagaya>
+        <olv>https://discovery.olv.nintendo.net/v1/endpoint</olv>
+    </urls>
+</content>

src/CMakeLists.txt

@@ -56,6 +56,12 @@ add_executable(CemuBin
 	mainLLE.cpp
 )
 
+if(MSVC AND MSVC_VERSION EQUAL 1940)
+	# workaround for an msvc issue on VS 17.10 where generated ILK files are too large
+	# see https://developercommunity.visualstudio.com/t/After-updating-to-VS-1710-the-size-of-/10665511
+	set_target_properties(CemuBin PROPERTIES LINK_FLAGS "/INCREMENTAL:NO")
+endif()
+
 if(WIN32)
 	target_sources(CemuBin PRIVATE
 	resource/cemu.rc
@@ -76,11 +82,13 @@ if (MACOS_BUNDLE)
 	set(MACOSX_BUNDLE_ICON_FILE "cemu.icns")
 	set(MACOSX_BUNDLE_GUI_IDENTIFIER "info.cemu.Cemu")
 	set(MACOSX_BUNDLE_BUNDLE_NAME "Cemu")
-	set(MACOSX_BUNDLE_SHORT_VERSION_STRING ${CMAKE_PROJECT_VERSION})
-	set(MACOSX_BUNDLE_BUNDLE_VERSION ${CMAKE_PROJECT_VERSION})
-	set(MACOSX_BUNDLE_COPYRIGHT "Copyright © 2023 Cemu Project")
+	set(MACOSX_BUNDLE_SHORT_VERSION_STRING "${EMULATOR_VERSION_MAJOR}.${EMULATOR_VERSION_MINOR}.${EMULATOR_VERSION_PATCH}")
+	set(MACOSX_BUNDLE_BUNDLE_VERSION "${EMULATOR_VERSION_MAJOR}.${EMULATOR_VERSION_MINOR}.${EMULATOR_VERSION_PATCH}")
+	set(MACOSX_BUNDLE_COPYRIGHT "Copyright © 2024 Cemu Project")
 
 	set(MACOSX_BUNDLE_CATEGORY "public.app-category.games")
+ 	set(MACOSX_MINIMUM_SYSTEM_VERSION "12.0")
+  	set(MACOSX_BUNDLE_TYPE_EXTENSION "wua")
 
 	set_target_properties(CemuBin PROPERTIES
 		MACOSX_BUNDLE true
@@ -93,11 +101,18 @@ if (MACOS_BUNDLE)
 			COMMAND ${CMAKE_COMMAND} ARGS -E copy_directory "${CMAKE_SOURCE_DIR}/bin/${folder}" "${CMAKE_SOURCE_DIR}/bin/${OUTPUT_NAME}.app/Contents/SharedSupport/${folder}")
 	endforeach(folder)
 
-	add_custom_command (TARGET CemuBin POST_BUILD
-		COMMAND ${CMAKE_COMMAND} ARGS -E copy "/usr/local/lib/libMoltenVK.dylib" "${CMAKE_SOURCE_DIR}/bin/${OUTPUT_NAME}.app/Contents/Frameworks/libMoltenVK.dylib")
+	if(CMAKE_BUILD_TYPE STREQUAL "Debug")
+	    set(LIBUSB_PATH "${CMAKE_BINARY_DIR}/vcpkg_installed/x64-osx/debug/lib/libusb-1.0.0.dylib")
+	else()
+	    set(LIBUSB_PATH "${CMAKE_BINARY_DIR}/vcpkg_installed/x64-osx/lib/libusb-1.0.0.dylib")
+	endif()
 
 	add_custom_command (TARGET CemuBin POST_BUILD
-		COMMAND bash -c "install_name_tool -add_rpath @executable_path/../Frameworks ${CMAKE_SOURCE_DIR}/bin/${OUTPUT_NAME}.app/Contents/MacOS/${OUTPUT_NAME}")
+		COMMAND ${CMAKE_COMMAND} ARGS -E copy "/usr/local/lib/libMoltenVK.dylib" "${CMAKE_SOURCE_DIR}/bin/${OUTPUT_NAME}.app/Contents/Frameworks/libMoltenVK.dylib"
+		COMMAND ${CMAKE_COMMAND} ARGS -E copy "${LIBUSB_PATH}" "${CMAKE_SOURCE_DIR}/bin/${OUTPUT_NAME}.app/Contents/Frameworks/libusb-1.0.0.dylib"
+		COMMAND ${CMAKE_COMMAND} ARGS -E copy "${CMAKE_SOURCE_DIR}/src/resource/update.sh" "${CMAKE_SOURCE_DIR}/bin/${OUTPUT_NAME}.app/Contents/MacOS/update.sh"
+		COMMAND bash -c "install_name_tool -add_rpath @executable_path/../Frameworks ${CMAKE_SOURCE_DIR}/bin/${OUTPUT_NAME}.app/Contents/MacOS/${OUTPUT_NAME}"
+		COMMAND bash -c "install_name_tool -change ${LIBUSB_PATH} @executable_path/../Frameworks/libusb-1.0.0.dylib ${CMAKE_SOURCE_DIR}/bin/${OUTPUT_NAME}.app/Contents/MacOS/${OUTPUT_NAME}")
 endif()
 
 set_target_properties(CemuBin PROPERTIES

src/Cafe/CMakeLists.txt

@@ -10,6 +10,7 @@ add_library(CemuCafe
   Filesystem/fscDeviceRedirect.cpp
   Filesystem/fscDeviceWua.cpp
   Filesystem/fscDeviceWud.cpp
+  Filesystem/fscDeviceWuhb.cpp
   Filesystem/fsc.h
   Filesystem/FST/FST.cpp
   Filesystem/FST/FST.h
@@ -18,6 +19,9 @@ add_library(CemuCafe
   Filesystem/FST/KeyCache.h
   Filesystem/WUD/wud.cpp
   Filesystem/WUD/wud.h
+  Filesystem/WUHB/RomFSStructs.h
+  Filesystem/WUHB/WUHBReader.cpp
+  Filesystem/WUHB/WUHBReader.h
   GamePatch.cpp
   GamePatch.h
   GameProfile/GameProfile.cpp
@@ -40,6 +44,7 @@ add_library(CemuCafe
   HW/Espresso/Debugger/DebugSymbolStorage.h
   HW/Espresso/Debugger/GDBStub.h
   HW/Espresso/Debugger/GDBStub.cpp
+  HW/Espresso/Debugger/GDBBreakpoints.cpp
   HW/Espresso/Debugger/GDBBreakpoints.h
   HW/Espresso/EspressoISA.h
   HW/Espresso/Interpreter/PPCInterpreterALU.hpp
@@ -213,6 +218,8 @@ add_library(CemuCafe
   HW/SI/SI.cpp
   HW/SI/si.h
   HW/VI/VI.cpp
+  IOSU/ccr_nfc/iosu_ccr_nfc.cpp
+  IOSU/ccr_nfc/iosu_ccr_nfc.h
   IOSU/fsa/fsa_types.h
   IOSU/fsa/iosu_fsa.cpp
   IOSU/fsa/iosu_fsa.h
@@ -367,12 +374,24 @@ add_library(CemuCafe
   OS/libs/gx2/GX2_Texture.h
   OS/libs/gx2/GX2_TilingAperture.cpp
   OS/libs/h264_avc/H264Dec.cpp
+  OS/libs/h264_avc/H264DecBackendAVC.cpp
   OS/libs/h264_avc/h264dec.h
+  OS/libs/h264_avc/H264DecInternal.h
   OS/libs/h264_avc/parser
   OS/libs/h264_avc/parser/H264Parser.cpp
   OS/libs/h264_avc/parser/H264Parser.h
   OS/libs/mic/mic.cpp
   OS/libs/mic/mic.h
+  OS/libs/nfc/ndef.cpp
+  OS/libs/nfc/ndef.h
+  OS/libs/nfc/nfc.cpp
+  OS/libs/nfc/nfc.h
+  OS/libs/nfc/stream.cpp
+  OS/libs/nfc/stream.h
+  OS/libs/nfc/TagV0.cpp
+  OS/libs/nfc/TagV0.h
+  OS/libs/nfc/TLV.cpp
+  OS/libs/nfc/TLV.h
   OS/libs/nlibcurl/nlibcurl.cpp
   OS/libs/nlibcurl/nlibcurlDebug.hpp
   OS/libs/nlibcurl/nlibcurl.h
@@ -403,6 +422,8 @@ add_library(CemuCafe
   OS/libs/nn_ndm/nn_ndm.h
   OS/libs/nn_spm/nn_spm.cpp
   OS/libs/nn_spm/nn_spm.h
+  OS/libs/nn_sl/nn_sl.cpp
+  OS/libs/nn_sl/nn_sl.h
   OS/libs/nn_nfp/AmiiboCrypto.h
   OS/libs/nn_nfp/nn_nfp.cpp
   OS/libs/nn_nfp/nn_nfp.h
@@ -438,14 +459,22 @@ add_library(CemuCafe
   OS/libs/nsyshid/AttachDefaultBackends.cpp
   OS/libs/nsyshid/Whitelist.cpp
   OS/libs/nsyshid/Whitelist.h
+  OS/libs/nsyshid/BackendEmulated.cpp
+  OS/libs/nsyshid/BackendEmulated.h
   OS/libs/nsyshid/BackendLibusb.cpp
   OS/libs/nsyshid/BackendLibusb.h
-  OS/libs/nsyshid/BackendWindowsHID.cpp
-  OS/libs/nsyshid/BackendWindowsHID.h
+  OS/libs/nsyshid/Dimensions.cpp
+  OS/libs/nsyshid/Dimensions.h
+  OS/libs/nsyshid/Infinity.cpp
+  OS/libs/nsyshid/Infinity.h
+  OS/libs/nsyshid/Skylander.cpp
+  OS/libs/nsyshid/Skylander.h
   OS/libs/nsyskbd/nsyskbd.cpp
   OS/libs/nsyskbd/nsyskbd.h
   OS/libs/nsysnet/nsysnet.cpp
   OS/libs/nsysnet/nsysnet.h
+  OS/libs/ntag/ntag.cpp
+  OS/libs/ntag/ntag.h
   OS/libs/padscore/padscore.cpp
   OS/libs/padscore/padscore.h
   OS/libs/proc_ui/proc_ui.cpp
@@ -501,6 +530,12 @@ set_property(TARGET CemuCafe PROPERTY MSVC_RUNTIME_LIBRARY "MultiThreaded$<$<CON
 
 target_include_directories(CemuCafe PUBLIC "../")
 
+if (glslang_VERSION VERSION_LESS "15.0.0")
+	set(glslang_target "glslang::SPIRV")
+else()
+	set(glslang_target "glslang")
+endif()
+
 target_link_libraries(CemuCafe PRIVATE
 	CemuAsm
 	CemuAudio
@@ -516,7 +551,7 @@ target_link_libraries(CemuCafe PRIVATE
 	Boost::nowide
 	CURL::libcurl
 	fmt::fmt
-	glslang::SPIRV
+	${glslang_target}
 	ih264d
 	OpenSSL::Crypto
 	OpenSSL::SSL
@@ -532,16 +567,17 @@ if (ENABLE_WAYLAND)
   target_link_libraries(CemuCafe PUBLIC Wayland::Client)
 endif()
 
-if (ENABLE_NSYSHID_LIBUSB)
 if (ENABLE_VCPKG)
-		find_package(libusb CONFIG REQUIRED)
-		target_include_directories(CemuCafe PRIVATE ${LIBUSB_INCLUDE_DIRS})
-		target_link_libraries(CemuCafe PRIVATE ${LIBUSB_LIBRARIES})
+  if(WIN32)
+    set(PKG_CONFIG_EXECUTABLE "${VCPKG_INSTALLED_DIR}/x64-windows/tools/pkgconf/pkgconf.exe")
+  endif()
+  find_package(PkgConfig REQUIRED)
+  pkg_check_modules(libusb REQUIRED IMPORTED_TARGET libusb-1.0)
+  target_link_libraries(CemuCafe PRIVATE PkgConfig::libusb)
 else ()
   find_package(libusb MODULE REQUIRED)
   target_link_libraries(CemuCafe PRIVATE libusb::libusb)
 endif ()
-endif ()
 
 if (ENABLE_WXWIDGETS)
 	target_link_libraries(CemuCafe PRIVATE wx::base wx::core)

src/Cafe/CafeSystem.cpp

@@ -9,6 +9,7 @@
 #include "audio/IAudioAPI.h"
 #include "audio/IAudioInputAPI.h"
 #include "config/ActiveSettings.h"
+#include "config/LaunchSettings.h"
 #include "Cafe/TitleList/GameInfo.h"
 #include "Cafe/GraphicPack/GraphicPack2.h"
 #include "util/helpers/SystemException.h"
@@ -35,6 +36,7 @@
 #include "Cafe/IOSU/legacy/iosu_boss.h"
 #include "Cafe/IOSU/legacy/iosu_nim.h"
 #include "Cafe/IOSU/PDM/iosu_pdm.h"
+#include "Cafe/IOSU/ccr_nfc/iosu_ccr_nfc.h"
 
 // IOSU initializer functions
 #include "Cafe/IOSU/kernel/iosu_kernel.h"
@@ -51,6 +53,8 @@
 #include "Cafe/OS/libs/gx2/GX2.h"
 #include "Cafe/OS/libs/gx2/GX2_Misc.h"
 #include "Cafe/OS/libs/mic/mic.h"
+#include "Cafe/OS/libs/nfc/nfc.h"
+#include "Cafe/OS/libs/ntag/ntag.h"
 #include "Cafe/OS/libs/nn_aoc/nn_aoc.h"
 #include "Cafe/OS/libs/nn_pdm/nn_pdm.h"
 #include "Cafe/OS/libs/nn_cmpt/nn_cmpt.h"
@@ -393,7 +397,7 @@ void cemu_initForGame()
 		// replace any known function signatures with our HLE implementations and patch bugs in the games
 		GamePatch_scan();
 	}
-	LatteGPUState.alwaysDisplayDRC = ActiveSettings::DisplayDRCEnabled();
+	LatteGPUState.isDRCPrimary = ActiveSettings::DisplayDRCEnabled();
 	InfoLog_PrintActiveSettings();
 	Latte_Start();
 	// check for debugger entrypoint bp
@@ -526,6 +530,16 @@ namespace CafeSystem
 		cemuLog_log(LogType::Force, "Platform: {}", platform);
 	}
 
+	static std::vector<IOSUModule*> s_iosuModules =
+	{
+		// entries in this list are ordered by initialization order. Shutdown in reverse order
+		iosu::kernel::GetModule(),
+		iosu::acp::GetModule(),
+		iosu::fpd::GetModule(),
+		iosu::pdm::GetModule(),
+		iosu::ccr_nfc::GetModule(),
+	};
+
 	// initialize all subsystems which are persistent and don't depend on a game running
 	void Initialize()
 	{
@@ -550,20 +564,20 @@ namespace CafeSystem
 		// allocate memory for all SysAllocators
 		// must happen before COS module init, but also before iosu::kernel::Initialize()
 		SysAllocatorContainer::GetInstance().Initialize();
-		// init IOSU
+		// init IOSU modules
+		for(auto& module : s_iosuModules)
+			module->SystemLaunch();
+		// init IOSU (deprecated manual init)
 		iosuCrypto_init();
-		iosu::kernel::Initialize();
 		iosu::fsa::Initialize();
 		iosuIoctl_init();
 		iosuAct_init_depr();
 		iosu::act::Initialize();
-		iosu::fpd::Initialize();
 		iosu::iosuMcp_init();
 		iosu::mcp::Init();
 		iosu::iosuAcp_init();
 		iosu::boss_init();
 		iosu::nim::Initialize();
-		iosu::pdm::Initialize();
 		iosu::odm::Initialize();
 		// init Cafe OS
 		avm::Initialize();
@@ -578,6 +592,8 @@ namespace CafeSystem
 		H264::Initialize();
 		snd_core::Initialize();
 		mic::Initialize();
+		nfc::Initialize();
+		ntag::Initialize();
 		// init hardware register interfaces
 		HW_SI::Initialize();
 	}
@@ -593,11 +609,14 @@ namespace CafeSystem
         // if a title is running, shut it down
         if (sSystemRunning)
             ShutdownTitle();
-        // shutdown persistent subsystems
+        // shutdown persistent subsystems (deprecated manual shutdown)
 		iosu::odm::Shutdown();
 		iosu::act::Stop();
         iosu::mcp::Shutdown();
         iosu::fsa::Shutdown();
+		// shutdown IOSU modules
+		for(auto it = s_iosuModules.rbegin(); it != s_iosuModules.rend(); ++it)
+			(*it)->SystemExit();
         s_initialized = false;
     }
 
@@ -619,40 +638,40 @@ namespace CafeSystem
         fsc_unmount("/cemuBossStorage/", FSC_PRIORITY_BASE);
     }
 
-	STATUS_CODE LoadAndMountForegroundTitle(TitleId titleId)
+	PREPARE_STATUS_CODE LoadAndMountForegroundTitle(TitleId titleId)
 	{
         cemuLog_log(LogType::Force, "Mounting title {:016x}", (uint64)titleId);
 		sGameInfo_ForegroundTitle = CafeTitleList::GetGameInfo(titleId);
 		if (!sGameInfo_ForegroundTitle.IsValid())
 		{
 			cemuLog_log(LogType::Force, "Mounting failed: Game meta information is either missing, inaccessible or not valid (missing or invalid .xml files in code and meta folder)");
-			return STATUS_CODE::UNABLE_TO_MOUNT;
+			return PREPARE_STATUS_CODE::UNABLE_TO_MOUNT;
 		}
 		// check base
 		TitleInfo& titleBase = sGameInfo_ForegroundTitle.GetBase();
 		if (!titleBase.IsValid())
-			return STATUS_CODE::UNABLE_TO_MOUNT;
+			return PREPARE_STATUS_CODE::UNABLE_TO_MOUNT;
 		if(!titleBase.ParseXmlInfo())
-			return STATUS_CODE::UNABLE_TO_MOUNT;
+			return PREPARE_STATUS_CODE::UNABLE_TO_MOUNT;
 		cemuLog_log(LogType::Force, "Base: {}", titleBase.GetPrintPath());
 		// mount base
 		if (!titleBase.Mount("/vol/content", "content", FSC_PRIORITY_BASE) || !titleBase.Mount(GetInternalVirtualCodeFolder(), "code", FSC_PRIORITY_BASE))
 		{
 			cemuLog_log(LogType::Force, "Mounting failed");
-			return STATUS_CODE::UNABLE_TO_MOUNT;
+			return PREPARE_STATUS_CODE::UNABLE_TO_MOUNT;
 		}
 		// check update
 		TitleInfo& titleUpdate = sGameInfo_ForegroundTitle.GetUpdate();
 		if (titleUpdate.IsValid())
 		{
 			if (!titleUpdate.ParseXmlInfo())
-				return STATUS_CODE::UNABLE_TO_MOUNT;
+				return PREPARE_STATUS_CODE::UNABLE_TO_MOUNT;
 			cemuLog_log(LogType::Force, "Update: {}", titleUpdate.GetPrintPath());
 			// mount update
 			if (!titleUpdate.Mount("/vol/content", "content", FSC_PRIORITY_PATCH) || !titleUpdate.Mount(GetInternalVirtualCodeFolder(), "code", FSC_PRIORITY_PATCH))
 			{
 				cemuLog_log(LogType::Force, "Mounting failed");
-				return STATUS_CODE::UNABLE_TO_MOUNT;
+				return PREPARE_STATUS_CODE::UNABLE_TO_MOUNT;
 			}
 		}
 		else
@@ -664,20 +683,20 @@ namespace CafeSystem
 			// todo - support for multi-title AOC
 			TitleInfo& titleAOC = aocList[0];
 			if (!titleAOC.ParseXmlInfo())
-				return STATUS_CODE::UNABLE_TO_MOUNT;
+				return PREPARE_STATUS_CODE::UNABLE_TO_MOUNT;
 			cemu_assert_debug(titleAOC.IsValid());
 			cemuLog_log(LogType::Force, "DLC: {}", titleAOC.GetPrintPath());
 			// mount AOC
 			if (!titleAOC.Mount(fmt::format("/vol/aoc{:016x}", titleAOC.GetAppTitleId()), "content", FSC_PRIORITY_PATCH))
 			{
 				cemuLog_log(LogType::Force, "Mounting failed");
-				return STATUS_CODE::UNABLE_TO_MOUNT;
+				return PREPARE_STATUS_CODE::UNABLE_TO_MOUNT;
 			}
 		}
 		else
 			cemuLog_log(LogType::Force, "DLC: Not present");
 		sForegroundTitleId = titleId;
-		return STATUS_CODE::SUCCESS;
+		return PREPARE_STATUS_CODE::SUCCESS;
 	}
 
     void UnmountForegroundTitle()
@@ -705,7 +724,7 @@ namespace CafeSystem
         }
     }
 
-	STATUS_CODE SetupExecutable()
+	PREPARE_STATUS_CODE SetupExecutable()
 	{
 		// set rpx path from cos.xml if available
 		_pathToBaseExecutable = _pathToExecutable;
@@ -737,8 +756,7 @@ namespace CafeSystem
 			}
 		}
 		LoadMainExecutable();
-		gameProfile_load();
-		return STATUS_CODE::SUCCESS;
+		return PREPARE_STATUS_CODE::SUCCESS;
 	}
 
     void SetupMemorySpace()
@@ -752,7 +770,7 @@ namespace CafeSystem
         memory_unmapForCurrentTitle();
     }
 
-	STATUS_CODE PrepareForegroundTitle(TitleId titleId)
+	PREPARE_STATUS_CODE PrepareForegroundTitle(TitleId titleId)
 	{
 		CafeTitleList::WaitForMandatoryScan();
 		sLaunchModeIsStandalone = false;
@@ -763,20 +781,21 @@ namespace CafeSystem
         // mount mlc storage
         MountBaseDirectories();
         // mount title folders
-		STATUS_CODE r = LoadAndMountForegroundTitle(titleId);
-		if (r != STATUS_CODE::SUCCESS)
+		PREPARE_STATUS_CODE r = LoadAndMountForegroundTitle(titleId);
+		if (r != PREPARE_STATUS_CODE::SUCCESS)
 			return r;
+		gameProfile_load();
 		// setup memory space and PPC recompiler
         SetupMemorySpace();
         PPCRecompiler_init();
 		r = SetupExecutable(); // load RPX
-		if (r != STATUS_CODE::SUCCESS)
+		if (r != PREPARE_STATUS_CODE::SUCCESS)
 			return r;
 		InitVirtualMlcStorage();
-		return STATUS_CODE::SUCCESS;
+		return PREPARE_STATUS_CODE::SUCCESS;
 	}
 
-	STATUS_CODE PrepareForegroundTitleFromStandaloneRPX(const fs::path& path)
+	PREPARE_STATUS_CODE PrepareForegroundTitleFromStandaloneRPX(const fs::path& path)
 	{
 		sLaunchModeIsStandalone = true;
 		cemuLog_log(LogType::Force, "Launching executable in standalone mode due to incorrect layout or missing meta files");
@@ -794,7 +813,7 @@ namespace CafeSystem
 				if (!r)
 				{
 					cemuLog_log(LogType::Force, "Failed to mount {}", _pathToUtf8(contentPath));
-					return STATUS_CODE::UNABLE_TO_MOUNT;
+					return PREPARE_STATUS_CODE::UNABLE_TO_MOUNT;
 				}
 			}
 		}
@@ -806,7 +825,7 @@ namespace CafeSystem
 		// since a lot of systems (including save folder location) rely on a TitleId, we derive a placeholder id from the executable hash
 		auto execData = fsc_extractFile(_pathToExecutable.c_str());
 		if (!execData)
-			return STATUS_CODE::INVALID_RPX;
+			return PREPARE_STATUS_CODE::INVALID_RPX;
 		uint32 h = generateHashFromRawRPXData(execData->data(), execData->size());
 		sForegroundTitleId = 0xFFFFFFFF00000000ULL | (uint64)h;
 		cemuLog_log(LogType::Force, "Generated placeholder TitleId: {:016x}", sForegroundTitleId);
@@ -816,19 +835,19 @@ namespace CafeSystem
         // load executable
         SetupExecutable();
 		InitVirtualMlcStorage();
-		return STATUS_CODE::SUCCESS;
+		return PREPARE_STATUS_CODE::SUCCESS;
 	}
 
 	void _LaunchTitleThread()
 	{
-		// init
+		for(auto& module : s_iosuModules)
+			module->TitleStart();
 		cemu_initForGame();
 		// enter scheduler
-		if (ActiveSettings::GetCPUMode() == CPUMode::MulticoreRecompiler)
+		if (ActiveSettings::GetCPUMode() == CPUMode::MulticoreRecompiler && !LaunchSettings::ForceInterpreter())
 			coreinit::OSSchedulerBegin(3);
 		else
 			coreinit::OSSchedulerBegin(1);
-		iosu::pdm::StartTrackingTime(GetForegroundTitleId());
 	}
 
 	void LaunchForegroundTitle()
@@ -903,6 +922,27 @@ namespace CafeSystem
 		return sGameInfo_ForegroundTitle.GetBase().GetArgStr();
 	}
 
+	CosCapabilityBits GetForegroundTitleCosCapabilities(CosCapabilityGroup group)
+	{
+		if (sLaunchModeIsStandalone)
+			return CosCapabilityBits::All;
+		auto& update = sGameInfo_ForegroundTitle.GetUpdate();
+		if (update.IsValid())
+		{
+			ParsedCosXml* cosXml = update.GetCosInfo();
+			if (cosXml)
+				return cosXml->GetCapabilityBits(group);
+		}
+		auto& base = sGameInfo_ForegroundTitle.GetBase();
+		if(base.IsValid())
+		{
+			ParsedCosXml* cosXml = base.GetCosInfo();
+			if (cosXml)
+				return cosXml->GetCapabilityBits(group);
+		}
+		return CosCapabilityBits::All;
+	}
+
 	// when switching titles custom parameters can be passed, returns true if override args are used
 	bool GetOverrideArgStr(std::vector<std::string>& args)
 	{
@@ -956,8 +996,8 @@ namespace CafeSystem
         nn::save::ResetToDefaultState();
         coreinit::__OSDeleteAllActivePPCThreads();
         RPLLoader_ResetState();
-        // stop time tracking
-		iosu::pdm::Stop();
+		for(auto it = s_iosuModules.rbegin(); it != s_iosuModules.rend(); ++it)
+			(*it)->TitleStop();
         // reset Cemu subsystems
         PPCRecompiler_Shutdown();
         GraphicPack2::Reset();

src/Cafe/CafeSystem.h

@@ -4,6 +4,9 @@
 #include "Cafe/TitleList/TitleId.h"
 #include "config/CemuConfig.h"
 
+enum class CosCapabilityBits : uint64;
+enum class CosCapabilityGroup : uint32;
+
 namespace CafeSystem
 {
 	class SystemImplementation
@@ -12,20 +15,19 @@ namespace CafeSystem
 		virtual void CafeRecreateCanvas() = 0;
 	};
 
-	enum class STATUS_CODE
+	enum class PREPARE_STATUS_CODE
 	{
 		SUCCESS,
 		INVALID_RPX,
 		UNABLE_TO_MOUNT, // failed to mount through TitleInfo (most likely caused by an invalid or outdated path)
-		//BAD_META_DATA, - the title list only stores titles with valid meta, so this error code is impossible
 	};
 
 	void Initialize();
 	void SetImplementation(SystemImplementation* impl);
     void Shutdown();
 
-	STATUS_CODE PrepareForegroundTitle(TitleId titleId);
-	STATUS_CODE PrepareForegroundTitleFromStandaloneRPX(const fs::path& path);
+	PREPARE_STATUS_CODE PrepareForegroundTitle(TitleId titleId);
+	PREPARE_STATUS_CODE PrepareForegroundTitleFromStandaloneRPX(const fs::path& path);
 	void LaunchForegroundTitle();
 	bool IsTitleRunning();
 
@@ -41,6 +43,7 @@ namespace CafeSystem
 	std::string GetForegroundTitleName();
 	std::string GetForegroundTitleArgStr();
 	uint32 GetForegroundTitleOlvAccesskey();
+	CosCapabilityBits GetForegroundTitleCosCapabilities(CosCapabilityGroup group);
 
 	void ShutdownTitle();
 

src/Cafe/Filesystem/FST/FST.cpp

@@ -3,8 +3,7 @@
 #include "Cemu/ncrypto/ncrypto.h"
 #include "Cafe/Filesystem/WUD/wud.h"
 #include "util/crypto/aes128.h"
-#include "openssl/evp.h" /* EVP_Digest */
-#include "openssl/sha.h" /* SHA1 / SHA256_DIGEST_LENGTH */
+#include "openssl/sha.h" /* SHA1 / SHA256 */
 #include "fstUtil.h"
 
 #include "FST.h"
@@ -141,7 +140,7 @@ struct DiscPartitionTableHeader
 	static constexpr uint32 MAGIC_VALUE = 0xCCA6E67B;
 
 	/* +0x00 */ uint32be magic;
-	/* +0x04 */ uint32be sectorSize; // must be 0x8000?
+	/* +0x04 */ uint32be blockSize; // must be 0x8000?
 	/* +0x08 */ uint8 partitionTableHash[20]; // hash of the data range at +0x800 to end of sector (0x8000)
 	/* +0x1C */ uint32be numPartitions;
 };
@@ -164,10 +163,10 @@ struct DiscPartitionHeader
 	static constexpr uint32 MAGIC_VALUE = 0xCC93A4F5;
 
 	/* +0x00 */ uint32be magic;
-	/* +0x04 */ uint32be sectorSize; // must match DISC_SECTOR_SIZE
+	/* +0x04 */ uint32be sectorSize; // must match DISC_SECTOR_SIZE for hashed blocks
 
 	/* +0x08 */ uint32be ukn008;
-	/* +0x0C */ uint32be ukn00C;
+	/* +0x0C */ uint32be ukn00C; // h3 array size?
 	/* +0x10 */ uint32be h3HashNum;
 	/* +0x14 */ uint32be fstSize; // in bytes
 	/* +0x18 */ uint32be fstSector; // relative to partition start
@@ -178,13 +177,15 @@ struct DiscPartitionHeader
 	/* +0x24 */ uint8 fstHashType;
 	/* +0x25 */ uint8 fstEncryptionType; // purpose of this isn't really understood. Maybe it controls which key is being used? (1 -> disc key, 2 -> partition key)
 
-	/* +0x26 */ uint8 versionA;
-	/* +0x27 */ uint8 ukn027; // also a version field?
+	/* +0x26 */ uint8be versionA;
+	/* +0x27 */ uint8be ukn027; // also a version field?
 
 	// there is an array at +0x40 ? Related to H3 list. Also related to value at +0x0C and h3HashNum
+	/* +0x28 */ uint8be _uknOrPadding028[0x18];
+	/* +0x40 */ uint8be h3HashArray[32]; // dynamic size. Only present if fstHashType != 0
 };
 
-static_assert(sizeof(DiscPartitionHeader) == 0x28);
+static_assert(sizeof(DiscPartitionHeader) == 0x40+0x20);
 
 bool FSTVolume::FindDiscKey(const fs::path& path, NCrypto::AesKey& discTitleKey)
 {
@@ -269,7 +270,7 @@ FSTVolume* FSTVolume::OpenFromDiscImage(const fs::path& path, NCrypto::AesKey& d
 		cemuLog_log(LogType::Force, "Disc image rejected because decryption failed");
 		return nullptr;
 	}
-	if (partitionHeader->sectorSize != DISC_SECTOR_SIZE)
+	if (partitionHeader->blockSize != DISC_SECTOR_SIZE)
 	{
 		cemuLog_log(LogType::Force, "Disc image rejected because partition sector size is invalid");
 		return nullptr;
@@ -336,6 +337,9 @@ FSTVolume* FSTVolume::OpenFromDiscImage(const fs::path& path, NCrypto::AesKey& d
 	cemu_assert_debug(partitionHeaderSI.fstEncryptionType == 1);
 	// todo - check other fields?
 
+	if(partitionHeaderSI.fstHashType == 0 && partitionHeaderSI.h3HashNum != 0)
+		cemuLog_log(LogType::Force, "FST: Partition uses unhashed blocks but stores a non-zero amount of H3 hashes");
+
 	// GM partition
 	DiscPartitionHeader partitionHeaderGM{};
 	if (!readPartitionHeader(partitionHeaderGM, gmPartitionIndex))
@@ -349,9 +353,10 @@ FSTVolume* FSTVolume::OpenFromDiscImage(const fs::path& path, NCrypto::AesKey& d
 	// if decryption is necessary
 	// load SI FST
 	dataSource->SetBaseOffset((uint64)partitionArray[siPartitionIndex].partitionAddress * DISC_SECTOR_SIZE);
-	auto siFST = OpenFST(dataSource.get(), (uint64)partitionHeaderSI.fstSector * DISC_SECTOR_SIZE, partitionHeaderSI.fstSize, &discTitleKey, static_cast<FSTVolume::ClusterHashMode>(partitionHeaderSI.fstHashType));
+	auto siFST = OpenFST(dataSource.get(), (uint64)partitionHeaderSI.fstSector * DISC_SECTOR_SIZE, partitionHeaderSI.fstSize, &discTitleKey, static_cast<FSTVolume::ClusterHashMode>(partitionHeaderSI.fstHashType), nullptr);
 	if (!siFST)
 		return nullptr;
+	cemu_assert_debug(!(siFST->HashIsDisabled() && partitionHeaderSI.h3HashNum != 0)); // if hash is disabled, no H3 data may be present
 	// load ticket file for partition that we want to decrypt
 	NCrypto::ETicketParser ticketParser;
 	std::vector<uint8> ticketData = siFST->ExtractFile(fmt::format("{:02x}/title.tik", gmPartitionIndex));
@@ -360,16 +365,32 @@ FSTVolume* FSTVolume::OpenFromDiscImage(const fs::path& path, NCrypto::AesKey& d
 		cemuLog_log(LogType::Force, "Disc image ticket file is invalid");
 		return nullptr;
 	}
+#if 0
+	// each SI partition seems to contain a title.tmd that we could parse and which should have information about the associated GM partition
+	// but the console seems to ignore this file for disc images, at least when mounting, so we shouldn't rely on it either
+	std::vector<uint8> tmdData = siFST->ExtractFile(fmt::format("{:02x}/title.tmd", gmPartitionIndex));
+	if (tmdData.empty())
+	{
+		cemuLog_log(LogType::Force, "Disc image TMD file is missing");
+		return nullptr;
+	}
+	// parse TMD
+	NCrypto::TMDParser tmdParser;
+	if (!tmdParser.parse(tmdData.data(), tmdData.size()))
+	{
+		cemuLog_log(LogType::Force, "Disc image TMD file is invalid");
+		return nullptr;
+	}
+#endif
 	delete siFST;
-
 	NCrypto::AesKey gmTitleKey;
 	ticketParser.GetTitleKey(gmTitleKey);
-
 	// load GM partition
 	dataSource->SetBaseOffset((uint64)partitionArray[gmPartitionIndex].partitionAddress * DISC_SECTOR_SIZE);
-	FSTVolume* r = OpenFST(std::move(dataSource), (uint64)partitionHeaderGM.fstSector * DISC_SECTOR_SIZE, partitionHeaderGM.fstSize, &gmTitleKey, static_cast<FSTVolume::ClusterHashMode>(partitionHeaderGM.fstHashType));
+	FSTVolume* r = OpenFST(std::move(dataSource), (uint64)partitionHeaderGM.fstSector * DISC_SECTOR_SIZE, partitionHeaderGM.fstSize, &gmTitleKey, static_cast<FSTVolume::ClusterHashMode>(partitionHeaderGM.fstHashType), nullptr);
 	if (r)
 		SET_FST_ERROR(OK);
+	cemu_assert_debug(!(r->HashIsDisabled() && partitionHeaderGM.h3HashNum != 0)); // if hash is disabled, no H3 data may be present
 	return r;
 }
 
@@ -426,15 +447,15 @@ FSTVolume* FSTVolume::OpenFromContentFolder(fs::path folderPath, ErrorCode* erro
 	}
 	// load FST
 	// fstSize = size of first cluster?
-	FSTVolume* fstVolume = FSTVolume::OpenFST(std::move(dataSource), 0, fstSize, &titleKey, fstHashMode);
+	FSTVolume* fstVolume = FSTVolume::OpenFST(std::move(dataSource), 0, fstSize, &titleKey, fstHashMode, &tmdParser);
 	if (fstVolume)
 		SET_FST_ERROR(OK);
 	return fstVolume;
 }
 
-FSTVolume* FSTVolume::OpenFST(FSTDataSource* dataSource, uint64 fstOffset, uint32 fstSize, NCrypto::AesKey* partitionTitleKey, ClusterHashMode fstHashMode)
+FSTVolume* FSTVolume::OpenFST(FSTDataSource* dataSource, uint64 fstOffset, uint32 fstSize, NCrypto::AesKey* partitionTitleKey, ClusterHashMode fstHashMode, NCrypto::TMDParser* optionalTMD)
 {
-	cemu_assert_debug(fstHashMode != ClusterHashMode::RAW || fstHashMode != ClusterHashMode::RAW2);
+	cemu_assert_debug(fstHashMode != ClusterHashMode::RAW || fstHashMode != ClusterHashMode::RAW_STREAM);
 	if (fstSize < sizeof(FSTHeader))
 		return nullptr;
 	constexpr uint64 FST_CLUSTER_OFFSET = 0;
@@ -465,6 +486,34 @@ FSTVolume* FSTVolume::OpenFST(FSTDataSource* dataSource, uint64 fstOffset, uint3
 		clusterTable[i].offset = clusterDataTable[i].offset;
 		clusterTable[i].size = clusterDataTable[i].size;
 		clusterTable[i].hashMode = static_cast<FSTVolume::ClusterHashMode>((uint8)clusterDataTable[i].hashMode);
+		clusterTable[i].hasContentHash = false; // from the TMD file (H4?)
+	}
+	// if the TMD is available (when opening .app files) we can use the extra info from it to validate unhashed clusters
+	// each content entry in the TMD corresponds to one cluster used by the FST
+	if(optionalTMD)
+	{
+		if(numCluster != optionalTMD->GetContentList().size())
+		{
+			cemuLog_log(LogType::Force, "FST: Number of clusters does not match TMD content list");
+			return nullptr;
+		}
+		auto& contentList = optionalTMD->GetContentList();
+		for(size_t i=0; i<contentList.size(); i++)
+		{
+			auto& cluster = clusterTable[i];
+			auto& content = contentList[i];
+			cluster.hasContentHash = true;
+			cluster.contentHashIsSHA1 = HAS_FLAG(contentList[i].contentFlags, NCrypto::TMDParser::TMDContentFlags::FLAG_SHA1);
+			cluster.contentSize = content.size;
+			static_assert(sizeof(content.hash32) == sizeof(cluster.contentHash32));
+			memcpy(cluster.contentHash32, content.hash32, sizeof(cluster.contentHash32));
+			// if unhashed mode, then initialize the hash context
+			if(cluster.hashMode == ClusterHashMode::RAW || cluster.hashMode == ClusterHashMode::RAW_STREAM)
+			{
+				cluster.singleHashCtx.reset(EVP_MD_CTX_new());
+				EVP_DigestInit_ex(cluster.singleHashCtx.get(), cluster.contentHashIsSHA1 ? EVP_sha1() : EVP_sha256(), nullptr);
+			}
+		}
 	}
 	// preprocess FST table
 	FSTHeader_FileEntry* fileTable = (FSTHeader_FileEntry*)(clusterDataTable + numCluster);
@@ -491,16 +540,17 @@ FSTVolume* FSTVolume::OpenFST(FSTDataSource* dataSource, uint64 fstOffset, uint3
 	fstVolume->m_offsetFactor = fstHeader->offsetFactor;
 	fstVolume->m_sectorSize = DISC_SECTOR_SIZE;
 	fstVolume->m_partitionTitlekey = *partitionTitleKey;
-	std::swap(fstVolume->m_cluster, clusterTable);
-	std::swap(fstVolume->m_entries, fstEntries);
-	std::swap(fstVolume->m_nameStringTable, nameStringTable);
+	fstVolume->m_hashIsDisabled = fstHeader->hashIsDisabled != 0;
+	fstVolume->m_cluster = std::move(clusterTable);
+	fstVolume->m_entries = std::move(fstEntries);
+	fstVolume->m_nameStringTable = std::move(nameStringTable);
 	return fstVolume;
 }
 
-FSTVolume* FSTVolume::OpenFST(std::unique_ptr<FSTDataSource> dataSource, uint64 fstOffset, uint32 fstSize, NCrypto::AesKey* partitionTitleKey, ClusterHashMode fstHashMode)
+FSTVolume* FSTVolume::OpenFST(std::unique_ptr<FSTDataSource> dataSource, uint64 fstOffset, uint32 fstSize, NCrypto::AesKey* partitionTitleKey, ClusterHashMode fstHashMode, NCrypto::TMDParser* optionalTMD)
 {
 	FSTDataSource* ds = dataSource.release();
-	FSTVolume* fstVolume = OpenFST(ds, fstOffset, fstSize, partitionTitleKey, fstHashMode);
+	FSTVolume* fstVolume = OpenFST(ds, fstOffset, fstSize, partitionTitleKey, fstHashMode, optionalTMD);
 	if (!fstVolume)
 	{
 		delete ds;
@@ -757,7 +807,7 @@ uint32 FSTVolume::ReadFile(FSTFileHandle& fileHandle, uint32 offset, uint32 size
 		return 0;
 	cemu_assert_debug(!HAS_FLAG(entry.GetFlags(), FSTEntry::FLAGS::FLAG_LINK));
 	FSTCluster& cluster = m_cluster[entry.fileInfo.clusterIndex];
-	if (cluster.hashMode == ClusterHashMode::RAW || cluster.hashMode == ClusterHashMode::RAW2)
+	if (cluster.hashMode == ClusterHashMode::RAW || cluster.hashMode == ClusterHashMode::RAW_STREAM)
 		return ReadFile_HashModeRaw(entry.fileInfo.clusterIndex, entry, offset, size, dataOut);
 	else if (cluster.hashMode == ClusterHashMode::HASH_INTERLEAVED)
 		return ReadFile_HashModeHashed(entry.fileInfo.clusterIndex, entry, offset, size, dataOut);
@@ -765,87 +815,15 @@ uint32 FSTVolume::ReadFile(FSTFileHandle& fileHandle, uint32 offset, uint32 size
 	return 0;
 }
 
-uint32 FSTVolume::ReadFile_HashModeRaw(uint32 clusterIndex, FSTEntry& entry, uint32 readOffset, uint32 readSize, void* dataOut)
-{
-	const uint32 readSizeInput = readSize;
-	uint8* dataOutU8 = (uint8*)dataOut;
-	if (readOffset >= entry.fileInfo.fileSize)
-		return 0;
-	else if ((readOffset + readSize) >= entry.fileInfo.fileSize)
-		readSize = (entry.fileInfo.fileSize - readOffset);
-
-	const FSTCluster& cluster = m_cluster[clusterIndex];
-	uint64 clusterOffset = (uint64)cluster.offset * m_sectorSize;
-	uint64 absFileOffset = entry.fileInfo.fileOffset * m_offsetFactor + readOffset;
-
-	// make sure the raw range we read is aligned to AES block size (16)
-	uint64 readAddrStart = absFileOffset & ~0xF;
-	uint64 readAddrEnd = (absFileOffset + readSize + 0xF) & ~0xF;
-
-	bool usesInitialIV = readOffset < 16;
-	if (!usesInitialIV)
-		readAddrStart -= 16; // read previous AES block since we require it for the IV
-	uint32 prePadding = (uint32)(absFileOffset - readAddrStart); // number of extra bytes we read before readOffset (for AES alignment and IV calculation)
-	uint32 postPadding = (uint32)(readAddrEnd - (absFileOffset + readSize));
-
-	uint8 readBuffer[64 * 1024];
-	// read first chunk
-	// if file read offset (readOffset) is within the first AES-block then use initial IV calculated from cluster index
-	// otherwise read previous AES-block is the IV (AES-CBC)
-	uint64 readAddrCurrent = readAddrStart;
-	uint32 rawBytesToRead = (uint32)std::min((readAddrEnd - readAddrStart), (uint64)sizeof(readBuffer));
-	if (m_dataSource->readData(clusterIndex, clusterOffset, readAddrCurrent, readBuffer, rawBytesToRead) != rawBytesToRead)
-	{
-		cemuLog_log(LogType::Force, "FST read error in raw content");
-		return 0;
-	}
-	readAddrCurrent += rawBytesToRead;
-
-	uint8 iv[16]{};
-	if (usesInitialIV)
-	{
-		// for the first AES block, the IV is initialized from cluster index
-		iv[0] = (uint8)(clusterIndex >> 8);
-		iv[1] = (uint8)(clusterIndex >> 0);
-		AES128_CBC_decrypt_updateIV(readBuffer, readBuffer, rawBytesToRead, m_partitionTitlekey.b, iv);
-		std::memcpy(dataOutU8, readBuffer + prePadding, rawBytesToRead - prePadding - postPadding);
-		dataOutU8 += (rawBytesToRead - prePadding - postPadding);
-		readSize -= (rawBytesToRead - prePadding - postPadding);
-	}
-	else
-	{
-		// IV is initialized from previous AES block (AES-CBC)
-		std::memcpy(iv, readBuffer, 16);
-		AES128_CBC_decrypt_updateIV(readBuffer + 16, readBuffer + 16, rawBytesToRead - 16, m_partitionTitlekey.b, iv);
-		std::memcpy(dataOutU8, readBuffer + prePadding, rawBytesToRead - prePadding - postPadding);
-		dataOutU8 += (rawBytesToRead - prePadding - postPadding);
-		readSize -= (rawBytesToRead - prePadding - postPadding);
-	}
-
-	// read remaining chunks
-	while (readSize > 0)
-	{
-		uint32 bytesToRead = (uint32)std::min((uint32)sizeof(readBuffer), readSize);
-		uint32 alignedBytesToRead = (bytesToRead + 15) & ~0xF;
-		if (m_dataSource->readData(clusterIndex, clusterOffset, readAddrCurrent, readBuffer, alignedBytesToRead) != alignedBytesToRead)
-		{
-			cemuLog_log(LogType::Force, "FST read error in raw content");
-			return 0;
-		}
-		AES128_CBC_decrypt_updateIV(readBuffer, readBuffer, alignedBytesToRead, m_partitionTitlekey.b, iv);
-		std::memcpy(dataOutU8, readBuffer, bytesToRead);
-		dataOutU8 += bytesToRead;
-		readSize -= bytesToRead;
-		readAddrCurrent += alignedBytesToRead;
-	}
-
-	return readSizeInput - readSize;
-}
-
 constexpr size_t BLOCK_SIZE = 0x10000;
 constexpr size_t BLOCK_HASH_SIZE = 0x0400;
 constexpr size_t BLOCK_FILE_SIZE = 0xFC00;
 
+struct FSTRawBlock
+{
+	std::vector<uint8> rawData; // unhashed block size depends on sector size field in partition header
+};
+
 struct FSTHashedBlock
 {
 	uint8 rawData[BLOCK_SIZE];
@@ -887,12 +865,160 @@ struct FSTHashedBlock
 
 static_assert(sizeof(FSTHashedBlock) == BLOCK_SIZE);
 
+struct FSTCachedRawBlock
+{
+	FSTRawBlock blockData;
+	uint8 ivForNextBlock[16];
+	uint64 lastAccess;
+};
+
 struct FSTCachedHashedBlock 
 {
 	FSTHashedBlock blockData;
 	uint64 lastAccess;
 };
 
+// Checks cache fill state and if necessary drops least recently accessed block from the cache. Optionally allows to recycle the released cache entry to cut down cost of memory allocation and clearing
+void FSTVolume::TrimCacheIfRequired(FSTCachedRawBlock** droppedRawBlock, FSTCachedHashedBlock** droppedHashedBlock)
+{
+	// calculate size used by cache
+	size_t cacheSize = 0;
+	for (auto& itr : m_cacheDecryptedRawBlocks)
+		cacheSize += itr.second->blockData.rawData.size();
+	for (auto& itr : m_cacheDecryptedHashedBlocks)
+		cacheSize += sizeof(FSTCachedHashedBlock) + sizeof(FSTHashedBlock);
+	// only trim if cache is full (larger than 2MB)
+	if (cacheSize < 2*1024*1024) // 2MB
+		return;
+	// scan both cache lists to find least recently accessed block to drop
+	auto dropRawItr = std::min_element(m_cacheDecryptedRawBlocks.begin(), m_cacheDecryptedRawBlocks.end(), [](const auto& a, const auto& b) -> bool
+										{ return a.second->lastAccess < b.second->lastAccess; });
+	auto dropHashedItr = std::min_element(m_cacheDecryptedHashedBlocks.begin(), m_cacheDecryptedHashedBlocks.end(), [](const auto& a, const auto& b) -> bool
+										{ return a.second->lastAccess < b.second->lastAccess; });
+	uint64 lastAccess = std::numeric_limits<uint64>::max();
+	if(dropRawItr != m_cacheDecryptedRawBlocks.end())
+		lastAccess = dropRawItr->second->lastAccess;
+	if(dropHashedItr != m_cacheDecryptedHashedBlocks.end())
+		lastAccess = std::min<uint64>(lastAccess, dropHashedItr->second->lastAccess);
+	if(dropRawItr != m_cacheDecryptedRawBlocks.end() && dropRawItr->second->lastAccess == lastAccess)
+	{
+		if (droppedRawBlock)
+			*droppedRawBlock = dropRawItr->second;
+		else
+			delete dropRawItr->second;
+		m_cacheDecryptedRawBlocks.erase(dropRawItr);
+		return;
+	}
+	else if(dropHashedItr != m_cacheDecryptedHashedBlocks.end() && dropHashedItr->second->lastAccess == lastAccess)
+	{
+		if (droppedHashedBlock)
+			*droppedHashedBlock = dropHashedItr->second;
+		else
+			delete dropHashedItr->second;
+		m_cacheDecryptedHashedBlocks.erase(dropHashedItr);
+	}
+}
+
+void FSTVolume::DetermineUnhashedBlockIV(uint32 clusterIndex, uint32 blockIndex, uint8 ivOut[16])
+{
+	memset(ivOut, 0, sizeof(ivOut));
+	if(blockIndex == 0)
+	{
+		ivOut[0] = (uint8)(clusterIndex >> 8);
+		ivOut[1] = (uint8)(clusterIndex >> 0);
+	}
+	else
+	{
+		// the last 16 encrypted bytes of the previous block are the IV (AES CBC)
+		// if the previous block is cached we can grab the IV from there. Otherwise we have to read the 16 bytes from the data source
+		uint32 prevBlockIndex = blockIndex - 1;
+		uint64 cacheBlockId = ((uint64)clusterIndex << (64 - 16)) | (uint64)prevBlockIndex;
+		auto itr = m_cacheDecryptedRawBlocks.find(cacheBlockId);
+		if (itr != m_cacheDecryptedRawBlocks.end())
+		{
+			memcpy(ivOut, itr->second->ivForNextBlock, 16);
+		}
+		else
+		{
+			cemu_assert(m_sectorSize >= 16);
+			uint64 clusterOffset = (uint64)m_cluster[clusterIndex].offset * m_sectorSize;
+			uint8 prevIV[16];
+			if (m_dataSource->readData(clusterIndex, clusterOffset, blockIndex * m_sectorSize - 16, prevIV, 16) != 16)
+			{
+				cemuLog_log(LogType::Force, "Failed to read IV for raw FST block");
+				m_detectedCorruption = true;
+				return;
+			}
+			memcpy(ivOut, prevIV, 16);
+		}
+	}
+}
+
+FSTCachedRawBlock* FSTVolume::GetDecryptedRawBlock(uint32 clusterIndex, uint32 blockIndex)
+{
+	FSTCluster& cluster = m_cluster[clusterIndex];
+	uint64 clusterOffset = (uint64)cluster.offset * m_sectorSize;
+	// generate id for cache
+	uint64 cacheBlockId = ((uint64)clusterIndex << (64 - 16)) | (uint64)blockIndex;
+	// lookup block in cache
+	FSTCachedRawBlock* block = nullptr;
+	auto itr = m_cacheDecryptedRawBlocks.find(cacheBlockId);
+	if (itr != m_cacheDecryptedRawBlocks.end())
+	{
+		block = itr->second;
+		block->lastAccess = ++m_cacheAccessCounter;
+		return block;
+	}
+	// if cache already full, drop least recently accessed block and recycle FSTCachedRawBlock object if possible
+	TrimCacheIfRequired(&block, nullptr);
+	if (!block)
+		block = new FSTCachedRawBlock();
+	block->blockData.rawData.resize(m_sectorSize);
+	// block not cached, read new
+	block->lastAccess = ++m_cacheAccessCounter;
+	if (m_dataSource->readData(clusterIndex, clusterOffset, blockIndex * m_sectorSize, block->blockData.rawData.data(), m_sectorSize) != m_sectorSize)
+	{
+		cemuLog_log(LogType::Force, "Failed to read raw FST block");
+		delete block;
+		m_detectedCorruption = true;
+		return nullptr;
+	}
+	// decrypt hash data
+	uint8 iv[16]{};
+	DetermineUnhashedBlockIV(clusterIndex, blockIndex, iv);
+	memcpy(block->ivForNextBlock, block->blockData.rawData.data() + m_sectorSize - 16, 16);
+	AES128_CBC_decrypt(block->blockData.rawData.data(), block->blockData.rawData.data(), m_sectorSize, m_partitionTitlekey.b, iv);
+	// if this is the next block, then hash it
+	if(cluster.hasContentHash)
+	{
+		if(cluster.singleHashNumBlocksHashed == blockIndex)
+		{
+			cemu_assert_debug(!(cluster.contentSize % m_sectorSize)); // size should be multiple of sector size? Regardless, the hashing code below can handle non-aligned sizes
+			bool isLastBlock = blockIndex == (std::max<uint32>(cluster.contentSize / m_sectorSize, 1) - 1);
+			uint32 hashSize = m_sectorSize;
+			if(isLastBlock)
+				hashSize = cluster.contentSize - (uint64)blockIndex*m_sectorSize;
+			EVP_DigestUpdate(cluster.singleHashCtx.get(), block->blockData.rawData.data(), hashSize);
+			cluster.singleHashNumBlocksHashed++;
+			if(isLastBlock)
+			{
+				uint8 hash[32];
+				EVP_DigestFinal_ex(cluster.singleHashCtx.get(), hash, nullptr);
+				if(memcmp(hash, cluster.contentHash32, cluster.contentHashIsSHA1 ? 20 : 32) != 0)
+				{
+					cemuLog_log(LogType::Force, "FST: Raw section hash mismatch");
+					delete block;
+					m_detectedCorruption = true;
+					return nullptr;
+				}
+			}
+		}
+	}
+	// register in cache
+	m_cacheDecryptedRawBlocks.emplace(cacheBlockId, block);
+	return block;
+}
+
 FSTCachedHashedBlock* FSTVolume::GetDecryptedHashedBlock(uint32 clusterIndex, uint32 blockIndex)
 {
 	const FSTCluster& cluster = m_cluster[clusterIndex];
@@ -908,22 +1034,17 @@ FSTCachedHashedBlock* FSTVolume::GetDecryptedHashedBlock(uint32 clusterIndex, ui
 		block->lastAccess = ++m_cacheAccessCounter;
 		return block;
 	}
-	// if cache already full, drop least recently accessed block (but recycle the FSTHashedBlock* object)
-	if (m_cacheDecryptedHashedBlocks.size() >= 16)
-	{
-		auto dropItr = std::min_element(m_cacheDecryptedHashedBlocks.begin(), m_cacheDecryptedHashedBlocks.end(), [](const auto& a, const auto& b) -> bool
-		{ return a.second->lastAccess < b.second->lastAccess; });
-		block = dropItr->second;
-		m_cacheDecryptedHashedBlocks.erase(dropItr);
-	}
-	else
+	// if cache already full, drop least recently accessed block and recycle FSTCachedHashedBlock object if possible
+	TrimCacheIfRequired(nullptr, &block);
+	if (!block)
 		block = new FSTCachedHashedBlock();
 	// block not cached, read new
 	block->lastAccess = ++m_cacheAccessCounter;
 	if (m_dataSource->readData(clusterIndex, clusterOffset, blockIndex * BLOCK_SIZE, block->blockData.rawData, BLOCK_SIZE) != BLOCK_SIZE)
 	{
-		cemuLog_log(LogType::Force, "Failed to read FST block");
+		cemuLog_log(LogType::Force, "Failed to read hashed FST block");
 		delete block;
+		m_detectedCorruption = true;
 		return nullptr;
 	}
 	// decrypt hash data
@@ -931,11 +1052,46 @@ FSTCachedHashedBlock* FSTVolume::GetDecryptedHashedBlock(uint32 clusterIndex, ui
 	AES128_CBC_decrypt(block->blockData.getHashData(), block->blockData.getHashData(), BLOCK_HASH_SIZE, m_partitionTitlekey.b, iv);
 	// decrypt file data
 	AES128_CBC_decrypt(block->blockData.getFileData(), block->blockData.getFileData(), BLOCK_FILE_SIZE, m_partitionTitlekey.b, block->blockData.getH0Hash(blockIndex%16));
+	// compare with H0 to verify data integrity
+	NCrypto::CHash160 h0;
+	SHA1(block->blockData.getFileData(), BLOCK_FILE_SIZE, h0.b);
+	uint32 h0Index = (blockIndex % 4096);
+	if (memcmp(h0.b, block->blockData.getH0Hash(h0Index & 0xF), sizeof(h0.b)) != 0)
+	{
+		cemuLog_log(LogType::Force, "FST: Hash H0 mismatch in hashed block (section {} index {})", clusterIndex, blockIndex);
+		delete block;
+		m_detectedCorruption = true;
+		return nullptr;
+	}
 	// register in cache
 	m_cacheDecryptedHashedBlocks.emplace(cacheBlockId, block);
 	return block;
 }
 
+uint32 FSTVolume::ReadFile_HashModeRaw(uint32 clusterIndex, FSTEntry& entry, uint32 readOffset, uint32 readSize, void* dataOut)
+{
+	uint8* dataOutU8 = (uint8*)dataOut;
+	if (readOffset >= entry.fileInfo.fileSize)
+		return 0;
+	else if ((readOffset + readSize) >= entry.fileInfo.fileSize)
+		readSize = (entry.fileInfo.fileSize - readOffset);
+	uint64 absFileOffset = entry.fileInfo.fileOffset * m_offsetFactor + readOffset;
+	uint32 remainingReadSize = readSize;
+	while (remainingReadSize > 0)
+	{
+		const FSTCachedRawBlock* rawBlock = this->GetDecryptedRawBlock(clusterIndex, absFileOffset/m_sectorSize);
+		if (!rawBlock)
+			break;
+		uint32 blockOffset = (uint32)(absFileOffset % m_sectorSize);
+		uint32 bytesToRead = std::min<uint32>(remainingReadSize, m_sectorSize - blockOffset);
+		std::memcpy(dataOutU8, rawBlock->blockData.rawData.data() + blockOffset, bytesToRead);
+		dataOutU8 += bytesToRead;
+		remainingReadSize -= bytesToRead;
+		absFileOffset += bytesToRead;
+	}
+	return readSize - remainingReadSize;
+}
+
 uint32 FSTVolume::ReadFile_HashModeHashed(uint32 clusterIndex, FSTEntry& entry, uint32 readOffset, uint32 readSize, void* dataOut)
 {
 	/*
@@ -966,7 +1122,6 @@ uint32 FSTVolume::ReadFile_HashModeHashed(uint32 clusterIndex, FSTEntry& entry,
 	*/
 
 	const FSTCluster& cluster = m_cluster[clusterIndex];
-	uint64 clusterBaseOffset = (uint64)cluster.offset * m_sectorSize;
 	uint64 fileReadOffset = entry.fileInfo.fileOffset * m_offsetFactor + readOffset;
 	uint32 blockIndex = (uint32)(fileReadOffset / BLOCK_FILE_SIZE);
 	uint32 bytesRemaining = readSize;
@@ -1019,6 +1174,8 @@ bool FSTVolume::Next(FSTDirectoryIterator& directoryIterator, FSTFileHandle& fil
 
 FSTVolume::~FSTVolume()
 {
+	for (auto& itr : m_cacheDecryptedRawBlocks)
+		delete itr.second;
 	for (auto& itr : m_cacheDecryptedHashedBlocks)
 		delete itr.second;
 	if (m_sourceIsOwned)

src/Cafe/Filesystem/FST/FST.h

@@ -1,5 +1,6 @@
 #pragma once
 #include "Cemu/ncrypto/ncrypto.h"
+#include "openssl/evp.h"
 
 struct FSTFileHandle
 {
@@ -45,6 +46,7 @@ public:
 	~FSTVolume();
 
 	uint32 GetFileCount() const;
+	bool HasCorruption() const { return m_detectedCorruption; }
 
 	bool OpenFile(std::string_view path, FSTFileHandle& fileHandleOut, bool openOnlyFiles = false);
 
@@ -86,15 +88,25 @@ private:
 	enum class ClusterHashMode : uint8
 	{
 		RAW = 0, // raw data + encryption, no hashing?
-		RAW2 = 1, // raw data + encryption, with hash stored in tmd?
+	  	RAW_STREAM = 1, // raw data + encryption, with hash stored in tmd?
 		HASH_INTERLEAVED = 2, // hashes + raw interleaved in 0x10000 blocks (0x400 bytes of hashes at the beginning, followed by 0xFC00 bytes of data)
 	};
 
 	struct FSTCluster
 	{
+		FSTCluster() : singleHashCtx(nullptr, &EVP_MD_CTX_free) {}
+
 		uint32 offset;
 		uint32 size;
 		ClusterHashMode hashMode;
+		// extra data if TMD is available
+		bool hasContentHash;
+		uint8 contentHash32[32];
+		bool contentHashIsSHA1; // if true then it's SHA1 (with extra bytes zeroed out), otherwise it's SHA256
+		uint64 contentSize; // size of the content (in blocks)
+		// hash context for single hash mode (content hash must be available)
+		std::unique_ptr<EVP_MD_CTX, decltype(&EVP_MD_CTX_free)> singleHashCtx; // unique_ptr to make this move-only
+		uint32 singleHashNumBlocksHashed{0};
 	};
 
 	struct FSTEntry
@@ -164,17 +176,30 @@ private:
 	bool m_sourceIsOwned{};
 	uint32 m_sectorSize{}; // for cluster offsets
 	uint32 m_offsetFactor{}; // for file offsets
+	bool m_hashIsDisabled{}; // disables hash verification (for all clusters of this volume?)
 	std::vector<FSTCluster> m_cluster;
 	std::vector<FSTEntry> m_entries;
 	std::vector<char> m_nameStringTable;
 	NCrypto::AesKey m_partitionTitlekey;
+	bool m_detectedCorruption{false};
 
-	/* Cache for decrypted hashed blocks */
+	bool HashIsDisabled() const
+	{
+		return m_hashIsDisabled;
+	}
+
+	/* Cache for decrypted raw and hashed blocks */
+	std::unordered_map<uint64, struct FSTCachedRawBlock*> m_cacheDecryptedRawBlocks;
 	std::unordered_map<uint64, struct FSTCachedHashedBlock*> m_cacheDecryptedHashedBlocks;
 	uint64 m_cacheAccessCounter{};
 
+	void DetermineUnhashedBlockIV(uint32 clusterIndex, uint32 blockIndex, uint8 ivOut[16]);
+
+	struct FSTCachedRawBlock* GetDecryptedRawBlock(uint32 clusterIndex, uint32 blockIndex);
 	struct FSTCachedHashedBlock* GetDecryptedHashedBlock(uint32 clusterIndex, uint32 blockIndex);
 
+	void TrimCacheIfRequired(struct FSTCachedRawBlock** droppedRawBlock, struct FSTCachedHashedBlock** droppedHashedBlock);
+
 	/* File reading */
 	uint32 ReadFile_HashModeRaw(uint32 clusterIndex, FSTEntry& entry, uint32 readOffset, uint32 readSize, void* dataOut);
 	uint32 ReadFile_HashModeHashed(uint32 clusterIndex, FSTEntry& entry, uint32 readOffset, uint32 readSize, void* dataOut);
@@ -185,7 +210,10 @@ private:
 		/* +0x00 */ uint32be magic;
 		/* +0x04 */ uint32be offsetFactor;
 		/* +0x08 */ uint32be numCluster;
-		/* +0x0C */ uint32be ukn0C;
+		/* +0x0C */ uint8be hashIsDisabled;
+		/* +0x0D */ uint8be ukn0D;
+		/* +0x0E */ uint8be ukn0E;
+		/* +0x0F */ uint8be ukn0F;
 		/* +0x10 */ uint32be ukn10;
 		/* +0x14 */ uint32be ukn14;
 		/* +0x18 */ uint32be ukn18;
@@ -262,8 +290,8 @@ private:
 
 	static_assert(sizeof(FSTHeader_FileEntry) == 0x10);
 
-	static FSTVolume* OpenFST(FSTDataSource* dataSource, uint64 fstOffset, uint32 fstSize, NCrypto::AesKey* partitionTitleKey, ClusterHashMode fstHashMode);
-	static FSTVolume* OpenFST(std::unique_ptr<FSTDataSource> dataSource, uint64 fstOffset, uint32 fstSize, NCrypto::AesKey* partitionTitleKey, ClusterHashMode fstHashMode);
+	static FSTVolume* OpenFST(FSTDataSource* dataSource, uint64 fstOffset, uint32 fstSize, NCrypto::AesKey* partitionTitleKey, ClusterHashMode fstHashMode, NCrypto::TMDParser* optionalTMD);
+	static FSTVolume* OpenFST(std::unique_ptr<FSTDataSource> dataSource, uint64 fstOffset, uint32 fstSize, NCrypto::AesKey* partitionTitleKey, ClusterHashMode fstHashMode, NCrypto::TMDParser* optionalTMD);
 	static bool ProcessFST(FSTHeader_FileEntry* fileTable, uint32 numFileEntries, uint32 numCluster, std::vector<char>& nameStringTable, std::vector<FSTEntry>& fstEntries);
 
 	bool MatchFSTEntryName(FSTEntry& entry, std::string_view comparedName)

src/Cafe/Filesystem/FST/fstUtil.h

@@ -3,6 +3,8 @@
 
 #include <boost/container/small_vector.hpp>
 
+#include "../fsc.h"
+
 // path parser and utility class for Wii U paths
 // optimized to be allocation-free for common path lengths
 class FSCPath
@@ -119,8 +121,6 @@ public:
 template<typename F>
 class FSAFileTree
 {
-public:
-
   private:
 
 	enum NODETYPE : uint8
@@ -133,6 +133,7 @@ private:
 	{
 		std::string name;
 		std::vector<node_t*> subnodes;
+		size_t fileSize;
 		F* custom;
 		NODETYPE type;
 	};
@@ -179,13 +180,54 @@ private:
 		return newNode;
 	}
 
+	class DirectoryIterator : public FSCVirtualFile
+	{
+	  public:
+		DirectoryIterator(node_t* node)
+			: m_node(node), m_subnodeIndex(0)
+		{
+		}
+
+		sint32 fscGetType() override
+		{
+			return FSC_TYPE_DIRECTORY;
+		}
+
+		bool fscDirNext(FSCDirEntry* dirEntry) override
+		{
+			if (m_subnodeIndex >= m_node->subnodes.size())
+				return false;
+
+			const node_t* subnode = m_node->subnodes[m_subnodeIndex];
+
+			strncpy(dirEntry->path, subnode->name.c_str(), sizeof(dirEntry->path) - 1);
+			dirEntry->path[sizeof(dirEntry->path) - 1] = '\0';
+			dirEntry->isDirectory = subnode->type == FSAFileTree::NODETYPE_DIRECTORY;
+			dirEntry->isFile = subnode->type == FSAFileTree::NODETYPE_FILE;
+			dirEntry->fileSize = subnode->type == FSAFileTree::NODETYPE_FILE ? subnode->fileSize : 0;
+
+			++m_subnodeIndex;
+			return true;
+		}
+
+		bool fscRewindDir() override
+		{
+			m_subnodeIndex = 0;
+			return true;
+		}
+
+	  private:
+		node_t* m_node;
+		size_t m_subnodeIndex;
+	};
+
 public:
 	FSAFileTree()
 	{
 		rootNode.type = NODETYPE_DIRECTORY;
 	}
 
-	bool addFile(std::string_view path, F* custom)
+	bool addFile(std::string_view path, size_t fileSize, F* custom)
 	{
 		FSCPath p(path);
 		if (p.GetNodeCount() == 0)
@@ -196,6 +238,7 @@ public:
 			return false; // node already exists
 		// add file node
 		node_t* fileNode = newNode(directoryNode, NODETYPE_FILE, p.GetNodeName(p.GetNodeCount() - 1));
+		fileNode->fileSize = fileSize;
 		fileNode->custom = custom;
 		return true;
 	}
@@ -214,6 +257,20 @@ public:
 		return true;
 	}
 
+	bool getDirectory(std::string_view path, FSCVirtualFile*& dirIterator)
+	{
+		FSCPath p(path);
+		if (p.GetNodeCount() == 0)
+			return false;
+		node_t* node = getByNodePath(p, p.GetNodeCount(), false);
+		if (node == nullptr)
+			return false;
+		if (node->type != NODETYPE_DIRECTORY)
+			return false;
+		dirIterator = new DirectoryIterator(node);
+		return true;
+	}
+
 	bool removeFile(std::string_view path)
 	{
 		FSCPath p(path);

src/Cafe/Filesystem/WUHB/RomFSStructs.h

@@ -0,0 +1,40 @@
+#pragma once
+
+struct romfs_header_t
+{
+	uint32 header_magic;
+	uint32be header_size;
+	uint64be dir_hash_table_ofs;
+	uint64be dir_hash_table_size;
+	uint64be dir_table_ofs;
+	uint64be dir_table_size;
+	uint64be file_hash_table_ofs;
+	uint64be file_hash_table_size;
+	uint64be file_table_ofs;
+	uint64be file_table_size;
+	uint64be file_partition_ofs;
+};
+
+struct romfs_direntry_t
+{
+	uint32be parent;
+	uint32be listNext;	   // offset to next directory entry in linked list of parent directory (aka "sibling")
+	uint32be dirListHead;  // offset to first entry in linked list of directory entries (aka "child")
+	uint32be fileListHead; // offset to first entry in linked list of file entries (aka "file")
+	uint32be hash;
+	uint32be name_size;
+	std::string name;
+};
+
+struct romfs_fentry_t
+{
+	uint32be parent;
+	uint32be listNext; // offset to next file entry in linked list of parent directory (aka "sibling")
+	uint64be offset;
+	uint64be size;
+	uint32be hash;
+	uint32be name_size;
+	std::string name;
+};
+
+#define ROMFS_ENTRY_EMPTY 0xFFFFFFFF

src/Cafe/Filesystem/WUHB/WUHBReader.cpp

@@ -0,0 +1,224 @@
+#include "WUHBReader.h"
+WUHBReader* WUHBReader::FromPath(const fs::path& path)
+{
+	FileStream* fileIn{FileStream::openFile2(path)};
+	if (!fileIn)
+		return nullptr;
+
+	WUHBReader* ret = new WUHBReader(fileIn);
+	if (!ret->CheckMagicValue())
+	{
+		delete ret;
+		return nullptr;
+	}
+
+	if (!ret->ReadHeader())
+	{
+		delete ret;
+		return nullptr;
+	}
+
+	return ret;
+}
+
+static const romfs_direntry_t fallbackDirEntry{
+	.parent = ROMFS_ENTRY_EMPTY,
+	.listNext = ROMFS_ENTRY_EMPTY,
+	.dirListHead = ROMFS_ENTRY_EMPTY,
+	.fileListHead = ROMFS_ENTRY_EMPTY,
+	.hash = ROMFS_ENTRY_EMPTY,
+	.name_size = 0,
+	.name = ""
+};
+static const romfs_fentry_t fallbackFileEntry{
+	.parent = ROMFS_ENTRY_EMPTY,
+	.listNext = ROMFS_ENTRY_EMPTY,
+	.offset = 0,
+	.size = 0,
+	.hash = ROMFS_ENTRY_EMPTY,
+	.name_size = 0,
+	.name = ""
+};
+template<bool File>
+const WUHBReader::EntryType<File>& WUHBReader::GetFallback()
+{
+	if constexpr (File)
+		return fallbackFileEntry;
+	else
+		return fallbackDirEntry;
+}
+
+template<bool File>
+WUHBReader::EntryType<File> WUHBReader::GetEntry(uint32 offset) const
+{
+	auto fallback = GetFallback<File>();
+	if(offset == ROMFS_ENTRY_EMPTY)
+		return fallback;
+
+	const char* typeName = File ? "fentry" : "direntry";
+	EntryType<File> ret;
+	if (offset >= (File ? m_header.file_table_size : m_header.dir_table_size))
+	{
+		cemuLog_log(LogType::Force, "WUHB {} offset exceeds table size declared in header", typeName);
+		return fallback;
+	}
+
+	// read the entry
+	m_fileIn->SetPosition((File ? m_header.file_table_ofs : m_header.dir_table_ofs) + offset);
+	auto read = m_fileIn->readData(&ret, offsetof(EntryType<File>, name));
+	if (read != offsetof(EntryType<File>, name))
+	{
+		cemuLog_log(LogType::Force, "failed to read WUHB {} at offset: {}", typeName, offset);
+		return fallback;
+	}
+
+	// read the name
+	ret.name.resize(ret.name_size);
+	read = m_fileIn->readData(ret.name.data(), ret.name_size);
+	if (read != ret.name_size)
+	{
+		cemuLog_log(LogType::Force, "failed to read WUHB {} name", typeName);
+		return fallback;
+	}
+
+	return ret;
+}
+
+romfs_direntry_t WUHBReader::GetDirEntry(uint32 offset) const
+{
+	return GetEntry<false>(offset);
+}
+romfs_fentry_t WUHBReader::GetFileEntry(uint32 offset) const
+{
+	return GetEntry<true>(offset);
+}
+
+uint64 WUHBReader::GetFileSize(uint32 entryOffset) const
+{
+	return GetFileEntry(entryOffset).size;
+}
+
+uint64 WUHBReader::ReadFromFile(uint32 entryOffset, uint64 fileOffset, uint64 length, void* buffer) const
+{
+	const auto fileEntry = GetFileEntry(entryOffset);
+	if (fileOffset >= fileEntry.size)
+		return 0;
+	const uint64 readAmount = std::min(length, fileEntry.size - fileOffset);
+	const uint64 wuhbOffset = m_header.file_partition_ofs + fileEntry.offset + fileOffset;
+	m_fileIn->SetPosition(wuhbOffset);
+	return m_fileIn->readData(buffer, readAmount);
+}
+
+uint32 WUHBReader::GetHashTableEntryOffset(uint32 hash, bool isFile) const
+{
+	const uint64 hash_table_size = (isFile ? m_header.file_hash_table_size : m_header.dir_hash_table_size);
+	const uint64 hash_table_ofs = (isFile ? m_header.file_hash_table_ofs : m_header.dir_hash_table_ofs);
+
+	const uint64 hash_table_entry_count = hash_table_size / sizeof(uint32);
+	const uint64 hash_table_entry_offset = hash_table_ofs + (hash % hash_table_entry_count) * sizeof(uint32);
+
+	m_fileIn->SetPosition(hash_table_entry_offset);
+	uint32 tableOffset;
+	if (!m_fileIn->readU32(tableOffset))
+	{
+		cemuLog_log(LogType::Force, "failed to read WUHB hash table entry at file offset: {}", hash_table_entry_offset);
+		return ROMFS_ENTRY_EMPTY;
+	}
+
+	return uint32be::from_bevalue(tableOffset);
+}
+
+template<bool T>
+bool WUHBReader::SearchHashList(uint32& entryOffset, const fs::path& targetName) const
+{
+	for (;;)
+	{
+		if (entryOffset == ROMFS_ENTRY_EMPTY)
+			return false;
+		auto entry = GetEntry<T>(entryOffset);
+
+		if (entry.name == targetName)
+			return true;
+		entryOffset = entry.hash;
+	}
+	return false;
+}
+
+uint32 WUHBReader::Lookup(const std::filesystem::path& path, bool isFile) const
+{
+	uint32 currentEntryOffset = 0;
+	auto look = [&](const fs::path& part, bool lookInFileHT) {
+		const auto partString = part.string();
+		currentEntryOffset = GetHashTableEntryOffset(CalcPathHash(currentEntryOffset, partString.c_str(), 0, partString.size()), lookInFileHT);
+		if (lookInFileHT)
+			return SearchHashList<true>(currentEntryOffset, part);
+		else
+			return SearchHashList<false>(currentEntryOffset, part);
+	};
+	// look for the root entry
+	if (!look("", false))
+		return ROMFS_ENTRY_EMPTY;
+
+	auto it = path.begin();
+	while (it != path.end())
+	{
+		fs::path part = *it;
+		++it;
+		// no need to recurse after trailing forward slash (e.g. directory/)
+		if (part.empty() && !isFile)
+			break;
+		// skip leading forward slash
+		if (part == "/")
+			continue;
+
+		// if the lookup target is a file and this is the last iteration, look in the file hash table instead.
+		if (!look(part, it == path.end() && isFile))
+			return ROMFS_ENTRY_EMPTY;
+	}
+	return currentEntryOffset;
+}
+bool WUHBReader::CheckMagicValue() const
+{
+	uint8 magic[4];
+	m_fileIn->SetPosition(0);
+	int read = m_fileIn->readData(magic, 4);
+	if (read != 4)
+	{
+		cemuLog_log(LogType::Force, "Failed to read WUHB magic numbers");
+		return false;
+	}
+	static_assert(sizeof(magic) == s_headerMagicValue.size());
+	return std::memcmp(&magic, s_headerMagicValue.data(), sizeof(magic)) == 0;
+}
+bool WUHBReader::ReadHeader()
+{
+	m_fileIn->SetPosition(0);
+	auto read = m_fileIn->readData(&m_header, sizeof(m_header));
+	auto readSuccess = read == sizeof(m_header);
+	if (!readSuccess)
+		cemuLog_log(LogType::Force, "Failed to read WUHB header");
+	return readSuccess;
+}
+unsigned char WUHBReader::NormalizeChar(unsigned char c)
+{
+	if (c >= 'a' && c <= 'z')
+	{
+		return c + 'A' - 'a';
+	}
+	else
+	{
+		return c;
+	}
+}
+uint32 WUHBReader::CalcPathHash(uint32 parent, const char* path, uint32 start, size_t path_len)
+{
+	cemu_assert(path != nullptr || path_len == 0);
+	uint32 hash = parent ^ 123456789;
+	for (uint32 i = 0; i < path_len; i++)
+	{
+		hash = (hash >> 5) | (hash << 27);
+		hash ^= NormalizeChar(path[start + i]);
+	}
+
+	return hash;
+}

src/Cafe/Filesystem/WUHB/WUHBReader.h

@@ -0,0 +1,45 @@
+#pragma once
+#include <Common/FileStream.h>
+#include "RomFSStructs.h"
+class WUHBReader
+{
+  public:
+	static WUHBReader* FromPath(const fs::path& path);
+
+	romfs_direntry_t GetDirEntry(uint32 offset) const;
+	romfs_fentry_t GetFileEntry(uint32 offset) const;
+
+	uint64 GetFileSize(uint32 entryOffset) const;
+
+	uint64 ReadFromFile(uint32 entryOffset, uint64 fileOffset, uint64 length, void* buffer) const;
+
+	uint32 Lookup(const std::filesystem::path& path, bool isFile) const;
+
+  private:
+	WUHBReader(FileStream* file)
+		: m_fileIn(file)
+	{
+		cemu_assert_debug(file != nullptr);
+	};
+	WUHBReader() = delete;
+
+	romfs_header_t m_header;
+	std::unique_ptr<FileStream> m_fileIn;
+	constexpr static std::string_view s_headerMagicValue = "WUHB";
+	bool ReadHeader();
+	bool CheckMagicValue() const;
+
+	static inline unsigned char NormalizeChar(unsigned char c);
+	static uint32 CalcPathHash(uint32 parent, const char* path, uint32 start, size_t path_len);
+
+	template<bool File>
+	using EntryType = std::conditional_t<File, romfs_fentry_t, romfs_direntry_t>;
+	template<bool File>
+	static const EntryType<File>& GetFallback();
+	template<bool File>
+	EntryType<File> GetEntry(uint32 offset) const;
+
+	template<bool T>
+	bool SearchHashList(uint32& entryOffset, const fs::path& targetName) const;
+	uint32 GetHashTableEntryOffset(uint32 hash, bool isFile) const;
+};

src/Cafe/Filesystem/fsc.h

@@ -204,9 +204,12 @@ bool FSCDeviceWUD_Mount(std::string_view mountPath, std::string_view destination
 // wua device
 bool FSCDeviceWUA_Mount(std::string_view mountPath, std::string_view destinationBaseDir, class ZArchiveReader* archive, sint32 priority);
 
+// wuhb device
+bool FSCDeviceWUHB_Mount(std::string_view mountPath, std::string_view destinationBaseDir, class WUHBReader* wuhbReader, sint32 priority);
+
 // hostFS device
 bool FSCDeviceHostFS_Mount(std::string_view mountPath, std::string_view hostTargetPath, sint32 priority);
 
 // redirect device
 void fscDeviceRedirect_map();
-void fscDeviceRedirect_add(std::string_view virtualSourcePath, const fs::path& targetFilePath, sint32 priority);
+void fscDeviceRedirect_add(std::string_view virtualSourcePath, size_t fileSize, const fs::path& targetFilePath, sint32 priority);

src/Cafe/Filesystem/fscDeviceRedirect.cpp

@@ -11,7 +11,7 @@ struct RedirectEntry
 
 FSAFileTree<RedirectEntry> redirectTree;
 
-void fscDeviceRedirect_add(std::string_view virtualSourcePath, const fs::path& targetFilePath, sint32 priority)
+void fscDeviceRedirect_add(std::string_view virtualSourcePath, size_t fileSize, const fs::path& targetFilePath, sint32 priority)
 {
 	// check if source already has a redirection
 	RedirectEntry* existingEntry;
@@ -24,7 +24,7 @@ void fscDeviceRedirect_add(std::string_view virtualSourcePath, const fs::path& t
 		delete existingEntry;
 	}
 	RedirectEntry* entry = new RedirectEntry(targetFilePath, priority);
-	redirectTree.addFile(virtualSourcePath, entry);
+	redirectTree.addFile(virtualSourcePath, fileSize, entry);
 }
 
 class fscDeviceTypeRedirect : public fscDeviceC
@@ -32,8 +32,15 @@ class fscDeviceTypeRedirect : public fscDeviceC
 	FSCVirtualFile* fscDeviceOpenByPath(std::string_view path, FSC_ACCESS_FLAG accessFlags, void* ctx, sint32* fscStatus) override
 	{
 		RedirectEntry* redirectionEntry;
-		if (redirectTree.getFile(path, redirectionEntry))
+
+		if (HAS_FLAG(accessFlags, FSC_ACCESS_FLAG::OPEN_FILE) && redirectTree.getFile(path, redirectionEntry))
 			return FSCVirtualFile_Host::OpenFile(redirectionEntry->dstPath, accessFlags, *fscStatus);
+
+		FSCVirtualFile* dirIterator;
+
+		if (HAS_FLAG(accessFlags, FSC_ACCESS_FLAG::OPEN_DIR) && redirectTree.getDirectory(path, dirIterator))
+			return dirIterator;
+
 		return nullptr;
 	}
 

src/Cafe/Filesystem/fscDeviceWuhb.cpp

@@ -0,0 +1,151 @@
+#include "Filesystem/WUHB/WUHBReader.h"
+#include "Cafe/Filesystem/fsc.h"
+#include "Cafe/Filesystem/FST/FST.h"
+
+class FSCDeviceWuhbFileCtx : public FSCVirtualFile
+{
+  public:
+	FSCDeviceWuhbFileCtx(WUHBReader* reader, uint32 entryOffset, uint32 fscType)
+		: m_wuhbReader(reader), m_entryOffset(entryOffset), m_fscType(fscType)
+	{
+		cemu_assert(entryOffset != ROMFS_ENTRY_EMPTY);
+		if (fscType == FSC_TYPE_DIRECTORY)
+		{
+			romfs_direntry_t entry = reader->GetDirEntry(entryOffset);
+			m_dirIterOffset = entry.dirListHead;
+			m_fileIterOffset = entry.fileListHead;
+		}
+	}
+	sint32 fscGetType() override
+	{
+		return m_fscType;
+	}
+	uint64 fscQueryValueU64(uint32 id) override
+	{
+		if (m_fscType == FSC_TYPE_FILE)
+		{
+			if (id == FSC_QUERY_SIZE)
+				return m_wuhbReader->GetFileSize(m_entryOffset);
+			else if (id == FSC_QUERY_WRITEABLE)
+				return 0; // WUHB images are read-only
+			else
+				cemu_assert_error();
+		}
+		else
+		{
+			cemu_assert_unimplemented();
+		}
+		return 0;
+	}
+	uint32 fscWriteData(void* buffer, uint32 size) override
+	{
+		cemu_assert_error();
+		return 0;
+	}
+	uint32 fscReadData(void* buffer, uint32 size) override
+	{
+		if (m_fscType != FSC_TYPE_FILE)
+			return 0;
+		auto read = m_wuhbReader->ReadFromFile(m_entryOffset, m_seek, size, buffer);
+		m_seek += read;
+		return read;
+	}
+	void fscSetSeek(uint64 seek) override
+	{
+		m_seek = seek;
+	}
+	uint64 fscGetSeek() override
+	{
+		if (m_fscType != FSC_TYPE_FILE)
+			return 0;
+		return m_seek;
+	}
+	void fscSetFileLength(uint64 endOffset) override
+	{
+		cemu_assert_error();
+	}
+	bool fscDirNext(FSCDirEntry* dirEntry) override
+	{
+		if (m_dirIterOffset != ROMFS_ENTRY_EMPTY)
+		{
+			romfs_direntry_t entry = m_wuhbReader->GetDirEntry(m_dirIterOffset);
+			m_dirIterOffset = entry.listNext;
+			if(entry.name_size > 0)
+			{
+				dirEntry->isDirectory = true;
+				dirEntry->isFile = false;
+				dirEntry->fileSize = 0;
+				std::strncpy(dirEntry->path, entry.name.c_str(), FSC_MAX_DIR_NAME_LENGTH);
+				return true;
+			}
+		}
+		if (m_fileIterOffset != ROMFS_ENTRY_EMPTY)
+		{
+			romfs_fentry_t entry = m_wuhbReader->GetFileEntry(m_fileIterOffset);
+			m_fileIterOffset = entry.listNext;
+			if(entry.name_size > 0)
+			{
+				dirEntry->isDirectory = false;
+				dirEntry->isFile = true;
+				dirEntry->fileSize = entry.size;
+				std::strncpy(dirEntry->path, entry.name.c_str(), FSC_MAX_DIR_NAME_LENGTH);
+				return true;
+			}
+		}
+
+		return false;
+	}
+
+  private:
+	WUHBReader* m_wuhbReader{};
+	uint32 m_fscType;
+	uint32 m_entryOffset = ROMFS_ENTRY_EMPTY;
+	uint32 m_dirIterOffset = ROMFS_ENTRY_EMPTY;
+	uint32 m_fileIterOffset = ROMFS_ENTRY_EMPTY;
+	uint64 m_seek = 0;
+};
+
+class fscDeviceWUHB : public fscDeviceC
+{
+	FSCVirtualFile* fscDeviceOpenByPath(std::string_view path, FSC_ACCESS_FLAG accessFlags, void* ctx, sint32* fscStatus) override
+	{
+		WUHBReader* reader = (WUHBReader*)ctx;
+		cemu_assert_debug(!HAS_FLAG(accessFlags, FSC_ACCESS_FLAG::WRITE_PERMISSION)); // writing to WUHB is not supported
+
+		bool isFile;
+		uint32 table_offset = ROMFS_ENTRY_EMPTY;
+
+		if (table_offset == ROMFS_ENTRY_EMPTY && HAS_FLAG(accessFlags, FSC_ACCESS_FLAG::OPEN_DIR))
+		{
+			table_offset = reader->Lookup(path, false);
+			isFile = false;
+		}
+		if (table_offset == ROMFS_ENTRY_EMPTY && HAS_FLAG(accessFlags, FSC_ACCESS_FLAG::OPEN_FILE))
+		{
+			table_offset = reader->Lookup(path, true);
+			isFile = true;
+		}
+
+		if (table_offset == ROMFS_ENTRY_EMPTY)
+		{
+			*fscStatus = FSC_STATUS_FILE_NOT_FOUND;
+			return nullptr;
+		}
+
+		*fscStatus = FSC_STATUS_OK;
+		return new FSCDeviceWuhbFileCtx(reader, table_offset, isFile ? FSC_TYPE_FILE : FSC_TYPE_DIRECTORY);
+	}
+
+	// singleton
+  public:
+	static fscDeviceWUHB& instance()
+	{
+		static fscDeviceWUHB _instance;
+		return _instance;
+	}
+};
+
+bool FSCDeviceWUHB_Mount(std::string_view mountPath, std::string_view destinationBaseDir, WUHBReader* wuhbReader, sint32 priority)
+{
+	return fsc_mount(mountPath, destinationBaseDir, &fscDeviceWUHB::instance(), wuhbReader, priority) == FSC_STATUS_OK;
+}

src/Cafe/GameProfile/GameProfile.cpp

@@ -140,7 +140,7 @@ bool gameProfile_loadEnumOption(IniParser& iniParser, const char* optionName, T&
 	for(const T& v : T())
 	{
 		// test integer option
-		if (boost::iequals(fmt::format("{}", static_cast<typename std::underlying_type<T>::type>(v)), *option_value))
+		if (boost::iequals(fmt::format("{}", fmt::underlying(v)), *option_value))
 		{
 			option = v;
 			return true;
@@ -209,7 +209,7 @@ bool GameProfile::Load(uint64_t title_id)
 		m_gameName = std::string(game_name.begin(), game_name.end());
 		trim(m_gameName.value());
 	}
-	IniParser iniParser(*profileContents, gameProfilePath.string());
+	IniParser iniParser(*profileContents, _pathToUtf8(gameProfilePath));
 	// parse ini
 	while (iniParser.NextSection())
 	{

src/Cafe/GraphicPack/GraphicPack2.cpp

@@ -28,7 +28,7 @@ void GraphicPack2::LoadGraphicPack(fs::path graphicPackPath)
 		return;
 	std::vector<uint8> rulesData;
 	fs_rules->extract(rulesData);
-	IniParser iniParser(rulesData, rulesPath.string());
+	IniParser iniParser(rulesData, _pathToUtf8(rulesPath));
 
 	if (!iniParser.NextSection())
 	{
@@ -51,10 +51,9 @@ void GraphicPack2::LoadGraphicPack(fs::path graphicPackPath)
 			cemuLog_log(LogType::Force, "{}: Unable to parse version", _pathToUtf8(rulesPath));
 			return;
 		}
-
 		if (versionNum > GP_LEGACY_VERSION)
 		{
-			GraphicPack2::LoadGraphicPack(_pathToUtf8(rulesPath), iniParser);
+			GraphicPack2::LoadGraphicPack(rulesPath, iniParser);
 			return;
 		}
 	}
@@ -79,22 +78,22 @@ void GraphicPack2::LoadAll()
 	}
 }
 
-bool GraphicPack2::LoadGraphicPack(const std::string& filename, IniParser& rules)
+bool GraphicPack2::LoadGraphicPack(const fs::path& rulesPath, IniParser& rules)
 {
 	try
 	{
-		auto gp = std::make_shared<GraphicPack2>(filename, rules);
+		auto gp = std::make_shared<GraphicPack2>(rulesPath, rules);
 
 		// check if enabled and preset set
 		const auto& config_entries = g_config.data().graphic_pack_entries;
 
 		// legacy absolute path checking for not breaking compatibility
-		auto file = gp->GetFilename2();
+		auto file = gp->GetRulesPath();
 		auto it = config_entries.find(file.lexically_normal());
 		if (it == config_entries.cend())
 		{
 			// check for relative path
-			it = config_entries.find(MakeRelativePath(ActiveSettings::GetUserDataPath(), gp->GetFilename2()).lexically_normal());
+			it = config_entries.find(_utf8ToPath(gp->GetNormalizedPathString()));
 		}
 
 		if (it != config_entries.cend())
@@ -145,7 +144,7 @@ bool GraphicPack2::DeactivateGraphicPack(const std::shared_ptr<GraphicPack2>& gr
 	const auto it = std::find_if(s_active_graphic_packs.begin(), s_active_graphic_packs.end(), 
 		[graphic_pack](const GraphicPackPtr& gp)
 	{
-		return gp->GetFilename() == graphic_pack->GetFilename();
+		return gp->GetNormalizedPathString() == graphic_pack->GetNormalizedPathString();
 	}
 	);
 
@@ -173,12 +172,12 @@ void GraphicPack2::ActivateForCurrentTitle()
 		{
 			if (gp->GetPresets().empty())
 			{
-				cemuLog_log(LogType::Force, "Activate graphic pack: {}", gp->GetPath());
+				cemuLog_log(LogType::Force, "Activate graphic pack: {}", gp->GetVirtualPath());
 			}
 			else
 			{
 				std::string logLine;
-				logLine.assign(fmt::format("Activate graphic pack: {} [Presets: ", gp->GetPath()));
+				logLine.assign(fmt::format("Activate graphic pack: {} [Presets: ", gp->GetVirtualPath()));
 				bool isFirst = true;
 				for (auto& itr : gp->GetPresets())
 				{
@@ -249,8 +248,8 @@ std::unordered_map<std::string, GraphicPack2::PresetVar> GraphicPack2::ParsePres
 	return vars;
 }
 
-GraphicPack2::GraphicPack2(std::string filename, IniParser& rules)
-	: m_filename(std::move(filename))
+GraphicPack2::GraphicPack2(fs::path rulesPath, IniParser& rules)
+	: m_rulesPath(std::move(rulesPath))
 {
 	// we're already in [Definition]
 	auto option_version = rules.FindOption("version");
@@ -259,7 +258,7 @@ GraphicPack2::GraphicPack2(std::string filename, IniParser& rules)
 	m_version = StringHelpers::ToInt(*option_version, -1);
 	if (m_version < 0)
 	{
-		cemuLog_log(LogType::Force, "{}: Invalid version", m_filename);
+		cemuLog_log(LogType::Force, "{}: Invalid version", _pathToUtf8(m_rulesPath));
 		throw std::exception();
 	}
 
@@ -281,6 +280,10 @@ GraphicPack2::GraphicPack2(std::string filename, IniParser& rules)
 		m_enabled = m_default_enabled;
 	}
 
+	auto option_allowRendertargetSizeOptimization = rules.FindOption("colorbufferOptimizationAware");
+	if (option_allowRendertargetSizeOptimization)
+		m_allowRendertargetSizeOptimization = boost::iequals(*option_allowRendertargetSizeOptimization, "true") || boost::iequals(*option_allowRendertargetSizeOptimization, "1");
+
 	auto option_vendorFilter = rules.FindOption("vendorFilter");
 	if (option_vendorFilter)
 	{
@@ -305,7 +308,7 @@ GraphicPack2::GraphicPack2(std::string filename, IniParser& rules)
 		cemuLog_log(LogType::Force, "[Definition] section from '{}' graphic pack must contain option: path", gp_name_log.has_value() ? *gp_name_log : "Unknown");
 		throw std::exception();
 	}
-	m_path = *option_path;
+	m_virtualPath = *option_path;
 
 	auto option_gp_name = rules.FindOption("name");
 	if (option_gp_name)
@@ -342,7 +345,7 @@ GraphicPack2::GraphicPack2(std::string filename, IniParser& rules)
 			const auto preset_name = rules.FindOption("name");
 			if (!preset_name)
 			{
-				cemuLog_log(LogType::Force, "Graphic pack \"{}\": Preset in line {} skipped because it has no name option defined", m_name, rules.GetCurrentSectionLineNumber());
+				cemuLog_log(LogType::Force, "Graphic pack \"{}\": Preset in line {} skipped because it has no name option defined", GetNormalizedPathString(), rules.GetCurrentSectionLineNumber());
 				continue;
 			}
 			
@@ -366,7 +369,7 @@ GraphicPack2::GraphicPack2(std::string filename, IniParser& rules)
 			}
 			catch (const std::exception & ex)
 			{
-				cemuLog_log(LogType::Force, "Graphic pack \"{}\": Can't parse preset \"{}\": {}", m_name, *preset_name, ex.what());
+				cemuLog_log(LogType::Force, "Graphic pack \"{}\": Can't parse preset \"{}\": {}", GetNormalizedPathString(), *preset_name, ex.what());
 			}
 		}
 		else if (boost::iequals(currentSectionName, "RAM"))
@@ -380,7 +383,7 @@ GraphicPack2::GraphicPack2(std::string filename, IniParser& rules)
 				{
 					if (m_version <= 5)
 					{
-						cemuLog_log(LogType::Force, "Graphic pack \"{}\": [RAM] options are only available for graphic pack version 6 or higher", m_name, optionNameBuf);
+						cemuLog_log(LogType::Force, "Graphic pack \"{}\": [RAM] options are only available for graphic pack version 6 or higher", GetNormalizedPathString(), optionNameBuf);
 						throw std::exception();
 					}
 
@@ -390,12 +393,12 @@ GraphicPack2::GraphicPack2(std::string filename, IniParser& rules)
 					{
 						if (addrEnd <= addrStart)
 						{
-							cemuLog_log(LogType::Force, "Graphic pack \"{}\": start address (0x{:08x}) must be greater than end address (0x{:08x}) for {}", m_name, addrStart, addrEnd, optionNameBuf);
+							cemuLog_log(LogType::Force, "Graphic pack \"{}\": start address (0x{:08x}) must be greater than end address (0x{:08x}) for {}", GetNormalizedPathString(), addrStart, addrEnd, optionNameBuf);
 							throw std::exception();
 						}
 						else if ((addrStart & 0xFFF) != 0 || (addrEnd & 0xFFF) != 0)
 						{
-							cemuLog_log(LogType::Force, "Graphic pack \"{}\": addresses for %s are not aligned to 0x1000", m_name, optionNameBuf);
+							cemuLog_log(LogType::Force, "Graphic pack \"{}\": addresses for %s are not aligned to 0x1000", GetNormalizedPathString(), optionNameBuf);
 							throw std::exception();
 						}
 						else
@@ -405,7 +408,7 @@ GraphicPack2::GraphicPack2(std::string filename, IniParser& rules)
 					}
 					else
 					{
-						cemuLog_log(LogType::Force, "Graphic pack \"{}\": has invalid syntax for option {}", m_name, optionNameBuf);
+						cemuLog_log(LogType::Force, "Graphic pack \"{}\": has invalid syntax for option {}", GetNormalizedPathString(), optionNameBuf);
 						throw std::exception();
 					}
 				}
@@ -419,22 +422,30 @@ GraphicPack2::GraphicPack2(std::string filename, IniParser& rules)
 		std::unordered_map<std::string, std::vector<PresetPtr>> tmp_map;
 		
 		// all vars must be defined in the default preset vars before
-		for (const auto& entry : m_presets)
+		std::vector<std::pair<std::string, std::string>> mismatchingPresetVars;
+		for (const auto& presetEntry : m_presets)
 		{
-			tmp_map[entry->category].emplace_back(entry);
+			tmp_map[presetEntry->category].emplace_back(presetEntry);
 			
-			for (auto& kv : entry->variables)
+			for (auto& presetVar : presetEntry->variables)
 			{
-				const auto it = m_preset_vars.find(kv.first);
+				const auto it = m_preset_vars.find(presetVar.first);
 				if (it == m_preset_vars.cend())
 				{
-					cemuLog_log(LogType::Force, "Graphic pack: \"{}\" contains preset variables which are not defined in the default section", m_name);
-					throw std::exception();
+					mismatchingPresetVars.emplace_back(presetEntry->name, presetVar.first);
+					continue;
+				}
+				// overwrite var type with default var type
+				presetVar.second.first = it->second.first;
+			}
 		}
 
-				// overwrite var type with default var type
-				kv.second.first = it->second.first;
-			}
+		if(!mismatchingPresetVars.empty())
+		{
+			cemuLog_log(LogType::Force, "Graphic pack \"{}\" contains preset variables which are not defined in the [Default] section:", GetNormalizedPathString());
+			for (const auto& [presetName, varName] : mismatchingPresetVars)
+				cemuLog_log(LogType::Force, "Preset: {} Variable: {}", presetName, varName);
+			throw std::exception();
 		}
 
 		// have first entry be default active for every category if no default= is set
@@ -466,7 +477,7 @@ GraphicPack2::GraphicPack2(std::string filename, IniParser& rules)
 				auto& p2 = kv.second[i + 1];
 				if (p1->variables.size() != p2->variables.size())
 				{
-					cemuLog_log(LogType::Force, "Graphic pack: \"{}\" contains inconsistent preset variables", m_name);
+					cemuLog_log(LogType::Force, "Graphic pack: \"{}\" contains inconsistent preset variables", GetNormalizedPathString());
 					throw std::exception();
 				}
 
@@ -474,14 +485,14 @@ GraphicPack2::GraphicPack2(std::string filename, IniParser& rules)
 				std::set<std::string> keys2(get_keys(p2->variables).begin(), get_keys(p2->variables).end());
 				if (keys1 != keys2)
 				{
-					cemuLog_log(LogType::Force, "Graphic pack: \"{}\" contains inconsistent preset variables", m_name);
+					cemuLog_log(LogType::Force, "Graphic pack: \"{}\" contains inconsistent preset variables", GetNormalizedPathString());
 					throw std::exception();
 				}
 
 				if(p1->is_default)
 				{
 					if(has_default)
-						cemuLog_log(LogType::Force, "Graphic pack: \"{}\" has more than one preset with the default key set for the same category \"{}\"", m_name, p1->name);
+						cemuLog_log(LogType::Force, "Graphic pack: \"{}\" has more than one preset with the default key set for the same category \"{}\"", GetNormalizedPathString(), p1->name);
 					p1->active = true;
 					has_default = true;
 				}
@@ -508,6 +519,11 @@ bool GraphicPack2::Reload()
 	return Activate();
 }
 
+std::string GraphicPack2::GetNormalizedPathString() const
+{
+	return _pathToUtf8(MakeRelativePath(ActiveSettings::GetUserDataPath(), GetRulesPath()).lexically_normal());
+}
+
 bool GraphicPack2::ContainsTitleId(uint64_t title_id) const
 {
 	const auto it = std::find_if(m_title_ids.begin(), m_title_ids.end(), [title_id](uint64 id) { return id == title_id; });
@@ -650,7 +666,7 @@ bool GraphicPack2::SetActivePreset(std::string_view category, std::string_view n
 
 void GraphicPack2::LoadShaders()
 {
-	fs::path path(m_filename);
+	fs::path path = GetRulesPath();
 	for (auto& it : fs::directory_iterator(path.remove_filename()))
 	{
 		if (!is_regular_file(it))
@@ -676,7 +692,7 @@ void GraphicPack2::LoadShaders()
 			{
 				std::ifstream file(p);
 				if (!file.is_open())
-					throw std::runtime_error(fmt::format("can't open graphic pack file: {}", p.filename().string()).c_str());
+					throw std::runtime_error(fmt::format("can't open graphic pack file: {}", _pathToUtf8(p.filename())));
 
 				file.seekg(0, std::ios::end);
 				m_output_shader_source.reserve(file.tellg());
@@ -689,7 +705,7 @@ void GraphicPack2::LoadShaders()
 			{
 				std::ifstream file(p);
 				if (!file.is_open())
-					throw std::runtime_error(fmt::format("can't open graphic pack file: {}", p.filename().string()).c_str());
+					throw std::runtime_error(fmt::format("can't open graphic pack file: {}", _pathToUtf8(p.filename())));
 
 				file.seekg(0, std::ios::end);
 				m_upscaling_shader_source.reserve(file.tellg());
@@ -702,7 +718,7 @@ void GraphicPack2::LoadShaders()
 			{
 				std::ifstream file(p);
 				if (!file.is_open())
-					throw std::runtime_error(fmt::format("can't open graphic pack file: {}", p.filename().string()).c_str());
+					throw std::runtime_error(fmt::format("can't open graphic pack file: {}", _pathToUtf8(p.filename())));
 
 				file.seekg(0, std::ios::end);
 				m_downscaling_shader_source.reserve(file.tellg());
@@ -805,7 +821,7 @@ void GraphicPack2::AddConstantsForCurrentPreset(ExpressionParser& ep)
 	}
 }
 
-void GraphicPack2::_iterateReplacedFiles(const fs::path& currentPath, std::wstring& internalPath, bool isAOC)
+void GraphicPack2::_iterateReplacedFiles(const fs::path& currentPath, bool isAOC)
 {
 	uint64 currentTitleId = CafeSystem::GetForegroundTitleId();
 	uint64 aocTitleId = (currentTitleId & 0xFFFFFFFFull) | 0x0005000c00000000ull;
@@ -822,7 +838,7 @@ void GraphicPack2::_iterateReplacedFiles(const fs::path& currentPath, std::wstri
 			{
 				virtualMountPath = fs::path("vol/content/") / virtualMountPath;
 			}
-			fscDeviceRedirect_add(virtualMountPath.generic_string(), it.path().generic_string(), m_fs_priority);
+			fscDeviceRedirect_add(virtualMountPath.generic_string(), it.file_size(), it.path().generic_string(), m_fs_priority);
 		}		
 	}
 }
@@ -833,7 +849,7 @@ void GraphicPack2::LoadReplacedFiles()
 		return;
 	m_patchedFilesLoaded = true;
 
-	fs::path gfxPackPath = _utf8ToPath(m_filename);
+	fs::path gfxPackPath = GetRulesPath();
 	gfxPackPath = gfxPackPath.remove_filename();
 
 	// /content/
@@ -843,10 +859,9 @@ void GraphicPack2::LoadReplacedFiles()
 	std::error_code ec;
 	if (fs::exists(contentPath, ec))
 	{
-		std::wstring internalPath(L"/vol/content/");
 		// setup redirections	
 		fscDeviceRedirect_map();
-		_iterateReplacedFiles(contentPath, internalPath, false);
+		_iterateReplacedFiles(contentPath, false);
 	}
 	// /aoc/
 	fs::path aocPath(gfxPackPath);
@@ -857,13 +872,9 @@ void GraphicPack2::LoadReplacedFiles()
 		uint64 aocTitleId = CafeSystem::GetForegroundTitleId();
 		aocTitleId = aocTitleId & 0xFFFFFFFFULL;
 		aocTitleId |= 0x0005000c00000000ULL;
-		wchar_t internalAocPath[128];
-		swprintf(internalAocPath, sizeof(internalAocPath)/sizeof(wchar_t), L"/aoc/%016llx/", aocTitleId);
-
-		std::wstring internalPath(internalAocPath);
 		// setup redirections	
 		fscDeviceRedirect_map();
-		_iterateReplacedFiles(aocPath, internalPath, true);
+		_iterateReplacedFiles(aocPath, true);
 	}
 }
 
@@ -879,21 +890,18 @@ bool GraphicPack2::Activate()
 	if (m_gfx_vendor.has_value())
 	{
 		auto vendor = g_renderer->GetVendor();
-		if (vendor == GfxVendor::IntelLegacy || vendor == GfxVendor::IntelNoLegacy)
-			vendor = GfxVendor::Intel;
-		
 		if (m_gfx_vendor.value() != vendor)
 			return false;
 	}
 
-	FileStream* fs_rules = FileStream::openFile2(_utf8ToPath(m_filename));
+	FileStream* fs_rules = FileStream::openFile2(m_rulesPath);
 	if (!fs_rules)
 		return false;
 	std::vector<uint8> rulesData;
 	fs_rules->extract(rulesData);
 	delete fs_rules;
 
-	IniParser rules({ (char*)rulesData.data(), rulesData.size()}, m_filename);
+	IniParser rules({ (char*)rulesData.data(), rulesData.size()}, GetNormalizedPathString());
 
 	// load rules
 	try
@@ -947,7 +955,7 @@ bool GraphicPack2::Activate()
 					else if (anisotropyValue == 16)
 						rule.overwrite_settings.anistropic_value = 4;
 					else
-						cemuLog_log(LogType::Force, "Invalid value {} for overwriteAnisotropy in graphic pack {}. Only the values 1, 2, 4, 8 or 16 are allowed.", anisotropyValue, m_filename);
+						cemuLog_log(LogType::Force, "Invalid value {} for overwriteAnisotropy in graphic pack {}. Only the values 1, 2, 4, 8 or 16 are allowed.", anisotropyValue, GetNormalizedPathString());
 				}
 				m_texture_rules.emplace_back(rule);
 			}
@@ -960,7 +968,7 @@ bool GraphicPack2::Activate()
 				auto option_upscale = rules.FindOption("upscaleMagFilter");
 				if(option_upscale && boost::iequals(*option_upscale, "NearestNeighbor"))
 					m_output_settings.upscale_filter = LatteTextureView::MagFilter::kNearestNeighbor;
-				auto option_downscale = rules.FindOption("NearestNeighbor");
+				auto option_downscale = rules.FindOption("downscaleMinFilter");
 				if (option_downscale && boost::iequals(*option_downscale, "NearestNeighbor"))
 					m_output_settings.downscale_filter = LatteTextureView::MagFilter::kNearestNeighbor;
 			}
@@ -992,11 +1000,11 @@ bool GraphicPack2::Activate()
 		if (LatteTiming_getCustomVsyncFrequency(globalCustomVsyncFreq))
 		{
 			if (customVsyncFreq != globalCustomVsyncFreq)
-				cemuLog_log(LogType::Force, "rules.txt error: Mismatching vsync frequency {} in graphic pack \'{}\'", customVsyncFreq, GetPath());
+				cemuLog_log(LogType::Force, "rules.txt error: Mismatching vsync frequency {} in graphic pack \'{}\'", customVsyncFreq, GetVirtualPath());
 		}
 		else
 		{
-			cemuLog_log(LogType::Force, "Set vsync frequency to {} (graphic pack {})", customVsyncFreq, GetPath());
+			cemuLog_log(LogType::Force, "Set vsync frequency to {} (graphic pack {})", customVsyncFreq, GetVirtualPath());
 			LatteTiming_setCustomVsyncFrequency(customVsyncFreq);
 		}
 	}

src/Cafe/GraphicPack/GraphicPack2.h

@@ -97,22 +97,23 @@ public:
 	};
 	using PresetPtr = std::shared_ptr<Preset>;
 
-	GraphicPack2(std::string filename, IniParser& rules);
+	GraphicPack2(fs::path rulesPath, IniParser& rules);
 
 	bool IsEnabled() const { return m_enabled; }
 	bool IsActivated() const { return m_activated; }
 	sint32 GetVersion() const { return m_version; }
-	const std::string& GetFilename() const { return m_filename; }
-	const fs::path GetFilename2() const { return fs::path(m_filename); }
+	const fs::path GetRulesPath() const { return m_rulesPath; }
+	std::string GetNormalizedPathString() const;
 	bool RequiresRestart(bool changeEnableState, bool changePreset);
 	bool Reload();
 
 	bool HasName() const { return !m_name.empty();  }
 
-	const std::string& GetName() const { return m_name.empty() ? m_path : m_name; }
-	const std::string& GetPath() const { return m_path; }
+	const std::string& GetName() const { return m_name.empty() ? m_virtualPath : m_name; }
+	const std::string& GetVirtualPath() const { return m_virtualPath; } // returns the path in the gfx tree hierarchy
 	const std::string& GetDescription() const { return m_description; }
 	bool IsDefaultEnabled() const {	return m_default_enabled; }
+	bool AllowRendertargetSizeOptimization() const { return m_allowRendertargetSizeOptimization; }
 
 	void SetEnabled(bool state) { m_enabled = state; }
 
@@ -164,7 +165,7 @@ public:
 	static const std::vector<std::shared_ptr<GraphicPack2>>& GetGraphicPacks() { return s_graphic_packs; }
 	static const std::vector<std::shared_ptr<GraphicPack2>>& GetActiveGraphicPacks() { return s_active_graphic_packs; }
 	static void LoadGraphicPack(fs::path graphicPackPath);
-	static bool LoadGraphicPack(const std::string& filename, class IniParser& rules);
+	static bool LoadGraphicPack(const fs::path& rulesPath, class IniParser& rules);
 	static bool ActivateGraphicPack(const std::shared_ptr<GraphicPack2>& graphic_pack);
 	static bool DeactivateGraphicPack(const std::shared_ptr<GraphicPack2>& graphic_pack);
 	static void ClearGraphicPacks();
@@ -208,15 +209,17 @@ private:
 			parser.TryAddConstant(var.first, (TType)var.second.second);
 	}
 
-	std::string m_filename;
+	fs::path m_rulesPath;
 
 	sint32 m_version;
 	std::string m_name;
-	std::string m_path;
+	std::string m_virtualPath;
 	std::string m_description;
 
 	bool m_default_enabled = false;
 
+	bool m_allowRendertargetSizeOptimization = false; // gfx pack supports framebuffers with non-padded sizes, which is an optional optimization introduced with Cemu 2.0-74
+
 	// filter
 	std::optional<RendererAPI> m_renderer_api;
 	std::optional<GfxVendor> m_gfx_vendor;
@@ -257,7 +260,7 @@ private:
 	CustomShader LoadShader(const fs::path& path, uint64 shader_base_hash, uint64 shader_aux_hash, GP_SHADER_TYPE shader_type) const;
 	void ApplyShaderPresets(std::string& shader_source) const;
 	void LoadReplacedFiles();
-	void _iterateReplacedFiles(const fs::path& currentPath, std::wstring& internalPath, bool isAOC);
+	void _iterateReplacedFiles(const fs::path& currentPath, bool isAOC);
 
 	// ram mappings
 	std::vector<std::pair<MPTR, MPTR>> m_ramMappings;

src/Cafe/GraphicPack/GraphicPack2Patches.cpp

@@ -71,19 +71,8 @@ void PatchErrorHandler::showStageErrorMessageBox()
 // returns true if at least one file was found even if it could not be successfully parsed
 bool GraphicPack2::LoadCemuPatches()
 {
-	// todo - once we have updated to C++20 we can replace these with the new std::string functions
-	auto startsWith = [](const std::wstring& str, const std::wstring& prefix)
-	{
-		return str.size() >= prefix.size() && 0 == str.compare(0, prefix.size(), prefix);
-	};
-
-	auto endsWith = [](const std::wstring& str, const std::wstring& suffix)
-	{
-		return str.size() >= suffix.size() && 0 == str.compare(str.size() - suffix.size(), suffix.size(), suffix);
-	};
-
 	bool foundPatches = false;
-	fs::path path(_utf8ToPath(m_filename));
+	fs::path path(m_rulesPath);
 	path.remove_filename();
 	for (auto& p : fs::directory_iterator(path))
 	{
@@ -129,7 +118,7 @@ void GraphicPack2::LoadPatchFiles()
 	if (LoadCemuPatches())
 		return; // exit if at least one Cemu style patch file was found
 	// fall back to Cemuhook patches.txt to guarantee backward compatibility
-	fs::path path(_utf8ToPath(m_filename));
+	fs::path path(m_rulesPath);
 	path.remove_filename();
 	path.append("patches.txt");
 	FileStream* patchFile = FileStream::openFile2(path);

src/Cafe/GraphicPack/GraphicPack2PatchesParser.cpp

@@ -25,7 +25,7 @@ sint32 GraphicPack2::GetLengthWithoutComment(const char* str, size_t length)
 
 void GraphicPack2::LogPatchesSyntaxError(sint32 lineNumber, std::string_view errorMsg)
 {
-	cemuLog_log(LogType::Force, "Syntax error while parsing patch for graphic pack '{}':", this->GetFilename());
+	cemuLog_log(LogType::Force, "Syntax error while parsing patch for graphic pack '{}':", _pathToUtf8(this->GetRulesPath()));
 	if(lineNumber >= 0)
 		cemuLog_log(LogType::Force, fmt::format("Line {0}: {1}", lineNumber, errorMsg));
 	else

src/Cafe/HW/Espresso/Debugger/DebugSymbolStorage.h

@@ -45,12 +45,17 @@ public:
 
 	static void ClearRange(MPTR address, uint32 length)
 	{
+		if (length == 0)
+			return;
 		s_lock.lock();
-		while (length > 0)
+		for (;;)
 		{
 			auto itr = s_typeStorage.find(address);
 			if (itr != s_typeStorage.end())
 				s_typeStorage.erase(itr);
+			
+			if (length <= 4)
+				break;
 			address += 4;
 			length -= 4;
 		}

src/Cafe/HW/Espresso/Debugger/Debugger.cpp

@@ -8,6 +8,7 @@
 #include "gui/debugger/DebuggerWindow2.h"
 
 #include "Cafe/OS/libs/coreinit/coreinit.h"
+#include "util/helpers/helpers.h"
 
 #if BOOST_OS_WINDOWS
 #include <Windows.h>
@@ -136,11 +137,6 @@ void debugger_createCodeBreakpoint(uint32 address, uint8 bpType)
 	debugger_updateExecutionBreakpoint(address);
 }
 
-void debugger_createExecuteBreakpoint(uint32 address)
-{
-	debugger_createCodeBreakpoint(address, DEBUGGER_BP_T_NORMAL);
-}
-
 namespace coreinit
 {
 	std::vector<std::thread::native_handle_type>& OSGetSchedulerThreads();
@@ -294,8 +290,23 @@ void debugger_toggleExecuteBreakpoint(uint32 address)
 	}
 	else
 	{
-		// create new breakpoint
-		debugger_createExecuteBreakpoint(address);
+		// create new execution breakpoint
+		debugger_createCodeBreakpoint(address, DEBUGGER_BP_T_NORMAL);
+	}
+}
+
+void debugger_toggleLoggingBreakpoint(uint32 address)
+{
+	auto existingBP = debugger_getFirstBP(address, DEBUGGER_BP_T_LOGGING);
+	if (existingBP)
+	{
+		// delete existing breakpoint
+		debugger_deleteBreakpoint(existingBP);
+	}
+	else
+	{
+		// create new logging breakpoint
+		debugger_createCodeBreakpoint(address, DEBUGGER_BP_T_LOGGING);
 	}
 }
 
@@ -447,6 +458,34 @@ bool debugger_hasPatch(uint32 address)
 	return false;
 }
 
+void debugger_removePatch(uint32 address)
+{
+	for (sint32 i = 0; i < debuggerState.patches.size(); i++)
+	{
+		auto& patch = debuggerState.patches[i];
+		if (address < patch->address || address >= (patch->address + patch->length))
+			continue;
+		MPTR startAddress = patch->address;
+		MPTR endAddress = patch->address + patch->length;
+		// remove any breakpoints overlapping with the patch
+		for (auto& bp : debuggerState.breakpoints)
+		{
+			if (bp->address + 4 > startAddress && bp->address < endAddress)
+			{
+				bp->enabled = false;
+				debugger_updateExecutionBreakpoint(bp->address);
+			}
+		}
+		// restore original data
+		memcpy(MEMPTR<void>(startAddress).GetPtr(), patch->origData.data(), patch->length);
+		PPCRecompiler_invalidateRange(startAddress, endAddress);
+		// remove patch
+		delete patch;
+		debuggerState.patches.erase(debuggerState.patches.begin() + i);
+		return;
+	}
+}
+
 void debugger_stepInto(PPCInterpreter_t* hCPU, bool updateDebuggerWindow = true)
 {
 	bool isRecEnabled = ppcRecompilerEnabled;
@@ -501,8 +540,6 @@ void debugger_createPPCStateSnapshot(PPCInterpreter_t* hCPU)
 		debuggerState.debugSession.ppcSnapshot.cr[i] = hCPU->cr[i];
 }
 
-void DebugLogStackTrace(OSThread_t* thread, MPTR sp);
-
 void debugger_enterTW(PPCInterpreter_t* hCPU)
 {
 	// handle logging points
@@ -512,7 +549,48 @@ void debugger_enterTW(PPCInterpreter_t* hCPU)
 	{
 		if (bp->bpType == DEBUGGER_BP_T_LOGGING && bp->enabled)
 		{
-			std::string logName = !bp->comment.empty() ? "Breakpoint '"+boost::nowide::narrow(bp->comment)+"'" : fmt::format("Breakpoint at 0x{:08X} (no comment)", bp->address);
+			std::string comment = !bp->comment.empty() ? boost::nowide::narrow(bp->comment) : fmt::format("Breakpoint at 0x{:08X} (no comment)", bp->address);
+
+			auto replacePlaceholders = [&](const std::string& prefix, const auto& formatFunc)
+			{
+				size_t pos = 0;
+				while ((pos = comment.find(prefix, pos)) != std::string::npos)
+				{
+					size_t endPos = comment.find('}', pos);
+					if (endPos == std::string::npos)
+						break;
+
+					try
+					{
+						if (int regNum = ConvertString<int>(comment.substr(pos + prefix.length(), endPos - pos - prefix.length())); regNum >= 0 && regNum < 32)
+						{
+							std::string replacement = formatFunc(regNum);
+							comment.replace(pos, endPos - pos + 1, replacement);
+							pos += replacement.length();
+						}
+						else
+						{
+							pos = endPos + 1;
+						}
+					}
+					catch (...)
+					{
+						pos = endPos + 1;
+					}
+				}
+			};
+
+			// Replace integer register placeholders {rX}
+			replacePlaceholders("{r", [&](int regNum) {
+				return fmt::format("0x{:08X}", hCPU->gpr[regNum]);
+			});
+
+			// Replace floating point register placeholders {fX}
+			replacePlaceholders("{f", [&](int regNum) {
+				return fmt::format("{}", hCPU->fpr[regNum].fpr);
+			});
+
+			std::string logName = "Breakpoint '" + comment + "'";
 			std::string logContext = fmt::format("Thread: {:08x} LR: 0x{:08x}", MEMPTR<OSThread_t>(coreinit::OSGetCurrentThread()).GetMPTR(), hCPU->spr.LR, cemuLog_advancedPPCLoggingEnabled() ? " Stack Trace:" : "");
 			cemuLog_log(LogType::Force, "[Debugger] {} was executed! {}", logName, logContext);
 			if (cemuLog_advancedPPCLoggingEnabled())
@@ -549,7 +627,7 @@ void debugger_enterTW(PPCInterpreter_t* hCPU)
 	debuggerState.debugSession.stepInto = false;
 	debuggerState.debugSession.stepOver = false;
 	debuggerState.debugSession.run = false;
-	while (true)
+	while (debuggerState.debugSession.isTrapped)
 	{
 		std::this_thread::sleep_for(std::chrono::milliseconds(1));
 		// check for step commands

src/Cafe/HW/Espresso/Debugger/Debugger.h

@@ -100,8 +100,8 @@ extern debuggerState_t debuggerState;
 // new API
 DebuggerBreakpoint* debugger_getFirstBP(uint32 address);
 void debugger_createCodeBreakpoint(uint32 address, uint8 bpType);
-void debugger_createExecuteBreakpoint(uint32 address);
 void debugger_toggleExecuteBreakpoint(uint32 address); // create/remove execute breakpoint
+void debugger_toggleLoggingBreakpoint(uint32 address); // create/remove logging breakpoint
 void debugger_toggleBreakpoint(uint32 address, bool state, DebuggerBreakpoint* bp);
 
 void debugger_createMemoryBreakpoint(uint32 address, bool onRead, bool onWrite);
@@ -114,6 +114,7 @@ void debugger_updateExecutionBreakpoint(uint32 address, bool forceRestore = fals
 
 void debugger_createPatch(uint32 address, std::span<uint8> patchData);
 bool debugger_hasPatch(uint32 address);
+void debugger_removePatch(uint32 address);
 
 void debugger_forceBreak(); // force breakpoint at the next possible instruction
 bool debugger_isTrapped();

src/Cafe/HW/Espresso/Debugger/GDBBreakpoints.cpp

@@ -0,0 +1,304 @@
+#include "GDBBreakpoints.h"
+#include "Debugger.h"
+#include "Cafe/HW/Espresso/Recompiler/PPCRecompiler.h"
+
+#if defined(ARCH_X86_64) && BOOST_OS_LINUX
+#include <sys/ptrace.h>
+#include <sys/wait.h>
+#include <sys/user.h>
+
+DRType _GetDR(pid_t tid, int drIndex)
+{
+	size_t drOffset = offsetof(struct user, u_debugreg) + drIndex * sizeof(user::u_debugreg[0]);
+
+	long v;
+	v = ptrace(PTRACE_PEEKUSER, tid, drOffset, nullptr);
+	if (v == -1)
+		perror("ptrace(PTRACE_PEEKUSER)");
+
+	return (DRType)v;
+}
+
+void _SetDR(pid_t tid, int drIndex, DRType newValue)
+{
+	size_t drOffset = offsetof(struct user, u_debugreg) + drIndex * sizeof(user::u_debugreg[0]);
+
+	long rc = ptrace(PTRACE_POKEUSER, tid, drOffset, newValue);
+	if (rc == -1)
+		perror("ptrace(PTRACE_POKEUSER)");
+}
+
+DRType _ReadDR6()
+{
+	pid_t tid = gettid();
+
+	// linux doesn't let us attach to the current thread / threads in the current thread group
+	// we have to create a child process which then modifies the debug registers and quits
+	pid_t child = fork();
+	if (child == -1)
+	{
+		perror("fork");
+		return 0;
+	}
+
+	if (child == 0)
+	{
+		if (ptrace(PTRACE_ATTACH, tid, nullptr, nullptr))
+		{
+			perror("attach");
+			_exit(0);
+		}
+
+		waitpid(tid, NULL, 0);
+
+		uint64_t dr6 = _GetDR(tid, 6);
+
+		if (ptrace(PTRACE_DETACH, tid, nullptr, nullptr))
+			perror("detach");
+
+		// since the status code only uses the lower 8 bits, we have to discard the rest of DR6
+		// this should be fine though, since the lower 4 bits of DR6 contain all the bp conditions
+		_exit(dr6 & 0xff);
+	}
+
+	// wait for child process
+	int wstatus;
+	waitpid(child, &wstatus, 0);
+
+	return (DRType)WEXITSTATUS(wstatus);
+}
+#endif
+
+GDBServer::ExecutionBreakpoint::ExecutionBreakpoint(MPTR address, BreakpointType type, bool visible, std::string reason)
+	: m_address(address), m_removedAfterInterrupt(false), m_reason(std::move(reason))
+{
+	if (type == BreakpointType::BP_SINGLE)
+	{
+		this->m_pauseThreads = true;
+		this->m_restoreAfterInterrupt = false;
+		this->m_deleteAfterAnyInterrupt = false;
+		this->m_pauseOnNextInterrupt = false;
+		this->m_visible = visible;
+	}
+	else if (type == BreakpointType::BP_PERSISTENT)
+	{
+		this->m_pauseThreads = true;
+		this->m_restoreAfterInterrupt = true;
+		this->m_deleteAfterAnyInterrupt = false;
+		this->m_pauseOnNextInterrupt = false;
+		this->m_visible = visible;
+	}
+	else if (type == BreakpointType::BP_RESTORE_POINT)
+	{
+		this->m_pauseThreads = false;
+		this->m_restoreAfterInterrupt = false;
+		this->m_deleteAfterAnyInterrupt = false;
+		this->m_pauseOnNextInterrupt = false;
+		this->m_visible = false;
+	}
+	else if (type == BreakpointType::BP_STEP_POINT)
+	{
+		this->m_pauseThreads = false;
+		this->m_restoreAfterInterrupt = false;
+		this->m_deleteAfterAnyInterrupt = true;
+		this->m_pauseOnNextInterrupt = true;
+		this->m_visible = false;
+	}
+
+	this->m_origOpCode = memory_readU32(address);
+	memory_writeU32(address, DEBUGGER_BP_T_GDBSTUB_TW);
+	PPCRecompiler_invalidateRange(address, address + 4);
+}
+
+GDBServer::ExecutionBreakpoint::~ExecutionBreakpoint()
+{
+	memory_writeU32(this->m_address, this->m_origOpCode);
+	PPCRecompiler_invalidateRange(this->m_address, this->m_address + 4);
+}
+
+uint32 GDBServer::ExecutionBreakpoint::GetVisibleOpCode() const
+{
+	if (this->m_visible)
+		return memory_readU32(this->m_address);
+	else
+		return this->m_origOpCode;
+}
+
+void GDBServer::ExecutionBreakpoint::RemoveTemporarily()
+{
+	memory_writeU32(this->m_address, this->m_origOpCode);
+	PPCRecompiler_invalidateRange(this->m_address, this->m_address + 4);
+	this->m_restoreAfterInterrupt = true;
+}
+
+void GDBServer::ExecutionBreakpoint::Restore()
+{
+	memory_writeU32(this->m_address, DEBUGGER_BP_T_GDBSTUB_TW);
+	PPCRecompiler_invalidateRange(this->m_address, this->m_address + 4);
+	this->m_restoreAfterInterrupt = false;
+}
+
+namespace coreinit
+{
+#if BOOST_OS_LINUX
+	std::vector<pid_t>& OSGetSchedulerThreadIds();
+#endif
+
+	std::vector<std::thread::native_handle_type>& OSGetSchedulerThreads();
+}
+
+GDBServer::AccessBreakpoint::AccessBreakpoint(MPTR address, AccessPointType type)
+	: m_address(address), m_type(type)
+{
+#if defined(ARCH_X86_64) && BOOST_OS_WINDOWS
+	for (auto& hThreadNH : coreinit::OSGetSchedulerThreads())
+	{
+		HANDLE hThread = (HANDLE)hThreadNH;
+		CONTEXT ctx{};
+		ctx.ContextFlags = CONTEXT_DEBUG_REGISTERS;
+		SuspendThread(hThread);
+		GetThreadContext(hThread, &ctx);
+
+		// use BP 2/3 for gdb stub since cemu's internal debugger uses BP 0/1 already
+		ctx.Dr2 = (DWORD64)memory_getPointerFromVirtualOffset(address);
+		ctx.Dr3 = (DWORD64)memory_getPointerFromVirtualOffset(address);
+		// breakpoint 2
+		SetBits(ctx.Dr7, 4, 1, 1);	// breakpoint #3 enabled: true
+		SetBits(ctx.Dr7, 24, 2, 1); // breakpoint #3 condition: 1 (write)
+		SetBits(ctx.Dr7, 26, 2, 3); // breakpoint #3 length: 3 (4 bytes)
+		// breakpoint 3
+		SetBits(ctx.Dr7, 6, 1, 1);	// breakpoint #4 enabled: true
+		SetBits(ctx.Dr7, 28, 2, 3); // breakpoint #4 condition: 3 (read & write)
+		SetBits(ctx.Dr7, 30, 2, 3); // breakpoint #4 length: 3 (4 bytes)
+
+		SetThreadContext(hThread, &ctx);
+		ResumeThread(hThread);
+	}
+#elif defined(ARCH_X86_64) && BOOST_OS_LINUX
+	// linux doesn't let us attach to threads which are in the same thread group as our current thread
+	// we have to create a child process which then modifies the debug registers and quits
+	pid_t child = fork();
+	if (child == -1)
+	{
+		perror("fork");
+		return;
+	}
+
+	if (child == 0)
+	{
+		for (pid_t tid : coreinit::OSGetSchedulerThreadIds())
+		{
+			long rc = ptrace(PTRACE_ATTACH, tid, nullptr, nullptr);
+			if (rc == -1)
+				perror("ptrace(PTRACE_ATTACH)");
+
+			waitpid(tid, nullptr, 0);
+
+			DRType dr7 = _GetDR(tid, 7);
+			// use BP 2/3 for gdb stub since cemu's internal debugger uses BP 0/1 already
+			DRType dr2 = (uint64)memory_getPointerFromVirtualOffset(address);
+			DRType dr3 = (uint64)memory_getPointerFromVirtualOffset(address);
+			// breakpoint 2
+			SetBits(dr7, 4, 1, 1);  // breakpoint #3 enabled: true
+			SetBits(dr7, 24, 2, 1); // breakpoint #3 condition: 1 (write)
+			SetBits(dr7, 26, 2, 3); // breakpoint #3 length: 3 (4 bytes)
+			// breakpoint 3
+			SetBits(dr7, 6, 1, 1);  // breakpoint #4 enabled: true
+			SetBits(dr7, 28, 2, 3); // breakpoint #4 condition: 3 (read & write)
+			SetBits(dr7, 30, 2, 3); // breakpoint #4 length: 3 (4 bytes)
+
+			_SetDR(tid, 2, dr2);
+			_SetDR(tid, 3, dr3);
+			_SetDR(tid, 7, dr7);
+
+			rc = ptrace(PTRACE_DETACH, tid, nullptr, nullptr);
+			if (rc == -1)
+				perror("ptrace(PTRACE_DETACH)");
+		}
+
+		// exit child process
+		_exit(0);
+	}
+
+	// wait for child process
+	waitpid(child, nullptr, 0);
+#else
+	cemuLog_log(LogType::Force, "Debugger read/write breakpoints are not supported on non-x86 CPUs yet.");
+#endif
+}
+
+GDBServer::AccessBreakpoint::~AccessBreakpoint()
+{
+#if defined(ARCH_X86_64) && BOOST_OS_WINDOWS
+	for (auto& hThreadNH : coreinit::OSGetSchedulerThreads())
+	{
+		HANDLE hThread = (HANDLE)hThreadNH;
+		CONTEXT ctx{};
+		ctx.ContextFlags = CONTEXT_DEBUG_REGISTERS;
+		SuspendThread(hThread);
+		GetThreadContext(hThread, &ctx);
+
+		// reset BP 2/3 to zero
+		ctx.Dr2 = (DWORD64)0;
+		ctx.Dr3 = (DWORD64)0;
+		// breakpoint 2
+		SetBits(ctx.Dr7, 4, 1, 0);
+		SetBits(ctx.Dr7, 24, 2, 0);
+		SetBits(ctx.Dr7, 26, 2, 0);
+		// breakpoint 3
+		SetBits(ctx.Dr7, 6, 1, 0);
+		SetBits(ctx.Dr7, 28, 2, 0);
+		SetBits(ctx.Dr7, 30, 2, 0);
+		SetThreadContext(hThread, &ctx);
+		ResumeThread(hThread);
+	}
+#elif defined(ARCH_X86_64) && BOOST_OS_LINUX
+	// linux doesn't let us attach to threads which are in the same thread group as our current thread
+	// we have to create a child process which then modifies the debug registers and quits
+	pid_t child = fork();
+	if (child == -1)
+	{
+		perror("fork");
+		return;
+	}
+
+	if (child == 0)
+	{
+		for (pid_t tid : coreinit::OSGetSchedulerThreadIds())
+		{
+			long rc = ptrace(PTRACE_ATTACH, tid, nullptr, nullptr);
+			if (rc == -1)
+				perror("ptrace(PTRACE_ATTACH)");
+
+			waitpid(tid, nullptr, 0);
+
+			DRType dr7 = _GetDR(tid, 7);
+			// reset BP 2/3 to zero
+			DRType dr2 = 0;
+			DRType dr3 = 0;
+			// breakpoint 2
+			SetBits(dr7, 4, 1, 0);
+			SetBits(dr7, 24, 2, 0);
+			SetBits(dr7, 26, 2, 0);
+			// breakpoint 3
+			SetBits(dr7, 6, 1, 0);
+			SetBits(dr7, 28, 2, 0);
+			SetBits(dr7, 30, 2, 0);
+
+			_SetDR(tid, 2, dr2);
+			_SetDR(tid, 3, dr3);
+			_SetDR(tid, 7, dr7);
+
+			rc = ptrace(PTRACE_DETACH, tid, nullptr, nullptr);
+			if (rc == -1)
+				perror("ptrace(PTRACE_DETACH)");
+		}
+
+		// exit child process
+		_exit(0);
+	}
+
+	// wait for child process
+	waitpid(child, nullptr, 0);
+#endif
+}

src/Cafe/HW/Espresso/Debugger/GDBBreakpoints.h

@@ -1,33 +1,18 @@
+#pragma once
+#include "GDBStub.h"
 #include <utility>
 
-#if defined(ARCH_X86_64) && BOOST_OS_LINUX && FALSE
-#include <sys/ptrace.h>
-#include <sys/wait.h>
-#include <sys/user.h>
+#if defined(ARCH_X86_64) && BOOST_OS_LINUX
+#include <sys/types.h>
 
 // helpers for accessing debug register
 typedef unsigned long DRType;
 
-DRType _GetDR(pid_t tid, int drIndex)
-{
-	unsigned long v;
-	v = ptrace (PTRACE_PEEKUSER, tid, offsetof (struct user, u_debugreg[drIndex]), 0);
-	return (DRType)v;
-}
-
-void _SetDR(pid_t tid, int drIndex, DRType newValue)
-{
-	unsigned long v = newValue;
-	ptrace (PTRACE_POKEUSER, tid, offsetof (struct user, u_debugreg[drIndex]), v);
-}
-
+DRType _GetDR(pid_t tid, int drIndex);
+void _SetDR(pid_t tid, int drIndex, DRType newValue);
+DRType _ReadDR6();
 #endif
 
-namespace coreinit
-{
-	std::vector<std::thread::native_handle_type>& OSGetSchedulerThreads();
-}
-
 enum class BreakpointType
 {
 	BP_SINGLE,
@@ -38,59 +23,10 @@ enum class BreakpointType
 
 class GDBServer::ExecutionBreakpoint {
 public:
-	ExecutionBreakpoint(MPTR address, BreakpointType type, bool visible, std::string reason)
-		: m_address(address), m_removedAfterInterrupt(false), m_reason(std::move(reason))
-	{
-		if (type == BreakpointType::BP_SINGLE)
-		{
-			this->m_pauseThreads = true;
-			this->m_restoreAfterInterrupt = false;
-			this->m_deleteAfterAnyInterrupt = false;
-			this->m_pauseOnNextInterrupt = false;
-			this->m_visible = visible;
-		}
-		else if (type == BreakpointType::BP_PERSISTENT)
-		{
-			this->m_pauseThreads = true;
-			this->m_restoreAfterInterrupt = true;
-			this->m_deleteAfterAnyInterrupt = false;
-			this->m_pauseOnNextInterrupt = false;
-			this->m_visible = visible;
-		}
-		else if (type == BreakpointType::BP_RESTORE_POINT)
-		{
-			this->m_pauseThreads = false;
-			this->m_restoreAfterInterrupt = false;
-			this->m_deleteAfterAnyInterrupt = false;
-			this->m_pauseOnNextInterrupt = false;
-			this->m_visible = false;
-		}
-		else if (type == BreakpointType::BP_STEP_POINT)
-		{
-			this->m_pauseThreads = false;
-			this->m_restoreAfterInterrupt = false;
-			this->m_deleteAfterAnyInterrupt = true;
-			this->m_pauseOnNextInterrupt = true;
-			this->m_visible = false;
-		}
+	ExecutionBreakpoint(MPTR address, BreakpointType type, bool visible, std::string reason);
+	~ExecutionBreakpoint();
 
-		this->m_origOpCode = memory_readU32(address);
-		memory_writeU32(address, DEBUGGER_BP_T_GDBSTUB_TW);
-		PPCRecompiler_invalidateRange(address, address + 4);
-	};
-	~ExecutionBreakpoint()
-	{
-		memory_writeU32(this->m_address, this->m_origOpCode);
-		PPCRecompiler_invalidateRange(this->m_address, this->m_address + 4);
-	};
-
-	[[nodiscard]] uint32 GetVisibleOpCode() const
-	{
-		if (this->m_visible)
-			return memory_readU32(this->m_address);
-		else
-			return this->m_origOpCode;
-	};
+	[[nodiscard]] uint32 GetVisibleOpCode() const;
 	[[nodiscard]] bool ShouldBreakThreads() const
 	{
 		return this->m_pauseThreads;
@@ -118,18 +54,8 @@ public:
 		return m_reason;
 	};
 
-	void RemoveTemporarily()
-	{
-		memory_writeU32(this->m_address, this->m_origOpCode);
-		PPCRecompiler_invalidateRange(this->m_address, this->m_address + 4);
-		this->m_restoreAfterInterrupt = true;
-	};
-	void Restore()
-	{
-		memory_writeU32(this->m_address, DEBUGGER_BP_T_GDBSTUB_TW);
-		PPCRecompiler_invalidateRange(this->m_address, this->m_address + 4);
-		this->m_restoreAfterInterrupt = false;
-	};
+	void RemoveTemporarily();
+	void Restore();
 	void PauseOnNextInterrupt()
 	{
 		this->m_pauseOnNextInterrupt = true;
@@ -162,115 +88,8 @@ enum class AccessPointType
 
 class GDBServer::AccessBreakpoint {
 public:
-	AccessBreakpoint(MPTR address, AccessPointType type)
-		: m_address(address), m_type(type)
-	{
-#if defined(ARCH_X86_64) && BOOST_OS_WINDOWS
-		for (auto& hThreadNH : coreinit::OSGetSchedulerThreads())
-		{
-			HANDLE hThread = (HANDLE)hThreadNH;
-			CONTEXT ctx{};
-			ctx.ContextFlags = CONTEXT_DEBUG_REGISTERS;
-			SuspendThread(hThread);
-			GetThreadContext(hThread, &ctx);
-
-			// use BP 2/3 for gdb stub since cemu's internal debugger uses BP 0/1 already
-			ctx.Dr2 = (DWORD64)memory_getPointerFromVirtualOffset(address);
-			ctx.Dr3 = (DWORD64)memory_getPointerFromVirtualOffset(address);
-			// breakpoint 2
-			SetBits(ctx.Dr7, 4, 1, 1);	// breakpoint #3 enabled: true
-			SetBits(ctx.Dr7, 24, 2, 1); // breakpoint #3 condition: 1 (write)
-			SetBits(ctx.Dr7, 26, 2, 3); // breakpoint #3 length: 3 (4 bytes)
-			// breakpoint 3
-			SetBits(ctx.Dr7, 6, 1, 1);	// breakpoint #4 enabled: true
-			SetBits(ctx.Dr7, 28, 2, 3); // breakpoint #4 condition: 3 (read & write)
-			SetBits(ctx.Dr7, 30, 2, 3); // breakpoint #4 length: 3 (4 bytes)
-
-			SetThreadContext(hThread, &ctx);
-			ResumeThread(hThread);
-		}
-		// todo: port the following code to all unix platforms, they seem to differ quite a bit
-#elif defined(ARCH_X86_64) && BOOST_OS_LINUX && FALSE
-		for (auto& hThreadNH : coreinit::OSGetSchedulerThreads())
-		{
-			pid_t pid = (pid_t)(uintptr_t)hThreadNH;
-			ptrace(PTRACE_ATTACH, pid, nullptr, nullptr);
-			waitpid(pid, nullptr, 0);
-
-			DRType dr7 = _GetDR(pid, 7);
-			// use BP 2/3 for gdb stub since cemu's internal debugger uses BP 0/1 already
-			DRType dr2 = (uint64)memory_getPointerFromVirtualOffset(address);
-			DRType dr3 = (uint64)memory_getPointerFromVirtualOffset(address);
-			// breakpoint 2
-			SetBits(dr7, 4, 1, 1);  // breakpoint #3 enabled: true
-			SetBits(dr7, 24, 2, 1); // breakpoint #3 condition: 1 (write)
-			SetBits(dr7, 26, 2, 3); // breakpoint #3 length: 3 (4 bytes)
-			// breakpoint 3
-			SetBits(dr7, 6, 1, 1);  // breakpoint #4 enabled: true
-			SetBits(dr7, 28, 2, 3); // breakpoint #4 condition: 3 (read & write)
-			SetBits(dr7, 30, 2, 3); // breakpoint #4 length: 3 (4 bytes)
-
-			_SetDR(pid, 2, dr2);
-			_SetDR(pid, 3, dr3);
-			_SetDR(pid, 7, dr7);			
-			ptrace(PTRACE_DETACH, pid, nullptr, nullptr);
-		}
-#else
-		cemuLog_log(LogType::Force, "Debugger read/write breakpoints are not supported on non-x86 CPUs yet.");
-#endif
-	};
-	~AccessBreakpoint()
-	{
-#if defined(ARCH_X86_64) && BOOST_OS_WINDOWS
-		for (auto& hThreadNH : coreinit::OSGetSchedulerThreads())
-		{
-			HANDLE hThread = (HANDLE)hThreadNH;
-			CONTEXT ctx{};
-			ctx.ContextFlags = CONTEXT_DEBUG_REGISTERS;
-			SuspendThread(hThread);
-			GetThreadContext(hThread, &ctx);
-
-			// reset BP 2/3 to zero
-			ctx.Dr2 = (DWORD64)0;
-			ctx.Dr3 = (DWORD64)0;
-			// breakpoint 2
-			SetBits(ctx.Dr7, 4, 1, 0);
-			SetBits(ctx.Dr7, 24, 2, 0);
-			SetBits(ctx.Dr7, 26, 2, 0);
-			// breakpoint 3
-			SetBits(ctx.Dr7, 6, 1, 0);
-			SetBits(ctx.Dr7, 28, 2, 0);
-			SetBits(ctx.Dr7, 30, 2, 0);
-			SetThreadContext(hThread, &ctx);
-			ResumeThread(hThread);
-		}
-#elif defined(ARCH_X86_64) && BOOST_OS_LINUX && FALSE
-		for (auto& hThreadNH : coreinit::OSGetSchedulerThreads())
-		{
-			pid_t pid = (pid_t)(uintptr_t)hThreadNH;
-			ptrace(PTRACE_ATTACH, pid, nullptr, nullptr);
-			waitpid(pid, nullptr, 0);
-
-			DRType dr7 = _GetDR(pid, 7);
-			// reset BP 2/3 to zero
-			DRType dr2 = 0;
-			DRType dr3 = 0;
-			// breakpoint 2
-			SetBits(dr7, 4, 1, 0);
-			SetBits(dr7, 24, 2, 0);
-			SetBits(dr7, 26, 2, 0);
-			// breakpoint 3
-			SetBits(dr7, 6, 1, 0);
-			SetBits(dr7, 28, 2, 0);
-			SetBits(dr7, 30, 2, 0);
-
-			_SetDR(pid, 2, dr2);
-			_SetDR(pid, 3, dr3);
-			_SetDR(pid, 7, dr7);
-			ptrace(PTRACE_DETACH, pid, nullptr, nullptr);
-		}
-#endif
-	};
+	AccessBreakpoint(MPTR address, AccessPointType type);
+	~AccessBreakpoint();
 
 	MPTR GetAddress() const
 	{

src/Cafe/HW/Espresso/Debugger/GDBStub.cpp

@@ -263,6 +263,14 @@ bool GDBServer::Initialize()
 		return false;
 	}
 
+	int nodelayEnabled = TRUE;
+	if (setsockopt(m_server_socket, IPPROTO_TCP, TCP_NODELAY, (char*)&nodelayEnabled, sizeof(nodelayEnabled)) == SOCKET_ERROR)
+	{
+		closesocket(m_server_socket);
+		m_server_socket = INVALID_SOCKET;
+		return false;
+	}
+
 	memset(&m_server_addr, 0, sizeof(m_server_addr));
 	m_server_addr.sin_family = AF_INET;
 	m_server_addr.sin_addr.s_addr = htonl(INADDR_ANY);
@@ -289,7 +297,7 @@ bool GDBServer::Initialize()
 
 void GDBServer::ThreadFunc()
 {
-	SetThreadName("GDBServer::ThreadFunc");
+	SetThreadName("GDBServer");
 
 	while (!m_stopRequested)
 	{
@@ -356,7 +364,7 @@ void GDBServer::ThreadFunc()
 				}
 				char checkSumStr[2];
 				receiveMessage(checkSumStr, 2);
-				uint32_t checkSum = std::stoi(checkSumStr, nullptr, 16);
+				uint32_t checkSum = std::stoi(std::string(checkSumStr, sizeof(checkSumStr)), nullptr, 16);
 				assert((checkedSum & 0xFF) == checkSum);
 
 				HandleCommand(message);

src/Cafe/HW/Espresso/Interpreter/PPCInterpreterALU.hpp

@@ -212,11 +212,12 @@ static void PPCInterpreter_SUBF(PPCInterpreter_t* hCPU, uint32 opcode)
 
 static void PPCInterpreter_SUBFO(PPCInterpreter_t* hCPU, uint32 opcode)
 {
-	// untested (Don't Starve Giant Edition uses this)
+	// Seen in Don't Starve Giant Edition and Teslagrad
 	// also used by DS Virtual Console (Super Mario 64 DS)
 	PPC_OPC_TEMPL3_XO();
-	hCPU->gpr[rD] = ~hCPU->gpr[rA] + hCPU->gpr[rB] + 1;
-	PPCInterpreter_setXerOV(hCPU, checkAdditionOverflow(~hCPU->gpr[rA], hCPU->gpr[rB], hCPU->gpr[rD]));
+	uint32 result = ~hCPU->gpr[rA] + hCPU->gpr[rB] + 1;
+	PPCInterpreter_setXerOV(hCPU, checkAdditionOverflow(~hCPU->gpr[rA], hCPU->gpr[rB], result));
+	hCPU->gpr[rD] = result;
 	if (opHasRC())
 		ppc_update_cr0(hCPU, hCPU->gpr[rD]);
 	PPCInterpreter_nextInstruction(hCPU);

src/Cafe/HW/Espresso/Interpreter/PPCInterpreterHLE.cpp

@@ -19,7 +19,7 @@ void PPCInterpreter_handleUnsupportedHLECall(PPCInterpreter_t* hCPU)
 
 std::vector<void(*)(PPCInterpreter_t* hCPU)>* sPPCHLETable{};
 
-HLEIDX PPCInterpreter_registerHLECall(HLECALL hleCall)
+HLEIDX PPCInterpreter_registerHLECall(HLECALL hleCall, std::string hleName)
 {
 	if (!sPPCHLETable)
 		sPPCHLETable = new std::vector<void(*)(PPCInterpreter_t* hCPU)>();

src/Cafe/HW/Espresso/Interpreter/PPCInterpreterMain.cpp

@@ -90,7 +90,7 @@ uint8* PPCInterpreterGetStackPointer()
 	return memory_getPointerFromVirtualOffset(PPCInterpreter_getCurrentInstance()->gpr[1]);
 }
 
-uint8* PPCInterpreterGetAndModifyStackPointer(sint32 offset)
+uint8* PPCInterpreter_PushAndReturnStackPointer(sint32 offset)
 {
 	PPCInterpreter_t* hCPU = PPCInterpreter_getCurrentInstance();
 	uint8* result = memory_getPointerFromVirtualOffset(hCPU->gpr[1] - offset);

src/Cafe/HW/Espresso/PPCCallback.h

@@ -5,8 +5,28 @@ struct PPCCoreCallbackData_t
 {
 	sint32 gprCount = 0;
 	sint32 floatCount = 0;
+	sint32 stackCount = 0;
 };
 
+inline void _PPCCoreCallback_writeGPRArg(PPCCoreCallbackData_t& data, PPCInterpreter_t* hCPU, uint32 value)
+{
+	if (data.gprCount < 8)
+	{
+		hCPU->gpr[3 + data.gprCount] = value;
+		data.gprCount++;
+	}
+	else
+	{
+		uint32 stackOffset = 8 + data.stackCount * 4;
+
+		// PPCCore_executeCallbackInternal does -16*4 to save the current stack area
+		stackOffset -= 16 * 4;
+
+		memory_writeU32(hCPU->gpr[1] + stackOffset, value);
+		data.stackCount++;
+	}
+}
+
 // callback functions
 inline uint32 PPCCoreCallback(MPTR function, const PPCCoreCallbackData_t& data)
 {
@@ -16,23 +36,21 @@ inline uint32 PPCCoreCallback(MPTR function, const PPCCoreCallbackData_t& data)
 template <typename T, typename... TArgs>
 uint32 PPCCoreCallback(MPTR function, PPCCoreCallbackData_t& data, T currentArg, TArgs... args)
 {
-	cemu_assert_debug(data.gprCount <= 8);
-	cemu_assert_debug(data.floatCount <= 8);
+	// TODO float arguments on stack
+	cemu_assert_debug(data.floatCount < 8);
+
 	PPCInterpreter_t* hCPU = PPCInterpreter_getCurrentInstance();
 	if constexpr (std::is_pointer_v<T>)
 	{
-		hCPU->gpr[3 + data.gprCount] = MEMPTR(currentArg).GetMPTR();
-		data.gprCount++;
+		_PPCCoreCallback_writeGPRArg(data, hCPU, MEMPTR(currentArg).GetMPTR());
 	}
 	else if constexpr (std::is_base_of_v<MEMPTRBase, std::remove_reference_t<T>>)
 	{
-		hCPU->gpr[3 + data.gprCount] = currentArg.GetMPTR();
-		data.gprCount++;
+		_PPCCoreCallback_writeGPRArg(data, hCPU, currentArg.GetMPTR());
 	}
 	else if constexpr (std::is_reference_v<T>)
 	{
-		hCPU->gpr[3 + data.gprCount] = MEMPTR(&currentArg).GetMPTR();
-		data.gprCount++;
+		_PPCCoreCallback_writeGPRArg(data, hCPU, MEMPTR(&currentArg).GetMPTR());
 	}
 	else if constexpr(std::is_enum_v<T>)
 	{
@@ -53,8 +71,7 @@ uint32 PPCCoreCallback(MPTR function, PPCCoreCallbackData_t& data, T currentArg,
 	}
 	else
 	{
-		hCPU->gpr[3 + data.gprCount] = (uint32)currentArg;
-		data.gprCount++;
+		_PPCCoreCallback_writeGPRArg(data, hCPU, (uint32)currentArg);
 	}
 	
 	return PPCCoreCallback(function, data, args...);

src/Cafe/HW/Espresso/PPCState.h

@@ -213,7 +213,7 @@ void PPCTimer_start();
 // core info and control
 extern uint32 ppcThreadQuantum;
 
-uint8* PPCInterpreterGetAndModifyStackPointer(sint32 offset);
+uint8* PPCInterpreter_PushAndReturnStackPointer(sint32 offset);
 uint8* PPCInterpreterGetStackPointer();
 void PPCInterpreterModifyStackPointer(sint32 offset);
 
@@ -230,7 +230,7 @@ static inline float flushDenormalToZero(float f)
 typedef void(*HLECALL)(PPCInterpreter_t* hCPU);
 
 typedef sint32 HLEIDX;
-HLEIDX PPCInterpreter_registerHLECall(HLECALL hleCall);
+HLEIDX PPCInterpreter_registerHLECall(HLECALL hleCall, std::string hleName);
 HLECALL PPCInterpreter_getHLECall(HLEIDX funcIndex);
 
 // HLE scheduler

src/Cafe/HW/Espresso/Recompiler/PPCRecompiler.cpp

@@ -294,7 +294,7 @@ std::atomic_bool s_recompilerThreadStopSignal{false};
 
 void PPCRecompiler_thread()
 {
-	SetThreadName("PPCRecompiler_thread");
+	SetThreadName("PPCRecompiler");
 	while (true)
 	{
         if(s_recompilerThreadStopSignal)

src/Cafe/HW/Espresso/Recompiler/PPCRecompilerX64.cpp

@@ -114,13 +114,13 @@ void* ATTR_MS_ABI PPCRecompiler_virtualHLE(PPCInterpreter_t* hCPU, uint32 hleFun
 
 void ATTR_MS_ABI PPCRecompiler_getTBL(PPCInterpreter_t* hCPU, uint32 gprIndex)
 {
-	uint64 coreTime = coreinit::coreinit_getTimerTick();
+	uint64 coreTime = coreinit::OSGetSystemTime();
 	hCPU->gpr[gprIndex] = (uint32)(coreTime&0xFFFFFFFF);
 }
 
 void ATTR_MS_ABI PPCRecompiler_getTBU(PPCInterpreter_t* hCPU, uint32 gprIndex)
 {
-	uint64 coreTime = coreinit::coreinit_getTimerTick();
+	uint64 coreTime = coreinit::OSGetSystemTime();
 	hCPU->gpr[gprIndex] = (uint32)((coreTime>>32)&0xFFFFFFFF);
 }
 

src/Cafe/HW/Latte/Core/Latte.h

@@ -25,6 +25,8 @@ struct LatteGPUState_t
 	// context control
 	uint32 contextControl0;
 	uint32 contextControl1;
+	// optional features
+	bool allowFramebufferSizeOptimization{false}; // allow using scissor box as size hint to determine non-padded rendertarget size
 	// draw context
 	struct  
 	{
@@ -50,7 +52,7 @@ struct LatteGPUState_t
 	uint32 gx2InitCalled; // incremented every time GX2Init() is called
 	// OpenGL control
 	uint32 glVendor; // GLVENDOR_*
-	bool alwaysDisplayDRC = false;
+	bool isDRCPrimary = false;
 	// temporary (replace with proper solution later)
 	bool tvBufferUsesSRGB;
 	bool drcBufferUsesSRGB;
@@ -98,7 +100,7 @@ void LatteRenderTarget_copyToBackbuffer(LatteTextureView* textureView, bool isPa
 void LatteRenderTarget_GetCurrentVirtualViewportSize(sint32* viewportWidth, sint32* viewportHeight);
 
 void LatteRenderTarget_itHLESwapScanBuffer();
-void LatteRenderTarget_itHLEClearColorDepthStencil(uint32 clearMask, MPTR colorBufferMPTR, MPTR colorBufferFormat, Latte::E_HWTILEMODE colorBufferTilemode, uint32 colorBufferWidth, uint32 colorBufferHeight, uint32 colorBufferPitch, uint32 colorBufferViewFirstSlice, uint32 colorBufferViewNumSlice, MPTR depthBufferMPTR, MPTR depthBufferFormat, Latte::E_HWTILEMODE depthBufferTileMode, sint32 depthBufferWidth, sint32 depthBufferHeight, sint32 depthBufferPitch, sint32 depthBufferViewFirstSlice, sint32 depthBufferViewNumSlice, float r, float g, float b, float a, float clearDepth, uint32 clearStencil);
+void LatteRenderTarget_itHLEClearColorDepthStencil(uint32 clearMask, MPTR colorBufferMPTR, Latte::E_GX2SURFFMT colorBufferFormat, Latte::E_HWTILEMODE colorBufferTilemode, uint32 colorBufferWidth, uint32 colorBufferHeight, uint32 colorBufferPitch, uint32 colorBufferViewFirstSlice, uint32 colorBufferViewNumSlice, MPTR depthBufferMPTR, Latte::E_GX2SURFFMT depthBufferFormat, Latte::E_HWTILEMODE depthBufferTileMode, sint32 depthBufferWidth, sint32 depthBufferHeight, sint32 depthBufferPitch, sint32 depthBufferViewFirstSlice, sint32 depthBufferViewNumSlice, float r, float g, float b, float a, float clearDepth, uint32 clearStencil);
 void LatteRenderTarget_itHLECopyColorBufferToScanBuffer(MPTR colorBufferPtr, uint32 colorBufferWidth, uint32 colorBufferHeight, uint32 colorBufferSliceIndex, uint32 colorBufferFormat, uint32 colorBufferPitch, Latte::E_HWTILEMODE colorBufferTilemode, uint32 colorBufferSwizzle, uint32 renderTarget);
 
 void LatteRenderTarget_unloadAll();
@@ -115,7 +117,7 @@ void LatteTC_RegisterTexture(LatteTexture* tex);
 void LatteTC_UnregisterTexture(LatteTexture* tex);
 
 uint32 LatteTexture_CalculateTextureDataHash(LatteTexture* hostTexture);
-void LatteTexture_ReloadData(LatteTexture* hostTexture, uint32 textureUnit);
+void LatteTexture_ReloadData(LatteTexture* hostTexture);
 
 bool LatteTC_HasTextureChanged(LatteTexture* hostTexture, bool force = false);
 void LatteTC_ResetTextureChangeTracker(LatteTexture* hostTexture, bool force = false);

src/Cafe/HW/Latte/Core/LatteBufferCache.cpp

@@ -309,7 +309,7 @@ public:
 	{
 		if ((rangeBegin & 0xF))
 		{
-			cemuLog_logDebug(LogType::Force, "writeStreamout(): RangeBegin not aligned to 16. Begin {:08x} End {:08x}", rangeBegin, rangeEnd);
+			cemuLog_logDebugOnce(LogType::Force, "writeStreamout(): RangeBegin not aligned to 16. Begin {:08x} End {:08x}", rangeBegin, rangeEnd);
 			rangeBegin = (rangeBegin + 0xF) & ~0xF;
 			rangeEnd = std::max(rangeBegin, rangeEnd);
 		}

src/Cafe/HW/Latte/Core/LatteCachedFBO.h

@@ -42,7 +42,7 @@ private:
 			if(colorBuffer[i].texture == nullptr)
 				continue;
 			sint32 effectiveWidth, effectiveHeight;
-			LatteTexture_getEffectiveSize(colorBuffer[i].texture->baseTexture, &effectiveWidth, &effectiveHeight, nullptr, colorBuffer[i].texture->firstMip);
+			colorBuffer[i].texture->baseTexture->GetEffectiveSize(effectiveWidth, effectiveHeight, colorBuffer[i].texture->firstMip);
 			if (rtEffectiveSize.x == 0 && rtEffectiveSize.y == 0)
 			{
 				rtEffectiveSize.x = effectiveWidth;
@@ -64,7 +64,7 @@ private:
 		if (depthBuffer.texture)
 		{
 			sint32 effectiveWidth, effectiveHeight;
-			LatteTexture_getEffectiveSize(depthBuffer.texture->baseTexture, &effectiveWidth, &effectiveHeight, nullptr, depthBuffer.texture->firstMip);
+			depthBuffer.texture->baseTexture->GetEffectiveSize(effectiveWidth, effectiveHeight, depthBuffer.texture->firstMip);
 			if (rtEffectiveSize.x == 0 && rtEffectiveSize.y == 0)
 			{
 				rtEffectiveSize.x = effectiveWidth;

src/Cafe/HW/Latte/Core/LatteCommandProcessor.cpp

@@ -141,6 +141,14 @@ private:
 
 void LatteCP_processCommandBuffer(DrawPassContext& drawPassCtx);
 
+// called whenever the GPU runs out of commands or hits a wait condition (semaphores, HLE waits)
+void LatteCP_signalEnterWait()
+{
+	// based on the assumption that games won't do a rugpull and swap out buffer data in the middle of an uninterrupted sequence of drawcalls,
+	// we only flush caches when the GPU goes idle or has to wait for any operation
+	LatteIndices_invalidateAll();
+}
+
 /*
 * Read a U32 from the command buffer
 * If no data is available then wait in a busy loop
@@ -466,6 +474,8 @@ LatteCMDPtr LatteCP_itWaitRegMem(LatteCMDPtr cmd, uint32 nWords)
 	const uint32 GPU7_WAIT_MEM_OP_GREATER = 6;
 	const uint32 GPU7_WAIT_MEM_OP_NEVER = 7;
 
+	LatteCP_signalEnterWait();
+
 	bool stalls = false;
 	if ((word0 & 0x10) != 0)
 	{
@@ -475,18 +485,45 @@ LatteCMDPtr LatteCP_itWaitRegMem(LatteCMDPtr cmd, uint32 nWords)
 		{
 			uint32 fenceMemValue = _swapEndianU32(*fencePtr);
 			fenceMemValue &= fenceMask;
-			if (compareOp == GPU7_WAIT_MEM_OP_GEQUAL)
+			if (compareOp == GPU7_WAIT_MEM_OP_LESS)
 			{
-				// greater or equal
-				if (fenceMemValue >= fenceValue)
+				if (fenceMemValue < fenceValue)
+					break;
+			}
+			else if (compareOp == GPU7_WAIT_MEM_OP_LEQUAL)
+			{
+				if (fenceMemValue <= fenceValue)
 					break;
 			}
 			else if (compareOp == GPU7_WAIT_MEM_OP_EQUAL)
 			{
-				// equal
 				if (fenceMemValue == fenceValue)
 					break;
 			}
+			else if (compareOp == GPU7_WAIT_MEM_OP_NOTEQUAL)
+			{
+				if (fenceMemValue != fenceValue)
+					break;
+			}
+			else if (compareOp == GPU7_WAIT_MEM_OP_GEQUAL)
+			{
+				if (fenceMemValue >= fenceValue)
+					break;
+			}
+			else if (compareOp == GPU7_WAIT_MEM_OP_GREATER)
+			{
+				if (fenceMemValue > fenceValue)
+					break;
+			}
+			else if (compareOp == GPU7_WAIT_MEM_OP_ALWAYS)
+			{
+				break;
+			}
+			else if (compareOp == GPU7_WAIT_MEM_OP_NEVER)
+			{
+				cemuLog_logOnce(LogType::Force, "Latte: WAIT_MEM_OP_NEVER encountered");
+				break;
+			}
 			else
 				assert_dbg();
 			if (!stalls)
@@ -567,6 +604,7 @@ LatteCMDPtr LatteCP_itMemSemaphore(LatteCMDPtr cmd, uint32 nWords)
 	else if(SEM_SIGNAL == 7)
 	{
 		// wait
+		LatteCP_signalEnterWait();
 		size_t loopCount = 0;
 		while (true)
 		{
@@ -761,7 +799,7 @@ LatteCMDPtr LatteCP_itHLESampleTimer(LatteCMDPtr cmd, uint32 nWords)
 {
 	cemu_assert_debug(nWords == 1);
 	MPTR timerMPTR = (MPTR)LatteReadCMD();
-	memory_writeU64(timerMPTR, coreinit::coreinit_getTimerTick());
+	memory_writeU64(timerMPTR, coreinit::OSGetSystemTime());
 	return cmd;
 }
 
@@ -864,8 +902,8 @@ LatteCMDPtr LatteCP_itHLEClearColorDepthStencil(LatteCMDPtr cmd, uint32 nWords)
 	cemu_assert_debug(nWords == 23);
 	uint32 clearMask = LatteReadCMD(); // color (1), depth (2), stencil (4)
 	// color buffer
-	MPTR colorBufferMPTR = LatteReadCMD(); // MPTR for color buffer (physical address)
-	MPTR colorBufferFormat = LatteReadCMD(); // format for color buffer
+	MPTR colorBufferMPTR = LatteReadCMD(); // physical address for color buffer
+	Latte::E_GX2SURFFMT colorBufferFormat = (Latte::E_GX2SURFFMT)LatteReadCMD();
 	Latte::E_HWTILEMODE colorBufferTilemode = (Latte::E_HWTILEMODE)LatteReadCMD();
 	uint32 colorBufferWidth = LatteReadCMD();
 	uint32 colorBufferHeight = LatteReadCMD();
@@ -873,8 +911,8 @@ LatteCMDPtr LatteCP_itHLEClearColorDepthStencil(LatteCMDPtr cmd, uint32 nWords)
 	uint32 colorBufferViewFirstSlice = LatteReadCMD();
 	uint32 colorBufferViewNumSlice = LatteReadCMD();
 	// depth buffer
-	MPTR depthBufferMPTR = LatteReadCMD(); // MPTR for depth buffer (physical address)
-	MPTR depthBufferFormat = LatteReadCMD(); // format for depth buffer
+	MPTR depthBufferMPTR = LatteReadCMD(); // physical address for depth buffer
+	Latte::E_GX2SURFFMT depthBufferFormat = (Latte::E_GX2SURFFMT)LatteReadCMD();
 	Latte::E_HWTILEMODE depthBufferTileMode = (Latte::E_HWTILEMODE)LatteReadCMD();
 	uint32 depthBufferWidth = LatteReadCMD();
 	uint32 depthBufferHeight = LatteReadCMD();
@@ -1278,11 +1316,13 @@ void LatteCP_processCommandBuffer(DrawPassContext& drawPassCtx)
 				}
 				case IT_HLE_TRIGGER_SCANBUFFER_SWAP:
 				{
+					LatteCP_signalEnterWait();
 					LatteCP_itHLESwapScanBuffer(cmdData, nWords);
 					break;
 				}
 				case IT_HLE_WAIT_FOR_FLIP:
 				{
+					LatteCP_signalEnterWait();
 					LatteCP_itHLEWaitForFlip(cmdData, nWords);
 					break;
 				}
@@ -1567,12 +1607,14 @@ void LatteCP_ProcessRingbuffer()
 			}
 			case IT_HLE_TRIGGER_SCANBUFFER_SWAP:
 			{
+				LatteCP_signalEnterWait();
 				LatteCP_itHLESwapScanBuffer(cmd, nWords);
 				timerRecheck += CP_TIMER_RECHECK / 64;
 				break;
 			}
 			case IT_HLE_WAIT_FOR_FLIP:
 			{
+				LatteCP_signalEnterWait();
 				LatteCP_itHLEWaitForFlip(cmd, nWords);
 				timerRecheck += CP_TIMER_RECHECK / 1;
 				break;

src/Cafe/HW/Latte/Core/LatteConst.h

@@ -82,8 +82,6 @@
 #define GLVENDOR_UNKNOWN			(0)
 #define GLVENDOR_AMD				(1)	 // AMD/ATI
 #define GLVENDOR_NVIDIA				(2)
-#define GLVENDOR_INTEL_LEGACY		(3)
-#define GLVENDOR_INTEL_NOLEGACY		(4)
 #define GLVENDOR_INTEL				(5)
 #define GLVENDOR_APPLE				(6)
 

src/Cafe/HW/Latte/Core/LatteIndices.cpp

@@ -1,6 +1,7 @@
 #include "Cafe/HW/Latte/Core/LatteConst.h"
 #include "Cafe/HW/Latte/Renderer/Renderer.h"
 #include "Cafe/HW/Latte/ISA/RegDefines.h"
+#include "Cafe/HW/Latte/Core/LattePerformanceMonitor.h"
 #include "Common/cpu_features.h"
 
 #if defined(ARCH_X86_64) && defined(__GNUC__)
@@ -9,32 +10,53 @@
 
 struct  
 {
+	struct CacheEntry
+	{
+		// input data
 		const void* lastPtr;
 		uint32 lastCount;
 		LattePrimitiveMode lastPrimitiveMode;
 		LatteIndexType lastIndexType;
+		uint64 lastUsed;
 		// output
 		uint32 indexMin;
 		uint32 indexMax;
 		Renderer::INDEX_TYPE renderIndexType;
 		uint32 outputCount;
-	uint32 indexBufferOffset;
-	uint32 indexBufferIndex;
+		Renderer::IndexAllocation indexAllocation;
+	};
+	std::array<CacheEntry, 8> entry;
+	uint64 currentUsageCounter{0};
 }LatteIndexCache{};
 
 void LatteIndices_invalidate(const void* memPtr, uint32 size)
 {
-	if (LatteIndexCache.lastPtr >= memPtr && (LatteIndexCache.lastPtr < ((uint8*)memPtr + size)) )
+	for(auto& entry : LatteIndexCache.entry)
 	{
-		LatteIndexCache.lastPtr = nullptr;
-		LatteIndexCache.lastCount = 0;
+		if (entry.lastPtr >= memPtr && (entry.lastPtr < ((uint8*)memPtr + size)) )
+		{
+			if(entry.lastPtr != nullptr)
+				g_renderer->indexData_releaseIndexMemory(entry.indexAllocation);
+			entry.lastPtr = nullptr;
+			entry.lastCount = 0;
+		}
 	}
 }
 
 void LatteIndices_invalidateAll()
 {
-	LatteIndexCache.lastPtr = nullptr;
-	LatteIndexCache.lastCount = 0;
+	for(auto& entry : LatteIndexCache.entry)
+	{
+		if (entry.lastPtr != nullptr)
+			g_renderer->indexData_releaseIndexMemory(entry.indexAllocation);
+		entry.lastPtr = nullptr;
+		entry.lastCount = 0;
+	}
+}
+
+uint64 LatteIndices_GetNextUsageIndex()
+{
+	return LatteIndexCache.currentUsageCounter++;
 }
 
 uint32 LatteIndices_calculateIndexOutputSize(LattePrimitiveMode primitiveMode, LatteIndexType indexType, uint32 count)
@@ -532,7 +554,7 @@ void LatteIndices_alternativeCalculateIndexMinMax(const void* indexData, LatteIn
 	}
 }
 
-void LatteIndices_decode(const void* indexData, LatteIndexType indexType, uint32 count, LattePrimitiveMode primitiveMode, uint32& indexMin, uint32& indexMax, Renderer::INDEX_TYPE& renderIndexType, uint32& outputCount, uint32& indexBufferOffset, uint32& indexBufferIndex)
+void LatteIndices_decode(const void* indexData, LatteIndexType indexType, uint32 count, LattePrimitiveMode primitiveMode, uint32& indexMin, uint32& indexMax, Renderer::INDEX_TYPE& renderIndexType, uint32& outputCount, Renderer::IndexAllocation& indexAllocation)
 {
 	// what this should do:
 	// [x] use fast SIMD-based index decoding
@@ -542,17 +564,18 @@ void LatteIndices_decode(const void* indexData, LatteIndexType indexType, uint32
 	// [ ] better cache implementation, allow to cache across frames
 
 	// reuse from cache if data didn't change
-	if (LatteIndexCache.lastPtr == indexData &&
-		LatteIndexCache.lastCount == count &&
-		LatteIndexCache.lastPrimitiveMode == primitiveMode &&
-		LatteIndexCache.lastIndexType == indexType)
+	auto cacheEntry = std::find_if(LatteIndexCache.entry.begin(), LatteIndexCache.entry.end(), [indexData, count, primitiveMode, indexType](const auto& entry)
 	{
-		indexMin = LatteIndexCache.indexMin;
-		indexMax = LatteIndexCache.indexMax;
-		renderIndexType = LatteIndexCache.renderIndexType;
-		outputCount = LatteIndexCache.outputCount;
-		indexBufferOffset = LatteIndexCache.indexBufferOffset;
-		indexBufferIndex = LatteIndexCache.indexBufferIndex;
+		return entry.lastPtr == indexData && entry.lastCount == count && entry.lastPrimitiveMode == primitiveMode && entry.lastIndexType == indexType;
+	});
+	if (cacheEntry != LatteIndexCache.entry.end())
+	{
+		indexMin = cacheEntry->indexMin;
+		indexMax = cacheEntry->indexMax;
+		renderIndexType = cacheEntry->renderIndexType;
+		outputCount = cacheEntry->outputCount;
+		indexAllocation = cacheEntry->indexAllocation;
+		cacheEntry->lastUsed = LatteIndices_GetNextUsageIndex();
 		return;
 	}
 
@@ -576,10 +599,12 @@ void LatteIndices_decode(const void* indexData, LatteIndexType indexType, uint32
 		indexMin = 0;
 		indexMax = std::max(count, 1u)-1;
 		renderIndexType = Renderer::INDEX_TYPE::NONE;
+		indexAllocation = {};
 		return; // no indices
 	}
 	// query index buffer from renderer
-	void* indexOutputPtr = g_renderer->indexData_reserveIndexMemory(indexOutputSize, indexBufferOffset, indexBufferIndex);
+	indexAllocation = g_renderer->indexData_reserveIndexMemory(indexOutputSize);
+	void* indexOutputPtr = indexAllocation.mem;
 
 	// decode indices
 	indexMin = std::numeric_limits<uint32>::max();
@@ -704,16 +729,25 @@ void LatteIndices_decode(const void* indexData, LatteIndexType indexType, uint32
 		// recalculate index range but filter out primitive restart index
 		LatteIndices_alternativeCalculateIndexMinMax(indexData, indexType, count, indexMin, indexMax);
 	}
-	g_renderer->indexData_uploadIndexMemory(indexBufferOffset, indexOutputSize);
+	g_renderer->indexData_uploadIndexMemory(indexAllocation);
+	performanceMonitor.cycle[performanceMonitor.cycleIndex].indexDataUploaded += indexOutputSize;
+	// get least recently used cache entry
+	auto lruEntry = std::min_element(LatteIndexCache.entry.begin(), LatteIndexCache.entry.end(), [](const auto& a, const auto& b)
+	{
+		return a.lastUsed < b.lastUsed;
+	});
+	// invalidate previous allocation
+	if(lruEntry->lastPtr != nullptr)
+		g_renderer->indexData_releaseIndexMemory(lruEntry->indexAllocation);
 	// update cache
-	LatteIndexCache.lastPtr = indexData;
-	LatteIndexCache.lastCount = count;
-	LatteIndexCache.lastPrimitiveMode = primitiveMode;
-	LatteIndexCache.lastIndexType = indexType;
-	LatteIndexCache.indexMin = indexMin;
-	LatteIndexCache.indexMax = indexMax;
-	LatteIndexCache.renderIndexType = renderIndexType;
-	LatteIndexCache.outputCount = outputCount;
-	LatteIndexCache.indexBufferOffset = indexBufferOffset;
-	LatteIndexCache.indexBufferIndex = indexBufferIndex;
+	lruEntry->lastPtr = indexData;
+	lruEntry->lastCount = count;
+	lruEntry->lastPrimitiveMode = primitiveMode;
+	lruEntry->lastIndexType = indexType;
+	lruEntry->indexMin = indexMin;
+	lruEntry->indexMax = indexMax;
+	lruEntry->renderIndexType = renderIndexType;
+	lruEntry->outputCount = outputCount;
+	lruEntry->indexAllocation = indexAllocation;
+	lruEntry->lastUsed = LatteIndices_GetNextUsageIndex();
 }

src/Cafe/HW/Latte/Core/LatteIndices.h

@@ -4,4 +4,4 @@
 
 void LatteIndices_invalidate(const void* memPtr, uint32 size);
 void LatteIndices_invalidateAll();
-void LatteIndices_decode(const void* indexData, LatteIndexType indexType, uint32 count, LattePrimitiveMode primitiveMode, uint32& indexMin, uint32& indexMax, Renderer::INDEX_TYPE& renderIndexType, uint32& outputCount, uint32& indexBufferOffset, uint32& indexBufferIndex);
+void LatteIndices_decode(const void* indexData, LatteIndexType indexType, uint32 count, LattePrimitiveMode primitiveMode, uint32& indexMin, uint32& indexMax, Renderer::INDEX_TYPE& renderIndexType, uint32& outputCount, Renderer::IndexAllocation& indexAllocation);

src/Cafe/HW/Latte/Core/LatteOverlay.cpp

@@ -107,7 +107,13 @@ void LatteOverlay_renderOverlay(ImVec2& position, ImVec2& pivot, sint32 directio
 				ImGui::Text("VRAM: %dMB / %dMB", g_state.vramUsage, g_state.vramTotal);
 
 			if (config.overlay.debug)
+			{
+				// general debug info
+				ImGui::Text("--- Debug info ---");
+				ImGui::Text("IndexUploadPerFrame: %dKB", (performanceMonitor.stats.indexDataUploadPerFrame+1023)/1024);
+				// backend specific info
 				g_renderer->AppendOverlayDebugInfo();
+			}
 
 			position.y += (ImGui::GetWindowSize().y + 10.0f) * direction;
 		}

src/Cafe/HW/Latte/Core/LattePerformanceMonitor.cpp

@@ -74,7 +74,6 @@ void LattePerformanceMonitor_frameEnd()
 		uniformBankDataUploadedPerFrame /= 1024ULL;
 		uint32 uniformBankCountUploadedPerFrame = (uint32)(uniformBankUploadedCount / (uint64)elapsedFrames);
 		uint64 indexDataUploadPerFrame = (indexDataUploaded / (uint64)elapsedFrames);
-		indexDataUploadPerFrame /= 1024ULL;
 
 		double fps = (double)elapsedFrames2S * 1000.0 / (double)totalElapsedTimeFPS;
 		uint32 shaderBindsPerFrame = shaderBindCounter / elapsedFrames;
@@ -82,7 +81,7 @@ void LattePerformanceMonitor_frameEnd()
 		uint32 rlps = (uint32)((uint64)recompilerLeaveCount * 1000ULL / (uint64)totalElapsedTime);
 		uint32 tlps = (uint32)((uint64)threadLeaveCount * 1000ULL / (uint64)totalElapsedTime);
 		// set stats
-
+		performanceMonitor.stats.indexDataUploadPerFrame = indexDataUploadPerFrame;
 		// next counter cycle
 		sint32 nextCycleIndex = (performanceMonitor.cycleIndex + 1) % PERFORMANCE_MONITOR_TRACK_CYCLES;
 		performanceMonitor.cycle[nextCycleIndex].drawCallCounter = 0;

src/Cafe/HW/Latte/Core/LattePerformanceMonitor.h

@@ -124,6 +124,7 @@ typedef struct
 		LattePerfStatCounter numGraphicPipelines;
 		LattePerfStatCounter numImages;
 		LattePerfStatCounter numImageViews;
+		LattePerfStatCounter numSamplers;
 		LattePerfStatCounter numRenderPass;
 		LattePerfStatCounter numFramebuffer;
 
@@ -131,6 +132,12 @@ typedef struct
 		LattePerfStatCounter numDrawBarriersPerFrame;
 		LattePerfStatCounter numBeginRenderpassPerFrame;
 	}vk;
+
+	// calculated stats (per frame)
+	struct
+	{
+		uint32 indexDataUploadPerFrame;
+	}stats;
 }performanceMonitor_t;
 
 extern performanceMonitor_t performanceMonitor;

src/Cafe/HW/Latte/Core/LatteRenderTarget.cpp

@@ -11,7 +11,6 @@
 #include "Cafe/HW/Latte/Core/LattePerformanceMonitor.h"
 #include "Cafe/GraphicPack/GraphicPack2.h"
 #include "config/ActiveSettings.h"
-#include "Cafe/HW/Latte/Renderer/Vulkan/VulkanRenderer.h"
 #include "gui/guiWrapper.h"
 #include "Cafe/OS/libs/erreula/erreula.h"
 #include "input/InputManager.h"
@@ -221,40 +220,10 @@ void LatteMRT::BindDepthBufferOnly(LatteTextureView* view)
 	ApplyCurrentState();
 }
 
-/***************************************************/
-
-LatteTextureView* LatteMRT_FindColorBufferForClearing(MPTR colorBufferPtr, sint32 colorBufferWidth, sint32 colorBufferHeight, sint32 colorBufferPitch, uint32 format, sint32 sliceIndex, sint32* searchIndex)
-{
-	LatteTextureView* view = LatteTC_LookupTextureByData(colorBufferPtr, colorBufferWidth, colorBufferHeight, colorBufferPitch, 0, 1, sliceIndex, 1, searchIndex);
-	if (view == nullptr)
-		return nullptr;
-	return view;
-}
-
-LatteTextureView* LatteMRT_CreateColorBuffer(MPTR colorBufferPhysMem, uint32 width, uint32 height, uint32 pitch, Latte::E_GX2SURFFMT format, Latte::E_HWTILEMODE tileMode, uint32 swizzle, uint32 viewSlice)
-{
-	cemu_assert_debug(colorBufferPhysMem != MPTR_NULL);
-	LatteTextureView* textureView;
-	if(viewSlice != 0)
-		textureView = LatteTexture_CreateMapping(colorBufferPhysMem, MPTR_NULL, width, height, viewSlice+1, pitch, tileMode, swizzle, 0, 1, viewSlice, 1, format, Latte::E_DIM::DIM_2D_ARRAY, Latte::E_DIM::DIM_2D, false);
-	else
-		textureView = LatteTexture_CreateMapping(colorBufferPhysMem, MPTR_NULL, width, height, 1, pitch, tileMode, swizzle, 0, 1, viewSlice, 1, format, Latte::E_DIM::DIM_2D, Latte::E_DIM::DIM_2D, false);
-	// unbind texture
-	g_renderer->texture_bindAndActivate(nullptr, 0);
-	return textureView;
-}
-
 LatteTextureView* LatteMRT_CreateDepthBuffer(MPTR depthBufferPhysMem, uint32 width, uint32 height, uint32 pitch, Latte::E_HWTILEMODE tileMode, Latte::E_GX2SURFFMT format, uint32 swizzle, sint32 viewSlice)
 {
-	LatteTextureView* textureView;
-	if(viewSlice == 0)
-		textureView = LatteTexture_CreateMapping(depthBufferPhysMem, MPTR_NULL, width, height, 1, pitch, tileMode, swizzle, 0, 1, viewSlice, 1, format, Latte::E_DIM::DIM_2D, Latte::E_DIM::DIM_2D, true);
-	else
-		textureView = LatteTexture_CreateMapping(depthBufferPhysMem, MPTR_NULL, width, height, viewSlice+1, pitch, tileMode, swizzle, 0, 1, viewSlice, 1, format, Latte::E_DIM::DIM_2D_ARRAY, Latte::E_DIM::DIM_2D, true);
-
+	LatteTextureView* textureView = LatteTexture_CreateMapping(depthBufferPhysMem, MPTR_NULL, width, height, viewSlice+1, pitch, tileMode, swizzle, 0, 1, viewSlice, 1, format, viewSlice > 0 ? Latte::E_DIM::DIM_2D_ARRAY : Latte::E_DIM::DIM_2D, Latte::E_DIM::DIM_2D, true);
 	LatteMRT::SetDepthAndStencilAttachment(textureView, textureView->baseTexture->hasStencil);
-	// unbind texture
-	g_renderer->texture_bindAndActivate(nullptr, 0);
 	return textureView;
 }
 
@@ -297,14 +266,15 @@ LatteTextureView* LatteMRT::GetColorAttachmentTexture(uint32 index, bool createN
 
 	// colorbuffer width/height has to be padded to 8/32 alignment but the actual resolution might be smaller
 	// use the scissor box as a clue to figure out the original resolution if possible
-#if 0
+	if(LatteGPUState.allowFramebufferSizeOptimization)
+	{
 		uint32 scissorBoxWidth = LatteGPUState.contextNew.PA_SC_GENERIC_SCISSOR_BR.get_BR_X();
 		uint32 scissorBoxHeight = LatteGPUState.contextNew.PA_SC_GENERIC_SCISSOR_BR.get_BR_Y();
 		if (((scissorBoxWidth + 7) & ~7) == colorBufferWidth)
 			colorBufferWidth = scissorBoxWidth;
 		if (((colorBufferHeight + 31) & ~31) == colorBufferHeight)
 			colorBufferHeight = scissorBoxHeight;
-#endif
+	}
 
 	// log resolution changes if the above heuristic takes effect
 	// this is useful to find resolutions which need to be updated in gfx pack texture rules
@@ -333,7 +303,7 @@ LatteTextureView* LatteMRT::GetColorAttachmentTexture(uint32 index, bool createN
 	if (colorBufferView == nullptr)
 	{
 		// create color buffer view
-		colorBufferView = LatteTexture_CreateMapping(colorBufferPhysMem, 0, colorBufferWidth, colorBufferHeight, (viewFirstSlice + viewNumSlices), colorBufferPitch, colorBufferTileMode, colorBufferSwizzle>>8, viewFirstMip, 1, viewFirstSlice, viewNumSlices, (Latte::E_GX2SURFFMT)colorBufferFormat, (viewFirstSlice + viewNumSlices)>1? Latte::E_DIM::DIM_2D_ARRAY: Latte::E_DIM::DIM_2D, Latte::E_DIM::DIM_2D, false);
+		colorBufferView = LatteTexture_CreateMapping(colorBufferPhysMem, 0, colorBufferWidth, colorBufferHeight, (viewFirstSlice + viewNumSlices), colorBufferPitch, colorBufferTileMode, colorBufferSwizzle>>8, viewFirstMip, 1, viewFirstSlice, viewNumSlices, (Latte::E_GX2SURFFMT)colorBufferFormat, (viewFirstSlice + viewNumSlices)>1? Latte::E_DIM::DIM_2D_ARRAY: Latte::E_DIM::DIM_2D, Latte::E_DIM::DIM_2D, false, true);
 		LatteGPUState.repeatTextureInitialization = true;
 		checkForTextureChanges = false;
 	}
@@ -369,7 +339,7 @@ uint8 LatteMRT::GetActiveColorBufferMask(const LatteDecompilerShader* pixelShade
 		return 0;
 	cemu_assert_debug(colorControlReg.get_DEGAMMA_ENABLE() == false); // not supported
 	// combine color buffer mask with pixel output mask from pixel shader
-	colorBufferMask &= pixelShader->pixelColorOutputMask;
+	colorBufferMask &= (pixelShader ? pixelShader->pixelColorOutputMask : 0);
 	// combine color buffer mask with color channel mask from mmCB_TARGET_MASK (disable render buffer if all colors are blocked)
 	uint32 channelTargetMask = lcr.CB_TARGET_MASK.get_MASK();
 	for (uint32 i = 0; i < 8; i++)
@@ -520,14 +490,12 @@ bool LatteMRT::UpdateCurrentFBO()
 		sLatteRenderTargetState.rtUpdateList[sLatteRenderTargetState.rtUpdateListCount] = colorAttachmentView;
 		sLatteRenderTargetState.rtUpdateListCount++;
 
-		sint32 colorAttachmentWidth;
-		sint32 colorAttachmentHeight;
-
-		LatteTexture_getSize(colorAttachmentView->baseTexture, &colorAttachmentWidth, &colorAttachmentHeight, nullptr, colorAttachmentView->firstMip);
+		sint32 colorAttachmentWidth, colorAttachmentHeight;
+		colorAttachmentView->baseTexture->GetSize(colorAttachmentWidth, colorAttachmentHeight, colorAttachmentView->firstMip);
 
 		// set effective size
 		sint32 effectiveWidth, effectiveHeight;
-		LatteTexture_getEffectiveSize(colorAttachmentView->baseTexture, &effectiveWidth, &effectiveHeight, nullptr, colorAttachmentView->firstMip);
+		colorAttachmentView->baseTexture->GetEffectiveSize(effectiveWidth, effectiveHeight, colorAttachmentView->firstMip);
 		if (rtEffectiveSize->width == 0 && rtEffectiveSize->height == 0)
 		{
 			rtEffectiveSize->width = effectiveWidth;
@@ -535,9 +503,7 @@ bool LatteMRT::UpdateCurrentFBO()
 		}
 		else if (rtEffectiveSize->width != effectiveWidth && rtEffectiveSize->height != effectiveHeight)
 		{
-#ifdef CEMU_DEBUG_ASSERT
-			cemuLog_log(LogType::Force, "Color buffer size mismatch ({}x{}). Effective size: {}x{} Real size: {}x{} Mismatching texture: {:08x} {}x{} fmt {:04x}", rtEffectiveSize->width, rtEffectiveSize->height, effectiveWidth, effectiveHeight, colorAttachmentView->baseTexture->width, colorAttachmentView->baseTexture->height, colorAttachmentView->baseTexture->physAddress, colorAttachmentView->baseTexture->width, colorAttachmentView->baseTexture->height, (uint32)colorAttachmentView->baseTexture->format);
-#endif
+			cemuLog_logDebug(LogType::Force, "Color buffer size mismatch ({}x{}). Effective size: {}x{} Real size: {}x{} Mismatching texture: {:08x} {}x{} fmt {:04x}", rtEffectiveSize->width, rtEffectiveSize->height, effectiveWidth, effectiveHeight, colorAttachmentView->baseTexture->width, colorAttachmentView->baseTexture->height, colorAttachmentView->baseTexture->physAddress, colorAttachmentView->baseTexture->width, colorAttachmentView->baseTexture->height, (uint32)colorAttachmentView->baseTexture->format);
 		}
 		// currently the first color attachment defines the size of the current render target
 		if (rtRealSize->width == 0 && rtRealSize->height == 0)
@@ -612,15 +578,11 @@ bool LatteMRT::UpdateCurrentFBO()
 
 			if (depthBufferPhysMem != MPTR_NULL)
 			{
-				bool depthBufferWasFound = false;
 				LatteTextureView* depthBufferView = LatteTextureViewLookupCache::lookupSliceEx(depthBufferPhysMem, depthBufferWidth, depthBufferHeight, depthBufferPitch, 0, depthBufferViewFirstSlice, depthBufferFormat, true);
-				if (depthBufferView == nullptr)
+				if (!depthBufferView)
 				{
-					// create depth buffer view
-					if(depthBufferViewFirstSlice == 0)
-						depthBufferView = LatteTexture_CreateMapping(depthBufferPhysMem, 0, depthBufferWidth, depthBufferHeight, 1, depthBufferPitch, depthBufferTileMode, depthBufferSwizzle, 0, 1, 0, 1, depthBufferFormat, Latte::E_DIM::DIM_2D, Latte::E_DIM::DIM_2D, true);
-					else
-						depthBufferView = LatteTexture_CreateMapping(depthBufferPhysMem, 0, depthBufferWidth, depthBufferHeight, depthBufferViewFirstSlice+1, depthBufferPitch, depthBufferTileMode, depthBufferSwizzle, 0, 1, depthBufferViewFirstSlice, 1, depthBufferFormat, Latte::E_DIM::DIM_2D_ARRAY, Latte::E_DIM::DIM_2D, true);
+					// create new depth buffer view and if it doesn't exist then also create the texture
+					depthBufferView = LatteTexture_CreateMapping(depthBufferPhysMem, 0, depthBufferWidth, depthBufferHeight, depthBufferViewFirstSlice+1, depthBufferPitch, depthBufferTileMode, depthBufferSwizzle, 0, 1, depthBufferViewFirstSlice, 1, depthBufferFormat, depthBufferViewFirstSlice > 0 ? Latte::E_DIM::DIM_2D_ARRAY : Latte::E_DIM::DIM_2D, Latte::E_DIM::DIM_2D, true, true);
 					LatteGPUState.repeatTextureInitialization = true;
 				}
 				else
@@ -630,7 +592,7 @@ bool LatteMRT::UpdateCurrentFBO()
 				}
 				// set effective size
 				sint32 effectiveWidth, effectiveHeight;
-				LatteTexture_getEffectiveSize(depthBufferView->baseTexture, &effectiveWidth, &effectiveHeight, NULL);
+				depthBufferView->baseTexture->GetEffectiveSize(effectiveWidth, effectiveHeight, depthBufferView->firstMip);
 				if (rtEffectiveSize->width == 0 && rtEffectiveSize->height == 0)
 				{
 					rtEffectiveSize->width = effectiveWidth;
@@ -780,7 +742,10 @@ void LatteRenderTarget_applyTextureDepthClear(LatteTexture* texture, uint32 slic
 	LatteTexture_MarkDynamicTextureAsChanged(texture->baseView, sliceIndex, mipIndex, eventCounter);
 }
 
-void LatteRenderTarget_itHLEClearColorDepthStencil(uint32 clearMask, MPTR colorBufferMPTR, MPTR colorBufferFormat, Latte::E_HWTILEMODE colorBufferTilemode, uint32 colorBufferWidth, uint32 colorBufferHeight, uint32 colorBufferPitch, uint32 colorBufferViewFirstSlice, uint32 colorBufferViewNumSlice, MPTR depthBufferMPTR, MPTR depthBufferFormat, Latte::E_HWTILEMODE depthBufferTileMode, sint32 depthBufferWidth, sint32 depthBufferHeight, sint32 depthBufferPitch, sint32 depthBufferViewFirstSlice, sint32 depthBufferViewNumSlice, float r, float g, float b, float a, float clearDepth, uint32 clearStencil)
+void LatteRenderTarget_itHLEClearColorDepthStencil(uint32 clearMask,
+												   MPTR colorBufferMPTR, Latte::E_GX2SURFFMT colorBufferFormat, Latte::E_HWTILEMODE colorBufferTilemode, uint32 colorBufferWidth, uint32 colorBufferHeight, uint32 colorBufferPitch, uint32 colorBufferViewFirstSlice, uint32 colorBufferViewNumSlice,
+												   MPTR depthBufferMPTR, Latte::E_GX2SURFFMT depthBufferFormat, Latte::E_HWTILEMODE depthBufferTileMode, sint32 depthBufferWidth, sint32 depthBufferHeight, sint32 depthBufferPitch, sint32 depthBufferViewFirstSlice, sint32 depthBufferViewNumSlice,
+												   float r, float g, float b, float a, float clearDepth, uint32 clearStencil)
 {
 	uint32 depthBufferMipIndex = 0; // todo
 	uint32 colorBufferMipIndex = 0; // todo
@@ -815,13 +780,11 @@ void LatteRenderTarget_itHLEClearColorDepthStencil(uint32 clearMask, MPTR colorB
 		bool targetFound = false;
 		while (true)
 		{
-			LatteTextureView* colorView = LatteMRT_FindColorBufferForClearing(colorBufferMPTR, colorBufferWidth, colorBufferHeight, colorBufferPitch, colorBufferFormat, colorBufferViewFirstSlice, &searchIndex);
+			LatteTextureView* colorView = LatteTC_LookupTextureByData(colorBufferMPTR, colorBufferWidth, colorBufferHeight, colorBufferPitch, 0, 1, colorBufferViewFirstSlice, 1, &searchIndex);
 			if (!colorView)
 				break;
-			if (Latte::GetFormatBits((Latte::E_GX2SURFFMT)colorBufferFormat) != Latte::GetFormatBits(colorView->baseTexture->format))
-			{
+			if (Latte::GetFormatBits(colorBufferFormat) != Latte::GetFormatBits(colorView->baseTexture->format))
 				continue;
-			}
 
 			if (colorView->baseTexture->pitch == colorBufferPitch && colorView->baseTexture->height == colorBufferHeight)
 				targetFound = true;
@@ -833,7 +796,7 @@ void LatteRenderTarget_itHLEClearColorDepthStencil(uint32 clearMask, MPTR colorB
 		{
 			// create new texture with matching format
 			cemu_assert_debug(colorBufferViewNumSlice <= 1);
-			LatteTextureView* newColorView = LatteMRT_CreateColorBuffer(colorBufferMPTR, colorBufferWidth, colorBufferHeight, colorBufferPitch, (Latte::E_GX2SURFFMT)colorBufferFormat, colorBufferTilemode, colorBufferSwizzle, colorBufferViewFirstSlice);
+			LatteTextureView* newColorView = LatteTexture_CreateMapping(colorBufferMPTR, MPTR_NULL, colorBufferWidth, colorBufferHeight, colorBufferViewFirstSlice+1, colorBufferPitch, colorBufferTilemode, colorBufferSwizzle, 0, 1, colorBufferViewFirstSlice, 1, colorBufferFormat, colorBufferViewFirstSlice > 0 ? Latte::E_DIM::DIM_2D_ARRAY : Latte::E_DIM::DIM_2D, Latte::E_DIM::DIM_2D, false);
 			LatteRenderTarget_applyTextureColorClear(newColorView->baseTexture, colorBufferViewFirstSlice, colorBufferMipIndex, r, g, b, a, eventCounter);
 		}
 	}
@@ -911,20 +874,13 @@ void LatteRenderTarget_getScreenImageArea(sint32* x, sint32* y, sint32* width, s
 
 void LatteRenderTarget_copyToBackbuffer(LatteTextureView* textureView, bool isPadView)
 {
-	if (g_renderer->GetType() == RendererAPI::Vulkan)
-	{
-		((VulkanRenderer*)g_renderer.get())->PreparePresentationFrame(!isPadView);
-	}
-
 	// make sure texture is updated to latest data in cache
 	LatteTexture_UpdateDataToLatest(textureView->baseTexture);
 	// mark source texture as still in use
 	LatteTC_MarkTextureStillInUse(textureView->baseTexture);
 
-	sint32 effectiveWidth;
-	sint32 effectiveHeight;
-	sint32 effectiveDepth;
-	LatteTexture_getEffectiveSize(textureView->baseTexture, &effectiveWidth, &effectiveHeight, &effectiveDepth, 0);
+	sint32 effectiveWidth, effectiveHeight;
+	textureView->baseTexture->GetEffectiveSize(effectiveWidth, effectiveHeight, 0);
 	_currentOutputImageWidth = effectiveWidth;
 	_currentOutputImageHeight = effectiveHeight;
 	
@@ -977,13 +933,6 @@ void LatteRenderTarget_copyToBackbuffer(LatteTextureView* textureView, bool isPa
 	{
 		sint32 scaling_filter = downscaling ? GetConfig().downscale_filter : GetConfig().upscale_filter;
 
-		if (g_renderer->GetType() == RendererAPI::Vulkan)
-		{
-			// force linear or nearest neighbor filter
-			if(scaling_filter != kLinearFilter && scaling_filter != kNearestNeighborFilter)
-				scaling_filter = kLinearFilter;
-		}
-
 		if (scaling_filter == kLinearFilter)
 		{
 			if(renderUpsideDown)
@@ -1000,7 +949,7 @@ void LatteRenderTarget_copyToBackbuffer(LatteTextureView* textureView, bool isPa
 			else
 				shader = RendererOutputShader::s_bicubic_shader;
 
-			filter = LatteTextureView::MagFilter::kNearestNeighbor;
+			filter = LatteTextureView::MagFilter::kLinear;
 		}
 		else if (scaling_filter == kBicubicHermiteFilter)
 		{
@@ -1032,8 +981,6 @@ void LatteRenderTarget_copyToBackbuffer(LatteTextureView* textureView, bool isPa
 	g_renderer->ImguiEnd();
 }
 
-bool ctrlTabHotkeyPressed = false;
-
 void LatteRenderTarget_itHLECopyColorBufferToScanBuffer(MPTR colorBufferPtr, uint32 colorBufferWidth, uint32 colorBufferHeight, uint32 colorBufferSliceIndex, uint32 colorBufferFormat, uint32 colorBufferPitch, Latte::E_HWTILEMODE colorBufferTilemode, uint32 colorBufferSwizzle, uint32 renderTarget)
 {
 	cemu_assert_debug(colorBufferSliceIndex == 0); // todo - support for non-zero slice
@@ -1043,38 +990,31 @@ void LatteRenderTarget_itHLECopyColorBufferToScanBuffer(MPTR colorBufferPtr, uin
 		return;
 	}
 
+	auto getVPADScreenActive = [](size_t n) -> std::pair<bool, bool> {
+		auto controller = InputManager::instance().get_vpad_controller(n);
+		if (!controller)
+			return {false,false};
+		auto pressed = controller->is_screen_active();
+		auto toggle = controller->is_screen_active_toggle();
+		return {pressed && !toggle, pressed && toggle};
+	};
+
 	const bool tabPressed = gui_isKeyDown(PlatformKeyCodes::TAB);
 	const bool ctrlPressed = gui_isKeyDown(PlatformKeyCodes::LCONTROL);
+	const auto [vpad0Active, vpad0Toggle] = getVPADScreenActive(0);
+	const auto [vpad1Active, vpad1Toggle] = getVPADScreenActive(1);
 
-	bool showDRC = swkbd_hasKeyboardInputHook() == false && tabPressed;
-	bool& alwaysDisplayDRC = LatteGPUState.alwaysDisplayDRC;
+	const bool altScreenRequested = (!ctrlPressed && tabPressed) || vpad0Active || vpad1Active;
+	const bool togglePressed = (ctrlPressed && tabPressed) || vpad0Toggle || vpad1Toggle;
+	static bool togglePressedLast = false;
 
-	if (ctrlPressed && tabPressed)
-	{
-		if (ctrlTabHotkeyPressed == false)
-		{
-			alwaysDisplayDRC = !alwaysDisplayDRC;
-			ctrlTabHotkeyPressed = true;
-		}
-	}
-	else
-		ctrlTabHotkeyPressed = false;
+	bool& isDRCPrimary = LatteGPUState.isDRCPrimary;
 
-	if (alwaysDisplayDRC)
-		showDRC = !tabPressed;
+	if(togglePressed && !togglePressedLast)
+		isDRCPrimary = !isDRCPrimary;
+	togglePressedLast = togglePressed;
 
-	if (!showDRC)
-	{
-		auto controller = InputManager::instance().get_vpad_controller(0);
-		if (controller && controller->is_screen_active())
-			showDRC = true;
-		if (!showDRC)
-		{
-			controller = InputManager::instance().get_vpad_controller(1);
-			if (controller && controller->is_screen_active())
-				showDRC = true;	
-		}
-	}
+	bool showDRC = swkbd_hasKeyboardInputHook() == false && (isDRCPrimary ^ altScreenRequested);
 
 	if ((renderTarget & RENDER_TARGET_DRC) && g_renderer->IsPadWindowActive())
 		LatteRenderTarget_copyToBackbuffer(texView, true);

src/Cafe/HW/Latte/Core/LatteShader.cpp

@@ -451,9 +451,8 @@ void LatteShader_DumpShader(uint64 baseHash, uint64 auxHash, LatteDecompilerShad
 		suffix = "gs";
 	else if (shader->shaderType == LatteConst::ShaderType::Pixel)
 		suffix = "ps";
-	fs::path dumpPath = "dump/shaders";
-	dumpPath /= fmt::format("{:016x}_{:016x}_{}.txt", baseHash, auxHash, suffix);
-	FileStream* fs = FileStream::createFile2(dumpPath);
+
+	FileStream* fs = FileStream::createFile2(ActiveSettings::GetUserDataPath("dump/shaders/{:016x}_{:016x}_{}.txt", baseHash, auxHash, suffix));
 	if (fs)
 	{
 		if (shader->strBuf_shaderSource)
@@ -479,9 +478,8 @@ void LatteShader_DumpRawShader(uint64 baseHash, uint64 auxHash, uint32 type, uin
 		suffix = "copy";
 	else if (type == SHADER_DUMP_TYPE_COMPUTE)
 		suffix = "compute";
-	fs::path dumpPath = "dump/shaders";
-	dumpPath /= fmt::format("{:016x}_{:016x}_{}.bin", baseHash, auxHash, suffix);
-	FileStream* fs = FileStream::createFile2(dumpPath);
+
+	FileStream* fs = FileStream::createFile2(ActiveSettings::GetUserDataPath("dump/shaders/{:016x}_{:016x}_{}.bin", baseHash, auxHash, suffix));
 	if (fs)
 	{
 		fs->writeData(programCode, programLen);
@@ -524,7 +522,7 @@ void LatteSHRC_UpdateGSBaseHash(uint8* geometryShaderPtr, uint32 geometryShaderS
 	// update hash from geometry shader data
 	uint64 gsHash1 = 0;
 	uint64 gsHash2 = 0;
-	_calculateShaderProgramHash((uint32*)geometryShaderPtr, geometryShaderSize, &hashCacheVS, &gsHash1, &gsHash2);
+	_calculateShaderProgramHash((uint32*)geometryShaderPtr, geometryShaderSize, &hashCacheGS, &gsHash1, &gsHash2);
 	// get geometry shader
 	uint64 gsHash = gsHash1 + gsHash2;
 	gsHash += (uint64)_activeVertexShader->ringParameterCount;
@@ -652,7 +650,7 @@ LatteDecompilerShader* LatteShader_CreateShaderFromDecompilerOutput(LatteDecompi
 	}
 	else
 	{
-		shader->uniform.count_uniformRegister = decompilerOutput.uniformOffsetsVK.count_uniformRegister;
+		shader->uniform.count_uniformRegister = decompilerOutput.uniformOffsetsGL.count_uniformRegister;
 	}
 	// calculate aux hash
 	if (calculateAuxHash)
@@ -838,7 +836,6 @@ LatteDecompilerShader* LatteShader_CompileSeparablePixelShader(uint64 baseHash,
 void LatteSHRC_UpdateVertexShader(uint8* vertexShaderPtr, uint32 vertexShaderSize, bool usesGeometryShader)
 {
 	// todo - should include VTX_SEMANTIC table in state
-
 	LatteSHRC_UpdateVSBaseHash(vertexShaderPtr, vertexShaderSize, usesGeometryShader);
 	uint64 vsAuxHash = 0;
 	auto itBaseShader = sVertexShaders.find(_shaderBaseHash_vs);
@@ -855,15 +852,13 @@ void LatteSHRC_UpdateVertexShader(uint8* vertexShaderPtr, uint32 vertexShaderSiz
 		LatteGPUState.activeShaderHasError = true;
 		return;
 	}
-	g_renderer->shader_bind(vertexShader->shader);
 	_activeVertexShader = vertexShader;
 }
 
 void LatteSHRC_UpdateGeometryShader(bool usesGeometryShader, uint8* geometryShaderPtr, uint32 geometryShaderSize, uint8* geometryCopyShader, uint32 geometryCopyShaderSize)
 {
-	if (usesGeometryShader == false || _activeVertexShader == nullptr)
+	if (!usesGeometryShader || !_activeVertexShader)
 	{
-		g_renderer->shader_unbind(RendererShader::ShaderType::kGeometry);
 		_shaderBaseHash_gs = 0;
 		_activeGeometryShader = nullptr;
 		return;
@@ -887,21 +882,11 @@ void LatteSHRC_UpdateGeometryShader(bool usesGeometryShader, uint8* geometryShad
 		LatteGPUState.activeShaderHasError = true;
 		return;
 	}
-	g_renderer->shader_bind(geometryShader->shader);
 	_activeGeometryShader = geometryShader;
 }
 
 void LatteSHRC_UpdatePixelShader(uint8* pixelShaderPtr, uint32 pixelShaderSize, bool usesGeometryShader)
 {
-	if (LatteGPUState.contextRegister[mmVGT_STRMOUT_EN] != 0 && g_renderer->GetType() == RendererAPI::OpenGL)
-	{
-		if (_activePixelShader)
-		{
-			g_renderer->shader_unbind(RendererShader::ShaderType::kFragment);
-			_activePixelShader = nullptr;
-		}
-		return;
-	}
 	LatteSHRC_UpdatePSBaseHash(pixelShaderPtr, pixelShaderSize, usesGeometryShader);
 	uint64 psAuxHash = 0;
 	auto itBaseShader = sPixelShaders.find(_shaderBaseHash_ps);
@@ -918,7 +903,6 @@ void LatteSHRC_UpdatePixelShader(uint8* pixelShaderPtr, uint32 pixelShaderSize,
 		LatteGPUState.activeShaderHasError = true;
 		return;
 	}
-	g_renderer->shader_bind(pixelShader->shader);
 	_activePixelShader = pixelShader;
 }
 

src/Cafe/HW/Latte/Core/LatteShaderAssembly.h

@@ -12,7 +12,7 @@
 #define GPU7_CF_INST_VTX				(0x02) // used only in GS copy program?
 #define GPU7_CF_INST_LOOP_END			(0x05)
 #define GPU7_CF_INST_LOOP_START_DX10	(0x06)
-#define GPU7_CF_INST_LOOP_START_NO_AL	(0x07) // (Seen in Project Zero)
+#define GPU7_CF_INST_LOOP_START_NO_AL	(0x07) // (Seen in Project Zero, Injustice: Gods Among Us)
 
 #define GPU7_CF_INST_LOOP_BREAK			(0x09)
 #define GPU7_CF_INST_JUMP				(0x0A)

src/Cafe/HW/Latte/Core/LatteShaderCache.cpp

@@ -25,6 +25,9 @@
 #include "util/helpers/Serializer.h"
 
 #include <wx/msgdlg.h>
+#include <audio/IAudioAPI.h>
+#include <util/bootSound/BootSoundReader.h>
+#include <thread>
 
 #if BOOST_OS_WINDOWS
 #include <psapi.h>
@@ -155,6 +158,118 @@ bool LoadTGAFile(const std::vector<uint8>& buffer, TGAFILE *tgaFile)
 	return true;
 }
 
+class BootSoundPlayer
+{
+  public:
+	BootSoundPlayer() = default;
+	~BootSoundPlayer()
+	{
+		m_stopRequested = true;
+	}
+
+	void StartSound()
+	{
+		if (!m_bootSndPlayThread.joinable())
+		{
+			m_fadeOutRequested = false;
+			m_stopRequested = false;
+			m_bootSndPlayThread = std::thread{[this]() {
+				StreamBootSound();
+			}};
+		}
+	}
+
+	void FadeOutSound()
+	{
+		m_fadeOutRequested = true;
+	}
+
+	void ApplyFadeOutEffect(std::span<sint16> samples, uint64& fadeOutSample, uint64 fadeOutDuration)
+	{
+		for (size_t i = 0; i < samples.size(); i += 2)
+		{
+			const float decibel = (float)fadeOutSample / fadeOutDuration * -60.0f;
+			const float volumeFactor = pow(10, decibel / 20);
+			samples[i] *= volumeFactor;
+			samples[i + 1] *= volumeFactor;
+			fadeOutSample++;
+		}
+	}
+
+	void StreamBootSound()
+	{
+		SetThreadName("bootsnd");
+		constexpr sint32 sampleRate = 48'000;
+		constexpr sint32 bitsPerSample = 16;
+		constexpr sint32 samplesPerBlock = sampleRate / 10; // block is 1/10th of a second
+		constexpr sint32 nChannels = 2;
+		static_assert(bitsPerSample % 8 == 0, "bits per sample is not a multiple of 8");
+
+		AudioAPIPtr bootSndAudioDev;
+
+		try
+		{
+			bootSndAudioDev = IAudioAPI::CreateDeviceFromConfig(true, sampleRate, nChannels, samplesPerBlock, bitsPerSample);
+			if(!bootSndAudioDev)
+				return;
+		}
+		catch (const std::runtime_error& ex)
+		{
+			cemuLog_log(LogType::Force, "Failed to initialise audio device for bootup sound");
+			return;
+		}
+		bootSndAudioDev->SetAudioDelayOverride(4);
+		bootSndAudioDev->Play();
+
+		std::string sndPath = fmt::format("{}/meta/{}", CafeSystem::GetMlcStoragePath(CafeSystem::GetForegroundTitleId()), "bootSound.btsnd");
+		sint32 fscStatus = FSC_STATUS_UNDEFINED;
+
+		if(!fsc_doesFileExist(sndPath.c_str()))
+			return;
+
+		FSCVirtualFile* bootSndFileHandle = fsc_open(sndPath.c_str(), FSC_ACCESS_FLAG::OPEN_FILE | FSC_ACCESS_FLAG::READ_PERMISSION, &fscStatus);
+		if(!bootSndFileHandle)
+		{
+			cemuLog_log(LogType::Force, "failed to open bootSound.btsnd");
+			return;
+		}
+
+		constexpr sint32 audioBlockSize = samplesPerBlock * (bitsPerSample/8) * nChannels;
+		BootSoundReader bootSndFileReader(bootSndFileHandle, audioBlockSize);
+
+		uint64 fadeOutSample = 0; // track how far into the fadeout
+		constexpr uint64 fadeOutDuration = sampleRate * 2; // fadeout should last 2 seconds
+		while(fadeOutSample < fadeOutDuration && !m_stopRequested)
+		{
+			while (bootSndAudioDev->NeedAdditionalBlocks())
+			{
+				sint16* data = bootSndFileReader.getSamples();
+				if(data == nullptr)
+				{
+					// break outer loop
+					m_stopRequested = true;
+					break;
+				}
+				if(m_fadeOutRequested)
+					ApplyFadeOutEffect({data, samplesPerBlock * nChannels}, fadeOutSample, fadeOutDuration);
+
+				bootSndAudioDev->FeedBlock(data);
+			}
+			// sleep for the duration of a single block
+			std::this_thread::sleep_for(std::chrono::milliseconds(samplesPerBlock / (sampleRate/ 1'000)));
+		}
+
+		if(bootSndFileHandle)
+			fsc_close(bootSndFileHandle);
+	}
+
+  private:
+	std::thread m_bootSndPlayThread;
+	std::atomic_bool m_fadeOutRequested = false;
+	std::atomic_bool m_stopRequested = false;
+};
+static BootSoundPlayer g_bootSndPlayer;
+
 void LatteShaderCache_finish()
 {
 	if (g_renderer->GetType() == RendererAPI::Vulkan)
@@ -299,6 +414,9 @@ void LatteShaderCache_Load()
 	loadBackgroundTexture(true, g_shaderCacheLoaderState.textureTVId);
 	loadBackgroundTexture(false, g_shaderCacheLoaderState.textureDRCId);
 
+	if(GetConfig().play_boot_sound)
+		g_bootSndPlayer.StartSound();
+
 	sint32 numLoadedShaders = 0;
 	uint32 loadIndex = 0;
 
@@ -365,6 +483,11 @@ void LatteShaderCache_Load()
 		g_renderer->DeleteTexture(g_shaderCacheLoaderState.textureTVId);
 	if (g_shaderCacheLoaderState.textureDRCId)
 		g_renderer->DeleteTexture(g_shaderCacheLoaderState.textureDRCId);
+
+	g_bootSndPlayer.FadeOutSound();
+
+	if(Latte_GetStopSignal())
+		LatteThread_Exit();
 }
 
 void LatteShaderCache_ShowProgress(const std::function <bool(void)>& loadUpdateFunc, bool isPipelines)
@@ -505,8 +628,6 @@ void LatteShaderCache_LoadVulkanPipelineCache(uint64 cacheTitleId)
 	g_shaderCacheLoaderState.loadedPipelines = 0;
 	LatteShaderCache_ShowProgress(LatteShaderCache_updatePipelineLoadingProgress, true);
 	pipelineCache.EndLoading();
-    if(Latte_GetStopSignal())
-        LatteThread_Exit();
 }
 
 bool LatteShaderCache_updatePipelineLoadingProgress()

src/Cafe/HW/Latte/Core/LatteSurfaceCopy.cpp

@@ -37,7 +37,7 @@ void LatteSurfaceCopy_copySurfaceNew(MPTR srcPhysAddr, MPTR srcMipAddr, uint32 s
 	if (!destinationTexture)
 	{
 		LatteTexture* renderTargetConf = nullptr;
-		destinationView = LatteTexture_CreateMapping(dstPhysAddr, dstMipAddr, dstWidth, dstHeight, dstDepth, dstPitch, dstTilemode, dstSwizzle, dstLevel, 1, dstSlice, 1, dstSurfaceFormat, dstDim, Latte::E_DIM::DIM_2D, false);
+		destinationView = LatteTexture_CreateMapping(dstPhysAddr, dstMipAddr, dstWidth, dstHeight, dstDepth, dstPitch, dstTilemode, dstSwizzle, dstLevel, 1, dstSlice, 1, dstSurfaceFormat, dstDim, Latte::IsMSAA(dstDim) ? Latte::E_DIM::DIM_2D_MSAA : Latte::E_DIM::DIM_2D, false);
 		destinationTexture = destinationView->baseTexture;
 	}
 	// copy texture
@@ -46,9 +46,7 @@ void LatteSurfaceCopy_copySurfaceNew(MPTR srcPhysAddr, MPTR srcMipAddr, uint32 s
 		// mark source and destination texture as still in use
 		LatteTC_MarkTextureStillInUse(destinationTexture);
 		LatteTC_MarkTextureStillInUse(sourceTexture);
-		// determine GL slice indices
 		sint32 realSrcSlice = srcSlice;
-		sint32 realDstSlice = dstSlice;
 		if (LatteTexture_doesEffectiveRescaleRatioMatch(sourceTexture, sourceView->firstMip, destinationTexture, destinationView->firstMip))
 		{
 			// adjust copy size
@@ -62,31 +60,13 @@ void LatteSurfaceCopy_copySurfaceNew(MPTR srcPhysAddr, MPTR srcMipAddr, uint32 s
 			LatteTexture_scaleToEffectiveSize(sourceTexture, &effectiveCopyWidth, &effectiveCopyHeight, 0);
 			// copy slice
 			if (sourceView->baseTexture->isDepth != destinationView->baseTexture->isDepth)
-			{
 				g_renderer->surfaceCopy_copySurfaceWithFormatConversion(sourceTexture, sourceView->firstMip, sourceView->firstSlice, destinationTexture, destinationView->firstMip, destinationView->firstSlice, copyWidth, copyHeight);
-				uint64 eventCounter = LatteTexture_getNextUpdateEventCounter();
+			else
+				g_renderer->texture_copyImageSubData(sourceTexture, sourceView->firstMip, 0, 0, realSrcSlice, destinationTexture, destinationView->firstMip, 0, 0, destinationView->firstSlice, effectiveCopyWidth, effectiveCopyHeight, 1);
+			const uint64 eventCounter = LatteTexture_getNextUpdateEventCounter();
 			LatteTexture_MarkDynamicTextureAsChanged(destinationTexture->baseView, destinationView->firstSlice, destinationView->firstMip, eventCounter);
 		}
 		else
-			{
-				// calculate mip levels relative to texture base
-				sint32 texDstMipLevel;
-				if (destinationTexture->physAddress == dstPhysAddr)
-				{
-					texDstMipLevel = dstLevel;
-				}
-				else
-				{
-					// todo - handle mip addresses properly
-					texDstMipLevel = dstLevel - destinationView->firstMip;
-				}
-
-				g_renderer->texture_copyImageSubData(sourceTexture, sourceView->firstMip, 0, 0, realSrcSlice, destinationTexture, texDstMipLevel, 0, 0, realDstSlice, effectiveCopyWidth, effectiveCopyHeight, 1);
-				uint64 eventCounter = LatteTexture_getNextUpdateEventCounter();
-				LatteTexture_MarkDynamicTextureAsChanged(destinationTexture->baseView, destinationView->firstSlice, texDstMipLevel, eventCounter);
-			}
-		}
-		else
 		{
 			debug_printf("gx2CP_itHLECopySurface(): Copy texture with non-matching effective size\n");
 		}

src/Cafe/HW/Latte/Core/LatteTexture.cpp

@@ -1,5 +1,4 @@
 #include "Cafe/HW/Latte/Core/Latte.h"
-#include "Cafe/HW/Latte/Core/LatteDraw.h"
 #include "Cafe/HW/Latte/Core/LatteShader.h"
 #include "Cafe/HW/Latte/Core/LattePerformanceMonitor.h"
 #include "Cafe/HW/Latte/Core/LatteTexture.h"
@@ -9,6 +8,8 @@
 
 #include "Cafe/GraphicPack/GraphicPack2.h"
 
+#include <boost/container/small_vector.hpp>
+
 struct TexMemOccupancyEntry
 {
 	uint32 addrStart;
@@ -234,6 +235,9 @@ void LatteTexture_InitSliceAndMipInfo(LatteTexture* texture)
 // if this function returns false, textures will not be synchronized even if their data overlaps
 bool LatteTexture_IsFormatViewCompatible(Latte::E_GX2SURFFMT formatA, Latte::E_GX2SURFFMT formatB)
 {
+	if(formatA == formatB)
+		return true; // if the format is identical then compatibility must be guaranteed (otherwise we can't create the necessary default view of a texture)
+
 	// todo - find a better way to handle this
 	for (sint32 swap = 0; swap < 2; swap++)
 	{
@@ -297,9 +301,9 @@ void LatteTexture_copyData(LatteTexture* srcTexture, LatteTexture* dstTexture, s
 	else
 	{
 		sint32 effectiveWidth_dst, effectiveHeight_dst;
-		LatteTexture_getEffectiveSize(srcTexture, &effectiveWidth_dst, &effectiveHeight_dst, NULL, 0);
+		srcTexture->GetEffectiveSize(effectiveWidth_dst, effectiveHeight_dst, 0);
 		sint32 effectiveWidth_src, effectiveHeight_src;
-		LatteTexture_getEffectiveSize(dstTexture, &effectiveWidth_src, &effectiveHeight_src, NULL, 0);
+		dstTexture->GetEffectiveSize(effectiveWidth_src, effectiveHeight_src, 0);
 
 		debug_printf("texture_copyData(): Effective size mismatch\n");
 		cemuLog_logDebug(LogType::Force, "texture_copyData(): Effective size mismatch (due to texture rule)");
@@ -307,8 +311,6 @@ void LatteTexture_copyData(LatteTexture* srcTexture, LatteTexture* dstTexture, s
 		cemuLog_logDebug(LogType::Force, "Source:      origResolution {:04}x{:04} effectiveResolution {:04}x{:04} fmt {:04x} mipIndex {}", srcTexture->width, srcTexture->height, effectiveWidth_src, effectiveHeight_src, (uint32)srcTexture->format, 0);
 		return;
 	}
-	catchOpenGLError();
-
 	for (sint32 mipIndex = 0; mipIndex < mipCount; mipIndex++)
 	{
 		sint32 sliceCopyWidth = std::max(effectiveCopyWidth >> mipIndex, 1);
@@ -323,9 +325,7 @@ void LatteTexture_copyData(LatteTexture* srcTexture, LatteTexture* dstTexture, s
 			LatteTextureSliceMipInfo* dstTexSliceInfo = dstTexture->sliceMipInfo + dstTexture->GetSliceMipArrayIndex(sliceIndex, mipIndex);
 			dstTexSliceInfo->lastDynamicUpdate = srcTexSliceInfo->lastDynamicUpdate;
 		}
-		catchOpenGLError();
 	}
-	catchOpenGLError();
 }
 
 template<bool bothMustMatch>
@@ -438,6 +438,11 @@ void LatteTexture_SyncSlice(LatteTexture* srcTexture, sint32 srcSliceIndex, sint
 	sint32 dstWidth = dstTexture->width;
 	sint32 dstHeight = dstTexture->height;
 
+	if(srcTexture->overwriteInfo.hasFormatOverwrite != dstTexture->overwriteInfo.hasFormatOverwrite)
+		return; // dont sync: format overwrite state needs to match. Not strictly necessary but it simplifies logic down the road
+	else if(srcTexture->overwriteInfo.hasFormatOverwrite && srcTexture->overwriteInfo.format != dstTexture->overwriteInfo.format)
+		return; // both are overwritten but with different formats
+
 	if (srcMipIndex == 0 && dstMipIndex == 0 && (srcTexture->tileMode == Latte::E_HWTILEMODE::TM_LINEAR_ALIGNED || srcTexture->tileMode == Latte::E_HWTILEMODE::TM_1D_TILED_THIN1) && srcTexture->height > dstTexture->height && (srcTexture->height % dstTexture->height) == 0)
 	{
 		bool isMatch = srcTexture->tileMode == Latte::E_HWTILEMODE::TM_LINEAR_ALIGNED;
@@ -790,80 +795,42 @@ enum VIEWCOMPATIBILITY
 	VIEW_NOT_COMPATIBLE,
 };
 
-bool IsDimensionCompatibleForView(Latte::E_DIM baseDim, Latte::E_DIM viewDim)
+bool IsDimensionCompatibleForGX2View(Latte::E_DIM baseDim, Latte::E_DIM viewDim)
 {
-	bool incompatibleDim = false;
-	if (baseDim == Latte::E_DIM::DIM_2D && viewDim == Latte::E_DIM::DIM_2D)
-		;
-	else if (baseDim == Latte::E_DIM::DIM_2D && viewDim == Latte::E_DIM::DIM_2D_ARRAY)
-		;
-	else if (baseDim == Latte::E_DIM::DIM_CUBEMAP && viewDim == Latte::E_DIM::DIM_CUBEMAP)
-		;
-	else if (baseDim == Latte::E_DIM::DIM_CUBEMAP && viewDim == Latte::E_DIM::DIM_2D_ARRAY)
-		;
-	else if (baseDim == Latte::E_DIM::DIM_2D_ARRAY && viewDim == Latte::E_DIM::DIM_2D_ARRAY)
-		;
-	else if (baseDim == Latte::E_DIM::DIM_2D_ARRAY && viewDim == Latte::E_DIM::DIM_2D)
-		;
-	else if (baseDim == Latte::E_DIM::DIM_2D_ARRAY && viewDim == Latte::E_DIM::DIM_CUBEMAP)
-		;
-	else if (baseDim == Latte::E_DIM::DIM_3D && viewDim == Latte::E_DIM::DIM_2D_ARRAY)
-		;
-	else if (baseDim == Latte::E_DIM::DIM_2D_MSAA && viewDim == Latte::E_DIM::DIM_2D_MSAA)
-		;
-	else if (baseDim == Latte::E_DIM::DIM_2D_ARRAY && viewDim == Latte::E_DIM::DIM_3D)
-	{
-		// not compatible on OpenGL
-		incompatibleDim = true;
-	}
-	else if (baseDim == Latte::E_DIM::DIM_2D && viewDim == Latte::E_DIM::DIM_2D_MSAA)
-	{
-		// not compatible
-		incompatibleDim = true;
-	}
-	else if (baseDim == Latte::E_DIM::DIM_2D && viewDim == Latte::E_DIM::DIM_1D)
-	{
-		// not compatible
-		incompatibleDim = true;
-	}
-	else if (baseDim == Latte::E_DIM::DIM_2D && viewDim == Latte::E_DIM::DIM_3D)
-	{
-		// not compatible
-		incompatibleDim = true;
-	}
-	else if (baseDim == Latte::E_DIM::DIM_3D && viewDim == Latte::E_DIM::DIM_2D)
-	{
-		// not compatible
-		incompatibleDim = true;
-	}
-	else if ((baseDim == Latte::E_DIM::DIM_2D && viewDim == Latte::E_DIM::DIM_CUBEMAP) ||
-		(baseDim == Latte::E_DIM::DIM_CUBEMAP && viewDim == Latte::E_DIM::DIM_2D))
-	{
-		// not compatible
-		incompatibleDim = true;
-	}
-	else if (baseDim == Latte::E_DIM::DIM_2D_MSAA && viewDim == Latte::E_DIM::DIM_2D)
-	{
-		// not compatible
-		incompatibleDim = true;
-	}
-	else if (baseDim == Latte::E_DIM::DIM_1D && viewDim == Latte::E_DIM::DIM_2D)
-	{
-		// not compatible (probably?)
-		incompatibleDim = true;
-	}
-	else
-	{
-		cemu_assert_debug(false);
-		incompatibleDim = true;
-	}
-	return !incompatibleDim;
+	// Note that some combinations depend on the exact view/slice index and count which we currently ignore (like a 3D view of a 3D texture)
+	bool isCompatible =
+		(baseDim == viewDim) ||
+		(baseDim == Latte::E_DIM::DIM_CUBEMAP && viewDim == Latte::E_DIM::DIM_2D) ||
+		(baseDim == Latte::E_DIM::DIM_2D && viewDim == Latte::E_DIM::DIM_2D_ARRAY) ||
+		(baseDim == Latte::E_DIM::DIM_2D_ARRAY && viewDim == Latte::E_DIM::DIM_2D) ||
+		(baseDim == Latte::E_DIM::DIM_CUBEMAP && viewDim == Latte::E_DIM::DIM_2D_ARRAY) ||
+		(baseDim == Latte::E_DIM::DIM_2D_ARRAY && viewDim == Latte::E_DIM::DIM_CUBEMAP) ||
+		(baseDim == Latte::E_DIM::DIM_3D && viewDim == Latte::E_DIM::DIM_2D_ARRAY);
+	if(isCompatible)
+		return true;
+	// these combinations have been seen in use by games and are considered incompatible:
+	// (baseDim == Latte::E_DIM::DIM_2D_ARRAY && viewDim == Latte::E_DIM::DIM_3D) -> Not allowed on OpenGL
+	// (baseDim == Latte::E_DIM::DIM_2D && viewDim == Latte::E_DIM::DIM_2D_MSAA)
+	// (baseDim == Latte::E_DIM::DIM_2D && viewDim == Latte::E_DIM::DIM_1D)
+	// (baseDim == Latte::E_DIM::DIM_2D && viewDim == Latte::E_DIM::DIM_3D)
+	// (baseDim == Latte::E_DIM::DIM_3D && viewDim == Latte::E_DIM::DIM_2D)
+	// (baseDim == Latte::E_DIM::DIM_3D && viewDim == Latte::E_DIM::DIM_3D) -> Only compatible if the same depth and shared at mip/slice 0
+	// (baseDim == Latte::E_DIM::DIM_2D && viewDim == Latte::E_DIM::DIM_CUBEMAP)
+	// (baseDim == Latte::E_DIM::DIM_2D_MSAA && viewDim == Latte::E_DIM::DIM_2D)
+	// (baseDim == Latte::E_DIM::DIM_1D && viewDim == Latte::E_DIM::DIM_2D)
+	return false;
 }
 
 VIEWCOMPATIBILITY LatteTexture_CanTextureBeRepresentedAsView(LatteTexture* baseTexture, uint32 physAddr, sint32 width, sint32 height, sint32 pitch, Latte::E_DIM dimView, Latte::E_GX2SURFFMT format, bool isDepth, sint32 firstMip, sint32 numMip, sint32 firstSlice, sint32 numSlice, sint32& relativeMipIndex, sint32& relativeSliceIndex)
 {
 	relativeMipIndex = 0;
 	relativeSliceIndex = 0;
+	if (baseTexture->overwriteInfo.hasFormatOverwrite)
+	{
+		// if the base format is overwritten, then we only allow aliasing if the view format matches the base format
+		if (baseTexture->format != format)
+			return VIEW_NOT_COMPATIBLE;
+	}
 	if (LatteTexture_IsFormatViewCompatible(baseTexture->format, format) == false)
 		return VIEW_NOT_COMPATIBLE;
 	if (baseTexture->physAddress == physAddr && baseTexture->pitch == pitch)
@@ -872,7 +839,9 @@ VIEWCOMPATIBILITY LatteTexture_CanTextureBeRepresentedAsView(LatteTexture* baseT
 			return VIEW_NOT_COMPATIBLE; // depth and non-depth formats are never compatible (on OpenGL)
 		if (!LatteTexture_IsTexelSizeCompatibleFormat(baseTexture->format, format) || baseTexture->width != width || baseTexture->height != height)
 			return VIEW_NOT_COMPATIBLE;
-		if (!IsDimensionCompatibleForView(baseTexture->dim, dimView))
+		// 3D views are only compatible on Vulkan if they match the base texture in regards to mip and slice count
+		bool isCompatible3DView = dimView == Latte::E_DIM::DIM_3D && baseTexture->dim == dimView && firstSlice == 0 && firstMip == 0 && baseTexture->mipLevels == numMip && baseTexture->depth == numSlice;
+		if (!isCompatible3DView && !IsDimensionCompatibleForGX2View(baseTexture->dim, dimView))
 			return VIEW_NOT_COMPATIBLE;
 		if (baseTexture->isDepth && baseTexture->format != format)
 		{
@@ -924,7 +893,7 @@ VIEWCOMPATIBILITY LatteTexture_CanTextureBeRepresentedAsView(LatteTexture* baseT
 				if (!LatteTexture_IsTexelSizeCompatibleFormat(baseTexture->format, format) )
 					return VIEW_NOT_COMPATIBLE;
 
-				if (!IsDimensionCompatibleForView(baseTexture->dim, dimView))
+				if (!IsDimensionCompatibleForGX2View(baseTexture->dim, dimView))
 					return VIEW_NOT_COMPATIBLE;
 				if (baseTexture->isDepth && baseTexture->format != format)
 				{
@@ -978,7 +947,7 @@ void LatteTexture_RecreateTextureWithDifferentMipSliceCount(LatteTexture* textur
 		newDim = Latte::E_DIM::DIM_2D_ARRAY;
 	else if (newDim == Latte::E_DIM::DIM_1D && newDepth > 1)
 		newDim = Latte::E_DIM::DIM_1D_ARRAY;
-	LatteTextureView* view = LatteTexture_CreateTexture(0, newDim, texture->physAddress, physMipAddr, texture->format, texture->width, texture->height, newDepth, texture->pitch, newMipCount, texture->swizzle, texture->tileMode, texture->isDepth);
+	LatteTextureView* view = LatteTexture_CreateTexture(newDim, texture->physAddress, physMipAddr, texture->format, texture->width, texture->height, newDepth, texture->pitch, newMipCount, texture->swizzle, texture->tileMode, texture->isDepth);
 	cemu_assert(!(view->baseTexture->mipLevels <= 1 && physMipAddr == MPTR_NULL && newMipCount > 1));
 	// copy data from old texture if its dynamically updated
 	if (texture->isUpdatedOnGPU)
@@ -998,7 +967,8 @@ void LatteTexture_RecreateTextureWithDifferentMipSliceCount(LatteTexture* textur
 }
 
 // create new texture representation
-// if allowCreateNewDataTexture is true, a new texture will be created if necessary. If it is false, only existing textures may be used, except if a data-compatible version of the requested texture already exists and it's not view compatible
+// if allowCreateNewDataTexture is true, a new texture will be created if necessary. If it is false, only existing textures may be used, except if a data-compatible version of the requested texture already exists and it's not view compatible (todo - we should differentiate between Latte compatible views and renderer compatible)
+// the returned view will map to the provided mip and slice range within the created texture, this is to match the behavior of lookupSliceEx
 LatteTextureView* LatteTexture_CreateMapping(MPTR physAddr, MPTR physMipAddr, sint32 width, sint32 height, sint32 depth, sint32 pitch, Latte::E_HWTILEMODE tileMode, uint32 swizzle, sint32 firstMip, sint32 numMip, sint32 firstSlice, sint32 numSlice, Latte::E_GX2SURFFMT format, Latte::E_DIM dimBase, Latte::E_DIM dimView, bool isDepth, bool allowCreateNewDataTexture)
 {
 	if (format == Latte::E_GX2SURFFMT::INVALID_FORMAT)
@@ -1014,7 +984,7 @@ LatteTextureView* LatteTexture_CreateMapping(MPTR physAddr, MPTR physMipAddr, si
 	// todo, depth and numSlice are redundant
 
 	sint32 sliceCount = firstSlice + numSlice;
-	std::vector<LatteTexture*> list_overlappingTextures;
+	boost::container::small_vector<LatteTexture*, 16> list_overlappingTextures;
 	for (sint32 sliceIndex = 0; sliceIndex < sliceCount; sliceIndex++)
 	{
 		sint32 mipIndex = 0;
@@ -1104,12 +1074,18 @@ LatteTextureView* LatteTexture_CreateMapping(MPTR physAddr, MPTR physMipAddr, si
 	// create new texture
 	if (allowCreateNewDataTexture == false)
 		return nullptr;
-	LatteTextureView* view = LatteTexture_CreateTexture(0, dimBase, physAddr, physMipAddr, format, width, height, depth, pitch, firstMip + numMip, swizzle, tileMode, isDepth);
+	LatteTextureView* view = LatteTexture_CreateTexture(dimBase, physAddr, physMipAddr, format, width, height, depth, pitch, firstMip + numMip, swizzle, tileMode, isDepth);
+	LatteTexture* newTexture = view->baseTexture;
 	LatteTexture_GatherTextureRelations(view->baseTexture);
 	LatteTexture_UpdateTextureFromDynamicChanges(view->baseTexture);
 	// delete any individual smaller slices/mips that have become redundant
 	LatteTexture_DeleteAbsorbedSubtextures(view->baseTexture);
-	return view;
+	// create view
+	sint32 relativeMipIndex;
+	sint32 relativeSliceIndex;
+	VIEWCOMPATIBILITY viewCompatibility = LatteTexture_CanTextureBeRepresentedAsView(newTexture, physAddr, width, height, pitch, dimView, format, isDepth, firstMip, numMip, firstSlice, numSlice, relativeMipIndex, relativeSliceIndex);
+	cemu_assert(viewCompatibility == VIEW_COMPATIBLE);
+	return view->baseTexture->GetOrCreateView(dimView, format, relativeMipIndex + firstMip, numMip, relativeSliceIndex + firstSlice, numSlice);
 }
 
 LatteTextureView* LatteTC_LookupTextureByData(MPTR physAddr, sint32 width, sint32 height, sint32 pitch, sint32 firstMip, sint32 numMip, sint32 firstSlice, sint32 numSlice, sint32* searchIndex)
@@ -1177,12 +1153,8 @@ LatteTextureView* LatteTC_GetTextureSliceViewOrTryCreate(MPTR srcImagePtr, MPTR
 void LatteTexture_UpdateDataToLatest(LatteTexture* texture)
 {
 	if (LatteTC_HasTextureChanged(texture))
-	{
-		g_renderer->texture_rememberBoundTexture(0);
-		g_renderer->texture_bindAndActivateRawTex(texture, 0);
-		LatteTexture_ReloadData(texture, 0);
-		g_renderer->texture_restoreBoundTexture(0);
-	}
+		LatteTexture_ReloadData(texture);
+
 	if (texture->reloadFromDynamicTextures)
 	{
 		LatteTexture_UpdateCacheFromDynamicTextures(texture);
@@ -1231,7 +1203,16 @@ std::vector<LatteTexture*>& LatteTexture::GetAllTextures()
 	return sAllTextures;
 }
 
-LatteTexture::LatteTexture(uint32 textureUnit, Latte::E_DIM dim, MPTR physAddress, MPTR physMipAddress, Latte::E_GX2SURFFMT format, uint32 width, uint32 height, uint32 depth, uint32 pitch, uint32 mipLevels, uint32 swizzle,
+bool LatteTexture_GX2FormatHasStencil(bool isDepth, Latte::E_GX2SURFFMT format)
+{
+	if (!isDepth)
+		return false;
+	return format == Latte::E_GX2SURFFMT::D24_S8_UNORM ||
+		   format == Latte::E_GX2SURFFMT::D24_S8_FLOAT ||
+		   format == Latte::E_GX2SURFFMT::D32_S8_FLOAT;
+}
+
+LatteTexture::LatteTexture(Latte::E_DIM dim, MPTR physAddress, MPTR physMipAddress, Latte::E_GX2SURFFMT format, uint32 width, uint32 height, uint32 depth, uint32 pitch, uint32 mipLevels, uint32 swizzle,
 	Latte::E_HWTILEMODE tileMode, bool isDepth)
 {
 	_AddTextureToGlobalList(this);
@@ -1249,6 +1230,7 @@ LatteTexture::LatteTexture(uint32 textureUnit, Latte::E_DIM dim, MPTR physAddres
 	this->mipLevels = mipLevels;
 	this->tileMode = tileMode;
 	this->isDepth = isDepth;
+	this->hasStencil = LatteTexture_GX2FormatHasStencil(isDepth, format);
 	this->physMipAddress = physMipAddress;
 	this->lastUpdateEventCounter = LatteTexture_getNextUpdateEventCounter();
 	this->lastWriteEventCounter = LatteTexture_getNextUpdateEventCounter();

src/Cafe/HW/Latte/Core/LatteTexture.h

@@ -24,10 +24,10 @@ struct LatteSamplerState
 class LatteTexture
 {
 public:
-	LatteTexture(uint32 textureUnit, Latte::E_DIM dim, MPTR physAddress, MPTR physMipAddress, Latte::E_GX2SURFFMT format, uint32 width, uint32 height, uint32 depth, uint32 pitch, uint32 mipLevels, uint32 swizzle, Latte::E_HWTILEMODE tileMode, bool isDepth);
+	LatteTexture(Latte::E_DIM dim, MPTR physAddress, MPTR physMipAddress, Latte::E_GX2SURFFMT format, uint32 width, uint32 height, uint32 depth, uint32 pitch, uint32 mipLevels, uint32 swizzle, Latte::E_HWTILEMODE tileMode, bool isDepth);
 	virtual ~LatteTexture();
 
-	virtual void InitTextureState() {};
+	virtual void AllocateOnHost() = 0;
 
 	LatteTextureView* GetOrCreateView(Latte::E_DIM dim, Latte::E_GX2SURFFMT format, sint32 firstMip, sint32 mipCount, sint32 firstSlice, sint32 sliceCount)
 	{
@@ -57,6 +57,29 @@ public:
 
 	bool Is3DTexture() const { return dim == Latte::E_DIM::DIM_3D; };
 
+	void GetSize(sint32& width, sint32& height, sint32 mipLevel) const
+	{
+		width = std::max(1, this->width >> mipLevel);
+		height = std::max(1, this->height >> mipLevel);
+	}
+
+	// similar to GetSize, but returns the real size of the texture taking into account any resolution overwrite by gfx pack rules
+	void GetEffectiveSize(sint32& effectiveWidth, sint32& effectiveHeight, sint32 mipLevel) const
+	{
+		if( overwriteInfo.hasResolutionOverwrite )
+		{
+			effectiveWidth = overwriteInfo.width;
+			effectiveHeight = overwriteInfo.height;
+		}
+		else
+		{
+			effectiveWidth = this->width;
+			effectiveHeight = this->height;
+		}
+		effectiveWidth = std::max(1, effectiveWidth >> mipLevel);
+		effectiveHeight = std::max(1, effectiveHeight >> mipLevel);
+	}
+
 	sint32 GetMipDepth(sint32 mipIndex)
 	{
 		cemu_assert_debug(mipIndex >= 0 && mipIndex < this->mipLevels);
@@ -307,13 +330,11 @@ std::vector<LatteTextureInformation> LatteTexture_QueryCacheInfo();
 
 float* LatteTexture_getEffectiveTextureScale(LatteConst::ShaderType shaderType, sint32 texUnit);
 
-LatteTextureView* LatteTexture_CreateTexture(uint32 textureUnit, Latte::E_DIM dim, MPTR physAddress, MPTR physMipAddress, Latte::E_GX2SURFFMT format, uint32 width, uint32 height, uint32 depth, uint32 pitch, uint32 mipLevels, uint32 swizzle, Latte::E_HWTILEMODE tileMode, bool isDepth);
+LatteTextureView* LatteTexture_CreateTexture(Latte::E_DIM dim, MPTR physAddress, MPTR physMipAddress, Latte::E_GX2SURFFMT format, uint32 width, uint32 height, uint32 depth, uint32 pitch, uint32 mipLevels, uint32 swizzle, Latte::E_HWTILEMODE tileMode, bool isDepth);
 void LatteTexture_Delete(LatteTexture* texture);
 
 void LatteTextureLoader_writeReadbackTextureToMemory(LatteTextureDefinition* textureData, uint32 sliceIndex, uint32 mipIndex, uint8* linearPixelData);
 
-void LatteTexture_getSize(LatteTexture* texture, sint32* width, sint32* height, sint32* depth, sint32 mipLevel);
-void LatteTexture_getEffectiveSize(LatteTexture* texture, sint32* effectiveWidth, sint32* effectiveHeight, sint32* effectiveDepth, sint32 mipLevel = 0);
 sint32 LatteTexture_getEffectiveWidth(LatteTexture* texture);
 bool LatteTexture_doesEffectiveRescaleRatioMatch(LatteTexture* texture1, sint32 mipLevel1, LatteTexture* texture2, sint32 mipLevel2);
 void LatteTexture_scaleToEffectiveSize(LatteTexture* texture, sint32* x, sint32* y, sint32 mipLevel);

src/Cafe/HW/Latte/Core/LatteTextureCache.cpp

@@ -316,7 +316,7 @@ void LatteTexture_Delete(LatteTexture* texture)
 		delete[] texture->sliceMipInfo;
 		texture->sliceMipInfo = nullptr;
 	}
-	g_renderer->texture_destroy(texture);
+	delete texture;
 }
 
 /*

src/Cafe/HW/Latte/Core/LatteTextureLegacy.cpp

@@ -32,9 +32,9 @@ void LatteTexture_setEffectiveTextureScale(LatteConst::ShaderType shaderType, si
 	t[1] = v;
 }
 
-void LatteTextureLoader_UpdateTextureSliceData(LatteTexture* tex, sint32 textureUnit, uint32 sliceIndex, uint32 mipIndex, MPTR physImagePtr, MPTR physMipPtr, Latte::E_DIM dim, uint32 width, uint32 height, uint32 depth, uint32 mipLevels, uint32 pitch, Latte::E_HWTILEMODE tileMode, uint32 swizzle, bool dumpTex);
+void LatteTextureLoader_UpdateTextureSliceData(LatteTexture* tex, uint32 sliceIndex, uint32 mipIndex, MPTR physImagePtr, MPTR physMipPtr, Latte::E_DIM dim, uint32 width, uint32 height, uint32 depth, uint32 mipLevels, uint32 pitch, Latte::E_HWTILEMODE tileMode, uint32 swizzle, bool dumpTex);
 
-void LatteTexture_ReloadData(LatteTexture* tex, uint32 textureUnit)
+void LatteTexture_ReloadData(LatteTexture* tex)
 {
 	tex->reloadCount++;
 	for(sint32 mip=0; mip<tex->mipLevels; mip++)
@@ -44,35 +44,35 @@ void LatteTexture_ReloadData(LatteTexture* tex, uint32 textureUnit)
 		{
 			sint32 numSlices = std::max(tex->depth, 1);
 			for(sint32 s=0; s<numSlices; s++)
-				LatteTextureLoader_UpdateTextureSliceData(tex, textureUnit, s, mip, tex->physAddress, tex->physMipAddress, tex->dim, tex->width, tex->height, tex->depth, tex->mipLevels, tex->pitch, tex->tileMode, tex->swizzle, true);
+				LatteTextureLoader_UpdateTextureSliceData(tex, s, mip, tex->physAddress, tex->physMipAddress, tex->dim, tex->width, tex->height, tex->depth, tex->mipLevels, tex->pitch, tex->tileMode, tex->swizzle, true);
 		}
 		else if( tex->dim == Latte::E_DIM::DIM_CUBEMAP )
 		{
 			cemu_assert_debug((tex->depth % 6) == 0);
 			sint32 numFullCubeMaps = tex->depth/6; // number of cubemaps (if numFullCubeMaps is >1 then this texture is a cubemap array)
 			for(sint32 s=0; s<numFullCubeMaps*6; s++)
-				LatteTextureLoader_UpdateTextureSliceData(tex, textureUnit, s, mip, tex->physAddress, tex->physMipAddress, tex->dim, tex->width, tex->height, tex->depth, tex->mipLevels, tex->pitch, tex->tileMode, tex->swizzle, true);
+				LatteTextureLoader_UpdateTextureSliceData(tex, s, mip, tex->physAddress, tex->physMipAddress, tex->dim, tex->width, tex->height, tex->depth, tex->mipLevels, tex->pitch, tex->tileMode, tex->swizzle, true);
 		}
 		else if( tex->dim == Latte::E_DIM::DIM_3D )
 		{
 			sint32 mipDepth = std::max(tex->depth>>mip, 1);
 			for(sint32 s=0; s<mipDepth; s++)
 			{
-				LatteTextureLoader_UpdateTextureSliceData(tex, textureUnit, s, mip, tex->physAddress, tex->physMipAddress, tex->dim, tex->width, tex->height, tex->depth, tex->mipLevels, tex->pitch, tex->tileMode, tex->swizzle, true);
+				LatteTextureLoader_UpdateTextureSliceData(tex, s, mip, tex->physAddress, tex->physMipAddress, tex->dim, tex->width, tex->height, tex->depth, tex->mipLevels, tex->pitch, tex->tileMode, tex->swizzle, true);
 			}
 		}
 		else
 		{
 			// load slice 0
-			LatteTextureLoader_UpdateTextureSliceData(tex, textureUnit, 0, mip, tex->physAddress, tex->physMipAddress, tex->dim, tex->width, tex->height, tex->depth, tex->mipLevels, tex->pitch, tex->tileMode, tex->swizzle, true);
+			LatteTextureLoader_UpdateTextureSliceData(tex, 0, mip, tex->physAddress, tex->physMipAddress, tex->dim, tex->width, tex->height, tex->depth, tex->mipLevels, tex->pitch, tex->tileMode, tex->swizzle, true);
 		}
 	}
 	tex->lastUpdateEventCounter = LatteTexture_getNextUpdateEventCounter();
 }
 
-LatteTextureView* LatteTexture_CreateTexture(uint32 textureUnit, Latte::E_DIM dim, MPTR physAddress, MPTR physMipAddress, Latte::E_GX2SURFFMT format, uint32 width, uint32 height, uint32 depth, uint32 pitch, uint32 mipLevels, uint32 swizzle, Latte::E_HWTILEMODE tileMode, bool isDepth)
+LatteTextureView* LatteTexture_CreateTexture(Latte::E_DIM dim, MPTR physAddress, MPTR physMipAddress, Latte::E_GX2SURFFMT format, uint32 width, uint32 height, uint32 depth, uint32 pitch, uint32 mipLevels, uint32 swizzle, Latte::E_HWTILEMODE tileMode, bool isDepth)
 {
-	const auto tex = g_renderer->texture_createTextureEx(textureUnit, dim, physAddress, physMipAddress, format, width, height, depth, pitch, mipLevels, swizzle, tileMode, isDepth);
+	const auto tex = g_renderer->texture_createTextureEx(dim, physAddress, physMipAddress, format, width, height, depth, pitch, mipLevels, swizzle, tileMode, isDepth);
 	// init slice/mip info array
 	LatteTexture_InitSliceAndMipInfo(tex);
 	LatteTexture_RegisterTextureMemoryOccupancy(tex);
@@ -110,7 +110,7 @@ LatteTextureView* LatteTexture_CreateTexture(uint32 textureUnit, Latte::E_DIM di
 			}
 		}
 	}
-	LatteTexture_ReloadData(tex, textureUnit);
+	LatteTexture_ReloadData(tex);
 	LatteTC_MarkTextureStillInUse(tex);
 	LatteTC_RegisterTexture(tex);
 	// create initial view that maps to the whole texture
@@ -207,13 +207,13 @@ void LatteTexture_updateTexturesForStage(LatteDecompilerShader* shaderContext, u
 		bool isDepthSampler = shaderContext->textureUsesDepthCompare[textureIndex];
 		// look for already existing texture
 		LatteTextureView* textureView;
-		if (isDepthSampler == false)
+		if (!isDepthSampler)
 			textureView = LatteTextureViewLookupCache::lookup(physAddr, width, height, depth, pitch, viewFirstMip, viewNumMips, viewFirstSlice, viewNumSlices, format, dim);
 		else
-			textureView = LatteTextureViewLookupCache::lookup(physAddr, width, height, depth, pitch, viewFirstMip, viewNumMips, viewFirstSlice, viewNumSlices, format, dim, true);
-		if (textureView == nullptr)
+			textureView = LatteTextureViewLookupCache::lookupWithColorOrDepthType(physAddr, width, height, depth, pitch, viewFirstMip, viewNumMips, viewFirstSlice, viewNumSlices, format, dim, true);
+		if (!textureView)
 		{
-			// create new mapping
+			// view not found, create a new mapping which will also create a new texture if necessary
 			textureView = LatteTexture_CreateMapping(physAddr, physMipAddr, width, height, depth, pitch, tileMode, swizzle, viewFirstMip, viewNumMips, viewFirstSlice, viewNumSlices, format, dim, dim, isDepthSampler);
 			if (textureView == nullptr)
 				continue;
@@ -228,10 +228,6 @@ void LatteTexture_updateTexturesForStage(LatteDecompilerShader* shaderContext, u
 
 			// if this texture is bound multiple times then use alternative views
 			if (textureView->lastTextureBindIndex == LatteGPUState.textureBindCounter)
-			{
-				// Intel driver has issues with textures that have multiple views bound and used by a shader, causes a softlock in BotW
-				// therefore we disable this on Intel
-				if (LatteGPUState.glVendor != GLVENDOR_INTEL_NOLEGACY)
 			{
 				LatteTextureViewGL* textureViewGL = (LatteTextureViewGL*)textureView;
 				// get next unused alternative texture view
@@ -243,11 +239,10 @@ void LatteTexture_updateTexturesForStage(LatteDecompilerShader* shaderContext, u
 				}
 				textureView = textureViewGL;
 		}
-			}
 			textureView->lastTextureBindIndex = LatteGPUState.textureBindCounter;
 			rendererGL->renderstate_updateTextureSettingsGL(shaderContext, textureView, textureIndex + glBackendBaseTexUnit, word4, textureIndex, isDepthSampler);
 		}
-		g_renderer->texture_bindOnly(textureView, textureIndex + glBackendBaseTexUnit);
+		g_renderer->texture_setLatteTexture(textureView, textureIndex + glBackendBaseTexUnit);
 		// update if data changed
 		bool swizzleChanged = false;
 		if (textureView->baseTexture->swizzle != swizzle)
@@ -273,9 +268,7 @@ void LatteTexture_updateTexturesForStage(LatteDecompilerShader* shaderContext, u
 		// check for changes
 		if (LatteTC_HasTextureChanged(textureView->baseTexture) || swizzleChanged)
 		{
-#ifdef CEMU_DEBUG_ASSERT
 			debug_printf("Reload texture 0x%08x res %dx%d memRange %08x-%08x SwizzleChange: %s\n", textureView->baseTexture->physAddress, textureView->baseTexture->width, textureView->baseTexture->height, textureView->baseTexture->texDataPtrLow, textureView->baseTexture->texDataPtrHigh, swizzleChanged ? "yes" : "no");
-#endif
 			// update swizzle / changed mip address
 			if (swizzleChanged)
 			{
@@ -285,9 +278,8 @@ void LatteTexture_updateTexturesForStage(LatteDecompilerShader* shaderContext, u
 					textureView->baseTexture->physMipAddress = physMipAddr;
 				}
 			}
-			g_renderer->texture_bindAndActivateRawTex(textureView->baseTexture, textureIndex + glBackendBaseTexUnit);
 			debug_printf("Reload reason: Data-change when bound as texture (new hash 0x%08x)\n", textureView->baseTexture->texDataHash2);
-			LatteTexture_ReloadData(textureView->baseTexture, textureIndex + glBackendBaseTexUnit);
+			LatteTexture_ReloadData(textureView->baseTexture);
 		}
 		LatteTexture* baseTexture = textureView->baseTexture;
 		if (baseTexture->reloadFromDynamicTextures)
@@ -339,44 +331,6 @@ void LatteTexture_updateTextures()
 		LatteTexture_updateTexturesForStage(geometryShader, LATTE_CEMU_GS_TEX_UNIT_BASE, LatteGPUState.contextNew.SQ_TEX_START_GS);
 }
 
-// returns the width, height, depth of the texture
-void LatteTexture_getSize(LatteTexture* texture, sint32* width, sint32* height, sint32* depth, sint32 mipLevel)
-{
-	*width = texture->width;
-	*height = texture->height;
-	if (depth != NULL)
-		*depth = texture->depth;
-	// handle mip level
-	*width = std::max(1, *width >> mipLevel);
-	*height = std::max(1, *height >> mipLevel);
-	if(texture->Is3DTexture() && depth)
-		*depth = std::max(1, *depth >> mipLevel);
-}
-
-/*
- * Returns the internally used width/height/depth of the texture
- * Usually this is the width/height/depth specified by the game,
- * unless the texture resolution was redefined via graphic pack texture rules
- */
-void LatteTexture_getEffectiveSize(LatteTexture* texture, sint32* effectiveWidth, sint32* effectiveHeight, sint32* effectiveDepth, sint32 mipLevel)
-{
-	*effectiveWidth = texture->width;
-	*effectiveHeight = texture->height;
-	if( effectiveDepth != NULL )
-		*effectiveDepth = texture->depth;
-	if( texture->overwriteInfo.hasResolutionOverwrite )
-	{
-		*effectiveWidth = texture->overwriteInfo.width;
-		*effectiveHeight = texture->overwriteInfo.height;
-		if( effectiveDepth != NULL )
-			*effectiveDepth = texture->overwriteInfo.depth;
-	}
-	// handle mipLevel
-	// todo: Mip-mapped 3D textures decrease in depth also?
-	*effectiveWidth = std::max(1, *effectiveWidth >> mipLevel);
-	*effectiveHeight = std::max(1, *effectiveHeight >> mipLevel);
-}
-
 sint32 LatteTexture_getEffectiveWidth(LatteTexture* texture)
 {
 	if (texture->overwriteInfo.hasResolutionOverwrite)

src/Cafe/HW/Latte/Core/LatteTextureLoader.cpp

@@ -599,7 +599,7 @@ void LatteTextureLoader_loadTextureDataIntoSlice(LatteTexture* hostTexture, sint
 	}
 }
 
-void LatteTextureLoader_UpdateTextureSliceData(LatteTexture* tex, sint32 textureUnit, uint32 sliceIndex, uint32 mipIndex, MPTR physImagePtr, MPTR physMipPtr, Latte::E_DIM dim, uint32 width, uint32 height, uint32 depth, uint32 mipLevels, uint32 pitch, Latte::E_HWTILEMODE tileMode, uint32 swizzle, bool dumpTex)
+void LatteTextureLoader_UpdateTextureSliceData(LatteTexture* tex, uint32 sliceIndex, uint32 mipIndex, MPTR physImagePtr, MPTR physMipPtr, Latte::E_DIM dim, uint32 width, uint32 height, uint32 depth, uint32 mipLevels, uint32 pitch, Latte::E_HWTILEMODE tileMode, uint32 swizzle, bool dumpTex)
 {
 	LatteTextureLoaderCtx textureLoader = { 0 };
 	
@@ -621,7 +621,7 @@ void LatteTextureLoader_UpdateTextureSliceData(LatteTexture* tex, sint32 texture
 
 	if (tex->isDataDefined == false)
 	{
-		g_renderer->texture_reserveTextureOnGPU(tex);
+		tex->AllocateOnHost();
 		tex->isDataDefined = true;
 		// if decoder is not set then clear texture
 		// on Vulkan this is used to make sure the texture is no longer in UNDEFINED layout

src/Cafe/HW/Latte/Core/LatteTextureView.cpp

@@ -143,7 +143,6 @@ void LatteTextureViewLookupCache::RemoveAll(LatteTextureView* view)
 	}
 }
 
-
 LatteTextureView* LatteTextureViewLookupCache::lookup(MPTR physAddr, sint32 width, sint32 height, sint32 depth, sint32 pitch, sint32 firstMip, sint32 numMip, sint32 firstSlice, sint32 numSlice, Latte::E_GX2SURFFMT format, Latte::E_DIM dim)
 {
 	// todo - add tileMode param to this and the other lookup functions?
@@ -163,7 +162,7 @@ LatteTextureView* LatteTextureViewLookupCache::lookup(MPTR physAddr, sint32 widt
 	return nullptr;
 }
 
-LatteTextureView* LatteTextureViewLookupCache::lookup(MPTR physAddr, sint32 width, sint32 height, sint32 depth, sint32 pitch, sint32 firstMip, sint32 numMip, sint32 firstSlice, sint32 numSlice, Latte::E_GX2SURFFMT format, Latte::E_DIM dim, bool isDepth)
+LatteTextureView* LatteTextureViewLookupCache::lookupWithColorOrDepthType(MPTR physAddr, sint32 width, sint32 height, sint32 depth, sint32 pitch, sint32 firstMip, sint32 numMip, sint32 firstSlice, sint32 numSlice, Latte::E_GX2SURFFMT format, Latte::E_DIM dim, bool isDepth)
 {
 	cemu_assert_debug(firstSlice == 0);
 	uint32 key = _getViewBucketKey(physAddr, width, height, pitch);

src/Cafe/HW/Latte/Core/LatteTextureView.h

@@ -41,7 +41,7 @@ public:
 	static void RemoveAll(LatteTextureView* view);
 
 	static LatteTextureView* lookup(MPTR physAddr, sint32 width, sint32 height, sint32 depth, sint32 pitch, sint32 firstMip, sint32 numMip, sint32 firstSlice, sint32 numSlice, Latte::E_GX2SURFFMT format, Latte::E_DIM dim);
-	static LatteTextureView* lookup(MPTR physAddr, sint32 width, sint32 height, sint32 depth, sint32 pitch, sint32 firstMip, sint32 numMip, sint32 firstSlice, sint32 numSlice, Latte::E_GX2SURFFMT format, Latte::E_DIM dim, bool isDepth);
+	static LatteTextureView* lookupWithColorOrDepthType(MPTR physAddr, sint32 width, sint32 height, sint32 depth, sint32 pitch, sint32 firstMip, sint32 numMip, sint32 firstSlice, sint32 numSlice, Latte::E_GX2SURFFMT format, Latte::E_DIM dim, bool isDepth);
 	static LatteTextureView* lookupSlice(MPTR physAddr, sint32 width, sint32 height, sint32 pitch, sint32 firstMip, sint32 firstSlice, Latte::E_GX2SURFFMT format);
 	static LatteTextureView* lookupSliceMinSize(MPTR physAddr, sint32 minWidth, sint32 minHeight, sint32 pitch, sint32 firstMip, sint32 firstSlice, Latte::E_GX2SURFFMT format);
 	static LatteTextureView* lookupSliceEx(MPTR physAddr, sint32 width, sint32 height, sint32 pitch, sint32 firstMip, sint32 firstSlice, Latte::E_GX2SURFFMT format, bool isDepth);

src/Cafe/HW/Latte/Core/LatteThread.cpp

@@ -44,7 +44,7 @@ LatteTextureView* LatteHandleOSScreen_getOrCreateScreenTex(MPTR physAddress, uin
 	LatteTextureView* texView = LatteTextureViewLookupCache::lookup(physAddress, width, height, 1, pitch, 0, 1, 0, 1, Latte::E_GX2SURFFMT::R8_G8_B8_A8_UNORM, Latte::E_DIM::DIM_2D);
 	if (texView)
 		return texView;
-	return LatteTexture_CreateTexture(0, Latte::E_DIM::DIM_2D, physAddress, 0, Latte::E_GX2SURFFMT::R8_G8_B8_A8_UNORM, width, height, 1, pitch, 1, 0, Latte::E_HWTILEMODE::TM_LINEAR_ALIGNED, false);
+	return LatteTexture_CreateTexture(Latte::E_DIM::DIM_2D, physAddress, 0, Latte::E_GX2SURFFMT::R8_G8_B8_A8_UNORM, width, height, 1, pitch, 1, 0, Latte::E_HWTILEMODE::TM_LINEAR_ALIGNED, false);
 }
 
 void LatteHandleOSScreen_prepareTextures()
@@ -71,8 +71,7 @@ bool LatteHandleOSScreen_TV()
 	const uint32 bufferIndexTV = (bufferDisplayTV);
 	const uint32 bufferIndexDRC = bufferDisplayDRC;
 
-	g_renderer->texture_bindAndActivate(osScreenTVTex[bufferIndexTV], 0);
-	LatteTexture_ReloadData(osScreenTVTex[bufferIndexTV]->baseTexture, 0);
+	LatteTexture_ReloadData(osScreenTVTex[bufferIndexTV]->baseTexture);
 
 	// TV screen
 	LatteRenderTarget_copyToBackbuffer(osScreenTVTex[bufferIndexTV]->baseTexture->baseView, false);
@@ -94,8 +93,7 @@ bool LatteHandleOSScreen_DRC()
 
 	const uint32 bufferIndexDRC = bufferDisplayDRC;
 
-	g_renderer->texture_bindAndActivate(osScreenDRCTex[bufferIndexDRC], 0);
-	LatteTexture_ReloadData(osScreenDRCTex[bufferIndexDRC]->baseTexture, 0);
+	LatteTexture_ReloadData(osScreenDRCTex[bufferIndexDRC]->baseTexture);
 
 	// GamePad screen
 	LatteRenderTarget_copyToBackbuffer(osScreenDRCTex[bufferIndexDRC]->baseTexture->baseView, true);
@@ -142,12 +140,6 @@ int Latte_ThreadEntry()
 	case GfxVendor::AMD: 
 		LatteGPUState.glVendor = GLVENDOR_AMD;
 		break;
-	case GfxVendor::IntelLegacy: 
-		LatteGPUState.glVendor = GLVENDOR_INTEL_LEGACY; 
-		break;
-	case GfxVendor::IntelNoLegacy: 
-		LatteGPUState.glVendor = GLVENDOR_INTEL_NOLEGACY; 
-		break;
 	case GfxVendor::Intel:
 		LatteGPUState.glVendor = GLVENDOR_INTEL; 
 		break;
@@ -183,6 +175,23 @@ int Latte_ThreadEntry()
 
 	// before doing anything with game specific shaders, we need to wait for graphic packs to finish loading
 	GraphicPack2::WaitUntilReady();
+	// if legacy packs are enabled we cannot use the colorbuffer resolution optimization
+	LatteGPUState.allowFramebufferSizeOptimization = true;
+	for(auto& pack : GraphicPack2::GetActiveGraphicPacks())
+	{
+		if(pack->AllowRendertargetSizeOptimization())
+			continue;
+		for(auto& rule : pack->GetTextureRules())
+		{
+			if(rule.filter_settings.width >= 0 || rule.filter_settings.height >= 0 || rule.filter_settings.depth >= 0 ||
+				rule.overwrite_settings.width >= 0 || rule.overwrite_settings.height >= 0 || rule.overwrite_settings.depth >= 0)
+			{
+				LatteGPUState.allowFramebufferSizeOptimization = false;
+				cemuLog_log(LogType::Force, "Graphic pack \"{}\" prevents rendertarget size optimization. This warning can be ignored and is intended for graphic pack developers", pack->GetName());
+				break;
+			}
+		}
+	}
 	// load disk shader cache
     LatteShaderCache_Load();
 	// init registers
@@ -248,6 +257,7 @@ void LatteThread_Exit()
     LatteSHRC_UnloadAll();
     // close disk cache
     LatteShaderCache_Close();
+	RendererOutputShader::ShutdownStatic();
     // destroy renderer but make sure that g_renderer remains valid until the destructor has finished
 	if (g_renderer)
 	{

src/Cafe/HW/Latte/ISA/LatteReg.h

@@ -345,6 +345,11 @@ namespace Latte
 		return IsCompressedFormat((Latte::E_HWSURFFMT)((uint32)format & 0x3F));
 	}
 
+	inline bool IsMSAA(Latte::E_DIM dim)
+	{
+		return dim == E_DIM::DIM_2D_MSAA || dim == E_DIM::DIM_2D_ARRAY_MSAA;
+	}
+
 	enum GPU_LIMITS
 	{
 		NUM_VERTEX_BUFFERS = 16,