build: Release v31.2 (bug fix release)

Signed-off-by: Bo Chen <chen.bo@intel.com>

.github/dependabot.yml

@@ -16,8 +16,3 @@ updates:
   allow:
   - dependency-type: direct
   - dependency-type: indirect
-- package-ecosystem: github-actions
-  directory: "/"
-  schedule:
-    interval: daily
-  open-pull-requests-limit: 1

.github/workflows/audit.yaml

@@ -4,13 +4,12 @@ on:
     paths: 
       - '**/Cargo.toml'
       - '**/Cargo.lock'
-
 jobs:
   security_audit:
     name: Audit
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v5
-      - uses: actions-rust-lang/audit@v1
+      - uses: actions/checkout@v1
+      - uses: actions-rs/audit-check@v1
         with:
-          token: ${{ secrets.GITHUB_TOKEN }}
+          token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/build.yaml

@@ -1,11 +1,9 @@
 name: Cloud Hypervisor Build
-on: [pull_request, merge_group]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
+on: [pull_request, create]
 
 jobs:
   build:
+    if: github.event_name == 'pull_request'
     name: Build
     runs-on: ubuntu-latest
     strategy:
@@ -15,13 +13,13 @@ jobs:
           - stable
           - beta
           - nightly
-          - "1.88.0"
+          - "1.62"
         target:
           - x86_64-unknown-linux-gnu
           - x86_64-unknown-linux-musl
     steps:
       - name: Code checkout
-        uses: actions/checkout@v5
+        uses: actions/checkout@v2
         with:
           fetch-depth: 0
 
@@ -29,46 +27,29 @@ jobs:
         run: sudo apt install -y musl-tools
 
       - name: Install Rust toolchain (${{ matrix.rust }})
-        uses: dtolnay/rust-toolchain@stable
+        uses: actions-rs/toolchain@v1
         with:
           toolchain: ${{ matrix.rust }}
           target: ${{ matrix.target }}
+          override: true
 
       - name: Build (default features)
-        run: cargo rustc --locked --bin cloud-hypervisor -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
+        run: cargo rustc --locked --bin cloud-hypervisor -- -D warnings -D clippy::undocumented_unsafe_blocks
 
       - name: Build (kvm)
-        run: cargo rustc --locked --bin cloud-hypervisor --no-default-features --features "kvm"  -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
+        run: cargo rustc --locked --bin cloud-hypervisor --no-default-features --features "kvm"  -- -D warnings -D clippy::undocumented_unsafe_blocks
 
       - name: Build (default features + tdx)
-        run: cargo rustc --locked --bin cloud-hypervisor --features "tdx" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Build (default features + dbus_api)
-        run: cargo rustc --locked --bin cloud-hypervisor --features "dbus_api" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
+        run: cargo rustc --locked --bin cloud-hypervisor --features "tdx" -- -D warnings -D clippy::undocumented_unsafe_blocks
 
       - name: Build (default features + guest_debug)
-        run: cargo rustc --locked --bin cloud-hypervisor --features "guest_debug" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Build (default features + pvmemcontrol)
-        run: cargo rustc --locked --bin cloud-hypervisor --features "pvmemcontrol" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Build (default features + fw_cfg)
-        run: cargo rustc --locked --bin cloud-hypervisor --features "fw_cfg" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Build (default features + ivshmem)
-        run: cargo rustc --locked --bin cloud-hypervisor --features "ivshmem" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
+        run: cargo rustc --locked --bin cloud-hypervisor --features "guest_debug" -- -D warnings -D clippy::undocumented_unsafe_blocks
 
       - name: Build (mshv)
-        run: cargo rustc --locked --bin cloud-hypervisor --no-default-features --features "mshv"  -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Build (sev_snp)
-        run: cargo rustc --locked --bin cloud-hypervisor --no-default-features --features "sev_snp"  -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Build (igvm)
-        run: cargo rustc --locked --bin cloud-hypervisor --no-default-features --features "igvm"  -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
+        run: cargo rustc --locked --bin cloud-hypervisor --no-default-features --features "mshv"  -- -D warnings -D clippy::undocumented_unsafe_blocks
 
       - name: Build (mshv + kvm)
-        run: cargo rustc --locked --bin cloud-hypervisor --no-default-features --features "mshv,kvm"  -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
+        run: cargo rustc --locked --bin cloud-hypervisor --no-default-features --features "mshv,kvm"  -- -D warnings -D clippy::undocumented_unsafe_blocks
 
       - name: Release Build (default features)
         run: cargo build --locked --all --release --target=${{ matrix.target }}

.github/workflows/dco.yaml

@@ -1,18 +1,16 @@
 name: DCO
-on: [pull_request, merge_group]
-
+on:
+  pull_request:
 jobs:
   check:
-    name: DCO Check ("Signed-Off-By")
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v5
+    - uses: actions/checkout@v2
     - name: Set up Python 3.x
-      uses: actions/setup-python@v6
+      uses: actions/setup-python@v1
       with:
         python-version: '3.x'
     - name: Check DCO
-      if: ${{ github.event_name == 'pull_request' }}
       env:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       run: |

.github/workflows/docker-image.yaml

@@ -1,13 +1,11 @@
 name: Cloud Hypervisor's Docker image update
+
 on:
   push:
     branches: main
     paths: resources/Dockerfile
   pull_request:
     paths: resources/Dockerfile
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
 
 env:
   REGISTRY: ghcr.io
@@ -18,16 +16,16 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
-        uses: actions/checkout@v5
+        uses: actions/checkout@v2
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
+        uses: docker/setup-qemu-action@v1
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@v1
 
       - name: Login to ghcr
-        uses: docker/login-action@v3
+        uses: docker/login-action@v2
         with:
           registry: ${{ env.REGISTRY }}
           username: ${{ github.actor }}
@@ -36,17 +34,17 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@v4
         with:
           images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
           # generate Docker tags based on the following events/attributes
           tags: |
-            type=raw,value=20250815-0
+            type=raw,value={{date 'YYYYMMDD'}}-0
             type=sha
 
       - name: Build and push
         if: ${{ github.event_name == 'push' }}
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@v2
         with:
           file: ./resources/Dockerfile
           platforms: linux/amd64,linux/arm64
@@ -55,7 +53,7 @@ jobs:
 
       - name: Build only
         if: ${{ github.event_name == 'pull_request' }}
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@v2
         with:
           file: ./resources/Dockerfile
           platforms: linux/amd64,linux/arm64

.github/workflows/formatting.yaml

@@ -1,32 +0,0 @@
-name: Cloud Hypervisor Code Formatting
-on: [pull_request, merge_group]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    name: Code Formatting
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        rust:
-          - nightly
-        target:
-          - x86_64-unknown-linux-gnu
-          - aarch64-unknown-linux-musl
-    env:
-      RUSTFLAGS: -D warnings
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v5
-      - name: Install Rust toolchain (${{ matrix.rust }})
-        uses: dtolnay/rust-toolchain@stable
-        with:
-            toolchain: ${{ matrix.rust }}
-            target: ${{ matrix.target }}
-            components: rustfmt
-      - name: Formatting (rustfmt)
-        run: cargo fmt --all -- --check
-      - name: Formatting (fuzz) (rustfmt)
-        run: cargo fmt --all --manifest-path fuzz/Cargo.toml -- --check

.github/workflows/fuzz-build.yaml

@@ -1,11 +1,9 @@
 name: Cloud Hypervisor Cargo Fuzz Build
-on: [pull_request, merge_group]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
+on: [pull_request, create]
 
 jobs:
   build:
+    if: github.event_name == 'pull_request'
     name: Cargo Fuzz Build
     runs-on: ubuntu-latest
     strategy:
@@ -14,19 +12,18 @@ jobs:
           - nightly
         target:
           - x86_64-unknown-linux-gnu
-    env:
-      RUSTFLAGS: -D warnings
     steps:
       - name: Code checkout
-        uses: actions/checkout@v5
+        uses: actions/checkout@v2
       - name: Install Rust toolchain (${{ matrix.rust }})
-        uses: dtolnay/rust-toolchain@stable
+        uses: actions-rs/toolchain@v1
         with:
             toolchain: ${{ matrix.rust }}
             target: ${{ matrix.target }}
+            override: true
       - name: Install Cargo fuzz
-        run: cargo install cargo-fuzz
-      - name: Fuzz Build
+        # Temporary fix for cargo-fuzz on latest nightly: https://github.com/rust-fuzz/cargo-fuzz/issues/276
+        #run: cargo install cargo-fuzz
+        run: cargo install --git https://github.com/rust-fuzz/cargo-fuzz --rev b4df3e58f767b5cad8d1aa6753961003f56f3609
+      - name: Cargo Fuzz Build
         run: cargo fuzz build
-      - name: Fuzz Check
-        run: cargo fuzz check

.github/workflows/gitlint.yaml

@@ -1,25 +0,0 @@
-name: Commit messages check
-on:
-  pull_request:
-
-jobs:
-  gitlint:
-    name: Check commit messages
-    runs-on: ubuntu-latest
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v5
-      with:
-        ref: ${{ github.event.pull_request.head.sha }}
-        fetch-depth: 0
-    - name: Set up Python 3.10
-      uses: actions/setup-python@v6
-      with:
-        python-version: "3.10"
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install --upgrade gitlint
-    - name: Lint git commit messages
-      run: |
-        gitlint --commits origin/$GITHUB_BASE_REF..

.github/workflows/hadolint.yaml

@@ -1,25 +0,0 @@
-name: Lint Dockerfile
-on:
-  push:
-    paths:
-    - resources/Dockerfile
-  pull_request:
-    paths:
-    - resources/Dockerfile
-
-jobs:
-  hadolint:
-    name: Run Hadolint Dockerfile Linter
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v5
-
-      - name: Lint Dockerfile
-        uses: hadolint/hadolint-action@master
-        with:
-          dockerfile: ./resources/Dockerfile
-          format: tty
-          no-fail: false
-          verbose: true
-          failure-threshold: info

.github/workflows/integration-arm64.yaml

@@ -1,54 +0,0 @@
-name: Cloud Hypervisor Tests (ARM64)
-on: [pull_request, merge_group]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    timeout-minutes: 120
-    name: Tests (ARM64)
-    runs-on: bookworm-arm64
-    steps:
-      - name: Fix workspace permissions
-        run: sudo chown -R runner:runner ${GITHUB_WORKSPACE}
-      - name: Code checkout
-        uses: actions/checkout@v5
-        with:
-          fetch-depth: 0
-      - name: Run unit tests (musl)
-        run: scripts/dev_cli.sh tests --unit --libc musl
-      - name: Load openvswitch module
-        run: sudo modprobe openvswitch
-      - name: Run integration tests (musl)
-        timeout-minutes: 60
-        run: scripts/dev_cli.sh tests --integration --libc musl
-      - name: Install Azure CLI
-        if: ${{ github.event_name != 'pull_request' }}
-        run: |
-          sudo apt install -y ca-certificates curl apt-transport-https lsb-release gnupg
-          curl -sL https://packages.microsoft.com/keys/microsoft.asc | gpg --dearmor | sudo tee /etc/apt/trusted.gpg.d/microsoft.gpg > /dev/null
-          echo "deb [arch=arm64] https://packages.microsoft.com/repos/azure-cli/ bookworm main" | sudo tee /etc/apt/sources.list.d/azure-cli.list
-          sudo apt update
-          sudo apt install -y azure-cli
-      - name: Download Windows image
-        if: ${{ github.event_name != 'pull_request' }}
-        shell: bash
-        run: |
-          IMG_BASENAME=windows-11-iot-enterprise-aarch64.raw
-          IMG_PATH=$HOME/workloads/$IMG_BASENAME
-          IMG_GZ_PATH=$HOME/workloads/$IMG_BASENAME.gz
-          IMG_GZ_BLOB_NAME=windows-11-iot-enterprise-aarch64-9-min.raw.gz
-          cp "scripts/$IMG_BASENAME.sha1" "$HOME/workloads/"
-          pushd "$HOME/workloads"
-          if sha1sum "$IMG_BASENAME.sha1" --check; then
-              exit
-          fi
-          popd
-          mkdir -p "$HOME/workloads"
-          az storage blob download --container-name private-images --file "$IMG_GZ_PATH" --name "$IMG_GZ_BLOB_NAME" --connection-string "${{ secrets.CH_PRIVATE_IMAGES }}"
-          gzip -d $IMG_GZ_PATH
-      - name: Run Windows guest integration tests
-        if: ${{ github.event_name != 'pull_request' }}
-        timeout-minutes: 30
-        run: scripts/dev_cli.sh tests --integration-windows --libc musl

.github/workflows/integration-metrics.yaml

@@ -1,22 +0,0 @@
-name: Cloud Hypervisor Tests (Metrics)
-on:
-  push:
-    branches:
-      - main
-
-jobs:
-  build:
-    name: Tests (Metrics)
-    runs-on: bare-metal-9950x
-    env:
-      METRICS_PUBLISH_KEY: ${{ secrets.METRICS_PUBLISH_KEY }}
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v5
-        with:
-          fetch-depth: 0
-      - name: Run metrics tests
-        timeout-minutes: 60
-        run: scripts/dev_cli.sh tests --metrics -- -- --report-file /root/workloads/metrics.json
-      - name: Upload metrics report
-        run: 'curl -X PUT https://ch-metrics.azurewebsites.net/api/publishmetrics -H "x-functions-key: $METRICS_PUBLISH_KEY" -T ~/workloads/metrics.json'

.github/workflows/integration-rate-limiter.yaml

@@ -1,25 +0,0 @@
-name: Cloud Hypervisor Tests (Rate-Limiter)
-on: [merge_group, pull_request]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    name: Tests (Rate-Limiter)
-    runs-on: ${{ github.event_name == 'pull_request' && 'ubuntu-latest' || 'bare-metal-9950x' }}
-    env:
-      AUTH_DOWNLOAD_TOKEN: ${{ secrets.AUTH_DOWNLOAD_TOKEN }}
-    steps:
-      - name: Code checkout
-        if: ${{ github.event_name != 'pull_request' }}
-        uses: actions/checkout@v5
-        with:
-          fetch-depth: 0
-      - name: Run rate-limiter integration tests
-        if: ${{ github.event_name != 'pull_request' }}
-        timeout-minutes: 20
-        run: scripts/dev_cli.sh tests --integration-rate-limiter
-      - name: Skipping build for PR
-        if: ${{ github.event_name == 'pull_request' }}
-        run: echo "Skipping build for PR"

.github/workflows/integration-vfio.yaml

@@ -1,33 +0,0 @@
-name: Cloud Hypervisor Tests (VFIO)
-on: [merge_group, pull_request]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    name: Tests (VFIO)
-    runs-on: ${{ github.event_name == 'pull_request' && 'ubuntu-latest' || 'vfio-nvidia' }}
-    env:
-      AUTH_DOWNLOAD_TOKEN: ${{ secrets.AUTH_DOWNLOAD_TOKEN }}
-    steps:
-      - name: Fix workspace permissions
-        if: ${{ github.event_name != 'pull_request' }}
-        run: sudo chown -R runner:runner ${GITHUB_WORKSPACE}
-      - name: Code checkout
-        if: ${{ github.event_name != 'pull_request' }}
-        uses: actions/checkout@v5
-        with:
-          fetch-depth: 0
-      - name: Run VFIO integration tests
-        if: ${{ github.event_name != 'pull_request' }}
-        timeout-minutes: 15
-        run: scripts/dev_cli.sh tests --integration-vfio
-      # Most tests are failing with musl see #6790
-      # - name: Run VFIO integration tests for musl
-      #   if: ${{ github.event_name != 'pull_request' }}
-      #   timeout-minutes: 15
-      #   run: scripts/dev_cli.sh tests --integration-vfio --libc musl
-      - name: Skipping build for PR
-        if: ${{ github.event_name == 'pull_request' }}
-        run: echo "Skipping build for PR"

.github/workflows/integration-windows.yaml

@@ -1,50 +0,0 @@
-name: Cloud Hypervisor Tests (Windows Guest)
-on: [merge_group, pull_request]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    name: Tests (Windows Guest)
-    runs-on: ${{ github.event_name == 'pull_request' && 'ubuntu-latest' || 'garm-jammy-16' }}
-    steps:
-      - name: Code checkout
-        if: ${{ github.event_name != 'pull_request' }}
-        uses: actions/checkout@v5
-        with:
-          fetch-depth: 0
-      - name: Install Docker
-        if: ${{ github.event_name != 'pull_request' }}
-        run: |
-          sudo apt-get update
-          sudo apt-get -y install ca-certificates curl gnupg
-          curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg
-          sudo chmod a+r /usr/share/keyrings/docker-archive-keyring.gpg
-          echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
-          sudo apt-get update
-          sudo apt install -y docker-ce docker-ce-cli
-      - name: Install Azure CLI
-        if: ${{ github.event_name != 'pull_request' }}
-        run: |
-          sudo apt install -y ca-certificates curl apt-transport-https lsb-release gnupg
-          curl -sL https://packages.microsoft.com/keys/microsoft.asc | gpg --dearmor | sudo tee /etc/apt/trusted.gpg.d/microsoft.gpg > /dev/null
-          echo "deb [arch=amd64] https://packages.microsoft.com/repos/azure-cli/ jammy main" | sudo tee /etc/apt/sources.list.d/azure-cli.list
-          sudo apt update
-          sudo apt install -y azure-cli
-      - name: Download Windows image
-        if: ${{ github.event_name != 'pull_request' }}
-        run: |
-          mkdir $HOME/workloads
-          az storage blob download --container-name private-images --file "$HOME/workloads/windows-server-2022-amd64-2.raw" --name windows-server-2022-amd64-2.raw --connection-string "${{ secrets.CH_PRIVATE_IMAGES }}"
-      - name: Run Windows guest integration tests
-        if: ${{ github.event_name != 'pull_request' }}
-        timeout-minutes: 15
-        run: scripts/dev_cli.sh tests --integration-windows
-      - name: Run Windows guest integration tests for musl
-        if: ${{ github.event_name != 'pull_request' }}
-        timeout-minutes: 15
-        run: scripts/dev_cli.sh tests --integration-windows --libc musl
-      - name: Skipping build for PR
-        if: ${{ github.event_name == 'pull_request' }}
-        run: echo "Skipping build for PR"

.github/workflows/integration-x86-64.yaml

@@ -1,52 +0,0 @@
-name: Cloud Hypervisor Tests (x86-64)
-on: [pull_request, merge_group]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    timeout-minutes: 60
-    strategy:
-      fail-fast: false
-      matrix:
-        runner: ['garm-jammy', "garm-jammy-amd"]
-        libc: ["musl", 'gnu']
-    name: Tests (x86-64)
-    runs-on: ${{ github.event_name == 'pull_request' && !(matrix.runner == 'garm-jammy' && matrix.libc == 'gnu') && 'ubuntu-latest' || format('{0}-16', matrix.runner) }}
-    steps:
-      - name: Code checkout
-        if: ${{ github.event_name != 'pull_request' || (matrix.runner == 'garm-jammy' && matrix.libc == 'gnu') }}
-        uses: actions/checkout@v5
-        with:
-          fetch-depth: 0
-      - name: Install Docker
-        if: ${{ github.event_name != 'pull_request' || (matrix.runner == 'garm-jammy' && matrix.libc == 'gnu') }}
-        run: |
-          sudo apt-get update
-          sudo apt-get -y install ca-certificates curl gnupg
-          curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg
-          sudo chmod a+r /usr/share/keyrings/docker-archive-keyring.gpg
-          echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
-          sudo apt-get update
-          sudo apt install -y docker-ce docker-ce-cli
-      - name: Prepare for VDPA
-        if: ${{ github.event_name != 'pull_request' || (matrix.runner == 'garm-jammy' && matrix.libc == 'gnu') }}
-        run: scripts/prepare_vdpa.sh
-      - name: Run unit tests
-        if: ${{ github.event_name != 'pull_request' || (matrix.runner == 'garm-jammy' && matrix.libc == 'gnu') }}
-        run: scripts/dev_cli.sh tests --unit --libc ${{ matrix.libc }}
-      - name: Load openvswitch module
-        if: ${{ github.event_name != 'pull_request' || (matrix.runner == 'garm-jammy' && matrix.libc == 'gnu') }}
-        run: sudo modprobe openvswitch
-      - name: Run integration tests
-        if: ${{ github.event_name != 'pull_request' || (matrix.runner == 'garm-jammy' && matrix.libc == 'gnu') }}
-        timeout-minutes: 40
-        run: scripts/dev_cli.sh tests --integration --libc ${{ matrix.libc }}
-      - name: Run live-migration integration tests
-        if: ${{ github.event_name != 'pull_request' || (matrix.runner == 'garm-jammy' && matrix.libc == 'gnu') }}
-        timeout-minutes: 20
-        run: scripts/dev_cli.sh tests --integration-live-migration --libc ${{ matrix.libc }}
-      - name: Skipping build for PR
-        if: ${{ github.event_name == 'pull_request' && matrix.runner != 'garm-jammy' && matrix.libc != 'gnu' }}
-        run: echo "Skipping build for PR"

.github/workflows/lychee.yaml

@@ -1,45 +0,0 @@
-name: Link Check (lychee)
-on: pull_request
-jobs:
-  link_check:
-    name: Link Check
-    runs-on: ubuntu-latest
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v5
-        with:
-          # Fetch the entire history so git diff can compare against the base branch
-          fetch-depth: 0
-      - name: Get changed files in PR
-        id: changed-files
-        uses: tj-actions/changed-files@v46 # Using a dedicated action for robustness
-        with:
-          # Compare the HEAD of the PR with the merge-base (where the PR branches off)
-          base_sha: ${{ github.event.pull_request.base.sha }}
-
-      # NEW STEP: Print all changed-files outputs for verification
-      - name: Verify Changed Files
-        run: |
-          echo "--- tj-actions/changed-files Outputs ---"
-          echo "any_changed: ${{ steps.changed-files.outputs.any_changed }}"
-          echo "all_changed_files: ${{ steps.changed-files.outputs.all_changed_files }}"
-          echo "added_files: ${{ steps.changed-files.outputs.added_files }}"
-          echo "modified_files: ${{ steps.changed-files.outputs.modified_files }}"
-          echo "deleted_files: ${{ steps.changed-files.outputs.deleted_files }}"
-          echo "renamed_files: ${{ steps.changed-files.outputs.renamed_files }}"
-          echo "----------------------------------------"
-          # This will also show if the all_changed_files string is empty or not
-          if [ -n "${{ steps.changed-files.outputs.all_changed_files }}" ]; then
-            echo "Detected changes: all_changed_files output is NOT empty."
-          else
-            echo "No changes detected: all_changed_files output IS empty."
-          fi
-      - name: Link Availability Check (Diff Only)
-        # MODIFIED: Only run lychee if the 'all_changed_files' output is not an empty string
-        if: ${{ steps.changed-files.outputs.all_changed_files != '' }}
-        uses: lycheeverse/lychee-action@master
-        with:
-          # Pass the space-separated list of changed files to lychee
-          args: --verbose --config .lychee.toml ${{ steps.changed-files.outputs.all_changed_files }}
-          failIfEmpty: false
-          fail: true

.github/workflows/openapi.yaml

@@ -1,14 +0,0 @@
-name: Cloud Hypervisor OpenAPI Validation
-on: [pull_request, merge_group]
-
-jobs:
-  Validate:
-    runs-on: ubuntu-latest
-    container: openapitools/openapi-generator-cli
-    steps:
-    - uses: actions/checkout@v5
-    - name: Validate OpenAPI
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      run: |
-        /usr/local/bin/docker-entrypoint.sh validate -i vmm/src/api/openapi/cloud-hypervisor.yaml

.github/workflows/package-consistency.yaml

@@ -1,32 +0,0 @@
-name: Cloud Hypervisor Consistency
-on: [pull_request, merge_group]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    name: Rust VMM Consistency Check
-    runs-on: ubuntu-latest
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v5
-        with:
-          fetch-depth: 0
-
-      - name: Install dependencies
-        run: sudo apt install -y python3
-
-      - name: Install Rust toolchain stable
-        uses: dtolnay/rust-toolchain@stable
-        with:
-          toolchain: stable
-
-      - name: Check Rust VMM Package Consistency of root Workspace
-        run: python3 scripts/package-consistency-check.py github.com/rust-vmm
-
-      - name: Check Rust VMM Package Consistency of fuzz Workspace
-        run: |
-          pushd fuzz
-          python3 ../scripts/package-consistency-check.py github.com/rust-vmm
-          popd

.github/workflows/preview-riscv64-build.yaml

@@ -1,30 +0,0 @@
-name: Cloud Hypervisor RISC-V 64-bit kvm build Preview
-on: [pull_request, merge_group]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    name: Cargo
-    runs-on: riscv64-qemu-host
-    strategy:
-      fail-fast: false
-
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v5
-        with:
-          fetch-depth: 0
-
-      - name: Install Rust toolchain
-        run: /opt/scripts/exec-in-qemu.sh rustup default 1.88.0
-
-      - name: Build test (kvm)
-        run: /opt/scripts/exec-in-qemu.sh cargo rustc --locked --no-default-features --features "kvm"
-
-      - name: Clippy test (kvm)
-        run: /opt/scripts/exec-in-qemu.sh cargo clippy --locked --no-default-features --features "kvm"
-
-      - name: Check no files were modified
-        run: test -z "$(git status --porcelain)"

.github/workflows/preview-riscv64-modules.yaml

@@ -1,39 +0,0 @@
-name: Cloud Hypervisor RISC-V 64-bit Preview
-on: [pull_request, merge_group]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    name: Cargo
-    runs-on: riscv64-qemu-host
-    strategy:
-      fail-fast: false
-      matrix:
-        module:
-          - hypervisor
-          - arch
-          - vm-allocator
-          - devices
-
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v5
-        with:
-          fetch-depth: 0
-
-      - name: Install Rust toolchain
-        run: /opt/scripts/exec-in-qemu.sh rustup default 1.88.0
-
-      - name: Build ${{ matrix.module }} Module (kvm)
-        run: /opt/scripts/exec-in-qemu.sh cargo rustc --locked -p ${{ matrix.module }} --no-default-features --features "kvm" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Clippy ${{ matrix.module }} Module (kvm)
-        run: /opt/scripts/exec-in-qemu.sh cargo clippy --locked -p ${{ matrix.module }} --no-default-features --features "kvm" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Test ${{ matrix.module }} Module (kvm)
-        run: /opt/scripts/exec-in-qemu.sh cargo test --locked -p ${{ matrix.module }} --no-default-features --features "kvm"
-
-      - name: Check no files were modified
-        run: test -z "$(git status --porcelain)"

.github/workflows/quality.yaml

@@ -1,19 +1,16 @@
 name: Cloud Hypervisor Quality Checks
-on: [pull_request, merge_group]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
+on: [pull_request, create]
 
 jobs:
   build:
-    name: Quality (clippy)
+    if: github.event_name == 'pull_request'
+    name: Quality (clippy, rustfmt)
     runs-on: ubuntu-latest
     continue-on-error: ${{ matrix.experimental }}
     strategy:
       fail-fast: false
       matrix:
         rust:
-          - beta
           - stable
         target:
           - aarch64-unknown-linux-gnu
@@ -21,15 +18,23 @@ jobs:
           - x86_64-unknown-linux-gnu
           - x86_64-unknown-linux-musl
 
+        experimental: [false]
         include:
           - rust: beta
+            target: aarch64-unknown-linux-gnu
+            experimental: true
+          - rust: beta
+            target: aarch64-unknown-linux-musl
+            experimental: true
+          - rust: beta
+            target: x86_64-unknown-linux-gnu
+            experimental: true
+          - rust: beta
+            target: x86_64-unknown-linux-musl
             experimental: true
-          - rust: stable
-            experimental: false
-
     steps:
       - name: Code checkout
-        uses: actions/checkout@v5
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0
 
@@ -39,132 +44,70 @@ jobs:
           toolchain: ${{ matrix.rust }}
           target: ${{ matrix.target }}
           override: true
-          components: clippy
+          components: rustfmt, clippy
 
-      - name: Bisectability Check (default features)
-        if: ${{ github.event_name == 'pull_request' && matrix.target == 'x86_64-unknown-linux-gnu' }}
+      - name: Debug Check (default features)
+        if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
         run: |
           set -e
           commits=$(git rev-list origin/${{ github.base_ref }}..${{ github.sha }})
           for commit in $commits; do git checkout $commit; cargo check --tests --examples --all --target=${{ matrix.target }}; done
           git checkout ${{ github.sha }}
 
+      - name: Formatting (rustfmt)
+        run: cargo fmt -- --check
+
       - name: Clippy (kvm)
-        uses: houseabsolute/actions-rust-cross@v1
-        with:
-          command: clippy
-          cross-version: 3e0957637b49b1bbced23ad909170650c5b70635
-          toolchain: ${{ matrix.rust }}
-          target: ${{ matrix.target }}
-          args: --locked --all --all-targets --no-default-features --tests --examples --features "kvm" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Clippy (mshv)
-        uses: houseabsolute/actions-rust-cross@v1
-        with:
-          command: clippy
-          cross-version: 3e0957637b49b1bbced23ad909170650c5b70635
-          toolchain: ${{ matrix.rust }}
-          target: ${{ matrix.target }}
-          args: --locked --all --all-targets --no-default-features --tests --examples --features "mshv" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Clippy (mshv + kvm)
-        uses: houseabsolute/actions-rust-cross@v1
-        with:
-          command: clippy
-          cross-version: 3e0957637b49b1bbced23ad909170650c5b70635
-          toolchain: ${{ matrix.rust }}
-          target: ${{ matrix.target }}
-          args: --locked --all --all-targets --no-default-features --tests --examples --features "mshv,kvm" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Clippy (default features)
-        uses: houseabsolute/actions-rust-cross@v1
-        with:
-          command: clippy
-          cross-version: 3e0957637b49b1bbced23ad909170650c5b70635
-          toolchain: ${{ matrix.rust }}
-          target: ${{ matrix.target }}
-          args: --locked --all --all-targets --tests --examples -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Clippy (default features + guest_debug)
-        uses: houseabsolute/actions-rust-cross@v1
-        with:
-          command: clippy
-          cross-version: 3e0957637b49b1bbced23ad909170650c5b70635
-          toolchain: ${{ matrix.rust }}
-          target: ${{ matrix.target }}
-          args: --locked --all --all-targets --tests --examples --features "guest_debug" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Clippy (default features + pvmemcontrol)
-        uses: houseabsolute/actions-rust-cross@v1
-        with:
-          command: clippy
-          cross-version: 3e0957637b49b1bbced23ad909170650c5b70635
-          toolchain: ${{ matrix.rust }}
-          target: ${{ matrix.target }}
-          args: --locked --all --all-targets --tests --examples --features "pvmemcontrol" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Clippy (default features + tracing)
-        uses: houseabsolute/actions-rust-cross@v1
-        with:
-          command: clippy
-          cross-version: 3e0957637b49b1bbced23ad909170650c5b70635
-          toolchain: ${{ matrix.rust }}
-          target: ${{ matrix.target }}
-          args: --locked --all --all-targets --tests --examples --features "tracing" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-      - name: Clippy (default features + fw_cfg)
         uses: actions-rs/cargo@v1
         with:
           use-cross: ${{ matrix.target != 'x86_64-unknown-linux-gnu' }}
           command: clippy
-          args: --target=${{ matrix.target }} --locked --all --all-targets --tests --examples --features "fw_cfg" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
+          args: --target=${{ matrix.target }} --locked --all --all-targets --no-default-features --tests --examples --features "kvm" -- -D warnings -D clippy::undocumented_unsafe_blocks
 
-      - name: Clippy (default features + ivshmem)
-        uses: houseabsolute/actions-rust-cross@v1
+      - name: Clippy (default features)
+        uses: actions-rs/cargo@v1
         with:
+          use-cross: ${{ matrix.target != 'x86_64-unknown-linux-gnu' }}
           command: clippy
-          cross-version: 3e0957637b49b1bbced23ad909170650c5b70635
-          toolchain: ${{ matrix.rust }}
-          target: ${{ matrix.target }}
-          args: --locked --all --all-targets --tests --examples --features "ivshmem" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
+          args: --target=${{ matrix.target }} --locked --all --all-targets --tests --examples -- -D warnings -D clippy::undocumented_unsafe_blocks
 
-      - name: Clippy (sev_snp)
+      - name: Clippy (default features + guest_debug)
+        uses: actions-rs/cargo@v1
+        with:
+          use-cross: ${{ matrix.target != 'x86_64-unknown-linux-gnu' }}
+          command: clippy
+          args: --target=${{ matrix.target }} --locked --all --all-targets --tests --examples --features "guest_debug" -- -D warnings -D clippy::undocumented_unsafe_blocks
+
+      - name: Clippy (default features + tracing)
+        uses: actions-rs/cargo@v1
+        with:
+          use-cross: ${{ matrix.target != 'x86_64-unknown-linux-gnu' }}
+          command: clippy
+          args: --target=${{ matrix.target }} --locked --all --all-targets --tests --examples --features "tracing" -- -D warnings -D clippy::undocumented_unsafe_blocks
+
+      - name: Clippy (mshv)
         if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
-        uses: houseabsolute/actions-rust-cross@v1
+        uses: actions-rs/cargo@v1
         with:
+          use-cross: ${{ matrix.target != 'x86_64-unknown-linux-gnu' }}
           command: clippy
-          cross-version: 3e0957637b49b1bbced23ad909170650c5b70635
-          toolchain: ${{ matrix.rust }}
-          target: ${{ matrix.target }}
-          args: --locked --all --all-targets --no-default-features --tests --examples --features "sev_snp" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
+          args: --target=${{ matrix.target }} --locked --all --all-targets --no-default-features --tests --examples --features "mshv" -- -D warnings -D clippy::undocumented_unsafe_blocks
 
-      - name: Clippy (igvm)
+      - name: Clippy (mshv + kvm)
         if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
-        uses: houseabsolute/actions-rust-cross@v1
+        uses: actions-rs/cargo@v1
         with:
+          use-cross: ${{ matrix.target != 'x86_64-unknown-linux-gnu' }}
           command: clippy
-          cross-version: 3e0957637b49b1bbced23ad909170650c5b70635
-          toolchain: ${{ matrix.rust }}
-          target: ${{ matrix.target }}
-          args: --locked --all --all-targets --no-default-features --tests --examples --features "igvm" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
+          args: --target=${{ matrix.target }} --locked --all --all-targets --no-default-features --tests --examples --features "mshv,kvm" -- -D warnings -D clippy::undocumented_unsafe_blocks
 
       - name: Clippy (kvm + tdx)
         if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
-        uses: houseabsolute/actions-rust-cross@v1
+        uses: actions-rs/cargo@v1
         with:
+          use-cross: ${{ matrix.target != 'x86_64-unknown-linux-gnu' }}
           command: clippy
-          cross-version: 3e0957637b49b1bbced23ad909170650c5b70635
-          toolchain: ${{ matrix.rust }}
-          target: ${{ matrix.target }}
-          args: --locked --all --all-targets --no-default-features --tests --examples --features "tdx,kvm" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
+          args: --target=${{ matrix.target }} --locked --all --all-targets --no-default-features --tests --examples --features "tdx,kvm" -- -D warnings -D clippy::undocumented_unsafe_blocks
 
       - name: Check build did not modify any files
         run: test -z "$(git status --porcelain)"
-
-  typos:
-    if: github.event_name == 'pull_request'
-    name: Typos / Spellcheck
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v5
-      # Executes "typos ."
-      - uses: crate-ci/typos@v1.36.2

.github/workflows/release.yaml

@@ -1,69 +1,134 @@
 name: Cloud Hypervisor Release
-on: [create, merge_group]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.event_name }}
-  cancel-in-progress: true
-env:
-  GITHUB_TOKEN: ${{ github.token }}
+on: [pull_request, create]
 
 jobs:
   release:
-    if: (github.event_name == 'create' && github.event.ref_type == 'tag') || github.event_name == 'merge_group'
-    name: Release ${{ matrix.platform.target }}
-    strategy:
-      fail-fast: false
-      matrix:
-        platform:
-        - target: x86_64-unknown-linux-gnu
-          args: --all --release --features mshv
-          name_ch: cloud-hypervisor
-          name_ch_remote: ch-remote
-        - target: x86_64-unknown-linux-musl
-          args: --all --release --features mshv
-          name_ch: cloud-hypervisor-static
-          name_ch_remote: ch-remote-static
-        - target: aarch64-unknown-linux-musl
-          args:  --all --release
-          name_ch: cloud-hypervisor-static-aarch64
-          name_ch_remote: ch-remote-static-aarch64
+    if: (github.event_name == 'create' && github.event.ref_type == 'tag') || github.event_name == 'pull_request'
+    name: Release
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
-        uses: actions/checkout@v5
+        uses: actions/checkout@v2
       - name: Install musl-gcc
-        if: contains(matrix.platform.target, 'musl')
         run: sudo apt install -y musl-tools
       - name: Create release directory
-        if: |
-          github.event_name == 'create' && github.event.ref_type == 'tag' &&
-          matrix.platform.target == 'x86_64-unknown-linux-gnu'
         run: rsync -rv --exclude=.git . ../cloud-hypervisor-${{ github.event.ref }}
-      - name: Build ${{ matrix.platform.target }}
-        uses: houseabsolute/actions-rust-cross@v1
+      - name: Install Rust toolchain (x86_64-unknown-linux-gnu)
+        uses: actions-rs/toolchain@v1
         with:
+          toolchain: "1.67.1"
+          target: x86_64-unknown-linux-gnu
+      - name: Install Rust toolchain (x86_64-unknown-linux-musl)
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: "1.67.1"
+          target: x86_64-unknown-linux-musl
+      - name: Build
+        uses: actions-rs/cargo@v1
+        with:
+          toolchain: "1.67.1"
           command: build
-          target: ${{ matrix.platform.target }}
-          args: ${{ matrix.platform.args  }}
-          strip: true
-          toolchain: "1.88.0"
-      - name: Copy Release Binaries
-        if: github.event_name == 'create' && github.event.ref_type == 'tag'
-        shell: bash
-        run: |
-          cp target/${{ matrix.platform.target }}/release/cloud-hypervisor ./${{ matrix.platform.name_ch }}
-          cp target/${{ matrix.platform.target }}/release/ch-remote ./${{ matrix.platform.name_ch_remote }}
-      - name: Upload Release Artifacts
-        if: github.event_name == 'create' && github.event.ref_type == 'tag'
-        uses: actions/upload-artifact@v4
+          args: --all --release --no-default-features --features "kvm,mshv" --target=x86_64-unknown-linux-gnu
+      - name: Static Build
+        uses: actions-rs/cargo@v1
         with:
-          name: Artifacts for ${{ matrix.platform.target }}
-          path: |
-            ./${{ matrix.platform.name_ch }}
-            ./${{ matrix.platform.name_ch_remote }}
+          toolchain: "1.67.1"
+          command: build
+          args: --all --release --no-default-features --features "kvm,mshv" --target=x86_64-unknown-linux-musl
+      - name: Install Rust toolchain (aarch64-unknown-linux-musl)
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: "1.67.1"
+          target: aarch64-unknown-linux-musl
+          override: true
+      - name: Create Release
+        if: github.event_name == 'create' && github.event.ref_type == 'tag'
+        id: create_release
+        uses: actions/create-release@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          tag_name: ${{ github.ref }}
+          release_name: ${{ github.ref }}
+          draft: true
+          prerelease: true
+      - name: Upload cloud-hypervisor
+        if: github.event_name == 'create' && github.event.ref_type == 'tag'
+        id: upload-release-cloud-hypervisor
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ steps.create_release.outputs.upload_url }}
+          asset_path: target/x86_64-unknown-linux-gnu/release/cloud-hypervisor
+          asset_name: cloud-hypervisor
+          asset_content_type: application/octet-stream
+      - name: Upload static cloud-hypervisor
+        if: github.event_name == 'create' && github.event.ref_type == 'tag'
+        id: upload-release-static-cloud-hypervisor
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ steps.create_release.outputs.upload_url }}
+          asset_path: target/x86_64-unknown-linux-musl/release/cloud-hypervisor
+          asset_name: cloud-hypervisor-static
+          asset_content_type: application/octet-stream
+      - name: Upload ch-remote
+        if: github.event_name == 'create' && github.event.ref_type == 'tag'
+        id: upload-release-ch-remote
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ steps.create_release.outputs.upload_url }}
+          asset_path: target/x86_64-unknown-linux-gnu/release/ch-remote
+          asset_name: ch-remote
+          asset_content_type: application/octet-stream
+      - name: Upload static-ch-remote
+        if: github.event_name == 'create' && github.event.ref_type == 'tag'
+        id: upload-release-static-ch-remote
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ steps.create_release.outputs.upload_url }}
+          asset_path: target/x86_64-unknown-linux-musl/release/ch-remote
+          asset_name: ch-remote-static
+          asset_content_type: application/octet-stream
+      - name: Clean build tree ahead of cross build
+        uses: actions-rs/cargo@v1
+        with:
+          command: clean
+      - name: Static Build (AArch64)
+        uses: actions-rs/cargo@v1
+        with:
+          use-cross: true
+          command: build
+          args: --all --release --target=aarch64-unknown-linux-musl
+      - name: Upload static AArch64 cloud-hypervisor
+        if: github.event_name == 'create' && github.event.ref_type == 'tag'
+        id: upload-release-static-aarch64-cloud-hypervisor
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ steps.create_release.outputs.upload_url }}
+          asset_path: target/aarch64-unknown-linux-musl/release/cloud-hypervisor
+          asset_name: cloud-hypervisor-static-aarch64
+          asset_content_type: application/octet-stream
+      - name: Upload static AArch64 ch-remote
+        if: github.event_name == 'create' && github.event.ref_type == 'tag'
+        id: upload-release-static-aarch64-ch-remote
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ steps.create_release.outputs.upload_url }}
+          asset_path: target/aarch64-unknown-linux-musl/release/ch-remote
+          asset_name: ch-remote-static-aarch64
+          asset_content_type: application/octet-stream
       - name: Vendor
-        if: |
-          github.event_name == 'create' && github.event.ref_type == 'tag' &&
-          matrix.platform.target == 'x86_64-unknown-linux-gnu'
         working-directory: ../cloud-hypervisor-${{ github.event.ref }}
         run: |
           mkdir ../vendor-cargo-home
@@ -71,25 +136,16 @@ jobs:
           mkdir .cargo
           cargo vendor > .cargo/config.toml
       - name: Create vendored source archive
-        if: |
-          github.event_name == 'create' && github.event.ref_type == 'tag' &&
-          matrix.platform.target == 'x86_64-unknown-linux-gnu'
-        run: tar cJf cloud-hypervisor-${{ github.event.ref }}.tar.xz ../cloud-hypervisor-${{ github.event.ref }}
+        working-directory: ../
+        run: tar cJf cloud-hypervisor-${{ github.event.ref }}.tar.xz cloud-hypervisor-${{ github.event.ref }}
       - name: Upload cloud-hypervisor vendored source archive
-        if: |
-          github.event_name == 'create' && github.event.ref_type == 'tag' &&
-          matrix.platform.target == 'x86_64-unknown-linux-gnu'
-        id: upload-release-cloud-hypervisor-vendored-sources
-        uses: actions/upload-artifact@v4
-        with:
-          path: cloud-hypervisor-${{ github.event.ref }}.tar.xz
-          name: cloud-hypervisor-${{ github.event.ref }}.tar.xz
-      - name: Create GitHub Release
         if: github.event_name == 'create' && github.event.ref_type == 'tag'
-        uses: softprops/action-gh-release@v2
+        id: upload-release-cloud-hypervisor-vendored-sources
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:
-          draft: true
-          files: |
-            ./${{ matrix.platform.name_ch }}
-            ./${{ matrix.platform.name_ch_remote }}
-            ./cloud-hypervisor-${{ github.event.ref }}.tar.xz
+          upload_url: ${{ steps.create_release.outputs.upload_url }}
+          asset_path: ../cloud-hypervisor-${{ github.event.ref }}.tar.xz
+          asset_name: cloud-hypervisor-${{ github.event.ref }}.tar.xz
+          asset_content_type: application/x-xz

.github/workflows/reuse.yaml

@@ -1,12 +0,0 @@
-name: REUSE Compliance Check
-
-on: [push, pull_request]
-
-jobs:
-  reuse:
-    name: REUSE Compliance Check
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v5
-    - name: REUSE Compliance Check
-      uses: fsfe/reuse-action@v5

.github/workflows/shlint.yaml

@@ -1,20 +0,0 @@
-name: Shell scripts check
-on:
-  pull_request:
-  merge_group:
-  push:
-    branches:
-      - main
-
-jobs:
-  sh-checker:
-    name: Check shell scripts
-    runs-on: ubuntu-latest
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v5
-    - name: Run the shell script checkers
-      uses: luizm/action-sh-checker@master
-      env:
-        SHFMT_OPTS: -i 4 -d
-        SHELLCHECK_OPTS: -x --source-path scripts

.github/workflows/taplo.yaml

@@ -1,21 +0,0 @@
-name: Cargo.toml Formatting (taplo)
-on:
-  pull_request:
-    paths: 
-      - '**/Cargo.toml'
-
-jobs:
-  cargo_toml_format:
-    name: Cargo.toml Formatting
-    runs-on: ubuntu-latest
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v5
-      - name: Install Rust toolchain
-        uses: dtolnay/rust-toolchain@stable
-      - name: Install build dependencies
-        run: sudo apt-get update && sudo apt-get -yqq install build-essential libssl-dev
-      - name: Install taplo
-        run: cargo install taplo-cli --locked
-      - name: Check formatting
-        run: taplo fmt --check

.gitignore

@@ -6,5 +6,3 @@
 **/rusty-tags.vi
 /rpm/SOURCES
 /.vscode
-/vendor
-__pycache__

.gitlint

@@ -1,13 +0,0 @@
-[general]
-extra-path=scripts/gitlint/rules
-regex-style-search=true
-ignore=body-max-line-length
-
-[ignore-by-author-name]
-regex=dependabot
-ignore=all
-
-# default 72
-[title-max-length]
-line-length=72
-

.lychee.toml

@@ -1,27 +0,0 @@
-verbose = "info"
-
-exclude = [
-    # Availability of links below should be manually verified.
-    # Page for intel TDX support, returns 403 while querying.
-    '^https://www.intel.com/content/www/us/en/developer/tools/trust-domain-extensions/overview.html',
-    # Page for TPM, returns 403 while querying.
-    '^https://trustedcomputinggroup.org/wp-content/uploads/PC-Client-Specific-Platform-TPM-Profile-for-TPM-2p0-v1p05p_r14_pub.pdf',
-
-    # GitHub user smibarber referenced in `CREDITS.md` no longer exist
-    '^https://github.com/smibarber',
-
-    # OSDev has added bot protection and accesses my result in 403 Forbidden.
-    '^https://wiki.osdev.org',
-    # Exclude all pages with $ in the URL since $XXX is a variable
-    "\\$.*",
-    # Exclude local files
-    "file://.*",
-]
-
-# Exclude loopback addresses
-exclude_loopback = true
-
-
-max_retries = 3
-
-retry_wait_time = 5

.reuse/dep5

@@ -1,12 +0,0 @@
-Format: https://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
-Upstream-Name: cloud-hypervisor
-Upstream-Contact:  <>
-Source: https://www.cloudhypervisor.org
-
-Files: docs/*.md *.md
-Copyright: 2024
-License: CC-BY-4.0
-
-Files: scripts/* test_data/* *.toml .git* fuzz/Cargo.lock fuzz/.gitignore resources/linux-config-* vmm/src/api/openapi/cloud-hypervisor.yaml CODEOWNERS Cargo.lock
-Copyright: 2024
-License: Apache-2.0

.rustfmt.toml

@@ -1,4 +1 @@
-edition = "2024"
-group_imports="StdExternalCrate"
-imports_granularity="Module"
-
+edition = "2021"

.taplo.toml

@@ -1,5 +0,0 @@
-include = ["**/Cargo.toml"]
-
-[formatting]
-reorder_arrays = true
-reorder_keys = true

.typos.toml

@@ -1,24 +0,0 @@
-# Configuration for https://github.com/crate-ci/typos
-
-[files]
-extend-exclude = [
-    "hypervisor/src/kvm/x86_64/mod.rs",
-    "resources/linux-config-*",
-]
-
-[default.extend-words]
-CLASSE = "CLASSE"
-Dake = "Dake"
-EXTINT = "EXTINT"
-INOUT = "INOUT"
-SME = "SME" # Secure Memory Encryption
-THR = "THR" # Transmitter Holding Register
-TRANSLATER = "TRANSLATER"
-ba = "ba"
-conectix = "conectix"
-liness = "liness"
-outout = "outout"
-
-[default.extend-identifiers]
-fo = "fo"
-fpr = "fpr"

CONTRIBUTING.md

@@ -5,7 +5,7 @@ License](https://opensource.org/licenses/Apache-2.0) and the [BSD 3
 Clause](https://opensource.org/licenses/BSD-3-Clause) license. Individual files
 contain details of their licensing and changes to that file are under the same
 license unless the contribution changes the license of the file. When importing
-code from a third party project (e.g. Firecracker or crosvm) please respect the
+code from a third party project (e.g. Firecracker or CrosVM) please respect the
 license of those projects.
 
 New code should be under the [Apache v2
@@ -13,7 +13,7 @@ License](https://opensource.org/licenses/Apache-2.0).
 
 ## Coding Style
 
-We follow the [Rust Style](https://github.com/rust-lang/rust/tree/HEAD/src/doc/style-guide/src)
+We follow the [Rust Style](https://github.com/rust-dev-tools/fmt-rfcs/blob/master/guide/guide.md)
 convention and enforce it through the Continuous Integration (CI) process calling into `rustfmt`
 for each submitted Pull Request (PR).
 
@@ -36,7 +36,7 @@ commit you make.
 
 ## Certificate of Origin
 
-In order to get a clear contribution chain of trust we use the [signed-off-by language](https://web.archive.org/web/20230406041855/https://01.org/community/signed-process)
+In order to get a clear contribution chain of trust we use the [signed-off-by language](https://01.org/community/signed-process)
 used by the Linux kernel project.
 
 ## Patch format
@@ -79,12 +79,12 @@ you want to merge your changes to `cloud-hypervisor`:
 
 1. Fork the [cloud-hypervisor](https://github.com/cloud-hypervisor/cloud-hypervisor) project
    into your github organization.
-1. Within your fork, create a branch for your contribution.
-1. [Create a pull request](https://help.github.com/articles/creating-a-pull-request-from-a-fork/)
+2. Within your fork, create a branch for your contribution.
+3. [Create a pull request](https://help.github.com/articles/creating-a-pull-request-from-a-fork/)
    against the main branch of the Cloud Hypervisor repository.
-1. To update your pull request amend existing commits whenever applicable and
+4. To update your pull request amend existing commits whenever applicable and
    then push the new changes to your pull request branch.
-1. Once the pull request is approved it can be integrated.
+5. Once the pull request is approved it can be integrated.
 
 ## Issue tracking
 
@@ -112,15 +112,5 @@ Fixes #88
 Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
 ```
 
-Then, after the corresponding PR is merged, GitHub will automatically close that issue when parsing the
+Then, after the corresponding PR is merged, Github will automatically close that issue when parsing the
 [commit message](https://help.github.com/articles/closing-issues-via-commit-messages/).
-
-## AI Generated Code
-
-Our policy is to decline any contributions known to contain contents
-generated or derived from using Large Language Models (LLMs). This
-includes ChatGPT, Gemini, Claude, Copilot and similar tools.
-
-The goal is to avoid ambiguity in license compliance and optimize the
-use of limited project resources, especially for code review and
-maintenance. This policy can be revisited as LLMs evolve and mature.

Cargo.toml

@@ -1,155 +1,102 @@
 [package]
-authors = ["The Cloud Hypervisor Authors"]
-build = "build.rs"
-default-run = "cloud-hypervisor"
-description = "Open source Virtual Machine Monitor (VMM) that runs on top of KVM & MSHV"
-edition = "2024"
-homepage = "https://github.com/cloud-hypervisor/cloud-hypervisor"
-license = "Apache-2.0 AND BSD-3-Clause"
 name = "cloud-hypervisor"
-version = "48.0.0"
+version = "31.2.0"
+authors = ["The Cloud Hypervisor Authors"]
+edition = "2021"
+default-run = "cloud-hypervisor"
+build = "build.rs"
+license = "LICENSE-APACHE & LICENSE-BSD-3-Clause"
+description = "Open source Virtual Machine Monitor (VMM) that runs on top of KVM"
+homepage = "https://github.com/cloud-hypervisor/cloud-hypervisor"
 # Minimum buildable version:
 # Keep in sync with version in .github/workflows/build.yaml
 # Policy on MSRV (see #4318):
-# Can only be bumped if satisfying any of the following:
+# Can only be bumped by:
 # a.) A dependency requires it,
 # b.) If we want to use a new feature and that MSRV is at least 6 months old,
 # c.) There is a security issue that is addressed by the toolchain update.
-rust-version = "1.88.0"
+rust-version = "1.62"
 
 [profile.release]
-codegen-units = 1
 lto = true
+codegen-units = 1
 opt-level = "s"
 strip = true
 
 [profile.profiling]
-debug = true
 inherits = "release"
 strip = false
+debug = true
 
 [dependencies]
-anyhow = { workspace = true }
+anyhow = "1.0.69"
 api_client = { path = "api_client" }
-clap = { workspace = true, features = ["string"] }
-dhat = { workspace = true, optional = true }
-env_logger = { workspace = true }
-epoll = { workspace = true }
+argh = "0.1.9"
+dhat = { version = "0.3.2", optional = true }
+epoll = "4.3.1"
 event_monitor = { path = "event_monitor" }
 hypervisor = { path = "hypervisor" }
-libc = { workspace = true }
-log = { workspace = true, features = ["std"] }
+libc = "0.2.139"
+log = { version = "0.4.17", features = ["std"] }
 option_parser = { path = "option_parser" }
-seccompiler = { workspace = true }
-serde_json = { workspace = true }
-signal-hook = { workspace = true }
-thiserror = { workspace = true }
-tpm = { path = "tpm" }
+seccompiler = "0.3.0"
+serde_json = "1.0.95"
+signal-hook = "0.3.15"
+thiserror = "1.0.39"
+tpm = { path = "tpm"}
 tracer = { path = "tracer" }
-vm-memory = { workspace = true }
 vmm = { path = "vmm" }
-vmm-sys-util = { workspace = true }
-zbus = { version = "5.7.1", optional = true }
+vmm-sys-util = "0.11.0"
+vm-memory = "0.10.0"
+
+# List of patched crates
+[patch.crates-io]
+kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.6.0-tdx" }
+kvm-ioctls = { git = "https://github.com/rust-vmm/kvm-ioctls", branch = "main" }
+versionize_derive = { git = "https://github.com/cloud-hypervisor/versionize_derive", branch = "ch" }
 
 [dev-dependencies]
-dirs = { workspace = true }
+dirs = "4.0.0"
 net_util = { path = "net_util" }
-serde_json = { workspace = true }
+once_cell = "1.17.1"
+serde_json = "1.0.95"
 test_infra = { path = "test_infra" }
-wait-timeout = { workspace = true }
+wait-timeout = "0.2.0"
 
-# Please adjust `vmm::feature_list()` accordingly when changing the
-# feature list below
 [features]
-dbus_api = ["vmm/dbus_api", "zbus"]
-default = ["io_uring", "kvm"]
-dhat-heap = ["dhat", "vmm/dhat-heap"]       # For heap profiling
-fw_cfg = ["vmm/fw_cfg"]
+default = ["kvm"]
+dhat-heap = ["dhat"] # For heap profiling
 guest_debug = ["vmm/guest_debug"]
-igvm = ["mshv", "vmm/igvm"]
-io_uring = ["vmm/io_uring"]
-ivshmem = ["vmm/ivshmem"]
 kvm = ["vmm/kvm"]
 mshv = ["vmm/mshv"]
-pvmemcontrol = ["vmm/pvmemcontrol"]
-sev_snp = ["igvm", "mshv", "vmm/sev_snp"]
 tdx = ["vmm/tdx"]
-tracing = ["tracer/tracing", "vmm/tracing"]
+tracing = ["vmm/tracing", "tracer/tracing"]
 
 [workspace]
 members = [
-  "api_client",
-  "arch",
-  "block",
-  "devices",
-  "event_monitor",
-  "hypervisor",
-  "net_gen",
-  "net_util",
-  "option_parser",
-  "pci",
-  "performance-metrics",
-  "rate_limiter",
-  "serial_buffer",
-  "test_infra",
-  "tracer",
-  "vhost_user_block",
-  "vhost_user_net",
-  "virtio-devices",
-  "vm-allocator",
-  "vm-device",
-  "vm-migration",
-  "vm-virtio",
-  "vmm",
+    "api_client",
+    "arch",
+    "block_util",
+    "devices",
+    "event_monitor",
+    "hypervisor",
+    "net_gen",
+    "net_util",
+    "option_parser",
+    "pci",
+    "performance-metrics",
+    "qcow",
+    "rate_limiter",
+    "serial_buffer",
+    "test_infra",
+    "tracer",
+    "vhdx",
+    "vhost_user_block",
+    "vhost_user_net",
+    "virtio-devices",
+    "vmm",
+    "vm-allocator",
+    "vm-device",
+    "vm-migration",
+    "vm-virtio"
 ]
-package.edition = "2024"
-
-[workspace.dependencies]
-# rust-vmm crates
-acpi_tables = { git = "https://github.com/rust-vmm/acpi_tables", branch = "main" }
-kvm-bindings = "0.12.0"
-kvm-ioctls = "0.22.0"
-# TODO: update to 0.13.1+
-linux-loader = { git = "https://github.com/rust-vmm/linux-loader", branch = "main" }
-mshv-bindings = "0.6.0"
-mshv-ioctls = "0.6.0"
-seccompiler = "0.5.0"
-vfio-bindings = { version = "0.6.0", default-features = false }
-vfio-ioctls = { version = "0.5.1", default-features = false }
-vfio_user = { version = "0.1.1", default-features = false }
-vhost = { version = "0.14.0", default-features = false }
-vhost-user-backend = { version = "0.20.0", default-features = false }
-virtio-bindings = "0.2.6"
-virtio-queue = "0.16.0"
-vm-fdt = { git = "https://github.com/rust-vmm/vm-fdt", branch = "main" }
-vm-memory = "0.16.1"
-vmm-sys-util = "0.14.0"
-
-# igvm crates
-# TODO: bump to 0.3.5 release
-igvm = { git = "https://github.com/microsoft/igvm", branch = "main" }
-igvm_defs = { git = "https://github.com/microsoft/igvm", branch = "main" }
-
-# serde crates
-serde = "1.0.208"
-serde_json = "1.0.143"
-serde_with = { version = "3.14.0", default-features = false }
-
-# other crates
-anyhow = "1.0.98"
-bitflags = "2.9.4"
-byteorder = "1.5.0"
-cfg-if = "1.0.0"
-clap = "4.5.47"
-dhat = "0.3.3"
-dirs = "6.0.0"
-env_logger = "0.11.8"
-epoll = "4.3.3"
-flume = "0.11.1"
-libc = "0.2.167"
-log = "0.4.22"
-signal-hook = "0.3.18"
-thiserror = "2.0.12"
-uuid = { version = "1.18.1" }
-wait-timeout = "0.2.1"
-zerocopy = { version = "0.8.26", default-features = false }

Jenkinsfile

@@ -0,0 +1,452 @@
+def runWorkers = true
+pipeline {
+    agent none
+    options {
+        timeout(time: 4, unit: 'HOURS')
+    }
+    stages {
+        stage('Early checks') {
+            agent { node { label 'built-in' } }
+            stages {
+                stage('Checkout') {
+                    steps {
+                        checkout scm
+                    }
+                }
+                stage('Check if worker build can be skipped') {
+                    when {
+                        expression {
+                            return skipWorkerBuild()
+                        }
+                    }
+                    steps {
+                        script {
+                            runWorkers = false
+                            echo 'No changes requring a build'
+                        }
+                    }
+                }
+                stage('Check for RFC/WIP builds') {
+                    when {
+                        changeRequest comparator: 'REGEXP', title: '.*(rfc|RFC|wip|WIP).*'
+                        beforeAgent true
+                    }
+                    steps {
+                        error('Failing as this is marked as a WIP or RFC PR.')
+                    }
+                }
+                stage('Cancel older builds') {
+                    when { not { branch 'main' } }
+                    steps {
+                        cancelPreviousBuilds()
+                    }
+                }
+            }
+        }
+        stage('Build') {
+            parallel {
+                stage('Worker build') {
+                    agent { node { label 'jammy' } }
+                    when {
+                        beforeAgent true
+                        expression {
+                            return runWorkers
+                        }
+                    }
+                    stages {
+                        stage('Checkout') {
+                            steps {
+                                checkout scm
+                            }
+                        }
+                        stage('Prepare environment') {
+                            steps {
+                                sh 'scripts/prepare_vdpa.sh'
+                            }
+                        }
+                        stage('Run OpenAPI tests') {
+                            steps {
+                                sh 'scripts/run_openapi_tests.sh'
+                            }
+                        }
+                        stage('Run unit tests') {
+                            steps {
+                                sh 'scripts/dev_cli.sh tests --unit'
+                            }
+                        }
+                        stage('Run integration tests') {
+                            options {
+                                timeout(time: 1, unit: 'HOURS')
+                            }
+                            steps {
+                                sh 'sudo modprobe openvswitch'
+                                sh 'scripts/dev_cli.sh tests --integration'
+                            }
+                        }
+                        stage('Run live-migration integration tests') {
+                            options {
+                                timeout(time: 1, unit: 'HOURS')
+                            }
+                            steps {
+                                sh 'sudo modprobe openvswitch'
+                                sh 'scripts/dev_cli.sh tests --integration-live-migration'
+                            }
+                        }
+                        stage('Run unit tests for musl') {
+                            steps {
+                                sh 'scripts/dev_cli.sh tests --unit --libc musl'
+                            }
+                        }
+                        stage('Run integration tests for musl') {
+                            options {
+                                timeout(time: 1, unit: 'HOURS')
+                            }
+                            steps {
+                                sh 'sudo modprobe openvswitch'
+                                sh 'scripts/dev_cli.sh tests --integration --libc musl'
+                            }
+                        }
+                        stage('Run live-migration integration tests for musl') {
+                            options {
+                                timeout(time: 1, unit: 'HOURS')
+                            }
+                            steps {
+                                sh 'sudo modprobe openvswitch'
+                                sh 'scripts/dev_cli.sh tests --integration-live-migration --libc musl'
+                            }
+                        }
+                    }
+                }
+                stage('AArch64 worker build') {
+                    agent { node { label 'bionic-arm64' } }
+                    when {
+                        beforeAgent true
+                        expression {
+                            return runWorkers
+                        }
+                    }
+                    environment {
+                            AZURE_CONNECTION_STRING = credentials('46b4e7d6-315f-4cc1-8333-b58780863b9b')
+                    }
+                    stages {
+                        stage('Checkout') {
+                            steps {
+                                checkout scm
+                            }
+                        }
+                        stage('Run unit tests') {
+                            steps {
+                                sh 'scripts/dev_cli.sh tests --unit --libc musl'
+                            }
+                        }
+                        stage('Run integration tests') {
+                            options {
+                                timeout(time: 1, unit: 'HOURS')
+                            }
+                            steps {
+                                sh 'sudo modprobe openvswitch'
+                                sh 'scripts/dev_cli.sh tests --integration --libc musl'
+                            }
+                        }
+                        stage('Install azure-cli') {
+                            steps {
+                                installAzureCli('bionic', 'arm64')
+                            }
+                        }
+                        stage('Download Windows image') {
+                            steps {
+                                sh '''#!/bin/bash -x
+                                    IMG_BASENAME=windows-11-iot-enterprise-aarch64.raw
+                                    IMG_PATH=$HOME/workloads/$IMG_BASENAME
+                                    IMG_GZ_PATH=$HOME/workloads/$IMG_BASENAME.gz
+                                    IMG_GZ_BLOB_NAME=windows-11-iot-enterprise-aarch64-9-min.raw.gz
+                                    cp "scripts/$IMG_BASENAME.sha1" "$HOME/workloads/"
+                                    pushd "$HOME/workloads"
+                                    if sha1sum "$IMG_BASENAME.sha1" --check; then
+                                        exit
+                                    fi
+                                    popd
+                                    mkdir -p "$HOME/workloads"
+                                    az storage blob download \
+                                        --container-name private-images \
+                                        --file "$IMG_GZ_PATH" \
+                                        --name "$IMG_GZ_BLOB_NAME" \
+                                        --connection-string "$AZURE_CONNECTION_STRING"
+                                    gzip -d $IMG_GZ_PATH
+                                '''
+                            }
+                        }
+                        stage('Run Windows guest integration tests') {
+                            options {
+                                timeout(time: 1, unit: 'HOURS')
+                            }
+                            steps {
+                                sh 'scripts/dev_cli.sh tests --integration-windows --libc musl'
+                            }
+                        }
+                    }
+                    post {
+                        always {
+                            sh "sudo chown -R jenkins.jenkins ${WORKSPACE}"
+                            deleteDir()
+                        }
+                    }
+                }
+                stage('Worker build - Windows guest') {
+                    agent { node { label 'jammy' } }
+                    when {
+                        beforeAgent true
+                        expression {
+                            return runWorkers
+                        }
+                    }
+                    environment {
+                            AZURE_CONNECTION_STRING = credentials('46b4e7d6-315f-4cc1-8333-b58780863b9b')
+                    }
+                    stages {
+                        stage('Checkout') {
+                            steps {
+                                checkout scm
+                            }
+                        }
+                        stage('Install azure-cli') {
+                            steps {
+                                installAzureCli('jammy', 'amd64')
+                            }
+                        }
+                        stage('Download assets') {
+                            steps {
+                                sh "mkdir ${env.HOME}/workloads"
+                                sh 'az storage blob download --container-name private-images --file "$HOME/workloads/windows-server-2022-amd64-2.raw" --name windows-server-2022-amd64-2.raw --connection-string "$AZURE_CONNECTION_STRING"'
+                            }
+                        }
+                        stage('Run Windows guest integration tests') {
+                            options {
+                                timeout(time: 1, unit: 'HOURS')
+                            }
+                            steps {
+                                sh 'scripts/dev_cli.sh tests --integration-windows'
+                            }
+                        }
+                        stage('Run Windows guest integration tests for musl') {
+                            options {
+                                timeout(time: 1, unit: 'HOURS')
+                            }
+                            steps {
+                                sh 'scripts/dev_cli.sh tests --integration-windows --libc musl'
+                            }
+                        }
+                    }
+                }
+                stage('Worker build - Metrics') {
+                    agent { node { label 'jammy-metrics' } }
+                    when {
+                        branch 'main'
+                        beforeAgent true
+                        expression {
+                            return runWorkers
+                        }
+                    }
+                    environment {
+                        METRICS_PUBLISH_KEY = credentials('52e0945f-ce7a-43d1-87af-67d1d87cc40f')
+                    }
+                    stages {
+                        stage('Checkout') {
+                            steps {
+                                checkout scm
+                            }
+                        }
+                        stage('Run metrics tests') {
+                            options {
+                                timeout(time: 1, unit: 'HOURS')
+                            }
+                            steps {
+                                sh 'scripts/dev_cli.sh tests --metrics -- -- --report-file /root/workloads/metrics.json'
+                            }
+                        }
+                        stage('Upload metrics report') {
+                            steps {
+                                sh 'curl -X PUT https://cloud-hypervisor-metrics.azurewebsites.net/api/publishmetrics -H "x-functions-key: $METRICS_PUBLISH_KEY" -T ~/workloads/metrics.json'
+                            }
+                        }
+                    }
+                }
+                stage('Worker build - Rate Limiter') {
+                    agent { node { label 'focal-metrics' } }
+                    when {
+                        branch 'main'
+                        beforeAgent true
+                        expression {
+                            return runWorkers
+                        }
+                    }
+                    stages {
+                        stage('Checkout') {
+                            steps {
+                                checkout scm
+                            }
+                        }
+                        stage('Run rate-limiter integration tests') {
+                            options {
+                                timeout(time: 10, unit: 'MINUTES')
+                            }
+                            steps {
+                                sh 'scripts/dev_cli.sh tests --integration-rate-limiter'
+                            }
+                        }
+                    }
+                }
+                stage('Worker build - SGX') {
+                    agent { node { label 'jammy-sgx' } }
+                    when {
+                        beforeAgent true
+                        allOf {
+                            branch 'main'
+                            expression {
+                                return runWorkers
+                            }
+                        }
+                    }
+                    stages {
+                        stage('Checkout') {
+                            steps {
+                                checkout scm
+                            }
+                        }
+                        stage('Run SGX integration tests') {
+                            options {
+                                timeout(time: 1, unit: 'HOURS')
+                            }
+                            steps {
+                                sh 'scripts/dev_cli.sh tests --integration-sgx'
+                            }
+                        }
+                        stage('Run SGX integration tests for musl') {
+                            options {
+                                timeout(time: 1, unit: 'HOURS')
+                            }
+                            steps {
+                                sh 'scripts/dev_cli.sh tests --integration-sgx --libc musl'
+                            }
+                        }
+                    }
+                    post {
+                        always {
+                            sh "sudo chown -R jenkins.jenkins ${WORKSPACE}"
+                            deleteDir()
+                        }
+                    }
+                }
+                stage('Worker build - VFIO') {
+                    agent { node { label 'jammy-vfio' } }
+                    when {
+                        beforeAgent true
+                        allOf {
+                            branch 'main'
+                            expression {
+                                return runWorkers
+                            }
+                        }
+                    }
+                    stages {
+                        stage('Checkout') {
+                            steps {
+                                checkout scm
+                            }
+                        }
+                        stage('Run VFIO integration tests') {
+                            options {
+                                timeout(time: 1, unit: 'HOURS')
+                            }
+                            steps {
+                                sh 'scripts/dev_cli.sh tests --integration-vfio'
+                            }
+                        }
+                        stage('Run VFIO integration tests for musl') {
+                            options {
+                                timeout(time: 1, unit: 'HOURS')
+                            }
+                            steps {
+                                sh 'scripts/dev_cli.sh tests --integration-vfio --libc musl'
+                            }
+                        }
+                    }
+                    post {
+                        always {
+                            sh "sudo chown -R jenkins.jenkins ${WORKSPACE}"
+                            deleteDir()
+                        }
+                    }
+                }
+            }
+        }
+    }
+    post {
+        regression {
+            script {
+                if (env.BRANCH_NAME == 'main') {
+                    slackSend(color: '#ff0000', message: '"main" branch build is now failing', channel: '#jenkins-ci')
+                }
+            }
+        }
+        fixed {
+            script {
+                if (env.BRANCH_NAME == 'main') {
+                    slackSend(color: '#00ff00', message: '"main" branch build is now fixed', channel: '#jenkins-ci')
+                }
+            }
+        }
+    }
+}
+
+def cancelPreviousBuilds() {
+    // Check for other instances of this particular build, cancel any that are older than the current one
+    def jobName = env.JOB_NAME
+    def currentBuildNumber = env.BUILD_NUMBER.toInteger()
+    def currentJob = Jenkins.instance.getItemByFullName(jobName)
+
+    // Loop through all instances of this particular job/branch
+    for (def build : currentJob.builds) {
+        if (build.isBuilding() && (build.number.toInteger() < currentBuildNumber)) {
+            echo "Older build still queued. Sending kill signal to build number: ${build.number}"
+            build.doStop()
+        }
+    }
+}
+
+def installAzureCli(distro, arch) {
+    sh 'sudo apt install -y ca-certificates curl apt-transport-https lsb-release gnupg'
+    sh 'curl -sL https://packages.microsoft.com/keys/microsoft.asc | gpg --dearmor | sudo tee /etc/apt/trusted.gpg.d/microsoft.gpg > /dev/null'
+    sh "echo \"deb [arch=${arch}] https://packages.microsoft.com/repos/azure-cli/ ${distro} main\" | sudo tee /etc/apt/sources.list.d/azure-cli.list"
+    sh 'sudo apt update'
+    sh 'sudo apt install -y azure-cli'
+}
+
+def boolean skipWorkerBuild() {
+    if (env.CHANGE_TARGET == null) {
+        return false
+    }
+
+    if (sh(
+        returnStatus: true,
+        script: "git diff --name-only origin/${env.CHANGE_TARGET}... | grep -v '\\.md'"
+    ) != 0) {
+        return true
+    }
+
+    if (sh(
+        returnStatus: true,
+        script: "git diff --name-only origin/${env.CHANGE_TARGET}... | grep -v -E 'fuzz/'"
+    ) != 0) {
+        return true
+    }
+
+    if (sh(
+        returnStatus: true,
+        script: "git diff --name-only origin/${env.CHANGE_TARGET}... | grep -v -E '.github/'"
+    ) != 0) {
+        return true
+    }
+
+    return false
+}

README.md

@@ -59,13 +59,9 @@ based on the [Rust VMM](https://github.com/rust-vmm) crates.
 
 ### Architectures
 
-Cloud Hypervisor supports the `x86-64`, `AArch64` and `riscv64`
-architectures, with functionality varying across these platforms. The
-functionality differences between `x86-64` and `AArch64` are documented
-in [#1125](https://github.com/cloud-hypervisor/cloud-hypervisor/issues/1125).
-The `riscv64` architecture support is experimental and offers limited
-functionality. For more details and instructions, please refer to [riscv
-documentation](docs/riscv.md).
+Cloud Hypervisor supports the `x86-64` and `AArch64` architectures. There are
+minor differences in functionality between the two architectures
+(see [#1125](https://github.com/cloud-hypervisor/cloud-hypervisor/issues/1125)).
 
 ### Guest OS
 
@@ -82,9 +78,9 @@ The following sections describe how to build and run Cloud Hypervisor.
 
 ## Host OS
 
-For required KVM functionality and adequate performance the recommended host
-kernel version is 5.13. The majority of the CI currently tests with kernel
-version 5.15.
+For required KVM functionality the minimum host kernel version is 4.11.  For
+adequate performance the minimum recommended host kernel version is 5.6. The
+majority of the CI currently tests with kernel version 5.15.
 
 ## Use Pre-built Binaries
 
@@ -112,7 +108,7 @@ do not wish to use the pre-built binaries.
 ## Booting Linux
 
 Cloud Hypervisor supports direct kernel boot (the x86-64 kernel requires the kernel
-built with PVH support or a bzImage) or booting via a firmware (either [Rust Hypervisor
+built with PVH support) or booting via a firmware (either [Rust Hypervisor
 Firmware](https://github.com/cloud-hypervisor/rust-hypervisor-firmware) or an
 edk2 UEFI firmware called `CLOUDHV` / `CLOUDHV_EFI`.)
 
@@ -144,17 +140,14 @@ The Ubuntu cloud images do not ship with a default password so it necessary to
 use a `cloud-init` disk image to customise the image on the first boot. A basic
 `cloud-init` image is generated by this [script](scripts/create-cloud-init.sh).
 This seeds the image with a default username/password of `cloud/cloud123`. It
-is only necessary to add this disk image on the first boot. Script also assigns
-default IP address using `test_data/cloud-init/ubuntu/local/network-config` details
-with `--net "mac=12:34:56:78:90:ab,tap="` option. Then the matching mac address
-interface will be enabled as per `network-config` details.
+is only necessary to add this disk image on the first boot.
 
 ```shell
 $ sudo setcap cap_net_admin+ep ./cloud-hypervisor
 $ ./create-cloud-init.sh
 $ ./cloud-hypervisor \
-	--firmware ./hypervisor-fw \
-	--disk path=focal-server-cloudimg-amd64.raw path=/tmp/ubuntu-cloudinit.img \
+	--kernel ./hypervisor-fw \
+	--disk path=focal-server-cloudimg-amd64.raw --disk path=/tmp/ubuntu-cloudinit.img \
 	--cpus boot=4 \
 	--memory size=1024M \
 	--net "tap=,mac=,ip=,mask="
@@ -167,7 +160,7 @@ GRUB) is required then it necessary to switch to the serial console instead of
 ```shell
 $ ./cloud-hypervisor \
 	--kernel ./hypervisor-fw \
-	--disk path=focal-server-cloudimg-amd64.raw path=/tmp/ubuntu-cloudinit.img \
+	--disk path=focal-server-cloudimg-amd64.raw --disk path=/tmp/ubuntu-cloudinit.img \
 	--cpus boot=4 \
 	--memory size=1024M \
 	--net "tap=,mac=,ip=,mask=" \
@@ -175,31 +168,24 @@ $ ./cloud-hypervisor \
 	--console off
 ```
 
-## Booting: `--firmware` vs `--kernel`
-
-The following scenarios are supported by Cloud Hypervisor to bootstrap a VM, i.e.,
-to load a payload/bootitem(s):
-
-- Provide firmware
-- Provide kernel \[+ cmdline\]\ [+ initrd\]
-
-Please note that our Cloud Hypervisor firmware (`hypervisor-fw`) has a Xen PVH
-boot entry, therefore it can also be booted via the `--kernel` parameter, as 
-seen in some examples.
-
 ### Custom Kernel and Disk Image
 
 #### Building your Kernel
 
-Cloud Hypervisor also supports direct kernel boot. For x86-64, a `vmlinux` ELF kernel (compiled with PVH support) or a regular bzImage are supported. In order to support development there is a custom branch; however provided the required options are enabled any recent kernel will suffice.
+Cloud Hypervisor also supports direct kernel boot. For x86-64, a `vmlinux` ELF kernel (compiled with PVH support) is needed. In order to support development there is a custom branch; however provided the required options are enabled any recent kernel will suffice.
 
 To build the kernel:
 
 ```shell
 # Clone the Cloud Hypervisor Linux branch
-$ git clone --depth 1 https://github.com/cloud-hypervisor/linux.git -b ch-6.12.8 linux-cloud-hypervisor
+$ git clone --depth 1 https://github.com/cloud-hypervisor/linux.git -b ch-6.2 linux-cloud-hypervisor
 $ pushd linux-cloud-hypervisor
-$ make ch_defconfig
+# Use the x86-64 cloud-hypervisor kernel config to build your kernel for x86-64
+$ wget https://raw.githubusercontent.com/cloud-hypervisor/cloud-hypervisor/main/resources/linux-config-x86_64
+# Use the AArch64 cloud-hypervisor kernel config to build your kernel for AArch64
+$ wget https://raw.githubusercontent.com/cloud-hypervisor/cloud-hypervisor/main/resources/linux-config-aarch64
+$ cp linux-config-x86_64 .config  # x86-64
+$ cp linux-config-aarch64 .config # AArch64
 # Do native build of the x86-64 kernel
 $ KCFLAGS="-Wa,-mx86-used-note=no" make bzImage -j `nproc`
 # Do native build of the AArch64 kernel
@@ -236,7 +222,7 @@ $ sudo setcap cap_net_admin+ep ./cloud-hypervisor
 $ ./create-cloud-init.sh
 $ ./cloud-hypervisor \
 	--kernel ./linux-cloud-hypervisor/arch/x86/boot/compressed/vmlinux.bin \
-	--disk path=focal-server-cloudimg-amd64.raw path=/tmp/ubuntu-cloudinit.img \
+	--disk path=focal-server-cloudimg-amd64.raw --disk path=/tmp/ubuntu-cloudinit.img \
 	--cmdline "console=hvc0 root=/dev/vda1 rw" \
 	--cpus boot=4 \
 	--memory size=1024M \
@@ -250,7 +236,7 @@ $ sudo setcap cap_net_admin+ep ./cloud-hypervisor
 $ ./create-cloud-init.sh
 $ ./cloud-hypervisor \
 	--kernel ./linux-cloud-hypervisor/arch/arm64/boot/Image \
-	--disk path=focal-server-cloudimg-arm64.raw path=/tmp/ubuntu-cloudinit.img \
+	--disk path=focal-server-cloudimg-arm64.raw --disk path=/tmp/ubuntu-cloudinit.img \
 	--cmdline "console=hvc0 root=/dev/vda1 rw" \
 	--cpus boot=4 \
 	--memory size=1024M \
@@ -313,9 +299,8 @@ Further details can be found in the [release documentation](docs/releases.md).
 As of 2023-01-03, the following cloud images are supported:
 
 - [Ubuntu Focal](https://cloud-images.ubuntu.com/focal/current/) (focal-server-cloudimg-{amd64,arm64}.img)
-- [Ubuntu Jammy](https://cloud-images.ubuntu.com/jammy/current/) (jammy-server-cloudimg-{amd64,arm64}.img)
-- [Ubuntu Noble](https://cloud-images.ubuntu.com/noble/current/) (noble-server-cloudimg-{amd64,arm64}.img)
-- [Fedora 36](https://archives.fedoraproject.org/pub/archive/fedora/linux/releases/36/Cloud/) ([Fedora-Cloud-Base-36-1.5.x86_64.raw.xz](https://archives.fedoraproject.org/pub/archive/fedora/linux/releases/36/Cloud/x86_64/images/) / [Fedora-Cloud-Base-36-1.5.aarch64.raw.xz](https://archives.fedoraproject.org/pub/archive/fedora/linux/releases/36/Cloud/aarch64/images/))
+- [Ubuntu Jammy](https://cloud-images.ubuntu.com/jammy/current/) (jammy-server-cloudimg-{amd64,arm64}.img )
+- [Fedora 36](https://fedora.mirrorservice.org/fedora/linux/releases/36/Cloud/) ([Fedora-Cloud-Base-36-1.5.x86_64.raw.xz](https://fedora.mirrorservice.org/fedora/linux/releases/36/Cloud/x86_64/images/) / [Fedora-Cloud-Base-36-1.5.aarch64.raw.xz](https://fedora.mirrorservice.org/fedora/linux/releases/36/Cloud/aarch64/images/))
 
 Direct kernel boot to userspace should work with a rootfs from most
 distributions although you may need to enable exotic filesystem types in the

api_client/Cargo.toml

@@ -1,9 +1,8 @@
 [package]
-authors = ["The Cloud Hypervisor Authors"]
-edition.workspace = true
 name = "api_client"
 version = "0.1.0"
+authors = ["The Cloud Hypervisor Authors"]
+edition = "2021"
 
 [dependencies]
-thiserror = { workspace = true }
-vmm-sys-util = { workspace = true }
+vmm-sys-util = "0.11.0"

api_client/src/lib.rs

@@ -3,32 +3,39 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
+use std::fmt;
 use std::io::{Read, Write};
 use std::os::unix::io::RawFd;
-
-use thiserror::Error;
 use vmm_sys_util::sock_ctrl_msg::ScmSocket;
 
-#[derive(Debug, Error)]
+#[derive(Debug)]
 pub enum Error {
-    #[error("Error writing to or reading from HTTP socket")]
-    Socket(#[source] std::io::Error),
-    #[error("Error sending file descriptors")]
-    SocketSendFds(#[source] vmm_sys_util::errno::Error),
-    #[error("Error parsing HTTP status code")]
-    StatusCodeParsing(#[source] std::num::ParseIntError),
-    #[error("HTTP output is missing protocol statement")]
+    Socket(std::io::Error),
+    SocketSendFds(vmm_sys_util::errno::Error),
+    StatusCodeParsing(std::num::ParseIntError),
     MissingProtocol,
-    #[error("Error parsing HTTP Content-Length field")]
-    ContentLengthParsing(#[source] std::num::ParseIntError),
-    #[error("Server responded with error {0:?}: {1:?}")]
-    ServerResponse(
-        StatusCode,
-        // TODO: Move `api` module from `vmm` to dedicated crate and use a common type definition
-        Option<
-            String, /* Untyped: Currently Vec<String> of error messages from top to root cause */
-        >,
-    ),
+    ContentLengthParsing(std::num::ParseIntError),
+    ServerResponse(StatusCode, Option<String>),
+}
+
+impl fmt::Display for Error {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        use Error::*;
+        match self {
+            Socket(e) => write!(f, "Error writing to or reading from HTTP socket: {e}"),
+            SocketSendFds(e) => write!(f, "Error writing to or reading from HTTP socket: {e}"),
+            StatusCodeParsing(e) => write!(f, "Error parsing HTTP status code: {e}"),
+            MissingProtocol => write!(f, "HTTP output is missing protocol statement"),
+            ContentLengthParsing(e) => write!(f, "Error parsing HTTP Content-Length field: {e}"),
+            ServerResponse(s, o) => {
+                if let Some(o) = o {
+                    write!(f, "Server responded with an error: {s:?}: {o}")
+                } else {
+                    write!(f, "Server responded with an error: {s:?}")
+                }
+            }
+        }
+    }
 }
 
 #[derive(Clone, Copy, Debug)]
@@ -38,7 +45,6 @@ pub enum StatusCode {
     NoContent,
     BadRequest,
     NotFound,
-    TooManyRequests,
     InternalServerError,
     NotImplemented,
     Unknown,
@@ -52,7 +58,6 @@ impl StatusCode {
             204 => StatusCode::NoContent,
             400 => StatusCode::BadRequest,
             404 => StatusCode::NotFound,
-            429 => StatusCode::TooManyRequests,
             500 => StatusCode::InternalServerError,
             501 => StatusCode::NotImplemented,
             _ => StatusCode::Unknown,
@@ -118,11 +123,12 @@ fn parse_http_response(socket: &mut dyn Read) -> Result<Option<String>, Error> {
             }
         }
 
-        if let Some(body_offset) = body_offset
-            && let Some(content_length) = content_length
-            && res.len() >= content_length + body_offset
-        {
-            break;
+        if let Some(body_offset) = body_offset {
+            if let Some(content_length) = content_length {
+                if res.len() >= content_length + body_offset {
+                    break;
+                }
+            }
         }
     }
     let body_string = content_length.and(body_offset.map(|o| String::from(&res[o..])));

arch/Cargo.toml

@@ -1,29 +1,29 @@
 [package]
-authors = ["The Chromium OS Authors"]
-edition.workspace = true
 name = "arch"
 version = "0.1.0"
+authors = ["The Chromium OS Authors"]
+edition = "2021"
 
 [features]
 default = []
-fw_cfg = []
-kvm = ["hypervisor/kvm"]
-sev_snp = []
 tdx = []
 
 [dependencies]
-anyhow = { workspace = true }
-byteorder = { workspace = true }
+anyhow = "1.0.69"
+byteorder = "1.4.3"
 hypervisor = { path = "../hypervisor" }
-libc = { workspace = true }
-linux-loader = { workspace = true, features = ["bzimage", "elf", "pe"] }
-log = { workspace = true }
-serde = { workspace = true, features = ["derive", "rc"] }
-thiserror = { workspace = true }
-uuid = { workspace = true }
-vm-memory = { workspace = true, features = ["backend-bitmap", "backend-mmap"] }
-vmm-sys-util = { workspace = true, features = ["with-serde"] }
+libc = "0.2.139"
+linux-loader = { version = "0.8.1", features = ["elf", "bzimage", "pe"] }
+log = "0.4.17"
+serde = { version = "1.0.151", features = ["rc", "derive"] }
+thiserror = "1.0.39"
+uuid = "1.3.0"
+versionize = "0.1.10"
+versionize_derive = "0.1.4"
+vm-memory = { version = "0.10.0", features = ["backend-mmap", "backend-bitmap"] }
+vm-migration = { path = "../vm-migration" }
+vmm-sys-util = { version = "0.11.0", features = ["with-serde"] }
 
-[target.'cfg(any(target_arch = "aarch64", target_arch = "riscv64"))'.dependencies]
-fdt_parser = { version = "0.1.5", package = "fdt" }
-vm-fdt = { workspace = true }
+[target.'cfg(target_arch = "aarch64")'.dependencies]
+fdt_parser = { version = "0.1.4", package = "fdt" }
+vm-fdt = { git = "https://github.com/rust-vmm/vm-fdt", branch = "main" }

arch/src/aarch64/fdt.rs

@@ -6,30 +6,27 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the THIRD-PARTY file.
 
+use crate::{NumaNodes, PciSpaceInfo};
+use byteorder::{BigEndian, ByteOrder};
+use hypervisor::arch::aarch64::gic::Vgic;
+use std::cmp;
 use std::collections::HashMap;
 use std::ffi::CStr;
 use std::fmt::Debug;
-use std::path::Path;
+use std::result;
+use std::str;
 use std::sync::{Arc, Mutex};
-use std::{cmp, fs, result, str};
 
-use byteorder::{BigEndian, ByteOrder};
-use hypervisor::arch::aarch64::gic::Vgic;
-use hypervisor::arch::aarch64::regs::{
-    AARCH64_ARCH_TIMER_HYP_IRQ, AARCH64_ARCH_TIMER_PHYS_NONSECURE_IRQ,
-    AARCH64_ARCH_TIMER_PHYS_SECURE_IRQ, AARCH64_ARCH_TIMER_VIRT_IRQ, AARCH64_PMU_IRQ,
+use super::super::DeviceType;
+use super::super::GuestMemoryMmap;
+use super::super::InitramfsConfig;
+use super::layout::{
+    IRQ_BASE, MEM_32BIT_DEVICES_SIZE, MEM_32BIT_DEVICES_START, MEM_PCI_IO_SIZE, MEM_PCI_IO_START,
+    PCI_HIGH_BASE, PCI_MMIO_CONFIG_SIZE_PER_SEGMENT,
 };
-use thiserror::Error;
 use vm_fdt::{FdtWriter, FdtWriterResult};
 use vm_memory::{Address, Bytes, GuestMemory, GuestMemoryError, GuestMemoryRegion};
 
-use super::super::{DeviceType, GuestMemoryMmap, InitramfsConfig};
-use super::layout::{
-    GIC_V2M_COMPATIBLE, IRQ_BASE, MEM_32BIT_DEVICES_SIZE, MEM_32BIT_DEVICES_START, MEM_PCI_IO_SIZE,
-    MEM_PCI_IO_START, PCI_HIGH_BASE, PCI_MMIO_CONFIG_SIZE_PER_SEGMENT, SPI_BASE, SPI_NUM,
-};
-use crate::{NumaNodes, PciSpaceInfo};
-
 // This is a value for uniquely identifying the FDT node declaring the interrupt controller.
 const GIC_PHANDLE: u32 = 1;
 // This is a value for uniquely identifying the FDT node declaring the MSI controller.
@@ -43,12 +40,8 @@ const VIRTIO_IOMMU_PHANDLE: u32 = 5;
 // NOTE: Keep FIRST_VCPU_PHANDLE the last PHANDLE defined.
 // This is a value for uniquely identifying the FDT node containing the first vCPU.
 // The last number of vCPU phandle depends on the number of vCPUs.
-const FIRST_VCPU_PHANDLE: u32 = 8;
+const FIRST_VCPU_PHANDLE: u32 = 6;
 
-// This is a value for uniquely identifying the FDT node containing the L2 cache info
-const L2_CACHE_PHANDLE: u32 = 6;
-// This is a value for uniquely identifying the FDT node containing the L3 cache info
-const L3_CACHE_PHANDLE: u32 = 7;
 // Read the documentation specified when appending the root node to the FDT.
 const ADDRESS_CELLS: u32 = 0x2;
 const SIZE_CELLS: u32 = 0x2;
@@ -63,6 +56,9 @@ const GIC_FDT_IRQ_TYPE_PPI: u32 = 1;
 const IRQ_TYPE_EDGE_RISING: u32 = 1;
 const IRQ_TYPE_LEVEL_HI: u32 = 4;
 
+// PMU PPI interrupt number
+pub const AARCH64_PMU_IRQ: u32 = 7;
+
 // Keys and Buttons
 // System Power Down
 const KEY_POWER: u32 = 116;
@@ -78,135 +74,20 @@ pub trait DeviceInfoForFdt {
 }
 
 /// Errors thrown while configuring the Flattened Device Tree for aarch64.
-#[derive(Debug, Error)]
+#[derive(Debug)]
 pub enum Error {
     /// Failure in writing FDT in memory.
-    #[error("Failure in writing FDT in memory")]
-    WriteFdtToMemory(#[source] GuestMemoryError),
+    WriteFdtToMemory(GuestMemoryError),
 }
 type Result<T> = result::Result<T, Error>;
 
-pub enum CacheLevel {
-    /// L1 data cache
-    L1D = 0,
-    /// L1 instruction cache
-    L1I = 1,
-    /// L2 cache
-    L2 = 2,
-    /// L3 cache
-    L3 = 3,
-}
-
-/// NOTE: cache size file directory example,
-/// "/sys/devices/system/cpu/cpu0/cache/index0/size".
-pub fn get_cache_size(cache_level: CacheLevel) -> u32 {
-    let mut file_directory: String = "/sys/devices/system/cpu/cpu0/cache".to_string();
-    match cache_level {
-        CacheLevel::L1D => file_directory += "/index0/size",
-        CacheLevel::L1I => file_directory += "/index1/size",
-        CacheLevel::L2 => file_directory += "/index2/size",
-        CacheLevel::L3 => file_directory += "/index3/size",
-    }
-
-    let file_path = Path::new(&file_directory);
-    if !file_path.exists() {
-        0
-    } else {
-        let src = fs::read_to_string(file_directory).expect("File not exists or file corrupted.");
-        // The content of the file is as simple as a size, like: "32K"
-        let src = src.trim();
-        let src_digits: u32 = src[0..src.len() - 1].parse().unwrap();
-        let src_unit = &src[src.len() - 1..];
-
-        src_digits
-            * match src_unit {
-                "K" => 1024,
-                "M" => 1024u32.pow(2),
-                "G" => 1024u32.pow(3),
-                _ => 1,
-            }
-    }
-}
-
-/// NOTE: coherency_line_size file directory example,
-/// "/sys/devices/system/cpu/cpu0/cache/index0/coherency_line_size".
-pub fn get_cache_coherency_line_size(cache_level: CacheLevel) -> u32 {
-    let mut file_directory: String = "/sys/devices/system/cpu/cpu0/cache".to_string();
-    match cache_level {
-        CacheLevel::L1D => file_directory += "/index0/coherency_line_size",
-        CacheLevel::L1I => file_directory += "/index1/coherency_line_size",
-        CacheLevel::L2 => file_directory += "/index2/coherency_line_size",
-        CacheLevel::L3 => file_directory += "/index3/coherency_line_size",
-    }
-
-    let file_path = Path::new(&file_directory);
-    if !file_path.exists() {
-        0
-    } else {
-        let src = fs::read_to_string(file_directory).expect("File not exists or file corrupted.");
-        src.trim().parse::<u32>().unwrap()
-    }
-}
-
-/// NOTE: number_of_sets file directory example,
-/// "/sys/devices/system/cpu/cpu0/cache/index0/number_of_sets".
-pub fn get_cache_number_of_sets(cache_level: CacheLevel) -> u32 {
-    let mut file_directory: String = "/sys/devices/system/cpu/cpu0/cache".to_string();
-    match cache_level {
-        CacheLevel::L1D => file_directory += "/index0/number_of_sets",
-        CacheLevel::L1I => file_directory += "/index1/number_of_sets",
-        CacheLevel::L2 => file_directory += "/index2/number_of_sets",
-        CacheLevel::L3 => file_directory += "/index3/number_of_sets",
-    }
-
-    let file_path = Path::new(&file_directory);
-    if !file_path.exists() {
-        0
-    } else {
-        let src = fs::read_to_string(file_directory).expect("File not exists or file corrupted.");
-        src.trim().parse::<u32>().unwrap()
-    }
-}
-
-/// NOTE: shared_cpu_list file directory example,
-/// "/sys/devices/system/cpu/cpu0/cache/index0/shared_cpu_list".
-pub fn get_cache_shared(cache_level: CacheLevel) -> bool {
-    let mut file_directory: String = "/sys/devices/system/cpu/cpu0/cache".to_string();
-    let mut result = true;
-
-    match cache_level {
-        CacheLevel::L1D | CacheLevel::L1I => result = false,
-        CacheLevel::L2 => file_directory += "/index2/shared_cpu_list",
-        CacheLevel::L3 => file_directory += "/index3/shared_cpu_list",
-    }
-
-    if !result {
-        return false;
-    }
-
-    let file_path = Path::new(&file_directory);
-    if !file_path.exists() {
-        result = false;
-    } else {
-        let src = fs::read_to_string(file_directory).expect("File not exists or file corrupted.");
-        let src = src.trim();
-        if src.is_empty() {
-            result = false;
-        } else {
-            result = src.contains('-') || src.contains(',');
-        }
-    }
-
-    result
-}
-
 /// Creates the flattened device tree for this aarch64 VM.
 #[allow(clippy::too_many_arguments)]
 pub fn create_fdt<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::BuildHasher>(
     guest_mem: &GuestMemoryMmap,
     cmdline: &str,
     vcpu_mpidr: Vec<u64>,
-    vcpu_topology: Option<(u16, u16, u16, u16)>,
+    vcpu_topology: Option<(u8, u8, u8)>,
     device_info: &HashMap<(DeviceType, String), T, S>,
     gic_device: &Arc<Mutex<dyn Vgic>>,
     initrd: &Option<InitramfsConfig>,
@@ -219,8 +100,8 @@ pub fn create_fdt<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::BuildHash
     let mut fdt = FdtWriter::new().unwrap();
 
     // For an explanation why these nodes were introduced in the blob take a look at
-    // the "Device Node Requirements" chapter of the Devicetree Specification.
-    // https://www.devicetree.org/specifications/
+    // https://github.com/torvalds/linux/blob/master/Documentation/devicetree/booting-without-of.txt#L845
+    // Look for "Required nodes and properties".
 
     // Header or the root node as per above mentioned documentation.
     let root_node = fdt.begin_node("")?;
@@ -268,7 +149,7 @@ pub fn write_fdt_to_memory(fdt_final: Vec<u8>, guest_mem: &GuestMemoryMmap) -> R
 fn create_cpu_nodes(
     fdt: &mut FdtWriter,
     vcpu_mpidr: &[u64],
-    vcpu_topology: Option<(u16, u16, u16, u16)>,
+    vcpu_topology: Option<(u8, u8, u8)>,
     numa_nodes: &NumaNodes,
 ) -> FdtWriterResult<()> {
     // See https://github.com/torvalds/linux/blob/master/Documentation/devicetree/bindings/arm/cpus.yaml.
@@ -277,70 +158,6 @@ fn create_cpu_nodes(
     fdt.property_u32("#size-cells", 0x0)?;
 
     let num_cpus = vcpu_mpidr.len();
-    let (threads_per_core, cores_per_die, dies_per_package, packages) =
-        vcpu_topology.unwrap_or((1, 1, 1, 1));
-    let cores_per_package = cores_per_die * dies_per_package;
-    let max_cpus: u32 =
-        threads_per_core as u32 * cores_per_die as u32 * dies_per_package as u32 * packages as u32;
-
-    // Add cache info.
-    // L1 Data Cache Info.
-    let mut l1_d_cache_size: u32 = 0;
-    let mut l1_d_cache_line_size: u32 = 0;
-    let mut l1_d_cache_sets: u32 = 0;
-
-    // L1 Instruction Cache Info.
-    let mut l1_i_cache_size: u32 = 0;
-    let mut l1_i_cache_line_size: u32 = 0;
-    let mut l1_i_cache_sets: u32 = 0;
-
-    // L2 Cache Info.
-    let mut l2_cache_size: u32 = 0;
-    let mut l2_cache_line_size: u32 = 0;
-    let mut l2_cache_sets: u32 = 0;
-
-    // L3 Cache Info.
-    let mut l3_cache_size: u32 = 0;
-    let mut l3_cache_line_size: u32 = 0;
-    let mut l3_cache_sets: u32 = 0;
-
-    // Cache Shared Info.
-    let mut l2_cache_shared: bool = false;
-    let mut l3_cache_shared: bool = false;
-
-    let cache_path = Path::new("/sys/devices/system/cpu/cpu0/cache");
-    let cache_exist: bool = cache_path.exists();
-    if !cache_exist {
-        warn!("cache sysfs system does not exist.");
-    } else {
-        // L1 Data Cache Info.
-        l1_d_cache_size = get_cache_size(CacheLevel::L1D);
-        l1_d_cache_line_size = get_cache_coherency_line_size(CacheLevel::L1D);
-        l1_d_cache_sets = get_cache_number_of_sets(CacheLevel::L1D);
-
-        // L1 Instruction Cache Info.
-        l1_i_cache_size = get_cache_size(CacheLevel::L1I);
-        l1_i_cache_line_size = get_cache_coherency_line_size(CacheLevel::L1I);
-        l1_i_cache_sets = get_cache_number_of_sets(CacheLevel::L1I);
-
-        // L2 Cache Info.
-        l2_cache_size = get_cache_size(CacheLevel::L2);
-        l2_cache_line_size = get_cache_coherency_line_size(CacheLevel::L2);
-        l2_cache_sets = get_cache_number_of_sets(CacheLevel::L2);
-
-        // L3 Cache Info.
-        l3_cache_size = get_cache_size(CacheLevel::L3);
-        l3_cache_line_size = get_cache_coherency_line_size(CacheLevel::L3);
-        l3_cache_sets = get_cache_number_of_sets(CacheLevel::L3);
-
-        // Cache Shared Info.
-        if l2_cache_size != 0 {
-            l2_cache_shared = get_cache_shared(CacheLevel::L2);
-        }
-        if l3_cache_size != 0 {
-            l3_cache_shared = get_cache_shared(CacheLevel::L3);
-        }
-    }
 
     for (cpu_id, mpidr) in vcpu_mpidr.iter().enumerate().take(num_cpus) {
         let cpu_name = format!("cpu@{cpu_id:x}");
@@ -360,97 +177,17 @@ fn create_cpu_nodes(
         if numa_nodes.len() > 1 {
             for numa_node_idx in 0..numa_nodes.len() {
                 let numa_node = numa_nodes.get(&(numa_node_idx as u32));
-                if numa_node.unwrap().cpus.contains(&(cpu_id as u32)) {
+                if numa_node.unwrap().cpus.contains(&(cpu_id as u8)) {
                     fdt.property_u32("numa-node-id", numa_node_idx as u32)?;
                 }
             }
         }
 
-        if cache_exist && l1_d_cache_size != 0 && l1_i_cache_size != 0 {
-            // Add cache info.
-            fdt.property_u32("d-cache-size", l1_d_cache_size)?;
-            fdt.property_u32("d-cache-line-size", l1_d_cache_line_size)?;
-            fdt.property_u32("d-cache-sets", l1_d_cache_sets)?;
-
-            fdt.property_u32("i-cache-size", l1_i_cache_size)?;
-            fdt.property_u32("i-cache-line-size", l1_i_cache_line_size)?;
-            fdt.property_u32("i-cache-sets", l1_i_cache_sets)?;
-
-            if l2_cache_size != 0 && !l2_cache_shared {
-                fdt.property_u32(
-                    "next-level-cache",
-                    cpu_id as u32 + max_cpus + FIRST_VCPU_PHANDLE + L2_CACHE_PHANDLE,
-                )?;
-
-                let l2_cache_name = "l2-cache0";
-                let l2_cache_node = fdt.begin_node(l2_cache_name)?;
-                // PHANDLE is used to mark device node, and PHANDLE is unique. To avoid phandle
-                // conflicts with other device nodes, consider the previous CPU PHANDLE, so the
-                // CPU L2 cache PHANDLE must start from the largest CPU PHANDLE plus 1.
-                fdt.property_u32(
-                    "phandle",
-                    cpu_id as u32 + max_cpus + FIRST_VCPU_PHANDLE + L2_CACHE_PHANDLE,
-                )?;
-
-                fdt.property_string("compatible", "cache")?;
-                fdt.property_u32("cache-size", l2_cache_size)?;
-                fdt.property_u32("cache-line-size", l2_cache_line_size)?;
-                fdt.property_u32("cache-sets", l2_cache_sets)?;
-                fdt.property_u32("cache-level", 2)?;
-
-                if l3_cache_size != 0 && l3_cache_shared {
-                    let package_id: u32 = cpu_id as u32 / cores_per_package as u32;
-                    fdt.property_u32(
-                        "next-level-cache",
-                        package_id
-                            + num_cpus as u32
-                            + max_cpus
-                            + FIRST_VCPU_PHANDLE
-                            + L2_CACHE_PHANDLE
-                            + L3_CACHE_PHANDLE,
-                    )?;
-                }
-
-                fdt.end_node(l2_cache_node)?;
-            }
-        }
-
         fdt.end_node(cpu_node)?;
     }
 
-    if cache_exist && l3_cache_size != 0 && !l2_cache_shared && l3_cache_shared {
-        let mut i: u32 = 0;
-        while i < packages.into() {
-            let l3_cache_name = "l3-cache0";
-            let l3_cache_node = fdt.begin_node(l3_cache_name)?;
-            // ARM L3 cache is generally shared within the package (socket), so the
-            // L3 cache node pointed to by the CPU in the package has the same L3
-            // cache PHANDLE. The L3 cache phandle must start from the largest L2
-            // cache PHANDLE plus 1 to avoid duplication.
-            fdt.property_u32(
-                "phandle",
-                i + num_cpus as u32
-                    + max_cpus
-                    + FIRST_VCPU_PHANDLE
-                    + L2_CACHE_PHANDLE
-                    + L3_CACHE_PHANDLE,
-            )?;
-
-            fdt.property_string("compatible", "cache")?;
-            fdt.property_null("cache-unified")?;
-            fdt.property_u32("cache-size", l3_cache_size)?;
-            fdt.property_u32("cache-line-size", l3_cache_line_size)?;
-            fdt.property_u32("cache-sets", l3_cache_sets)?;
-            fdt.property_u32("cache-level", 3)?;
-            fdt.end_node(l3_cache_node)?;
-
-            i += 1;
-        }
-    }
-
     if let Some(topology) = vcpu_topology {
-        let (threads_per_core, cores_per_die, dies_per_package, packages) = topology;
-        let cores_per_package = cores_per_die * dies_per_package;
+        let (threads_per_core, cores_per_package, packages) = topology;
         let cpu_map_node = fdt.begin_node("cpu-map")?;
 
         // Create device tree nodes with regard of above mapping.
@@ -510,7 +247,7 @@ fn create_memory_node(
                 let memory_region_size: u64 = memory_region.size() as u64;
                 mem_reg_prop.push(memory_region_start_addr);
                 mem_reg_prop.push(memory_region_size);
-                // Set the node address the first non-zero region address
+                // Set the node address the first non-zero regison address
                 if node_memory_addr == 0 {
                     node_memory_addr = memory_region_start_addr;
                 }
@@ -556,7 +293,7 @@ fn create_memory_node(
 
         if ram_regions.len() > 2 {
             panic!(
-                "There should be up to two non-continuous regions, divided by the
+                "There should be up to two non-continuous regions, devidided by the
                     gap at the end of 32bit address space."
             );
         }
@@ -574,14 +311,15 @@ fn create_memory_node(
                 && (first_region_end <= &mem_32bit_reserved_start))
             {
                 panic!(
-                    "Unexpected first memory region layout: (start: 0x{first_region_start:08x}, end: 0x{first_region_end:08x}).
-                    ram_start: 0x{ram_start:08x}, mem_32bit_reserved_start: 0x{mem_32bit_reserved_start:08x}"
+                    "Unexpected first memory region layout: (start: 0x{:08x}, end: 0x{:08x}).
+                    ram_start: 0x{:08x}, mem_32bit_reserved_start: 0x{:08x}",
+                    first_region_start, first_region_end, ram_start, mem_32bit_reserved_start
                 );
             }
 
             let mem_size = first_region_end - ram_start;
             let mem_reg_prop = [ram_start, mem_size];
-            let memory_node_name = format!("memory@{ram_start:x}");
+            let memory_node_name = format!("memory@{:x}", ram_start);
             let memory_node = fdt.begin_node(&memory_node_name)?;
             fdt.property_string("device_type", "memory")?;
             fdt.property_array_u64("reg", &mem_reg_prop)?;
@@ -594,13 +332,14 @@ fn create_memory_node(
 
             if second_region_start != &ram_64bit_start {
                 panic!(
-                    "Unexpected second memory region layout: start: 0x{second_region_start:08x}, ram_64bit_start: 0x{ram_64bit_start:08x}"
+                    "Unexpected second memory region layout: start: 0x{:08x}, ram_64bit_start: 0x{:08x}",
+                    second_region_start, ram_64bit_start
                 );
             }
 
             let mem_size = second_region_end - ram_64bit_start;
             let mem_reg_prop = [ram_64bit_start, mem_size];
-            let memory_node_name = format!("memory@{ram_64bit_start:x}");
+            let memory_node_name = format!("memory@{:x}", ram_64bit_start);
             let memory_node = fdt.begin_node(&memory_node_name)?;
             fdt.property_string("device_type", "memory")?;
             fdt.property_array_u64("reg", &mem_reg_prop)?;
@@ -657,19 +396,11 @@ fn create_gic_node(fdt: &mut FdtWriter, gic_device: &Arc<Mutex<dyn Vgic>>) -> Fd
 
     if gic_device.lock().unwrap().msi_compatible() {
         let msic_node = fdt.begin_node("msic")?;
-        let msi_compatibility = gic_device.lock().unwrap().msi_compatibility().to_string();
-
-        fdt.property_string("compatible", msi_compatibility.as_str())?;
+        fdt.property_string("compatible", gic_device.lock().unwrap().msi_compatibility())?;
         fdt.property_null("msi-controller")?;
         fdt.property_u32("phandle", MSI_PHANDLE)?;
         let msi_reg_prop = gic_device.lock().unwrap().msi_properties();
         fdt.property_array_u64("reg", &msi_reg_prop)?;
-
-        if msi_compatibility == GIC_V2M_COMPATIBLE {
-            fdt.property_u32("arm,msi-base-spi", SPI_BASE)?;
-            fdt.property_u32("arm,msi-num-spis", SPI_NUM)?;
-        }
-
         fdt.end_node(msic_node)?;
     }
 
@@ -696,14 +427,9 @@ fn create_clock_node(fdt: &mut FdtWriter) -> FdtWriterResult<()> {
 
 fn create_timer_node(fdt: &mut FdtWriter) -> FdtWriterResult<()> {
     // See
-    // https://github.com/torvalds/linux/blob/master/Documentation/devicetree/bindings/timer/arm%2Carch_timer.yaml
+    // https://github.com/torvalds/linux/blob/master/Documentation/devicetree/bindings/interrupt-controller/arch_timer.txt
     // These are fixed interrupt numbers for the timer device.
-    let irqs = [
-        AARCH64_ARCH_TIMER_PHYS_SECURE_IRQ,
-        AARCH64_ARCH_TIMER_PHYS_NONSECURE_IRQ,
-        AARCH64_ARCH_TIMER_VIRT_IRQ,
-        AARCH64_ARCH_TIMER_HYP_IRQ,
-    ];
+    let irqs = [13, 14, 11, 10];
     let compatible = "arm,armv8-timer";
 
     let mut timer_reg_cells: Vec<u32> = Vec::new();
@@ -838,21 +564,6 @@ fn create_gpio_node<T: DeviceInfoForFdt + Clone + Debug>(
     Ok(())
 }
 
-// https://www.kernel.org/doc/Documentation/devicetree/bindings/arm/fw-cfg.txt
-#[cfg(feature = "fw_cfg")]
-fn create_fw_cfg_node<T: DeviceInfoForFdt + Clone + Debug>(
-    fdt: &mut FdtWriter,
-    dev_info: &T,
-) -> FdtWriterResult<()> {
-    // FwCfg node
-    let fw_cfg_node = fdt.begin_node(&format!("fw-cfg@{:x}", dev_info.addr()))?;
-    fdt.property("compatible", b"qemu,fw-cfg-mmio\0")?;
-    fdt.property_array_u64("reg", &[dev_info.addr(), dev_info.length()])?;
-    fdt.end_node(fw_cfg_node)?;
-
-    Ok(())
-}
-
 fn create_devices_node<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::BuildHasher>(
     fdt: &mut FdtWriter,
     dev_info: &HashMap<(DeviceType, String), T, S>,
@@ -868,8 +579,6 @@ fn create_devices_node<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::Buil
             DeviceType::Virtio(_) => {
                 ordered_virtio_device.push(info);
             }
-            #[cfg(feature = "fw_cfg")]
-            DeviceType::FwCfg => create_fw_cfg_node(fdt, info)?,
         }
     }
 
@@ -909,7 +618,7 @@ fn create_pci_nodes(
     for pci_device_info_elem in pci_device_info.iter() {
         // EDK2 requires the PCIe high space above 4G address.
         // The actual space in CLH follows the RAM. If the RAM space is small, the PCIe high space
-        // could fall below 4G.
+        // could fall bellow 4G.
         // Here we cut off PCI device space below 8G in FDT to workaround the EDK2 check.
         // But the address written in ACPI is not impacted.
         let (pci_device_base_64bit, pci_device_size_64bit) =
@@ -999,39 +708,39 @@ fn create_pci_nodes(
         fdt.property_array_u32("msi-map", &msi_map)?;
         fdt.property_u32("msi-parent", MSI_PHANDLE)?;
 
-        if pci_device_info_elem.pci_segment_id == 0
-            && let Some(virtio_iommu_bdf) = virtio_iommu_bdf
-        {
-            // See kernel document Documentation/devicetree/bindings/pci/pci-iommu.txt
-            // for 'iommu-map' attribute setting.
-            let iommu_map = [
-                0_u32,
-                VIRTIO_IOMMU_PHANDLE,
-                0_u32,
-                virtio_iommu_bdf,
-                virtio_iommu_bdf + 1,
-                VIRTIO_IOMMU_PHANDLE,
-                virtio_iommu_bdf + 1,
-                0xffff - virtio_iommu_bdf,
-            ];
-            fdt.property_array_u32("iommu-map", &iommu_map)?;
+        if pci_device_info_elem.pci_segment_id == 0 {
+            if let Some(virtio_iommu_bdf) = virtio_iommu_bdf {
+                // See kernel document Documentation/devicetree/bindings/pci/pci-iommu.txt
+                // for 'iommu-map' attribute setting.
+                let iommu_map = [
+                    0_u32,
+                    VIRTIO_IOMMU_PHANDLE,
+                    0_u32,
+                    virtio_iommu_bdf,
+                    virtio_iommu_bdf + 1,
+                    VIRTIO_IOMMU_PHANDLE,
+                    virtio_iommu_bdf + 1,
+                    0xffff - virtio_iommu_bdf,
+                ];
+                fdt.property_array_u32("iommu-map", &iommu_map)?;
 
-            // See kernel document Documentation/devicetree/bindings/virtio/iommu.txt
-            // for virtio-iommu node settings.
-            let virtio_iommu_node_name = format!("virtio_iommu@{virtio_iommu_bdf:x}");
-            let virtio_iommu_node = fdt.begin_node(&virtio_iommu_node_name)?;
-            fdt.property_u32("#iommu-cells", 1)?;
-            fdt.property_string("compatible", "virtio,pci-iommu")?;
+                // See kernel document Documentation/devicetree/bindings/virtio/iommu.txt
+                // for virtio-iommu node settings.
+                let virtio_iommu_node_name = format!("virtio_iommu@{virtio_iommu_bdf:x}");
+                let virtio_iommu_node = fdt.begin_node(&virtio_iommu_node_name)?;
+                fdt.property_u32("#iommu-cells", 1)?;
+                fdt.property_string("compatible", "virtio,pci-iommu")?;
 
-            // 'reg' is a five-cell address encoded as
-            // (phys.hi phys.mid phys.lo size.hi size.lo). phys.hi should contain the
-            // device's BDF as 0b00000000 bbbbbbbb dddddfff 00000000. The other cells
-            // should be zero.
-            let reg = [virtio_iommu_bdf << 8, 0_u32, 0_u32, 0_u32, 0_u32];
-            fdt.property_array_u32("reg", &reg)?;
-            fdt.property_u32("phandle", VIRTIO_IOMMU_PHANDLE)?;
+                // 'reg' is a five-cell address encoded as
+                // (phys.hi phys.mid phys.lo size.hi size.lo). phys.hi should contain the
+                // device's BDF as 0b00000000 bbbbbbbb dddddfff 00000000. The other cells
+                // should be zero.
+                let reg = [virtio_iommu_bdf << 8, 0_u32, 0_u32, 0_u32, 0_u32];
+                fdt.property_array_u32("reg", &reg)?;
+                fdt.property_u32("phandle", VIRTIO_IOMMU_PHANDLE)?;
 
-            fdt.end_node(virtio_iommu_node)?;
+                fdt.end_node(virtio_iommu_node)?;
+            }
         }
 
         fdt.end_node(pci_node)?;
@@ -1126,7 +835,10 @@ fn print_node(node: fdt_parser::node::FdtNode<'_, '_>, n_spaces: usize) {
         //   - At first, try to convert it to CStr and print,
         //   - If failed, print it as u32 array.
         let value_result = match CStr::from_bytes_with_nul(value) {
-            Ok(value_cstr) => value_cstr.to_str().ok(),
+            Ok(value_cstr) => match value_cstr.to_str() {
+                Ok(value_str) => Some(value_str),
+                Err(_e) => None,
+            },
             Err(_e) => None,
         };
 

arch/src/aarch64/layout.rs

@@ -111,9 +111,8 @@ pub const RAM_64BIT_START: GuestAddress = GuestAddress(0x1_0000_0000);
 pub const CMDLINE_MAX_SIZE: usize = 2048;
 
 /// FDT is at the beginning of RAM.
+/// Maximum size of the device tree blob as specified in https://www.kernel.org/doc/Documentation/arm64/booting.txt.
 pub const FDT_START: GuestAddress = RAM_START;
-/// Maximum size of the device tree blob as specified in [the kernel
-/// documentation](https://www.kernel.org/doc/Documentation/arm64/booting.txt).
 pub const FDT_MAX_SIZE: u64 = 0x20_0000;
 
 /// Put ACPI table above dtb
@@ -138,12 +137,3 @@ pub const IRQ_BASE: u32 = 32;
 
 /// Number of supported interrupts
 pub const IRQ_NUM: u32 = 256;
-
-/// Base SPI interrupt number
-pub const SPI_BASE: u32 = 32;
-
-/// Total number of SPIs
-pub const SPI_NUM: u32 = 64;
-
-/// GICv2M compatible string
-pub const GIC_V2M_COMPATIBLE: &str = "arm,gic-v2m-frame";

arch/src/aarch64/mod.rs

@@ -6,56 +6,54 @@
 pub mod fdt;
 /// Layout for this aarch64 system.
 pub mod layout;
+/// Module for system registers definition
+pub mod regs;
 /// Module for loading UEFI binary.
 pub mod uefi;
 
-use std::collections::HashMap;
-use std::fmt::Debug;
-use std::sync::{Arc, Mutex};
-
-use hypervisor::arch::aarch64::gic::Vgic;
-use hypervisor::arch::aarch64::regs::MPIDR_EL1;
-use log::{Level, log_enabled};
-use thiserror::Error;
-use vm_memory::{Address, GuestAddress, GuestMemory, GuestMemoryAtomic};
-
 pub use self::fdt::DeviceInfoForFdt;
 use crate::{DeviceType, GuestMemoryMmap, NumaNodes, PciSpaceInfo, RegionType};
+use hypervisor::arch::aarch64::gic::Vgic;
+use log::{log_enabled, Level};
+use std::collections::HashMap;
+use std::convert::TryInto;
+use std::fmt::Debug;
+use std::sync::{Arc, Mutex};
+use vm_memory::{Address, GuestAddress, GuestMemory, GuestMemoryAtomic};
 
 pub const _NSIG: i32 = 65;
 
 /// Errors thrown while configuring aarch64 system.
-#[derive(Debug, Error)]
+#[derive(Debug)]
 pub enum Error {
     /// Failed to create a FDT.
-    #[error("Failed to create a FDT")]
     SetupFdt,
 
     /// Failed to write FDT to memory.
-    #[error("Failed to write FDT to memory")]
-    WriteFdtToMemory(#[source] fdt::Error),
+    WriteFdtToMemory(fdt::Error),
 
     /// Failed to create a GIC.
-    #[error("Failed to create a GIC")]
     SetupGic,
 
     /// Failed to compute the initramfs address.
-    #[error("Failed to compute the initramfs address")]
     InitramfsAddress,
 
     /// Error configuring the general purpose registers
-    #[error("Error configuring the general purpose registers")]
-    RegsConfiguration(#[source] hypervisor::HypervisorCpuError),
+    RegsConfiguration(hypervisor::HypervisorCpuError),
 
     /// Error configuring the MPIDR register
-    #[error("Error configuring the MPIDR register")]
-    VcpuRegMpidr(#[source] hypervisor::HypervisorCpuError),
+    VcpuRegMpidr(hypervisor::HypervisorCpuError),
 
     /// Error initializing PMU for vcpu
-    #[error("Error initializing PMU for vcpu")]
     VcpuInitPmu,
 }
 
+impl From<Error> for super::Error {
+    fn from(e: Error) -> super::Error {
+        super::Error::PlatformSpecific(e)
+    }
+}
+
 #[derive(Debug, Copy, Clone)]
 /// Specifies the entry point address where the guest must start
 /// executing code.
@@ -67,7 +65,7 @@ pub struct EntryPoint {
 /// Configure the specified VCPU, and return its MPIDR.
 pub fn configure_vcpu(
     vcpu: &Arc<dyn hypervisor::Vcpu>,
-    id: u32,
+    id: u8,
     boot_setup: Option<(EntryPoint, &GuestMemoryAtomic<GuestMemoryMmap>)>,
 ) -> super::Result<u64> {
     if let Some((kernel_entry_point, _guest_memory)) = boot_setup {
@@ -79,7 +77,9 @@ pub fn configure_vcpu(
         .map_err(Error::RegsConfiguration)?;
     }
 
-    let mpidr = vcpu.get_sys_reg(MPIDR_EL1).map_err(Error::VcpuRegMpidr)?;
+    let mpidr = vcpu
+        .get_sys_reg(regs::MPIDR_EL1)
+        .map_err(Error::VcpuRegMpidr)?;
     Ok(mpidr)
 }
 
@@ -126,7 +126,7 @@ pub fn configure_system<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::Bui
     guest_mem: &GuestMemoryMmap,
     cmdline: &str,
     vcpu_mpidr: Vec<u64>,
-    vcpu_topology: Option<(u16, u16, u16, u16)>,
+    vcpu_topology: Option<(u8, u8, u8)>,
     device_info: &HashMap<(DeviceType, String), T, S>,
     initrd: &Option<super::InitramfsConfig>,
     pci_space_info: &[PciSpaceInfo],
@@ -180,8 +180,11 @@ pub fn initramfs_load_addr(
     }
 }
 
-pub fn get_host_cpu_phys_bits(hypervisor: &Arc<dyn hypervisor::Hypervisor>) -> u8 {
-    let host_cpu_phys_bits = hypervisor.get_host_ipa_limit().try_into().unwrap();
+pub fn get_host_cpu_phys_bits() -> u8 {
+    // A dummy hypervisor created only for querying the host IPA size and will
+    // be freed after the query.
+    let hv = hypervisor::new().unwrap();
+    let host_cpu_phys_bits = hv.get_host_ipa_limit().try_into().unwrap();
     if host_cpu_phys_bits == 0 {
         // Host kernel does not support `get_host_ipa_limit`,
         // we return the default value 40 here.

arch/src/aarch64/regs.rs

@@ -0,0 +1,43 @@
+// Copyright 2022 Arm Limited (or its affiliates). All rights reserved.
+// SPDX-License-Identifier: Apache-2.0
+
+// AArch64 system register encoding:
+// See https://developer.arm.com/documentation/ddi0487 (chapter D12)
+//
+//   31      22  21 20 19 18 16 15 12 11  8 7   5 4  0
+//  +----------+---+-----+-----+-----+-----+-----+----+
+//  |1101010100| L | op0 | op1 | CRn | CRm | op2 | Rt |
+//  +----------+---+-----+-----+-----+-----+-----+----+
+//
+// Notes:
+// - L and Rt are reserved as implementation defined fields, ignored.
+
+const SYSREG_HEAD: u32 = 0b1101010100u32 << 22;
+const SYSREG_OP0_SHIFT: u32 = 19;
+const SYSREG_OP0_MASK: u32 = 0b11u32 << 19;
+const SYSREG_OP1_SHIFT: u32 = 16;
+const SYSREG_OP1_MASK: u32 = 0b111u32 << 16;
+const SYSREG_CRN_SHIFT: u32 = 12;
+const SYSREG_CRN_MASK: u32 = 0b1111u32 << 12;
+const SYSREG_CRM_SHIFT: u32 = 8;
+const SYSREG_CRM_MASK: u32 = 0b1111u32 << 8;
+const SYSREG_OP2_SHIFT: u32 = 5;
+const SYSREG_OP2_MASK: u32 = 0b111u32 << 5;
+
+/// Define the ID of system registers
+#[macro_export]
+macro_rules! arm64_sys_reg {
+    ($name: tt, $op0: tt, $op1: tt, $crn: tt, $crm: tt, $op2: tt) => {
+        pub const $name: u32 = SYSREG_HEAD
+            | ((($op0 as u32) << SYSREG_OP0_SHIFT) & SYSREG_OP0_MASK as u32)
+            | ((($op1 as u32) << SYSREG_OP1_SHIFT) & SYSREG_OP1_MASK as u32)
+            | ((($crn as u32) << SYSREG_CRN_SHIFT) & SYSREG_CRN_MASK as u32)
+            | ((($crm as u32) << SYSREG_CRM_SHIFT) & SYSREG_CRM_MASK as u32)
+            | ((($op2 as u32) << SYSREG_OP2_SHIFT) & SYSREG_OP2_MASK as u32);
+    };
+}
+
+arm64_sys_reg!(MPIDR_EL1, 3, 0, 0, 0, 5);
+arm64_sys_reg!(ID_AA64MMFR0_EL1, 3, 0, 0, 7, 0);
+arm64_sys_reg!(TTBR1_EL1, 3, 0, 2, 0, 1);
+arm64_sys_reg!(TCR_EL1, 3, 0, 2, 0, 2);

arch/src/aarch64/uefi.rs

@@ -1,28 +1,19 @@
 // Copyright 2020 Arm Limited (or its affiliates). All rights reserved.
-//
-// SPDX-License-Identifier: Apache-2.0
 
 use std::io::{Read, Seek, SeekFrom};
-use std::os::fd::AsFd;
 use std::result;
-
-use thiserror::Error;
-use vm_memory::{GuestAddress, GuestMemory};
+use vm_memory::{Bytes, GuestAddress, GuestMemory};
 
 /// Errors thrown while loading UEFI binary
-#[derive(Debug, Error)]
+#[derive(Debug)]
 pub enum Error {
     /// Unable to seek to UEFI image start.
-    #[error("Unable to seek to UEFI image start")]
     SeekUefiStart,
     /// Unable to seek to UEFI image end.
-    #[error("Unable to seek to UEFI image end")]
     SeekUefiEnd,
     /// UEFI image too big.
-    #[error("UEFI image too big")]
     UefiTooBig,
     /// Unable to read UEFI image
-    #[error("Unable to read UEFI image")]
     ReadUefiImage,
 }
 type Result<T> = result::Result<T, Error>;
@@ -33,7 +24,7 @@ pub fn load_uefi<F, M: GuestMemory>(
     uefi_image: &mut F,
 ) -> Result<()>
 where
-    F: Read + Seek + AsFd,
+    F: Read + Seek,
 {
     let uefi_size = uefi_image
         .seek(SeekFrom::End(0))
@@ -45,6 +36,6 @@ where
     }
     uefi_image.rewind().map_err(|_| Error::SeekUefiStart)?;
     guest_mem
-        .read_exact_volatile_from(guest_addr, &mut uefi_image.as_fd(), uefi_size)
+        .read_exact_from(guest_addr, uefi_image, uefi_size)
         .map_err(|_| Error::ReadUefiImage)
 }

arch/src/lib.rs

@@ -1,4 +1,3 @@
-// Copyright © 2024 Institute of Software, CAS. All rights reserved.
 // Copyright 2020 Arm Limited (or its affiliates). All rights reserved.
 // Copyright © 2020, Oracle and/or its affiliates.
 //
@@ -6,17 +5,22 @@
 // SPDX-License-Identifier: Apache-2.0
 
 //! Implements platform specific functionality.
-//! Supported platforms: x86_64, aarch64, riscv64.
+//! Supported platforms: x86_64, aarch64.
 
 #[macro_use]
 extern crate log;
 
-use std::collections::BTreeMap;
-use std::sync::Arc;
-use std::{fmt, result};
-
+#[cfg(target_arch = "x86_64")]
+use crate::x86_64::SgxEpcSection;
 use serde::{Deserialize, Serialize};
+use std::collections::BTreeMap;
+use std::fmt;
+use std::result;
+use std::sync::Arc;
 use thiserror::Error;
+use versionize::{VersionMap, Versionize, VersionizeError, VersionizeResult};
+use versionize_derive::Versionize;
+use vm_migration::VersionMapped;
 
 type GuestMemoryMmap = vm_memory::GuestMemoryMmap<vm_memory::bitmap::AtomicBitmap>;
 type GuestRegionMmap = vm_memory::GuestRegionMmap<vm_memory::bitmap::AtomicBitmap>;
@@ -25,14 +29,11 @@ type GuestRegionMmap = vm_memory::GuestRegionMmap<vm_memory::bitmap::AtomicBitma
 #[derive(Debug, Error)]
 pub enum Error {
     #[cfg(target_arch = "x86_64")]
-    #[error("Platform specific error (x86_64)")]
-    PlatformSpecific(#[from] x86_64::Error),
+    #[error("Platform specific error (x86_64): {0:?}")]
+    PlatformSpecific(x86_64::Error),
     #[cfg(target_arch = "aarch64")]
-    #[error("Platform specific error (aarch64)")]
-    PlatformSpecific(#[from] aarch64::Error),
-    #[cfg(target_arch = "riscv64")]
-    #[error("Platform specific error (riscv64)")]
-    PlatformSpecific(#[from] riscv64::Error),
+    #[error("Platform specific error (aarch64): {0:?}")]
+    PlatformSpecific(aarch64::Error),
     #[error("The memory map table extends past the end of guest memory")]
     MemmapTablePastRamEnd,
     #[error("Error writing memory map table to guest memory")]
@@ -43,21 +44,17 @@ pub enum Error {
     StartInfoSetup,
     #[error("Failed to compute initramfs address")]
     InitramfsAddress,
-    #[error("Error writing module entry to guest memory")]
+    #[error("Error writing module entry to guest memory: {0}")]
     ModlistSetup(#[source] vm_memory::GuestMemoryError),
     #[error("RSDP extends past the end of guest memory")]
     RsdpPastRamEnd,
-    #[error("Failed to setup Zero Page for bzImage")]
-    ZeroPageSetup(#[source] vm_memory::GuestMemoryError),
-    #[error("Zero Page for bzImage past RAM end")]
-    ZeroPagePastRamEnd,
 }
 
 /// Type for returning public functions outcome.
 pub type Result<T> = result::Result<T, Error>;
 
 /// Type for memory region types.
-#[derive(Clone, Copy, PartialEq, Eq, Debug, Serialize, Deserialize)]
+#[derive(Clone, Copy, PartialEq, Eq, Debug, Serialize, Deserialize, Versionize)]
 pub enum RegionType {
     /// RAM type
     Ram,
@@ -75,26 +72,17 @@ pub enum RegionType {
     Reserved,
 }
 
+impl VersionMapped for RegionType {}
+
 /// Module for aarch64 related functionality.
 #[cfg(target_arch = "aarch64")]
 pub mod aarch64;
 
 #[cfg(target_arch = "aarch64")]
 pub use aarch64::{
-    _NSIG, EntryPoint, arch_memory_regions, configure_system, configure_vcpu,
-    fdt::DeviceInfoForFdt, get_host_cpu_phys_bits, initramfs_load_addr, layout,
-    layout::CMDLINE_MAX_SIZE, layout::IRQ_BASE, uefi,
-};
-
-/// Module for riscv64 related functionality.
-#[cfg(target_arch = "riscv64")]
-pub mod riscv64;
-
-#[cfg(target_arch = "riscv64")]
-pub use riscv64::{
-    _NSIG, EntryPoint, arch_memory_regions, configure_system, configure_vcpu,
-    fdt::DeviceInfoForFdt, get_host_cpu_phys_bits, initramfs_load_addr, layout,
-    layout::CMDLINE_MAX_SIZE, layout::IRQ_BASE, uefi,
+    arch_memory_regions, configure_system, configure_vcpu, fdt::DeviceInfoForFdt,
+    get_host_cpu_phys_bits, initramfs_load_addr, layout, layout::CMDLINE_MAX_SIZE,
+    layout::IRQ_BASE, uefi, EntryPoint, _NSIG,
 };
 
 #[cfg(target_arch = "x86_64")]
@@ -102,9 +90,9 @@ pub mod x86_64;
 
 #[cfg(target_arch = "x86_64")]
 pub use x86_64::{
-    _NSIG, CpuidConfig, CpuidFeatureEntry, EntryPoint, arch_memory_regions, configure_system,
-    configure_vcpu, generate_common_cpuid, generate_ram_ranges, get_host_cpu_phys_bits,
-    initramfs_load_addr, layout, layout::CMDLINE_MAX_SIZE, layout::CMDLINE_START, regs,
+    arch_memory_regions, configure_system, configure_vcpu, generate_common_cpuid,
+    get_host_cpu_phys_bits, initramfs_load_addr, layout, layout::CMDLINE_MAX_SIZE,
+    layout::CMDLINE_START, regs, CpuidFeatureEntry, EntryPoint, _NSIG,
 };
 
 /// Safe wrapper for `sysconf(_SC_PAGESIZE)`.
@@ -119,10 +107,11 @@ fn pagesize() -> usize {
 pub struct NumaNode {
     pub memory_regions: Vec<Arc<GuestRegionMmap>>,
     pub hotplug_regions: Vec<Arc<GuestRegionMmap>>,
-    pub cpus: Vec<u32>,
-    pub pci_segments: Vec<u16>,
+    pub cpus: Vec<u8>,
     pub distances: BTreeMap<u32, u8>,
     pub memory_zones: Vec<String>,
+    #[cfg(target_arch = "x86_64")]
+    pub sgx_epc_sections: Vec<SgxEpcSection>,
 }
 
 pub type NumaNodes = BTreeMap<u32, NumaNode>;
@@ -141,7 +130,7 @@ pub enum DeviceType {
     /// Device Type: Virtio.
     Virtio(u32),
     /// Device Type: Serial.
-    #[cfg(any(target_arch = "aarch64", target_arch = "riscv64"))]
+    #[cfg(target_arch = "aarch64")]
     Serial,
     /// Device Type: RTC.
     #[cfg(target_arch = "aarch64")]
@@ -149,9 +138,6 @@ pub enum DeviceType {
     /// Device Type: GPIO.
     #[cfg(target_arch = "aarch64")]
     Gpio,
-    /// Device Type: fw_cfg.
-    #[cfg(feature = "fw_cfg")]
-    FwCfg,
 }
 
 /// Default (smallest) memory page size for the supported architectures.
@@ -165,7 +151,7 @@ impl fmt::Display for DeviceType {
 
 /// Structure to describe MMIO device information
 #[derive(Clone, Debug)]
-#[cfg(any(target_arch = "aarch64", target_arch = "riscv64"))]
+#[cfg(target_arch = "aarch64")]
 pub struct MmioDeviceInfo {
     pub addr: u64,
     pub len: u64,
@@ -174,7 +160,7 @@ pub struct MmioDeviceInfo {
 
 /// Structure to describe PCI space information
 #[derive(Clone, Debug)]
-#[cfg(any(target_arch = "aarch64", target_arch = "riscv64"))]
+#[cfg(target_arch = "aarch64")]
 pub struct PciSpaceInfo {
     pub pci_segment_id: u16,
     pub mmio_config_address: u64,
@@ -182,7 +168,7 @@ pub struct PciSpaceInfo {
     pub pci_device_space_size: u64,
 }
 
-#[cfg(any(target_arch = "aarch64", target_arch = "riscv64"))]
+#[cfg(target_arch = "aarch64")]
 impl DeviceInfoForFdt for MmioDeviceInfo {
     fn addr(&self) -> u64 {
         self.addr

arch/src/riscv64/fdt.rs

@@ -1,481 +0,0 @@
-// Copyright © 2024 Institute of Software, CAS. All rights reserved.
-// Copyright 2020 Arm Limited (or its affiliates). All rights reserved.
-// Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
-// SPDX-License-Identifier: Apache-2.0
-//
-// Portions Copyright 2017 The Chromium OS Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the THIRD-PARTY file.
-
-use std::collections::HashMap;
-use std::ffi::CStr;
-use std::fmt::Debug;
-use std::sync::{Arc, Mutex};
-use std::{cmp, result, str};
-
-use byteorder::{BigEndian, ByteOrder};
-use hypervisor::arch::riscv64::aia::Vaia;
-use thiserror::Error;
-use vm_fdt::{FdtWriter, FdtWriterResult};
-use vm_memory::{Address, Bytes, GuestMemory, GuestMemoryError, GuestMemoryRegion};
-
-use super::super::{DeviceType, GuestMemoryMmap, InitramfsConfig};
-use super::layout::{
-    IRQ_BASE, MEM_32BIT_DEVICES_SIZE, MEM_32BIT_DEVICES_START, MEM_PCI_IO_SIZE, MEM_PCI_IO_START,
-    PCI_HIGH_BASE, PCI_MMIO_CONFIG_SIZE_PER_SEGMENT,
-};
-use crate::PciSpaceInfo;
-
-const AIA_APLIC_PHANDLE: u32 = 1;
-const AIA_IMSIC_PHANDLE: u32 = 2;
-const CPU_INTC_BASE_PHANDLE: u32 = 3;
-const CPU_BASE_PHANDLE: u32 = 256 + CPU_INTC_BASE_PHANDLE;
-// Read the documentation specified when appending the root node to the FDT.
-const ADDRESS_CELLS: u32 = 0x2;
-const SIZE_CELLS: u32 = 0x2;
-
-// From https://elixir.bootlin.com/linux/v6.10/source/include/dt-bindings/interrupt-controller/irq.h#L14
-const _IRQ_TYPE_EDGE_RISING: u32 = 1;
-const IRQ_TYPE_LEVEL_HI: u32 = 4;
-
-const S_MODE_EXT_IRQ: u32 = 9;
-
-/// Trait for devices to be added to the Flattened Device Tree.
-pub trait DeviceInfoForFdt {
-    /// Returns the address where this device will be loaded.
-    fn addr(&self) -> u64;
-    /// Returns the associated interrupt for this device.
-    fn irq(&self) -> u32;
-    /// Returns the amount of memory that needs to be reserved for this device.
-    fn length(&self) -> u64;
-}
-
-/// Errors thrown while configuring the Flattened Device Tree for riscv64.
-#[derive(Debug, Error)]
-pub enum Error {
-    /// Failure in writing FDT in memory.
-    #[error("Failure in writing FDT in memory")]
-    WriteFdtToMemory(#[source] GuestMemoryError),
-}
-type Result<T> = result::Result<T, Error>;
-
-/// Creates the flattened device tree for this riscv64 VM.
-#[allow(clippy::too_many_arguments)]
-pub fn create_fdt<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::BuildHasher>(
-    guest_mem: &GuestMemoryMmap,
-    cmdline: &str,
-    num_vcpu: u32,
-    device_info: &HashMap<(DeviceType, String), T, S>,
-    aia_device: &Arc<Mutex<dyn Vaia>>,
-    initrd: &Option<InitramfsConfig>,
-    pci_space_info: &[PciSpaceInfo],
-) -> FdtWriterResult<Vec<u8>> {
-    // Allocate stuff necessary for the holding the blob.
-    let mut fdt = FdtWriter::new()?;
-
-    // For an explanation why these nodes were introduced in the blob take a look at
-    // https://github.com/devicetree-org/devicetree-specification/releases/tag/v0.4
-    // In chapter 3.
-
-    // Header or the root node as per above mentioned documentation.
-    let root_node = fdt.begin_node("")?;
-    fdt.property_string("compatible", "linux,dummy-virt")?;
-    // For info on #address-cells and size-cells resort to Table 3.1 Root Node
-    // Properties
-    fdt.property_u32("#address-cells", ADDRESS_CELLS)?;
-    fdt.property_u32("#size-cells", SIZE_CELLS)?;
-    create_cpu_nodes(&mut fdt, num_vcpu)?;
-    create_memory_node(&mut fdt, guest_mem)?;
-    create_chosen_node(&mut fdt, cmdline, initrd)?;
-    create_aia_node(&mut fdt, aia_device)?;
-    create_devices_node(&mut fdt, device_info)?;
-    create_pci_nodes(&mut fdt, pci_space_info)?;
-
-    // End Header node.
-    fdt.end_node(root_node)?;
-
-    let fdt_final = fdt.finish()?;
-
-    Ok(fdt_final)
-}
-
-pub fn write_fdt_to_memory(fdt_final: Vec<u8>, guest_mem: &GuestMemoryMmap) -> Result<()> {
-    // Write FDT to memory.
-    guest_mem
-        .write_slice(fdt_final.as_slice(), super::layout::FDT_START)
-        .map_err(Error::WriteFdtToMemory)?;
-    Ok(())
-}
-
-// Following are the auxiliary function for creating the different nodes that we append to our FDT.
-fn create_cpu_nodes(fdt: &mut FdtWriter, num_cpus: u32) -> FdtWriterResult<()> {
-    // See https://elixir.bootlin.com/linux/v6.10/source/Documentation/devicetree/bindings/riscv/cpus.yaml
-    let cpus = fdt.begin_node("cpus")?;
-    // As per documentation, on RISC-V 64-bit systems value should be set to 1.
-    fdt.property_u32("#address-cells", 0x01)?;
-    fdt.property_u32("#size-cells", 0x0)?;
-    // TODO: Retrieve CPU frequency from cpu timer regs
-    let timebase_frequency: u32 = 0x989680;
-    fdt.property_u32("timebase-frequency", timebase_frequency)?;
-
-    for cpu_index in 0..num_cpus {
-        let cpu = fdt.begin_node(&format!("cpu@{cpu_index:x}"))?;
-        fdt.property_string("device_type", "cpu")?;
-        fdt.property_string("compatible", "riscv")?;
-        fdt.property_string("mmu-type", "sv48")?;
-        fdt.property_string("riscv,isa", "rv64imafdc_smaia_ssaia")?;
-        fdt.property_string("status", "okay")?;
-        fdt.property_u32("reg", cpu_index)?;
-        fdt.property_u32("phandle", CPU_BASE_PHANDLE + cpu_index)?;
-
-        // interrupt controller node
-        let intc_node = fdt.begin_node("interrupt-controller")?;
-        fdt.property_string("compatible", "riscv,cpu-intc")?;
-        fdt.property_u32("#interrupt-cells", 1u32)?;
-        fdt.property_null("interrupt-controller")?;
-        fdt.property_u32("phandle", CPU_INTC_BASE_PHANDLE + cpu_index)?;
-        fdt.end_node(intc_node)?;
-
-        fdt.end_node(cpu)?;
-    }
-
-    fdt.end_node(cpus)?;
-
-    Ok(())
-}
-
-fn create_memory_node(fdt: &mut FdtWriter, guest_mem: &GuestMemoryMmap) -> FdtWriterResult<()> {
-    // Note: memory regions from "GuestMemory" are sorted and non-zero sized.
-    let ram_regions = {
-        let mut ram_regions = Vec::new();
-        let mut current_start = guest_mem
-            .iter()
-            .next()
-            .map(GuestMemoryRegion::start_addr)
-            .expect("GuestMemory must have one memory region at least")
-            .raw_value();
-        let mut current_end = current_start;
-
-        for (start, size) in guest_mem
-            .iter()
-            .map(|m| (m.start_addr().raw_value(), m.len()))
-        {
-            if current_end == start {
-                // This zone is continuous with the previous one.
-                current_end += size;
-            } else {
-                ram_regions.push((current_start, current_end));
-
-                current_start = start;
-                current_end = start + size;
-            }
-        }
-
-        ram_regions.push((current_start, current_end));
-
-        ram_regions
-    };
-
-    let mut mem_reg_property = Vec::new();
-    for region in ram_regions {
-        let mem_size = region.1 - region.0;
-        mem_reg_property.push(region.0);
-        mem_reg_property.push(mem_size);
-    }
-
-    let ram_start = super::layout::RAM_START.raw_value();
-    let memory_node_name = format!("memory@{ram_start:x}");
-    let memory_node = fdt.begin_node(&memory_node_name)?;
-    fdt.property_string("device_type", "memory")?;
-    fdt.property_array_u64("reg", &mem_reg_property)?;
-    fdt.end_node(memory_node)?;
-
-    Ok(())
-}
-
-fn create_chosen_node(
-    fdt: &mut FdtWriter,
-    cmdline: &str,
-    initrd: &Option<InitramfsConfig>,
-) -> FdtWriterResult<()> {
-    let chosen_node = fdt.begin_node("chosen")?;
-    fdt.property_string("bootargs", cmdline)?;
-
-    if let Some(initrd_config) = initrd {
-        let initrd_start = initrd_config.address.raw_value();
-        let initrd_end = initrd_config.address.raw_value() + initrd_config.size as u64;
-        fdt.property_u64("linux,initrd-start", initrd_start)?;
-        fdt.property_u64("linux,initrd-end", initrd_end)?;
-    }
-
-    fdt.end_node(chosen_node)?;
-
-    Ok(())
-}
-
-fn create_aia_node(fdt: &mut FdtWriter, aia_device: &Arc<Mutex<dyn Vaia>>) -> FdtWriterResult<()> {
-    // IMSIC
-    if aia_device.lock().unwrap().msi_compatible() {
-        use super::layout::IMSIC_START;
-        let imsic_name = format!("imsics@{:x}", IMSIC_START.0);
-        let imsic_node = fdt.begin_node(&imsic_name)?;
-
-        fdt.property_string(
-            "compatible",
-            aia_device.lock().unwrap().imsic_compatibility(),
-        )?;
-        let imsic_reg_prop = aia_device.lock().unwrap().imsic_properties();
-        fdt.property_array_u32("reg", &imsic_reg_prop)?;
-        fdt.property_u32("#interrupt-cells", 0u32)?;
-        fdt.property_null("interrupt-controller")?;
-        fdt.property_null("msi-controller")?;
-        // TODO complete num-ids
-        fdt.property_u32("riscv,num-ids", 2047u32)?;
-        fdt.property_u32("phandle", AIA_IMSIC_PHANDLE)?;
-
-        let mut irq_cells = Vec::new();
-        let num_cpus = aia_device.lock().unwrap().vcpu_count();
-        for i in 0..num_cpus {
-            irq_cells.push(CPU_INTC_BASE_PHANDLE + i);
-            irq_cells.push(S_MODE_EXT_IRQ);
-        }
-        fdt.property_array_u32("interrupts-extended", &irq_cells)?;
-
-        fdt.end_node(imsic_node)?;
-    }
-
-    // APLIC
-    use super::layout::APLIC_START;
-    let aplic_name = format!("aplic@{:x}", APLIC_START.0);
-    let aplic_node = fdt.begin_node(&aplic_name)?;
-
-    fdt.property_string(
-        "compatible",
-        aia_device.lock().unwrap().aplic_compatibility(),
-    )?;
-    let reg_cells = aia_device.lock().unwrap().aplic_properties();
-    fdt.property_array_u32("reg", &reg_cells)?;
-    fdt.property_u32("#interrupt-cells", 2u32)?;
-    fdt.property_null("interrupt-controller")?;
-    // TODO complete num-srcs
-    fdt.property_u32("riscv,num-sources", 96u32)?;
-    fdt.property_u32("phandle", AIA_APLIC_PHANDLE)?;
-    fdt.property_u32("msi-parent", AIA_IMSIC_PHANDLE)?;
-
-    fdt.end_node(aplic_node)?;
-
-    Ok(())
-}
-
-fn create_serial_node<T: DeviceInfoForFdt + Clone + Debug>(
-    fdt: &mut FdtWriter,
-    dev_info: &T,
-) -> FdtWriterResult<()> {
-    let serial_reg_prop = [dev_info.addr(), dev_info.length()];
-    let irq = [dev_info.irq() - IRQ_BASE, IRQ_TYPE_LEVEL_HI];
-
-    let serial_node = fdt.begin_node(&format!("serial@{:x}", dev_info.addr()))?;
-    fdt.property_string("compatible", "ns16550a")?;
-    fdt.property_array_u64("reg", &serial_reg_prop)?;
-    fdt.property_u32("clock-frequency", 3686400)?;
-    fdt.property_u32("interrupt-parent", AIA_APLIC_PHANDLE)?;
-    fdt.property_array_u32("interrupts", &irq)?;
-    fdt.end_node(serial_node)?;
-
-    Ok(())
-}
-
-fn create_devices_node<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::BuildHasher>(
-    fdt: &mut FdtWriter,
-    dev_info: &HashMap<(DeviceType, String), T, S>,
-) -> FdtWriterResult<()> {
-    for ((device_type, _device_id), info) in dev_info {
-        match device_type {
-            DeviceType::Serial => create_serial_node(fdt, info)?,
-            DeviceType::Virtio(_) => unreachable!(),
-        }
-    }
-
-    Ok(())
-}
-
-fn create_pci_nodes(fdt: &mut FdtWriter, pci_device_info: &[PciSpaceInfo]) -> FdtWriterResult<()> {
-    // Add node for PCIe controller.
-    // See Documentation/devicetree/bindings/pci/host-generic-pci.txt in the kernel
-    // and https://elinux.org/Device_Tree_Usage.
-    // In multiple PCI segments setup, each PCI segment needs a PCI node.
-    for pci_device_info_elem in pci_device_info.iter() {
-        // EDK2 requires the PCIe high space above 4G address.
-        // The actual space in CLH follows the RAM. If the RAM space is small, the PCIe high space
-        // could fall below 4G.
-        // Here we cut off PCI device space below 8G in FDT to workaround the EDK2 check.
-        // But the address written in ACPI is not impacted.
-        let (pci_device_base_64bit, pci_device_size_64bit) =
-            if pci_device_info_elem.pci_device_space_start < PCI_HIGH_BASE.raw_value() {
-                (
-                    PCI_HIGH_BASE.raw_value(),
-                    pci_device_info_elem.pci_device_space_size
-                        - (PCI_HIGH_BASE.raw_value() - pci_device_info_elem.pci_device_space_start),
-                )
-            } else {
-                (
-                    pci_device_info_elem.pci_device_space_start,
-                    pci_device_info_elem.pci_device_space_size,
-                )
-            };
-        // There is no specific requirement of the 32bit MMIO range, and
-        // therefore at least we can make these ranges 4K aligned.
-        let pci_device_size_32bit: u64 =
-            MEM_32BIT_DEVICES_SIZE / ((1 << 12) * pci_device_info.len() as u64) * (1 << 12);
-        let pci_device_base_32bit: u64 = MEM_32BIT_DEVICES_START.0
-            + pci_device_size_32bit * pci_device_info_elem.pci_segment_id as u64;
-
-        let ranges = [
-            // io addresses. Since AArch64 will not use IO address,
-            // we can set the same IO address range for every segment.
-            0x1000000,
-            0_u32,
-            0_u32,
-            (MEM_PCI_IO_START.0 >> 32) as u32,
-            MEM_PCI_IO_START.0 as u32,
-            (MEM_PCI_IO_SIZE >> 32) as u32,
-            MEM_PCI_IO_SIZE as u32,
-            // mmio addresses
-            0x2000000,                            // (ss = 10: 32-bit memory space)
-            (pci_device_base_32bit >> 32) as u32, // PCI address
-            pci_device_base_32bit as u32,
-            (pci_device_base_32bit >> 32) as u32, // CPU address
-            pci_device_base_32bit as u32,
-            (pci_device_size_32bit >> 32) as u32, // size
-            pci_device_size_32bit as u32,
-            // device addresses
-            0x3000000,                            // (ss = 11: 64-bit memory space)
-            (pci_device_base_64bit >> 32) as u32, // PCI address
-            pci_device_base_64bit as u32,
-            (pci_device_base_64bit >> 32) as u32, // CPU address
-            pci_device_base_64bit as u32,
-            (pci_device_size_64bit >> 32) as u32, // size
-            pci_device_size_64bit as u32,
-        ];
-        let bus_range = [0, 0]; // Only bus 0
-        let reg = [
-            pci_device_info_elem.mmio_config_address,
-            PCI_MMIO_CONFIG_SIZE_PER_SEGMENT,
-        ];
-        // See kernel document Documentation/devicetree/bindings/pci/pci-msi.txt
-        let msi_map = [
-            // rid-base: A single cell describing the first RID matched by the entry.
-            0x0,
-            // msi-controller: A single phandle to an MSI controller.
-            AIA_IMSIC_PHANDLE,
-            // msi-base: An msi-specifier describing the msi-specifier produced for the
-            // first RID matched by the entry.
-            (pci_device_info_elem.pci_segment_id as u32) << 8,
-            // length: A single cell describing how many consecutive RIDs are matched
-            // following the rid-base.
-            0x100,
-        ];
-
-        let pci_node_name = format!("pci@{:x}", pci_device_info_elem.mmio_config_address);
-        let pci_node = fdt.begin_node(&pci_node_name)?;
-
-        fdt.property_string("compatible", "pci-host-ecam-generic")?;
-        fdt.property_string("device_type", "pci")?;
-        fdt.property_array_u32("ranges", &ranges)?;
-        fdt.property_array_u32("bus-range", &bus_range)?;
-        fdt.property_u32(
-            "linux,pci-domain",
-            pci_device_info_elem.pci_segment_id as u32,
-        )?;
-        fdt.property_u32("#address-cells", 3)?;
-        fdt.property_u32("#size-cells", 2)?;
-        fdt.property_array_u64("reg", &reg)?;
-        fdt.property_u32("#interrupt-cells", 1)?;
-        fdt.property_null("interrupt-map")?;
-        fdt.property_null("interrupt-map-mask")?;
-        fdt.property_null("dma-coherent")?;
-        fdt.property_array_u32("msi-map", &msi_map)?;
-        fdt.property_u32("msi-parent", AIA_IMSIC_PHANDLE)?;
-
-        fdt.end_node(pci_node)?;
-    }
-
-    Ok(())
-}
-
-// Parse the DTB binary and print for debugging
-pub fn print_fdt(dtb: &[u8]) {
-    match fdt_parser::Fdt::new(dtb) {
-        Ok(fdt) => {
-            if let Some(root) = fdt.find_node("/") {
-                debug!("Printing the FDT:");
-                print_node(root, 0);
-            } else {
-                debug!("Failed to find root node in FDT for debugging.");
-            }
-        }
-        Err(_) => debug!("Failed to parse FDT for debugging."),
-    }
-}
-
-fn print_node(node: fdt_parser::node::FdtNode<'_, '_>, n_spaces: usize) {
-    debug!("{:indent$}{}/", "", node.name, indent = n_spaces);
-    for property in node.properties() {
-        let name = property.name;
-
-        // If the property is 'compatible', its value requires special handling.
-        // The u8 array could contain multiple null-terminated strings.
-        // We copy the original array and simply replace all 'null' characters with spaces.
-        let value = if name == "compatible" {
-            let mut compatible = vec![0u8; 256];
-            let handled_value = property
-                .value
-                .iter()
-                .map(|&c| if c == 0 { b' ' } else { c })
-                .collect::<Vec<_>>();
-            let len = cmp::min(255, handled_value.len());
-            compatible[..len].copy_from_slice(&handled_value[..len]);
-            compatible[..(len + 1)].to_vec()
-        } else {
-            property.value.to_vec()
-        };
-        let value = &value;
-
-        // Now the value can be either:
-        //   - A null-terminated C string, or
-        //   - Binary data
-        // We follow a very simple logic to present the value:
-        //   - At first, try to convert it to CStr and print,
-        //   - If failed, print it as u32 array.
-        let value_result = match CStr::from_bytes_with_nul(value) {
-            Ok(value_cstr) => value_cstr.to_str().ok(),
-            Err(_e) => None,
-        };
-
-        if let Some(value_str) = value_result {
-            debug!(
-                "{:indent$}{} : {:#?}",
-                "",
-                name,
-                value_str,
-                indent = (n_spaces + 2)
-            );
-        } else {
-            let mut array = Vec::with_capacity(256);
-            array.resize(value.len() / 4, 0u32);
-            BigEndian::read_u32_into(value, &mut array);
-            debug!(
-                "{:indent$}{} : {:X?}",
-                "",
-                name,
-                array,
-                indent = (n_spaces + 2)
-            );
-        };
-    }
-
-    // Print children nodes if there is any
-    for child in node.children() {
-        print_node(child, n_spaces + 2);
-    }
-}

arch/src/riscv64/layout.rs

@@ -1,112 +0,0 @@
-// Copyright © 2024 Institute of Software, CAS. All rights reserved.
-// Copyright 2020 Arm Limited (or its affiliates). All rights reserved.
-// Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
-// SPDX-License-Identifier: Apache-2.0
-
-//
-// Memory layout of RISC-V 64-bit guest:
-//
-// Physical  +---------------------------------------------------------------+
-// address   |                                                               |
-// end       |                                                               |
-//           ~                   ~                       ~                   ~
-//           |                                                               |
-//           |                    Highmem PCI MMIO space                     |
-//           |                                                               |
-// RAM end   +---------------------------------------------------------------+
-// (dynamic, |                                                               |
-// including |                                                               |
-// hotplug   ~                   ~                       ~                   ~
-// memory)   |                                                               |
-//           |                             DRAM                              |
-//           |                                                               |
-//           |                                                               |
-//           |                                                               |
-//           |                                                               |
-//    1 GB   +---------------------------------------------------------------+
-//           |                                                               |
-//           |                      PCI MMCONFIG space                       |
-//           |                                                               |
-//  768 MB   +---------------------------------------------------------------+
-//           |                                                               |
-//           |                                                               |
-//           |                        PCI MMIO space                         |
-//           |                                                               |
-//  256 MB   +---------------------------------------------------------------|
-//           |                                                               |
-//           |                     Legacy devices space                      |
-//           |                                                               |
-//  128 MB   +---------------------------------------------------------------|
-//           |                                                               |
-//           |                            IMSICs                             |
-//           |                                                               |
-//   64 MB   +---------------------------------------------------------------+
-//           |                                                               |
-//           |                            APLICs                             |
-//           |                                                               |
-//    4 MB   +---------------------------------------------------------------+
-//           |                          UEFI flash                           |
-//    0 GB   +---------------------------------------------------------------+
-//
-//
-
-use vm_memory::GuestAddress;
-
-/// 0x0 ~ 0x40_0000 (4 MiB) is reserved to UEFI
-/// UEFI binary size is required less than 3 MiB, reserving 4 MiB is enough.
-pub const UEFI_START: GuestAddress = GuestAddress(0);
-pub const UEFI_SIZE: u64 = 0x040_0000;
-
-/// AIA related devices
-/// See https://elixir.bootlin.com/linux/v6.10/source/arch/riscv/include/uapi/asm/kvm.h
-/// 0x40_0000 ~ 0x0400_0000 (64 MiB) resides APLICs
-pub const APLIC_START: GuestAddress = GuestAddress(0x40_0000);
-pub const APLIC_SIZE: u64 = 0x4000;
-
-/// 0x0400_0000 ~ 0x0800_0000 (64 MiB) resides IMSICs
-pub const IMSIC_START: GuestAddress = GuestAddress(0x0400_0000);
-pub const IMSIC_SIZE: u64 = 0x1000;
-
-/// Below this address will reside the AIA, above this address will reside the MMIO devices.
-const MAPPED_IO_START: GuestAddress = GuestAddress(0x0800_0000);
-
-/// Space 0x0800_0000 ~ 0x1000_0000 is reserved for legacy devices.
-pub const LEGACY_SERIAL_MAPPED_IO_START: GuestAddress = MAPPED_IO_START;
-
-/// Space 0x0905_0000 ~ 0x0906_0000 is reserved for pcie io address
-pub const MEM_PCI_IO_START: GuestAddress = GuestAddress(0x0905_0000);
-pub const MEM_PCI_IO_SIZE: u64 = 0x1_0000;
-
-/// Starting from 0x1000_0000 (256MiB) to 0x3000_0000 (768MiB) is used for PCIE MMIO
-pub const MEM_32BIT_DEVICES_START: GuestAddress = GuestAddress(0x1000_0000);
-pub const MEM_32BIT_DEVICES_SIZE: u64 = 0x2000_0000;
-
-/// PCI MMCONFIG space (start: after the device space at 768MiB, length: 256MiB)
-pub const PCI_MMCONFIG_START: GuestAddress = GuestAddress(0x3000_0000);
-pub const PCI_MMCONFIG_SIZE: u64 = 256 << 20;
-// One bus with potentially 256 devices (32 slots x 8 functions).
-pub const PCI_MMIO_CONFIG_SIZE_PER_SEGMENT: u64 = 4096 * 256;
-
-/// Start of RAM.
-pub const RAM_START: GuestAddress = GuestAddress(0x4000_0000);
-
-/// Kernel command line maximum size on RISC-V.
-/// See https://elixir.bootlin.com/linux/v6.10/source/arch/riscv/include/uapi/asm/setup.h
-pub const CMDLINE_MAX_SIZE: usize = 1024;
-
-/// FDT is at the beginning of RAM.
-pub const FDT_START: GuestAddress = RAM_START;
-pub const FDT_MAX_SIZE: u64 = 0x1_0000;
-
-/// Kernel start after FDT
-pub const KERNEL_START: GuestAddress = GuestAddress(RAM_START.0 + FDT_MAX_SIZE);
-
-/// Pci high memory base
-pub const PCI_HIGH_BASE: GuestAddress = GuestAddress(0x2_0000_0000);
-
-/// First usable interrupt on riscv64
-pub const IRQ_BASE: u32 = 0;
-
-// As per https://elixir.bootlin.com/linux/v6.10/source/arch/riscv/include/asm/kvm_host.h#L31
-/// Number of supported interrupts
-pub const IRQ_NUM: u32 = 1023;

arch/src/riscv64/mod.rs

@@ -1,169 +0,0 @@
-// Copyright © 2024 Institute of Software, CAS. All rights reserved.
-// Copyright 2020 Arm Limited (or its affiliates). All rights reserved.
-// Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
-// SPDX-License-Identifier: Apache-2.0
-
-/// Module for the flattened device tree.
-pub mod fdt;
-/// Layout for this riscv64 system.
-pub mod layout;
-/// Module for loading UEFI binary.
-pub mod uefi;
-
-use std::collections::HashMap;
-use std::fmt::Debug;
-use std::sync::{Arc, Mutex};
-
-use hypervisor::arch::riscv64::aia::Vaia;
-use log::{Level, log_enabled};
-use thiserror::Error;
-use vm_memory::{Address, GuestAddress, GuestMemory, GuestMemoryAtomic};
-
-pub use self::fdt::DeviceInfoForFdt;
-use crate::{DeviceType, GuestMemoryMmap, PciSpaceInfo, RegionType};
-
-pub const _NSIG: i32 = 65;
-
-/// Errors thrown while configuring riscv64 system.
-#[derive(Debug, Error)]
-pub enum Error {
-    /// Failed to create a FDT.
-    #[error("Failed to create a FDT")]
-    SetupFdt,
-
-    /// Failed to write FDT to memory.
-    #[error("Failed to write FDT to memory")]
-    WriteFdtToMemory(#[source] fdt::Error),
-
-    /// Failed to create a AIA.
-    #[error("Failed to create a AIA")]
-    SetupAia,
-
-    /// Failed to compute the initramfs address.
-    #[error("Failed to compute the initramfs address")]
-    InitramfsAddress,
-
-    /// Error configuring the general purpose registers
-    #[error("Error configuring the general purpose registers")]
-    RegsConfiguration(#[source] hypervisor::HypervisorCpuError),
-}
-
-#[derive(Debug, Copy, Clone)]
-/// Specifies the entry point address where the guest must start
-/// executing code.
-pub struct EntryPoint {
-    /// Address in guest memory where the guest must start execution
-    pub entry_addr: GuestAddress,
-}
-
-/// Configure the specified VCPU, and return its MPIDR.
-pub fn configure_vcpu(
-    vcpu: &Arc<dyn hypervisor::Vcpu>,
-    id: u32,
-    boot_setup: Option<(EntryPoint, &GuestMemoryAtomic<GuestMemoryMmap>)>,
-) -> super::Result<()> {
-    if let Some((kernel_entry_point, _guest_memory)) = boot_setup {
-        vcpu.setup_regs(
-            id,
-            kernel_entry_point.entry_addr.raw_value(),
-            layout::FDT_START.raw_value(),
-        )
-        .map_err(Error::RegsConfiguration)?;
-    }
-
-    Ok(())
-}
-
-pub fn arch_memory_regions() -> Vec<(GuestAddress, usize, RegionType)> {
-    vec![
-        // 0 MiB ~ 256 MiB: AIA and legacy devices
-        (
-            GuestAddress(0),
-            layout::MEM_32BIT_DEVICES_START.0 as usize,
-            RegionType::Reserved,
-        ),
-        // 256 MiB ~ 768 MiB: MMIO space
-        (
-            layout::MEM_32BIT_DEVICES_START,
-            layout::MEM_32BIT_DEVICES_SIZE as usize,
-            RegionType::SubRegion,
-        ),
-        // 768 MiB ~ 1 GiB: reserved. The leading 256M for PCIe MMCONFIG space
-        (
-            layout::PCI_MMCONFIG_START,
-            layout::PCI_MMCONFIG_SIZE as usize,
-            RegionType::Reserved,
-        ),
-        // 1GiB ~ inf: RAM
-        (layout::RAM_START, usize::MAX, RegionType::Ram),
-    ]
-}
-
-/// Configures the system and should be called once per vm before starting vcpu threads.
-#[allow(clippy::too_many_arguments)]
-pub fn configure_system<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::BuildHasher>(
-    guest_mem: &GuestMemoryMmap,
-    cmdline: &str,
-    num_vcpu: u32,
-    device_info: &HashMap<(DeviceType, String), T, S>,
-    initrd: &Option<super::InitramfsConfig>,
-    pci_space_info: &[PciSpaceInfo],
-    aia_device: &Arc<Mutex<dyn Vaia>>,
-) -> super::Result<()> {
-    let fdt_final = fdt::create_fdt(
-        guest_mem,
-        cmdline,
-        num_vcpu,
-        device_info,
-        aia_device,
-        initrd,
-        pci_space_info,
-    )
-    .map_err(|_| Error::SetupFdt)?;
-
-    if log_enabled!(Level::Debug) {
-        fdt::print_fdt(&fdt_final);
-    }
-
-    fdt::write_fdt_to_memory(fdt_final, guest_mem).map_err(Error::WriteFdtToMemory)?;
-
-    Ok(())
-}
-
-/// Returns the memory address where the initramfs could be loaded.
-pub fn initramfs_load_addr(
-    guest_mem: &GuestMemoryMmap,
-    initramfs_size: usize,
-) -> super::Result<u64> {
-    let round_to_pagesize = |size| (size + (super::PAGE_SIZE - 1)) & !(super::PAGE_SIZE - 1);
-    match guest_mem
-        .last_addr()
-        .checked_sub(round_to_pagesize(initramfs_size) as u64 - 1)
-    {
-        Some(offset) => {
-            if guest_mem.address_in_range(offset) {
-                Ok(offset.raw_value())
-            } else {
-                Err(super::Error::PlatformSpecific(Error::InitramfsAddress))
-            }
-        }
-        None => Err(super::Error::PlatformSpecific(Error::InitramfsAddress)),
-    }
-}
-
-pub fn get_host_cpu_phys_bits(_hypervisor: &Arc<dyn hypervisor::Hypervisor>) -> u8 {
-    40
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_arch_memory_regions_dram() {
-        let regions = arch_memory_regions();
-        assert_eq!(4, regions.len());
-        assert_eq!(layout::RAM_START, regions[3].0);
-        assert_eq!(RegionType::Ram, regions[3].2);
-    }
-}

arch/src/riscv64/uefi.rs

@@ -1,50 +0,0 @@
-// Copyright 2020 Arm Limited (or its affiliates). All rights reserved.
-//
-// SPDX-License-Identifier: Apache-2.0
-
-use std::io::{Read, Seek, SeekFrom};
-use std::os::fd::AsFd;
-use std::result;
-
-use thiserror::Error;
-use vm_memory::{GuestAddress, GuestMemory};
-
-/// Errors thrown while loading UEFI binary
-#[derive(Debug, Error)]
-pub enum Error {
-    /// Unable to seek to UEFI image start.
-    #[error("Unable to seek to UEFI image start")]
-    SeekUefiStart,
-    /// Unable to seek to UEFI image end.
-    #[error("Unable to seek to UEFI image end")]
-    SeekUefiEnd,
-    /// UEFI image too big.
-    #[error("UEFI image too big")]
-    UefiTooBig,
-    /// Unable to read UEFI image
-    #[error("Unable to read UEFI image")]
-    ReadUefiImage,
-}
-type Result<T> = result::Result<T, Error>;
-
-pub fn load_uefi<F, M: GuestMemory>(
-    guest_mem: &M,
-    guest_addr: GuestAddress,
-    uefi_image: &mut F,
-) -> Result<()>
-where
-    F: Read + Seek + AsFd,
-{
-    let uefi_size = uefi_image
-        .seek(SeekFrom::End(0))
-        .map_err(|_| Error::SeekUefiEnd)? as usize;
-
-    // edk2 image on virtual platform is smaller than 3M
-    if uefi_size > 0x300000 {
-        return Err(Error::UefiTooBig);
-    }
-    uefi_image.rewind().map_err(|_| Error::SeekUefiStart)?;
-    guest_mem
-        .read_exact_volatile_from(guest_addr, &mut uefi_image.as_fd(), uefi_size)
-        .map_err(|_| Error::ReadUefiImage)
-}

arch/src/x86_64/mpspec.rs

@@ -1,10 +1,6 @@
 // Copyright 2017 The Chromium OS Authors. All rights reserved.
-//
-// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE-BSD-3-Clause file.
-#![allow(non_camel_case_types)]
-use vm_memory::ByteValued;
 
 pub const MP_PROCESSOR: ::std::os::raw::c_uint = 0;
 pub const MP_BUS: ::std::os::raw::c_uint = 1;
@@ -19,7 +15,7 @@ pub const MP_IRQDIR_DEFAULT: ::std::os::raw::c_uint = 0;
 #[repr(C)]
 #[derive(Debug, Default, Copy, Clone)]
 pub struct mpf_intel {
-    pub signature: [::std::os::raw::c_uchar; 4usize],
+    pub signature: [::std::os::raw::c_char; 4usize],
     pub physptr: ::std::os::raw::c_uint,
     pub length: ::std::os::raw::c_uchar,
     pub specification: ::std::os::raw::c_uchar,
@@ -31,22 +27,15 @@ pub struct mpf_intel {
     pub feature5: ::std::os::raw::c_uchar,
 }
 
-const _: () = assert!(::core::mem::size_of::<mpf_intel>() == 16);
-// SAFETY: all members of this struct are plain integers
-// and the sum of their sizes is the size of the struct, so
-// padding and reserved values are not possible as there
-// would be nowhere for them to exist.
-unsafe impl ByteValued for mpf_intel {}
-
 #[repr(C)]
 #[derive(Debug, Default, Copy, Clone)]
 pub struct mpc_table {
-    pub signature: [::std::os::raw::c_uchar; 4usize],
+    pub signature: [::std::os::raw::c_char; 4usize],
     pub length: ::std::os::raw::c_ushort,
-    pub spec: ::std::os::raw::c_uchar,
-    pub checksum: ::std::os::raw::c_uchar,
-    pub oem: [::std::os::raw::c_uchar; 8usize],
-    pub productid: [::std::os::raw::c_uchar; 12usize],
+    pub spec: ::std::os::raw::c_char,
+    pub checksum: ::std::os::raw::c_char,
+    pub oem: [::std::os::raw::c_char; 8usize],
+    pub productid: [::std::os::raw::c_char; 12usize],
     pub oemptr: ::std::os::raw::c_uint,
     pub oemsize: ::std::os::raw::c_ushort,
     pub oemcount: ::std::os::raw::c_ushort,
@@ -54,19 +43,6 @@ pub struct mpc_table {
     pub reserved: ::std::os::raw::c_uint,
 }
 
-const _: () = {
-    assert!(::core::mem::size_of::<mpc_table>() == 4 + 2 + 1 + 1 + 8 + 12 + 4 + 2 + 2 + 4 + 4);
-    assert!(::core::mem::size_of::<::std::os::raw::c_uint>() == 4);
-    assert!(::core::mem::size_of::<::std::os::raw::c_ushort>() == 2);
-    assert!(::core::mem::size_of::<::std::os::raw::c_uchar>() == 1);
-};
-
-// SAFETY: all members of this struct are plain integers
-// and the sum of their sizes is the size of the struct, so
-// padding and reserved values are not possible as there
-// would be nowhere for them to exist.
-unsafe impl ByteValued for mpc_table {}
-
 #[repr(C)]
 #[derive(Debug, Default, Copy, Clone)]
 pub struct mpc_cpu {
@@ -79,13 +55,6 @@ pub struct mpc_cpu {
     pub reserved: [::std::os::raw::c_uint; 2usize],
 }
 
-const _: () = assert!(::core::mem::size_of::<mpc_cpu>() == 20);
-// SAFETY: all members of this struct are plain integers
-// and the sum of their sizes is the size of the struct, so
-// padding and reserved values are not possible as there
-// would be nowhere for them to exist.
-unsafe impl ByteValued for mpc_cpu {}
-
 #[repr(C)]
 #[derive(Debug, Default, Copy, Clone)]
 pub struct mpc_bus {
@@ -94,13 +63,6 @@ pub struct mpc_bus {
     pub bustype: [::std::os::raw::c_uchar; 6usize],
 }
 
-const _: () = assert!(::core::mem::size_of::<mpc_bus>() == 8);
-// SAFETY: all members of this struct are plain integers
-// and the sum of their sizes is the size of the struct, so
-// padding and reserved values are not possible as there
-// would be nowhere for them to exist.
-unsafe impl ByteValued for mpc_bus {}
-
 #[repr(C)]
 #[derive(Debug, Default, Copy, Clone)]
 pub struct mpc_ioapic {
@@ -111,13 +73,6 @@ pub struct mpc_ioapic {
     pub apicaddr: ::std::os::raw::c_uint,
 }
 
-const _: () = assert!(::core::mem::size_of::<mpc_ioapic>() == 8);
-// SAFETY: all members of this struct are plain integers
-// and the sum of their sizes is the size of the struct, so
-// padding and reserved values are not possible as there
-// would be nowhere for them to exist.
-unsafe impl ByteValued for mpc_ioapic {}
-
 #[repr(C)]
 #[derive(Debug, Default, Copy, Clone)]
 pub struct mpc_intsrc {
@@ -130,13 +85,6 @@ pub struct mpc_intsrc {
     pub dstirq: ::std::os::raw::c_uchar,
 }
 
-const _: () = assert!(::core::mem::size_of::<mpc_intsrc>() == 8);
-// SAFETY: all members of this struct are plain integers
-// and the sum of their sizes is the size of the struct, so
-// padding and reserved values are not possible as there
-// would be nowhere for them to exist.
-unsafe impl ByteValued for mpc_intsrc {}
-
 pub const MP_IRQ_SOURCE_TYPES_MP_INT: ::std::os::raw::c_uint = 0;
 pub const MP_IRQ_SOURCE_TYPES_MP_NMI: ::std::os::raw::c_uint = 1;
 pub const MP_IRQ_SOURCE_TYPES_MP_EXT_INT: ::std::os::raw::c_uint = 3;
@@ -153,26 +101,12 @@ pub struct mpc_lintsrc {
     pub destapiclint: ::std::os::raw::c_uchar,
 }
 
-const _: () = assert!(::core::mem::size_of::<mpc_lintsrc>() == 8);
-// SAFETY: all members of this struct are plain integers
-// and the sum of their sizes is the size of the struct, so
-// padding and reserved values are not possible as there
-// would be nowhere for them to exist.
-unsafe impl ByteValued for mpc_lintsrc {}
-
 #[repr(C)]
 #[derive(Debug, Default, Copy, Clone)]
 pub struct mpc_oemtable {
-    pub signature: [::std::os::raw::c_uchar; 4usize],
+    pub signature: [::std::os::raw::c_char; 4usize],
     pub length: ::std::os::raw::c_ushort,
-    pub rev: ::std::os::raw::c_uchar,
-    pub checksum: ::std::os::raw::c_uchar,
-    pub mpc: [::std::os::raw::c_uchar; 8usize],
+    pub rev: ::std::os::raw::c_char,
+    pub checksum: ::std::os::raw::c_char,
+    pub mpc: [::std::os::raw::c_char; 8usize],
 }
-
-const _: () = assert!(::core::mem::size_of::<mpc_oemtable>() == 16);
-// SAFETY: all members of this struct are plain integers
-// and the sum of their sizes is the size of the struct, so
-// padding and reserved values are not possible as there
-// would be nowhere for them to exist.
-unsafe impl ByteValued for mpc_oemtable {}

arch/src/x86_64/mptable.rs

@@ -5,16 +5,15 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE-BSD-3-Clause file.
 
-use std::{mem, result, slice};
-
-use libc::c_uchar;
-use thiserror::Error;
-use vm_memory::{Address, ByteValued, Bytes, GuestAddress, GuestMemory, GuestMemoryError};
-
-use super::MAX_SUPPORTED_CPUS_LEGACY;
-use crate::GuestMemoryMmap;
 use crate::layout::{APIC_START, HIGH_RAM_START, IOAPIC_START};
-use crate::x86_64::{get_x2apic_id, mpspec};
+use crate::x86_64::mpspec;
+use crate::GuestMemoryMmap;
+use libc::c_char;
+use std::io;
+use std::mem;
+use std::result;
+use std::slice;
+use vm_memory::{Address, ByteValued, Bytes, GuestAddress, GuestMemory, GuestMemoryError};
 
 // This is a workaround to the Rust enforcement specifying that any implementation of a foreign
 // trait (in this case `ByteValued`) where:
@@ -51,55 +50,57 @@ unsafe impl ByteValued for MpcLintsrcWrapper {}
 // SAFETY: see above
 unsafe impl ByteValued for MpfIntelWrapper {}
 
-#[derive(Debug, Error)]
+#[derive(Debug)]
 pub enum Error {
     /// There was too little guest memory to store the entire MP table.
-    #[error("There was too little guest memory to store the entire MP table")]
     NotEnoughMemory,
     /// The MP table has too little address space to be stored.
-    #[error("The MP table has too little address space to be stored")]
     AddressOverflow,
     /// Failure while zeroing out the memory for the MP table.
-    #[error("Failure while zeroing out the memory for the MP table")]
-    Clear(#[source] GuestMemoryError),
+    Clear(GuestMemoryError),
+    /// Number of CPUs exceeds the maximum supported CPUs
+    TooManyCpus,
     /// Failure to write the MP floating pointer.
-    #[error("Failure to write the MP floating pointer")]
-    WriteMpfIntel(#[source] GuestMemoryError),
+    WriteMpfIntel(GuestMemoryError),
     /// Failure to write MP CPU entry.
-    #[error("Failure to write MP CPU entry")]
-    WriteMpcCpu(#[source] GuestMemoryError),
+    WriteMpcCpu(GuestMemoryError),
     /// Failure to write MP ioapic entry.
-    #[error("Failure to write MP ioapic entry")]
-    WriteMpcIoapic(#[source] GuestMemoryError),
+    WriteMpcIoapic(GuestMemoryError),
     /// Failure to write MP bus entry.
-    #[error("Failure to write MP bus entry")]
-    WriteMpcBus(#[source] GuestMemoryError),
+    WriteMpcBus(GuestMemoryError),
     /// Failure to write MP interrupt source entry.
-    #[error("Failure to write MP interrupt source entry")]
-    WriteMpcIntsrc(#[source] GuestMemoryError),
+    WriteMpcIntsrc(GuestMemoryError),
     /// Failure to write MP local interrupt source entry.
-    #[error("Failure to write MP local interrupt source entry")]
-    WriteMpcLintsrc(#[source] GuestMemoryError),
+    WriteMpcLintsrc(GuestMemoryError),
     /// Failure to write MP table header.
-    #[error("Failure to write MP table header")]
-    WriteMpcTable(#[source] GuestMemoryError),
+    WriteMpcTable(GuestMemoryError),
 }
 
 pub type Result<T> = result::Result<T, Error>;
 
+// With APIC/xAPIC, there are only 255 APIC IDs available. And IOAPIC occupies
+// one APIC ID, so only 254 CPUs at maximum may be supported. Actually it's
+// a large number for FC usecases.
+pub const MAX_SUPPORTED_CPUS: u32 = 254;
+
+// Convenience macro for making arrays of diverse character types.
+macro_rules! char_array {
+    ($t:ty; $( $c:expr ),*) => ( [ $( $c as $t ),* ] )
+}
+
 // Most of these variables are sourced from the Intel MP Spec 1.4.
-const SMP_MAGIC_IDENT: &[c_uchar; 4] = b"_MP_";
-const MPC_SIGNATURE: &[c_uchar; 4] = b"PCMP";
-const MPC_SPEC: u8 = 4;
-const MPC_OEM: &[c_uchar; 8] = b"FC      ";
-const MPC_PRODUCT_ID: &[c_uchar; 12] = &[b'0'; 12];
-const BUS_TYPE_ISA: &[c_uchar; 6] = b"ISA   ";
+const SMP_MAGIC_IDENT: [c_char; 4] = char_array!(c_char; '_', 'M', 'P', '_');
+const MPC_SIGNATURE: [c_char; 4] = char_array!(c_char; 'P', 'C', 'M', 'P');
+const MPC_SPEC: i8 = 4;
+const MPC_OEM: [c_char; 8] = char_array!(c_char; 'F', 'C', ' ', ' ', ' ', ' ', ' ', ' ');
+const MPC_PRODUCT_ID: [c_char; 12] = ['0' as c_char; 12];
+const BUS_TYPE_ISA: [u8; 6] = char_array!(u8; 'I', 'S', 'A', ' ', ' ', ' ');
 const APIC_VERSION: u8 = 0x14;
 const CPU_STEPPING: u32 = 0x600;
 const CPU_FEATURE_APIC: u32 = 0x200;
 const CPU_FEATURE_FPU: u32 = 0x001;
 
-fn compute_checksum<T: Copy + ByteValued>(v: &T) -> u8 {
+fn compute_checksum<T: Copy>(v: &T) -> u8 {
     // SAFETY: we are only reading the bytes within the size of the `T` reference `v`.
     let v_slice = unsafe { slice::from_raw_parts(v as *const T as *const u8, mem::size_of::<T>()) };
     let mut checksum: u8 = 0;
@@ -114,7 +115,7 @@ fn mpf_intel_compute_checksum(v: &mpspec::mpf_intel) -> u8 {
     (!checksum).wrapping_add(1)
 }
 
-fn compute_mp_size(num_cpus: u32) -> usize {
+fn compute_mp_size(num_cpus: u8) -> usize {
     mem::size_of::<MpfIntelWrapper>()
         + mem::size_of::<MpcTableWrapper>()
         + mem::size_of::<MpcCpuWrapper>() * (num_cpus as usize)
@@ -125,19 +126,9 @@ fn compute_mp_size(num_cpus: u32) -> usize {
 }
 
 /// Performs setup of the MP table for the given `num_cpus`.
-pub fn setup_mptable(
-    offset: GuestAddress,
-    mem: &GuestMemoryMmap,
-    num_cpus: u32,
-    topology: Option<(u16, u16, u16, u16)>,
-) -> Result<()> {
-    if num_cpus > 0 {
-        let cpu_id_max = num_cpus - 1;
-        let x2apic_id_max = get_x2apic_id(cpu_id_max, topology);
-        if x2apic_id_max >= MAX_SUPPORTED_CPUS_LEGACY {
-            info!("Skipping mptable creation due to too many CPUs");
-            return Ok(());
-        }
+pub fn setup_mptable(offset: GuestAddress, mem: &GuestMemoryMmap, num_cpus: u8) -> Result<()> {
+    if num_cpus as u32 > MAX_SUPPORTED_CPUS {
+        return Err(Error::TooManyCpus);
     }
 
     // Used to keep track of the next base pointer into the MP table.
@@ -151,7 +142,7 @@ pub fn setup_mptable(
     }
 
     let mut checksum: u8 = 0;
-    let ioapicid: u8 = MAX_SUPPORTED_CPUS_LEGACY as u8 + 1;
+    let ioapicid: u8 = num_cpus + 1;
 
     // The checked_add here ensures the all of the following base_mp.unchecked_add's will be without
     // overflow.
@@ -163,13 +154,13 @@ pub fn setup_mptable(
         return Err(Error::AddressOverflow);
     }
 
-    mem.read_exact_volatile_from(base_mp, &mut vec![0; mp_size].as_slice(), mp_size)
+    mem.read_exact_from(base_mp, &mut io::repeat(0), mp_size)
         .map_err(Error::Clear)?;
 
     {
         let mut mpf_intel = MpfIntelWrapper(mpspec::mpf_intel::default());
         let size = mem::size_of::<MpfIntelWrapper>() as u64;
-        mpf_intel.0.signature = *SMP_MAGIC_IDENT;
+        mpf_intel.0.signature = SMP_MAGIC_IDENT;
         mpf_intel.0.length = 1;
         mpf_intel.0.specification = 4;
         mpf_intel.0.physptr = (base_mp.raw_value() + size) as u32;
@@ -189,7 +180,7 @@ pub fn setup_mptable(
         for cpu_id in 0..num_cpus {
             let mut mpc_cpu = MpcCpuWrapper(mpspec::mpc_cpu::default());
             mpc_cpu.0.type_ = mpspec::MP_PROCESSOR as u8;
-            mpc_cpu.0.apicid = get_x2apic_id(cpu_id, topology) as u8;
+            mpc_cpu.0.apicid = cpu_id;
             mpc_cpu.0.apicver = APIC_VERSION;
             mpc_cpu.0.cpuflag = mpspec::CPU_ENABLED as u8
                 | if cpu_id == 0 {
@@ -210,7 +201,7 @@ pub fn setup_mptable(
         let mut mpc_bus = MpcBusWrapper(mpspec::mpc_bus::default());
         mpc_bus.0.type_ = mpspec::MP_BUS as u8;
         mpc_bus.0.busid = 0;
-        mpc_bus.0.bustype = *BUS_TYPE_ISA;
+        mpc_bus.0.bustype = BUS_TYPE_ISA;
         mem.write_obj(mpc_bus, base_mp)
             .map_err(Error::WriteMpcBus)?;
         base_mp = base_mp.unchecked_add(size as u64);
@@ -281,14 +272,14 @@ pub fn setup_mptable(
 
     {
         let mut mpc_table = MpcTableWrapper(mpspec::mpc_table::default());
-        mpc_table.0.signature = *MPC_SIGNATURE;
+        mpc_table.0.signature = MPC_SIGNATURE;
         mpc_table.0.length = table_end.unchecked_offset_from(table_base) as u16;
         mpc_table.0.spec = MPC_SPEC;
-        mpc_table.0.oem = *MPC_OEM;
-        mpc_table.0.productid = *MPC_PRODUCT_ID;
+        mpc_table.0.oem = MPC_OEM;
+        mpc_table.0.productid = MPC_PRODUCT_ID;
         mpc_table.0.lapic = APIC_START.0 as u32;
         checksum = checksum.wrapping_add(compute_checksum(&mpc_table.0));
-        mpc_table.0.checksum = (!checksum).wrapping_add(1);
+        mpc_table.0.checksum = (!checksum).wrapping_add(1) as i8;
         mem.write_obj(mpc_table, table_base)
             .map_err(Error::WriteMpcTable)?;
     }
@@ -298,11 +289,9 @@ pub fn setup_mptable(
 
 #[cfg(test)]
 mod tests {
-    use vm_memory::bitmap::BitmapSlice;
-    use vm_memory::{GuestUsize, VolatileMemoryError, VolatileSlice, WriteVolatile};
-
     use super::*;
     use crate::layout::MPTABLE_START;
+    use vm_memory::{GuestAddress, GuestUsize};
 
     fn table_entry_size(type_: u8) -> usize {
         match type_ as u32 {
@@ -321,7 +310,7 @@ mod tests {
         let mem =
             GuestMemoryMmap::from_ranges(&[(MPTABLE_START, compute_mp_size(num_cpus))]).unwrap();
 
-        setup_mptable(MPTABLE_START, &mem, num_cpus, None).unwrap();
+        setup_mptable(MPTABLE_START, &mem, num_cpus).unwrap();
     }
 
     #[test]
@@ -330,7 +319,7 @@ mod tests {
         let mem = GuestMemoryMmap::from_ranges(&[(MPTABLE_START, compute_mp_size(num_cpus) - 1)])
             .unwrap();
 
-        setup_mptable(MPTABLE_START, &mem, num_cpus, None).unwrap_err();
+        assert!(setup_mptable(MPTABLE_START, &mem, num_cpus).is_err());
     }
 
     #[test]
@@ -339,7 +328,7 @@ mod tests {
         let mem =
             GuestMemoryMmap::from_ranges(&[(MPTABLE_START, compute_mp_size(num_cpus))]).unwrap();
 
-        setup_mptable(MPTABLE_START, &mem, num_cpus, None).unwrap();
+        setup_mptable(MPTABLE_START, &mem, num_cpus).unwrap();
 
         let mpf_intel: MpfIntelWrapper = mem.read_obj(MPTABLE_START).unwrap();
 
@@ -355,31 +344,27 @@ mod tests {
         let mem =
             GuestMemoryMmap::from_ranges(&[(MPTABLE_START, compute_mp_size(num_cpus))]).unwrap();
 
-        setup_mptable(MPTABLE_START, &mem, num_cpus, None).unwrap();
+        setup_mptable(MPTABLE_START, &mem, num_cpus).unwrap();
 
         let mpf_intel: MpfIntelWrapper = mem.read_obj(MPTABLE_START).unwrap();
         let mpc_offset = GuestAddress(mpf_intel.0.physptr as GuestUsize);
         let mpc_table: MpcTableWrapper = mem.read_obj(mpc_offset).unwrap();
 
         struct Sum(u8);
-        impl WriteVolatile for Sum {
-            fn write_volatile<B: BitmapSlice>(
-                &mut self,
-                buf: &VolatileSlice<B>,
-            ) -> result::Result<usize, VolatileMemoryError> {
-                let mut tmp = vec![0u8; buf.len()];
-                tmp.write_all_volatile(buf)?;
-
-                for v in tmp.iter() {
+        impl io::Write for Sum {
+            fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
+                for v in buf.iter() {
                     self.0 = self.0.wrapping_add(*v);
                 }
-
                 Ok(buf.len())
             }
+            fn flush(&mut self) -> io::Result<()> {
+                Ok(())
+            }
         }
 
         let mut sum = Sum(0);
-        mem.write_volatile_to(mpc_offset, &mut sum, mpc_table.0.length as usize)
+        mem.write_to(mpc_offset, &mut sum, mpc_table.0.length as usize)
             .unwrap();
         assert_eq!(sum.0, 0);
     }
@@ -388,12 +373,12 @@ mod tests {
     fn cpu_entry_count() {
         let mem = GuestMemoryMmap::from_ranges(&[(
             MPTABLE_START,
-            compute_mp_size(MAX_SUPPORTED_CPUS_LEGACY),
+            compute_mp_size(MAX_SUPPORTED_CPUS as u8),
         )])
         .unwrap();
 
-        for i in 0..MAX_SUPPORTED_CPUS_LEGACY {
-            setup_mptable(MPTABLE_START, &mem, i, None).unwrap();
+        for i in 0..MAX_SUPPORTED_CPUS as u8 {
+            setup_mptable(MPTABLE_START, &mem, i).unwrap();
 
             let mpf_intel: MpfIntelWrapper = mem.read_obj(MPTABLE_START).unwrap();
             let mpc_offset = GuestAddress(mpf_intel.0.physptr as GuestUsize);
@@ -422,9 +407,11 @@ mod tests {
 
     #[test]
     fn cpu_entry_count_max() {
-        let cpus = MAX_SUPPORTED_CPUS_LEGACY + 1;
-        let mem = GuestMemoryMmap::from_ranges(&[(MPTABLE_START, compute_mp_size(cpus))]).unwrap();
+        let cpus = MAX_SUPPORTED_CPUS + 1;
+        let mem =
+            GuestMemoryMmap::from_ranges(&[(MPTABLE_START, compute_mp_size(cpus as u8))]).unwrap();
 
-        setup_mptable(MPTABLE_START, &mem, cpus, None).unwrap();
+        let result = setup_mptable(MPTABLE_START, &mem, cpus as u8);
+        assert!(result.is_err());
     }
 }

arch/src/x86_64/regs.rs

@@ -6,58 +6,41 @@
 // Portions Copyright 2017 The Chromium OS Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE-BSD-3-Clause file.
-use std::sync::Arc;
-use std::{mem, result};
-
+use crate::layout::{BOOT_GDT_START, BOOT_IDT_START, PVH_INFO_START};
+use crate::GuestMemoryMmap;
 use hypervisor::arch::x86::gdt::{gdt_entry, segment_from_gdt};
 use hypervisor::arch::x86::regs::CR0_PE;
-use hypervisor::arch::x86::{FpuState, SpecialRegisters};
-use thiserror::Error;
+use hypervisor::arch::x86::{FpuState, SpecialRegisters, StandardRegisters};
+use std::sync::Arc;
+use std::{mem, result};
 use vm_memory::{Address, Bytes, GuestMemory, GuestMemoryError};
 
-use crate::layout::{
-    BOOT_GDT_START, BOOT_IDT_START, BOOT_STACK_POINTER, PVH_INFO_START, ZERO_PAGE_START,
-};
-use crate::{EntryPoint, GuestMemoryMmap};
-
-#[derive(Debug, Error)]
+#[derive(Debug)]
 pub enum Error {
     /// Failed to get SREGs for this CPU.
-    #[error("Failed to get SREGs for this CPU")]
-    GetStatusRegisters(#[source] hypervisor::HypervisorCpuError),
+    GetStatusRegisters(hypervisor::HypervisorCpuError),
     /// Failed to set base registers for this CPU.
-    #[error("Failed to set base registers for this CPU")]
-    SetBaseRegisters(#[source] hypervisor::HypervisorCpuError),
+    SetBaseRegisters(hypervisor::HypervisorCpuError),
     /// Failed to configure the FPU.
-    #[error("Failed to configure the FPU")]
-    SetFpuRegisters(#[source] hypervisor::HypervisorCpuError),
+    SetFpuRegisters(hypervisor::HypervisorCpuError),
     /// Setting up MSRs failed.
-    #[error("Setting up MSRs failed")]
-    SetModelSpecificRegisters(#[source] hypervisor::HypervisorCpuError),
+    SetModelSpecificRegisters(hypervisor::HypervisorCpuError),
     /// Failed to set SREGs for this CPU.
-    #[error("Failed to set SREGs for this CPU")]
-    SetStatusRegisters(#[source] hypervisor::HypervisorCpuError),
+    SetStatusRegisters(hypervisor::HypervisorCpuError),
     /// Checking the GDT address failed.
-    #[error("Checking the GDT address failed")]
     CheckGdtAddr,
     /// Writing the GDT to RAM failed.
-    #[error("Writing the GDT to RAM failed")]
-    WriteGdt(#[source] GuestMemoryError),
+    WriteGdt(GuestMemoryError),
     /// Writing the IDT to RAM failed.
-    #[error("Writing the IDT to RAM failed")]
-    WriteIdt(#[source] GuestMemoryError),
+    WriteIdt(GuestMemoryError),
     /// Writing PDPTE to RAM failed.
-    #[error("Writing PDPTE to RAM failed")]
-    WritePdpteAddress(#[source] GuestMemoryError),
+    WritePdpteAddress(GuestMemoryError),
     /// Writing PDE to RAM failed.
-    #[error("Writing PDE to RAM failed")]
-    WritePdeAddress(#[source] GuestMemoryError),
+    WritePdeAddress(GuestMemoryError),
     /// Writing PML4 to RAM failed.
-    #[error("Writing PML4 to RAM failed")]
-    WritePml4Address(#[source] GuestMemoryError),
+    WritePml4Address(GuestMemoryError),
     /// Writing PML5 to RAM failed.
-    #[error("Writing PML5 to RAM failed")]
-    WritePml5Address(#[source] GuestMemoryError),
+    WritePml5Address(GuestMemoryError),
 }
 
 pub type Result<T> = result::Result<T, Error>;
@@ -94,21 +77,13 @@ pub fn setup_msrs(vcpu: &Arc<dyn hypervisor::Vcpu>) -> Result<()> {
 /// # Arguments
 ///
 /// * `vcpu` - Structure for the VCPU that holds the VCPU's fd.
-/// * `entry_point` - Description of the boot entry to set up.
-pub fn setup_regs(vcpu: &Arc<dyn hypervisor::Vcpu>, entry_point: EntryPoint) -> Result<()> {
-    let mut regs = vcpu.create_standard_regs();
-    match entry_point.setup_header {
-        None => {
-            regs.set_rflags(0x0000000000000002u64);
-            regs.set_rip(entry_point.entry_addr.raw_value());
-            regs.set_rbx(PVH_INFO_START.raw_value());
-        }
-        Some(_) => {
-            regs.set_rflags(0x0000000000000002u64);
-            regs.set_rip(entry_point.entry_addr.raw_value());
-            regs.set_rsp(BOOT_STACK_POINTER.raw_value());
-            regs.set_rsi(ZERO_PAGE_START.raw_value());
-        }
+/// * `boot_ip` - Starting instruction pointer.
+pub fn setup_regs(vcpu: &Arc<dyn hypervisor::Vcpu>, boot_ip: u64) -> Result<()> {
+    let regs = StandardRegisters {
+        rflags: 0x0000000000000002u64,
+        rbx: PVH_INFO_START.raw_value(),
+        rip: boot_ip,
+        ..Default::default()
     };
     vcpu.set_regs(&regs).map_err(Error::SetBaseRegisters)
 }
@@ -119,13 +94,9 @@ pub fn setup_regs(vcpu: &Arc<dyn hypervisor::Vcpu>, entry_point: EntryPoint) ->
 ///
 /// * `mem` - The memory that will be passed to the guest.
 /// * `vcpu` - Structure for the VCPU that holds the VCPU's fd.
-pub fn setup_sregs(
-    mem: &GuestMemoryMmap,
-    vcpu: &Arc<dyn hypervisor::Vcpu>,
-    enable_x2_apic_mode: bool,
-) -> Result<()> {
+pub fn setup_sregs(mem: &GuestMemoryMmap, vcpu: &Arc<dyn hypervisor::Vcpu>) -> Result<()> {
     let mut sregs: SpecialRegisters = vcpu.get_sregs().map_err(Error::GetStatusRegisters)?;
-    configure_segments_and_sregs(mem, &mut sregs, enable_x2_apic_mode)?;
+    configure_segments_and_sregs(mem, &mut sregs)?;
     vcpu.set_sregs(&sregs).map_err(Error::SetStatusRegisters)
 }
 
@@ -152,7 +123,6 @@ fn write_idt_value(val: u64, guest_mem: &GuestMemoryMmap) -> Result<()> {
 pub fn configure_segments_and_sregs(
     mem: &GuestMemoryMmap,
     sregs: &mut SpecialRegisters,
-    enable_x2_apic_mode: bool,
 ) -> Result<()> {
     let gdt_table: [u64; BOOT_GDT_MAX] = {
         // Configure GDT entries as specified by PVH boot protocol
@@ -188,19 +158,14 @@ pub fn configure_segments_and_sregs(
     sregs.cr0 = CR0_PE;
     sregs.cr4 = 0;
 
-    if enable_x2_apic_mode {
-        const X2APIC_ENABLE_BIT: u64 = 1 << 10;
-        sregs.apic_base |= X2APIC_ENABLE_BIT;
-    }
-
     Ok(())
 }
 
 #[cfg(test)]
 mod tests {
-    use vm_memory::GuestAddress;
-
     use super::*;
+    use crate::GuestMemoryMmap;
+    use vm_memory::GuestAddress;
 
     fn create_guest_mem() -> GuestMemoryMmap {
         GuestMemoryMmap::from_ranges(&[(GuestAddress(0), 0x10000)]).unwrap()
@@ -214,7 +179,7 @@ mod tests {
     fn segments_and_sregs() {
         let mut sregs: SpecialRegisters = Default::default();
         let gm = create_guest_mem();
-        configure_segments_and_sregs(&gm, &mut sregs, false).unwrap();
+        configure_segments_and_sregs(&gm, &mut sregs).unwrap();
         assert_eq!(0x0, read_u64(&gm, BOOT_GDT_START));
         assert_eq!(
             0xcf9b000000ffff,

arch/src/x86_64/smbios.rs

@@ -6,35 +6,53 @@
 //
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
-use std::{mem, result, slice};
-
-use thiserror::Error;
-use uuid::Uuid;
-use vm_memory::{Address, ByteValued, Bytes, GuestAddress};
-
-use crate::GuestMemoryMmap;
 use crate::layout::SMBIOS_START;
+use crate::GuestMemoryMmap;
+use std::fmt::{self, Display};
+use std::mem;
+use std::result;
+use std::slice;
+use uuid::Uuid;
+use vm_memory::ByteValued;
+use vm_memory::{Address, Bytes, GuestAddress};
 
-#[derive(Debug, Error)]
+#[derive(Debug)]
 pub enum Error {
     /// There was too little guest memory to store the entire SMBIOS table.
-    #[error("There was too little guest memory to store the SMBIOS table")]
     NotEnoughMemory,
     /// The SMBIOS table has too little address space to be stored.
-    #[error("The SMBIOS table has too little address space to be stored")]
     AddressOverflow,
     /// Failure while zeroing out the memory for the SMBIOS table.
-    #[error("Failure while zeroing out the memory for the SMBIOS table")]
     Clear,
     /// Failure to write SMBIOS entrypoint structure
-    #[error("Failure to write SMBIOS entrypoint structure")]
     WriteSmbiosEp,
     /// Failure to write additional data to memory
-    #[error("Failure to write additional data to memory")]
     WriteData,
     /// Failure to parse uuid, uuid format may be error
-    #[error("Failure to parse uuid")]
-    ParseUuid(#[source] uuid::Error),
+    ParseUuid(uuid::Error),
+}
+
+impl std::error::Error for Error {}
+
+impl Display for Error {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        use self::Error::*;
+
+        let description = match self {
+            NotEnoughMemory => {
+                "There was too little guest memory to store the SMBIOS table".to_string()
+            }
+            AddressOverflow => {
+                "The SMBIOS table has too little address space to be stored".to_string()
+            }
+            Clear => "Failure while zeroing out the memory for the SMBIOS table".to_string(),
+            WriteSmbiosEp => "Failure to write SMBIOS entrypoint structure".to_string(),
+            WriteData => "Failure to write additional data to memory".to_string(),
+            ParseUuid(e) => format!("Failure to parse uuid: {e}"),
+        };
+
+        write!(f, "SMBIOS error: {description}")
+    }
 }
 
 pub type Result<T> = result::Result<T, Error>;

arch/src/x86_64/tdx/mod.rs

@@ -1,23 +1,21 @@
 // Copyright © 2021 Intel Corporation
 //
 // SPDX-License-Identifier: Apache-2.0
+use crate::GuestMemoryMmap;
 use std::fs::File;
 use std::io::{Read, Seek, SeekFrom};
 use std::str::FromStr;
-
 use thiserror::Error;
 use uuid::Uuid;
 use vm_memory::{ByteValued, Bytes, GuestAddress, GuestMemoryError};
 
-use crate::GuestMemoryMmap;
-
 #[derive(Error, Debug)]
 pub enum TdvfError {
-    #[error("Failed read TDVF descriptor")]
+    #[error("Failed read TDVF descriptor: {0}")]
     ReadDescriptor(#[source] std::io::Error),
-    #[error("Failed read TDVF descriptor offset")]
+    #[error("Failed read TDVF descriptor offset: {0}")]
     ReadDescriptorOffset(#[source] std::io::Error),
-    #[error("Failed read GUID table")]
+    #[error("Failed read GUID table: {0}")]
     ReadGuidTable(#[source] std::io::Error),
     #[error("Invalid descriptor signature")]
     InvalidDescriptorSignature,
@@ -25,9 +23,9 @@ pub enum TdvfError {
     InvalidDescriptorSize,
     #[error("Invalid descriptor version")]
     InvalidDescriptorVersion,
-    #[error("Failed to write HOB details to guest memory")]
+    #[error("Failed to write HOB details to guest memory: {0}")]
     GuestMemoryWriteHob(#[source] GuestMemoryError),
-    #[error("Failed to create Uuid")]
+    #[error("Failed to create Uuid: {0}")]
     UuidCreation(#[source] uuid::Error),
 }
 
@@ -35,7 +33,7 @@ const TABLE_FOOTER_GUID: &str = "96b582de-1fb2-45f7-baea-a366c55a082d";
 const TDVF_METADATA_OFFSET_GUID: &str = "e47a6535-984a-4798-865e-4685a7bf8ec2";
 
 // TDVF_DESCRIPTOR
-#[repr(C, packed)]
+#[repr(packed)]
 #[derive(Default)]
 pub struct TdvfDescriptor {
     signature: [u8; 4],
@@ -45,7 +43,7 @@ pub struct TdvfDescriptor {
 }
 
 // TDVF_SECTION
-#[repr(C, packed)]
+#[repr(packed)]
 #[derive(Clone, Copy, Default, Debug)]
 pub struct TdvfSection {
     pub data_offset: u32,
@@ -100,7 +98,7 @@ fn tdvf_descriptor_offset(file: &mut File) -> Result<(SeekFrom, bool), TdvfError
         // We start after the footer GUID and the table length.
         let mut offset = table_size - 18;
 
-        debug!("Parsing GUID structure");
+        debug!("Parsing GUIDed structure");
         while offset >= 18 {
             let entry_uuid = Uuid::from_slice_le(&table[offset - 16..offset])
                 .map_err(TdvfError::UuidCreation)?;
@@ -209,7 +207,7 @@ enum HobType {
     EndOfHobList = 0xffff,
 }
 
-#[repr(C, packed)]
+#[repr(C)]
 #[derive(Copy, Clone, Default, Debug)]
 struct HobHeader {
     r#type: HobType,
@@ -217,7 +215,7 @@ struct HobHeader {
     reserved: u32,
 }
 
-#[repr(C, packed)]
+#[repr(C)]
 #[derive(Copy, Clone, Default, Debug)]
 struct HobHandoffInfoTable {
     header: HobHeader,
@@ -230,7 +228,7 @@ struct HobHandoffInfoTable {
     efi_end_of_hob_list: u64,
 }
 
-#[repr(C, packed)]
+#[repr(C)]
 #[derive(Copy, Clone, Default, Debug)]
 struct EfiGuid {
     data1: u32,
@@ -239,7 +237,7 @@ struct EfiGuid {
     data4: [u8; 8],
 }
 
-#[repr(C, packed)]
+#[repr(C)]
 #[derive(Copy, Clone, Default, Debug)]
 struct HobResourceDescriptor {
     header: HobHeader,
@@ -250,7 +248,7 @@ struct HobResourceDescriptor {
     resource_length: u64,
 }
 
-#[repr(C, packed)]
+#[repr(C)]
 #[derive(Copy, Clone, Default, Debug)]
 struct HobGuidType {
     header: HobHeader,
@@ -266,14 +264,14 @@ pub enum PayloadImageType {
     RawVmLinux,
 }
 
-#[repr(C, packed)]
+#[repr(C)]
 #[derive(Copy, Clone, Default, Debug)]
 pub struct PayloadInfo {
     pub image_type: PayloadImageType,
     pub entry_point: u64,
 }
 
-#[repr(C, packed)]
+#[repr(C)]
 #[derive(Copy, Clone, Default, Debug)]
 struct TdPayload {
     guid_type: HobGuidType,
@@ -299,7 +297,7 @@ pub struct TdHob {
 }
 
 fn align_hob(v: u64) -> u64 {
-    v.div_ceil(8) * 8
+    (v + 7) / 8 * 8
 }
 
 impl TdHob {

block/Cargo.toml

@@ -1,30 +0,0 @@
-[package]
-authors = ["The Chromium OS Authors", "The Cloud Hypervisor Authors"]
-edition.workspace = true
-name = "block"
-version = "0.1.0"
-
-[features]
-default = []
-io_uring = ["dep:io-uring"]
-
-[dependencies]
-byteorder = { workspace = true }
-crc-any = "2.5.0"
-io-uring = { version = "0.7.10", optional = true }
-libc = { workspace = true }
-log = { workspace = true }
-remain = "0.2.15"
-serde = { workspace = true, features = ["derive"] }
-smallvec = "1.15.1"
-thiserror = { workspace = true }
-uuid = { workspace = true, features = ["v4"] }
-virtio-bindings = { workspace = true }
-virtio-queue = { workspace = true }
-vm-memory = { workspace = true, features = [
-  "backend-atomic",
-  "backend-bitmap",
-  "backend-mmap",
-] }
-vm-virtio = { path = "../vm-virtio" }
-vmm-sys-util = { workspace = true }

block/src/async_io.rs

@@ -1,111 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
-
-use std::marker::PhantomData;
-use std::os::fd::{AsRawFd, OwnedFd, RawFd};
-
-use thiserror::Error;
-use vmm_sys_util::eventfd::EventFd;
-
-use crate::{BatchRequest, DiskTopology};
-
-#[derive(Error, Debug)]
-pub enum DiskFileError {
-    /// Failed getting disk file size.
-    #[error("Failed getting disk file size")]
-    Size(#[source] std::io::Error),
-    /// Failed creating a new AsyncIo.
-    #[error("Failed creating a new AsyncIo")]
-    NewAsyncIo(#[source] std::io::Error),
-}
-
-pub type DiskFileResult<T> = std::result::Result<T, DiskFileError>;
-
-/// A wrapper for [`RawFd`] capturing the lifetime of a corresponding [`DiskFile`].
-///
-/// This fulfills the same role as [`BorrowedFd`] but is tailored to the limitations
-/// by some implementations of [`DiskFile`], which wrap the effective [`File`]
-/// in an `Arc<Mutex<T>>`, making the use of [`BorrowedFd`] impossible.
-///
-/// [`BorrowedFd`]: std::os::fd::BorrowedFd
-#[derive(Copy, Clone, Debug)]
-pub struct BorrowedDiskFd<'fd> {
-    raw_fd: RawFd,
-    _lifetime: PhantomData<&'fd OwnedFd>,
-}
-
-impl BorrowedDiskFd<'_> {
-    pub(super) fn new(raw_fd: RawFd) -> Self {
-        Self {
-            raw_fd,
-            _lifetime: PhantomData,
-        }
-    }
-}
-
-impl AsRawFd for BorrowedDiskFd<'_> {
-    fn as_raw_fd(&self) -> RawFd {
-        self.raw_fd
-    }
-}
-
-/// Abstraction over the effective [`File`] backing up a block device,
-/// with support for synchronous and asynchronous I/O.
-///
-/// This allows abstracting over raw image formats as well as structured
-/// image formats.
-pub trait DiskFile: Send {
-    fn size(&mut self) -> DiskFileResult<u64>;
-    fn new_async_io(&self, ring_depth: u32) -> DiskFileResult<Box<dyn AsyncIo>>;
-    fn topology(&mut self) -> DiskTopology {
-        DiskTopology::default()
-    }
-    /// Returns the file descriptor of the underlying disk image file.
-    ///
-    /// The file descriptor is supposed to be used for `fcntl()` calls but no
-    /// other operation.
-    fn fd(&mut self) -> BorrowedDiskFd<'_>;
-}
-
-#[derive(Error, Debug)]
-pub enum AsyncIoError {
-    /// Failed vectored reading from file.
-    #[error("Failed vectored reading from file")]
-    ReadVectored(#[source] std::io::Error),
-    /// Failed vectored writing to file.
-    #[error("Failed vectored writing to file")]
-    WriteVectored(#[source] std::io::Error),
-    /// Failed synchronizing file.
-    #[error("Failed synchronizing file")]
-    Fsync(#[source] std::io::Error),
-    /// Failed submitting batch requests.
-    #[error("Failed submitting batch requests: {0}")]
-    SubmitBatchRequests(#[source] std::io::Error),
-}
-
-pub type AsyncIoResult<T> = std::result::Result<T, AsyncIoError>;
-
-pub trait AsyncIo: Send {
-    fn notifier(&self) -> &EventFd;
-    fn read_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()>;
-    fn write_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()>;
-    fn fsync(&mut self, user_data: Option<u64>) -> AsyncIoResult<()>;
-    fn next_completed_request(&mut self) -> Option<(u64, i32)>;
-    fn batch_requests_enabled(&self) -> bool {
-        false
-    }
-    fn submit_batch_requests(&mut self, _batch_request: &[BatchRequest]) -> AsyncIoResult<()> {
-        Ok(())
-    }
-}

block/src/fcntl.rs

@@ -1,173 +0,0 @@
-// Copyright © 2025 Cyberus Technology GmbH
-//
-// SPDX-License-Identifier: Apache-2.0
-//
-
-//! Helpers for advisory file locking.
-//!
-//! Under the hood, the implementation uses OFD locks for the entire file,
-//! as described in [[0]]. The advantage over `F_SETLKW` (currently used by
-//! Rust std: `File::try_lock()`) is that only the very last `close()` on a
-//! file descriptor releases the lock. This prevents mistakes and unexpected
-//! behavior.
-//!
-//! [0]: <https://apenwarr.ca/log/20101213>.
-
-use std::fmt::Debug;
-use std::io;
-use std::os::fd::{AsRawFd, RawFd};
-
-use thiserror::Error;
-
-/// Errors that can happen when working with file locks.
-#[derive(Error, Debug)]
-pub enum LockError {
-    /// The file is already locked.
-    ///
-    /// A call to [`get_lock_state`] can help to identify the reason.
-    #[error("The file is already locked")]
-    AlreadyLocked,
-    /// IO error.
-    #[error("The lock state could not be checked or set")]
-    Io(#[source] io::Error),
-}
-
-/// Commands for use with [`fcntl`].
-#[allow(non_camel_case_types)]
-enum FcntlArg<'a> {
-    /// Set an OFD lock from the given lock description.
-    F_OFD_SETLK(&'a libc::flock),
-    /// Get the first OFD lock for the given lock description.
-    F_OFD_GETLK(&'a mut libc::flock),
-}
-
-/// Wrapper for [`libc::fcntl`] that properly sets the function arguments.
-fn fcntl(fd: RawFd, arg: FcntlArg) -> libc::c_int {
-    // SAFETY: We use a valid FD.
-    unsafe {
-        match arg {
-            FcntlArg::F_OFD_SETLK(flock) => libc::fcntl(fd, libc::F_OFD_SETLK, flock),
-            FcntlArg::F_OFD_GETLK(flock) => libc::fcntl(fd, libc::F_OFD_GETLK, flock),
-        }
-    }
-}
-
-/// Describes the type of lock you want to set.
-#[derive(Clone, Copy, Debug)]
-pub enum LockType {
-    /// Clear a lock.
-    Unlock,
-    /// Set a write lock (exclusive).
-    Write,
-    /// Set a read lock (shared).
-    Read,
-}
-
-impl LockType {
-    pub const fn to_libc_val(self) -> libc::c_int {
-        match self {
-            Self::Unlock => libc::F_UNLCK as libc::c_int,
-            Self::Write => libc::F_WRLCK as libc::c_int,
-            Self::Read => libc::F_RDLCK as libc::c_int,
-        }
-    }
-}
-
-/// Describes the current state of a lock.
-#[derive(Debug)]
-pub enum LockState {
-    /// No lock set.
-    Unlocked,
-    /// Locked for reading (non-exclusive).
-    SharedRead,
-    /// Locked for writing (exclusive mode).
-    ExclusiveWrite,
-}
-
-impl LockState {
-    fn new(value: libc::c_int) -> Self {
-        const F_UNLCK: libc::c_int = libc::F_UNLCK as libc::c_int;
-        const F_WRLCK: libc::c_int = libc::F_WRLCK as libc::c_int;
-        const F_RDLCK: libc::c_int = libc::F_RDLCK as libc::c_int;
-        match value {
-            F_UNLCK => Self::Unlocked,
-            F_WRLCK => Self::ExclusiveWrite,
-            F_RDLCK => Self::SharedRead,
-            // This is so unlikely that we want to avoid the complexity of
-            // coping with this error case. Can only fail if either Linux
-            // is broken or memory is messed up.
-            other => panic!("Unexpected lock state: {other}"),
-        }
-    }
-}
-
-/// Returns a [`struct@libc::flock`] structure for the whole file.
-const fn get_flock(lock_type: LockType) -> libc::flock {
-    libc::flock {
-        l_type: lock_type.to_libc_val() as libc::c_short,
-        l_whence: libc::SEEK_SET as libc::c_short,
-        l_start: 0,
-        l_len: 0, /* EOF */
-        l_pid: 0, /* filled by callee */
-    }
-}
-
-/// Tries to acquire a lock using [`fcntl`] with respect to the given
-/// parameters.
-///
-/// Please note that `fcntl()` OFD locks are **advisory locks**, which do not
-/// prevent to `open()` a file if a lock is already placed.
-///
-/// # Parameters
-/// - `file`: The file to acquire a lock for [`LockType`]. The file's state will
-///   be logically mutated, but not technically.
-/// - `lock_type`: The [`LockType`]
-pub fn try_acquire_lock<Fd: AsRawFd>(file: Fd, lock_type: LockType) -> Result<(), LockError> {
-    let flock = get_flock(lock_type);
-
-    let res = fcntl(file.as_raw_fd(), FcntlArg::F_OFD_SETLK(&flock));
-    match res {
-        0 => Ok(()),
-        -1 => {
-            let io_error = io::Error::last_os_error();
-            let errno = io_error.raw_os_error().unwrap();
-            match errno {
-                // See man page for error code:
-                // <https://man7.org/linux/man-pages/man2/fcntl.2.html>
-                libc::EAGAIN | libc::EACCES => Err(LockError::AlreadyLocked),
-                _ => Err(LockError::Io(io_error)),
-            }
-        }
-        val => panic!("Unexpected return value from fcntl(): {val}"),
-    }
-}
-
-/// Clears a lock.
-///
-/// # Parameters
-/// - `file`: The file to clear all locks for [`LockType`].
-pub fn clear_lock<Fd: AsRawFd>(file: Fd) -> Result<(), LockError> {
-    try_acquire_lock(file, LockType::Unlock)
-}
-
-/// Returns the current lock state using [`fcntl`] with respect to the given
-/// parameters.
-///
-/// # Parameters
-/// - `file`: The file for which to get the lock state.
-pub fn get_lock_state<Fd: AsRawFd>(file: Fd) -> Result<LockState, LockError> {
-    let mut flock = get_flock(LockType::Write);
-    let res = fcntl(file.as_raw_fd(), FcntlArg::F_OFD_GETLK(&mut flock));
-    match res {
-        0 => {
-            let state = flock.l_type as libc::c_int;
-            let state = LockState::new(state);
-            Ok(state)
-        }
-        -1 => {
-            let io_error = io::Error::last_os_error();
-            Err(LockError::Io(io_error))
-        }
-        val => panic!("Unexpected return value from fcntl(): {val}"),
-    }
-}

block/src/fixed_vhd.rs

@@ -1,91 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-
-use std::fs::File;
-use std::io::{Read, Seek, SeekFrom, Write};
-use std::os::unix::io::{AsRawFd, RawFd};
-
-use crate::BlockBackend;
-use crate::vhd::VhdFooter;
-
-#[derive(Debug)]
-pub struct FixedVhd {
-    file: File,
-    size: u64,
-    position: u64,
-}
-
-impl FixedVhd {
-    pub fn new(mut file: File) -> std::io::Result<Self> {
-        let footer = VhdFooter::new(&mut file)?;
-
-        Ok(Self {
-            file,
-            size: footer.current_size(),
-            position: 0,
-        })
-    }
-}
-
-impl AsRawFd for FixedVhd {
-    fn as_raw_fd(&self) -> RawFd {
-        self.file.as_raw_fd()
-    }
-}
-
-impl Read for FixedVhd {
-    fn read(&mut self, buf: &mut [u8]) -> std::io::Result<usize> {
-        match self.file.read(buf) {
-            Ok(r) => {
-                self.position = self.position.checked_add(r.try_into().unwrap()).unwrap();
-                Ok(r)
-            }
-            Err(e) => Err(e),
-        }
-    }
-}
-
-impl Write for FixedVhd {
-    fn write(&mut self, buf: &[u8]) -> std::io::Result<usize> {
-        match self.file.write(buf) {
-            Ok(r) => {
-                self.position = self.position.checked_add(r.try_into().unwrap()).unwrap();
-                Ok(r)
-            }
-            Err(e) => Err(e),
-        }
-    }
-
-    fn flush(&mut self) -> std::io::Result<()> {
-        self.file.sync_all()
-    }
-}
-
-impl Seek for FixedVhd {
-    fn seek(&mut self, newpos: SeekFrom) -> std::io::Result<u64> {
-        match self.file.seek(newpos) {
-            Ok(pos) => {
-                self.position = pos;
-                Ok(pos)
-            }
-            Err(e) => Err(e),
-        }
-    }
-}
-
-impl BlockBackend for FixedVhd {
-    fn size(&self) -> std::result::Result<u64, crate::Error> {
-        Ok(self.size)
-    }
-}
-
-impl Clone for FixedVhd {
-    fn clone(&self) -> Self {
-        Self {
-            file: self.file.try_clone().expect("FixedVhd cloning failed"),
-            size: self.size,
-            position: self.position,
-        }
-    }
-}

block/src/raw_async_aio.rs

@@ -1,156 +0,0 @@
-// Copyright © 2023 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
-//
-// Copyright © 2023 Crusoe Energy Systems LLC
-//
-
-use std::fs::File;
-use std::io::{Seek, SeekFrom};
-use std::os::unix::io::{AsRawFd, RawFd};
-
-use vmm_sys_util::aio;
-use vmm_sys_util::eventfd::EventFd;
-
-use crate::DiskTopology;
-use crate::async_io::{
-    AsyncIo, AsyncIoError, AsyncIoResult, BorrowedDiskFd, DiskFile, DiskFileError, DiskFileResult,
-};
-
-pub struct RawFileDiskAio {
-    file: File,
-}
-
-impl RawFileDiskAio {
-    pub fn new(file: File) -> Self {
-        RawFileDiskAio { file }
-    }
-}
-
-impl DiskFile for RawFileDiskAio {
-    fn size(&mut self) -> DiskFileResult<u64> {
-        self.file
-            .seek(SeekFrom::End(0))
-            .map_err(DiskFileError::Size)
-    }
-
-    fn new_async_io(&self, ring_depth: u32) -> DiskFileResult<Box<dyn AsyncIo>> {
-        Ok(Box::new(
-            RawFileAsyncAio::new(self.file.as_raw_fd(), ring_depth)
-                .map_err(DiskFileError::NewAsyncIo)?,
-        ) as Box<dyn AsyncIo>)
-    }
-
-    fn topology(&mut self) -> DiskTopology {
-        if let Ok(topology) = DiskTopology::probe(&self.file) {
-            topology
-        } else {
-            warn!("Unable to get device topology. Using default topology");
-            DiskTopology::default()
-        }
-    }
-
-    fn fd(&mut self) -> BorrowedDiskFd<'_> {
-        BorrowedDiskFd::new(self.file.as_raw_fd())
-    }
-}
-
-pub struct RawFileAsyncAio {
-    fd: RawFd,
-    ctx: aio::IoContext,
-    eventfd: EventFd,
-}
-
-impl RawFileAsyncAio {
-    pub fn new(fd: RawFd, queue_depth: u32) -> std::io::Result<Self> {
-        let eventfd = EventFd::new(libc::EFD_NONBLOCK)?;
-        let ctx = aio::IoContext::new(queue_depth)?;
-
-        Ok(RawFileAsyncAio { fd, ctx, eventfd })
-    }
-}
-
-impl AsyncIo for RawFileAsyncAio {
-    fn notifier(&self) -> &EventFd {
-        &self.eventfd
-    }
-
-    fn read_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        let iocbs = [&mut aio::IoControlBlock {
-            aio_fildes: self.fd.as_raw_fd() as u32,
-            aio_lio_opcode: aio::IOCB_CMD_PREADV as u16,
-            aio_buf: iovecs.as_ptr() as u64,
-            aio_nbytes: iovecs.len() as u64,
-            aio_offset: offset,
-            aio_data: user_data,
-            aio_flags: aio::IOCB_FLAG_RESFD,
-            aio_resfd: self.eventfd.as_raw_fd() as u32,
-            ..Default::default()
-        }];
-        let _ = self
-            .ctx
-            .submit(&iocbs[..])
-            .map_err(AsyncIoError::ReadVectored)?;
-
-        Ok(())
-    }
-
-    fn write_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        let iocbs = [&mut aio::IoControlBlock {
-            aio_fildes: self.fd.as_raw_fd() as u32,
-            aio_lio_opcode: aio::IOCB_CMD_PWRITEV as u16,
-            aio_buf: iovecs.as_ptr() as u64,
-            aio_nbytes: iovecs.len() as u64,
-            aio_offset: offset,
-            aio_data: user_data,
-            aio_flags: aio::IOCB_FLAG_RESFD,
-            aio_resfd: self.eventfd.as_raw_fd() as u32,
-            ..Default::default()
-        }];
-        let _ = self
-            .ctx
-            .submit(&iocbs[..])
-            .map_err(AsyncIoError::WriteVectored)?;
-
-        Ok(())
-    }
-
-    fn fsync(&mut self, user_data: Option<u64>) -> AsyncIoResult<()> {
-        if let Some(user_data) = user_data {
-            let iocbs = [&mut aio::IoControlBlock {
-                aio_fildes: self.fd.as_raw_fd() as u32,
-                aio_lio_opcode: aio::IOCB_CMD_FSYNC as u16,
-                aio_data: user_data,
-                aio_flags: aio::IOCB_FLAG_RESFD,
-                aio_resfd: self.eventfd.as_raw_fd() as u32,
-                ..Default::default()
-            }];
-            let _ = self.ctx.submit(&iocbs[..]).map_err(AsyncIoError::Fsync)?;
-        } else {
-            // SAFETY: FFI call with a valid fd
-            unsafe { libc::fsync(self.fd) };
-        }
-
-        Ok(())
-    }
-
-    fn next_completed_request(&mut self) -> Option<(u64, i32)> {
-        let mut events: [aio::IoEvent; 1] = [aio::IoEvent::default()];
-        let rc = self.ctx.get_events(0, &mut events, None).unwrap();
-        if rc == 0 {
-            None
-        } else {
-            Some((events[0].data, events[0].res as i32))
-        }
-    }
-}

block/src/vhdx/vhdx_io.rs

@@ -1,219 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-
-use std::fs::File;
-use std::io::{self, Read, Seek, SeekFrom, Write};
-
-use remain::sorted;
-use thiserror::Error;
-
-use crate::vhdx::vhdx_bat::{self, BatEntry, VhdxBatError};
-use crate::vhdx::vhdx_metadata::{self, DiskSpec};
-
-const SECTOR_SIZE: u64 = 512;
-
-#[sorted]
-#[derive(Error, Debug)]
-pub enum VhdxIoError {
-    #[error("Invalid BAT entry state")]
-    InvalidBatEntryState,
-    #[error("Invalid BAT entry count")]
-    InvalidBatIndex,
-    #[error("Invalid disk size")]
-    InvalidDiskSize,
-    #[error("Failed reading sector blocks from file {0}")]
-    ReadSectorBlock(#[source] io::Error),
-    #[error("Failed changing file length {0}")]
-    ResizeFile(#[source] io::Error),
-    #[error("Differencing mode is not supported yet")]
-    UnsupportedMode,
-    #[error("Failed writing BAT to file {0}")]
-    WriteBat(#[source] VhdxBatError),
-}
-
-pub type Result<T> = std::result::Result<T, VhdxIoError>;
-
-macro_rules! align {
-    ($n:expr, $align:expr) => {{ $n.div_ceil($align) * $align }};
-}
-
-#[derive(Default)]
-struct Sector {
-    bat_index: u64,
-    free_sectors: u64,
-    free_bytes: u64,
-    file_offset: u64,
-    block_offset: u64,
-}
-
-impl Sector {
-    /// Translate sector index and count of data in file to actual offsets and
-    /// BAT index.
-    pub fn new(
-        disk_spec: &DiskSpec,
-        bat: &[BatEntry],
-        sector_index: u64,
-        sector_count: u64,
-    ) -> Result<Sector> {
-        let mut sector = Sector::default();
-
-        sector.bat_index = sector_index / disk_spec.sectors_per_block as u64;
-        sector.block_offset = sector_index % disk_spec.sectors_per_block as u64;
-        sector.free_sectors = disk_spec.sectors_per_block as u64 - sector.block_offset;
-        if sector.free_sectors > sector_count {
-            sector.free_sectors = sector_count;
-        }
-
-        sector.free_bytes = sector.free_sectors * disk_spec.logical_sector_size as u64;
-        sector.block_offset *= disk_spec.logical_sector_size as u64;
-
-        let bat_entry = match bat.get(sector.bat_index as usize) {
-            Some(entry) => entry.0,
-            None => {
-                return Err(VhdxIoError::InvalidBatIndex);
-            }
-        };
-        sector.file_offset = bat_entry & vhdx_bat::BAT_FILE_OFF_MASK;
-        if sector.file_offset != 0 {
-            sector.file_offset += sector.block_offset;
-        }
-
-        Ok(sector)
-    }
-}
-
-/// VHDx IO read routine: requires relative sector index and count for the
-/// requested data.
-pub fn read(
-    f: &mut File,
-    buf: &mut [u8],
-    disk_spec: &DiskSpec,
-    bat: &[BatEntry],
-    mut sector_index: u64,
-    mut sector_count: u64,
-) -> Result<usize> {
-    if disk_spec.has_parent {
-        return Err(VhdxIoError::UnsupportedMode);
-    }
-
-    let mut read_count: usize = 0;
-    while sector_count > 0 {
-        let sector = Sector::new(disk_spec, bat, sector_index, sector_count)?;
-
-        let bat_entry = match bat.get(sector.bat_index as usize) {
-            Some(entry) => entry.0,
-            None => {
-                return Err(VhdxIoError::InvalidBatIndex);
-            }
-        };
-
-        match bat_entry & vhdx_bat::BAT_STATE_BIT_MASK {
-            vhdx_bat::PAYLOAD_BLOCK_NOT_PRESENT
-            | vhdx_bat::PAYLOAD_BLOCK_UNDEFINED
-            | vhdx_bat::PAYLOAD_BLOCK_UNMAPPED
-            | vhdx_bat::PAYLOAD_BLOCK_ZERO => {}
-            vhdx_bat::PAYLOAD_BLOCK_FULLY_PRESENT => {
-                f.seek(SeekFrom::Start(sector.file_offset))
-                    .map_err(VhdxIoError::ReadSectorBlock)?;
-                f.read_exact(
-                    &mut buf
-                        [read_count..(read_count + (sector.free_sectors * SECTOR_SIZE) as usize)],
-                )
-                .map_err(VhdxIoError::ReadSectorBlock)?;
-            }
-            vhdx_bat::PAYLOAD_BLOCK_PARTIALLY_PRESENT => {
-                return Err(VhdxIoError::UnsupportedMode);
-            }
-            _ => {
-                return Err(VhdxIoError::InvalidBatEntryState);
-            }
-        };
-        sector_count -= sector.free_sectors;
-        sector_index += sector.free_sectors;
-        read_count += sector.free_bytes as usize;
-    }
-    Ok(read_count)
-}
-
-/// VHDx IO write routine: requires relative sector index and count for the
-/// requested data.
-pub fn write(
-    f: &mut File,
-    buf: &[u8],
-    disk_spec: &mut DiskSpec,
-    bat_offset: u64,
-    bat: &mut [BatEntry],
-    mut sector_index: u64,
-    mut sector_count: u64,
-) -> Result<usize> {
-    if disk_spec.has_parent {
-        return Err(VhdxIoError::UnsupportedMode);
-    }
-
-    let mut write_count: usize = 0;
-    while sector_count > 0 {
-        let sector = Sector::new(disk_spec, bat, sector_index, sector_count)?;
-
-        let bat_entry = match bat.get(sector.bat_index as usize) {
-            Some(entry) => entry.0,
-            None => {
-                return Err(VhdxIoError::InvalidBatIndex);
-            }
-        };
-
-        match bat_entry & vhdx_bat::BAT_STATE_BIT_MASK {
-            vhdx_bat::PAYLOAD_BLOCK_NOT_PRESENT
-            | vhdx_bat::PAYLOAD_BLOCK_UNDEFINED
-            | vhdx_bat::PAYLOAD_BLOCK_UNMAPPED
-            | vhdx_bat::PAYLOAD_BLOCK_ZERO => {
-                let file_offset =
-                    align!(disk_spec.image_size, vhdx_metadata::BLOCK_SIZE_MIN as u64);
-                let new_size = file_offset
-                    .checked_add(disk_spec.block_size as u64)
-                    .ok_or(VhdxIoError::InvalidDiskSize)?;
-
-                f.set_len(new_size).map_err(VhdxIoError::ResizeFile)?;
-                disk_spec.image_size = new_size;
-
-                let new_bat_entry = file_offset
-                    | (vhdx_bat::PAYLOAD_BLOCK_FULLY_PRESENT & vhdx_bat::BAT_STATE_BIT_MASK);
-                bat[sector.bat_index as usize] = BatEntry(new_bat_entry);
-                BatEntry::write_bat_entries(f, bat_offset, bat).map_err(VhdxIoError::WriteBat)?;
-
-                if file_offset < vhdx_metadata::BLOCK_SIZE_MIN as u64 {
-                    break;
-                }
-
-                f.seek(SeekFrom::Start(file_offset))
-                    .map_err(VhdxIoError::ReadSectorBlock)?;
-                f.write_all(
-                    &buf[write_count..(write_count + (sector.free_sectors * SECTOR_SIZE) as usize)],
-                )
-                .map_err(VhdxIoError::ReadSectorBlock)?;
-            }
-            vhdx_bat::PAYLOAD_BLOCK_FULLY_PRESENT => {
-                if sector.file_offset < vhdx_metadata::BLOCK_SIZE_MIN as u64 {
-                    break;
-                }
-
-                f.seek(SeekFrom::Start(sector.file_offset))
-                    .map_err(VhdxIoError::ReadSectorBlock)?;
-                f.write_all(
-                    &buf[write_count..(write_count + (sector.free_sectors * SECTOR_SIZE) as usize)],
-                )
-                .map_err(VhdxIoError::ReadSectorBlock)?;
-            }
-            vhdx_bat::PAYLOAD_BLOCK_PARTIALLY_PRESENT => {
-                return Err(VhdxIoError::UnsupportedMode);
-            }
-            _ => {
-                return Err(VhdxIoError::InvalidBatEntryState);
-            }
-        };
-        sector_count -= sector.free_sectors;
-        sector_index += sector.free_sectors;
-        write_count += sector.free_bytes as usize;
-    }
-    Ok(write_count)
-}

block_util/Cargo.toml

@@ -0,0 +1,25 @@
+[package]
+name = "block_util"
+version = "0.1.0"
+authors = ["The Cloud Hypervisor Authors"]
+edition = "2021"
+
+[features]
+default = []
+
+[dependencies]
+io-uring = "0.5.13"
+libc = "0.2.139"
+log = "0.4.17"
+qcow = { path = "../qcow" }
+smallvec = "1.10.0"
+thiserror = "1.0.39"
+versionize = "0.1.10"
+versionize_derive = "0.1.4"
+vhdx = { path = "../vhdx" }
+virtio-bindings = { version = "0.2.0", features = ["virtio-v5_0_0"] }
+virtio-queue = "0.7.1"
+vm-memory = { version = "0.10.0", features = ["backend-mmap", "backend-atomic", "backend-bitmap"] }
+vm-virtio = { path = "../vm-virtio" }
+vmm-sys-util = "0.11.0"
+

block_util/src/async_io.rs

@@ -0,0 +1,145 @@
+// Copyright © 2021 Intel Corporation
+//
+// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
+
+use libc::{ioctl, S_IFBLK, S_IFMT};
+use std::fs::File;
+use std::os::unix::io::AsRawFd;
+use thiserror::Error;
+use vmm_sys_util::eventfd::EventFd;
+use vmm_sys_util::{ioctl_io_nr, ioctl_ioc_nr};
+
+#[derive(Error, Debug)]
+pub enum DiskFileError {
+    /// Failed getting disk file size.
+    #[error("Failed getting disk file size: {0}")]
+    Size(#[source] std::io::Error),
+    /// Failed creating a new AsyncIo.
+    #[error("Failed creating a new AsyncIo: {0}")]
+    NewAsyncIo(#[source] std::io::Error),
+}
+
+#[derive(Debug)]
+pub struct DiskTopology {
+    pub logical_block_size: u64,
+    pub physical_block_size: u64,
+    pub minimum_io_size: u64,
+    pub optimal_io_size: u64,
+}
+
+impl Default for DiskTopology {
+    fn default() -> Self {
+        Self {
+            logical_block_size: 512,
+            physical_block_size: 512,
+            minimum_io_size: 512,
+            optimal_io_size: 0,
+        }
+    }
+}
+
+ioctl_io_nr!(BLKSSZGET, 0x12, 104);
+ioctl_io_nr!(BLKPBSZGET, 0x12, 123);
+ioctl_io_nr!(BLKIOMIN, 0x12, 120);
+ioctl_io_nr!(BLKIOOPT, 0x12, 121);
+
+enum BlockSize {
+    LogicalBlock,
+    PhysicalBlock,
+    MinimumIo,
+    OptimalIo,
+}
+
+impl DiskTopology {
+    fn is_block_device(f: &mut File) -> std::io::Result<bool> {
+        let mut stat = std::mem::MaybeUninit::<libc::stat>::uninit();
+        // SAFETY: FFI call with a valid fd and buffer
+        let ret = unsafe { libc::fstat(f.as_raw_fd(), stat.as_mut_ptr()) };
+        if ret != 0 {
+            return Err(std::io::Error::last_os_error());
+        }
+
+        // SAFETY: stat is valid at this point
+        let is_block = unsafe { (*stat.as_ptr()).st_mode & S_IFMT == S_IFBLK };
+        Ok(is_block)
+    }
+
+    // libc::ioctl() takes different types on different architectures
+    fn query_block_size(f: &mut File, block_size_type: BlockSize) -> std::io::Result<u64> {
+        let mut block_size = 0;
+        // SAFETY: FFI call with correct arguments
+        let ret = unsafe {
+            ioctl(
+                f.as_raw_fd(),
+                match block_size_type {
+                    BlockSize::LogicalBlock => BLKSSZGET(),
+                    BlockSize::PhysicalBlock => BLKPBSZGET(),
+                    BlockSize::MinimumIo => BLKIOMIN(),
+                    BlockSize::OptimalIo => BLKIOOPT(),
+                } as _,
+                &mut block_size,
+            )
+        };
+        if ret != 0 {
+            return Err(std::io::Error::last_os_error());
+        };
+
+        Ok(block_size)
+    }
+
+    pub fn probe(f: &mut File) -> std::io::Result<Self> {
+        if !Self::is_block_device(f)? {
+            return Ok(DiskTopology::default());
+        }
+
+        Ok(DiskTopology {
+            logical_block_size: Self::query_block_size(f, BlockSize::LogicalBlock)?,
+            physical_block_size: Self::query_block_size(f, BlockSize::PhysicalBlock)?,
+            minimum_io_size: Self::query_block_size(f, BlockSize::MinimumIo)?,
+            optimal_io_size: Self::query_block_size(f, BlockSize::OptimalIo)?,
+        })
+    }
+}
+
+pub type DiskFileResult<T> = std::result::Result<T, DiskFileError>;
+
+pub trait DiskFile: Send {
+    fn size(&mut self) -> DiskFileResult<u64>;
+    fn new_async_io(&self, ring_depth: u32) -> DiskFileResult<Box<dyn AsyncIo>>;
+    fn topology(&mut self) -> DiskTopology {
+        DiskTopology::default()
+    }
+}
+
+#[derive(Error, Debug)]
+pub enum AsyncIoError {
+    /// Failed vectored reading from file.
+    #[error("Failed vectored reading from file: {0}")]
+    ReadVectored(#[source] std::io::Error),
+    /// Failed vectored writing to file.
+    #[error("Failed vectored writing to file: {0}")]
+    WriteVectored(#[source] std::io::Error),
+    /// Failed synchronizing file.
+    #[error("Failed synchronizing file: {0}")]
+    Fsync(#[source] std::io::Error),
+}
+
+pub type AsyncIoResult<T> = std::result::Result<T, AsyncIoError>;
+
+pub trait AsyncIo: Send {
+    fn notifier(&self) -> &EventFd;
+    fn read_vectored(
+        &mut self,
+        offset: libc::off_t,
+        iovecs: &[libc::iovec],
+        user_data: u64,
+    ) -> AsyncIoResult<()>;
+    fn write_vectored(
+        &mut self,
+        offset: libc::off_t,
+        iovecs: &[libc::iovec],
+        user_data: u64,
+    ) -> AsyncIoResult<()>;
+    fn fsync(&mut self, user_data: Option<u64>) -> AsyncIoResult<()>;
+    fn next_completed_request(&mut self) -> Option<(u64, i32)>;
+}

block_util/src/fixed_vhd_async.rs

@@ -2,41 +2,42 @@
 //
 // SPDX-License-Identifier: Apache-2.0
 
+use crate::async_io::{
+    AsyncIo, AsyncIoError, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult,
+};
+use crate::raw_async::RawFileAsync;
+use crate::vhd::VhdFooter;
 use std::fs::File;
 use std::os::unix::io::{AsRawFd, RawFd};
-
 use vmm_sys_util::eventfd::EventFd;
 
-use crate::async_io::{
-    AsyncIo, AsyncIoError, AsyncIoResult, BorrowedDiskFd, DiskFile, DiskFileError, DiskFileResult,
-};
-use crate::fixed_vhd::FixedVhd;
-use crate::raw_async::RawFileAsync;
-use crate::{BatchRequest, BlockBackend};
-
-pub struct FixedVhdDiskAsync(FixedVhd);
+pub struct FixedVhdDiskAsync {
+    file: File,
+    size: u64,
+}
 
 impl FixedVhdDiskAsync {
-    pub fn new(file: File) -> std::io::Result<Self> {
-        Ok(Self(FixedVhd::new(file)?))
+    pub fn new(mut file: File) -> std::io::Result<Self> {
+        let footer = VhdFooter::new(&mut file)?;
+
+        Ok(FixedVhdDiskAsync {
+            file,
+            size: footer.current_size(),
+        })
     }
 }
 
 impl DiskFile for FixedVhdDiskAsync {
     fn size(&mut self) -> DiskFileResult<u64> {
-        Ok(self.0.size().unwrap())
+        Ok(self.size)
     }
 
     fn new_async_io(&self, ring_depth: u32) -> DiskFileResult<Box<dyn AsyncIo>> {
         Ok(Box::new(
-            FixedVhdAsync::new(self.0.as_raw_fd(), ring_depth, self.0.size().unwrap())
+            FixedVhdAsync::new(self.file.as_raw_fd(), ring_depth, self.size)
                 .map_err(DiskFileError::NewAsyncIo)?,
         ) as Box<dyn AsyncIo>)
     }
-
-    fn fd(&mut self) -> BorrowedDiskFd<'_> {
-        BorrowedDiskFd::new(self.0.as_raw_fd())
-    }
 }
 
 pub struct FixedVhdAsync {
@@ -106,12 +107,4 @@ impl AsyncIo for FixedVhdAsync {
     fn next_completed_request(&mut self) -> Option<(u64, i32)> {
         self.raw_file_async.next_completed_request()
     }
-
-    fn batch_requests_enabled(&self) -> bool {
-        true
-    }
-
-    fn submit_batch_requests(&mut self, batch_request: &[BatchRequest]) -> AsyncIoResult<()> {
-        self.raw_file_async.submit_batch_requests(batch_request)
-    }
 }

block_util/src/fixed_vhd_sync.rs

@@ -2,41 +2,42 @@
 //
 // SPDX-License-Identifier: Apache-2.0
 
+use crate::async_io::{
+    AsyncIo, AsyncIoError, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult,
+};
+use crate::raw_sync::RawFileSync;
+use crate::vhd::VhdFooter;
 use std::fs::File;
 use std::os::unix::io::{AsRawFd, RawFd};
-
 use vmm_sys_util::eventfd::EventFd;
 
-use crate::BlockBackend;
-use crate::async_io::{
-    AsyncIo, AsyncIoError, AsyncIoResult, BorrowedDiskFd, DiskFile, DiskFileError, DiskFileResult,
-};
-use crate::fixed_vhd::FixedVhd;
-use crate::raw_sync::RawFileSync;
-
-pub struct FixedVhdDiskSync(FixedVhd);
+pub struct FixedVhdDiskSync {
+    file: File,
+    size: u64,
+}
 
 impl FixedVhdDiskSync {
-    pub fn new(file: File) -> std::io::Result<Self> {
-        Ok(Self(FixedVhd::new(file)?))
+    pub fn new(mut file: File) -> std::io::Result<Self> {
+        let footer = VhdFooter::new(&mut file)?;
+
+        Ok(FixedVhdDiskSync {
+            file,
+            size: footer.current_size(),
+        })
     }
 }
 
 impl DiskFile for FixedVhdDiskSync {
     fn size(&mut self) -> DiskFileResult<u64> {
-        Ok(self.0.size().unwrap())
+        Ok(self.size)
     }
 
     fn new_async_io(&self, _ring_depth: u32) -> DiskFileResult<Box<dyn AsyncIo>> {
         Ok(Box::new(
-            FixedVhdSync::new(self.0.as_raw_fd(), self.0.size().unwrap())
+            FixedVhdSync::new(self.file.as_raw_fd(), self.size)
                 .map_err(DiskFileError::NewAsyncIo)?,
         ) as Box<dyn AsyncIo>)
     }
-
-    fn fd(&mut self) -> BorrowedDiskFd<'_> {
-        BorrowedDiskFd::new(self.0.as_raw_fd())
-    }
 }
 
 pub struct FixedVhdSync {

block_util/src/lib.rs

@@ -12,55 +12,42 @@
 extern crate log;
 
 pub mod async_io;
-pub mod fcntl;
-pub mod fixed_vhd;
-#[cfg(feature = "io_uring")]
-/// Enabled with the `"io_uring"` feature
 pub mod fixed_vhd_async;
 pub mod fixed_vhd_sync;
-pub mod qcow;
 pub mod qcow_sync;
-#[cfg(feature = "io_uring")]
-/// Async primitives based on `io-uring`
-///
-/// Enabled with the `"io_uring"` feature
 pub mod raw_async;
-pub mod raw_async_aio;
 pub mod raw_sync;
 pub mod vhd;
-pub mod vhdx;
 pub mod vhdx_sync;
 
-use std::alloc::{Layout, alloc_zeroed, dealloc};
+use crate::async_io::{AsyncIo, AsyncIoError, AsyncIoResult};
+use io_uring::{opcode, IoUring, Probe};
+use smallvec::SmallVec;
+use std::alloc::{alloc_zeroed, dealloc, Layout};
+use std::cmp;
 use std::collections::VecDeque;
-use std::fmt::Debug;
+use std::convert::TryInto;
 use std::fs::File;
 use std::io::{self, IoSlice, IoSliceMut, Read, Seek, SeekFrom, Write};
 use std::os::linux::fs::MetadataExt;
-use std::os::unix::io::AsRawFd;
 use std::path::Path;
+use std::result;
 use std::sync::Arc;
+use std::sync::MutexGuard;
 use std::time::Instant;
-use std::{cmp, result};
-
-#[cfg(feature = "io_uring")]
-use io_uring::{IoUring, Probe, opcode};
-use libc::{S_IFBLK, S_IFMT, ioctl};
-use serde::{Deserialize, Serialize};
-use smallvec::SmallVec;
 use thiserror::Error;
+use versionize::{VersionMap, Versionize, VersionizeResult};
+use versionize_derive::Versionize;
 use virtio_bindings::virtio_blk::*;
 use virtio_queue::DescriptorChain;
-use vm_memory::bitmap::Bitmap;
 use vm_memory::{
-    ByteValued, Bytes, GuestAddress, GuestMemory, GuestMemoryError, GuestMemoryLoadGuard,
+    bitmap::AtomicBitmap, bitmap::Bitmap, ByteValued, Bytes, GuestAddress, GuestMemory,
+    GuestMemoryError, GuestMemoryLoadGuard,
 };
 use vm_virtio::{AccessPlatform, Translatable};
 use vmm_sys_util::eventfd::EventFd;
-use vmm_sys_util::{aio, ioctl_io_nr};
 
-use crate::async_io::{AsyncIo, AsyncIoError, AsyncIoResult};
-use crate::vhdx::VhdxError;
+type GuestMemoryMmap = vm_memory::GuestMemoryMmap<AtomicBitmap>;
 
 const SECTOR_SHIFT: u8 = 9;
 pub const SECTOR_SIZE: u64 = 0x01 << SECTOR_SHIFT;
@@ -68,9 +55,9 @@ pub const SECTOR_SIZE: u64 = 0x01 << SECTOR_SHIFT;
 #[derive(Error, Debug)]
 pub enum Error {
     #[error("Guest gave us bad memory addresses")]
-    GuestMemory(#[source] GuestMemoryError),
+    GuestMemory(GuestMemoryError),
     #[error("Guest gave us offsets that would have overflowed a usize")]
-    CheckedOffset(GuestAddress, usize /* sector offset */),
+    CheckedOffset(GuestAddress, usize),
     #[error("Guest gave us a write only descriptor that protocol says to read from")]
     UnexpectedWriteOnlyDescriptor,
     #[error("Guest gave us a read only descriptor that protocol says to write to")]
@@ -79,22 +66,12 @@ pub enum Error {
     DescriptorChainTooShort,
     #[error("Guest gave us a descriptor that was too short to use")]
     DescriptorLengthTooSmall,
-    #[error("Failed to detect image type")]
-    DetectImageType(#[source] std::io::Error),
-    #[error("Failure in fixed vhd")]
-    FixedVhdError(#[source] std::io::Error),
     #[error("Getting a block's metadata fails for any reason")]
     GetFileMetadata,
     #[error("The requested operation would cause a seek beyond disk end")]
     InvalidOffset,
-    #[error("Failure in qcow")]
-    QcowError(#[source] qcow::Error),
-    #[error("Failure in raw file")]
-    RawFileError(#[source] std::io::Error),
     #[error("The requested operation does not support multiple descriptors")]
     TooManyDescriptors,
-    #[error("Failure in vhdx")]
-    VhdxError(#[source] VhdxError),
 }
 
 fn build_device_id(disk_path: &Path) -> result::Result<String, Error> {
@@ -112,8 +89,8 @@ fn build_device_id(disk_path: &Path) -> result::Result<String, Error> {
     Ok(device_id)
 }
 
-pub fn build_serial(disk_path: &Path) -> Vec<u8> {
-    let mut default_serial = vec![0; VIRTIO_BLK_ID_BYTES as usize];
+pub fn build_disk_image_id(disk_path: &Path) -> Vec<u8> {
+    let mut default_disk_image_id = vec![0; VIRTIO_BLK_ID_BYTES as usize];
     match build_device_id(disk_path) {
         Err(_) => {
             warn!("Could not generate device id. We'll use a default.");
@@ -123,57 +100,48 @@ pub fn build_serial(disk_path: &Path) -> Vec<u8> {
             // This will also zero out any leftover bytes.
             let disk_id = m.as_bytes();
             let bytes_to_copy = cmp::min(disk_id.len(), VIRTIO_BLK_ID_BYTES as usize);
-            default_serial[..bytes_to_copy].clone_from_slice(&disk_id[..bytes_to_copy])
+            default_disk_image_id[..bytes_to_copy].clone_from_slice(&disk_id[..bytes_to_copy])
         }
     }
-    default_serial
+    default_disk_image_id
 }
 
 #[derive(Error, Debug)]
 pub enum ExecuteError {
-    #[error("Bad request")]
-    BadRequest(#[source] Error),
-    #[error("Failed to flush")]
-    Flush(#[source] io::Error),
-    #[error("Failed to read")]
-    Read(#[source] GuestMemoryError),
-    #[error("Failed to read_exact")]
-    ReadExact(#[source] io::Error),
-    #[error("Can't execute an operation other than `read` on a read-only device")]
-    ReadOnly,
-    #[error("Failed to seek")]
-    Seek(#[source] io::Error),
-    #[error("Failed to write")]
-    Write(#[source] GuestMemoryError),
-    #[error("Failed to write_all")]
-    WriteAll(#[source] io::Error),
+    #[error("Bad request: {0}")]
+    BadRequest(Error),
+    #[error("Falied to flush: {0}")]
+    Flush(io::Error),
+    #[error("Failed to read: {0}")]
+    Read(GuestMemoryError),
+    #[error("Failed to seek: {0}")]
+    Seek(io::Error),
+    #[error("Failed to write: {0}")]
+    Write(GuestMemoryError),
     #[error("Unsupported request: {0}")]
     Unsupported(u32),
-    #[error("Failed to submit io uring")]
-    SubmitIoUring(#[source] io::Error),
-    #[error("Failed to get guest address")]
-    GetHostAddress(#[source] GuestMemoryError),
-    #[error("Failed to async read")]
-    AsyncRead(#[source] AsyncIoError),
-    #[error("Failed to async write")]
-    AsyncWrite(#[source] AsyncIoError),
-    #[error("failed to async flush")]
-    AsyncFlush(#[source] AsyncIoError),
-    #[error("Failed allocating a temporary buffer")]
-    TemporaryBufferAllocation(#[source] io::Error),
+    #[error("Failed to submit io uring: {0}")]
+    SubmitIoUring(io::Error),
+    #[error("Failed to get guest address: {0}")]
+    GetHostAddress(GuestMemoryError),
+    #[error("Failed to async read: {0}")]
+    AsyncRead(AsyncIoError),
+    #[error("Failed to async write: {0}")]
+    AsyncWrite(AsyncIoError),
+    #[error("failed to async flush: {0}")]
+    AsyncFlush(AsyncIoError),
+    #[error("Failed allocating a temporary buffer: {0}")]
+    TemporaryBufferAllocation(io::Error),
 }
 
 impl ExecuteError {
-    pub fn status(&self) -> u8 {
-        let status = match *self {
+    pub fn status(&self) -> u32 {
+        match *self {
             ExecuteError::BadRequest(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::Flush(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::Read(_) => VIRTIO_BLK_S_IOERR,
-            ExecuteError::ReadExact(_) => VIRTIO_BLK_S_IOERR,
-            ExecuteError::ReadOnly => VIRTIO_BLK_S_IOERR,
             ExecuteError::Seek(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::Write(_) => VIRTIO_BLK_S_IOERR,
-            ExecuteError::WriteAll(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::Unsupported(_) => VIRTIO_BLK_S_UNSUPP,
             ExecuteError::SubmitIoUring(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::GetHostAddress(_) => VIRTIO_BLK_S_IOERR,
@@ -181,8 +149,7 @@ impl ExecuteError {
             ExecuteError::AsyncWrite(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::AsyncFlush(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::TemporaryBufferAllocation(_) => VIRTIO_BLK_S_IOERR,
-        };
-        status as u8
+        }
     }
 }
 
@@ -195,8 +162,8 @@ pub enum RequestType {
     Unsupported(u32),
 }
 
-pub fn request_type<B: Bitmap + 'static>(
-    mem: &vm_memory::GuestMemoryMmap<B>,
+pub fn request_type(
+    mem: &GuestMemoryMmap,
     desc_addr: GuestAddress,
 ) -> result::Result<RequestType, Error> {
     let type_ = mem.read_obj(desc_addr).map_err(Error::GuestMemory)?;
@@ -209,10 +176,7 @@ pub fn request_type<B: Bitmap + 'static>(
     }
 }
 
-fn sector<B: Bitmap + 'static>(
-    mem: &vm_memory::GuestMemoryMmap<B>,
-    desc_addr: GuestAddress,
-) -> result::Result<u64, Error> {
+fn sector(mem: &GuestMemoryMmap, desc_addr: GuestAddress) -> result::Result<u64, Error> {
     const SECTOR_OFFSET: usize = 8;
     let addr = match mem.checked_offset(desc_addr, SECTOR_OFFSET) {
         Some(v) => v,
@@ -222,8 +186,6 @@ fn sector<B: Bitmap + 'static>(
     mem.read_obj(addr).map_err(Error::GuestMemory)
 }
 
-const DEFAULT_DESCRIPTOR_VEC_SIZE: usize = 32;
-
 #[derive(Debug)]
 pub struct AlignedOperation {
     origin_ptr: u64,
@@ -232,41 +194,28 @@ pub struct AlignedOperation {
     layout: Layout,
 }
 
-pub struct BatchRequest {
-    pub offset: libc::off_t,
-    pub iovecs: SmallVec<[libc::iovec; DEFAULT_DESCRIPTOR_VEC_SIZE]>,
-    pub user_data: u64,
-    pub request_type: RequestType,
-}
-
-pub struct ExecuteAsync {
-    // `true` if the execution will complete asynchronously
-    pub async_complete: bool,
-    // request need to be batched for submission if any
-    pub batch_request: Option<BatchRequest>,
-}
-
 #[derive(Debug)]
 pub struct Request {
     pub request_type: RequestType,
     pub sector: u64,
-    pub data_descriptors: SmallVec<[(GuestAddress, u32); DEFAULT_DESCRIPTOR_VEC_SIZE]>,
+    pub data_descriptors: SmallVec<[(GuestAddress, u32); 1]>,
     pub status_addr: GuestAddress,
     pub writeback: bool,
-    pub aligned_operations: SmallVec<[AlignedOperation; DEFAULT_DESCRIPTOR_VEC_SIZE]>,
+    pub aligned_operations: SmallVec<[AlignedOperation; 1]>,
     pub start: Instant,
 }
 
 impl Request {
-    pub fn parse<B: Bitmap + 'static>(
-        desc_chain: &mut DescriptorChain<GuestMemoryLoadGuard<vm_memory::GuestMemoryMmap<B>>>,
+    pub fn parse(
+        desc_chain: &mut DescriptorChain<GuestMemoryLoadGuard<GuestMemoryMmap>>,
         access_platform: Option<&Arc<dyn AccessPlatform>>,
     ) -> result::Result<Request, Error> {
         let hdr_desc = desc_chain
             .next()
             .ok_or(Error::DescriptorChainTooShort)
-            .inspect_err(|_| {
+            .map_err(|e| {
                 error!("Missing head descriptor");
+                e
             })?;
 
         // The head contains the request type which MUST be readable.
@@ -281,10 +230,10 @@ impl Request {
         let mut req = Request {
             request_type: request_type(desc_chain.memory(), hdr_desc_addr)?,
             sector: sector(desc_chain.memory(), hdr_desc_addr)?,
-            data_descriptors: SmallVec::with_capacity(DEFAULT_DESCRIPTOR_VEC_SIZE),
+            data_descriptors: SmallVec::with_capacity(1),
             status_addr: GuestAddress(0),
             writeback: true,
-            aligned_operations: SmallVec::with_capacity(DEFAULT_DESCRIPTOR_VEC_SIZE),
+            aligned_operations: SmallVec::with_capacity(1),
             start: Instant::now(),
         };
 
@@ -292,8 +241,9 @@ impl Request {
         let mut desc = desc_chain
             .next()
             .ok_or(Error::DescriptorChainTooShort)
-            .inspect_err(|_| {
+            .map_err(|e| {
                 error!("Only head descriptor present: request = {:?}", req);
+                e
             })?;
 
         if !desc.has_next() {
@@ -324,8 +274,9 @@ impl Request {
                 desc = desc_chain
                     .next()
                     .ok_or(Error::DescriptorChainTooShort)
-                    .inspect_err(|_| {
+                    .map_err(|e| {
                         error!("DescriptorChain corrupted: request = {:?}", req);
+                        e
                     })?;
             }
             status_desc = desc;
@@ -347,12 +298,12 @@ impl Request {
         Ok(req)
     }
 
-    pub fn execute<T: Seek + Read + Write, B: Bitmap + 'static>(
+    pub fn execute<T: Seek + Read + Write>(
         &self,
         disk: &mut T,
         disk_nsectors: u64,
-        mem: &vm_memory::GuestMemoryMmap<B>,
-        serial: &[u8],
+        mem: &GuestMemoryMmap,
+        disk_id: &[u8],
     ) -> result::Result<u32, ExecuteError> {
         disk.seek(SeekFrom::Start(self.sector << SECTOR_SHIFT))
             .map_err(ExecuteError::Seek)?;
@@ -371,31 +322,23 @@ impl Request {
 
             match self.request_type {
                 RequestType::In => {
-                    let mut buf = vec![0u8; *data_len as usize];
-                    disk.read_exact(&mut buf).map_err(ExecuteError::ReadExact)?;
-                    mem.read_exact_volatile_from(
-                        *data_addr,
-                        &mut buf.as_slice(),
-                        *data_len as usize,
-                    )
-                    .map_err(ExecuteError::Read)?;
+                    mem.read_exact_from(*data_addr, disk, *data_len as usize)
+                        .map_err(ExecuteError::Read)?;
                     len += data_len;
                 }
                 RequestType::Out => {
-                    let mut buf: Vec<u8> = Vec::new();
-                    mem.write_all_volatile_to(*data_addr, &mut buf, *data_len as usize)
+                    mem.write_all_to(*data_addr, disk, *data_len as usize)
                         .map_err(ExecuteError::Write)?;
-                    disk.write_all(&buf).map_err(ExecuteError::WriteAll)?;
                     if !self.writeback {
                         disk.flush().map_err(ExecuteError::Flush)?;
                     }
                 }
                 RequestType::Flush => disk.flush().map_err(ExecuteError::Flush)?,
                 RequestType::GetDeviceId => {
-                    if (*data_len as usize) < serial.len() {
+                    if (*data_len as usize) < disk_id.len() {
                         return Err(ExecuteError::BadRequest(Error::InvalidOffset));
                     }
-                    mem.write_slice(serial, *data_addr)
+                    mem.write_slice(disk_id, *data_addr)
                         .map_err(ExecuteError::Write)?;
                 }
                 RequestType::Unsupported(t) => return Err(ExecuteError::Unsupported(t)),
@@ -404,34 +347,28 @@ impl Request {
         Ok(len)
     }
 
-    pub fn execute_async<B: Bitmap + 'static>(
+    pub fn execute_async(
         &mut self,
-        mem: &vm_memory::GuestMemoryMmap<B>,
+        mem: &GuestMemoryMmap,
         disk_nsectors: u64,
         disk_image: &mut dyn AsyncIo,
-        serial: &[u8],
+        disk_id: &[u8],
         user_data: u64,
-    ) -> result::Result<ExecuteAsync, ExecuteError> {
+    ) -> result::Result<bool, ExecuteError> {
         let sector = self.sector;
         let request_type = self.request_type;
         let offset = (sector << SECTOR_SHIFT) as libc::off_t;
 
-        let mut iovecs: SmallVec<[libc::iovec; DEFAULT_DESCRIPTOR_VEC_SIZE]> =
+        let mut iovecs: SmallVec<[libc::iovec; 1]> =
             SmallVec::with_capacity(self.data_descriptors.len());
-        for &(data_addr, data_len) in &self.data_descriptors {
-            let _: u32 = data_len; // compiler-checked documentation
-            const _: () = assert!(
-                core::mem::size_of::<u32>() <= core::mem::size_of::<usize>(),
-                "unsupported platform"
-            );
-            if data_len == 0 {
+        for (data_addr, data_len) in &self.data_descriptors {
+            if *data_len == 0 {
                 continue;
             }
-            let mut top: u64 = u64::from(data_len) / SECTOR_SIZE;
-            if u64::from(data_len) % SECTOR_SIZE != 0 {
+            let mut top: u64 = u64::from(*data_len) / SECTOR_SIZE;
+            if u64::from(*data_len) % SECTOR_SIZE != 0 {
                 top += 1;
             }
-            let data_len = data_len as usize;
             top = top
                 .checked_add(sector)
                 .ok_or(ExecuteError::BadRequest(Error::InvalidOffset))?;
@@ -440,16 +377,17 @@ impl Request {
             }
 
             let origin_ptr = mem
-                .get_slice(data_addr, data_len)
+                .get_slice(*data_addr, *data_len as usize)
                 .map_err(ExecuteError::GetHostAddress)?
-                .ptr_guard();
+                .as_ptr();
 
             // Verify the buffer alignment.
             // In case it's not properly aligned, an intermediate buffer is
             // created with the correct alignment, and a copy from/to the
             // origin buffer is performed, depending on the type of operation.
-            let iov_base = if !(origin_ptr.as_ptr() as u64).is_multiple_of(SECTOR_SIZE) {
-                let layout = Layout::from_size_align(data_len, SECTOR_SIZE as usize).unwrap();
+            let iov_base = if (origin_ptr as u64) % SECTOR_SIZE != 0 {
+                let layout =
+                    Layout::from_size_align(*data_len as usize, SECTOR_SIZE as usize).unwrap();
                 // SAFETY: layout has non-zero size
                 let aligned_ptr = unsafe { alloc_zeroed(layout) };
                 if aligned_ptr.is_null() {
@@ -463,34 +401,32 @@ impl Request {
                 if request_type == RequestType::Out {
                     // SAFETY: destination buffer has been allocated with
                     // the proper size.
-                    unsafe { std::ptr::copy(origin_ptr.as_ptr(), aligned_ptr, data_len) };
+                    unsafe {
+                        std::ptr::copy(origin_ptr as *const u8, aligned_ptr, *data_len as usize)
+                    };
                 }
 
                 // Store both origin and aligned pointers for complete_async()
                 // to process them.
                 self.aligned_operations.push(AlignedOperation {
-                    origin_ptr: origin_ptr.as_ptr() as u64,
+                    origin_ptr: origin_ptr as u64,
                     aligned_ptr: aligned_ptr as u64,
-                    size: data_len,
+                    size: *data_len as usize,
                     layout,
                 });
 
                 aligned_ptr as *mut libc::c_void
             } else {
-                origin_ptr.as_ptr() as *mut libc::c_void
+                origin_ptr as *mut libc::c_void
             };
 
             let iovec = libc::iovec {
                 iov_base,
-                iov_len: data_len as libc::size_t,
+                iov_len: *data_len as libc::size_t,
             };
             iovecs.push(iovec);
         }
 
-        let mut ret = ExecuteAsync {
-            async_complete: true,
-            batch_request: None,
-        };
         // Queue operations expected to be submitted.
         match request_type {
             RequestType::In => {
@@ -500,32 +436,14 @@ impl Request {
                         .bitmap()
                         .mark_dirty(0, *data_len as usize);
                 }
-                if disk_image.batch_requests_enabled() {
-                    ret.batch_request = Some(BatchRequest {
-                        offset,
-                        iovecs,
-                        user_data,
-                        request_type,
-                    });
-                } else {
-                    disk_image
-                        .read_vectored(offset, &iovecs, user_data)
-                        .map_err(ExecuteError::AsyncRead)?;
-                }
+                disk_image
+                    .read_vectored(offset, &iovecs, user_data)
+                    .map_err(ExecuteError::AsyncRead)?;
             }
             RequestType::Out => {
-                if disk_image.batch_requests_enabled() {
-                    ret.batch_request = Some(BatchRequest {
-                        offset,
-                        iovecs,
-                        user_data,
-                        request_type,
-                    });
-                } else {
-                    disk_image
-                        .write_vectored(offset, &iovecs, user_data)
-                        .map_err(ExecuteError::AsyncWrite)?;
-                }
+                disk_image
+                    .write_vectored(offset, &iovecs, user_data)
+                    .map_err(ExecuteError::AsyncWrite)?;
             }
             RequestType::Flush => {
                 disk_image
@@ -538,18 +456,17 @@ impl Request {
                 } else {
                     return Err(ExecuteError::BadRequest(Error::TooManyDescriptors));
                 };
-                if (data_len as usize) < serial.len() {
+                if (data_len as usize) < disk_id.len() {
                     return Err(ExecuteError::BadRequest(Error::InvalidOffset));
                 }
-                mem.write_slice(serial, data_addr)
+                mem.write_slice(disk_id, data_addr)
                     .map_err(ExecuteError::Write)?;
-                ret.async_complete = false;
-                return Ok(ret);
+                return Ok(false);
             }
             RequestType::Unsupported(t) => return Err(ExecuteError::Unsupported(t)),
         }
 
-        Ok(ret)
+        Ok(true)
     }
 
     pub fn complete_async(&mut self) -> result::Result<(), Error> {
@@ -587,7 +504,7 @@ impl Request {
     }
 }
 
-#[derive(Copy, Clone, Debug, Default, Serialize, Deserialize)]
+#[derive(Copy, Clone, Debug, Default, Versionize)]
 #[repr(C, packed)]
 pub struct VirtioBlockConfig {
     pub capacity: u64,
@@ -610,7 +527,7 @@ pub struct VirtioBlockConfig {
     pub write_zeroes_may_unmap: u8,
     pub unused1: [u8; 3],
 }
-#[derive(Copy, Clone, Debug, Default, Serialize, Deserialize)]
+#[derive(Copy, Clone, Debug, Default, Versionize)]
 #[repr(C, packed)]
 pub struct VirtioBlockGeometry {
     pub cylinders: u16,
@@ -623,70 +540,59 @@ unsafe impl ByteValued for VirtioBlockConfig {}
 // SAFETY: data structure only contain a series of integers
 unsafe impl ByteValued for VirtioBlockGeometry {}
 
-/// Check if aio can be used on the current system.
-pub fn block_aio_is_supported() -> bool {
-    aio::IoContext::new(1).is_ok()
-}
-
 /// Check if io_uring for block device can be used on the current system, as
 /// it correctly supports the expected io_uring features.
 pub fn block_io_uring_is_supported() -> bool {
-    #[cfg(not(feature = "io_uring"))]
-    {
-        info!("io_uring is disabled by crate features");
-        false
+    let error_msg = "io_uring not supported:";
+
+    // Check we can create an io_uring instance, which effectively verifies
+    // that io_uring_setup() syscall is supported.
+    let io_uring = match IoUring::new(1) {
+        Ok(io_uring) => io_uring,
+        Err(e) => {
+            info!("{} failed to create io_uring instance: {}", error_msg, e);
+            return false;
+        }
+    };
+
+    let submitter = io_uring.submitter();
+
+    let mut probe = Probe::new();
+
+    // Check we can register a probe to validate supported operations.
+    match submitter.register_probe(&mut probe) {
+        Ok(_) => {}
+        Err(e) => {
+            info!("{} failed to register a probe: {}", error_msg, e);
+            return false;
+        }
     }
 
-    #[cfg(feature = "io_uring")]
-    {
-        let error_msg = "io_uring not supported:";
-
-        // Check we can create an io_uring instance, which effectively verifies
-        // that io_uring_setup() syscall is supported.
-        let io_uring = match IoUring::new(1) {
-            Ok(io_uring) => io_uring,
-            Err(e) => {
-                info!("{} failed to create io_uring instance: {}", error_msg, e);
-                return false;
-            }
-        };
-
-        let submitter = io_uring.submitter();
-
-        let mut probe = Probe::new();
-
-        // Check we can register a probe to validate supported operations.
-        match submitter.register_probe(&mut probe) {
-            Ok(_) => {}
-            Err(e) => {
-                info!("{} failed to register a probe: {}", error_msg, e);
-                return false;
-            }
-        }
-
-        // Check IORING_OP_FSYNC is supported
-        if !probe.is_supported(opcode::Fsync::CODE) {
-            info!("{} IORING_OP_FSYNC operation not supported", error_msg);
-            return false;
-        }
-
-        // Check IORING_OP_READV is supported
-        if !probe.is_supported(opcode::Readv::CODE) {
-            info!("{} IORING_OP_READV operation not supported", error_msg);
-            return false;
-        }
-
-        // Check IORING_OP_WRITEV is supported
-        if !probe.is_supported(opcode::Writev::CODE) {
-            info!("{} IORING_OP_WRITEV operation not supported", error_msg);
-            return false;
-        }
-
-        true
+    // Check IORING_OP_FSYNC is supported
+    if !probe.is_supported(opcode::Fsync::CODE) {
+        info!("{} IORING_OP_FSYNC operation not supported", error_msg);
+        return false;
     }
+
+    // Check IORING_OP_READV is supported
+    if !probe.is_supported(opcode::Readv::CODE) {
+        info!("{} IORING_OP_READV operation not supported", error_msg);
+        return false;
+    }
+
+    // Check IORING_OP_WRITEV is supported
+    if !probe.is_supported(opcode::Writev::CODE) {
+        info!("{} IORING_OP_WRITEV operation not supported", error_msg);
+        return false;
+    }
+
+    true
 }
 
-pub trait AsyncAdaptor {
+pub trait AsyncAdaptor<F>
+where
+    F: Read + Write + Seek,
+{
     fn read_vectored_sync(
         &mut self,
         offset: libc::off_t,
@@ -694,30 +600,24 @@ pub trait AsyncAdaptor {
         user_data: u64,
         eventfd: &EventFd,
         completion_list: &mut VecDeque<(u64, i32)>,
-    ) -> AsyncIoResult<()>
-    where
-        Self: Read + Seek,
-    {
+    ) -> AsyncIoResult<()> {
         // Convert libc::iovec into IoSliceMut
-        let mut slices: SmallVec<[IoSliceMut; DEFAULT_DESCRIPTOR_VEC_SIZE]> =
-            SmallVec::with_capacity(iovecs.len());
+        let mut slices: SmallVec<[IoSliceMut; 1]> = SmallVec::with_capacity(iovecs.len());
         for iovec in iovecs.iter() {
             // SAFETY: on Linux IoSliceMut wraps around libc::iovec
-            slices.push(IoSliceMut::new(unsafe {
-                std::mem::transmute::<libc::iovec, &mut [u8]>(*iovec)
-            }));
+            slices.push(IoSliceMut::new(unsafe { std::mem::transmute(*iovec) }));
         }
 
         let result = {
+            let mut file = self.file();
+
             // Move the cursor to the right offset
-            self.seek(SeekFrom::Start(offset as u64))
+            file.seek(SeekFrom::Start(offset as u64))
                 .map_err(AsyncIoError::ReadVectored)?;
 
-            let mut r = 0;
-            for b in slices.iter_mut() {
-                r += self.read(b).map_err(AsyncIoError::ReadVectored)?;
-            }
-            r
+            // Read vectored
+            file.read_vectored(slices.as_mut_slice())
+                .map_err(AsyncIoError::ReadVectored)?
         };
 
         completion_list.push_back((user_data, result as i32));
@@ -733,30 +633,24 @@ pub trait AsyncAdaptor {
         user_data: u64,
         eventfd: &EventFd,
         completion_list: &mut VecDeque<(u64, i32)>,
-    ) -> AsyncIoResult<()>
-    where
-        Self: Write + Seek,
-    {
+    ) -> AsyncIoResult<()> {
         // Convert libc::iovec into IoSlice
-        let mut slices: SmallVec<[IoSlice; DEFAULT_DESCRIPTOR_VEC_SIZE]> =
-            SmallVec::with_capacity(iovecs.len());
+        let mut slices: SmallVec<[IoSlice; 1]> = SmallVec::with_capacity(iovecs.len());
         for iovec in iovecs.iter() {
             // SAFETY: on Linux IoSlice wraps around libc::iovec
-            slices.push(IoSlice::new(unsafe {
-                std::mem::transmute::<libc::iovec, &mut [u8]>(*iovec)
-            }));
+            slices.push(IoSlice::new(unsafe { std::mem::transmute(*iovec) }));
         }
 
         let result = {
+            let mut file = self.file();
+
             // Move the cursor to the right offset
-            self.seek(SeekFrom::Start(offset as u64))
+            file.seek(SeekFrom::Start(offset as u64))
                 .map_err(AsyncIoError::WriteVectored)?;
 
-            let mut r = 0;
-            for b in slices.iter() {
-                r += self.write(b).map_err(AsyncIoError::WriteVectored)?;
-            }
-            r
+            // Write vectored
+            file.write_vectored(slices.as_slice())
+                .map_err(AsyncIoError::WriteVectored)?
         };
 
         completion_list.push_back((user_data, result as i32));
@@ -770,13 +664,12 @@ pub trait AsyncAdaptor {
         user_data: Option<u64>,
         eventfd: &EventFd,
         completion_list: &mut VecDeque<(u64, i32)>,
-    ) -> AsyncIoResult<()>
-    where
-        Self: Write,
-    {
+    ) -> AsyncIoResult<()> {
         let result: i32 = {
+            let mut file = self.file();
+
             // Flush
-            self.flush().map_err(AsyncIoError::Fsync)?;
+            file.flush().map_err(AsyncIoError::Fsync)?;
 
             0
         };
@@ -788,6 +681,8 @@ pub trait AsyncAdaptor {
 
         Ok(())
     }
+
+    fn file(&mut self) -> MutexGuard<F>;
 }
 
 pub enum ImageType {
@@ -800,33 +695,24 @@ pub enum ImageType {
 const QCOW_MAGIC: u32 = 0x5146_49fb;
 const VHDX_SIGN: u64 = 0x656C_6966_7864_6876;
 
-/// Read a block into memory aligned by the source block size (needed for O_DIRECT)
-pub fn read_aligned_block_size(f: &mut File) -> std::io::Result<Vec<u8>> {
-    let blocksize = DiskTopology::probe(f)?.logical_block_size as usize;
-    // SAFETY: We are allocating memory that is naturally aligned (size = alignment) and we meet
-    // requirements for safety from Vec::from_raw_parts() as we are using the global allocator
-    // and transferring ownership of the memory.
-    let mut data = unsafe {
-        Vec::from_raw_parts(
-            alloc_zeroed(Layout::from_size_align_unchecked(blocksize, blocksize)),
-            blocksize,
-            blocksize,
-        )
-    };
-    f.read_exact(&mut data)?;
-    Ok(data)
-}
-
 /// Determine image type through file parsing.
 pub fn detect_image_type(f: &mut File) -> std::io::Result<ImageType> {
-    let block = read_aligned_block_size(f)?;
+    // We must create a buffer aligned on 512 bytes with a size being a
+    // multiple of 512 bytes as the file might be opened with O_DIRECT flag.
+    #[repr(align(512))]
+    struct Sector {
+        data: [u8; 512],
+    }
+    let mut s = Sector { data: [0; 512] };
+
+    f.read_exact(&mut s.data)?;
 
     // Check 4 first bytes to get the header value and determine the image type
-    let image_type = if u32::from_be_bytes(block[0..4].try_into().unwrap()) == QCOW_MAGIC {
+    let image_type = if u32::from_be_bytes(s.data[0..4].try_into().unwrap()) == QCOW_MAGIC {
         ImageType::Qcow2
     } else if vhd::is_fixed_vhd(f)? {
         ImageType::FixedVhd
-    } else if u64::from_le_bytes(block[0..8].try_into().unwrap()) == VHDX_SIGN {
+    } else if u64::from_le_bytes(s.data[0..8].try_into().unwrap()) == VHDX_SIGN {
         ImageType::Vhdx
     } else {
         ImageType::Raw
@@ -834,89 +720,3 @@ pub fn detect_image_type(f: &mut File) -> std::io::Result<ImageType> {
 
     Ok(image_type)
 }
-
-pub trait BlockBackend: Read + Write + Seek + Send + Debug {
-    fn size(&self) -> Result<u64, Error>;
-}
-
-#[derive(Debug)]
-pub struct DiskTopology {
-    pub logical_block_size: u64,
-    pub physical_block_size: u64,
-    pub minimum_io_size: u64,
-    pub optimal_io_size: u64,
-}
-
-impl Default for DiskTopology {
-    fn default() -> Self {
-        Self {
-            logical_block_size: 512,
-            physical_block_size: 512,
-            minimum_io_size: 512,
-            optimal_io_size: 0,
-        }
-    }
-}
-
-ioctl_io_nr!(BLKSSZGET, 0x12, 104);
-ioctl_io_nr!(BLKPBSZGET, 0x12, 123);
-ioctl_io_nr!(BLKIOMIN, 0x12, 120);
-ioctl_io_nr!(BLKIOOPT, 0x12, 121);
-
-enum BlockSize {
-    LogicalBlock,
-    PhysicalBlock,
-    MinimumIo,
-    OptimalIo,
-}
-
-impl DiskTopology {
-    fn is_block_device(f: &File) -> std::io::Result<bool> {
-        let mut stat = std::mem::MaybeUninit::<libc::stat>::uninit();
-        // SAFETY: FFI call with a valid fd and buffer
-        let ret = unsafe { libc::fstat(f.as_raw_fd(), stat.as_mut_ptr()) };
-        if ret != 0 {
-            return Err(std::io::Error::last_os_error());
-        }
-
-        // SAFETY: stat is valid at this point
-        let is_block = unsafe { (*stat.as_ptr()).st_mode & S_IFMT == S_IFBLK };
-        Ok(is_block)
-    }
-
-    // libc::ioctl() takes different types on different architectures
-    fn query_block_size(f: &File, block_size_type: BlockSize) -> std::io::Result<u64> {
-        let mut block_size = 0;
-        // SAFETY: FFI call with correct arguments
-        let ret = unsafe {
-            ioctl(
-                f.as_raw_fd(),
-                match block_size_type {
-                    BlockSize::LogicalBlock => BLKSSZGET(),
-                    BlockSize::PhysicalBlock => BLKPBSZGET(),
-                    BlockSize::MinimumIo => BLKIOMIN(),
-                    BlockSize::OptimalIo => BLKIOOPT(),
-                } as _,
-                &mut block_size,
-            )
-        };
-        if ret != 0 {
-            return Err(std::io::Error::last_os_error());
-        };
-
-        Ok(block_size)
-    }
-
-    pub fn probe(f: &File) -> std::io::Result<Self> {
-        if !Self::is_block_device(f)? {
-            return Ok(DiskTopology::default());
-        }
-
-        Ok(DiskTopology {
-            logical_block_size: Self::query_block_size(f, BlockSize::LogicalBlock)?,
-            physical_block_size: Self::query_block_size(f, BlockSize::PhysicalBlock)?,
-            minimum_io_size: Self::query_block_size(f, BlockSize::MinimumIo)?,
-            optimal_io_size: Self::query_block_size(f, BlockSize::OptimalIo)?,
-        })
-    }
-}

block_util/src/qcow_sync.rs

@@ -2,55 +2,47 @@
 //
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
+use crate::async_io::{AsyncIo, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult};
+use crate::AsyncAdaptor;
+use qcow::{QcowFile, RawFile, Result as QcowResult};
 use std::collections::VecDeque;
 use std::fs::File;
 use std::io::{Seek, SeekFrom};
-use std::os::fd::AsRawFd;
-
+use std::sync::{Arc, Mutex, MutexGuard};
 use vmm_sys_util::eventfd::EventFd;
 
-use crate::AsyncAdaptor;
-use crate::async_io::{
-    AsyncIo, AsyncIoResult, BorrowedDiskFd, DiskFile, DiskFileError, DiskFileResult,
-};
-use crate::qcow::{QcowFile, RawFile, Result as QcowResult};
-
 pub struct QcowDiskSync {
-    qcow_file: QcowFile,
+    qcow_file: Arc<Mutex<QcowFile>>,
 }
 
 impl QcowDiskSync {
     pub fn new(file: File, direct_io: bool) -> QcowResult<Self> {
         Ok(QcowDiskSync {
-            qcow_file: QcowFile::from(RawFile::new(file, direct_io))?,
+            qcow_file: Arc::new(Mutex::new(QcowFile::from(RawFile::new(file, direct_io))?)),
         })
     }
 }
 
 impl DiskFile for QcowDiskSync {
     fn size(&mut self) -> DiskFileResult<u64> {
-        self.qcow_file
-            .seek(SeekFrom::End(0))
-            .map_err(DiskFileError::Size)
+        let mut file = self.qcow_file.lock().unwrap();
+
+        file.seek(SeekFrom::End(0)).map_err(DiskFileError::Size)
     }
 
     fn new_async_io(&self, _ring_depth: u32) -> DiskFileResult<Box<dyn AsyncIo>> {
         Ok(Box::new(QcowSync::new(self.qcow_file.clone())) as Box<dyn AsyncIo>)
     }
-
-    fn fd(&mut self) -> BorrowedDiskFd<'_> {
-        BorrowedDiskFd::new(self.qcow_file.as_raw_fd())
-    }
 }
 
 pub struct QcowSync {
-    qcow_file: QcowFile,
+    qcow_file: Arc<Mutex<QcowFile>>,
     eventfd: EventFd,
     completion_list: VecDeque<(u64, i32)>,
 }
 
 impl QcowSync {
-    pub fn new(qcow_file: QcowFile) -> Self {
+    pub fn new(qcow_file: Arc<Mutex<QcowFile>>) -> Self {
         QcowSync {
             qcow_file,
             eventfd: EventFd::new(libc::EFD_NONBLOCK)
@@ -60,7 +52,11 @@ impl QcowSync {
     }
 }
 
-impl AsyncAdaptor for QcowFile {}
+impl AsyncAdaptor<QcowFile> for Arc<Mutex<QcowFile>> {
+    fn file(&mut self) -> MutexGuard<QcowFile> {
+        self.lock().unwrap()
+    }
+}
 
 impl AsyncIo for QcowSync {
     fn notifier(&self) -> &EventFd {

block_util/src/raw_async.rs

@@ -2,17 +2,14 @@
 //
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
-use std::fs::File;
-use std::io::{Error, Seek, SeekFrom};
-use std::os::unix::io::{AsRawFd, RawFd};
-
-use io_uring::{IoUring, opcode, types};
-use vmm_sys_util::eventfd::EventFd;
-
 use crate::async_io::{
-    AsyncIo, AsyncIoError, AsyncIoResult, BorrowedDiskFd, DiskFile, DiskFileError, DiskFileResult,
+    AsyncIo, AsyncIoError, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult, DiskTopology,
 };
-use crate::{BatchRequest, DiskTopology, RequestType};
+use io_uring::{opcode, squeue, types, IoUring};
+use std::fs::File;
+use std::io::{Seek, SeekFrom};
+use std::os::unix::io::{AsRawFd, RawFd};
+use vmm_sys_util::eventfd::EventFd;
 
 pub struct RawFileDisk {
     file: File,
@@ -39,17 +36,13 @@ impl DiskFile for RawFileDisk {
     }
 
     fn topology(&mut self) -> DiskTopology {
-        if let Ok(topology) = DiskTopology::probe(&self.file) {
+        if let Ok(topology) = DiskTopology::probe(&mut self.file) {
             topology
         } else {
             warn!("Unable to get device topology. Using default topology");
             DiskTopology::default()
         }
     }
-
-    fn fd(&mut self) -> BorrowedDiskFd<'_> {
-        BorrowedDiskFd::new(self.file.as_raw_fd())
-    }
 }
 
 pub struct RawFileAsync {
@@ -90,14 +83,14 @@ impl AsyncIo for RawFileAsync {
 
         // SAFETY: we know the file descriptor is valid and we
         // relied on vm-memory to provide the buffer address.
-        unsafe {
+        let _ = unsafe {
             sq.push(
                 &opcode::Readv::new(types::Fd(self.fd), iovecs.as_ptr(), iovecs.len() as u32)
-                    .offset(offset.try_into().unwrap())
+                    .offset(offset)
                     .build()
+                    .flags(squeue::Flags::ASYNC)
                     .user_data(user_data),
             )
-            .map_err(|_| AsyncIoError::ReadVectored(Error::other("Submission queue is full")))?
         };
 
         // Update the submission queue and submit new operations to the
@@ -118,14 +111,14 @@ impl AsyncIo for RawFileAsync {
 
         // SAFETY: we know the file descriptor is valid and we
         // relied on vm-memory to provide the buffer address.
-        unsafe {
+        let _ = unsafe {
             sq.push(
                 &opcode::Writev::new(types::Fd(self.fd), iovecs.as_ptr(), iovecs.len() as u32)
-                    .offset(offset.try_into().unwrap())
+                    .offset(offset)
                     .build()
+                    .flags(squeue::Flags::ASYNC)
                     .user_data(user_data),
             )
-            .map_err(|_| AsyncIoError::WriteVectored(Error::other("Submission queue is full")))?
         };
 
         // Update the submission queue and submit new operations to the
@@ -141,13 +134,13 @@ impl AsyncIo for RawFileAsync {
             let (submitter, mut sq, _) = self.io_uring.split();
 
             // SAFETY: we know the file descriptor is valid.
-            unsafe {
+            let _ = unsafe {
                 sq.push(
                     &opcode::Fsync::new(types::Fd(self.fd))
                         .build()
+                        .flags(squeue::Flags::ASYNC)
                         .user_data(user_data),
                 )
-                .map_err(|_| AsyncIoError::Fsync(Error::other("Submission queue is full")))?
             };
 
             // Update the submission queue and submit new operations to the
@@ -168,77 +161,4 @@ impl AsyncIo for RawFileAsync {
             .next()
             .map(|entry| (entry.user_data(), entry.result()))
     }
-
-    fn batch_requests_enabled(&self) -> bool {
-        true
-    }
-
-    fn submit_batch_requests(&mut self, batch_request: &[BatchRequest]) -> AsyncIoResult<()> {
-        if !self.batch_requests_enabled() {
-            return Ok(());
-        }
-
-        let (submitter, mut sq, _) = self.io_uring.split();
-        let mut submitted = false;
-
-        for req in batch_request {
-            match req.request_type {
-                RequestType::In => {
-                    // SAFETY: we know the file descriptor is valid and we
-                    // relied on vm-memory to provide the buffer address.
-                    unsafe {
-                        sq.push(
-                            &opcode::Readv::new(
-                                types::Fd(self.fd),
-                                req.iovecs.as_ptr(),
-                                req.iovecs.len() as u32,
-                            )
-                            .offset(req.offset as u64)
-                            .build()
-                            .user_data(req.user_data),
-                        )
-                        .map_err(|_| {
-                            AsyncIoError::ReadVectored(Error::other("Submission queue is full"))
-                        })?
-                    };
-                    submitted = true;
-                }
-                RequestType::Out => {
-                    // SAFETY: we know the file descriptor is valid and we
-                    // relied on vm-memory to provide the buffer address.
-                    unsafe {
-                        sq.push(
-                            &opcode::Writev::new(
-                                types::Fd(self.fd),
-                                req.iovecs.as_ptr(),
-                                req.iovecs.len() as u32,
-                            )
-                            .offset(req.offset as u64)
-                            .build()
-                            .user_data(req.user_data),
-                        )
-                        .map_err(|_| {
-                            AsyncIoError::WriteVectored(Error::other("Submission queue is full"))
-                        })?
-                    };
-                    submitted = true;
-                }
-                _ => {
-                    unreachable!("Unexpected batch request type: {:?}", req.request_type)
-                }
-            }
-        }
-
-        // Only submit if we actually queued something
-        if submitted {
-            // Update the submission queue and submit new operations to the
-            // io_uring instance.
-            sq.sync();
-            submitter
-                .submit()
-                .map_err(AsyncIoError::SubmitBatchRequests)?;
-        }
-
-        Ok(())
-    }
 }

block_util/src/raw_sync.rs

@@ -2,18 +2,15 @@
 //
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
+use crate::async_io::{
+    AsyncIo, AsyncIoError, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult, DiskTopology,
+};
 use std::collections::VecDeque;
 use std::fs::File;
 use std::io::{Seek, SeekFrom};
 use std::os::unix::io::{AsRawFd, RawFd};
-
 use vmm_sys_util::eventfd::EventFd;
 
-use crate::DiskTopology;
-use crate::async_io::{
-    AsyncIo, AsyncIoError, AsyncIoResult, BorrowedDiskFd, DiskFile, DiskFileError, DiskFileResult,
-};
-
 pub struct RawFileDiskSync {
     file: File,
 }
@@ -36,17 +33,13 @@ impl DiskFile for RawFileDiskSync {
     }
 
     fn topology(&mut self) -> DiskTopology {
-        if let Ok(topology) = DiskTopology::probe(&self.file) {
+        if let Ok(topology) = DiskTopology::probe(&mut self.file) {
             topology
         } else {
             warn!("Unable to get device topology. Using default topology");
             DiskTopology::default()
         }
     }
-
-    fn fd(&mut self) -> BorrowedDiskFd<'_> {
-        BorrowedDiskFd::new(self.file.as_raw_fd())
-    }
 }
 
 pub struct RawFileSync {
@@ -80,7 +73,7 @@ impl AsyncIo for RawFileSync {
         let result = unsafe {
             libc::preadv(
                 self.fd as libc::c_int,
-                iovecs.as_ptr(),
+                iovecs.as_ptr() as *const libc::iovec,
                 iovecs.len() as libc::c_int,
                 offset,
             )
@@ -105,7 +98,7 @@ impl AsyncIo for RawFileSync {
         let result = unsafe {
             libc::pwritev(
                 self.fd as libc::c_int,
-                iovecs.as_ptr(),
+                iovecs.as_ptr() as *const libc::iovec,
                 iovecs.len() as libc::c_int,
                 offset,
             )

block_util/src/vhd.rs

@@ -2,10 +2,9 @@
 //
 // SPDX-License-Identifier: Apache-2.0
 
+use std::convert::TryInto;
 use std::fs::File;
-use std::io::{Seek, SeekFrom};
-
-use crate::{DiskTopology, read_aligned_block_size};
+use std::io::{Read, Seek, SeekFrom};
 
 #[derive(Clone, Copy)]
 pub struct VhdFooter {
@@ -28,33 +27,37 @@ pub struct VhdFooter {
 
 impl VhdFooter {
     pub fn new(file: &mut File) -> std::io::Result<VhdFooter> {
-        let blocksize = DiskTopology::probe(file)?.logical_block_size as usize;
+        // We must create a buffer aligned on 512 bytes with a size being a
+        // multiple of 512 bytes as the file might be opened with O_DIRECT flag.
+        #[repr(align(512))]
+        struct Sector {
+            data: [u8; 512],
+        }
+        let mut s = Sector { data: [0; 512] };
 
-        // Place the cursor in the last block of the file
-        file.seek(SeekFrom::End(0 - (blocksize as i64)))?;
-        // Read in the last block
-        let data = read_aligned_block_size(file)?;
+        // Place the cursor 512 bytes before the end of the file, as this is
+        // where the footer starts.
+        file.seek(SeekFrom::End(-512))?;
 
-        // We only care about the last sector
-        let offset = blocksize - 512;
-        let sector = &data[offset..];
+        // Fill in the VhdFooter structure
+        file.read_exact(&mut s.data)?;
 
         Ok(VhdFooter {
-            cookie: u64::from_be_bytes(sector[0..8].try_into().unwrap()),
-            features: u32::from_be_bytes(sector[8..12].try_into().unwrap()),
-            file_format_version: u32::from_be_bytes(sector[12..16].try_into().unwrap()),
-            data_offset: u64::from_be_bytes(sector[16..24].try_into().unwrap()),
-            time_stamp: u32::from_be_bytes(sector[24..28].try_into().unwrap()),
-            creator_application: u32::from_be_bytes(sector[28..32].try_into().unwrap()),
-            creator_version: u32::from_be_bytes(sector[32..36].try_into().unwrap()),
-            creator_host_os: u32::from_be_bytes(sector[36..40].try_into().unwrap()),
-            original_size: u64::from_be_bytes(sector[40..48].try_into().unwrap()),
-            current_size: u64::from_be_bytes(sector[48..56].try_into().unwrap()),
-            disk_geometry: u32::from_be_bytes(sector[56..60].try_into().unwrap()),
-            disk_type: u32::from_be_bytes(sector[60..64].try_into().unwrap()),
-            checksum: u32::from_be_bytes(sector[64..68].try_into().unwrap()),
-            unique_id: u128::from_be_bytes(sector[68..84].try_into().unwrap()),
-            saved_state: u8::from_be_bytes(sector[84..85].try_into().unwrap()),
+            cookie: u64::from_be_bytes(s.data[0..8].try_into().unwrap()),
+            features: u32::from_be_bytes(s.data[8..12].try_into().unwrap()),
+            file_format_version: u32::from_be_bytes(s.data[12..16].try_into().unwrap()),
+            data_offset: u64::from_be_bytes(s.data[16..24].try_into().unwrap()),
+            time_stamp: u32::from_be_bytes(s.data[24..28].try_into().unwrap()),
+            creator_application: u32::from_be_bytes(s.data[28..32].try_into().unwrap()),
+            creator_version: u32::from_be_bytes(s.data[32..36].try_into().unwrap()),
+            creator_host_os: u32::from_be_bytes(s.data[36..40].try_into().unwrap()),
+            original_size: u64::from_be_bytes(s.data[40..48].try_into().unwrap()),
+            current_size: u64::from_be_bytes(s.data[48..56].try_into().unwrap()),
+            disk_geometry: u32::from_be_bytes(s.data[56..60].try_into().unwrap()),
+            disk_type: u32::from_be_bytes(s.data[60..64].try_into().unwrap()),
+            checksum: u32::from_be_bytes(s.data[64..68].try_into().unwrap()),
+            unique_id: u128::from_be_bytes(s.data[68..84].try_into().unwrap()),
+            saved_state: u8::from_be_bytes(s.data[84..85].try_into().unwrap()),
         })
     }
 
@@ -118,13 +121,11 @@ pub fn is_fixed_vhd(f: &mut File) -> std::io::Result<bool> {
 
 #[cfg(test)]
 mod tests {
+    use super::{is_fixed_vhd, VhdFooter};
     use std::fs::File;
     use std::io::{Seek, SeekFrom, Write};
-
     use vmm_sys_util::tempfile::TempFile;
 
-    use super::{VhdFooter, is_fixed_vhd};
-
     fn valid_fixed_vhd_footer() -> Vec<u8> {
         vec![
             0x63, 0x6f, 0x6e, 0x65, 0x63, 0x74, 0x69, 0x78, // cookie

block_util/src/vhdx_sync.rs

@@ -2,33 +2,29 @@
 //
 // SPDX-License-Identifier: Apache-2.0
 
+use crate::async_io::{AsyncIo, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult};
+use crate::AsyncAdaptor;
 use std::collections::VecDeque;
 use std::fs::File;
-use std::os::fd::AsRawFd;
-
+use std::sync::{Arc, Mutex, MutexGuard};
+use vhdx::vhdx::{Result as VhdxResult, Vhdx};
 use vmm_sys_util::eventfd::EventFd;
 
-use crate::AsyncAdaptor;
-use crate::async_io::{
-    AsyncIo, AsyncIoResult, BorrowedDiskFd, DiskFile, DiskFileError, DiskFileResult,
-};
-use crate::vhdx::{Result as VhdxResult, Vhdx};
-
 pub struct VhdxDiskSync {
-    vhdx_file: Vhdx,
+    vhdx_file: Arc<Mutex<Vhdx>>,
 }
 
 impl VhdxDiskSync {
     pub fn new(f: File) -> VhdxResult<Self> {
         Ok(VhdxDiskSync {
-            vhdx_file: Vhdx::new(f)?,
+            vhdx_file: Arc::new(Mutex::new(Vhdx::new(f)?)),
         })
     }
 }
 
 impl DiskFile for VhdxDiskSync {
     fn size(&mut self) -> DiskFileResult<u64> {
-        Ok(self.vhdx_file.virtual_disk_size())
+        Ok(self.vhdx_file.lock().unwrap().virtual_disk_size())
     }
 
     fn new_async_io(&self, _ring_depth: u32) -> DiskFileResult<Box<dyn AsyncIo>> {
@@ -37,20 +33,16 @@ impl DiskFile for VhdxDiskSync {
                 as Box<dyn AsyncIo>,
         )
     }
-
-    fn fd(&mut self) -> BorrowedDiskFd<'_> {
-        BorrowedDiskFd::new(self.vhdx_file.as_raw_fd())
-    }
 }
 
 pub struct VhdxSync {
-    vhdx_file: Vhdx,
+    vhdx_file: Arc<Mutex<Vhdx>>,
     eventfd: EventFd,
     completion_list: VecDeque<(u64, i32)>,
 }
 
 impl VhdxSync {
-    pub fn new(vhdx_file: Vhdx) -> std::io::Result<Self> {
+    pub fn new(vhdx_file: Arc<Mutex<Vhdx>>) -> std::io::Result<Self> {
         Ok(VhdxSync {
             vhdx_file,
             eventfd: EventFd::new(libc::EFD_NONBLOCK)?,
@@ -59,7 +51,11 @@ impl VhdxSync {
     }
 }
 
-impl AsyncAdaptor for Vhdx {}
+impl AsyncAdaptor<Vhdx> for Arc<Mutex<Vhdx>> {
+    fn file(&mut self) -> MutexGuard<Vhdx> {
+        self.lock().unwrap()
+    }
+}
 
 impl AsyncIo for VhdxSync {
     fn notifier(&self) -> &EventFd {

build.rs

@@ -3,30 +3,22 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
-use std::env;
 use std::process::Command;
 
 fn main() {
     let mut version = "v".to_owned() + env!("CARGO_PKG_VERSION");
 
-    if let Ok(git_out) = Command::new("git").args(["describe", "--dirty"]).output()
-        && git_out.status.success()
-        && let Ok(git_out_str) = String::from_utf8(git_out.stdout)
-    {
-        version = git_out_str;
-        // Pop the trailing newline.
-        version.pop();
-    }
-
-    // Append CH_EXTRA_VERSION to version if it is set.
-    if let Ok(extra_version) = env::var("CH_EXTRA_VERSION") {
-        println!("cargo:rerun-if-env-changed=CH_EXTRA_VERSION");
-        version.push_str(&format!("-{extra_version}"));
+    if let Ok(git_out) = Command::new("git").args(["describe", "--dirty"]).output() {
+        if git_out.status.success() {
+            if let Ok(git_out_str) = String::from_utf8(git_out.stdout) {
+                version = git_out_str;
+            }
+        }
     }
 
     // This println!() has a special behavior, as it will set the environment
-    // variable BUILD_VERSION, so that it can be reused from the binary.
+    // variable BUILT_VERSION, so that it can be reused from the binary.
     // Particularly, this is used from src/main.rs to display the exact
     // version.
-    println!("cargo:rustc-env=BUILD_VERSION={version}");
+    println!("cargo:rustc-env=BUILT_VERSION={version}");
 }

devices/Cargo.toml

@@ -1,50 +1,29 @@
 [package]
-authors = ["The Chromium OS Authors"]
-edition.workspace = true
 name = "devices"
 version = "0.1.0"
+authors = ["The Chromium OS Authors"]
+edition = "2021"
 
 [dependencies]
-acpi_tables = { workspace = true }
-anyhow = { workspace = true }
+acpi_tables = { git = "https://github.com/rust-vmm/acpi_tables", branch = "main"  }
+anyhow = "1.0.69"
 arch = { path = "../arch" }
-bitfield-struct = { version = "0.10.1", optional = true }
-bitflags = { workspace = true }
-byteorder = { workspace = true }
-event_monitor = { path = "../event_monitor" }
+bitflags = "1.3.2"
+byteorder = "1.4.3"
 hypervisor = { path = "../hypervisor" }
-libc = { workspace = true }
-linux-loader = { workspace = true, features = [
-  "bzimage",
-  "elf",
-  "pe",
-], optional = true }
-log = { workspace = true }
-num_enum = "0.7.2"
-pci = { path = "../pci" }
-serde = { workspace = true, features = ["derive"] }
-thiserror = { workspace = true }
+libc = "0.2.139"
+log = "0.4.17"
+thiserror = "1.0.39"
 tpm = { path = "../tpm" }
-vm-allocator = { path = "../vm-allocator" }
+versionize = "0.1.10"
+versionize_derive = "0.1.4"
 vm-device = { path = "../vm-device" }
-vm-memory = { workspace = true, features = [
-  "backend-atomic",
-  "backend-bitmap",
-  "backend-mmap",
-] }
+vm-memory = "0.10.0"
 vm-migration = { path = "../vm-migration" }
-vmm-sys-util = { workspace = true }
-zerocopy = { version = "0.8.26", features = [
-  "alloc",
-  "derive",
-], optional = true }
+vmm-sys-util = "0.11.0"
 
-[target.'cfg(any(target_arch = "aarch64", target_arch = "riscv64"))'.dependencies]
+[target.'cfg(target_arch = "aarch64")'.dependencies]
 arch = { path = "../arch" }
 
 [features]
 default = []
-fw_cfg = ["arch/fw_cfg", "bitfield-struct", "linux-loader", "zerocopy"]
-ivshmem = []
-kvm = ["arch/kvm"]
-pvmemcontrol = []

devices/src/acpi.rs

@@ -3,39 +3,29 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
-use std::sync::atomic::{AtomicBool, Ordering};
+use super::AcpiNotificationFlags;
+use acpi_tables::{aml, Aml, AmlSink};
 use std::sync::{Arc, Barrier};
-use std::thread;
 use std::time::Instant;
-
-use acpi_tables::{Aml, AmlSink, aml};
-use vm_device::BusDevice;
 use vm_device::interrupt::InterruptSourceGroup;
+use vm_device::BusDevice;
 use vm_memory::GuestAddress;
 use vmm_sys_util::eventfd::EventFd;
 
-use super::AcpiNotificationFlags;
-
 pub const GED_DEVICE_ACPI_SIZE: usize = 0x1;
 
 /// A device for handling ACPI shutdown and reboot
 pub struct AcpiShutdownDevice {
     exit_evt: EventFd,
     reset_evt: EventFd,
-    vcpus_kill_signalled: Arc<AtomicBool>,
 }
 
 impl AcpiShutdownDevice {
     /// Constructs a device that will signal the given event when the guest requests it.
-    pub fn new(
-        exit_evt: EventFd,
-        reset_evt: EventFd,
-        vcpus_kill_signalled: Arc<AtomicBool>,
-    ) -> AcpiShutdownDevice {
+    pub fn new(exit_evt: EventFd, reset_evt: EventFd) -> AcpiShutdownDevice {
         AcpiShutdownDevice {
             exit_evt,
             reset_evt,
-            vcpus_kill_signalled,
         }
     }
 }
@@ -53,13 +43,6 @@ impl BusDevice for AcpiShutdownDevice {
             if let Err(e) = self.reset_evt.write(1) {
                 error!("Error triggering ACPI reset event: {}", e);
             }
-            // Spin until we are sure the reset_evt has been handled and that when
-            // we return from the KVM_RUN we will exit rather than re-enter the guest.
-            while !self.vcpus_kill_signalled.load(Ordering::SeqCst) {
-                // This is more effective than thread::yield_now() at
-                // avoiding a priority inversion with the VMM thread
-                thread::sleep(std::time::Duration::from_millis(1));
-            }
         }
         // The ACPI DSDT table specifies the S5 sleep state (shutdown) as value 5
         const S5_SLEEP_VALUE: u8 = 5;
@@ -70,13 +53,6 @@ impl BusDevice for AcpiShutdownDevice {
             if let Err(e) = self.exit_evt.write(1) {
                 error!("Error triggering ACPI shutdown event: {}", e);
             }
-            // Spin until we are sure the reset_evt has been handled and that when
-            // we return from the KVM_RUN we will exit rather than re-enter the guest.
-            while !self.vcpus_kill_signalled.load(Ordering::SeqCst) {
-                // This is more effective than thread::yield_now() at
-                // avoiding a priority inversion with the VMM thread
-                thread::sleep(std::time::Duration::from_millis(1));
-            }
         }
         None
     }
@@ -136,11 +112,10 @@ impl Aml for AcpiGedDevice {
                 &aml::Name::new(
                     "_CRS".into(),
                     &aml::ResourceTemplate::new(vec![&aml::AddressSpace::new_memory(
-                        aml::AddressSpaceCacheable::NotCacheable,
+                        aml::AddressSpaceCachable::NotCacheable,
                         true,
                         self.address.0,
                         self.address.0 + GED_DEVICE_ACPI_SIZE as u64 - 1,
-                        None,
                     )]),
                 ),
                 &aml::OpRegion::new(

devices/src/aia.rs

@@ -1,144 +0,0 @@
-// Copyright © 2024 Institute of Software, CAS. All rights reserved.
-// Copyright 2020, ARM Limited.
-//
-// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
-
-use super::interrupt_controller::{Error, InterruptController};
-extern crate arch;
-use std::result;
-use std::sync::{Arc, Mutex};
-
-use arch::layout;
-use hypervisor::arch::riscv64::aia::{Vaia, VaiaConfig};
-use hypervisor::{AiaState, CpuState};
-use vm_device::interrupt::{
-    InterruptIndex, InterruptManager, InterruptSourceConfig, InterruptSourceGroup,
-    LegacyIrqSourceConfig, MsiIrqGroupConfig,
-};
-use vm_memory::address::Address;
-use vm_migration::{Migratable, Pausable, Snapshottable, Transportable};
-use vmm_sys_util::eventfd::EventFd;
-
-type Result<T> = result::Result<T, Error>;
-
-// Reserve 32 IRQs for legacy devices.
-pub const IRQ_LEGACY_BASE: usize = layout::IRQ_BASE as usize;
-pub const IRQ_LEGACY_COUNT: usize = 32;
-// TODO: AIA snapshotting is not yet completed.
-pub const _AIA_SNAPSHOT_ID: &str = "";
-
-// Aia (Advance Interrupt Architecture) struct provides all the functionality of a
-// AIA device. It wraps a hypervisor-emulated AIA device (Vaia) provided by the
-// `hypervisor` crate.
-// Aia struct also implements InterruptController to provide interrupt delivery
-// service.
-pub struct Aia {
-    interrupt_source_group: Arc<dyn InterruptSourceGroup>,
-    // The hypervisor agnostic virtual AIA
-    vaia: Arc<Mutex<dyn Vaia>>,
-}
-
-impl Aia {
-    pub fn new(
-        vcpu_count: u32,
-        interrupt_manager: Arc<dyn InterruptManager<GroupConfig = MsiIrqGroupConfig>>,
-        vm: Arc<dyn hypervisor::Vm>,
-    ) -> Result<Aia> {
-        let interrupt_source_group = interrupt_manager
-            .create_group(MsiIrqGroupConfig {
-                base: IRQ_LEGACY_BASE as InterruptIndex,
-                count: IRQ_LEGACY_COUNT as InterruptIndex,
-            })
-            .map_err(Error::CreateInterruptSourceGroup)?;
-
-        let vaia = vm
-            .create_vaia(Aia::create_default_config(vcpu_count as u64))
-            .map_err(Error::CreateAia)?;
-
-        let aia = Aia {
-            interrupt_source_group,
-            vaia,
-        };
-        aia.enable()?;
-
-        Ok(aia)
-    }
-
-    pub fn restore_vaia(
-        &mut self,
-        state: Option<AiaState>,
-        _saved_vcpu_states: &[CpuState],
-    ) -> Result<()> {
-        self.vaia
-            .clone()
-            .lock()
-            .unwrap()
-            .set_state(&state.unwrap())
-            .map_err(Error::RestoreAia)
-    }
-
-    fn enable(&self) -> Result<()> {
-        // Set irqfd for legacy interrupts
-        self.interrupt_source_group
-            .enable()
-            .map_err(Error::EnableInterrupt)?;
-
-        // Set irq_routing for legacy interrupts.
-        //   irqchip: Hardcode to 0 as we support only 1 APLIC
-        //   pin: Use irq number as pin
-        for i in IRQ_LEGACY_BASE..(IRQ_LEGACY_BASE + IRQ_LEGACY_COUNT) {
-            let config = LegacyIrqSourceConfig {
-                irqchip: 0,
-                pin: (i - IRQ_LEGACY_BASE) as u32,
-            };
-            self.interrupt_source_group
-                .update(
-                    i as InterruptIndex,
-                    InterruptSourceConfig::LegacyIrq(config),
-                    false,
-                    false,
-                )
-                .map_err(Error::EnableInterrupt)?;
-        }
-
-        self.interrupt_source_group
-            .set_gsi()
-            .map_err(Error::EnableInterrupt)?;
-        Ok(())
-    }
-
-    /// Default config implied by arch::layout
-    pub fn create_default_config(vcpu_count: u64) -> VaiaConfig {
-        VaiaConfig {
-            vcpu_count: vcpu_count as u32,
-            aplic_addr: layout::APLIC_START.raw_value(),
-            imsic_addr: layout::IMSIC_START.raw_value(),
-            nr_irqs: layout::IRQ_NUM,
-        }
-    }
-
-    pub fn get_vaia(&mut self) -> Result<Arc<Mutex<dyn Vaia>>> {
-        Ok(self.vaia.clone())
-    }
-}
-
-impl InterruptController for Aia {
-    // This should be called anytime an interrupt needs to be injected into the
-    // running guest.
-    fn service_irq(&mut self, irq: usize) -> Result<()> {
-        self.interrupt_source_group
-            .trigger(irq as InterruptIndex)
-            .map_err(Error::TriggerInterrupt)?;
-
-        Ok(())
-    }
-
-    fn notifier(&self, irq: usize) -> Option<EventFd> {
-        self.interrupt_source_group.notifier(irq as InterruptIndex)
-    }
-}
-
-impl Snapshottable for Aia {}
-impl Pausable for Aia {}
-impl Transportable for Aia {}
-impl Migratable for Aia {}

devices/src/debug_console.rs

@@ -1,65 +0,0 @@
-// Copyright © 2023 Cyberus Technology
-//
-// SPDX-License-Identifier: Apache-2.0
-//
-
-//! Module for [`DebugconState`].
-
-use std::io;
-use std::io::Write;
-use std::sync::{Arc, Barrier};
-
-use vm_device::BusDevice;
-use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
-
-/// I/O-port.
-pub const DEFAULT_PORT: u64 = 0xe9;
-
-#[derive(Default)]
-pub struct DebugconState {}
-
-/// Emulates a debug console similar to the QEMU debugcon device. This device
-/// is stateless and only prints the bytes (usually text) that are written to
-/// it.
-///
-/// This device is only available on x86.
-///
-/// Reference:
-/// - https://github.com/qemu/qemu/blob/master/hw/char/debugcon.c
-/// - https://phip1611.de/blog/how-to-use-qemus-debugcon-feature-and-write-to-a-file/
-pub struct DebugConsole {
-    id: String,
-    out: Box<dyn io::Write + Send>,
-}
-
-impl DebugConsole {
-    pub fn new(id: String, out: Box<dyn io::Write + Send>) -> Self {
-        Self { id, out }
-    }
-}
-
-impl BusDevice for DebugConsole {
-    fn read(&mut self, _base: u64, _offset: u64, _data: &mut [u8]) {}
-
-    fn write(&mut self, _base: u64, _offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
-        if let Err(e) = self.out.write_all(data) {
-            // unlikely
-            error!("debug-console: failed writing data: {e:?}");
-        }
-        None
-    }
-}
-
-impl Snapshottable for DebugConsole {
-    fn id(&self) -> String {
-        self.id.clone()
-    }
-
-    fn snapshot(&mut self) -> Result<Snapshot, MigratableError> {
-        Snapshot::new_from_state(&())
-    }
-}
-
-impl Pausable for DebugConsole {}
-impl Transportable for DebugConsole {}
-impl Migratable for DebugConsole {}

devices/src/gic.rs

@@ -4,13 +4,14 @@
 
 use super::interrupt_controller::{Error, InterruptController};
 extern crate arch;
-use std::result;
-use std::sync::{Arc, Mutex};
-
 use anyhow::anyhow;
 use arch::layout;
-use hypervisor::CpuState;
-use hypervisor::arch::aarch64::gic::{GicState, Vgic, VgicConfig};
+use hypervisor::{
+    arch::aarch64::gic::{Vgic, VgicConfig},
+    CpuState, GicState,
+};
+use std::result;
+use std::sync::{Arc, Mutex};
 use vm_device::interrupt::{
     InterruptIndex, InterruptManager, InterruptSourceConfig, InterruptSourceGroup,
     LegacyIrqSourceConfig, MsiIrqGroupConfig,
@@ -26,7 +27,7 @@ pub const IRQ_LEGACY_BASE: usize = layout::IRQ_BASE as usize;
 pub const IRQ_LEGACY_COUNT: usize = 32;
 pub const GIC_SNAPSHOT_ID: &str = "gic-v3-its";
 
-// Gic (Generic Interrupt Controller) struct provides all the functionality of a
+// Gic (Generic Interupt Controller) struct provides all the functionality of a
 // GIC device. It wraps a hypervisor-emulated GIC device (Vgic) provided by the
 // `hypervisor` crate.
 // Gic struct also implements InterruptController to provide interrupt delivery
@@ -39,7 +40,7 @@ pub struct Gic {
 
 impl Gic {
     pub fn new(
-        vcpu_count: u32,
+        vcpu_count: u8,
         interrupt_manager: Arc<dyn InterruptManager<GroupConfig = MsiIrqGroupConfig>>,
         vm: Arc<dyn hypervisor::Vm>,
     ) -> Result<Gic> {
@@ -97,14 +98,9 @@ impl Gic {
                     i as InterruptIndex,
                     InterruptSourceConfig::LegacyIrq(config),
                     false,
-                    false,
                 )
                 .map_err(Error::EnableInterrupt)?;
         }
-
-        self.interrupt_source_group
-            .set_gsi()
-            .map_err(Error::EnableInterrupt)?;
         Ok(())
     }
 

devices/src/interrupt_controller.rs

@@ -1,55 +1,35 @@
-// Copyright © 2024 Institute of Software, CAS. All rights reserved.
 // Copyright 2020, ARM Limited.
 //
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
-use std::{io, result};
-
-use thiserror::Error;
+use std::io;
+use std::result;
 use vmm_sys_util::eventfd::EventFd;
 
-#[derive(Debug, Error)]
+#[derive(Debug)]
 pub enum Error {
     /// Invalid trigger mode.
-    #[error("Invalid trigger mode")]
     InvalidTriggerMode,
     /// Invalid delivery mode.
-    #[error("Invalid delivery mode")]
     InvalidDeliveryMode,
     /// Failed creating the interrupt source group.
-    #[error("Failed creating the interrupt source group")]
-    CreateInterruptSourceGroup(#[source] io::Error),
+    CreateInterruptSourceGroup(io::Error),
     /// Failed triggering the interrupt.
-    #[error("Failed triggering the interrupt")]
-    TriggerInterrupt(#[source] io::Error),
+    TriggerInterrupt(io::Error),
     /// Failed masking the interrupt.
-    #[error("Failed masking the interrupt")]
-    MaskInterrupt(#[source] io::Error),
+    MaskInterrupt(io::Error),
     /// Failed unmasking the interrupt.
-    #[error("Failed unmasking the interrupt")]
-    UnmaskInterrupt(#[source] io::Error),
+    UnmaskInterrupt(io::Error),
     /// Failed updating the interrupt.
-    #[error("Failed updating the interrupt")]
-    UpdateInterrupt(#[source] io::Error),
+    UpdateInterrupt(io::Error),
     /// Failed enabling the interrupt.
-    #[error("Failed enabling the interrupt")]
-    EnableInterrupt(#[source] io::Error),
+    EnableInterrupt(io::Error),
     #[cfg(target_arch = "aarch64")]
     /// Failed creating GIC device.
-    #[error("Failed creating GIC device")]
-    CreateGic(#[source] hypervisor::HypervisorVmError),
+    CreateGic(hypervisor::HypervisorVmError),
     #[cfg(target_arch = "aarch64")]
     /// Failed restoring GIC device.
-    #[error("Failed restoring GIC device")]
-    RestoreGic(#[source] hypervisor::arch::aarch64::gic::Error),
-    #[cfg(target_arch = "riscv64")]
-    /// Failed creating AIA device.
-    #[error("Failed creating AIA device")]
-    CreateAia(#[source] hypervisor::HypervisorVmError),
-    #[cfg(target_arch = "riscv64")]
-    /// Failed restoring AIA device.
-    #[error("Failed restoring AIA device")]
-    RestoreAia(#[source] hypervisor::arch::riscv64::aia::Error),
+    RestoreGic(hypervisor::arch::aarch64::gic::Error),
 }
 
 type Result<T> = result::Result<T, Error>;
@@ -76,7 +56,7 @@ pub struct MsiMessage {
 // Introduce trait InterruptController to uniform the interrupt
 // service provided for devices.
 // Device manager uses this trait without caring whether it is a
-// IOAPIC (X86), GIC (Arm) or AIA (RISC-V).
+// IOAPIC (X86) or GIC (Arm).
 pub trait InterruptController: Send {
     fn service_irq(&mut self, irq: usize) -> Result<()>;
     #[cfg(target_arch = "x86_64")]

devices/src/ioapic.rs

@@ -9,22 +9,23 @@
 // Implementation of an intel 82093AA Input/Output Advanced Programmable Interrupt Controller
 // See https://pdos.csail.mit.edu/6.828/2016/readings/ia32/ioapic.pdf for a specification.
 
+use super::interrupt_controller::{Error, InterruptController};
+use byteorder::{ByteOrder, LittleEndian};
 use std::result;
 use std::sync::{Arc, Barrier};
-
-use byteorder::{ByteOrder, LittleEndian};
-use serde::{Deserialize, Serialize};
-use vm_device::BusDevice;
+use versionize::{VersionMap, Versionize, VersionizeResult};
+use versionize_derive::Versionize;
 use vm_device::interrupt::{
     InterruptIndex, InterruptManager, InterruptSourceConfig, InterruptSourceGroup,
     MsiIrqGroupConfig, MsiIrqSourceConfig,
 };
+use vm_device::BusDevice;
 use vm_memory::GuestAddress;
-use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
+use vm_migration::{
+    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
+};
 use vmm_sys_util::eventfd::EventFd;
 
-use super::interrupt_controller::{Error, InterruptController};
-
 type Result<T> = result::Result<T, Error>;
 
 // I/O REDIRECTION TABLE REGISTER
@@ -135,7 +136,7 @@ pub struct Ioapic {
     interrupt_source_group: Arc<dyn InterruptSourceGroup>,
 }
 
-#[derive(Serialize, Deserialize)]
+#[derive(Versionize)]
 pub struct IoapicState {
     id_reg: u32,
     reg_sel: u32,
@@ -143,6 +144,7 @@ pub struct IoapicState {
     used_entries: [bool; NUM_IOAPIC_PINS],
     apic_address: u64,
 }
+impl VersionMapped for IoapicState {}
 
 impl BusDevice for Ioapic {
     fn read(&mut self, _base: u64, offset: u64, data: &mut [u8]) {
@@ -235,14 +237,9 @@ impl Ioapic {
         if state.is_some() {
             for (irq, entry) in ioapic.used_entries.iter().enumerate() {
                 if *entry {
-                    ioapic.update_entry(irq, false)?;
+                    ioapic.update_entry(irq)?;
                 }
             }
-
-            ioapic
-                .interrupt_source_group
-                .set_gsi()
-                .map_err(Error::UpdateInterrupt)?;
         }
 
         Ok(ioapic)
@@ -281,7 +278,7 @@ impl Ioapic {
                 }
                 // The entry must be updated through the interrupt source
                 // group.
-                if let Err(e) = self.update_entry(index, true) {
+                if let Err(e) = self.update_entry(index) {
                     error!("Failed updating IOAPIC entry: {:?}", e);
                 }
                 // Store the information this IRQ is now being used.
@@ -332,7 +329,7 @@ impl Ioapic {
         }
     }
 
-    fn update_entry(&self, irq: usize, set_gsi: bool) -> Result<()> {
+    fn update_entry(&self, irq: usize) -> Result<()> {
         let entry = self.reg_entries[irq];
 
         // Validate Destination Mode value, and retrieve Destination ID
@@ -346,9 +343,9 @@ impl Ioapic {
 
         // Generate MSI message address
         let low_addr: u32 = self.apic_address.0 as u32
-            | (u32::from(destination_id) << 12)
-            | (u32::from(redirection_hint) << 3)
-            | (u32::from(destination_mode) << 2);
+            | u32::from(destination_id) << 12
+            | u32::from(redirection_hint) << 3
+            | u32::from(destination_mode) << 2;
 
         // Validate Trigger Mode value
         let trigger_mode = trigger_mode(entry);
@@ -372,9 +369,9 @@ impl Ioapic {
         }
 
         // Generate MSI message data
-        let data: u32 = (u32::from(trigger_mode) << 15)
-            | (u32::from(remote_irr(entry)) << 14)
-            | (u32::from(delivery_mode) << 8)
+        let data: u32 = u32::from(trigger_mode) << 15
+            | u32::from(remote_irr(entry)) << 14
+            | u32::from(delivery_mode) << 8
             | u32::from(vector(entry));
 
         let config = MsiIrqSourceConfig {
@@ -389,7 +386,6 @@ impl Ioapic {
                 irq as InterruptIndex,
                 InterruptSourceConfig::MsiIrq(config),
                 interrupt_mask(entry) == 1,
-                set_gsi,
             )
             .map_err(Error::UpdateInterrupt)?;
 
@@ -418,7 +414,7 @@ impl InterruptController for Ioapic {
         self.interrupt_source_group
             .trigger(irq as InterruptIndex)
             .map_err(Error::TriggerInterrupt)?;
-        trace!("Interrupt {irq} successfully delivered");
+        debug!("Interrupt successfully delivered");
 
         // If trigger mode is level sensitive, set the Remote IRR bit.
         // It will be cleared when the EOI is received.
@@ -442,7 +438,7 @@ impl Snapshottable for Ioapic {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        Snapshot::new_from_state(&self.state())
+        Snapshot::new_from_versioned_state(&self.state())
     }
 }
 

devices/src/ivshmem.rs

@@ -1,420 +0,0 @@
-// Copyright © 2024 Tencent Corporation. All rights reserved.
-//
-// SPDX-License-Identifier: Apache-2.0
-//
-
-use std::any::Any;
-use std::path::PathBuf;
-use std::result;
-use std::sync::atomic::{AtomicU32, Ordering};
-use std::sync::{Arc, Barrier, Mutex};
-
-use anyhow::anyhow;
-use byteorder::{ByteOrder, LittleEndian};
-use pci::{
-    BarReprogrammingParams, PCI_CONFIGURATION_ID, PciBarConfiguration, PciBarPrefetchable,
-    PciBarRegionType, PciClassCode, PciConfiguration, PciDevice, PciDeviceError, PciHeaderType,
-    PciSubclass,
-};
-use serde::{Deserialize, Serialize};
-use thiserror::Error;
-use vm_allocator::{AddressAllocator, SystemAllocator};
-use vm_device::{BusDevice, Resource, UserspaceMapping};
-use vm_memory::bitmap::AtomicBitmap;
-use vm_memory::{Address, GuestAddress};
-use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
-
-const IVSHMEM_BAR0_IDX: usize = 0;
-const IVSHMEM_BAR1_IDX: usize = 1;
-const IVSHMEM_BAR2_IDX: usize = 2;
-
-const IVSHMEM_VENDOR_ID: u16 = 0x1af4;
-const IVSHMEM_DEVICE_ID: u16 = 0x1110;
-
-const IVSHMEM_REG_BAR_SIZE: u64 = 0x100;
-
-type GuestRegionMmap = vm_memory::GuestRegionMmap<AtomicBitmap>;
-
-#[derive(Debug, Error)]
-pub enum IvshmemError {
-    #[error("Failed to retrieve PciConfigurationState: {0}")]
-    RetrievePciConfigurationState(#[source] anyhow::Error),
-    #[error("Failed to retrieve IvshmemDeviceState: {0}")]
-    RetrieveIvshmemDeviceStateState(#[source] anyhow::Error),
-    #[error("Failed to remove user memory region")]
-    RemoveUserMemoryRegion,
-    #[error("Failed to create user memory region.")]
-    CreateUserMemoryRegion,
-    #[error("Failed to create userspace mapping.")]
-    CreateUserspaceMapping,
-    #[error("Failed to remove old userspace mapping.")]
-    RemoveUserspaceMapping,
-}
-
-#[derive(Copy, Clone)]
-pub enum IvshmemSubclass {
-    Other = 0x00,
-}
-
-impl PciSubclass for IvshmemSubclass {
-    fn get_register_value(&self) -> u8 {
-        *self as u8
-    }
-}
-
-pub trait IvshmemOps: Send + Sync {
-    fn map_ram_region(
-        &mut self,
-        start_addr: u64,
-        size: usize,
-        backing_file: Option<PathBuf>,
-    ) -> Result<(Arc<GuestRegionMmap>, UserspaceMapping), IvshmemError>;
-
-    fn unmap_ram_region(&mut self, mapping: UserspaceMapping) -> Result<(), IvshmemError>;
-}
-
-/// Inner-Vm Shared Memory Device (Ivshmem device)
-///
-/// This device can share memory between host and guest(ivshmem-plain)
-/// and share memory between guests(ivshmem-doorbell).
-/// But only ivshmem-plain support now, ivshmem-doorbell doesn't support yet.
-pub struct IvshmemDevice {
-    id: String,
-
-    // ivshmem device registers
-    // (only used for ivshmem-doorbell, ivshmem-doorbell don't support yet)
-    _interrupt_mask: u32,
-    _interrupt_status: Arc<AtomicU32>,
-    _iv_position: u32,
-    _doorbell: u32,
-
-    // PCI configuration registers.
-    configuration: PciConfiguration,
-    bar_regions: Vec<PciBarConfiguration>,
-
-    region_size: u64,
-    ivshmem_ops: Arc<Mutex<dyn IvshmemOps>>,
-    backend_file: Option<PathBuf>,
-    region: Option<Arc<GuestRegionMmap>>,
-    userspace_mapping: Option<UserspaceMapping>,
-}
-
-#[derive(Serialize, Deserialize, Default, Clone)]
-pub struct IvshmemDeviceState {
-    interrupt_mask: u32,
-    interrupt_status: u32,
-    iv_position: u32,
-    doorbell: u32,
-}
-
-impl IvshmemDevice {
-    pub fn new(
-        id: String,
-        region_size: u64,
-        backend_file: Option<PathBuf>,
-        ivshmem_ops: Arc<Mutex<dyn IvshmemOps>>,
-        snapshot: Option<Snapshot>,
-    ) -> Result<Self, IvshmemError> {
-        let pci_configuration_state =
-            vm_migration::state_from_id(snapshot.as_ref(), PCI_CONFIGURATION_ID).map_err(|e| {
-                IvshmemError::RetrievePciConfigurationState(anyhow!(
-                    "Failed to get PciConfigurationState from Snapshot: {e}",
-                ))
-            })?;
-
-        let state: Option<IvshmemDeviceState> = snapshot
-            .as_ref()
-            .map(|s| s.to_state())
-            .transpose()
-            .map_err(|e| {
-                IvshmemError::RetrieveIvshmemDeviceStateState(anyhow!(
-                    "Failed to get IvshmemDeviceState from Snapshot: {e}",
-                ))
-            })?;
-
-        let configuration = PciConfiguration::new(
-            IVSHMEM_VENDOR_ID,
-            IVSHMEM_DEVICE_ID,
-            0x1,
-            PciClassCode::MemoryController,
-            &IvshmemSubclass::Other,
-            None,
-            PciHeaderType::Device,
-            0,
-            0,
-            None,
-            pci_configuration_state,
-        );
-
-        let device = if let Some(s) = state {
-            IvshmemDevice {
-                id,
-                configuration,
-                bar_regions: vec![],
-                _interrupt_mask: s.interrupt_mask,
-                _interrupt_status: Arc::new(AtomicU32::new(s.interrupt_status)),
-                _iv_position: s.iv_position,
-                _doorbell: s.doorbell,
-                region_size,
-                ivshmem_ops,
-                region: None,
-                userspace_mapping: None,
-                backend_file,
-            }
-        } else {
-            IvshmemDevice {
-                id,
-                configuration,
-                bar_regions: vec![],
-                _interrupt_mask: 0,
-                _interrupt_status: Arc::new(AtomicU32::new(0)),
-                _iv_position: 0,
-                _doorbell: 0,
-                region_size,
-                ivshmem_ops,
-                region: None,
-                userspace_mapping: None,
-                backend_file,
-            }
-        };
-        Ok(device)
-    }
-
-    pub fn set_region(
-        &mut self,
-        region: Arc<GuestRegionMmap>,
-        userspace_mapping: UserspaceMapping,
-    ) {
-        self.region = Some(region);
-        self.userspace_mapping = Some(userspace_mapping);
-    }
-
-    pub fn config_bar_addr(&self) -> u64 {
-        self.configuration.get_bar_addr(IVSHMEM_BAR0_IDX)
-    }
-
-    pub fn data_bar_addr(&self) -> u64 {
-        self.configuration.get_bar_addr(IVSHMEM_BAR2_IDX)
-    }
-
-    fn state(&self) -> IvshmemDeviceState {
-        IvshmemDeviceState {
-            interrupt_mask: self._interrupt_mask,
-            interrupt_status: self._interrupt_status.load(Ordering::SeqCst),
-            iv_position: self._iv_position,
-            doorbell: self._doorbell,
-        }
-    }
-}
-
-impl BusDevice for IvshmemDevice {
-    fn read(&mut self, base: u64, offset: u64, data: &mut [u8]) {
-        self.read_bar(base, offset, data)
-    }
-
-    fn write(&mut self, base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
-        self.write_bar(base, offset, data)
-    }
-}
-
-impl PciDevice for IvshmemDevice {
-    fn allocate_bars(
-        &mut self,
-        _allocator: &Arc<Mutex<SystemAllocator>>,
-        mmio32_allocator: &mut AddressAllocator,
-        mmio64_allocator: &mut AddressAllocator,
-        resources: Option<Vec<Resource>>,
-    ) -> std::result::Result<Vec<PciBarConfiguration>, PciDeviceError> {
-        let mut bars = Vec::new();
-        let mut bar0_addr = None;
-        let mut bar2_addr = None;
-
-        let restoring = resources.is_some();
-        if let Some(resources) = resources {
-            for resource in resources {
-                match resource {
-                    Resource::PciBar { index, base, .. } => {
-                        match index {
-                            IVSHMEM_BAR0_IDX => {
-                                bar0_addr = Some(GuestAddress(base));
-                            }
-                            IVSHMEM_BAR1_IDX => {}
-                            IVSHMEM_BAR2_IDX => {
-                                bar2_addr = Some(GuestAddress(base));
-                            }
-                            _ => {
-                                error!("Unexpected pci bar index {index}");
-                            }
-                        };
-                    }
-                    _ => {
-                        error!("Unexpected resource {resource:?}");
-                    }
-                }
-            }
-            if bar0_addr.is_none() || bar2_addr.is_none() {
-                return Err(PciDeviceError::MissingResource);
-            }
-        }
-
-        // BAR0 holds device registers (256 Byte MMIO)
-        let bar0_addr = mmio32_allocator
-            .allocate(bar0_addr, IVSHMEM_REG_BAR_SIZE, None)
-            .ok_or(PciDeviceError::IoAllocationFailed(IVSHMEM_REG_BAR_SIZE))?;
-        debug!("ivshmem bar0 address 0x{:x}", bar0_addr.0);
-
-        let bar0 = PciBarConfiguration::default()
-            .set_index(IVSHMEM_BAR0_IDX)
-            .set_address(bar0_addr.raw_value())
-            .set_size(IVSHMEM_REG_BAR_SIZE)
-            .set_region_type(PciBarRegionType::Memory32BitRegion)
-            .set_prefetchable(PciBarPrefetchable::NotPrefetchable);
-
-        // BAR1 holds MSI-X table and PBA (only ivshmem-doorbell).
-
-        // BAR2 maps the shared memory object
-        let bar2_size = self.region_size;
-        let bar2_addr = mmio64_allocator
-            .allocate(bar2_addr, bar2_size, None)
-            .ok_or(PciDeviceError::IoAllocationFailed(bar2_size))?;
-        debug!("ivshmem bar2 address 0x{:x}", bar2_addr.0);
-
-        let bar2 = PciBarConfiguration::default()
-            .set_index(IVSHMEM_BAR2_IDX)
-            .set_address(bar2_addr.raw_value())
-            .set_size(bar2_size)
-            .set_region_type(PciBarRegionType::Memory64BitRegion)
-            .set_prefetchable(PciBarPrefetchable::Prefetchable);
-
-        if !restoring {
-            self.configuration
-                .add_pci_bar(&bar0)
-                .map_err(|e| PciDeviceError::IoRegistrationFailed(bar0_addr.raw_value(), e))?;
-            self.configuration
-                .add_pci_bar(&bar2)
-                .map_err(|e| PciDeviceError::IoRegistrationFailed(bar2_addr.raw_value(), e))?;
-        }
-
-        bars.push(bar0);
-        bars.push(bar2);
-        self.bar_regions = bars.clone();
-
-        Ok(bars)
-    }
-
-    fn free_bars(
-        &mut self,
-        _allocator: &mut SystemAllocator,
-        _mmio32_allocator: &mut AddressAllocator,
-        _mmio64_allocator: &mut AddressAllocator,
-    ) -> std::result::Result<(), PciDeviceError> {
-        unimplemented!("Device hotplug  and remove are not supported for ivshmem");
-    }
-
-    fn write_config_register(
-        &mut self,
-        reg_idx: usize,
-        offset: u64,
-        data: &[u8],
-    ) -> (Vec<BarReprogrammingParams>, Option<Arc<Barrier>>) {
-        (
-            self.configuration
-                .write_config_register(reg_idx, offset, data),
-            None,
-        )
-    }
-
-    fn read_config_register(&mut self, reg_idx: usize) -> u32 {
-        self.configuration.read_reg(reg_idx)
-    }
-
-    fn read_bar(&mut self, base: u64, offset: u64, data: &mut [u8]) {
-        debug!("read base {base:x} offset {offset}");
-
-        let mut bar_idx = 0;
-        for (idx, bar) in self.bar_regions.iter().enumerate() {
-            if bar.addr() == base {
-                bar_idx = idx;
-            }
-        }
-        match bar_idx {
-            // bar 0
-            0 => {
-                // ivshmem don't use interrupt, we return zero now.
-                LittleEndian::write_u32(data, 0);
-            }
-            // bar 2
-            1 => warn!("Unexpected read ivshmem memory idx: {offset}"),
-            _ => {
-                warn!("Invalid bar_idx: {bar_idx}");
-            }
-        };
-    }
-
-    fn write_bar(&mut self, base: u64, offset: u64, _data: &[u8]) -> Option<Arc<Barrier>> {
-        debug!("write base {base:x} offset {offset}");
-        warn!("Unexpected write ivshmem memory idx: {offset}");
-        None
-    }
-
-    fn move_bar(&mut self, old_base: u64, new_base: u64) -> result::Result<(), std::io::Error> {
-        if new_base == self.data_bar_addr() {
-            if let Some(old_mapping) = self.userspace_mapping.take() {
-                self.ivshmem_ops
-                    .lock()
-                    .unwrap()
-                    .unmap_ram_region(old_mapping)
-                    .map_err(std::io::Error::other)?;
-            }
-            let (region, new_mapping) = self
-                .ivshmem_ops
-                .lock()
-                .unwrap()
-                .map_ram_region(
-                    new_base,
-                    self.region_size as usize,
-                    self.backend_file.clone(),
-                )
-                .map_err(std::io::Error::other)?;
-            self.set_region(region, new_mapping);
-        }
-        for bar in self.bar_regions.iter_mut() {
-            if bar.addr() == old_base {
-                *bar = bar.set_address(new_base);
-            }
-        }
-
-        Ok(())
-    }
-
-    fn as_any_mut(&mut self) -> &mut dyn Any {
-        self
-    }
-
-    fn id(&self) -> Option<String> {
-        Some(self.id.clone())
-    }
-}
-
-impl Pausable for IvshmemDevice {}
-
-impl Snapshottable for IvshmemDevice {
-    fn id(&self) -> String {
-        self.id.clone()
-    }
-
-    // The snapshot/restore (also live migration) support only work for ivshmem-plain mode.
-    // Additional work is needed for supporting ivshmem-doorbell.
-    fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        let mut snapshot = Snapshot::new_from_state(&self.state())?;
-
-        // Snapshot PciConfiguration
-        snapshot.add_snapshot(self.configuration.id(), self.configuration.snapshot()?);
-
-        Ok(snapshot)
-    }
-}
-
-impl Transportable for IvshmemDevice {}
-
-impl Migratable for IvshmemDevice {}

devices/src/legacy/cmos.rs

@@ -1,20 +1,17 @@
 // Copyright 2017 The Chromium OS Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
-//
-// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
+use libc::{clock_gettime, gmtime_r, timespec, tm, CLOCK_REALTIME};
 use std::cmp::min;
-use std::sync::atomic::{AtomicBool, Ordering};
+use std::mem;
 use std::sync::{Arc, Barrier};
-use std::{mem, thread};
+use vm_device::BusDevice;
+use vmm_sys_util::eventfd::EventFd;
 
 // https://github.com/rust-lang/libc/issues/1848
 #[cfg_attr(target_env = "musl", allow(deprecated))]
 use libc::time_t;
-use libc::{CLOCK_REALTIME, clock_gettime, gmtime_r, timespec, tm};
-use vm_device::BusDevice;
-use vmm_sys_util::eventfd::EventFd;
 
 const INDEX_MASK: u8 = 0x7f;
 const INDEX_OFFSET: u64 = 0x0;
@@ -26,19 +23,13 @@ pub struct Cmos {
     index: u8,
     data: [u8; DATA_LEN],
     reset_evt: EventFd,
-    vcpus_kill_signalled: Option<Arc<AtomicBool>>,
 }
 
 impl Cmos {
     /// Constructs a CMOS/RTC device with initial data.
     /// `mem_below_4g` is the size of memory in bytes below the 32-bit gap.
     /// `mem_above_4g` is the size of memory in bytes above the 32-bit gap.
-    pub fn new(
-        mem_below_4g: u64,
-        mem_above_4g: u64,
-        reset_evt: EventFd,
-        vcpus_kill_signalled: Option<Arc<AtomicBool>>,
-    ) -> Cmos {
+    pub fn new(mem_below_4g: u64, mem_above_4g: u64, reset_evt: EventFd) -> Cmos {
         let mut data = [0u8; DATA_LEN];
 
         // Extended memory from 16 MB to 4 GB in units of 64 KB
@@ -59,7 +50,6 @@ impl Cmos {
             index: 0,
             data,
             reset_evt,
-            vcpus_kill_signalled,
         }
     }
 }
@@ -77,15 +67,6 @@ impl BusDevice for Cmos {
                 if self.index == 0x8f && data[0] == 0 {
                     info!("CMOS reset");
                     self.reset_evt.write(1).unwrap();
-                    if let Some(vcpus_kill_signalled) = self.vcpus_kill_signalled.take() {
-                        // Spin until we are sure the reset_evt has been handled and that when
-                        // we return from the KVM_RUN we will exit rather than re-enter the guest.
-                        while !vcpus_kill_signalled.load(Ordering::SeqCst) {
-                            // This is more effective than thread::yield_now() at
-                            // avoiding a priority inversion with the VMM thread
-                            thread::sleep(std::time::Duration::from_millis(1));
-                        }
-                    }
                 } else {
                     self.data[(self.index & INDEX_MASK) as usize] = data[0]
                 }
@@ -152,7 +133,7 @@ impl BusDevice for Cmos {
                     0x08 => to_bcd(month as u8),
                     0x09 => to_bcd((year % 100) as u8),
                     // Bit 5 for 32kHz clock. Bit 7 for Update in Progress
-                    0x0a => (1 << 5) | ((update_in_progress as u8) << 7),
+                    0x0a => 1 << 5 | (update_in_progress as u8) << 7,
                     // Bit 0-6 are reserved and must be 0.
                     // Bit 7 must be 1 (CMOS has power)
                     0x0d => 1 << 7,

devices/src/legacy/debug_port.rs

@@ -5,7 +5,6 @@
 
 use std::fmt;
 use std::time::Instant;
-
 use vm_device::BusDevice;
 
 /// Debug I/O port, see:

devices/src/legacy/fw_cfg.rs

@@ -1,954 +0,0 @@
-// Copyright 2025 Google LLC.
-//
-// SPDX-License-Identifier: Apache-2.0
-//
-
-/// Cloud Hypervisor implementation of Qemu's fw_cfg spec
-/// https://www.qemu.org/docs/master/specs/fw_cfg.html
-/// Linux kernel fw_cfg driver header
-/// https://github.com/torvalds/linux/blob/master/include/uapi/linux/qemu_fw_cfg.h
-/// Uploading files to the guest via fw_cfg is supported for all kernels 4.6+ w/ CONFIG_FW_CFG_SYSFS enabled
-/// https://cateee.net/lkddb/web-lkddb/FW_CFG_SYSFS.html
-/// No kernel requirement if above functionality is not required,
-/// only firmware must implement mechanism to interact with this fw_cfg device
-use std::{
-    fs::File,
-    io::{ErrorKind, Read, Result, Seek, SeekFrom},
-    mem::offset_of,
-    os::unix::fs::FileExt,
-    sync::{Arc, Barrier},
-};
-
-use acpi_tables::rsdp::Rsdp;
-use arch::RegionType;
-#[cfg(target_arch = "aarch64")]
-use arch::aarch64::layout::{
-    MEM_32BIT_DEVICES_START, MEM_32BIT_RESERVED_START, RAM_64BIT_START, RAM_START as HIGH_RAM_START,
-};
-#[cfg(target_arch = "x86_64")]
-use arch::layout::{
-    EBDA_START, HIGH_RAM_START, MEM_32BIT_DEVICES_SIZE, MEM_32BIT_DEVICES_START,
-    MEM_32BIT_RESERVED_START, PCI_MMCONFIG_SIZE, PCI_MMCONFIG_START, RAM_64BIT_START,
-};
-use bitfield_struct::bitfield;
-#[cfg(target_arch = "x86_64")]
-use linux_loader::bootparam::boot_params;
-#[cfg(target_arch = "aarch64")]
-use linux_loader::loader::pe::arm64_image_header as boot_params;
-use vm_device::BusDevice;
-use vm_memory::bitmap::AtomicBitmap;
-use vm_memory::{
-    ByteValued, Bytes, GuestAddress, GuestAddressSpace, GuestMemoryAtomic, GuestMemoryMmap,
-};
-use vmm_sys_util::sock_ctrl_msg::IntoIovec;
-use zerocopy::{FromBytes, FromZeros, Immutable, IntoBytes};
-
-#[cfg(target_arch = "x86_64")]
-// https://github.com/project-oak/oak/tree/main/stage0_bin#memory-layout
-const STAGE0_START_ADDRESS: GuestAddress = GuestAddress(0xfffe_0000);
-#[cfg(target_arch = "x86_64")]
-const STAGE0_SIZE: usize = 0x2_0000;
-const E820_RAM: u32 = 1;
-const E820_RESERVED: u32 = 2;
-
-#[cfg(target_arch = "x86_64")]
-const PORT_FW_CFG_SELECTOR: u64 = 0x510;
-#[cfg(target_arch = "x86_64")]
-const PORT_FW_CFG_DATA: u64 = 0x511;
-#[cfg(target_arch = "x86_64")]
-const PORT_FW_CFG_DMA_HI: u64 = 0x514;
-#[cfg(target_arch = "x86_64")]
-const PORT_FW_CFG_DMA_LO: u64 = 0x518;
-#[cfg(target_arch = "x86_64")]
-pub const PORT_FW_CFG_BASE: u64 = 0x510;
-#[cfg(target_arch = "x86_64")]
-pub const PORT_FW_CFG_WIDTH: u64 = 0xc;
-#[cfg(target_arch = "aarch64")]
-const PORT_FW_CFG_SELECTOR: u64 = 0x9030008;
-#[cfg(target_arch = "aarch64")]
-const PORT_FW_CFG_DATA: u64 = 0x9030000;
-#[cfg(target_arch = "aarch64")]
-const PORT_FW_CFG_DMA_HI: u64 = 0x9030010;
-#[cfg(target_arch = "aarch64")]
-const PORT_FW_CFG_DMA_LO: u64 = 0x9030014;
-#[cfg(target_arch = "aarch64")]
-pub const PORT_FW_CFG_BASE: u64 = 0x9030000;
-#[cfg(target_arch = "aarch64")]
-pub const PORT_FW_CFG_WIDTH: u64 = 0x10;
-
-const FW_CFG_SIGNATURE: u16 = 0x00;
-const FW_CFG_ID: u16 = 0x01;
-const FW_CFG_KERNEL_SIZE: u16 = 0x08;
-const FW_CFG_INITRD_SIZE: u16 = 0x0b;
-const FW_CFG_KERNEL_DATA: u16 = 0x11;
-const FW_CFG_INITRD_DATA: u16 = 0x12;
-const FW_CFG_CMDLINE_SIZE: u16 = 0x14;
-const FW_CFG_CMDLINE_DATA: u16 = 0x15;
-const FW_CFG_SETUP_SIZE: u16 = 0x17;
-const FW_CFG_SETUP_DATA: u16 = 0x18;
-const FW_CFG_FILE_DIR: u16 = 0x19;
-const FW_CFG_KNOWN_ITEMS: usize = 0x20;
-
-pub const FW_CFG_FILE_FIRST: u16 = 0x20;
-pub const FW_CFG_DMA_SIGNATURE: [u8; 8] = *b"QEMU CFG";
-// https://github.com/torvalds/linux/blob/master/include/uapi/linux/qemu_fw_cfg.h
-pub const FW_CFG_ACPI_ID: &str = "QEMU0002";
-// Reserved (must be enabled)
-const FW_CFG_F_RESERVED: u8 = 1 << 0;
-// DMA Toggle Bit (enabled by default)
-const FW_CFG_F_DMA: u8 = 1 << 1;
-pub const FW_CFG_FEATURE: [u8; 4] = [FW_CFG_F_RESERVED | FW_CFG_F_DMA, 0, 0, 0];
-
-const COMMAND_ALLOCATE: u32 = 0x1;
-const COMMAND_ADD_POINTER: u32 = 0x2;
-const COMMAND_ADD_CHECKSUM: u32 = 0x3;
-
-const ALLOC_ZONE_HIGH: u8 = 0x1;
-const ALLOC_ZONE_FSEG: u8 = 0x2;
-
-const FW_CFG_FILENAME_TABLE_LOADER: &str = "etc/table-loader";
-const FW_CFG_FILENAME_RSDP: &str = "acpi/rsdp";
-const FW_CFG_FILENAME_ACPI_TABLES: &str = "acpi/tables";
-
-#[derive(Debug)]
-pub enum FwCfgContent {
-    Bytes(Vec<u8>),
-    Slice(&'static [u8]),
-    File(u64, File),
-    U32(u32),
-}
-
-struct FwCfgContentAccess<'a> {
-    content: &'a FwCfgContent,
-    offset: u32,
-}
-
-impl Read for FwCfgContentAccess<'_> {
-    fn read(&mut self, buf: &mut [u8]) -> Result<usize> {
-        match self.content {
-            FwCfgContent::File(offset, f) => {
-                Seek::seek(&mut (&*f), SeekFrom::Start(offset + self.offset as u64))?;
-                Read::read(&mut (&*f), buf)
-            }
-            FwCfgContent::Bytes(b) => match b.get(self.offset as usize..) {
-                Some(mut s) => s.read(buf),
-                None => Err(ErrorKind::UnexpectedEof)?,
-            },
-            FwCfgContent::Slice(b) => match b.get(self.offset as usize..) {
-                Some(mut s) => s.read(buf),
-                None => Err(ErrorKind::UnexpectedEof)?,
-            },
-            FwCfgContent::U32(n) => match n.to_le_bytes().get(self.offset as usize..) {
-                Some(mut s) => s.read(buf),
-                None => Err(ErrorKind::UnexpectedEof)?,
-            },
-        }
-    }
-}
-
-impl Default for FwCfgContent {
-    fn default() -> Self {
-        FwCfgContent::Slice(&[])
-    }
-}
-
-impl FwCfgContent {
-    fn size(&self) -> Result<u32> {
-        let ret = match self {
-            FwCfgContent::Bytes(v) => v.len(),
-            FwCfgContent::File(offset, f) => (f.metadata()?.len() - offset) as usize,
-            FwCfgContent::Slice(s) => s.len(),
-            FwCfgContent::U32(n) => size_of_val(n),
-        };
-        u32::try_from(ret).map_err(|_| std::io::ErrorKind::InvalidInput.into())
-    }
-    fn access(&self, offset: u32) -> FwCfgContentAccess<'_> {
-        FwCfgContentAccess {
-            content: self,
-            offset,
-        }
-    }
-}
-
-#[derive(Debug, Default)]
-pub struct FwCfgItem {
-    pub name: String,
-    pub content: FwCfgContent,
-}
-
-/// https://www.qemu.org/docs/master/specs/fw_cfg.html
-#[derive(Debug)]
-pub struct FwCfg {
-    selector: u16,
-    data_offset: u32,
-    dma_address: u64,
-    items: Vec<FwCfgItem>,                           // 0x20 and above
-    known_items: [FwCfgContent; FW_CFG_KNOWN_ITEMS], // 0x0 to 0x19
-    memory: GuestMemoryAtomic<GuestMemoryMmap<AtomicBitmap>>,
-}
-
-#[repr(C)]
-#[derive(Debug, IntoBytes, FromBytes)]
-struct FwCfgDmaAccess {
-    control_be: u32,
-    length_be: u32,
-    address_be: u64,
-}
-
-// https://github.com/torvalds/linux/blob/master/include/uapi/linux/qemu_fw_cfg.h#L67
-#[bitfield(u32)]
-struct AccessControl {
-    // FW_CFG_DMA_CTL_ERROR = 0x01
-    error: bool,
-    // FW_CFG_DMA_CTL_READ = 0x02
-    read: bool,
-    #[bits(1)]
-    _unused2: u8,
-    // FW_CFG_DMA_CTL_SKIP = 0x04
-    skip: bool,
-    #[bits(3)]
-    _unused3: u8,
-    // FW_CFG_DMA_CTL_ERROR = 0x08
-    select: bool,
-    #[bits(7)]
-    _unused4: u8,
-    // FW_CFG_DMA_CTL_WRITE = 0x10
-    write: bool,
-    #[bits(16)]
-    _unused: u32,
-}
-
-#[repr(C)]
-#[derive(Debug, IntoBytes, FromBytes)]
-struct FwCfgFilesHeader {
-    count_be: u32,
-}
-
-pub const FILE_NAME_SIZE: usize = 56;
-
-pub fn create_file_name(name: &str) -> [u8; FILE_NAME_SIZE] {
-    let mut c_name = [0u8; FILE_NAME_SIZE];
-    let c_len = std::cmp::min(FILE_NAME_SIZE - 1, name.len());
-    c_name[0..c_len].copy_from_slice(&name.as_bytes()[0..c_len]);
-    c_name
-}
-
-#[allow(dead_code)]
-#[repr(C, packed)]
-#[derive(Debug, IntoBytes, FromBytes, Clone, Copy)]
-struct BootE820Entry {
-    addr: u64,
-    size: u64,
-    type_: u32,
-}
-
-#[repr(C)]
-#[derive(Debug, IntoBytes, FromBytes)]
-struct FwCfgFile {
-    size_be: u32,
-    select_be: u16,
-    _reserved: u16,
-    name: [u8; FILE_NAME_SIZE],
-}
-
-#[repr(C, align(4))]
-#[derive(Debug, IntoBytes, Immutable)]
-struct Allocate {
-    command: u32,
-    file: [u8; FILE_NAME_SIZE],
-    align: u32,
-    zone: u8,
-    _pad: [u8; 63],
-}
-
-#[repr(C, align(4))]
-#[derive(Debug, IntoBytes, Immutable)]
-struct AddPointer {
-    command: u32,
-    dst: [u8; FILE_NAME_SIZE],
-    src: [u8; FILE_NAME_SIZE],
-    offset: u32,
-    size: u8,
-    _pad: [u8; 7],
-}
-
-#[repr(C, align(4))]
-#[derive(Debug, IntoBytes, Immutable)]
-struct AddChecksum {
-    command: u32,
-    file: [u8; FILE_NAME_SIZE],
-    offset: u32,
-    start: u32,
-    len: u32,
-    _pad: [u8; 56],
-}
-
-fn create_intra_pointer(name: &str, offset: usize, size: u8) -> AddPointer {
-    AddPointer {
-        command: COMMAND_ADD_POINTER,
-        dst: create_file_name(name),
-        src: create_file_name(name),
-        offset: offset as u32,
-        size,
-        _pad: [0; 7],
-    }
-}
-
-fn create_acpi_table_checksum(offset: usize, len: usize) -> AddChecksum {
-    AddChecksum {
-        command: COMMAND_ADD_CHECKSUM,
-        file: create_file_name(FW_CFG_FILENAME_ACPI_TABLES),
-        offset: (offset + offset_of!(AcpiTableHeader, checksum)) as u32,
-        start: offset as u32,
-        len: len as u32,
-        _pad: [0; 56],
-    }
-}
-
-#[repr(C, align(4))]
-#[derive(Debug, Clone, Default, FromBytes, IntoBytes)]
-struct AcpiTableHeader {
-    signature: [u8; 4],
-    length: u32,
-    revision: u8,
-    checksum: u8,
-    oem_id: [u8; 6],
-    oem_table_id: [u8; 8],
-    oem_revision: u32,
-    asl_compiler_id: [u8; 4],
-    asl_compiler_revision: u32,
-}
-
-struct AcpiTable {
-    rsdp: Rsdp,
-    tables: Vec<u8>,
-    table_pointers: Vec<usize>,
-    table_checksums: Vec<(usize, usize)>,
-}
-
-impl AcpiTable {
-    fn pointers(&self) -> &[usize] {
-        &self.table_pointers
-    }
-
-    fn checksums(&self) -> &[(usize, usize)] {
-        &self.table_checksums
-    }
-
-    fn take(self) -> (Rsdp, Vec<u8>) {
-        (self.rsdp, self.tables)
-    }
-}
-
-// Creates fw_cfg items used by firmware to load and verify Acpi tables
-// https://github.com/qemu/qemu/blob/master/hw/acpi/bios-linker-loader.c
-fn create_acpi_loader(acpi_table: AcpiTable) -> [FwCfgItem; 3] {
-    let mut table_loader_bytes: Vec<u8> = Vec::new();
-    let allocate_rsdp = Allocate {
-        command: COMMAND_ALLOCATE,
-        file: create_file_name(FW_CFG_FILENAME_RSDP),
-        align: 4,
-        zone: ALLOC_ZONE_FSEG,
-        _pad: [0; 63],
-    };
-    table_loader_bytes.extend(allocate_rsdp.as_bytes());
-
-    let allocate_tables = Allocate {
-        command: COMMAND_ALLOCATE,
-        file: create_file_name(FW_CFG_FILENAME_ACPI_TABLES),
-        align: 4,
-        zone: ALLOC_ZONE_HIGH,
-        _pad: [0; 63],
-    };
-    table_loader_bytes.extend(allocate_tables.as_bytes());
-
-    for pointer_offset in acpi_table.pointers().iter() {
-        let pointer = create_intra_pointer(FW_CFG_FILENAME_ACPI_TABLES, *pointer_offset, 8);
-        table_loader_bytes.extend(pointer.as_bytes());
-    }
-    for (offset, len) in acpi_table.checksums().iter() {
-        let checksum = create_acpi_table_checksum(*offset, *len);
-        table_loader_bytes.extend(checksum.as_bytes());
-    }
-    let pointer_rsdp_to_xsdt = AddPointer {
-        command: COMMAND_ADD_POINTER,
-        dst: create_file_name(FW_CFG_FILENAME_RSDP),
-        src: create_file_name(FW_CFG_FILENAME_ACPI_TABLES),
-        offset: offset_of!(Rsdp, xsdt_addr) as u32,
-        size: 8,
-        _pad: [0; 7],
-    };
-    table_loader_bytes.extend(pointer_rsdp_to_xsdt.as_bytes());
-    let checksum_rsdp = AddChecksum {
-        command: COMMAND_ADD_CHECKSUM,
-        file: create_file_name(FW_CFG_FILENAME_RSDP),
-        offset: offset_of!(Rsdp, checksum) as u32,
-        start: 0,
-        len: offset_of!(Rsdp, length) as u32,
-        _pad: [0; 56],
-    };
-    let checksum_rsdp_ext = AddChecksum {
-        command: COMMAND_ADD_CHECKSUM,
-        file: create_file_name(FW_CFG_FILENAME_RSDP),
-        offset: offset_of!(Rsdp, extended_checksum) as u32,
-        start: 0,
-        len: size_of::<Rsdp>() as u32,
-        _pad: [0; 56],
-    };
-    table_loader_bytes.extend(checksum_rsdp.as_bytes());
-    table_loader_bytes.extend(checksum_rsdp_ext.as_bytes());
-
-    let table_loader = FwCfgItem {
-        name: FW_CFG_FILENAME_TABLE_LOADER.to_owned(),
-        content: FwCfgContent::Bytes(table_loader_bytes),
-    };
-    let (rsdp, tables) = acpi_table.take();
-    let acpi_rsdp = FwCfgItem {
-        name: FW_CFG_FILENAME_RSDP.to_owned(),
-        content: FwCfgContent::Bytes(rsdp.as_bytes().to_owned()),
-    };
-    let apci_tables = FwCfgItem {
-        name: FW_CFG_FILENAME_ACPI_TABLES.to_owned(),
-        content: FwCfgContent::Bytes(tables),
-    };
-    [table_loader, acpi_rsdp, apci_tables]
-}
-
-impl FwCfg {
-    pub fn new(memory: GuestMemoryAtomic<GuestMemoryMmap<AtomicBitmap>>) -> FwCfg {
-        const DEFAULT_ITEM: FwCfgContent = FwCfgContent::Slice(&[]);
-        let mut known_items = [DEFAULT_ITEM; FW_CFG_KNOWN_ITEMS];
-        known_items[FW_CFG_SIGNATURE as usize] = FwCfgContent::Slice(&FW_CFG_DMA_SIGNATURE);
-        known_items[FW_CFG_ID as usize] = FwCfgContent::Slice(&FW_CFG_FEATURE);
-        let file_buf = Vec::from(FwCfgFilesHeader { count_be: 0 }.as_mut_bytes());
-        known_items[FW_CFG_FILE_DIR as usize] = FwCfgContent::Bytes(file_buf);
-
-        FwCfg {
-            selector: 0,
-            data_offset: 0,
-            dma_address: 0,
-            items: vec![],
-            known_items,
-            memory,
-        }
-    }
-
-    pub fn populate_fw_cfg(
-        &mut self,
-        mem_size: Option<usize>,
-        kernel: Option<File>,
-        initramfs: Option<File>,
-        cmdline: Option<std::ffi::CString>,
-        fw_cfg_item_list: Option<Vec<FwCfgItem>>,
-    ) -> Result<()> {
-        if let Some(mem_size) = mem_size {
-            self.add_e820(mem_size)?
-        }
-        if let Some(kernel) = kernel {
-            self.add_kernel_data(&kernel)?;
-        }
-        if let Some(cmdline) = cmdline {
-            self.add_kernel_cmdline(cmdline);
-        }
-        if let Some(initramfs) = initramfs {
-            self.add_initramfs_data(&initramfs)?
-        }
-        if let Some(fw_cfg_item_list) = fw_cfg_item_list {
-            for item in fw_cfg_item_list {
-                self.add_item(item)?;
-            }
-        }
-        Ok(())
-    }
-
-    pub fn add_e820(&mut self, mem_size: usize) -> Result<()> {
-        #[cfg(target_arch = "x86_64")]
-        let mut mem_regions = vec![
-            (GuestAddress(0), EBDA_START.0 as usize, RegionType::Ram),
-            (
-                MEM_32BIT_DEVICES_START,
-                MEM_32BIT_DEVICES_SIZE as usize,
-                RegionType::Reserved,
-            ),
-            (
-                PCI_MMCONFIG_START,
-                PCI_MMCONFIG_SIZE as usize,
-                RegionType::Reserved,
-            ),
-            (STAGE0_START_ADDRESS, STAGE0_SIZE, RegionType::Reserved),
-        ];
-        #[cfg(target_arch = "aarch64")]
-        let mut mem_regions = arch::aarch64::arch_memory_regions();
-        if mem_size < MEM_32BIT_DEVICES_START.0 as usize {
-            mem_regions.push((
-                HIGH_RAM_START,
-                mem_size - HIGH_RAM_START.0 as usize,
-                RegionType::Ram,
-            ));
-        } else {
-            mem_regions.push((
-                HIGH_RAM_START,
-                MEM_32BIT_RESERVED_START.0 as usize - HIGH_RAM_START.0 as usize,
-                RegionType::Ram,
-            ));
-            mem_regions.push((
-                RAM_64BIT_START,
-                mem_size - (MEM_32BIT_DEVICES_START.0 as usize),
-                RegionType::Ram,
-            ));
-        }
-        let mut bytes = vec![];
-        for (addr, size, region) in mem_regions.iter() {
-            let type_ = match region {
-                RegionType::Ram => E820_RAM,
-                RegionType::Reserved => E820_RESERVED,
-                RegionType::SubRegion => continue,
-            };
-            let mut entry = BootE820Entry {
-                addr: addr.0,
-                size: *size as u64,
-                type_,
-            };
-            bytes.extend_from_slice(entry.as_mut_bytes());
-        }
-        let item = FwCfgItem {
-            name: "etc/e820".to_owned(),
-            content: FwCfgContent::Bytes(bytes),
-        };
-        self.add_item(item)
-    }
-
-    fn file_dir_mut(&mut self) -> &mut Vec<u8> {
-        let FwCfgContent::Bytes(file_buf) = &mut self.known_items[FW_CFG_FILE_DIR as usize] else {
-            unreachable!("fw_cfg: selector {FW_CFG_FILE_DIR:#x} should be FwCfgContent::Byte!")
-        };
-        file_buf
-    }
-
-    fn update_count(&mut self) {
-        let mut header = FwCfgFilesHeader {
-            count_be: (self.items.len() as u32).to_be(),
-        };
-        self.file_dir_mut()[0..4].copy_from_slice(header.as_mut_bytes());
-    }
-
-    pub fn add_item(&mut self, item: FwCfgItem) -> Result<()> {
-        let index = self.items.len();
-        let c_name = create_file_name(&item.name);
-        let size = item.content.size()?;
-        let mut cfg_file = FwCfgFile {
-            size_be: size.to_be(),
-            select_be: (FW_CFG_FILE_FIRST + index as u16).to_be(),
-            _reserved: 0,
-            name: c_name,
-        };
-        self.file_dir_mut()
-            .extend_from_slice(cfg_file.as_mut_bytes());
-        self.items.push(item);
-        self.update_count();
-        Ok(())
-    }
-
-    fn dma_read_content(
-        &self,
-        content: &FwCfgContent,
-        offset: u32,
-        len: u32,
-        address: u64,
-    ) -> Result<u32> {
-        let content_size = content.size()?.saturating_sub(offset);
-        let op_size = std::cmp::min(content_size, len);
-        let mut access = content.access(offset);
-        let mut buf = vec![0u8; op_size as usize];
-        access.read_exact(buf.as_mut_bytes())?;
-        let r = self
-            .memory
-            .memory()
-            .write(buf.as_bytes(), GuestAddress(address));
-        match r {
-            Err(e) => {
-                error!("fw_cfg: dma read error: {e:x?}");
-                Err(ErrorKind::InvalidInput.into())
-            }
-            Ok(size) => Ok(size as u32),
-        }
-    }
-
-    fn dma_read(&mut self, selector: u16, len: u32, address: u64) -> Result<()> {
-        let op_size = if let Some(content) = self.known_items.get(selector as usize) {
-            self.dma_read_content(content, self.data_offset, len, address)
-        } else if let Some(item) = self.items.get((selector - FW_CFG_FILE_FIRST) as usize) {
-            self.dma_read_content(&item.content, self.data_offset, len, address)
-        } else {
-            error!("fw_cfg: selector {selector:#x} does not exist.");
-            Err(ErrorKind::NotFound.into())
-        }?;
-        self.data_offset += op_size;
-        Ok(())
-    }
-
-    fn do_dma(&mut self) {
-        let dma_address = self.dma_address;
-        let mut access = FwCfgDmaAccess::new_zeroed();
-        let dma_access = match self
-            .memory
-            .memory()
-            .read(access.as_mut_bytes(), GuestAddress(dma_address))
-        {
-            Ok(_) => access,
-            Err(e) => {
-                error!("fw_cfg: invalid address of dma access {dma_address:#x}: {e:?}");
-                return;
-            }
-        };
-        let control = AccessControl(u32::from_be(dma_access.control_be));
-        if control.select() {
-            self.selector = control.select() as u16;
-        }
-        let len = u32::from_be(dma_access.length_be);
-        let addr = u64::from_be(dma_access.address_be);
-        let ret = if control.read() {
-            self.dma_read(self.selector, len, addr)
-        } else if control.write() {
-            Err(ErrorKind::InvalidInput.into())
-        } else if control.skip() {
-            self.data_offset += len;
-            Ok(())
-        } else {
-            Err(ErrorKind::InvalidData.into())
-        };
-        let mut access_resp = AccessControl(0);
-        if let Err(e) = ret {
-            error!("fw_cfg: dma operation {dma_access:x?}: {e:x?}");
-            access_resp.set_error(true);
-        }
-        if let Err(e) = self.memory.memory().write(
-            &access_resp.0.to_be_bytes(),
-            GuestAddress(dma_address + core::mem::offset_of!(FwCfgDmaAccess, control_be) as u64),
-        ) {
-            error!("fw_cfg: finishing dma: {e:?}")
-        }
-    }
-
-    pub fn add_kernel_data(&mut self, file: &File) -> Result<()> {
-        let mut buffer = vec![0u8; size_of::<boot_params>()];
-        file.read_exact_at(&mut buffer, 0)?;
-        let bp = boot_params::from_mut_slice(&mut buffer).unwrap();
-        #[cfg(target_arch = "x86_64")]
-        {
-            // must set to 4 for backwards compatibility
-            // https://docs.kernel.org/arch/x86/boot.html#the-real-mode-kernel-header
-            if bp.hdr.setup_sects == 0 {
-                bp.hdr.setup_sects = 4;
-            }
-            // wildcard boot loader type
-            bp.hdr.type_of_loader = 0xff;
-        }
-        #[cfg(target_arch = "aarch64")]
-        let kernel_start = bp.text_offset;
-        #[cfg(target_arch = "x86_64")]
-        let kernel_start = (bp.hdr.setup_sects as usize + 1) * 512;
-        self.known_items[FW_CFG_SETUP_SIZE as usize] = FwCfgContent::U32(buffer.len() as u32);
-        self.known_items[FW_CFG_SETUP_DATA as usize] = FwCfgContent::Bytes(buffer);
-        self.known_items[FW_CFG_KERNEL_SIZE as usize] =
-            FwCfgContent::U32(file.metadata()?.len() as u32 - kernel_start as u32);
-        self.known_items[FW_CFG_KERNEL_DATA as usize] =
-            FwCfgContent::File(kernel_start as u64, file.try_clone()?);
-        Ok(())
-    }
-
-    pub fn add_kernel_cmdline(&mut self, s: std::ffi::CString) {
-        let bytes = s.into_bytes_with_nul();
-        self.known_items[FW_CFG_CMDLINE_SIZE as usize] = FwCfgContent::U32(bytes.len() as u32);
-        self.known_items[FW_CFG_CMDLINE_DATA as usize] = FwCfgContent::Bytes(bytes);
-    }
-
-    pub fn add_acpi(
-        &mut self,
-        rsdp: Rsdp,
-        tables: Vec<u8>,
-        table_checksums: Vec<(usize, usize)>,
-        table_pointers: Vec<usize>,
-    ) -> Result<()> {
-        let acpi_table = AcpiTable {
-            rsdp,
-            tables,
-            table_checksums,
-            table_pointers,
-        };
-        let [table_loader, acpi_rsdp, apci_tables] = create_acpi_loader(acpi_table);
-        self.add_item(table_loader)?;
-        self.add_item(acpi_rsdp)?;
-        self.add_item(apci_tables)
-    }
-
-    pub fn add_initramfs_data(&mut self, file: &File) -> Result<()> {
-        let initramfs_size = file.metadata()?.len();
-        self.known_items[FW_CFG_INITRD_SIZE as usize] = FwCfgContent::U32(initramfs_size as _);
-        self.known_items[FW_CFG_INITRD_DATA as usize] = FwCfgContent::File(0, file.try_clone()?);
-        Ok(())
-    }
-
-    fn read_content(content: &FwCfgContent, offset: u32, data: &mut [u8], size: u32) -> Option<u8> {
-        let start = offset as usize;
-        let end = start + size as usize;
-        match content {
-            FwCfgContent::Bytes(b) => {
-                if b.len() >= size as usize {
-                    data.copy_from_slice(&b[start..end]);
-                }
-            }
-            FwCfgContent::Slice(s) => {
-                if s.len() >= size as usize {
-                    data.copy_from_slice(&s[start..end]);
-                }
-            }
-            FwCfgContent::File(o, f) => {
-                f.read_exact_at(data, o + offset as u64).ok()?;
-            }
-            FwCfgContent::U32(n) => {
-                let bytes = n.to_le_bytes();
-                data.copy_from_slice(&bytes[start..end]);
-            }
-        };
-        Some(size as u8)
-    }
-
-    fn read_data(&mut self, data: &mut [u8], size: u32) -> u8 {
-        let ret = if let Some(content) = self.known_items.get(self.selector as usize) {
-            Self::read_content(content, self.data_offset, data, size)
-        } else if let Some(item) = self.items.get((self.selector - FW_CFG_FILE_FIRST) as usize) {
-            Self::read_content(&item.content, self.data_offset, data, size)
-        } else {
-            error!("fw_cfg: selector {:#x} does not exist.", self.selector);
-            None
-        };
-        if let Some(val) = ret {
-            self.data_offset += size;
-            val
-        } else {
-            0
-        }
-    }
-}
-
-impl BusDevice for FwCfg {
-    fn read(&mut self, _base: u64, offset: u64, data: &mut [u8]) {
-        let port = offset + PORT_FW_CFG_BASE;
-        let size = data.len();
-        match (port, size) {
-            (PORT_FW_CFG_SELECTOR, _) => {
-                error!("fw_cfg: selector register is write-only.");
-            }
-            (PORT_FW_CFG_DATA, _) => _ = self.read_data(data, size as u32),
-            (PORT_FW_CFG_DMA_HI, 4) => {
-                let addr = self.dma_address;
-                let addr_hi = (addr >> 32) as u32;
-                data.copy_from_slice(&addr_hi.to_be_bytes());
-            }
-            (PORT_FW_CFG_DMA_LO, 4) => {
-                let addr = self.dma_address;
-                let addr_lo = (addr & 0xffff_ffff) as u32;
-                data.copy_from_slice(&addr_lo.to_be_bytes());
-            }
-            _ => {
-                debug!(
-                    "fw_cfg: read from unknown port {port:#x}: {size:#x} bytes and offset {offset:#x}."
-                );
-            }
-        };
-    }
-
-    fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
-        let port = offset + PORT_FW_CFG_BASE;
-        let size = data.size();
-        match (port, size) {
-            (PORT_FW_CFG_SELECTOR, 2) => {
-                let mut buf = [0u8; 2];
-                buf[..size].copy_from_slice(&data[..size]);
-                #[cfg(target_arch = "x86_64")]
-                let val = u16::from_le_bytes(buf);
-                #[cfg(target_arch = "aarch64")]
-                let val = u16::from_be_bytes(buf);
-                self.selector = val;
-                self.data_offset = 0;
-            }
-            (PORT_FW_CFG_DATA, 1) => error!("fw_cfg: data register is read-only."),
-            (PORT_FW_CFG_DMA_HI, 4) => {
-                let mut buf = [0u8; 4];
-                buf[..size].copy_from_slice(&data[..size]);
-                let val = u32::from_be_bytes(buf);
-                self.dma_address &= 0xffff_ffff;
-                self.dma_address |= (val as u64) << 32;
-            }
-            (PORT_FW_CFG_DMA_LO, 4) => {
-                let mut buf = [0u8; 4];
-                buf[..size].copy_from_slice(&data[..size]);
-                let val = u32::from_be_bytes(buf);
-                self.dma_address &= !0xffff_ffff;
-                self.dma_address |= val as u64;
-                self.do_dma();
-            }
-            _ => debug!(
-                "fw_cfg: write to unknown port {port:#x}: {size:#x} bytes and offset {offset:#x} ."
-            ),
-        };
-        None
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use std::ffi::CString;
-    use std::io::Write;
-
-    use vmm_sys_util::tempfile::TempFile;
-
-    use super::*;
-
-    #[cfg(target_arch = "x86_64")]
-    const SELECTOR_OFFSET: u64 = 0;
-    #[cfg(target_arch = "aarch64")]
-    const SELECTOR_OFFSET: u64 = 8;
-    #[cfg(target_arch = "x86_64")]
-    const DATA_OFFSET: u64 = 1;
-    #[cfg(target_arch = "aarch64")]
-    const DATA_OFFSET: u64 = 0;
-    #[cfg(target_arch = "x86_64")]
-    const DMA_OFFSET: u64 = 4;
-    #[cfg(target_arch = "aarch64")]
-    const DMA_OFFSET: u64 = 16;
-
-    #[test]
-    fn test_signature() {
-        let gm = GuestMemoryAtomic::new(
-            GuestMemoryMmap::from_ranges(&[(GuestAddress(0), RAM_64BIT_START.0 as usize)]).unwrap(),
-        );
-
-        let mut fw_cfg = FwCfg::new(gm);
-
-        let mut data = vec![0u8];
-
-        let mut sig_iter = FW_CFG_DMA_SIGNATURE.into_iter();
-        fw_cfg.write(0, SELECTOR_OFFSET, &[FW_CFG_SIGNATURE as u8, 0]);
-        loop {
-            if let Some(char) = sig_iter.next() {
-                fw_cfg.read(0, DATA_OFFSET, &mut data);
-                assert_eq!(data[0], char);
-            } else {
-                return;
-            }
-        }
-    }
-    #[test]
-    fn test_kernel_cmdline() {
-        let gm = GuestMemoryAtomic::new(
-            GuestMemoryMmap::from_ranges(&[(GuestAddress(0), RAM_64BIT_START.0 as usize)]).unwrap(),
-        );
-
-        let mut fw_cfg = FwCfg::new(gm);
-
-        let cmdline = *b"cmdline\0";
-
-        fw_cfg.add_kernel_cmdline(CString::from_vec_with_nul(cmdline.to_vec()).unwrap());
-
-        let mut data = vec![0u8];
-
-        let mut cmdline_iter = cmdline.into_iter();
-        fw_cfg.write(0, SELECTOR_OFFSET, &[FW_CFG_CMDLINE_DATA as u8, 0]);
-        loop {
-            if let Some(char) = cmdline_iter.next() {
-                fw_cfg.read(0, DATA_OFFSET, &mut data);
-                assert_eq!(data[0], char);
-            } else {
-                return;
-            }
-        }
-    }
-
-    #[test]
-    fn test_initram_fs() {
-        let gm = GuestMemoryAtomic::new(
-            GuestMemoryMmap::from_ranges(&[(GuestAddress(0), RAM_64BIT_START.0 as usize)]).unwrap(),
-        );
-
-        let mut fw_cfg = FwCfg::new(gm);
-
-        let temp = TempFile::new().unwrap();
-        let mut temp_file = temp.as_file();
-
-        let initram_content = b"this is the initramfs";
-        let written = temp_file.write(initram_content);
-        assert_eq!(written.unwrap(), 21);
-        let _ = fw_cfg.add_initramfs_data(temp_file);
-
-        let mut data = vec![0u8];
-
-        let mut initram_iter = (*initram_content).into_iter();
-        fw_cfg.write(0, SELECTOR_OFFSET, &[FW_CFG_INITRD_DATA as u8, 0]);
-        loop {
-            if let Some(char) = initram_iter.next() {
-                fw_cfg.read(0, DATA_OFFSET, &mut data);
-                assert_eq!(data[0], char);
-            } else {
-                return;
-            }
-        }
-    }
-
-    #[test]
-    fn test_dma() {
-        let code = [
-            0xba, 0xf8, 0x03, 0x00, 0xd8, 0x04, b'0', 0xee, 0xb0, b'\n', 0xee, 0xf4,
-        ];
-
-        let content = FwCfgContent::Bytes(code.to_vec());
-
-        let mem_size = 0x1000;
-        let load_addr = GuestAddress(0x1000);
-        let mem: GuestMemoryMmap<AtomicBitmap> =
-            GuestMemoryMmap::from_ranges(&[(load_addr, mem_size)]).unwrap();
-
-        // Note: In firmware we would just allocate FwCfgDmaAccess struct
-        // and use address of struct (&) as dma address
-        let mut access_control = AccessControl(0);
-        // bit 1 = read access
-        access_control.set_read(true);
-        // length of data to access
-        let length_be = (code.len() as u32).to_be();
-        // guest address for data
-        let code_address = 0x1900_u64;
-        let address_be = code_address.to_be();
-        let mut access = FwCfgDmaAccess {
-            control_be: access_control.0.to_be(), // bit(1) = read bit
-            length_be,
-            address_be,
-        };
-        // access address is where to put the code
-        let access_address = GuestAddress(load_addr.0);
-        let address_bytes = access_address.0.to_be_bytes();
-        let dma_lo: [u8; 4] = address_bytes[0..4].try_into().unwrap();
-        let dma_hi: [u8; 4] = address_bytes[4..8].try_into().unwrap();
-
-        // writing the FwCfgDmaAccess to mem (this would just be self.dma_access.as_ref() in guest)
-        let _ = mem.write(access.as_mut_bytes(), access_address);
-        let mem_m = GuestMemoryAtomic::new(mem.clone());
-        let mut fw_cfg = FwCfg::new(mem_m);
-        let cfg_item = FwCfgItem {
-            name: "code".to_string(),
-            content,
-        };
-        let _ = fw_cfg.add_item(cfg_item);
-
-        let mut data = [0u8; 12];
-
-        let _ = mem.read(&mut data, GuestAddress(code_address));
-        assert_ne!(data, code);
-
-        fw_cfg.write(0, SELECTOR_OFFSET, &[FW_CFG_FILE_FIRST as u8, 0]);
-        fw_cfg.write(0, DMA_OFFSET, &dma_lo);
-        fw_cfg.write(0, DMA_OFFSET + 4, &dma_hi);
-        let _ = mem.read(&mut data, GuestAddress(code_address));
-        assert_eq!(data, code);
-    }
-}

devices/src/legacy/fwdebug.rs

@@ -8,7 +8,6 @@
 //
 
 use std::sync::{Arc, Barrier};
-
 use vm_device::BusDevice;
 
 /// Provides firmware debug output via I/O port controls

devices/src/legacy/gpio_pl061.rs

@@ -7,16 +7,17 @@
 //! This module implements an ARM PrimeCell General Purpose Input/Output(PL061) to support gracefully poweroff microvm from external.
 //!
 
-use std::sync::{Arc, Barrier};
-use std::{io, result};
-
-use serde::{Deserialize, Serialize};
-use thiserror::Error;
-use vm_device::BusDevice;
-use vm_device::interrupt::InterruptSourceGroup;
-use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
-
 use crate::{read_le_u32, write_le_u32};
+use std::result;
+use std::sync::{Arc, Barrier};
+use std::{fmt, io};
+use versionize::{VersionMap, Versionize, VersionizeResult};
+use versionize_derive::Versionize;
+use vm_device::interrupt::InterruptSourceGroup;
+use vm_device::BusDevice;
+use vm_migration::{
+    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
+};
 
 const OFS_DATA: u64 = 0x400; // Data Register
 const GPIODIR: u64 = 0x400; // Direction Register
@@ -28,10 +29,10 @@ const GPIORIE: u64 = 0x414; // Raw Interrupt Status Register
 const GPIOMIS: u64 = 0x418; // Masked Interrupt Status Register
 const GPIOIC: u64 = 0x41c; // Interrupt Clear Register
 const GPIOAFSEL: u64 = 0x420; // Mode Control Select Register
-// From 0x424 to 0xFDC => reserved space.
-// From 0xFE0 to 0xFFC => Peripheral and PrimeCell Identification Registers which are Read Only registers.
-// These registers can conceptually be treated as a 32-bit register, and PartNumber[11:0] is used to identify the peripheral.
-// We are putting the expected values (look at 'Reset value' column from above mentioned document) in an array.
+                              // From 0x424 to 0xFDC => reserved space.
+                              // From 0xFE0 to 0xFFC => Peripheral and PrimeCell Identification Registers which are Read Only registers.
+                              // Thses registers can conceptually be treated as a 32-bit register, and PartNumber[11:0] is used to identify the peripheral.
+                              // We are putting the expected values (look at 'Reset value' column from above mentioned document) in an array.
 const GPIO_ID: [u8; 8] = [0x61, 0x10, 0x14, 0x00, 0x0d, 0xf0, 0x05, 0xb1];
 // ID Margins
 const GPIO_ID_LOW: u64 = 0xfe0;
@@ -39,18 +40,29 @@ const GPIO_ID_HIGH: u64 = 0x1000;
 
 const N_GPIOS: u32 = 8;
 
-#[derive(Debug, Error)]
+#[derive(Debug)]
 pub enum Error {
-    #[error("Bad Write Offset: {0}")]
     BadWriteOffset(u64),
-    #[error("GPIO interrupt disabled by guest driver")]
     GpioInterruptDisabled,
-    #[error("Could not trigger GPIO interrupt")]
-    GpioInterruptFailure(#[source] io::Error),
-    #[error("Invalid GPIO Input key triggered: {0}")]
+    GpioInterruptFailure(io::Error),
     GpioTriggerKeyFailure(u32),
 }
 
+impl fmt::Display for Error {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        match self {
+            Error::BadWriteOffset(offset) => write!(f, "Bad Write Offset: {offset}"),
+            Error::GpioInterruptDisabled => write!(f, "GPIO interrupt disabled by guest driver.",),
+            Error::GpioInterruptFailure(ref e) => {
+                write!(f, "Could not trigger GPIO interrupt: {e}.")
+            }
+            Error::GpioTriggerKeyFailure(key) => {
+                write!(f, "Invalid GPIO Input key triggerd: {key}.")
+            }
+        }
+    }
+}
+
 type Result<T> = result::Result<T, Error>;
 
 /// A GPIO device following the PL061 specification.
@@ -77,7 +89,7 @@ pub struct Gpio {
     interrupt: Arc<dyn InterruptSourceGroup>,
 }
 
-#[derive(Serialize, Deserialize)]
+#[derive(Versionize)]
 pub struct GpioState {
     data: u32,
     old_in_data: u32,
@@ -90,6 +102,8 @@ pub struct GpioState {
     afsel: u32,
 }
 
+impl VersionMapped for GpioState {}
+
 impl Gpio {
     /// Constructs an PL061 GPIO device.
     pub fn new(
@@ -314,7 +328,7 @@ impl Snapshottable for Gpio {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        Snapshot::new_from_state(&self.state())
+        Snapshot::new_from_versioned_state(&self.state())
     }
 }
 
@@ -324,11 +338,12 @@ impl Migratable for Gpio {}
 
 #[cfg(test)]
 mod tests {
+    use super::*;
+    use crate::{read_le_u32, write_le_u32};
+    use std::sync::Arc;
     use vm_device::interrupt::{InterruptIndex, InterruptSourceConfig};
     use vmm_sys_util::eventfd::EventFd;
 
-    use super::*;
-
     const GPIO_NAME: &str = "gpio";
     const LEGACY_GPIO_MAPPED_IO_START: u64 = 0x0902_0000;
 
@@ -346,15 +361,10 @@ mod tests {
             _index: InterruptIndex,
             _config: InterruptSourceConfig,
             _masked: bool,
-            _set_gsi: bool,
         ) -> result::Result<(), std::io::Error> {
             Ok(())
         }
 
-        fn set_gsi(&self) -> result::Result<(), std::io::Error> {
-            Ok(())
-        }
-
         fn notifier(&self, _index: InterruptIndex) -> Option<EventFd> {
             Some(self.event_fd.try_clone().unwrap())
         }

devices/src/legacy/i8042.rs

@@ -1,29 +1,20 @@
 // Copyright 2017 The Chromium OS Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE-BSD-3-Clause file.
-//
-// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
-use std::sync::atomic::{AtomicBool, Ordering};
 use std::sync::{Arc, Barrier};
-use std::thread;
-
 use vm_device::BusDevice;
 use vmm_sys_util::eventfd::EventFd;
 
 /// A i8042 PS/2 controller that emulates just enough to shutdown the machine.
 pub struct I8042Device {
     reset_evt: EventFd,
-    vcpus_kill_signalled: Arc<AtomicBool>,
 }
 
 impl I8042Device {
     /// Constructs a i8042 device that will signal the given event when the guest requests it.
-    pub fn new(reset_evt: EventFd, vcpus_kill_signalled: Arc<AtomicBool>) -> I8042Device {
-        I8042Device {
-            reset_evt,
-            vcpus_kill_signalled,
-        }
+    pub fn new(reset_evt: EventFd) -> I8042Device {
+        I8042Device { reset_evt }
     }
 }
 
@@ -47,13 +38,6 @@ impl BusDevice for I8042Device {
             if let Err(e) = self.reset_evt.write(1) {
                 error!("Error triggering i8042 reset event: {}", e);
             }
-            // Spin until we are sure the reset_evt has been handled and that when
-            // we return from the KVM_RUN we will exit rather than re-enter the guest.
-            while !self.vcpus_kill_signalled.load(Ordering::SeqCst) {
-                // This is more effective than thread::yield_now() at
-                // avoiding a priority inversion with the VMM thread
-                thread::sleep(std::time::Duration::from_millis(1));
-            }
         }
 
         None

devices/src/legacy/mod.rs

@@ -8,8 +8,6 @@
 mod cmos;
 #[cfg(target_arch = "x86_64")]
 mod debug_port;
-#[cfg(feature = "fw_cfg")]
-pub mod fw_cfg;
 #[cfg(target_arch = "x86_64")]
 mod fwdebug;
 #[cfg(target_arch = "aarch64")]
@@ -24,17 +22,16 @@ mod uart_pl011;
 pub use self::cmos::Cmos;
 #[cfg(target_arch = "x86_64")]
 pub use self::debug_port::DebugPort;
-#[cfg(feature = "fw_cfg")]
-pub use self::fw_cfg::FwCfg;
 #[cfg(target_arch = "x86_64")]
 pub use self::fwdebug::FwDebugDevice;
+pub use self::i8042::I8042Device;
+pub use self::serial::Serial;
+
 #[cfg(target_arch = "aarch64")]
 pub use self::gpio_pl061::Error as GpioDeviceError;
 #[cfg(target_arch = "aarch64")]
 pub use self::gpio_pl061::Gpio;
-pub use self::i8042::I8042Device;
 #[cfg(target_arch = "aarch64")]
 pub use self::rtc_pl031::Rtc;
-pub use self::serial::Serial;
 #[cfg(target_arch = "aarch64")]
 pub use self::uart_pl011::Pl011;

devices/src/legacy/rtc_pl031.rs

@@ -4,22 +4,18 @@
 
 //! ARM PL031 Real Time Clock
 //!
-//! This module implements part of a PL031 Real Time Clock (RTC):
-//! * provide a clock value via RTCDR
-//! * no alarm is implemented through the match register
-//! * no interrupt is generated
-//! * RTC cannot be disabled via RTCCR
-//! * no test registers
+//! This module implements a PL031 Real Time Clock (RTC) that provides to provides long time base counter.
+//! This is achieved by generating an interrupt signal after counting for a programmed number of cycles of
+//! a real-time clock input.
 //!
-use std::result;
+use crate::{read_le_u32, write_le_u32};
+use std::fmt;
 use std::sync::{Arc, Barrier};
 use std::time::Instant;
-
-use thiserror::Error;
+use std::{io, result};
+use vm_device::interrupt::InterruptSourceGroup;
 use vm_device::BusDevice;
 
-use crate::{read_le_u32, write_le_u32};
-
 // As you can see in https://static.docs.arm.com/ddi0224/c/real_time_clock_pl031_r1p3_technical_reference_manual_DDI0224C.pdf
 // at section 3.2 Summary of RTC registers, the total size occupied by this device is 0x000 -> 0xFFC + 4 = 0x1000.
 // From 0x0 to 0x1C we have following registers:
@@ -31,11 +27,11 @@ const RTCIMSC: u64 = 0x10; // Interrupt Mask Set or Clear Register.
 const RTCRIS: u64 = 0x14; // Raw Interrupt Status.
 const RTCMIS: u64 = 0x18; // Masked Interrupt Status.
 const RTCICR: u64 = 0x1c; // Interrupt Clear Register.
-// From 0x020 to 0xFDC => reserved space.
-// From 0xFE0 to 0x1000 => Peripheral and PrimeCell Identification Registers which are Read Only registers.
-// AMBA standard devices have CIDs (Cell IDs) and PIDs (Peripheral IDs). The linux kernel will look for these in order to assert the identity
-// of these devices (i.e look at the `amba_device_try_add` function).
-// We are putting the expected values (look at 'Reset value' column from above mentioned document) in an array.
+                          // From 0x020 to 0xFDC => reserved space.
+                          // From 0xFE0 to 0x1000 => Peripheral and PrimeCell Identification Registers which are Read Only registers.
+                          // AMBA standard devices have CIDs (Cell IDs) and PIDs (Peripheral IDs). The linux kernel will look for these in order to assert the identity
+                          // of these devices (i.e look at the `amba_device_try_add` function).
+                          // We are putting the expected values (look at 'Reset value' column from above mentioned document) in an array.
 const PL031_ID: [u8; 8] = [0x31, 0x10, 0x14, 0x00, 0x0d, 0xf0, 0x05, 0xb1];
 // We are only interested in the margins.
 const AMBA_ID_LOW: u64 = 0xFE0;
@@ -43,10 +39,19 @@ const AMBA_ID_HIGH: u64 = 0x1000;
 /// Constant to convert seconds to nanoseconds.
 pub const NANOS_PER_SECOND: u64 = 1_000_000_000;
 
-#[derive(Debug, Error)]
+#[derive(Debug)]
 pub enum Error {
-    #[error("Bad Write Offset: {0}")]
     BadWriteOffset(u64),
+    InterruptFailure(io::Error),
+}
+
+impl fmt::Display for Error {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        match self {
+            Error::BadWriteOffset(offset) => write!(f, "Bad Write Offset: {offset}"),
+            Error::InterruptFailure(e) => write!(f, "Failed to trigger interrupt: {e}"),
+        }
+    }
 }
 
 type Result<T> = result::Result<T, Error>;
@@ -74,6 +79,98 @@ impl From<ClockType> for libc::clockid_t {
     }
 }
 
+/// Structure representing the date in local time with nanosecond precision.
+pub struct LocalTime {
+    /// Seconds in current minute.
+    sec: i32,
+    /// Minutes in current hour.
+    min: i32,
+    /// Hours in current day, 24H format.
+    hour: i32,
+    /// Days in current month.
+    mday: i32,
+    /// Months in current year.
+    mon: i32,
+    /// Years passed since 1900 BC.
+    year: i32,
+    /// Nanoseconds in current second.
+    nsec: i64,
+}
+
+impl LocalTime {
+    /// Returns the [LocalTime](struct.LocalTime.html) structure for the calling moment.
+    #[cfg(test)]
+    pub fn now() -> LocalTime {
+        let mut timespec = libc::timespec {
+            tv_sec: 0,
+            tv_nsec: 0,
+        };
+        let mut tm: libc::tm = libc::tm {
+            tm_sec: 0,
+            tm_min: 0,
+            tm_hour: 0,
+            tm_mday: 0,
+            tm_mon: 0,
+            tm_year: 0,
+            tm_wday: 0,
+            tm_yday: 0,
+            tm_isdst: 0,
+            tm_gmtoff: 0,
+            tm_zone: std::ptr::null(),
+        };
+
+        // SAFETY: the parameters are valid.
+        unsafe {
+            libc::clock_gettime(libc::CLOCK_REALTIME, &mut timespec);
+            libc::localtime_r(&timespec.tv_sec, &mut tm);
+        }
+
+        LocalTime {
+            sec: tm.tm_sec,
+            min: tm.tm_min,
+            hour: tm.tm_hour,
+            mday: tm.tm_mday,
+            mon: tm.tm_mon,
+            year: tm.tm_year,
+            nsec: timespec.tv_nsec,
+        }
+    }
+}
+
+impl fmt::Display for LocalTime {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        write!(
+            f,
+            "{}-{:02}-{:02}T{:02}:{:02}:{:02}.{:09}",
+            self.year + 1900,
+            self.mon + 1,
+            self.mday,
+            self.hour,
+            self.min,
+            self.sec,
+            self.nsec
+        )
+    }
+}
+
+/// Holds a micro-second resolution timestamp with both the real time and cpu time.
+#[derive(Clone)]
+pub struct TimestampUs {
+    /// Real time in microseconds.
+    pub time_us: u64,
+    /// Cpu time in microseconds.
+    pub cputime_us: u64,
+}
+
+impl Default for TimestampUs {
+    fn default() -> TimestampUs {
+        TimestampUs {
+            time_us: get_time(ClockType::Monotonic) / 1000,
+            cputime_us: get_time(ClockType::ProcessCpu) / 1000,
+        }
+    }
+}
+
 /// Returns a timestamp in nanoseconds based on the provided clock type.
 ///
 /// # Arguments
@@ -107,20 +204,31 @@ pub struct Rtc {
     match_value: u32,
     // Writes to this register load an update value into the RTC.
     load: u32,
+    imsc: u32,
+    ris: u32,
+    interrupt: Arc<dyn InterruptSourceGroup>,
 }
 
 impl Rtc {
     /// Constructs an AMBA PL031 RTC device.
-    pub fn new() -> Self {
+    pub fn new(interrupt: Arc<dyn InterruptSourceGroup>) -> Self {
         Self {
             // This is used only for duration measuring purposes.
             previous_now: Instant::now(),
             tick_offset: get_time(ClockType::Real) as i64,
             match_value: 0,
             load: 0,
+            imsc: 0,
+            ris: 0,
+            interrupt,
         }
     }
 
+    fn trigger_interrupt(&mut self) -> Result<()> {
+        self.interrupt.trigger(0).map_err(Error::InterruptFailure)?;
+        Ok(())
+    }
+
     fn get_time(&self) -> u32 {
         let ts = (self.tick_offset as i128)
             + (Instant::now().duration_since(self.previous_now).as_nanos() as i128);
@@ -144,8 +252,16 @@ impl Rtc {
                 // we want to terminate the execution of the process.
                 self.tick_offset = seconds_to_nanoseconds(i64::from(val)).unwrap();
             }
-            RTCIMSC => (),
-            RTCICR => (),
+            RTCIMSC => {
+                self.imsc = val & 1;
+                self.trigger_interrupt()?;
+            }
+            RTCICR => {
+                // As per above mentioned doc, the interrupt is cleared by writing any data value to
+                // the Interrupt Clear Register.
+                self.ris = 0;
+                self.trigger_interrupt()?;
+            }
             RTCCR => (), // ignore attempts to turn off the timer.
             o => {
                 return Err(Error::BadWriteOffset(o));
@@ -155,12 +271,6 @@ impl Rtc {
     }
 }
 
-impl Default for Rtc {
-    fn default() -> Self {
-        Self::new()
-    }
-}
-
 impl BusDevice for Rtc {
     fn read(&mut self, _base: u64, offset: u64, data: &mut [u8]) {
         let mut read_ok = true;
@@ -176,10 +286,10 @@ impl BusDevice for Rtc {
                     self.match_value
                 }
                 RTCLR => self.load,
-                RTCCR => 1,   // RTC is always enabled.
-                RTCIMSC => 0, // Interrupt is always disabled.
-                RTCRIS => 0,
-                RTCMIS => 0,
+                RTCCR => 1, // RTC is always enabled.
+                RTCIMSC => self.imsc,
+                RTCRIS => self.ris,
+                RTCMIS => self.ris & self.imsc,
                 _ => {
                     read_ok = false;
                     0
@@ -219,76 +329,15 @@ impl BusDevice for Rtc {
 mod tests {
     use super::*;
     use crate::{
-        read_be_u16, read_be_u32, read_le_i32, read_le_u16, read_le_u64, write_be_u16,
-        write_be_u32, write_le_i32, write_le_u16, write_le_u64,
+        read_be_u16, read_be_u32, read_le_i32, read_le_u16, read_le_u32, read_le_u64, write_be_u16,
+        write_be_u32, write_le_i32, write_le_u16, write_le_u32, write_le_u64,
     };
+    use std::sync::Arc;
+    use vm_device::interrupt::{InterruptIndex, InterruptSourceConfig};
+    use vmm_sys_util::eventfd::EventFd;
 
     const LEGACY_RTC_MAPPED_IO_START: u64 = 0x0901_0000;
 
-    struct LocalTime {
-        sec: i32,
-        min: i32,
-        hour: i32,
-        mday: i32,
-        mon: i32,
-        year: i32,
-        nsec: i64,
-    }
-
-    impl LocalTime {
-        fn now() -> LocalTime {
-            let mut timespec = libc::timespec {
-                tv_sec: 0,
-                tv_nsec: 0,
-            };
-            let mut tm: libc::tm = libc::tm {
-                tm_sec: 0,
-                tm_min: 0,
-                tm_hour: 0,
-                tm_mday: 0,
-                tm_mon: 0,
-                tm_year: 0,
-                tm_wday: 0,
-                tm_yday: 0,
-                tm_isdst: 0,
-                tm_gmtoff: 0,
-                tm_zone: std::ptr::null(),
-            };
-
-            // SAFETY: the parameters are valid.
-            unsafe {
-                libc::clock_gettime(libc::CLOCK_REALTIME, &mut timespec);
-                libc::localtime_r(&timespec.tv_sec, &mut tm);
-            }
-
-            LocalTime {
-                sec: tm.tm_sec,
-                min: tm.tm_min,
-                hour: tm.tm_hour,
-                mday: tm.tm_mday,
-                mon: tm.tm_mon,
-                year: tm.tm_year,
-                nsec: timespec.tv_nsec,
-            }
-        }
-    }
-
-    impl std::fmt::Display for LocalTime {
-        fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-            write!(
-                f,
-                "{}-{:02}-{:02}T{:02}:{:02}:{:02}.{:09}",
-                self.year + 1900,
-                self.mon + 1,
-                self.mday,
-                self.hour,
-                self.min,
-                self.sec,
-                self.nsec
-            )
-        }
-    }
-
     #[test]
     fn test_get_time() {
         for _ in 0..1000 {
@@ -350,9 +399,40 @@ mod tests {
         assert!(seconds_to_nanoseconds(9_223_372_037).is_none());
     }
 
+    struct TestInterrupt {
+        event_fd: EventFd,
+    }
+
+    impl InterruptSourceGroup for TestInterrupt {
+        fn trigger(&self, _index: InterruptIndex) -> result::Result<(), std::io::Error> {
+            self.event_fd.write(1)
+        }
+
+        fn update(
+            &self,
+            _index: InterruptIndex,
+            _config: InterruptSourceConfig,
+            _masked: bool,
+        ) -> result::Result<(), std::io::Error> {
+            Ok(())
+        }
+
+        fn notifier(&self, _index: InterruptIndex) -> Option<EventFd> {
+            Some(self.event_fd.try_clone().unwrap())
+        }
+    }
+
+    impl TestInterrupt {
+        fn new(event_fd: EventFd) -> Self {
+            TestInterrupt { event_fd }
+        }
+    }
+
     #[test]
     fn test_rtc_read_write_and_event() {
-        let mut rtc = Rtc::new();
+        let intr_evt = EventFd::new(libc::EFD_NONBLOCK).unwrap();
+
+        let mut rtc = Rtc::new(Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())));
         let mut data = [0; 4];
 
         // Read and write to the MR register.
@@ -375,13 +455,15 @@ mod tests {
         assert_eq!((v / NANOS_PER_SECOND) as u32, v_read);
 
         // Read and write to IMSC register.
-        // Test with non zero value. Our device ignores the write.
+        // Test with non zero value.
         let non_zero = 1;
         write_le_u32(&mut data, non_zero);
         rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCIMSC, &data);
+        // The interrupt line should be on.
+        assert!(rtc.interrupt.notifier(0).unwrap().read().unwrap() == 1);
         rtc.read(LEGACY_RTC_MAPPED_IO_START, RTCIMSC, &mut data);
         let v = read_le_u32(&data);
-        assert_eq!(0, v);
+        assert_eq!(non_zero & 1, v);
 
         // Now test with 0.
         write_le_u32(&mut data, 0);
@@ -393,6 +475,8 @@ mod tests {
         // Read and write to the ICR register.
         write_le_u32(&mut data, 1);
         rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCICR, &data);
+        // The interrupt line should be on.
+        assert!(rtc.interrupt.notifier(0).unwrap().read().unwrap() > 1);
         let v_before = read_le_u32(&data);
 
         rtc.read(LEGACY_RTC_MAPPED_IO_START, RTCICR, &mut data);

devices/src/legacy/serial.rs

@@ -8,11 +8,13 @@
 use std::collections::VecDeque;
 use std::sync::{Arc, Barrier};
 use std::{io, result};
-
-use serde::{Deserialize, Serialize};
-use vm_device::BusDevice;
+use versionize::{VersionMap, Versionize, VersionizeResult};
+use versionize_derive::Versionize;
 use vm_device::interrupt::InterruptSourceGroup;
-use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
+use vm_device::BusDevice;
+use vm_migration::{
+    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
+};
 use vmm_sys_util::errno::Result;
 
 const LOOP_SIZE: usize = 0x40;
@@ -72,7 +74,7 @@ pub struct Serial {
     out: Option<Box<dyn io::Write + Send>>,
 }
 
-#[derive(Serialize, Deserialize)]
+#[derive(Versionize)]
 pub struct SerialState {
     interrupt_enable: u8,
     interrupt_identification: u8,
@@ -84,6 +86,7 @@ pub struct SerialState {
     baud_divisor: u16,
     in_buffer: Vec<u8>,
 }
+impl VersionMapped for SerialState {}
 
 impl Serial {
     pub fn new(
@@ -163,8 +166,8 @@ impl Serial {
         Self::new(id, interrupt, None, state)
     }
 
-    pub fn set_out(&mut self, out: Option<Box<dyn io::Write + Send>>) {
-        self.out = out;
+    pub fn set_out(&mut self, out: Box<dyn io::Write + Send>) {
+        self.out = Some(out);
     }
 
     /// Queues raw bytes for the guest to read and signals the interrupt if the line status would
@@ -331,7 +334,7 @@ impl Snapshottable for Serial {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        Snapshot::new_from_state(&self.state())
+        Snapshot::new_from_versioned_state(&self.state())
     }
 }
 
@@ -341,13 +344,12 @@ impl Migratable for Serial {}
 
 #[cfg(test)]
 mod tests {
-    use std::sync::Mutex;
-
+    use super::*;
+    use std::io;
+    use std::sync::{Arc, Mutex};
     use vm_device::interrupt::{InterruptIndex, InterruptSourceConfig};
     use vmm_sys_util::eventfd::EventFd;
 
-    use super::*;
-
     const SERIAL_NAME: &str = "serial";
 
     struct TestInterrupt {
@@ -363,13 +365,9 @@ mod tests {
             _index: InterruptIndex,
             _config: InterruptSourceConfig,
             _masked: bool,
-            _set_gsi: bool,
         ) -> result::Result<(), std::io::Error> {
             Ok(())
         }
-        fn set_gsi(&self) -> result::Result<(), std::io::Error> {
-            Ok(())
-        }
         fn notifier(&self, _index: InterruptIndex) -> Option<EventFd> {
             Some(self.event_fd.try_clone().unwrap())
         }
@@ -414,11 +412,14 @@ mod tests {
             None,
         );
 
-        serial.write(0, DATA as u64, b"xy");
-        serial.write(0, DATA as u64, b"a");
-        serial.write(0, DATA as u64, b"b");
-        serial.write(0, DATA as u64, b"c");
-        assert_eq!(serial_out.buf.lock().unwrap().as_slice(), b"abc");
+        serial.write(0, DATA as u64, &[b'x', b'y']);
+        serial.write(0, DATA as u64, &[b'a']);
+        serial.write(0, DATA as u64, &[b'b']);
+        serial.write(0, DATA as u64, &[b'c']);
+        assert_eq!(
+            serial_out.buf.lock().unwrap().as_slice(),
+            &[b'a', b'b', b'c']
+        );
     }
 
     #[test]
@@ -434,9 +435,9 @@ mod tests {
 
         // write 1 to the interrupt event fd, so that read doesn't block in case the event fd
         // counter doesn't change (for 0 it blocks)
-        intr_evt.write(1).unwrap();
+        assert!(intr_evt.write(1).is_ok());
         serial.write(0, IER as u64, &[IER_RECV_BIT]);
-        serial.queue_input_bytes(b"abc").unwrap();
+        serial.queue_input_bytes(&[b'a', b'b', b'c']).unwrap();
 
         assert_eq!(intr_evt.read().unwrap(), 2);
 
@@ -471,9 +472,9 @@ mod tests {
 
         // write 1 to the interrupt event fd, so that read doesn't block in case the event fd
         // counter doesn't change (for 0 it blocks)
-        intr_evt.write(1).unwrap();
+        assert!(intr_evt.write(1).is_ok());
         serial.write(0, IER as u64, &[IER_THR_BIT]);
-        serial.write(0, DATA as u64, b"a");
+        serial.write(0, DATA as u64, &[b'a']);
 
         assert_eq!(intr_evt.read().unwrap(), 2);
         let mut data = [0u8];
@@ -515,9 +516,9 @@ mod tests {
         );
 
         serial.write(0, MCR as u64, &[MCR_LOOP_BIT]);
-        serial.write(0, DATA as u64, b"a");
-        serial.write(0, DATA as u64, b"b");
-        serial.write(0, DATA as u64, b"c");
+        serial.write(0, DATA as u64, &[b'a']);
+        serial.write(0, DATA as u64, &[b'b']);
+        serial.write(0, DATA as u64, &[b'c']);
 
         let mut data = [0u8];
         serial.read(0, MSR as u64, &mut data[..]);

devices/src/legacy/uart_pl011.rs

@@ -6,18 +6,19 @@
 //! This module implements an ARM PrimeCell UART(PL011).
 //!
 
+use crate::{read_le_u32, write_le_u32};
 use std::collections::VecDeque;
+use std::fmt;
 use std::sync::{Arc, Barrier};
 use std::time::Instant;
 use std::{io, result};
-
-use serde::{Deserialize, Serialize};
-use thiserror::Error;
-use vm_device::BusDevice;
+use versionize::{VersionMap, Versionize, VersionizeResult};
+use versionize_derive::Versionize;
 use vm_device::interrupt::InterruptSourceGroup;
-use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
-
-use crate::{read_le_u32, write_le_u32};
+use vm_device::BusDevice;
+use vm_migration::{
+    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
+};
 
 /* Registers */
 const UARTDR: u64 = 0;
@@ -47,18 +48,25 @@ const PL011_ID: [u8; 8] = [0x11, 0x10, 0x14, 0x00, 0x0d, 0xf0, 0x05, 0xb1];
 const AMBA_ID_LOW: u64 = 0x3f8;
 const AMBA_ID_HIGH: u64 = 0x401;
 
-#[derive(Debug, Error)]
+#[derive(Debug)]
 pub enum Error {
-    #[error("pl011_write: Bad Write Offset: {0}")]
     BadWriteOffset(u64),
-    #[error("pl011: DMA not implemented")]
     DmaNotImplemented,
-    #[error("Failed to trigger interrupt")]
-    InterruptFailure(#[source] io::Error),
-    #[error("Failed to write")]
-    WriteAllFailure(#[source] io::Error),
-    #[error("Failed to flush")]
-    FlushFailure(#[source] io::Error),
+    InterruptFailure(io::Error),
+    WriteAllFailure(io::Error),
+    FlushFailure(io::Error),
+}
+
+impl fmt::Display for Error {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        match self {
+            Error::BadWriteOffset(offset) => write!(f, "pl011_write: Bad Write Offset: {offset}"),
+            Error::DmaNotImplemented => write!(f, "pl011: DMA not implemented."),
+            Error::InterruptFailure(e) => write!(f, "Failed to trigger interrupt: {e}"),
+            Error::WriteAllFailure(e) => write!(f, "Failed to write: {e}"),
+            Error::FlushFailure(e) => write!(f, "Failed to flush: {e}"),
+        }
+    }
 }
 
 type Result<T> = result::Result<T, Error>;
@@ -86,7 +94,7 @@ pub struct Pl011 {
     timestamp: std::time::Instant,
 }
 
-#[derive(Serialize, Deserialize)]
+#[derive(Versionize)]
 pub struct Pl011State {
     flags: u32,
     lcr: u32,
@@ -105,6 +113,8 @@ pub struct Pl011State {
     read_trigger: u32,
 }
 
+impl VersionMapped for Pl011State {}
+
 impl Pl011 {
     /// Constructs an AMBA PL011 UART device.
     pub fn new(
@@ -191,8 +201,8 @@ impl Pl011 {
         }
     }
 
-    pub fn set_out(&mut self, out: Option<Box<dyn io::Write + Send>>) {
-        self.out = out;
+    pub fn set_out(&mut self, out: Box<dyn io::Write + Send>) {
+        self.out = Some(out);
     }
 
     fn state(&self) -> Pl011State {
@@ -444,7 +454,7 @@ impl Snapshottable for Pl011 {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        Snapshot::new_from_state(&self.state())
+        Snapshot::new_from_versioned_state(&self.state())
     }
 }
 
@@ -454,13 +464,12 @@ impl Migratable for Pl011 {}
 
 #[cfg(test)]
 mod tests {
-    use std::sync::Mutex;
-
+    use super::*;
+    use std::io;
+    use std::sync::{Arc, Mutex};
     use vm_device::interrupt::{InterruptIndex, InterruptSourceConfig};
     use vmm_sys_util::eventfd::EventFd;
 
-    use super::*;
-
     const SERIAL_NAME: &str = "serial";
 
     struct TestInterrupt {
@@ -476,13 +485,9 @@ mod tests {
             _index: InterruptIndex,
             _config: InterruptSourceConfig,
             _masked: bool,
-            _set_gsi: bool,
         ) -> result::Result<(), std::io::Error> {
             Ok(())
         }
-        fn set_gsi(&self) -> result::Result<(), std::io::Error> {
-            Ok(())
-        }
         fn notifier(&self, _index: InterruptIndex) -> Option<EventFd> {
             Some(self.event_fd.try_clone().unwrap())
         }
@@ -528,11 +533,14 @@ mod tests {
             None,
         );
 
-        pl011.write(0, UARTDR, b"xy");
-        pl011.write(0, UARTDR, b"a");
-        pl011.write(0, UARTDR, b"b");
-        pl011.write(0, UARTDR, b"c");
-        assert_eq!(pl011_out.buf.lock().unwrap().as_slice(), b"xabc");
+        pl011.write(0, UARTDR, &[b'x', b'y']);
+        pl011.write(0, UARTDR, &[b'a']);
+        pl011.write(0, UARTDR, &[b'b']);
+        pl011.write(0, UARTDR, &[b'c']);
+        assert_eq!(
+            pl011_out.buf.lock().unwrap().as_slice(),
+            &[b'x', b'a', b'b', b'c']
+        );
     }
 
     #[test]
@@ -549,8 +557,8 @@ mod tests {
 
         // write 1 to the interrupt event fd, so that read doesn't block in case the event fd
         // counter doesn't change (for 0 it blocks)
-        intr_evt.write(1).unwrap();
-        pl011.queue_input_bytes(b"abc").unwrap();
+        assert!(intr_evt.write(1).is_ok());
+        pl011.queue_input_bytes(&[b'a', b'b', b'c']).unwrap();
 
         assert_eq!(intr_evt.read().unwrap(), 2);
 

devices/src/lib.rs

@@ -10,34 +10,18 @@
 #[macro_use]
 extern crate bitflags;
 #[macro_use]
-extern crate event_monitor;
-#[macro_use]
 extern crate log;
 
 pub mod acpi;
-#[cfg(target_arch = "riscv64")]
-pub mod aia;
-#[cfg(target_arch = "x86_64")]
-pub mod debug_console;
 #[cfg(target_arch = "aarch64")]
 pub mod gic;
 pub mod interrupt_controller;
 #[cfg(target_arch = "x86_64")]
 pub mod ioapic;
-#[cfg(feature = "ivshmem")]
-pub mod ivshmem;
 pub mod legacy;
-#[cfg(feature = "pvmemcontrol")]
-pub mod pvmemcontrol;
-pub mod pvpanic;
-// TODO: TPM is not yet supported
-#[cfg(not(target_arch = "riscv64"))]
 pub mod tpm;
 
 pub use self::acpi::{AcpiGedDevice, AcpiPmTimerDevice, AcpiShutdownDevice};
-#[cfg(feature = "ivshmem")]
-pub use self::ivshmem::IvshmemDevice;
-pub use self::pvpanic::{PVPANIC_DEVICE_MMIO_SIZE, PvPanicDevice};
 
 bitflags! {
     pub struct AcpiNotificationFlags: u8 {

devices/src/pvmemcontrol.rs

@@ -1,815 +0,0 @@
-// Copyright © 2024 Google LLC
-//
-// SPDX-License-Identifier: Apache-2.0
-//
-
-use std::collections::HashMap;
-use std::ffi::CString;
-use std::sync::{Arc, Barrier, Mutex, RwLock};
-use std::{io, result};
-
-use num_enum::TryFromPrimitive;
-use pci::{
-    BarReprogrammingParams, PciBarConfiguration, PciBarPrefetchable, PciBarRegionType,
-    PciClassCode, PciConfiguration, PciDevice, PciDeviceError, PciHeaderType, PciSubclass,
-};
-use thiserror::Error;
-use vm_allocator::page_size::get_page_size;
-use vm_allocator::{AddressAllocator, SystemAllocator};
-use vm_device::{BusDeviceSync, Resource};
-use vm_memory::bitmap::AtomicBitmap;
-use vm_memory::{
-    Address, ByteValued, Bytes, GuestAddress, GuestAddressSpace, GuestMemory, GuestMemoryAtomic,
-    GuestMemoryError, GuestMemoryMmap, Le32, Le64,
-};
-use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
-
-const PVMEMCONTROL_VENDOR_ID: u16 = 0x1ae0;
-const PVMEMCONTROL_DEVICE_ID: u16 = 0x0087;
-
-const PVMEMCONTROL_SUBSYSTEM_VENDOR_ID: u16 = 0x1ae0;
-const PVMEMCONTROL_SUBSYSTEM_ID: u16 = 0x011F;
-
-const MAJOR_VERSION: u64 = 1;
-const MINOR_VERSION: u64 = 0;
-
-#[derive(Error, Debug)]
-pub enum Error {
-    // device errors
-    #[error("Guest gave us bad memory addresses")]
-    GuestMemory(#[source] GuestMemoryError),
-    #[error("Guest sent us invalid request")]
-    InvalidRequest,
-
-    #[error("Guest sent us invalid command: {0}")]
-    InvalidCommand(u32),
-    #[error("Guest sent us invalid connection: {0}")]
-    InvalidConnection(u32),
-
-    // pvmemcontrol errors
-    #[error("Request contains invalid arguments: {0}")]
-    InvalidArgument(u64),
-    #[error("Unknown function code: {0}")]
-    UnknownFunctionCode(u64),
-    #[error("Libc call fail")]
-    LibcFail(#[source] std::io::Error),
-}
-
-#[derive(Copy, Clone)]
-enum PvmemcontrolSubclass {
-    Other = 0x80,
-}
-
-impl PciSubclass for PvmemcontrolSubclass {
-    fn get_register_value(&self) -> u8 {
-        *self as u8
-    }
-}
-
-/// commands have 0 as the most significant byte
-#[repr(u32)]
-#[derive(PartialEq, Eq, Copy, Clone, TryFromPrimitive)]
-enum PvmemcontrolTransportCommand {
-    Reset = 0x060f_e6d2,
-    Register = 0x0e35_9539,
-    Ready = 0x0ca8_d227,
-    Disconnect = 0x030f_5da0,
-    Ack = 0x03cf_5196,
-    Error = 0x01fb_a249,
-}
-
-#[repr(C)]
-#[derive(Copy, Clone)]
-struct PvmemcontrolTransportRegister {
-    buf_phys_addr: Le64,
-}
-
-#[repr(C)]
-#[derive(Copy, Clone)]
-struct PvmemcontrolTransportRegisterResponse {
-    command: Le32,
-    _padding: u32,
-}
-
-#[repr(C)]
-#[derive(Copy, Clone)]
-union PvmemcontrolTransportUnion {
-    register: PvmemcontrolTransportRegister,
-    register_response: PvmemcontrolTransportRegisterResponse,
-    unit: (),
-}
-
-#[repr(C)]
-#[derive(Copy, Clone)]
-struct PvmemcontrolTransport {
-    payload: PvmemcontrolTransportUnion,
-    command: PvmemcontrolTransportCommand,
-}
-
-const PVMEMCONTROL_DEVICE_MMIO_SIZE: u64 = std::mem::size_of::<PvmemcontrolTransport>() as u64;
-const PVMEMCONTROL_DEVICE_MMIO_ALIGN: u64 = std::mem::align_of::<PvmemcontrolTransport>() as u64;
-
-impl PvmemcontrolTransport {
-    fn ack() -> Self {
-        PvmemcontrolTransport {
-            payload: PvmemcontrolTransportUnion { unit: () },
-            command: PvmemcontrolTransportCommand::Ack,
-        }
-    }
-
-    fn error() -> Self {
-        PvmemcontrolTransport {
-            payload: PvmemcontrolTransportUnion { unit: () },
-            command: PvmemcontrolTransportCommand::Error,
-        }
-    }
-
-    fn register_response(command: u32) -> Self {
-        PvmemcontrolTransport {
-            payload: PvmemcontrolTransportUnion {
-                register_response: PvmemcontrolTransportRegisterResponse {
-                    command: command.into(),
-                    _padding: 0,
-                },
-            },
-            command: PvmemcontrolTransportCommand::Ack,
-        }
-    }
-
-    unsafe fn as_register(self) -> PvmemcontrolTransportRegister {
-        // SAFETY: We access initialized data.
-        unsafe { self.payload.register }
-    }
-}
-
-// SAFETY: Contains no references and does not have compiler-inserted padding
-unsafe impl ByteValued for PvmemcontrolTransportUnion {}
-// SAFETY: Contains no references and does not have compiler-inserted padding
-unsafe impl ByteValued for PvmemcontrolTransport {}
-
-#[repr(u64)]
-#[derive(Copy, Clone, TryFromPrimitive, Debug)]
-enum FunctionCode {
-    Info = 0,
-    Dontneed = 1,
-    Remove = 2,
-    Free = 3,
-    Pageout = 4,
-    Dontdump = 5,
-    SetVMAAnonName = 6,
-    Mlock = 7,
-    Munlock = 8,
-    MprotectNone = 9,
-    MprotectR = 10,
-    MprotectW = 11,
-    MprotectRW = 12,
-    Mergeable = 13,
-    Unmergeable = 14,
-}
-
-#[repr(C)]
-#[derive(Copy, Clone, Debug, Default)]
-struct PvmemcontrolReq {
-    func_code: Le64,
-    addr: Le64,
-    length: Le64,
-    arg: Le64,
-}
-
-// SAFETY: it only has data and has no implicit padding.
-unsafe impl ByteValued for PvmemcontrolReq {}
-
-#[repr(C)]
-#[derive(Copy, Clone, Default)]
-struct PvmemcontrolResp {
-    ret_errno: Le32,
-    ret_code: Le32,
-    ret_value: Le64,
-    arg0: Le64,
-    arg1: Le64,
-}
-
-impl std::fmt::Debug for PvmemcontrolResp {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        let PvmemcontrolResp {
-            ret_errno,
-            ret_code,
-            ..
-        } = self;
-        write!(
-            f,
-            "PvmemcontrolResp {{ ret_errno: {}, ret_code: {}, .. }}",
-            ret_errno.to_native(),
-            ret_code.to_native()
-        )
-    }
-}
-
-// SAFETY: it only has data and has no implicit padding.
-unsafe impl ByteValued for PvmemcontrolResp {}
-
-/// The guest connections start at 0x8000_0000, which has a leading 1 in
-/// the most significant byte, this ensures it does not conflict with
-/// any of the transport commands
-#[derive(Hash, Clone, Copy, PartialEq, Eq, Debug)]
-pub struct GuestConnection {
-    command: u32,
-}
-
-impl Default for GuestConnection {
-    fn default() -> Self {
-        GuestConnection::new(0x8000_0000)
-    }
-}
-
-impl GuestConnection {
-    fn new(command: u32) -> Self {
-        Self { command }
-    }
-
-    fn next(&self) -> Self {
-        let GuestConnection { command } = *self;
-
-        if command == u32::MAX {
-            GuestConnection::default()
-        } else {
-            GuestConnection::new(command + 1)
-        }
-    }
-}
-
-impl TryFrom<u32> for GuestConnection {
-    type Error = Error;
-
-    fn try_from(value: u32) -> Result<Self, Self::Error> {
-        if (value & 0x8000_0000) != 0 {
-            Ok(GuestConnection::new(value))
-        } else {
-            Err(Error::InvalidConnection(value))
-        }
-    }
-}
-
-struct PercpuInitState {
-    port_buf_map: HashMap<GuestConnection, GuestAddress>,
-    next_conn: GuestConnection,
-}
-
-impl PercpuInitState {
-    fn new() -> Self {
-        PercpuInitState {
-            port_buf_map: HashMap::new(),
-            next_conn: GuestConnection::default(),
-        }
-    }
-}
-
-enum PvmemcontrolState {
-    PercpuInit(PercpuInitState),
-    Ready(HashMap<GuestConnection, GuestAddress>),
-    Broken,
-}
-
-pub struct PvmemcontrolDevice {
-    transport: PvmemcontrolTransport,
-    state: PvmemcontrolState,
-}
-
-impl PvmemcontrolDevice {
-    fn new(transport: PvmemcontrolTransport, state: PvmemcontrolState) -> Self {
-        PvmemcontrolDevice { transport, state }
-    }
-}
-
-impl PvmemcontrolDevice {
-    fn register_percpu_buf(
-        guest_memory: &GuestMemoryAtomic<GuestMemoryMmap<AtomicBitmap>>,
-        mut state: PercpuInitState,
-        PvmemcontrolTransportRegister { buf_phys_addr }: PvmemcontrolTransportRegister,
-    ) -> Self {
-        // access to this address is checked
-        let buf_phys_addr = GuestAddress(buf_phys_addr.into());
-        if !guest_memory.memory().check_range(
-            buf_phys_addr,
-            std::mem::size_of::<PvmemcontrolResp>().max(std::mem::size_of::<PvmemcontrolReq>()),
-        ) {
-            warn!("guest sent invalid phys addr {:#x}", buf_phys_addr.0);
-            return PvmemcontrolDevice::new(
-                PvmemcontrolTransport::error(),
-                PvmemcontrolState::Broken,
-            );
-        }
-
-        let conn = {
-            // find an available port+byte combination, and fail if full
-            let mut next_conn = state.next_conn;
-            while state.port_buf_map.contains_key(&next_conn) {
-                next_conn = next_conn.next();
-                if next_conn == state.next_conn {
-                    warn!("connections exhausted");
-                    return PvmemcontrolDevice::new(
-                        PvmemcontrolTransport::error(),
-                        PvmemcontrolState::Broken,
-                    );
-                }
-            }
-            next_conn
-        };
-        state.next_conn = conn.next();
-        state.port_buf_map.insert(conn, buf_phys_addr);
-
-        // inform guest of the connection
-        let response = PvmemcontrolTransport::register_response(conn.command);
-
-        PvmemcontrolDevice::new(response, PvmemcontrolState::PercpuInit(state))
-    }
-
-    fn reset() -> Self {
-        PvmemcontrolDevice::new(
-            PvmemcontrolTransport::ack(),
-            PvmemcontrolState::PercpuInit(PercpuInitState::new()),
-        )
-    }
-
-    fn error() -> Self {
-        PvmemcontrolDevice::new(PvmemcontrolTransport::error(), PvmemcontrolState::Broken)
-    }
-
-    fn ready(PercpuInitState { port_buf_map, .. }: PercpuInitState) -> Self {
-        PvmemcontrolDevice::new(
-            PvmemcontrolTransport::ack(),
-            PvmemcontrolState::Ready(port_buf_map),
-        )
-    }
-
-    fn run_command(
-        &mut self,
-        guest_memory: &GuestMemoryAtomic<GuestMemoryMmap<AtomicBitmap>>,
-        command: PvmemcontrolTransportCommand,
-    ) {
-        let state = std::mem::replace(&mut self.state, PvmemcontrolState::Broken);
-
-        *self = match command {
-            PvmemcontrolTransportCommand::Reset => Self::reset(),
-            PvmemcontrolTransportCommand::Register => {
-                if let PvmemcontrolState::PercpuInit(state) = state {
-                    // SAFETY: By device protocol. If driver is wrong the device
-                    // can enter a Broken state, but the behavior is still sound.
-                    Self::register_percpu_buf(guest_memory, state, unsafe {
-                        self.transport.as_register()
-                    })
-                } else {
-                    debug!("received register without reset");
-                    Self::error()
-                }
-            }
-            PvmemcontrolTransportCommand::Ready => {
-                if let PvmemcontrolState::PercpuInit(state) = state {
-                    Self::ready(state)
-                } else {
-                    debug!("received ready without reset");
-                    Self::error()
-                }
-            }
-            PvmemcontrolTransportCommand::Disconnect => Self::error(),
-            PvmemcontrolTransportCommand::Ack => {
-                debug!("received ack as command");
-                Self::error()
-            }
-            PvmemcontrolTransportCommand::Error => {
-                debug!("received error as command");
-                Self::error()
-            }
-        }
-    }
-
-    /// read from the transport
-    fn read_transport(&self, offset: u64, data: &mut [u8]) {
-        self.transport
-            .as_slice()
-            .iter()
-            .skip(offset as usize)
-            .zip(data.iter_mut())
-            .for_each(|(src, dest)| *dest = *src)
-    }
-
-    /// can only write to transport payload
-    /// command is a special register that needs separate dispatching
-    fn write_transport(&mut self, offset: u64, data: &[u8]) {
-        self.transport
-            .payload
-            .as_mut_slice()
-            .iter_mut()
-            .skip(offset as usize)
-            .zip(data.iter())
-            .for_each(|(dest, src)| *dest = *src)
-    }
-
-    fn find_connection(&self, conn: GuestConnection) -> Option<GuestAddress> {
-        match &self.state {
-            PvmemcontrolState::Ready(map) => map.get(&conn).copied(),
-            _ => None,
-        }
-    }
-}
-
-pub struct PvmemcontrolBusDevice {
-    mem: GuestMemoryAtomic<GuestMemoryMmap<AtomicBitmap>>,
-    dev: RwLock<PvmemcontrolDevice>,
-}
-
-pub struct PvmemcontrolPciDevice {
-    id: String,
-    configuration: PciConfiguration,
-    bar_regions: Vec<PciBarConfiguration>,
-}
-
-impl PvmemcontrolBusDevice {
-    /// f is called with the host address of `range_base` and only when
-    /// [`range_base`, `range_base` + `range_len`) is present in the guest
-    fn operate_on_memory_range<F>(&self, addr: u64, length: u64, f: F) -> result::Result<(), Error>
-    where
-        F: FnOnce(*mut libc::c_void, libc::size_t) -> libc::c_int,
-    {
-        let memory = self.mem.memory();
-        let range_base = GuestAddress(addr);
-        let range_len = usize::try_from(length).map_err(|_| Error::InvalidRequest)?;
-
-        // assume guest memory is not interleaved with vmm memory on the host.
-        if !memory.check_range(range_base, range_len) {
-            return Err(Error::GuestMemory(GuestMemoryError::InvalidGuestAddress(
-                range_base,
-            )));
-        }
-        let hva = memory
-            .get_host_address(range_base)
-            .map_err(Error::GuestMemory)?;
-        let res = f(hva as *mut libc::c_void, range_len as libc::size_t);
-        if res != 0 {
-            return Err(Error::LibcFail(io::Error::last_os_error()));
-        }
-        Ok(())
-    }
-
-    fn madvise(&self, addr: u64, length: u64, advice: libc::c_int) -> result::Result<(), Error> {
-        // SAFETY: [`base`, `base` + `len`) is guest memory
-        self.operate_on_memory_range(addr, length, |base, len| unsafe {
-            libc::madvise(base, len, advice)
-        })
-    }
-
-    fn mlock(&self, addr: u64, length: u64, on_default: bool) -> result::Result<(), Error> {
-        // SAFETY: [`base`, `base` + `len`) is guest memory
-        self.operate_on_memory_range(addr, length, |base, len| unsafe {
-            libc::mlock2(base, len, if on_default { libc::MLOCK_ONFAULT } else { 0 })
-        })
-    }
-
-    fn munlock(&self, addr: u64, length: u64) -> result::Result<(), Error> {
-        // SAFETY: [`base`, `base` + `len`) is guest memory
-        self.operate_on_memory_range(addr, length, |base, len| unsafe {
-            libc::munlock(base, len)
-        })
-    }
-
-    fn mprotect(
-        &self,
-        addr: u64,
-        length: u64,
-        protection: libc::c_int,
-    ) -> result::Result<(), Error> {
-        // SAFETY: [`base`, `base` + `len`) is guest memory
-        self.operate_on_memory_range(addr, length, |base, len| unsafe {
-            libc::mprotect(base, len, protection)
-        })
-    }
-
-    fn set_vma_anon_name(&self, addr: u64, length: u64, name: u64) -> result::Result<(), Error> {
-        let name = (name != 0).then(|| CString::new(format!("pvmemcontrol-{name}")).unwrap());
-        let name_ptr = if let Some(name) = &name {
-            name.as_ptr()
-        } else {
-            std::ptr::null()
-        };
-        debug!("addr {:X} length {} name {:?}", addr, length, name);
-
-        // SAFETY: [`base`, `base` + `len`) is guest memory
-        self.operate_on_memory_range(addr, length, |base, len| unsafe {
-            libc::prctl(
-                libc::PR_SET_VMA,
-                libc::PR_SET_VMA_ANON_NAME,
-                base,
-                len,
-                name_ptr,
-            )
-        })
-    }
-
-    fn process_request(
-        &self,
-        func_code: FunctionCode,
-        addr: u64,
-        length: u64,
-        arg: u64,
-    ) -> Result<PvmemcontrolResp, Error> {
-        let result = match func_code {
-            FunctionCode::Info => {
-                return Ok(PvmemcontrolResp {
-                    ret_errno: 0.into(),
-                    ret_code: 0.into(),
-                    ret_value: get_page_size().into(),
-                    arg0: MAJOR_VERSION.into(),
-                    arg1: MINOR_VERSION.into(),
-                });
-            }
-            FunctionCode::Dontneed => self.madvise(addr, length, libc::MADV_DONTNEED),
-            FunctionCode::Remove => self.madvise(addr, length, libc::MADV_REMOVE),
-            FunctionCode::Free => self.madvise(addr, length, libc::MADV_FREE),
-            FunctionCode::Pageout => self.madvise(addr, length, libc::MADV_PAGEOUT),
-            FunctionCode::Dontdump => self.madvise(addr, length, libc::MADV_DONTDUMP),
-            FunctionCode::SetVMAAnonName => self.set_vma_anon_name(addr, length, arg),
-            FunctionCode::Mlock => self.mlock(addr, length, false),
-            FunctionCode::Munlock => self.munlock(addr, length),
-            FunctionCode::MprotectNone => self.mprotect(addr, length, libc::PROT_NONE),
-            FunctionCode::MprotectR => self.mprotect(addr, length, libc::PROT_READ),
-            FunctionCode::MprotectW => self.mprotect(addr, length, libc::PROT_WRITE),
-            FunctionCode::MprotectRW => {
-                self.mprotect(addr, length, libc::PROT_READ | libc::PROT_WRITE)
-            }
-            FunctionCode::Mergeable => self.madvise(addr, length, libc::MADV_MERGEABLE),
-            FunctionCode::Unmergeable => self.madvise(addr, length, libc::MADV_UNMERGEABLE),
-        };
-        result.map(|_| PvmemcontrolResp::default())
-    }
-
-    fn handle_request(
-        &self,
-        PvmemcontrolReq {
-            func_code,
-            addr,
-            length,
-            arg,
-        }: PvmemcontrolReq,
-    ) -> Result<PvmemcontrolResp, Error> {
-        let (func_code, addr, length, arg) = (
-            func_code.to_native(),
-            addr.to_native(),
-            length.to_native(),
-            arg.to_native(),
-        );
-
-        let resp_or_err = FunctionCode::try_from(func_code)
-            .map_err(|_| Error::UnknownFunctionCode(func_code))
-            .and_then(|func_code| self.process_request(func_code, addr, length, arg));
-
-        let resp = match resp_or_err {
-            Ok(resp) => resp,
-            Err(e) => match e {
-                Error::InvalidArgument(arg) => PvmemcontrolResp {
-                    ret_errno: (libc::EINVAL as u32).into(),
-                    ret_code: (arg as u32).into(),
-                    ..Default::default()
-                },
-                Error::LibcFail(err) => PvmemcontrolResp {
-                    ret_errno: (err.raw_os_error().unwrap_or(libc::EFAULT) as u32).into(),
-                    ret_code: 0u32.into(),
-                    ..Default::default()
-                },
-                Error::UnknownFunctionCode(func_code) => PvmemcontrolResp {
-                    ret_errno: (libc::EOPNOTSUPP as u32).into(),
-                    ret_code: (func_code as u32).into(),
-                    ..Default::default()
-                },
-                Error::GuestMemory(err) => {
-                    warn!("{}", err);
-                    PvmemcontrolResp {
-                        ret_errno: (libc::EINVAL as u32).into(),
-                        ret_code: (func_code as u32).into(),
-                        ..Default::default()
-                    }
-                }
-                // device error, stop responding
-                other => return Err(other),
-            },
-        };
-        Ok(resp)
-    }
-
-    fn handle_pvmemcontrol_request(&self, guest_addr: GuestAddress) {
-        let request: PvmemcontrolReq = if let Ok(x) = self.mem.memory().read_obj(guest_addr) {
-            x
-        } else {
-            warn!("cannot read from guest address {:#x}", guest_addr.0);
-            return;
-        };
-
-        let response: PvmemcontrolResp = match self.handle_request(request) {
-            Ok(x) => x,
-            Err(e) => {
-                warn!("cannot process request {:?} with error {}", request, e);
-                return;
-            }
-        };
-
-        if self.mem.memory().write_obj(response, guest_addr).is_err() {
-            warn!("cannot write to guest address {:#x}", guest_addr.0);
-        }
-    }
-
-    fn handle_guest_write(&self, offset: u64, data: &[u8]) {
-        if offset as usize != std::mem::offset_of!(PvmemcontrolTransport, command) {
-            if data.len() != 4 && data.len() != 8 {
-                warn!("guest write is not 4 or 8 bytes long");
-                return;
-            }
-            self.dev.write().unwrap().write_transport(offset, data);
-            return;
-        }
-        let data = if data.len() == 4 {
-            let mut d = [0u8; 4];
-            d.iter_mut()
-                .zip(data.iter())
-                .for_each(|(d, data)| *d = *data);
-            d
-        } else {
-            warn!("guest write with non u32 at command register");
-            return;
-        };
-        let data_cmd = u32::from_le_bytes(data);
-        let command = PvmemcontrolTransportCommand::try_from(data_cmd);
-
-        match command {
-            Ok(command) => self.dev.write().unwrap().run_command(&self.mem, command),
-            Err(_) => {
-                GuestConnection::try_from(data_cmd)
-                    .and_then(|conn| {
-                        self.dev
-                            .read()
-                            .unwrap()
-                            .find_connection(conn)
-                            .ok_or(Error::InvalidConnection(conn.command))
-                    })
-                    .map(|gpa| self.handle_pvmemcontrol_request(gpa))
-                    .unwrap_or_else(|err| warn!("{:?}", err));
-            }
-        }
-    }
-
-    fn handle_guest_read(&self, offset: u64, data: &mut [u8]) {
-        self.dev.read().unwrap().read_transport(offset, data)
-    }
-}
-
-impl PvmemcontrolDevice {
-    pub fn make_device(
-        id: String,
-        mem: GuestMemoryAtomic<GuestMemoryMmap<AtomicBitmap>>,
-    ) -> (PvmemcontrolPciDevice, PvmemcontrolBusDevice) {
-        let dev = RwLock::new(PvmemcontrolDevice::error());
-        let mut configuration = PciConfiguration::new(
-            PVMEMCONTROL_VENDOR_ID,
-            PVMEMCONTROL_DEVICE_ID,
-            0x1,
-            PciClassCode::BaseSystemPeripheral,
-            &PvmemcontrolSubclass::Other,
-            None,
-            PciHeaderType::Device,
-            PVMEMCONTROL_SUBSYSTEM_VENDOR_ID,
-            PVMEMCONTROL_SUBSYSTEM_ID,
-            None,
-            None,
-        );
-        let command: [u8; 2] = [0x03, 0x01]; // memory, io, SERR#
-
-        configuration.write_config_register(1, 0, &command);
-        (
-            PvmemcontrolPciDevice {
-                id,
-                configuration,
-                bar_regions: Vec::new(),
-            },
-            PvmemcontrolBusDevice { mem, dev },
-        )
-    }
-}
-
-impl PciDevice for PvmemcontrolPciDevice {
-    fn write_config_register(
-        &mut self,
-        reg_idx: usize,
-        offset: u64,
-        data: &[u8],
-    ) -> (Vec<BarReprogrammingParams>, Option<Arc<Barrier>>) {
-        (
-            self.configuration
-                .write_config_register(reg_idx, offset, data),
-            None,
-        )
-    }
-
-    fn read_config_register(&mut self, reg_idx: usize) -> u32 {
-        self.configuration.read_config_register(reg_idx)
-    }
-
-    fn as_any_mut(&mut self) -> &mut dyn std::any::Any {
-        self
-    }
-
-    fn id(&self) -> Option<String> {
-        Some(self.id.clone())
-    }
-
-    fn allocate_bars(
-        &mut self,
-        _allocator: &Arc<Mutex<SystemAllocator>>,
-        mmio32_allocator: &mut AddressAllocator,
-        _mmio64_allocator: &mut AddressAllocator,
-        resources: Option<Vec<Resource>>,
-    ) -> Result<Vec<PciBarConfiguration>, PciDeviceError> {
-        let mut bars = Vec::new();
-        let region_type = PciBarRegionType::Memory32BitRegion;
-        let bar_id = 0;
-        let region_size = PVMEMCONTROL_DEVICE_MMIO_SIZE;
-        let restoring = resources.is_some();
-        let bar_addr = mmio32_allocator
-            .allocate(None, region_size, Some(PVMEMCONTROL_DEVICE_MMIO_ALIGN))
-            .ok_or(PciDeviceError::IoAllocationFailed(region_size))?;
-
-        let bar = PciBarConfiguration::default()
-            .set_index(bar_id as usize)
-            .set_address(bar_addr.raw_value())
-            .set_size(region_size)
-            .set_region_type(region_type)
-            .set_prefetchable(PciBarPrefetchable::NotPrefetchable);
-
-        if !restoring {
-            self.configuration
-                .add_pci_bar(&bar)
-                .map_err(|e| PciDeviceError::IoRegistrationFailed(bar_addr.raw_value(), e))?;
-        }
-
-        bars.push(bar);
-        self.bar_regions.clone_from(&bars);
-        Ok(bars)
-    }
-
-    fn free_bars(
-        &mut self,
-        _allocator: &mut SystemAllocator,
-        mmio32_allocator: &mut AddressAllocator,
-        _mmio64_allocator: &mut AddressAllocator,
-    ) -> Result<(), PciDeviceError> {
-        for bar in self.bar_regions.drain(..) {
-            mmio32_allocator.free(GuestAddress(bar.addr()), bar.size())
-        }
-        Ok(())
-    }
-
-    fn move_bar(&mut self, old_base: u64, new_base: u64) -> result::Result<(), io::Error> {
-        for bar in self.bar_regions.iter_mut() {
-            if bar.addr() == old_base {
-                *bar = bar.set_address(new_base);
-            }
-        }
-        Ok(())
-    }
-}
-
-impl Pausable for PvmemcontrolPciDevice {
-    fn pause(&mut self) -> std::result::Result<(), MigratableError> {
-        Ok(())
-    }
-
-    fn resume(&mut self) -> std::result::Result<(), MigratableError> {
-        Ok(())
-    }
-}
-
-impl Snapshottable for PvmemcontrolPciDevice {
-    fn id(&self) -> String {
-        self.id.clone()
-    }
-
-    fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        let mut snapshot = Snapshot::new_from_state(&())?;
-
-        // Snapshot PciConfiguration
-        snapshot.add_snapshot(self.configuration.id(), self.configuration.snapshot()?);
-
-        Ok(snapshot)
-    }
-}
-
-impl Transportable for PvmemcontrolPciDevice {}
-impl Migratable for PvmemcontrolPciDevice {}
-
-impl BusDeviceSync for PvmemcontrolBusDevice {
-    fn read(&self, _base: u64, offset: u64, data: &mut [u8]) {
-        self.handle_guest_read(offset, data)
-    }
-
-    fn write(&self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
-        self.handle_guest_write(offset, data);
-        None
-    }
-}

devices/src/pvpanic.rs

@@ -1,265 +0,0 @@
-// Copyright © 2023 Tencent Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-//
-
-use std::any::Any;
-use std::result;
-use std::sync::{Arc, Barrier, Mutex};
-
-use anyhow::anyhow;
-use pci::{
-    BarReprogrammingParams, PCI_CONFIGURATION_ID, PciBarConfiguration, PciBarPrefetchable,
-    PciBarRegionType, PciClassCode, PciConfiguration, PciDevice, PciDeviceError, PciHeaderType,
-    PciSubclass,
-};
-use serde::{Deserialize, Serialize};
-use thiserror::Error;
-use vm_allocator::{AddressAllocator, SystemAllocator};
-use vm_device::{BusDevice, Resource};
-use vm_memory::{Address, GuestAddress};
-use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
-
-const PVPANIC_VENDOR_ID: u16 = 0x1b36;
-const PVPANIC_DEVICE_ID: u16 = 0x0011;
-
-pub const PVPANIC_DEVICE_MMIO_SIZE: u64 = 0x2;
-pub const PVPANIC_DEVICE_MMIO_ALIGNMENT: u64 = 0x10;
-
-const PVPANIC_PANICKED: u8 = 1 << 0;
-const PVPANIC_CRASH_LOADED: u8 = 1 << 1;
-
-#[derive(Debug, Error)]
-pub enum PvPanicError {
-    #[error("Failed creating PvPanicDevice")]
-    CreatePvPanicDevice(#[source] anyhow::Error),
-    #[error("Failed to retrieve PciConfigurationState")]
-    RetrievePciConfigurationState(#[source] anyhow::Error),
-}
-
-#[derive(Copy, Clone)]
-enum PvPanicSubclass {
-    Other = 0x80,
-}
-
-impl PciSubclass for PvPanicSubclass {
-    fn get_register_value(&self) -> u8 {
-        *self as u8
-    }
-}
-
-/// A device for handling guest panic event
-pub struct PvPanicDevice {
-    id: String,
-    events: u8,
-
-    // PCI configuration registers.
-    configuration: PciConfiguration,
-    bar_regions: Vec<PciBarConfiguration>,
-}
-
-#[derive(Serialize, Deserialize)]
-pub struct PvPanicDeviceState {
-    events: u8,
-}
-
-impl PvPanicDevice {
-    pub fn new(id: String, snapshot: Option<Snapshot>) -> Result<Self, PvPanicError> {
-        let pci_configuration_state =
-            vm_migration::state_from_id(snapshot.as_ref(), PCI_CONFIGURATION_ID).map_err(|e| {
-                PvPanicError::RetrievePciConfigurationState(anyhow!(
-                    "Failed to get PciConfigurationState from Snapshot: {}",
-                    e
-                ))
-            })?;
-
-        let mut configuration = PciConfiguration::new(
-            PVPANIC_VENDOR_ID,
-            PVPANIC_DEVICE_ID,
-            0x1, // modern pci devices
-            PciClassCode::BaseSystemPeripheral,
-            &PvPanicSubclass::Other,
-            None,
-            PciHeaderType::Device,
-            0,
-            0,
-            None,
-            pci_configuration_state,
-        );
-
-        let command: [u8; 2] = [0x03, 0x01];
-        let bar_reprogram = configuration.write_config_register(1, 0, &command);
-        assert!(
-            bar_reprogram.is_empty(),
-            "No bar reprogrammig is expected from writing to the COMMAND register"
-        );
-
-        let state: Option<PvPanicDeviceState> = snapshot
-            .as_ref()
-            .map(|s| s.to_state())
-            .transpose()
-            .map_err(|e| {
-                PvPanicError::CreatePvPanicDevice(anyhow!(
-                    "Failed to get PvPanicDeviceState from Snapshot: {}",
-                    e
-                ))
-            })?;
-        let events = if let Some(state) = state {
-            state.events
-        } else {
-            PVPANIC_PANICKED | PVPANIC_CRASH_LOADED
-        };
-
-        let pvpanic_device = PvPanicDevice {
-            id,
-            events,
-            configuration,
-            bar_regions: vec![],
-        };
-
-        Ok(pvpanic_device)
-    }
-
-    pub fn event_to_string(&self, event: u8) -> String {
-        if event == PVPANIC_PANICKED {
-            "panic".to_string()
-        } else if event == PVPANIC_CRASH_LOADED {
-            "crash_loaded".to_string()
-        } else {
-            "unknown_event".to_string()
-        }
-    }
-
-    fn state(&self) -> PvPanicDeviceState {
-        PvPanicDeviceState {
-            events: self.events,
-        }
-    }
-
-    pub fn config_bar_addr(&self) -> u64 {
-        self.configuration.get_bar_addr(0)
-    }
-}
-
-impl BusDevice for PvPanicDevice {
-    fn read(&mut self, base: u64, offset: u64, data: &mut [u8]) {
-        self.read_bar(base, offset, data)
-    }
-
-    fn write(&mut self, _base: u64, _offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
-        let event = self.event_to_string(data[0]);
-        info!("pvpanic got guest event {}", event);
-        event!("guest", "panic", "event", &event);
-        None
-    }
-}
-
-impl PciDevice for PvPanicDevice {
-    fn write_config_register(
-        &mut self,
-        reg_idx: usize,
-        offset: u64,
-        data: &[u8],
-    ) -> (Vec<BarReprogrammingParams>, Option<Arc<Barrier>>) {
-        (
-            self.configuration
-                .write_config_register(reg_idx, offset, data),
-            None,
-        )
-    }
-
-    fn read_config_register(&mut self, reg_idx: usize) -> u32 {
-        self.configuration.read_reg(reg_idx)
-    }
-
-    fn allocate_bars(
-        &mut self,
-        _allocator: &Arc<Mutex<SystemAllocator>>,
-        mmio32_allocator: &mut AddressAllocator,
-        _mmio64_allocator: &mut AddressAllocator,
-        resources: Option<Vec<Resource>>,
-    ) -> std::result::Result<Vec<PciBarConfiguration>, PciDeviceError> {
-        let mut bars = Vec::new();
-        let region_type = PciBarRegionType::Memory32BitRegion;
-        let bar_id = 0;
-        let region_size = PVPANIC_DEVICE_MMIO_SIZE;
-        let restoring = resources.is_some();
-        let bar_addr = mmio32_allocator
-            .allocate(None, region_size, Some(PVPANIC_DEVICE_MMIO_ALIGNMENT))
-            .ok_or(PciDeviceError::IoAllocationFailed(region_size))?;
-
-        let bar = PciBarConfiguration::default()
-            .set_index(bar_id as usize)
-            .set_address(bar_addr.raw_value())
-            .set_size(region_size)
-            .set_region_type(region_type)
-            .set_prefetchable(PciBarPrefetchable::NotPrefetchable);
-
-        debug!("pvpanic bar address 0x{:x}", bar_addr.0);
-        if !restoring {
-            self.configuration
-                .add_pci_bar(&bar)
-                .map_err(|e| PciDeviceError::IoRegistrationFailed(bar_addr.raw_value(), e))?;
-        }
-
-        bars.push(bar);
-        self.bar_regions.clone_from(&bars);
-
-        Ok(bars)
-    }
-
-    fn free_bars(
-        &mut self,
-        _allocator: &mut SystemAllocator,
-        mmio32_allocator: &mut AddressAllocator,
-        _mmio64_allocator: &mut AddressAllocator,
-    ) -> std::result::Result<(), PciDeviceError> {
-        for bar in self.bar_regions.drain(..) {
-            mmio32_allocator.free(GuestAddress(bar.addr()), bar.size());
-        }
-
-        Ok(())
-    }
-
-    fn move_bar(&mut self, old_base: u64, new_base: u64) -> result::Result<(), std::io::Error> {
-        for bar in self.bar_regions.iter_mut() {
-            if bar.addr() == old_base {
-                *bar = bar.set_address(new_base);
-            }
-        }
-
-        Ok(())
-    }
-
-    fn read_bar(&mut self, _base: u64, _offset: u64, data: &mut [u8]) {
-        data[0] = self.events;
-    }
-
-    fn as_any_mut(&mut self) -> &mut dyn Any {
-        self
-    }
-
-    fn id(&self) -> Option<String> {
-        Some(self.id.clone())
-    }
-}
-
-impl Pausable for PvPanicDevice {}
-
-impl Snapshottable for PvPanicDevice {
-    fn id(&self) -> String {
-        self.id.clone()
-    }
-
-    fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        let mut snapshot = Snapshot::new_from_state(&self.state())?;
-
-        // Snapshot PciConfiguration
-        snapshot.add_snapshot(self.configuration.id(), self.configuration.snapshot()?);
-
-        Ok(snapshot)
-    }
-}
-
-impl Transportable for PvPanicDevice {}
-impl Migratable for PvPanicDevice {}

devices/src/tpm.rs

@@ -3,24 +3,23 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
-use std::cmp;
-use std::sync::{Arc, Barrier};
-
 use anyhow::anyhow;
 #[cfg(target_arch = "aarch64")]
 use arch::aarch64::layout::{TPM_SIZE, TPM_START};
 #[cfg(target_arch = "x86_64")]
 use arch::x86_64::layout::{TPM_SIZE, TPM_START};
+use std::cmp;
+use std::sync::{Arc, Barrier};
 use thiserror::Error;
-use tpm::TPM_CRB_BUFFER_MAX;
 use tpm::emulator::{BackendCmd, Emulator};
+use tpm::TPM_CRB_BUFFER_MAX;
 use vm_device::BusDevice;
 
 #[derive(Error, Debug)]
 pub enum Error {
-    #[error("Emulator doesn't implement min required capabilities")]
+    #[error("Emulator doesn't implement min required capabilities: {0}")]
     CheckCaps(#[source] anyhow::Error),
-    #[error("Failed to initialize tpm")]
+    #[error("Failed to initialize tpm: {0}")]
     Init(#[source] anyhow::Error),
 }
 type Result<T> = anyhow::Result<T, Error>;
@@ -451,16 +450,17 @@ impl BusDevice for Tpm {
                         );
                     }
                     _ => {
-                        error!("Invalid value passed to CTRL_REQ register");
+                        error!("Invalid value passed to CRTL_REQ register");
                         return None;
                     }
                 },
                 CRB_CTRL_CANCEL => {
                     if v == CRB_CANCEL_INVOKE
                         && (self.regs[CRB_CTRL_START as usize] & CRB_START_INVOKE != 0)
-                        && let Err(e) = self.emulator.cancel_cmd()
                     {
-                        error!("Failed to run cancel command. Error: {:?}", e);
+                        if let Err(e) = self.emulator.cancel_cmd() {
+                            error!("Failed to run cancel command. Error: {:?}", e);
+                        }
                     }
                 }
                 CRB_CTRL_START => {

docs/COPYING.docs

@@ -1,5 +1,4 @@
-All documentations (e.g. files with extension `.md`) in this repository is
-covered by the following license:
+The documentation in this directory is covered by the following license:
 
 Attribution 4.0 International
 

docs/amd_sev_snp.md

@@ -1,41 +0,0 @@
-# AMD SEV-SNP
-
-### WARNING
-
-This feature is only currently supported on MSHV.
-
-AMD Secure Encrypted Virtualization & Secure Nested Paging (SEV-SNP) is an AMD
-technology designed to add strong memory integrity protection to help prevent
-malicious hypervisor-based attacks like data replay, memory-remapping and more
-in order to create an isolated execution environment. Here are some useful
-links:
-
-- [SNP Homepage](https://www.amd.com/content/dam/amd/en/documents/epyc-business-docs/solution-briefs/amd-secure-encrypted-virtualization-solution-brief.pdf):
-  more information about SEV-SNP technical aspects, design and specification.
-
-## Cloud Hypervisor support
-
-It is required to use a machine which has enabled support for AMD SEV-SNP in
-the BIOS.
-
-On the Cloud Hypervisor side, all you need is to build the project with the
-`sev_snp` feature enabled:
-
-```bash
-cargo build --no-default-features --features "sev_snp"
-```
-
-**Note**
-Please note that `sev_snp` cannot be enabled in conjunction with `tdx` feature flag.
-
-You can run a SEV-SNP VM using the following command:
-
-```bash
-./cloud-hypervisor \
-     --platform sev_snp=on \
-     --cpus boot=1 \
-     --memory size=1G \
-     --disk path=ubuntu.img
-```
-
-For more information related to Microsoft Hypervisor please see [mshv.md](mshv.md)

docs/api.md

@@ -1,21 +1,18 @@
 - [Cloud Hypervisor API](#cloud-hypervisor-api)
   - [External API](#external-api)
     - [REST API](#rest-api)
-      - [REST API Location and availability](#rest-api-location-and-availability)
-      - [REST API Endpoints](#rest-api-endpoints)
-        - [Virtual Machine Manager (VMM) Actions](#virtual-machine-manager-vmm-actions)
-        - [Virtual Machine (VM) Actions](#virtual-machine-vm-actions)
-      - [REST API Examples](#rest-api-examples)
-        - [Create a Virtual Machine](#create-a-virtual-machine)
-        - [Boot a Virtual Machine](#boot-a-virtual-machine)
-        - [Dump a Virtual Machine Information](#dump-a-virtual-machine-information)
-        - [Reboot a Virtual Machine](#reboot-a-virtual-machine)
-        - [Shut a Virtual Machine Down](#shut-a-virtual-machine-down)
-    - [D-Bus API](#d-bus-api)
-      - [D-Bus API Location and availability](#d-bus-api-location-and-availability)
-      - [D-Bus API Interface](#d-bus-api-interface)
+    - [Location and availability](#location-and-availability)
+    - [Endpoints](#endpoints)
+      - [Virtual Machine Manager (VMM) Actions](#virtual-machine-manager-vmm-actions)
+      - [Virtual Machine (VM) Actions](#virtual-machine-vm-actions)
+    - [REST API Examples](#rest-api-examples)
+      - [Create a Virtual Machine](#create-a-virtual-machine)
+      - [Boot a Virtual Machine](#boot-a-virtual-machine)
+      - [Dump a Virtual Machine Information](#dump-a-virtual-machine-information)
+      - [Reboot a Virtual Machine](#reboot-a-virtual-machine)
+      - [Shut a Virtual Machine Down](#shut-a-virtual-machine-down)
     - [Command Line Interface](#command-line-interface)
-    - [REST API, D-Bus API and CLI Architectural Relationship](#rest-api-and-cli-architectural-relationship)
+    - [REST API and CLI Architectural Relationship](#rest-api-and-cli-architectural-relationship)
   - [Internal API](#internal-api)
     - [Goals and Design](#goals-and-design)
   - [End to End Example](#end-to-end-example)
@@ -24,11 +21,9 @@
 
 The Cloud Hypervisor API is made of 2 distinct interfaces:
 
-1. **The External API** This is the user facing API. Users and operators
-   can control and manage the Cloud Hypervisor through various options
-   including a REST API, a Command Line Interface (CLI) or a D-Bus based API,
-   which is not compiled into Cloud Hypervisor by default.
-
+1. **The external API**. This is the user facing API. Users and operators can
+   control and manage Cloud Hypervisor through either a REST API or a Command
+   Line Interface (CLI).
 1. **The internal API**, based on [rust's Multi-Producer, Single-Consumer (MPSC)](https://doc.rust-lang.org/std/sync/mpsc/)
    module. This API is used internally by the Cloud Hypervisor threads to
    communicate between each others.
@@ -45,17 +40,22 @@ API triggers VM and VMM specific actions, and as such it is designed as a
 collection of RPC-style, static methods.
 
 The API is [OpenAPI 3.0](https://github.com/OAI/OpenAPI-Specification/blob/master/versions/3.0.0.md)
-compliant. Please consult the [Cloud Hypervisor OpenAPI Document](https://raw.githubusercontent.com/cloud-hypervisor/cloud-hypervisor/master/vmm/src/api/openapi/cloud-hypervisor.yaml)
-for more details about the API payloads and responses.
+compliant. Please consult the [Cloud Hypervisor API](https://raw.githubusercontent.com/cloud-hypervisor/cloud-hypervisor/master/vmm/src/api/openapi/cloud-hypervisor.yaml)
+document for more details about the API payloads and responses.
 
-#### REST API Location and availability
+### Location and availability
 
-The REST API, if enabled, is available as soon as the Cloud Hypervisor binary is started,
-through either a local UNIX socket as given in the Cloud Hypervisor option `--api-socket path=...`
-or a fd with `--api-socket fd=...`.
+The REST API is available as soon as the Cloud Hypervisor binary is started,
+through a local UNIX socket.
+By default, it is located at `/run/user/{user ID}/cloud-hypervisor.{Cloud Hypervisor PID}`.
+For example, if you launched Cloud Hypervisor as user ID 1000 and its PID is
+123456, the Cloud Hypervisor REST API will be available at `/run/user/1000/cloud-hypervisor.123456`.
+
+The REST API default URL can be overridden through the Cloud Hypervisor
+option `--api-socket`:
 
 ```
-$ ./target/debug/cloud-hypervisor --api-socket path=/tmp/cloud-hypervisor.sock
+$ ./target/debug/cloud-hypervisor --api-socket /tmp/cloud-hypervisor.sock
 Cloud Hypervisor Guest
     API server: /tmp/cloud-hypervisor.sock
     vCPUs: 1
@@ -65,18 +65,18 @@ Cloud Hypervisor Guest
     Disk(s): None
 ```
 
-#### REST API Endpoints
+### Endpoints
 
 The Cloud Hypervisor API exposes the following actions through its endpoints:
 
-##### Virtual Machine Manager (VMM) Actions
+#### Virtual Machine Manager (VMM) Actions
 
 | Action                              | Endpoint        | Request Body | Response Body              | Prerequisites      |
 | ----------------------------------- | --------------- | ------------ | -------------------------- | ------------------ |
 | Check for the REST API availability | `/vmm.ping`     | N/A          | `/schemas/VmmPingResponse` | N/A                |
 | Shut the VMM down                   | `/vmm.shutdown` | N/A          | N/A                        | The VMM is running |
 
-##### Virtual Machine (VM) Actions
+#### Virtual Machine (VM) Actions
 
 | Action                             | Endpoint                | Request Body                    | Response Body            | Prerequisites                                          |
 | ---------------------------------- | ----------------------- | ------------------------------- | ------------------------ | ------------------------------------------------------ |
@@ -105,16 +105,15 @@ The Cloud Hypervisor API exposes the following actions through its endpoints:
 | Add vsock device to the VM         | `/vm.add-vsock`         | `/schemas/VsockConfig`          | `/schemas/PciDeviceInfo` | The VM is booted                                       |
 | Remove device from the VM          | `/vm.remove-device`     | `/schemas/VmRemoveDevice`       | N/A                      | The VM is booted                                       |
 | Dump the VM counters               | `/vm.counters`          | N/A                             | `/schemas/VmCounters`    | The VM is booted                                       |
-| Inject an NMI                      | `/vm.nmi`               | N/A                             | N/A                      | The VM is booted                                       |
 | Prepare to receive a migration     | `/vm.receive-migration` | `/schemas/ReceiveMigrationData` | N/A                      | N/A                                                    |
 | Start to send migration to target  | `/vm.send-migration`    | `/schemas/SendMigrationData`    | N/A                      | The VM is booted and (shared mem or hugepages enabled) |
 
 * The `vmcoredump` action is available exclusively for the `x86_64`
 architecture and can be executed only when the `guest_debug` feature is
-enabled. Without this feature, the corresponding [REST API](#rest-api) or
-[D-Bus API](#d-bus-api) endpoints are not available.
+enabled. Without this feature, the corresponding REST API endpoint is not
+available.
 
-#### REST API Examples
+### REST API Examples
 
 For the following set of examples, we assume Cloud Hypervisor is started with
 the REST API available at `/tmp/cloud-hypervisor.sock`:
@@ -130,7 +129,7 @@ Cloud Hypervisor Guest
     Disk(s): None
 ```
 
-##### Create a Virtual Machine
+#### Create a Virtual Machine
 
 We want to create a virtual machine with the following characteristics:
 
@@ -143,7 +142,7 @@ We want to create a virtual machine with the following characteristics:
   `/opt/clh/images/focal-server-cloudimg-amd64.raw`
 
 ```shell
-#!/usr/bin/env bash
+#!/bin/bash
 
 curl --unix-socket /tmp/cloud-hypervisor.sock -i \
      -X PUT 'http://localhost/api/v1/vm.create'  \
@@ -158,140 +157,74 @@ curl --unix-socket /tmp/cloud-hypervisor.sock -i \
          }'
 ```
 
-##### Boot a Virtual Machine
+#### Boot a Virtual Machine
 
 Once the VM is created, we can boot it:
 
 ```shell
-#!/usr/bin/env bash
+#!/bin/bash
 
 curl --unix-socket /tmp/cloud-hypervisor.sock -i -X PUT 'http://localhost/api/v1/vm.boot'
 ```
 
-##### Dump a Virtual Machine Information
+#### Dump a Virtual Machine Information
 
 We can fetch information about any VM, as soon as it's created:
 
 ```shell
-#!/usr/bin/env bash
+#!/bin/bash
 
 curl --unix-socket /tmp/cloud-hypervisor.sock -i \
      -X GET 'http://localhost/api/v1/vm.info' \
      -H 'Accept: application/json'
 ```
 
-##### Reboot a Virtual Machine
+#### Reboot a Virtual Machine
 
 We can reboot a VM that's already booted:
 
 ```shell
-#!/usr/bin/env bash
+#!/bin/bash
 
 curl --unix-socket /tmp/cloud-hypervisor.sock -i -X PUT 'http://localhost/api/v1/vm.reboot'
 ```
 
-##### Shut a Virtual Machine Down
+#### Shut a Virtual Machine Down
 
 Once booted, we can shut a VM down from the REST API:
 
 ```shell
-#!/usr/bin/env bash
+#!/bin/bash
 
 curl --unix-socket /tmp/cloud-hypervisor.sock -i -X PUT 'http://localhost/api/v1/vm.shutdown'
 ```
 
-### D-Bus API
-
-Cloud Hypervisor offers a D-Bus API as an alternative to its REST API. This
-D-Bus API fully reflects the functionality of the REST API, exposing the
-same group of endpoints. It can be a drop-in replacement since it also
-consumes/produces JSON.
-
-In addition, the D-Bus API also exposes events from `event-monitor` in the
-form of a D-Bus signal to which users can subscribe. For more information,
-see [D-Bus API Interface](#d-bus-api-interface).
-
-#### D-Bus API Location and availability
-
-This feature is not compiled into Cloud Hypervisor by default. Users who
-wish to use the D-Bus API, must explicitly enable it with the `dbus_api`
-feature flag when compiling Cloud Hypervisor.
-
-```sh
-$ ./scripts/dev_cli.sh build --release --libc musl -- --features dbus_api
-```
-
-Once this feature is enabled, it can be configured with the following
-CLI options:
-
-```
-  --dbus-service-name
-                    well known name of the service
-  --dbus-object-path
-                    object path to serve the dbus interface
-  --dbus-system-bus use the system bus instead of a session bus
-```
-
-Example invocation:
-
-```sh
-$ ./cloud-hypervisor --dbus-service-name "org.cloudhypervisor.DBusApi" \
-                     --dbus-object-path "/org/cloudhypervisor/DBusApi"
-```
-
-This will start serving a service with the name `org.cloudhypervisor.DBusApi1`
-which in turn can be used to control and manage Cloud Hypervisor.
-
-#### D-Bus API Interface
-
-Please refer to the [REST API](#rest-api) documentation for everything that
-is in common with the REST API. As previously mentioned, the D-Bus API can
-be used as a drop-in replacement for the [REST API](#rest-api).
-
-The D-Bus interface also exposes a signal, named `Event`, which is emitted
-whenever a new event is published from the `event-monitor` crate. Here is its
-definition in XML format:
-
-```xml
-<node>
-  <interface name="org.cloudhypervisor.DBusApi1">
-    <signal name="Event">
-      <arg name="event" type="s"/>
-    </signal>
-  </interface>
-</node>
-```
-
 ### Command Line Interface
 
 The Cloud Hypervisor Command Line Interface (CLI) can only be used for launching
-the Cloud Hypervisor binary, i.e. it cannot be used for controlling the VMM or
+the Cloud Hypervisor binary, i.e. it can not be used for controlling the VMM or
 the launched VM once they're up and running.
 
 If you want to inspect the VMM, or control the VM after launching Cloud
-Hypervisor from the CLI, you must use either the [REST API](#rest-api)
-or the [D-Bus API](#d-bus-api).
+Hypervisor from the CLI, you must use the [REST API](#rest-api).
 
-From the CLI, one can:
+From the CLI, one can either:
 
 1. Create and boot a complete virtual machine by using the CLI options to build
    the VM config. Run `cloud-hypervisor --help` for a complete list of CLI
-   options. As soon as the `cloud-hypervisor` binary is launched, contrary
-   to the [D-Bus API](#d-bus-api), the [REST API](#rest-api) is available
-   for controlling and managing the VM. The [D-Bus API](#d-bus-api) doesn't start
-   automatically and needs to be explicitly configured in order to be run.
-1. Start either the REST API, D-Bus API or both simultaneously without passing
-   any VM configuration options. The VM can then be asynchronously created and
-   booted by calling API methods of choice. It should be noted that one external
-   API does not exclude another; it is possible to have both the REST and D-Bus
-   APIs running simultaneously.
+   options. As soon as the `cloud-hypervisor` binary is launched, the
+   [REST API](#rest-api) is available for controlling and managing the VM.
+1. Start the [REST API](#rest-api) server only, by not passing any VM
+   configuration options. The VM can then be asynchronously created and booted
+   by sending HTTP commands to the [REST API](#rest-api). Check the
+   [REST API examples](#rest-api-examples) section for more details.
 
-### REST API, D-Bus API and CLI Architectural Relationship
+### REST API and CLI Architectural Relationship
 
-The REST API, D-Bus API and the CLI all rely on a common, [internal API](#internal-api).
+The REST API and the CLI both rely on a common, [internal API](#internal-api).
 
 The CLI options are parsed by the
-[clap crate](https://docs.rs/clap/4.3.11/clap/) and then translated into
+[argh crate](https://docs.rs/argh/latest/argh/) and then translated into
 [internal API](#internal-api) commands.
 
 The REST API is processed by an HTTP thread using the
@@ -299,11 +232,7 @@ The REST API is processed by an HTTP thread using the
 crate. As with the CLI, the HTTP requests eventually get translated into
 [internal API](#internal-api) commands.
 
-The D-Bus API is implemented using the [zbus](https://github.com/dbus2/zbus)
-crate and runs in its own thread. Whenever it needs to call the [internal API](#internal-api),
-the [blocking](https://github.com/smol-rs/blocking) crate is used perform the call in zbus' async context.
-
-As a summary, the REST API, the D-Bus API and the CLI are essentially frontends for the
+As a summary, the REST API and the CLI are essentially frontends for the
 [internal API](#internal-api):
 
 ```
@@ -314,16 +243,16 @@ As a summary, the REST API, the D-Bus API and the CLI are essentially frontends
                        |          +------------------+        |
                        |                                      |      +------------------------+
                        |                                      |      |                        |
-+------------+         |            +----------+              |      |                        |
-|            |         |  D-Bus API |          |              |      | +--------------+       |
-|    User    +---------+----------->+   zbus   +--------------+------> | Internal API |       |
-|            |         |            |          |              |      | +--------------+       |
-+------------+         |            +----------+              |      |                        |
++------------+         |                                      |      |                        |
+|            |         |                                      |      | +--------------+       |
+|    User    +---------+                                      +------> | Internal API |       |
+|            |         |                                      |      | +--------------+       |
++------------+         |                                      |      |                        |
                        |                                      |      |                        |
                        |                                      |      +------------------------+
                        |            +----------+              |                 VMM
                        |     CLI    |          |              |
-                       +----------->+   clap   +--------------+
+                       +----------->+   argh   +--------------+
                                     |          |
                                     +----------+
 
@@ -333,23 +262,22 @@ As a summary, the REST API, the D-Bus API and the CLI are essentially frontends
 ## Internal API
 
 The Cloud Hypervisor internal API, as its name suggests, is used internally
-by the different Cloud Hypervisor threads (VMM, HTTP, D-Bus, control loop,
-etc) to send commands and responses to each others.
+by the different Cloud Hypervisor threads (VMM, HTTP, control loop, etc) to
+send commands and responses to each others.
 
 It is based on [rust's Multi-Producer, Single-Consumer (MPSC)](https://doc.rust-lang.org/std/sync/mpsc/),
 and the single consumer (a.k.a. the API receiver) is the Cloud Hypervisor
 control loop.
 
-API producers are the HTTP thread handling the [REST API](#rest-api), the
-D-Bus thread handling the [D-Bus API](#d-bus-api) and the main thread that
-initially parses the [CLI](#command-line-interface).
+API producers are the HTTP thread handling the [REST API](#rest-api) and the
+main thread that initially parses the [CLI](#command-line-interface).
 
 ### Goals and Design
 
 The internal API is designed for controlling, managing and inspecting a Cloud
 Hypervisor VMM and its guest. It is a backend for handling external, user
-visible requests through the [REST API](#rest-api), the [D-Bus API](#d-bus-api)
-or the [CLI](#command-line-interface) interfaces.
+visible requests through either the [REST API](#rest-api) or the
+[CLI](#command-line-interface) interfaces.
 
 The API follows a command-response scheme that closely maps the [REST API](#rest-api).
 Any command must be replied to with a response.
@@ -381,7 +309,7 @@ APIs work together, let's look at a complete VM creation flow, from the
    [REST API](#rest-api) in order to creates a virtual machine:
    ```
    shell
-   #!/usr/bin/env bash
+   #!/bin/bash
 
 	curl --unix-socket /tmp/cloud-hypervisor.sock -i \
 		-X PUT 'http://localhost/api/v1/vm.create'  \