build: Bump version to 0.5.1

Signed-off-by: Rob Bradford <robert.bradford@intel.com>

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,34 +0,0 @@
----
-name: Bug report
-about: File a bug report
-title: ''
-labels: ''
-assignees: ''
-
----
-
-**Describe the bug**
-A clear and concise description of what the bug is.
-
-**To Reproduce**
-Steps to reproduce the behaviour:
-
-**Version**
-
-Output of `cloud-hypervisor --version`:
-
-Did you build from source, if so build command line (e.g. features):
-
-**VM configuration**
-
-What command line did you run (or JSON config data):
-
-Guest OS version details:
-
-Host OS version details:
-
-**Logs**
-
-Output of `cloud-hypervisor -v` from either standard error or via `--log-file`:
-
-Linux kernel output:

.github/dependabot.yml

@@ -1,18 +0,0 @@
-version: 2
-updates:
-- package-ecosystem: cargo
-  directory: "/"
-  schedule:
-    interval: daily
-  open-pull-requests-limit: 1
-  allow:
-  - dependency-type: direct
-  - dependency-type: indirect
-- package-ecosystem: cargo
-  directory: "/fuzz"
-  schedule:
-    interval: daily
-  open-pull-requests-limit: 1
-  allow:
-  - dependency-type: direct
-  - dependency-type: indirect

.github/workflows/audit.yaml

@@ -1,16 +0,0 @@
-name: Cloud Hypervisor Dependency Audit
-on:
-  pull_request:
-    paths: 
-      - '**/Cargo.toml'
-      - '**/Cargo.lock'
-
-jobs:
-  security_audit:
-    name: Audit
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - uses: actions-rust-lang/audit@v1
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/build.yaml

@@ -1,71 +0,0 @@
-name: Cloud Hypervisor Build
-on: [pull_request, merge_group]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    name: Build
-    runs-on: ubuntu-latest
-    strategy:
-      fail-fast: false
-      matrix:
-        rust:
-          - stable
-          - beta
-          - nightly
-          - "1.77.0"
-        target:
-          - x86_64-unknown-linux-gnu
-          - x86_64-unknown-linux-musl
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Install musl-gcc
-        run: sudo apt install -y musl-tools
-
-      - name: Install Rust toolchain (${{ matrix.rust }})
-        uses: dtolnay/rust-toolchain@stable
-        with:
-          toolchain: ${{ matrix.rust }}
-          target: ${{ matrix.target }}
-
-      - name: Build (default features)
-        run: cargo rustc --locked --bin cloud-hypervisor -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - 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
-
-      - 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
-
-      - 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 (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
-
-      - 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
-
-      - name: Release Build (default features)
-        run: cargo build --locked --all --release --target=${{ matrix.target }}
-
-      - name: Check build did not modify any files
-        run: test -z "$(git status --porcelain)"

.github/workflows/dco.yaml

@@ -1,20 +0,0 @@
-name: DCO
-on: [pull_request, merge_group]
-
-jobs:
-  check:
-    name: DCO Check ("Signed-Off-By")
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v4
-    - name: Set up Python 3.x
-      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: |
-        pip3 install -U dco-check
-        dco-check -e "49699333+dependabot[bot]@users.noreply.github.com"

.github/workflows/docker-image.yaml

@@ -1,65 +0,0 @@
-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
-  IMAGE_NAME: ${{ github.repository }}
-
-jobs:
-  main:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v4
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v1
-
-      - name: Login to ghcr
-        uses: docker/login-action@v2
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-
-      - name: Docker meta
-        id: meta
-        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=20241022-0
-            type=sha
-
-      - name: Build and push
-        if: ${{ github.event_name == 'push' }}
-        uses: docker/build-push-action@v2
-        with:
-          file: ./resources/Dockerfile
-          platforms: linux/amd64,linux/arm64
-          push: true
-          tags: ${{ steps.meta.outputs.tags }}
-
-      - name: Build only
-        if: ${{ github.event_name == 'pull_request' }}
-        uses: docker/build-push-action@v2
-        with:
-          file: ./resources/Dockerfile
-          platforms: linux/amd64,linux/arm64
-          tags: ${{ steps.meta.outputs.tags }}
-
-      - name: Image digest
-        run: echo ${{ steps.docker_build.outputs.digest }}

.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@v4
-      - 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

@@ -1,32 +0,0 @@
-name: Cloud Hypervisor Cargo Fuzz Build
-on: [pull_request, merge_group]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    name: Cargo Fuzz Build
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        rust:
-          - nightly
-        target:
-          - x86_64-unknown-linux-gnu
-    env:
-      RUSTFLAGS: -D warnings
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v4
-      - name: Install Rust toolchain (${{ matrix.rust }})
-        uses: dtolnay/rust-toolchain@stable
-        with:
-            toolchain: ${{ matrix.rust }}
-            target: ${{ matrix.target }}
-      - name: Install Cargo fuzz
-        run: cargo install cargo-fuzz
-      - name: 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@v4
-      with:
-        ref: ${{ github.event.pull_request.head.sha }}
-        fetch-depth: 0
-    - name: Set up Python 3.10
-      uses: actions/setup-python@v3
-      with:
-        python-version: "3.10"
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install --upgrade gitlint
-    - name: Lint git commit messages
-      run: |
-        gitlint --commits origin/$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@v4
-
-      - 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: 60
-    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@v4
-        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: 30
-        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

@@ -1,31 +0,0 @@
-name: Cloud Hypervisor Tests (Metrics)
-on:
-  push:
-    branches:
-      - main
-
-jobs:
-  build:
-    name: Tests (Metrics)
-    runs-on: garm-jammy-16
-    env:
-      METRICS_PUBLISH_KEY: ${{ secrets.METRICS_PUBLISH_KEY }}
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-      - name: Install Docker
-        run: |
-          sudo apt-get update
-          sudo apt-get -y install ca-certificates curl gnupg
-          curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg
-          sudo chmod a+r /usr/share/keyrings/docker-archive-keyring.gpg
-          echo "deb [arch=$(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: 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

@@ -1,35 +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' || 'garm-jammy-16' }}
-    env:
-      AUTH_DOWNLOAD_TOKEN: ${{ secrets.AUTH_DOWNLOAD_TOKEN }}
-    steps:
-      - name: Code checkout
-        if: ${{ github.event_name != 'pull_request' }}
-        uses: actions/checkout@v4
-        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: Run rate-limiter integration tests
-        if: ${{ github.event_name != 'pull_request' }}
-        timeout-minutes: 10
-        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@v4
-        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@v4
-        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@v4
-        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/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@v4
-    - 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/quality.yaml

@@ -1,132 +0,0 @@
-name: Cloud Hypervisor Quality Checks
-on: [pull_request, merge_group]
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    name: Quality (clippy)
-    runs-on: ubuntu-latest
-    continue-on-error: ${{ matrix.experimental }}
-    strategy:
-      fail-fast: false
-      matrix:
-        rust:
-          - beta
-          - stable
-        target:
-          - aarch64-unknown-linux-gnu
-          - aarch64-unknown-linux-musl
-          - x86_64-unknown-linux-gnu
-          - x86_64-unknown-linux-musl
-
-        include:
-          - rust: beta
-            experimental: true
-          - rust: stable
-            experimental: false
-
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Install Rust toolchain (${{ matrix.rust }})
-        uses: actions-rs/toolchain@v1
-        with:
-          toolchain: ${{ matrix.rust }}
-          target: ${{ matrix.target }}
-          override: true
-          components: clippy
-
-      - name: Bisectability Check (default features)
-        if: ${{ github.event_name == 'pull_request' && matrix.target == 'x86_64-unknown-linux-gnu' }}
-        run: |
-          set -e
-          commits=$(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: Clippy (kvm)
-        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 --no-default-features --tests --examples --features "kvm" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Clippy (default features)
-        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 -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - 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 -W clippy::assertions_on_result_states
-
-      - name: Clippy (default features + pvmemcontrol)
-        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 "pvmemcontrol" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - 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 -W clippy::assertions_on_result_states
-
-      - name: Clippy (mshv)
-        if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
-        uses: actions-rs/cargo@v1
-        with:
-          command: clippy
-          args: --target=${{ matrix.target }} --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)
-        if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
-        uses: actions-rs/cargo@v1
-        with:
-          command: clippy
-          args: --target=${{ matrix.target }} --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 (sev_snp)
-        if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
-        uses: actions-rs/cargo@v1
-        with:
-          command: clippy
-          args: --target=${{ matrix.target }} --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
-
-      - name: Clippy (igvm)
-        if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
-        uses: actions-rs/cargo@v1
-        with:
-          command: clippy
-          args: --target=${{ matrix.target }} --locked --all --all-targets --no-default-features --tests --examples --features "igvm" -- -D warnings -D clippy::undocumented_unsafe_blocks -W clippy::assertions_on_result_states
-
-      - name: Clippy (kvm + tdx)
-        if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
-        uses: actions-rs/cargo@v1
-        with:
-          command: clippy
-          args: --target=${{ matrix.target }} --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
-
-      - 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@v4
-      # Executes "typos ."
-      - uses: crate-ci/typos@v1.16.11

.github/workflows/release.yaml

@@ -1,95 +0,0 @@
-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 }}
-
-jobs:
-  release:
-    if: (github.event_name == 'create' && github.event.ref_type == 'tag') || github.event_name == 'merge_group'
-    name: Release ${{ matrix.platform.target }}
-    strategy:
-      fail-fast: false
-      matrix:
-        platform:
-        - target: x86_64-unknown-linux-gnu
-          args: --all --release --features mshv
-          name_ch: cloud-hypervisor
-          name_ch_remote: ch-remote
-        - target: x86_64-unknown-linux-musl
-          args: --all --release --features mshv
-          name_ch: cloud-hypervisor-static
-          name_ch_remote: ch-remote-static
-        - target: aarch64-unknown-linux-musl
-          args:  --all --release
-          name_ch: cloud-hypervisor-static-aarch64
-          name_ch_remote: ch-remote-static-aarch64
-    runs-on: ubuntu-latest
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v4
-      - name: Install musl-gcc
-        if: contains(matrix.platform.target, 'musl')
-        run: sudo apt install -y musl-tools
-      - name: Create release directory
-        if: |
-          github.event_name == 'create' && github.event.ref_type == 'tag' &&
-          matrix.platform.target == 'x86_64-unknown-linux-gnu'
-        run: rsync -rv --exclude=.git . ../cloud-hypervisor-${{ github.event.ref }}
-      - name: Build ${{ matrix.platform.target }}
-        uses: houseabsolute/actions-rust-cross@v0
-        with:
-          command: build
-          target: ${{ matrix.platform.target }}
-          args: ${{ matrix.platform.args  }}
-          strip: true
-          toolchain: "1.77.0"
-      - name: Copy Release Binaries
-        if: github.event_name == 'create' && github.event.ref_type == 'tag'
-        shell: bash
-        run: |
-          cp target/${{ 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@v3
-        with:
-          name: Artifacts for ${{ matrix.platform.target }}
-          path: |
-            ./${{ matrix.platform.name_ch }}
-            ./${{ matrix.platform.name_ch_remote }}
-      - name: Vendor
-        if: |
-          github.event_name == 'create' && github.event.ref_type == 'tag' &&
-          matrix.platform.target == 'x86_64-unknown-linux-gnu'
-        working-directory: ../cloud-hypervisor-${{ github.event.ref }}
-        run: |
-          mkdir ../vendor-cargo-home
-          export CARGO_HOME=$(realpath ../vendor-cargo-home)
-          mkdir .cargo
-          cargo vendor > .cargo/config.toml
-      - name: Create vendored source archive
-        if: |
-          github.event_name == 'create' && github.event.ref_type == 'tag' &&
-          matrix.platform.target == 'x86_64-unknown-linux-gnu'
-        run: tar cJf cloud-hypervisor-${{ github.event.ref }}.tar.xz ../cloud-hypervisor-${{ github.event.ref }}
-      - name: Upload cloud-hypervisor vendored source archive
-        if: |
-          github.event_name == 'create' && github.event.ref_type == 'tag' &&
-          matrix.platform.target == 'x86_64-unknown-linux-gnu'
-        id: upload-release-cloud-hypervisor-vendored-sources
-        uses: actions/upload-artifact@v3
-        with:
-          path: cloud-hypervisor-${{ github.event.ref }}.tar.xz
-          name: cloud-hypervisor-${{ github.event.ref }}.tar.xz
-      - name: Create GitHub Release
-        if: github.event_name == 'create' && github.event.ref_type == 'tag'
-        uses: softprops/action-gh-release@v1
-        with:
-          draft: true
-          files: |
-            ./${{ matrix.platform.name_ch }}
-            ./${{ matrix.platform.name_ch_remote }}
-            ./cloud-hypervisor-${{ github.event.ref }}.tar.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@v4
-    - name: REUSE Compliance Check
-      uses: fsfe/reuse-action@v3

.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@v4
-    - 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@v4
-      - 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

@@ -1,9 +1,4 @@
-/build
-/.cargo
 /target
 **/*.rs.bk
 **/Cargo.lock
 **/rusty-tags.vi
-/rpm/SOURCES
-/.vscode
-/vendor

.gitlint

@@ -1,15 +0,0 @@
-[general]
-extra-path=scripts/gitlint/rules.py
-regex-style-search=true
-
-[ignore-by-author-name]
-regex=dependabot
-ignore=all
-
-# default 72
-[title-max-length]
-line-length=72
-
-# default 80
-[body-max-line-length]
-line-length=72

.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 +0,0 @@
-edition = "2021"
-group_imports="StdExternalCrate"
-imports_granularity="Module"
-

.taplo.toml

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

.travis.yml

@@ -0,0 +1,16 @@
+language: rust
+
+rust:
+  - stable
+
+script:
+  - cargo build --release
+  
+deploy:
+  provider: releases
+  api_key: $GITHUB_OAUTH_TOKEN
+  file: target/release/cloud-hypervisor
+  skip_cleanup: true
+  draft: true
+  on:
+    tags: true

.typos.toml

@@ -1,21 +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]
-ba = "ba"
-CLASSE = "CLASSE"
-conectix = "conectix"
-Dake = "Dake"
-EXTINT = "EXTINT"
-INOUT = "INOUT"
-liness = "liness"
-outout = "outout"
-
-[default.extend-identifiers]
-fo = "fo"
-fpr = "fpr"

CODEOWNERS

@@ -1,2 +0,0 @@
-# Add the list of code owners here (using their GitHub username)
-* @cloud-hypervisor/cloud-hypervisor-reviewers

CONTRIBUTING.md

@@ -1,15 +1,6 @@
 # Contributing to Cloud Hypervisor
 
-Cloud Hypervisor is an open source project licensed under the [Apache v2
-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
-license of those projects.
-
-New code should be under the [Apache v2
-License](https://opensource.org/licenses/Apache-2.0).
+Cloud Hypervisor is an open source project licensed under the [Apache v2 License](https://opensource.org/licenses/Apache-2.0) and the [BSD 3 Clause](https://opensource.org/licenses/BSD-3-Clause) license.
 
 ## Coding Style
 
@@ -17,23 +8,6 @@ We follow the [Rust Style](https://github.com/rust-dev-tools/fmt-rfcs/blob/maste
 convention and enforce it through the Continuous Integration (CI) process calling into `rustfmt`
 for each submitted Pull Request (PR).
 
-## Basic Checks
-
-Please consider creating the following hook as `.git/hooks/pre-commit` in order
-to ensure basic correctness of your code. You can extend this further if you
-have specific features that you regularly develop against.
-
-```sh
-#!/bin/sh
-
-cargo fmt -- --check || exit 1
-cargo check --locked --all --all-targets --tests || exit 1
-cargo clippy --locked --all --all-targets --tests -- -D warnings || exit 1
-```
-
-You will need to `chmod +x .git/hooks/pre-commit` to have it run on every
-commit you make.
-
 ## Certificate of Origin
 
 In order to get a clear contribution chain of trust we use the [signed-off-by language](https://01.org/community/signed-process)
@@ -81,10 +55,12 @@ you want to merge your changes to `cloud-hypervisor`:
    into your github organization.
 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.
-4. To update your pull request amend existing commits whenever applicable and
+   against the master branch of the Cloud Hypervisor repository.
+4. Add reviewers to your pull request and then work with your reviewers to address
+   any comments and obtain minimum of 2 [maintainers](MAINTAINERS.md) approvals.
+   To update your pull request amend existing commits whenever applicable and
    then push the new changes to your pull request branch.
-5. Once the pull request is approved it can be integrated.
+5. Once the pull request is approved, one of the maintainers will merge it.
 
 ## Issue tracking
 
@@ -112,5 +88,5 @@ 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 correspoding PR is merged, Github will automatically close that issue when parsing the
 [commit message](https://help.github.com/articles/closing-issues-via-commit-messages/).

Cargo.toml

@@ -1,120 +1,68 @@
 [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 = "2021"
-homepage = "https://github.com/cloud-hypervisor/cloud-hypervisor"
-license = "Apache-2.0 AND BSD-3-Clause"
 name = "cloud-hypervisor"
-version = "42.0.0"
-# Minimum buildable version:
-# Keep in sync with version in .github/workflows/build.yaml
-# Policy on MSRV (see #4318):
-# 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 = "1.77.0"
-
-[profile.release]
-codegen-units = 1
-lto = true
-opt-level = "s"
-strip = true
-
-[profile.profiling]
-debug = true
-inherits = "release"
-strip = false
+version = "0.5.1"
+authors = ["The Cloud Hypervisor Authors"]
+edition = "2018"
+default-run = "cloud-hypervisor"
 
 [dependencies]
-anyhow = "1.0.87"
-api_client = { path = "api_client" }
-clap = { version = "4.5.13", features = ["string"] }
-dhat = { version = "0.3.3", optional = true }
-epoll = "4.3.3"
-event_monitor = { path = "event_monitor" }
-hypervisor = { path = "hypervisor" }
-libc = "0.2.158"
-log = { version = "0.4.22", features = ["std"] }
-option_parser = { path = "option_parser" }
-seccompiler = { workspace = true }
-serde_json = "1.0.120"
-signal-hook = "0.3.17"
-thiserror = "1.0.62"
-tpm = { path = "tpm" }
-tracer = { path = "tracer" }
-vm-memory = { workspace = true }
+arc-swap = "0.4.4"
+clap = "2.33.0"
+epoll = "4.1.0"
+lazy_static = "1.4.0"
+libc = "0.2.66"
+log = { version = "0.4.8", features = ["std"] }
+vhost_user_backend = { path = "vhost_user_backend"}
+vhost_user_block = { path = "vhost_user_block"}
+vhost_user_fs = { path = "vhost_user_fs"}
+vhost_user_net = { path = "vhost_user_net"}
+virtio-bindings = "0.1.0"
 vmm = { path = "vmm" }
-vmm-sys-util = { workspace = true }
-zbus = { version = "4.4.0", optional = true }
+vm-device = { path = "vm-device" }
+vm-memory = { git = "https://github.com/rust-vmm/vm-memory" }
+vmm-sys-util = "0.4.0"
+vm-virtio = { path = "vm-virtio" }
+
+[dependencies.vhost_rs]
+path = "vhost_rs"
+features = ["vhost-user-slave"]
 
 [dev-dependencies]
-dirs = "5.0.1"
-net_util = { path = "net_util" }
-once_cell = "1.20.2"
-serde_json = "1.0.120"
-test_infra = { path = "test_infra" }
-wait-timeout = "0.2.0"
+ssh2 = "0.7.1"
+dirs = "2.0.2"
+credibility = "0.1.3"
+tempdir= "0.3.7"
+lazy_static= "1.4.0"
+serde_json = "1.0.48"
 
-# 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
-guest_debug = ["vmm/guest_debug"]
-igvm = ["mshv", "vmm/igvm"]
-io_uring = ["vmm/io_uring"]
-kvm = ["vmm/kvm"]
-mshv = ["vmm/mshv"]
-pvmemcontrol = ["vmm/pvmemcontrol"]
-sev_snp = ["igvm", "mshv", "vmm/sev_snp"]
-tdx = ["vmm/tdx"]
-tracing = ["tracer/tracing", "vmm/tracing"]
+default = ["acpi", "pci", "cmos"]
+acpi = ["vmm/acpi"]
+pci = ["vmm/pci_support"]
+mmio = ["vmm/mmio_support"]
+cmos = ["vmm/cmos"]
+
+# Integration tests require a special environment to run in
+integration_tests = []
 
 [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",
+    "arch",
+    "devices",
+    "vhost_rs",
+    "qcow",
+    "pci",
+    "vmm",
+    "vm-virtio",
+    "vm-device",
+    "vhost_user_block",
+    "vhost_user_backend",
+    "vhost_user_fs",
+    "vhost_user_net",
+    "vfio",
+    "net_util",
+    "acpi_tables",
+    "arch_gen",
+    "net_gen",
+    "vm-allocator",
 ]
-
-[workspace.dependencies]
-acpi_tables = { git = "https://github.com/rust-vmm/acpi_tables", branch = "main" }
-kvm-bindings = "0.9.1"
-kvm-ioctls = "0.18.0"
-linux-loader = "0.12.0"
-mshv-bindings = { git = "https://github.com/rust-vmm/mshv", tag = "v0.3.0" }
-mshv-ioctls = { git = "https://github.com/rust-vmm/mshv", tag = "v0.3.0" }
-seccompiler = "0.4.0"
-vfio-bindings = { git = "https://github.com/rust-vmm/vfio", branch = "main" }
-vfio-ioctls = { git = "https://github.com/rust-vmm/vfio", branch = "main", default-features = false }
-vfio_user = { git = "https://github.com/rust-vmm/vfio-user", branch = "main" }
-vhost = "0.12.0"
-virtio-bindings = "0.2.2"
-virtio-queue = "0.13.0"
-vm-fdt = { git = "https://github.com/rust-vmm/vm-fdt", branch = "main" }
-vm-memory = "0.15.0"
-vmm-sys-util = "0.12.1"

Jenkinsfile

@@ -0,0 +1,85 @@
+pipeline{
+	agent none
+	stages {
+		stage ('Master build') {
+			agent { node { label 'master' } }
+			stages {
+				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') {
+					steps {
+						cancelPreviousBuilds()
+					}
+				}
+			}
+		}
+		stage ('Worker build') {
+			agent { node { label 'bionic' } }
+			options {
+				timeout(time: 1, unit: 'HOURS')
+			}
+			stages {
+				stage ('Checkout') {
+					steps {
+						checkout scm
+					}
+				}
+				stage ('Install system packages') {
+					steps {
+						sh "sudo DEBIAN_FRONTEND=noninteractive apt-get install -yq build-essential mtools libssl-dev pkg-config"
+							sh "sudo apt-get install -yq flex bison libelf-dev qemu-utils qemu-system libglib2.0-dev libpixman-1-dev libseccomp-dev libcap-ng-dev socat"
+							sh "sudo snap install docker"
+					}
+				}
+				stage ('Install Rust') {
+					steps {
+						sh "nohup curl https://sh.rustup.rs -sSf | sh -s -- -y"
+					}
+				}
+				stage ('Run Cargo tests') {
+					steps {
+						sh "scripts/run_cargo_tests.sh"
+					}
+				}
+				stage ('Run OpenAPI tests') {
+					steps {
+						sh "scripts/run_openapi_tests.sh"
+					}
+				}
+				stage ('Run unit tests') {
+					steps {
+						sh "scripts/run_unit_tests.sh"
+					}
+				}
+				stage ('Run integration tests') {
+					steps {
+						sh "sudo mount -t tmpfs tmpfs /tmp"
+							sh "scripts/run_integration_tests.sh"
+					}
+				}
+			}
+		}
+	}
+}
+
+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()
+			}
+		}
+}

LICENSES/CC-BY-4.0.txt

@@ -1,400 +0,0 @@
-All documentations (e.g. files with extension `.md`) in this repository is
-covered by the following license:
-
-Attribution 4.0 International
-
-=======================================================================
-
-Creative Commons Corporation ("Creative Commons") is not a law firm and
-does not provide legal services or legal advice. Distribution of
-Creative Commons public licenses does not create a lawyer-client or
-other relationship. Creative Commons makes its licenses and related
-information available on an "as-is" basis. Creative Commons gives no
-warranties regarding its licenses, any material licensed under their
-terms and conditions, or any related information. Creative Commons
-disclaims all liability for damages resulting from their use to the
-fullest extent possible.
-
-Using Creative Commons Public Licenses
-
-Creative Commons public licenses provide a standard set of terms and
-conditions that creators and other rights holders may use to share
-original works of authorship and other material subject to copyright
-and certain other rights specified in the public license below. The
-following considerations are for informational purposes only, are not
-exhaustive, and do not form part of our licenses.
-
-     Considerations for licensors: Our public licenses are
-     intended for use by those authorized to give the public
-     permission to use material in ways otherwise restricted by
-     copyright and certain other rights. Our licenses are
-     irrevocable. Licensors should read and understand the terms
-     and conditions of the license they choose before applying it.
-     Licensors should also secure all rights necessary before
-     applying our licenses so that the public can reuse the
-     material as expected. Licensors should clearly mark any
-     material not subject to the license. This includes other CC-
-     licensed material, or material used under an exception or
-     limitation to copyright. More considerations for licensors:
-    wiki.creativecommons.org/Considerations_for_licensors
-
-     Considerations for the public: By using one of our public
-     licenses, a licensor grants the public permission to use the
-     licensed material under specified terms and conditions. If
-     the licensor's permission is not necessary for any reason--for
-     example, because of any applicable exception or limitation to
-     copyright--then that use is not regulated by the license. Our
-     licenses grant only permissions under copyright and certain
-     other rights that a licensor has authority to grant. Use of
-     the licensed material may still be restricted for other
-     reasons, including because others have copyright or other
-     rights in the material. A licensor may make special requests,
-     such as asking that all changes be marked or described.
-     Although not required by our licenses, you are encouraged to
-     respect those requests where reasonable. More considerations
-     for the public:
-    wiki.creativecommons.org/Considerations_for_licensees
-
-=======================================================================
-
-Creative Commons Attribution 4.0 International Public License
-
-By exercising the Licensed Rights (defined below), You accept and agree
-to be bound by the terms and conditions of this Creative Commons
-Attribution 4.0 International Public License ("Public License"). To the
-extent this Public License may be interpreted as a contract, You are
-granted the Licensed Rights in consideration of Your acceptance of
-these terms and conditions, and the Licensor grants You such rights in
-consideration of benefits the Licensor receives from making the
-Licensed Material available under these terms and conditions.
-
-
-Section 1 -- Definitions.
-
-  a. Adapted Material means material subject to Copyright and Similar
-     Rights that is derived from or based upon the Licensed Material
-     and in which the Licensed Material is translated, altered,
-     arranged, transformed, or otherwise modified in a manner requiring
-     permission under the Copyright and Similar Rights held by the
-     Licensor. For purposes of this Public License, where the Licensed
-     Material is a musical work, performance, or sound recording,
-     Adapted Material is always produced where the Licensed Material is
-     synched in timed relation with a moving image.
-
-  b. Adapter's License means the license You apply to Your Copyright
-     and Similar Rights in Your contributions to Adapted Material in
-     accordance with the terms and conditions of this Public License.
-
-  c. Copyright and Similar Rights means copyright and/or similar rights
-     closely related to copyright including, without limitation,
-     performance, broadcast, sound recording, and Sui Generis Database
-     Rights, without regard to how the rights are labeled or
-     categorized. For purposes of this Public License, the rights
-     specified in Section 2(b)(1)-(2) are not Copyright and Similar
-     Rights.
-
-  d. Effective Technological Measures means those measures that, in the
-     absence of proper authority, may not be circumvented under laws
-     fulfilling obligations under Article 11 of the WIPO Copyright
-     Treaty adopted on December 20, 1996, and/or similar international
-     agreements.
-
-  e. Exceptions and Limitations means fair use, fair dealing, and/or
-     any other exception or limitation to Copyright and Similar Rights
-     that applies to Your use of the Licensed Material.
-
-  f. Licensed Material means the artistic or literary work, database,
-     or other material to which the Licensor applied this Public
-     License.
-
-  g. Licensed Rights means the rights granted to You subject to the
-     terms and conditions of this Public License, which are limited to
-     all Copyright and Similar Rights that apply to Your use of the
-     Licensed Material and that the Licensor has authority to license.
-
-  h. Licensor means the individual(s) or entity(ies) granting rights
-     under this Public License.
-
-  i. Share means to provide material to the public by any means or
-     process that requires permission under the Licensed Rights, such
-     as reproduction, public display, public performance, distribution,
-     dissemination, communication, or importation, and to make material
-     available to the public including in ways that members of the
-     public may access the material from a place and at a time
-     individually chosen by them.
-
-  j. Sui Generis Database Rights means rights other than copyright
-     resulting from Directive 96/9/EC of the European Parliament and of
-     the Council of 11 March 1996 on the legal protection of databases,
-     as amended and/or succeeded, as well as other essentially
-     equivalent rights anywhere in the world.
-
-  k. You means the individual or entity exercising the Licensed Rights
-     under this Public License. Your has a corresponding meaning.
-
-
-Section 2 -- Scope.
-
-  a. License grant.
-
-       1. Subject to the terms and conditions of this Public License,
-          the Licensor hereby grants You a worldwide, royalty-free,
-          non-sublicensable, non-exclusive, irrevocable license to
-          exercise the Licensed Rights in the Licensed Material to:
-
-            a. reproduce and Share the Licensed Material, in whole or
-               in part; and
-
-            b. produce, reproduce, and Share Adapted Material.
-
-       2. Exceptions and Limitations. For the avoidance of doubt, where
-          Exceptions and Limitations apply to Your use, this Public
-          License does not apply, and You do not need to comply with
-          its terms and conditions.
-
-       3. Term. The term of this Public License is specified in Section
-          6(a).
-
-       4. Media and formats; technical modifications allowed. The
-          Licensor authorizes You to exercise the Licensed Rights in
-          all media and formats whether now known or hereafter created,
-          and to make technical modifications necessary to do so. The
-          Licensor waives and/or agrees not to assert any right or
-          authority to forbid You from making technical modifications
-          necessary to exercise the Licensed Rights, including
-          technical modifications necessary to circumvent Effective
-          Technological Measures. For purposes of this Public License,
-          simply making modifications authorized by this Section 2(a)
-          (4) never produces Adapted Material.
-
-       5. Downstream recipients.
-
-            a. Offer from the Licensor -- Licensed Material. Every
-               recipient of the Licensed Material automatically
-               receives an offer from the Licensor to exercise the
-               Licensed Rights under the terms and conditions of this
-               Public License.
-
-            b. No downstream restrictions. You may not offer or impose
-               any additional or different terms or conditions on, or
-               apply any Effective Technological Measures to, the
-               Licensed Material if doing so restricts exercise of the
-               Licensed Rights by any recipient of the Licensed
-               Material.
-
-       6. No endorsement. Nothing in this Public License constitutes or
-          may be construed as permission to assert or imply that You
-          are, or that Your use of the Licensed Material is, connected
-          with, or sponsored, endorsed, or granted official status by,
-          the Licensor or others designated to receive attribution as
-          provided in Section 3(a)(1)(A)(i).
-
-  b. Other rights.
-
-       1. Moral rights, such as the right of integrity, are not
-          licensed under this Public License, nor are publicity,
-          privacy, and/or other similar personality rights; however, to
-          the extent possible, the Licensor waives and/or agrees not to
-          assert any such rights held by the Licensor to the limited
-          extent necessary to allow You to exercise the Licensed
-          Rights, but not otherwise.
-
-       2. Patent and trademark rights are not licensed under this
-          Public License.
-
-       3. To the extent possible, the Licensor waives any right to
-          collect royalties from You for the exercise of the Licensed
-          Rights, whether directly or through a collecting society
-          under any voluntary or waivable statutory or compulsory
-          licensing scheme. In all other cases the Licensor expressly
-          reserves any right to collect such royalties.
-
-
-Section 3 -- License Conditions.
-
-Your exercise of the Licensed Rights is expressly made subject to the
-following conditions.
-
-  a. Attribution.
-
-       1. If You Share the Licensed Material (including in modified
-          form), You must:
-
-            a. retain the following if it is supplied by the Licensor
-               with the Licensed Material:
-
-                 i. identification of the creator(s) of the Licensed
-                    Material and any others designated to receive
-                    attribution, in any reasonable manner requested by
-                    the Licensor (including by pseudonym if
-                    designated);
-
-                ii. a copyright notice;
-
-               iii. a notice that refers to this Public License;
-
-                iv. a notice that refers to the disclaimer of
-                    warranties;
-
-                 v. a URI or hyperlink to the Licensed Material to the
-                    extent reasonably practicable;
-
-            b. indicate if You modified the Licensed Material and
-               retain an indication of any previous modifications; and
-
-            c. indicate the Licensed Material is licensed under this
-               Public License, and include the text of, or the URI or
-               hyperlink to, this Public License.
-
-       2. You may satisfy the conditions in Section 3(a)(1) in any
-          reasonable manner based on the medium, means, and context in
-          which You Share the Licensed Material. For example, it may be
-          reasonable to satisfy the conditions by providing a URI or
-          hyperlink to a resource that includes the required
-          information.
-
-       3. If requested by the Licensor, You must remove any of the
-          information required by Section 3(a)(1)(A) to the extent
-          reasonably practicable.
-
-       4. If You Share Adapted Material You produce, the Adapter's
-          License You apply must not prevent recipients of the Adapted
-          Material from complying with this Public License.
-
-
-Section 4 -- Sui Generis Database Rights.
-
-Where the Licensed Rights include Sui Generis Database Rights that
-apply to Your use of the Licensed Material:
-
-  a. for the avoidance of doubt, Section 2(a)(1) grants You the right
-     to extract, reuse, reproduce, and Share all or a substantial
-     portion of the contents of the database;
-
-  b. if You include all or a substantial portion of the database
-     contents in a database in which You have Sui Generis Database
-     Rights, then the database in which You have Sui Generis Database
-     Rights (but not its individual contents) is Adapted Material; and
-
-  c. You must comply with the conditions in Section 3(a) if You Share
-     all or a substantial portion of the contents of the database.
-
-For the avoidance of doubt, this Section 4 supplements and does not
-replace Your obligations under this Public License where the Licensed
-Rights include other Copyright and Similar Rights.
-
-
-Section 5 -- Disclaimer of Warranties and Limitation of Liability.
-
-  a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE
-     EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS
-     AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF
-     ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS,
-     IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION,
-     WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR
-     PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS,
-     ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT
-     KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT
-     ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU.
-
-  b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE
-     TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION,
-     NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT,
-     INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES,
-     COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR
-     USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN
-     ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR
-     DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR
-     IN PART, THIS LIMITATION MAY NOT APPLY TO YOU.
-
-  c. The disclaimer of warranties and limitation of liability provided
-     above shall be interpreted in a manner that, to the extent
-     possible, most closely approximates an absolute disclaimer and
-     waiver of all liability.
-
-
-Section 6 -- Term and Termination.
-
-  a. This Public License applies for the term of the Copyright and
-     Similar Rights licensed here. However, if You fail to comply with
-     this Public License, then Your rights under this Public License
-     terminate automatically.
-
-  b. Where Your right to use the Licensed Material has terminated under
-     Section 6(a), it reinstates:
-
-       1. automatically as of the date the violation is cured, provided
-          it is cured within 30 days of Your discovery of the
-          violation; or
-
-       2. upon express reinstatement by the Licensor.
-
-     For the avoidance of doubt, this Section 6(b) does not affect any
-     right the Licensor may have to seek remedies for Your violations
-     of this Public License.
-
-  c. For the avoidance of doubt, the Licensor may also offer the
-     Licensed Material under separate terms or conditions or stop
-     distributing the Licensed Material at any time; however, doing so
-     will not terminate this Public License.
-
-  d. Sections 1, 5, 6, 7, and 8 survive termination of this Public
-     License.
-
-
-Section 7 -- Other Terms and Conditions.
-
-  a. The Licensor shall not be bound by any additional or different
-     terms or conditions communicated by You unless expressly agreed.
-
-  b. Any arrangements, understandings, or agreements regarding the
-     Licensed Material not stated herein are separate from and
-     independent of the terms and conditions of this Public License.
-
-
-Section 8 -- Interpretation.
-
-  a. For the avoidance of doubt, this Public License does not, and
-     shall not be interpreted to, reduce, limit, restrict, or impose
-     conditions on any use of the Licensed Material that could lawfully
-     be made without permission under this Public License.
-
-  b. To the extent possible, if any provision of this Public License is
-     deemed unenforceable, it shall be automatically reformed to the
-     minimum extent necessary to make it enforceable. If the provision
-     cannot be reformed, it shall be severed from this Public License
-     without affecting the enforceability of the remaining terms and
-     conditions.
-
-  c. No term or condition of this Public License will be waived and no
-     failure to comply consented to unless expressly agreed to by the
-     Licensor.
-
-  d. Nothing in this Public License constitutes or may be interpreted
-     as a limitation upon, or waiver of, any privileges and immunities
-     that apply to the Licensor or You, including from the legal
-     processes of any jurisdiction or authority.
-
-
-=======================================================================
-
-Creative Commons is not a party to its public
-licenses. Notwithstanding, Creative Commons may elect to apply one of
-its public licenses to material it publishes and in those instances
-will be considered the “Licensor.” The text of the Creative Commons
-public licenses is dedicated to the public domain under the CC0 Public
-Domain Dedication. Except for the limited purpose of indicating that
-material is shared under a Creative Commons public license or as
-otherwise permitted by the Creative Commons policies published at
-creativecommons.org/policies, Creative Commons does not authorize the
-use of the trademark "Creative Commons" or any other trademark or logo
-of Creative Commons without its prior written consent including,
-without limitation, in connection with any unauthorized modifications
-to any of its public licenses or any other arrangements,
-understandings, or agreements concerning use of licensed material. For
-the avoidance of doubt, this paragraph does not form part of the
-public licenses.
-
-Creative Commons may be contacted at creativecommons.org.
-
-

MAINTAINERS.md

@@ -1,8 +1,6 @@
 # Maintainers
 
-- Sebastien Boeuf - @sboeuf
-- Robert Bradford - @rbradford
-- Bo Chen - @likebreath
-- Samuel Ortiz - @sameo
-- Wei Liu - @liuw
-- Michael Zhao - @michael2012z
+- Sebastien Boeuf <sebastien.boeuf@intel.com> @sboeuf
+- Robert Bradford <robert.bradford@intel.com> @rbradford
+- Samuel Ortiz <sameo@linux.intel.com> @sameo
+- Chao P Peng <chao.p.peng@linux.intel.com> @chao-p

README.md

@@ -1,390 +1,324 @@
-- [1. What is Cloud Hypervisor?](#1-what-is-cloud-hypervisor)
-  - [Objectives](#objectives)
-    - [High Level](#high-level)
-    - [Architectures](#architectures)
-    - [Guest OS](#guest-os)
-- [2. Getting Started](#2-getting-started)
-  - [Host OS](#host-os)
-  - [Use Pre-built Binaries](#use-pre-built-binaries)
-  - [Packages](#packages)
-  - [Building from Source](#building-from-source)
-  - [Booting Linux](#booting-linux)
-    - [Firmware Booting](#firmware-booting)
-    - [Custom Kernel and Disk Image](#custom-kernel-and-disk-image)
-      - [Building your Kernel](#building-your-kernel)
-      - [Disk image](#disk-image)
-      - [Booting the guest VM](#booting-the-guest-vm)
-- [3. Status](#3-status)
-  - [Hot Plug](#hot-plug)
-  - [Device Model](#device-model)
-  - [Roadmap](#roadmap)
-- [4. Relationship with _Rust VMM_ Project](#4-relationship-with-rust-vmm-project)
-  - [Differences with Firecracker and crosvm](#differences-with-firecracker-and-crosvm)
-- [5. Community](#5-community)
-  - [Contribute](#contribute)
-  - [Slack](#slack)
-  - [Mailing list](#mailing-list)
-  - [Security issues](#security-issues)
+[![Build Status](https://travis-ci.com/cloud-hypervisor/cloud-hypervisor.svg?branch=master)](https://travis-ci.com/cloud-hypervisor/cloud-hypervisor)
+
+1. [What is Cloud Hypervisor?](#1-what-is-cloud-hypervisor)
+   * [Requirements](#requirements)
+	 + [High Level](#high-level)
+     + [Architectures](#architectures)
+	 + [Guest OS](#guest-os)
+2. [Getting Started](#2-getting-started)
+   * [Clone and build](#clone-and-build)
+   * [Run](#run)
+	 + [Cloud image](#cloud-image)
+	 + [Custom kernel and disk image](#custom-kernel-and-disk-image)
+		 - [Building your kernel](#building-your-kernel)
+		 - [Disk image](#disk-image)
+		 - [Booting the guest VM](#booting-the-guest-vm)
+3. [Status](#2-status)
+	* [Device Model](#device-model)
+	* [TODO](#todo)
+4. [rust-vmm dependency](#4-rust-vmm-dependency)
+	* [Firecracker and crosvm](#firecracker-and-crosvm)
+5. [Community](#5-community)
+	* [Join us](#join-us)
+6. [Security](#6-security)
 
 # 1. What is Cloud Hypervisor?
 
-Cloud Hypervisor is an open source Virtual Machine Monitor (VMM) that runs on
-top of the [KVM](https://www.kernel.org/doc/Documentation/virtual/kvm/api.txt)
-hypervisor and the Microsoft Hypervisor (MSHV).
+**This project is an experiment and should not be used with production workloads.**
 
-The project focuses on running modern, _Cloud Workloads_, on specific, common,
-hardware architectures. In this case _Cloud Workloads_ refers to those that are
-run by customers inside a Cloud Service Provider. This means modern operating
-systems with most I/O handled by
-paravirtualised devices (e.g. _virtio_), no requirement for legacy devices, and
-64-bit CPUs.
+Cloud Hypervisor is an open source Virtual Machine Monitor (VMM) that runs on top of [KVM](https://www.kernel.org/doc/Documentation/virtual/kvm/api.txt).
+The project focuses on exclusively running modern, cloud workloads, on top of a limited set of hardware architectures and platforms.
+Cloud workloads refers to those that are usually run by customers inside a cloud provider. For our purposes this means modern
+Linux* distributions with most I/O handled by paravirtualised devices (i.e. virtio), no requirement for legacy devices and recent CPUs and KVM.
 
-Cloud Hypervisor is implemented in [Rust](https://www.rust-lang.org/) and is
-based on the [Rust VMM](https://github.com/rust-vmm) crates.
+Cloud Hypervisor is implemented in [Rust](https://www.rust-lang.org/) and is based on the [rust-vmm](https://github.com/rust-vmm) crates.
 
 ## Objectives
 
 ### High Level
 
-- Runs on KVM or MSHV
-- Minimal emulation
-- Low latency
-- Low memory footprint
-- Low complexity
-- High performance
-- Small attack surface
-- 64-bit support only
-- CPU, memory, PCI hotplug
-- Machine to machine migration
+* KVM and KVM only based
+* Minimal emulation
+* Low latency
+* Low memory footprint
+* Low complexity
+* High performance
+* Small attack surface
+* 64-bit support only
+* Build time configurable CPU, memory, PCI and NVDIMM hotplug
+* Machine to machine migration
 
 ### Architectures
 
-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)).
+`cloud-hypervisor` only supports the `x86-64` CPU architecture for now.
+
+We're planning to add support for the `AArch64` architecture in the future.
 
 ### Guest OS
+* `64-bit Linux`
 
-Cloud Hypervisor supports `64-bit Linux` and Windows 10/Windows Server 2019.
+Support for *modern* 64-bit Windows guest is being evaluated.
 
 # 2. Getting Started
 
-The following sections describe how to build and run Cloud Hypervisor.
-
-## Prerequisites for AArch64
-
-- AArch64 servers (recommended) or development boards equipped with the GICv3
-  interrupt controller.
-
-## 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.
-
-## Use Pre-built Binaries
-
-The recommended approach to getting started with Cloud Hypervisor is by using a
-pre-built binary. Binaries are available for the [latest
-release](https://github.com/cloud-hypervisor/cloud-hypervisor/releases/latest).
-Use `cloud-hypervisor-static` for `x86-64` or `cloud-hypervisor-static-aarch64`
-for `AArch64` platform.
-
-## Packages
-
-For convenience, packages are also available targeting some popular Linux
-distributions. This is thanks to the [Open Build
-Service](https://build.opensuse.org). The [OBS
-README](https://github.com/cloud-hypervisor/obs-packaging) explains how to
-enable the repository in a supported Linux distribution and install Cloud Hypervisor
-and accompanying packages. Please report any packaging issues in the
-[obs-packaging](https://github.com/cloud-hypervisor/obs-packaging) repository.
-
-## Building from Source
-
-Please see the [instructions for building from source](docs/building.md) if you
-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
-Firmware](https://github.com/cloud-hypervisor/rust-hypervisor-firmware) or an
-edk2 UEFI firmware called `CLOUDHV` / `CLOUDHV_EFI`.)
-
-Binary builds of the firmware files are available for the latest release of
-[Rust Hypervisor
-Firmware](https://github.com/cloud-hypervisor/rust-hypervisor-firmware/releases/latest)
-and [our edk2
-repository](https://github.com/cloud-hypervisor/edk2/releases/latest)
-
-The choice of firmware depends on your guest OS choice; some experimentation
-may be required.
-
-### Firmware Booting
-
-Cloud Hypervisor supports booting disk images containing all needed components
-to run cloud workloads, a.k.a. cloud images.
-
-The following sample commands will download an Ubuntu Cloud image, converting
-it into a format that Cloud Hypervisor can use and a firmware to boot the image
-with.
+We create a folder to build and run `cloud-hypervisor` at `$HOME/cloud-hypervisor`
 
 ```shell
-$ wget https://cloud-images.ubuntu.com/focal/current/focal-server-cloudimg-amd64.img
-$ qemu-img convert -p -f qcow2 -O raw focal-server-cloudimg-amd64.img focal-server-cloudimg-amd64.raw
-$ wget https://github.com/cloud-hypervisor/rust-hypervisor-firmware/releases/download/0.4.2/hypervisor-fw
+$ export CLOUDH=$HOME/cloud-hypervisor
+$ mkdir $CLOUDH
 ```
 
-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.
+## Clone and build
+
+First you need to clone and build the cloud-hypervisor repo:
 
 ```shell
-$ sudo setcap cap_net_admin+ep ./cloud-hypervisor
-$ ./create-cloud-init.sh
-$ ./cloud-hypervisor \
-	--kernel ./hypervisor-fw \
-	--disk path=focal-server-cloudimg-amd64.raw path=/tmp/ubuntu-cloudinit.img \
-	--cpus boot=4 \
-	--memory size=1024M \
-	--net "tap=,mac=,ip=,mask="
+$ pushd $CLOUDH
+$ git clone https://github.com/cloud-hypervisor/cloud-hypervisor.git
+$ cd cloud-hypervisor
+$ cargo build --release
+
+# We need to give the cloud-hypervisor binary the NET_ADMIN capabilities for it to set TAP interfaces up on the host.
+$ sudo setcap cap_net_admin+ep ./target/release/cloud-hypervisor
+
+$ popd
 ```
 
-If access to the firmware messages or interaction with the boot loader (e.g.
-GRUB) is required then it necessary to switch to the serial console instead of
-`virtio-console`.
+This will build a `cloud-hypervisor` binary under `$CLOUDH/cloud-hypervisor/target/release/cloud-hypervisor`.
+
+### Containerized builds and tests
+
+If you want to build and test Cloud Hypervisor without having to install all the
+required dependencies (The rust toolchain, cargo tools, etc), you can also use
+Cloud Hypervisor's development script: `dev_cli.sh`. Please note that upon its
+first invocation, this script will pull a fairly large container image.
+
+For example, to build the Cloud Hypervisor release binary:
 
 ```shell
-$ ./cloud-hypervisor \
+$ pushd $CLOUDH
+$ cd cloud-hypervisor
+$ ./scripts/dev_cli.sh build --release
+```
+
+With `dev_cli.sh`, one can also run the Cloud Hypervisor CI locally. This can be
+very convenient for debugging CI errors without having to fully rely on the
+Cloud Hypervisor CI infrastructure.
+
+For example, to run the Cloud Hypervisor unit tests:
+
+```shell
+$ ./scripts/dev_cli.sh tests --unit
+```
+
+Run the `./scripts/dev_cli.sh --help` command to view all the supported
+development script commands and their related options.
+
+## Run
+
+You can run a guest VM by either using an existing cloud image or booting into your own kernel and disk image.
+
+### Cloud image
+
+`cloud-hypervisor` supports booting disk images containing all needed
+components to run cloud workloads, a.k.a. cloud images.  To do that we rely on
+the [Rust Hypervisor
+Firmware](https://github.com/cloud-hypervisor/rust-hypervisor-firmware) project to provide
+an ELF
+formatted KVM firmware for `cloud-hypervisor` to directly boot into.
+
+We need to get the latest `rust-hypervisor-firmware` release and also a working cloud image. Here we will use a Clear Linux image:
+
+```shell
+$ pushd $CLOUDH
+$ wget https://download.clearlinux.org/releases/31890/clear/clear-31890-kvm.img.xz
+$ unxz clear-31890-kvm.img.xz
+$ wget https://github.com/cloud-hypervisor/rust-hypervisor-firmware/releases/download/0.2.6/hypervisor-fw
+$ popd
+```
+
+```shell
+$ pushd $CLOUDH
+$ sudo setcap cap_net_admin+ep ./cloud-hypervisor/target/release/cloud-hypervisor
+$ ./cloud-hypervisor/target/release/cloud-hypervisor \
 	--kernel ./hypervisor-fw \
-	--disk path=focal-server-cloudimg-amd64.raw path=/tmp/ubuntu-cloudinit.img \
+	--disk path=clear-31890-kvm.img \
 	--cpus boot=4 \
 	--memory size=1024M \
 	--net "tap=,mac=,ip=,mask=" \
-	--serial tty \
-	--console off
+	--rng
+$ popd
 ```
 
-### Custom Kernel and Disk Image
+Multiple arguments can be given to the `--disk` parameter.
 
-#### Building your Kernel
+### Custom kernel and disk image
 
-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.
+#### Building your kernel
+
+`cloud-hypervisor` also supports direct kernel boot into a `vmlinux` ELF kernel
+image. In order to support virtio-fs and virtio-iommu we have our own development branch. You are of course able to use your own kernel but these instructions will continue with the version that we develop and test against.
 
 To build the kernel:
 
 ```shell
+
 # Clone the Cloud Hypervisor Linux branch
-$ git clone --depth 1 https://github.com/cloud-hypervisor/linux.git -b ch-6.2 linux-cloud-hypervisor
+$ pushd $CLOUDH
+$ git clone --depth 1 https://github.com/cloud-hypervisor/linux.git -b virtio-fs-virtio-iommu-5.5-rc1 linux-cloud-hypervisor
 $ pushd linux-cloud-hypervisor
-# 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
-$ make -j `nproc`
+
+# Use the cloud-hypervisor kernel config to build your kernel
+$ cp $CLOUDH/cloud-hypervisor/resources/linux-virtio-fs-virtio-iommu-config .config
+$ make bzImage -j `nproc`
 $ popd
 ```
 
-For x86-64, the `vmlinux` kernel image will then be located at
-`linux-cloud-hypervisor/arch/x86/boot/compressed/vmlinux.bin`.
-For AArch64, the `Image` kernel image will then be located at
-`linux-cloud-hypervisor/arch/arm64/boot/Image`.
+The `vmlinux` kernel image will then be located at `linux-cloud-hypervisor/arch/x86/boot/compressed/vmlinux.bin`.
 
 #### Disk image
 
-For the disk image the same Ubuntu image as before can be used. This contains
-an `ext4` root filesystem.
+For the disk image, we will use a Clear Linux cloud image that contains a root partition:
 
 ```shell
-$ wget https://cloud-images.ubuntu.com/focal/current/focal-server-cloudimg-amd64.img # x86-64
-$ wget https://cloud-images.ubuntu.com/focal/current/focal-server-cloudimg-arm64.img # AArch64
-$ qemu-img convert -p -f qcow2 -O raw focal-server-cloudimg-amd64.img focal-server-cloudimg-amd64.raw # x86-64
-$ qemu-img convert -p -f qcow2 -O raw focal-server-cloudimg-arm64.img focal-server-cloudimg-arm64.raw # AArch64
+$ pushd $CLOUDH
+$ wget https://download.clearlinux.org/releases/31890/clear/clear-31890-kvm.img.xz
+$ unxz clear-31890-kvm.img.xz
+$ popd
 ```
 
 #### Booting the guest VM
 
-These sample commands boot the disk image using the custom kernel whilst also
-supplying the desired kernel command line.
-
-- x86-64
+Now we can directly boot into our custom kernel and make it use the Clear Linux root partition.
+If we want to have 4 vCPUs and 512 MBytes of memory:
 
 ```shell
-$ sudo setcap cap_net_admin+ep ./cloud-hypervisor
-$ ./create-cloud-init.sh
-$ ./cloud-hypervisor \
+$ pushd $CLOUDH
+$ sudo setcap cap_net_admin+ep ./cloud-hypervisor/target/release/cloud-hypervisor
+$ ./cloud-hypervisor/target/release/cloud-hypervisor \
 	--kernel ./linux-cloud-hypervisor/arch/x86/boot/compressed/vmlinux.bin \
-	--disk path=focal-server-cloudimg-amd64.raw path=/tmp/ubuntu-cloudinit.img \
-	--cmdline "console=hvc0 root=/dev/vda1 rw" \
+	--disk path=clear-31890-kvm.img \
+	--cmdline "console=hvc0 reboot=k panic=1 nomodules i8042.noaux i8042.nomux i8042.nopnp i8042.dumbkbd root=/dev/vda3" \
 	--cpus boot=4 \
 	--memory size=1024M \
-	--net "tap=,mac=,ip=,mask="
+	--net "tap=,mac=,ip=,mask=" \
+	--rng
 ```
 
-- AArch64
+The above example use the `virtio-console` device as the guest console, and this
+device may not be enabled soon enough by the guest kernel to get early kernel
+debug messages.
+
+When in need for earlier debug messages, using the legacy serial device based
+console is preferred:
 
-```shell
-$ 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 \
-	--cmdline "console=hvc0 root=/dev/vda1 rw" \
-	--cpus boot=4 \
-	--memory size=1024M \
-	--net "tap=,mac=,ip=,mask="
 ```
-
-If earlier kernel messages are required the serial console should be used instead of `virtio-console`.
-
-- x86-64
-
-```shell
-$ ./cloud-hypervisor \
+$ ./cloud-hypervisor/target/release/cloud-hypervisor \
 	--kernel ./linux-cloud-hypervisor/arch/x86/boot/compressed/vmlinux.bin \
 	--console off \
 	--serial tty \
-	--disk path=focal-server-cloudimg-amd64.raw \
-	--cmdline "console=ttyS0 root=/dev/vda1 rw" \
+	--disk path=clear-31890-kvm.img \
+	--cmdline "console=ttyS0 reboot=k panic=1 nomodules i8042.noaux i8042.nomux i8042.nopnp i8042.dumbkbd root=/dev/vda3" \
 	--cpus boot=4 \
 	--memory size=1024M \
-	--net "tap=,mac=,ip=,mask="
-```
-
-- AArch64
-
-```shell
-$ ./cloud-hypervisor \
-	--kernel ./linux-cloud-hypervisor/arch/arm64/boot/Image \
-	--console off \
-	--serial tty \
-	--disk path=focal-server-cloudimg-arm64.raw \
-	--cmdline "console=ttyAMA0 root=/dev/vda1 rw" \
-	--cpus boot=4 \
-	--memory size=1024M \
-	--net "tap=,mac=,ip=,mask="
+	--net "tap=,mac=,ip=,mask=" \
+	--rng
 ```
 
 # 3. Status
 
-Cloud Hypervisor is under active development. The following stability
-guarantees are currently made:
+`cloud-hypervisor` is in a very early, pre-alpha stage. Use at your own risk!
 
-* The API (including command line options) will not be removed or changed in a
-  breaking way without a minimum of 2 major releases notice. Where possible
-  warnings will be given about the use of deprecated functionality and the
-  deprecations will be documented in the release notes.
+As of 2019-12-12, the following cloud images are supported:
+* [Clear Linux](https://download.clearlinux.org/current/) (cloudguest and kvm)
+* [Ubuntu Bionic](https://cloud-images.ubuntu.com/bionic/current/) (cloudimg)
+* [Ubuntu Eoan](https://cloud-images.ubuntu.com/eoan/current/) (cloudimg)
 
-* Point releases will be made between individual releases where there are
-  substantial bug fixes or security issues that need to be fixed. These point
-  releases will only include bug fixes.
-
-Currently the following items are **not** guaranteed across updates:
-
-* Snapshot/restore is not supported across different versions
-* Live migration is not supported across different versions
-* The following features are considered experimental and may change
-  substantially between releases: TDX, vfio-user, vDPA.
-
-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 )
-- [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
-reference kernel configuration (e.g. XFS or btrfs.)
+Direct kernel boot to userspace should work with most rootfs.
 
 ## Hot Plug
 
-Cloud Hypervisor supports hotplug of CPUs, passthrough devices (VFIO),
-`virtio-{net,block,pmem,fs,vsock}` and memory resizing. This
-[document](docs/hotplug.md) details how to add devices to a running VM.
+This [document](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/hotplug.md) details how to add devices to
+a running VM. Currently only CPU hot plug is supported.
 
 ## Device Model
 
-Details of the device model can be found in this
-[documentation](docs/device_model.md).
+Follow this [documentation](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/device_model.md).
 
-## Roadmap
+## TODO
 
-The project roadmap is tracked through a [GitHub
-project](https://github.com/orgs/cloud-hypervisor/projects/6).
+We are not tracking the `cloud-hypervisor` TODO list from a specific git tracked file but through
+[github issues](https://github.com/cloud-hypervisor/cloud-hypervisor/issues/new) instead.
 
-# 4. Relationship with _Rust VMM_ Project
+# 4. `rust-vmm` project dependency
 
-In order to satisfy the design goal of having a high-performance,
-security-focused hypervisor the decision was made to use the
-[Rust](https://www.rust-lang.org/) programming language. The language's strong
-focus on memory and thread safety makes it an ideal candidate for implementing
-VMMs.
+In order to satisfy the design goal of having a high-performance, security-focused hypervisor the decision
+was made to use the [Rust](https://www.rust-lang.org/) programming language.
+The language's strong focus on memory and thread safety makes it an ideal candidate for implementing VMMs
 
-Instead of implementing the VMM components from scratch, Cloud Hypervisor is
-importing the [Rust VMM](https://github.com/rust-vmm) crates, and sharing code
-and architecture together with other VMMs like e.g. Amazon's
-[Firecracker](https://firecracker-microvm.github.io/) and Google's
-[crosvm](https://chromium.googlesource.com/chromiumos/platform/crosvm/).
+Instead of implementing the VMM components from scratch, `cloud-hypervisor` is importing the [rust-vmm](https://github.com/rust-vmm)
+crates, and sharing code and architecture together with other VMMs like e.g. Amazon's [Firecracker](https://firecracker-microvm.github.io/)
+and Google's [crosvm](https://chromium.googlesource.com/chromiumos/platform/crosvm/).
 
-Cloud Hypervisor embraces the _Rust VMM_ project's goals, which is to be able
-to share and re-use as many virtualization crates as possible.
+`cloud-hypervisor` embraces the rust-vmm project goals, which is to be able to share and re-use
+as many virtualization crates as possible. As such, the `cloud-hypervisor` relationship with the rust-vmm
+project is twofold:
 
-## Differences with Firecracker and crosvm
+1. It will use as much of the rust-vmm code as possible. Any new rust-vmm crate that's relevant to the project
+   goals will be integrated as soon as possible.
+2. As it is likely that the rust-vmm project will lack some of the features that `cloud-hypervisor` needs (e.g. ACPI,
+   VFIO, vhost-user, etc), we will be using the `cloud-hypervisor` VMM to implement and test them, and contribute them
+   back to the rust-vmm project.
 
-A large part of the Cloud Hypervisor code is based on either the Firecracker or
-the crosvm project's implementations. Both of these are VMMs written in Rust
-with a focus on safety and security, like Cloud Hypervisor.
+## Firecracker and crosvm
 
-The goal of the Cloud Hypervisor project differs from the aforementioned
-projects in that it aims to be a general purpose VMM for _Cloud Workloads_ and
-not limited to container/serverless or client workloads.
+A large part of the `cloud-hypervisor` code is based on either the Firecracker or the crosvm projects implementations.
+Both of these are VMMs written in Rust with a focus on safety and security, like Cloud Hypervisor.
 
-The Cloud Hypervisor community thanks the communities of both the Firecracker
-and crosvm projects for their excellent work.
+However we want to emphasize that the Cloud Hypervisor project is neither a fork nor a reimplementation of any of those
+projects. The goals and use cases we're trying to meet are different.
+We're aiming at supporting cloud workloads, i.e. those modern, full Linux distribution images currently being run by
+Cloud Service Provider (CSP) tenants.
+
+Our primary target is not to support client or serverless use cases, and as such our code base already diverges
+from the crosvm and Firecracker ones. As we add more features to support our use cases, we believe that the divergence
+will increase while at the same time sharing as much of the fundamental virtualization code through the rust-vmm project
+crates as possible.
 
 # 5. Community
 
-The Cloud Hypervisor project follows the governance, and community guidelines
-described in the [Community](https://github.com/cloud-hypervisor/community)
-repository.
+We are working on building a global, diverse and collaborative community around the Cloud Hypervisor project.
+Anyone who is interested in [contributing](CONTRIBUTING.md) to the project is welcome to participate.
 
-## Contribute
+We believe that contributing to a open source project like Cloud Hypervisor covers a lot more than just sending
+code. Testing, documentation, pull request reviews, bug reports, feature requests, project improvement suggestions,
+etc, are all equal and welcome means of contribution. See the [CONTRIBUTING](CONTRIBUTING.md) document for more details.
 
-The project strongly believes in building a global, diverse and collaborative
-community around the Cloud Hypervisor project. Anyone who is interested in
-[contributing](CONTRIBUTING.md) to the project is welcome to participate.
+## Join us
 
-Contributing to a open source project like Cloud Hypervisor covers a lot more
-than just sending code. Testing, documentation, pull request
-reviews, bug reports, feature requests, project improvement suggestions, etc,
-are all equal and welcome means of contribution. See the
-[CONTRIBUTING](CONTRIBUTING.md) document for more details.
+Get an [invite to our Slack channel](https://join.slack.com/t/cloud-hypervisor/shared_invite/enQtNjY3MTE3MDkwNDQ4LWQ1MTA1ZDVmODkwMWQ1MTRhYzk4ZGNlN2UwNTI3ZmFlODU0OTcwOWZjMTkwZDExYWE3YjFmNzgzY2FmNDAyMjI)
+and [join us on Slack](https://cloud-hypervisor.slack.com/).
 
-## Slack
+# 6. Security
 
-Get an [invite to our Slack channel](https://join.slack.com/t/cloud-hypervisor/shared_invite/enQtNjY3MTE3MDkwNDQ4LWQ1MTA1ZDVmODkwMWQ1MTRhYzk4ZGNlN2UwNTI3ZmFlODU0OTcwOWZjMTkwZDExYWE3YjFmNzgzY2FmNDAyMjI),
- [join us on Slack](https://cloud-hypervisor.slack.com/), and [participate in our community activities](https://cloud-hypervisor.slack.com/archives/C04R5DUQVBN).
+**Reporting a Potential Security Vulnerability**: If you have discovered
+potential security vulnerability in this project, please send an e-mail to
+secure@intel.com. For issues related to Intel Products, please visit
+https://security-center.intel.com.
 
-## Mailing list
+It is important to include the following details:
+  - The projects and versions affected
+  - Detailed description of the vulnerability
+  - Information on known exploits
 
-Please report bugs using the [GitHub issue
-tracker](https://github.com/cloud-hypervisor/cloud-hypervisor/issues) but for
-broader community discussions you may use our [mailing
-list](https://lists.cloudhypervisor.org/g/dev/).
+Vulnerability information is extremely sensitive. Please encrypt all security
+vulnerability reports using our *PGP key*
 
-## Security issues
+A member of the Intel Product Security Team will review your e-mail and
+contact you to to collaborate on resolving the issue. For more information on
+how Intel works to resolve security issues, see: *Vulnerability Handling
+Guidelines*
 
-Please contact the maintainers listed in the MAINTAINERS.md file with security issues.
+PGP Key: https://www.intel.com/content/www/us/en/security-center/pgp-public-key.html
+
+Vulnerability Handling Guidelines: https://www.intel.com/content/www/us/en/security-center/vulnerability-handling-guidelines.html

acpi_tables/Cargo.toml

@@ -0,0 +1,9 @@
+[package]
+name = "acpi_tables"
+version = "0.1.0"
+authors = ["The Cloud Hypervisor Authors"]
+edition = "2018"
+
+[dependencies]
+vm-memory = { git = "https://github.com/rust-vmm/vm-memory" }
+

acpi_tables/src/lib.rs

@@ -0,0 +1,12 @@
+// Copyright © 2019 Intel Corporation
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+pub mod aml;
+pub mod rsdp;
+pub mod sdt;
+
+fn generate_checksum(data: &[u8]) -> u8 {
+    (255 - data.iter().fold(0u8, |acc, x| acc.wrapping_add(*x))).wrapping_add(1)
+}

acpi_tables/src/rsdp.rs

@@ -0,0 +1,67 @@
+// Copyright © 2019 Intel Corporation
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+use vm_memory::ByteValued;
+
+#[repr(packed)]
+#[derive(Clone, Copy, Default)]
+pub struct RSDP {
+    pub signature: [u8; 8],
+    pub checksum: u8,
+    pub oem_id: [u8; 6],
+    pub revision: u8,
+    _rsdt_addr: u32,
+    pub length: u32,
+    pub xsdt_addr: u64,
+    pub extended_checksum: u8,
+    _reserved: [u8; 3],
+}
+
+unsafe impl ByteValued for RSDP {}
+
+impl RSDP {
+    pub fn new(oem_id: [u8; 6], xsdt_addr: u64) -> Self {
+        let mut rsdp = RSDP {
+            signature: *b"RSD PTR ",
+            checksum: 0,
+            oem_id,
+            revision: 2,
+            _rsdt_addr: 0,
+            length: std::mem::size_of::<RSDP>() as u32,
+            xsdt_addr,
+            extended_checksum: 0,
+            _reserved: [0; 3],
+        };
+
+        rsdp.checksum = super::generate_checksum(&rsdp.as_slice()[0..19]);
+        rsdp.extended_checksum = super::generate_checksum(&rsdp.as_slice());
+        rsdp
+    }
+
+    pub fn len() -> usize {
+        std::mem::size_of::<RSDP>()
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::RSDP;
+    use vm_memory::bytes::ByteValued;
+
+    #[test]
+    fn test_rsdp() {
+        let rsdp = RSDP::new(*b"CHYPER", 0xdead_beef);
+        let sum = rsdp
+            .as_slice()
+            .iter()
+            .fold(0u8, |acc, x| acc.wrapping_add(*x));
+        assert_eq!(sum, 0);
+        let sum: u8 = rsdp
+            .as_slice()
+            .iter()
+            .fold(0u8, |acc, x| acc.wrapping_add(*x));
+        assert_eq!(sum, 0);
+    }
+}

acpi_tables/src/sdt.rs

@@ -0,0 +1,137 @@
+// Copyright © 2019 Intel Corporation
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+#[repr(packed)]
+pub struct GenericAddress {
+    pub address_space_id: u8,
+    pub register_bit_width: u8,
+    pub register_bit_offset: u8,
+    pub access_size: u8,
+    pub address: u64,
+}
+
+impl GenericAddress {
+    pub fn io_port_address(address: u16) -> Self {
+        GenericAddress {
+            address_space_id: 1,
+            register_bit_width: 8,
+            register_bit_offset: 0,
+            access_size: 1,
+            address: u64::from(address),
+        }
+    }
+}
+
+pub struct SDT {
+    data: Vec<u8>,
+}
+
+#[allow(clippy::len_without_is_empty)]
+impl SDT {
+    pub fn new(
+        signature: [u8; 4],
+        length: u32,
+        revision: u8,
+        oem_id: [u8; 6],
+        oem_table: [u8; 8],
+        oem_revision: u32,
+    ) -> Self {
+        assert!(length >= 36);
+
+        let mut data = Vec::with_capacity(length as usize);
+        data.extend_from_slice(&signature);
+        data.extend_from_slice(&length.to_le_bytes());
+        data.push(revision);
+        data.push(0); // checksum
+        data.extend_from_slice(&oem_id);
+        data.extend_from_slice(&oem_table);
+        data.extend_from_slice(&oem_revision.to_le_bytes());
+        data.extend_from_slice(b"CLDH");
+        data.extend_from_slice(&0u32.to_le_bytes());
+        assert_eq!(data.len(), 36);
+
+        data.resize(length as usize, 0);
+        let mut sdt = SDT { data };
+
+        sdt.update_checksum();
+        sdt
+    }
+
+    pub fn update_checksum(&mut self) {
+        self.data[9] = 0;
+        let checksum = super::generate_checksum(self.data.as_slice());
+        self.data[9] = checksum
+    }
+
+    pub fn as_slice(&self) -> &[u8] {
+        &self.data.as_slice()
+    }
+
+    pub fn append<T>(&mut self, value: T) {
+        let orig_length = self.data.len();
+        let new_length = orig_length + std::mem::size_of::<T>();
+        self.data.resize(new_length, 0);
+        self.write_u32(4, new_length as u32);
+        self.write(orig_length, value);
+    }
+
+    pub fn append_slice(&mut self, data: &[u8]) {
+        let orig_length = self.data.len();
+        let new_length = orig_length + data.len();
+        self.write_u32(4, new_length as u32);
+        self.data.extend_from_slice(data);
+        self.update_checksum();
+    }
+
+    /// Write a value at the given offset
+    pub fn write<T>(&mut self, offset: usize, value: T) {
+        assert!((offset + (std::mem::size_of::<T>() - 1)) < self.data.len());
+        unsafe {
+            *(((self.data.as_mut_ptr() as usize) + offset) as *mut T) = value;
+        }
+        self.update_checksum();
+    }
+
+    pub fn write_u8(&mut self, offset: usize, val: u8) {
+        self.write(offset, val);
+    }
+
+    pub fn write_u16(&mut self, offset: usize, val: u16) {
+        self.write(offset, val);
+    }
+
+    pub fn write_u32(&mut self, offset: usize, val: u32) {
+        self.write(offset, val);
+    }
+
+    pub fn write_u64(&mut self, offset: usize, val: u64) {
+        self.write(offset, val);
+    }
+
+    pub fn len(&self) -> usize {
+        self.data.len()
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::SDT;
+
+    #[test]
+    fn test_sdt() {
+        let mut sdt = SDT::new(*b"TEST", 40, 1, *b"CLOUDH", *b"TESTTEST", 1);
+        let sum: u8 = sdt
+            .as_slice()
+            .iter()
+            .fold(0u8, |acc, x| acc.wrapping_add(*x));
+        assert_eq!(sum, 0);
+        sdt.write_u32(36, 0x12345678);
+        let sum: u8 = sdt
+            .as_slice()
+            .iter()
+            .fold(0u8, |acc, x| acc.wrapping_add(*x));
+        assert_eq!(sum, 0);
+    }
+}

api_client/Cargo.toml

@@ -1,9 +0,0 @@
-[package]
-authors = ["The Cloud Hypervisor Authors"]
-edition = "2021"
-name = "api_client"
-version = "0.1.0"
-
-[dependencies]
-thiserror = "1.0.62"
-vmm-sys-util = { workspace = true }

api_client/src/lib.rs

@@ -1,236 +0,0 @@
-// Copyright © 2020 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-//
-
-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)]
-pub enum Error {
-    #[error("Error writing to or reading from HTTP socket: {0}")]
-    Socket(std::io::Error),
-    #[error("Error sending file descriptors: {0}")]
-    SocketSendFds(vmm_sys_util::errno::Error),
-    #[error("Error parsing HTTP status code: {0}")]
-    StatusCodeParsing(std::num::ParseIntError),
-    #[error("HTTP output is missing protocol statement")]
-    MissingProtocol,
-    #[error("Error parsing HTTP Content-Length field: {0}")]
-    ContentLengthParsing(std::num::ParseIntError),
-    #[error("Server responded with an error: {0:?}: {1:?}")]
-    ServerResponse(StatusCode, Option<String>),
-}
-
-#[derive(Clone, Copy, Debug)]
-pub enum StatusCode {
-    Continue,
-    Ok,
-    NoContent,
-    BadRequest,
-    NotFound,
-    InternalServerError,
-    NotImplemented,
-    Unknown,
-}
-
-impl StatusCode {
-    fn from_raw(code: usize) -> StatusCode {
-        match code {
-            100 => StatusCode::Continue,
-            200 => StatusCode::Ok,
-            204 => StatusCode::NoContent,
-            400 => StatusCode::BadRequest,
-            404 => StatusCode::NotFound,
-            500 => StatusCode::InternalServerError,
-            501 => StatusCode::NotImplemented,
-            _ => StatusCode::Unknown,
-        }
-    }
-
-    fn parse(code: &str) -> Result<StatusCode, Error> {
-        Ok(StatusCode::from_raw(
-            code.trim().parse().map_err(Error::StatusCodeParsing)?,
-        ))
-    }
-
-    fn is_server_error(self) -> bool {
-        !matches!(
-            self,
-            StatusCode::Ok | StatusCode::Continue | StatusCode::NoContent
-        )
-    }
-}
-
-fn get_header<'a>(res: &'a str, header: &'a str) -> Option<&'a str> {
-    let header_str = format!("{header}: ");
-    res.find(&header_str)
-        .map(|o| &res[o + header_str.len()..o + res[o..].find('\r').unwrap()])
-}
-
-fn get_status_code(res: &str) -> Result<StatusCode, Error> {
-    if let Some(o) = res.find("HTTP/1.1") {
-        Ok(StatusCode::parse(
-            &res[o + "HTTP/1.1 ".len()..res[o..].find('\r').unwrap()],
-        )?)
-    } else {
-        Err(Error::MissingProtocol)
-    }
-}
-
-fn parse_http_response(socket: &mut dyn Read) -> Result<Option<String>, Error> {
-    let mut res = String::new();
-    let mut body_offset = None;
-    let mut content_length: Option<usize> = None;
-    loop {
-        let mut bytes = vec![0; 256];
-        let count = socket.read(&mut bytes).map_err(Error::Socket)?;
-        // If the return value is 0, the peer has performed an orderly shutdown.
-        if count == 0 {
-            break;
-        }
-        res.push_str(std::str::from_utf8(&bytes[0..count]).unwrap());
-
-        // End of headers
-        if let Some(o) = res.find("\r\n\r\n") {
-            body_offset = Some(o + "\r\n\r\n".len());
-
-            // With all headers available we can see if there is any body
-            content_length = if let Some(length) = get_header(&res, "Content-Length") {
-                Some(length.trim().parse().map_err(Error::ContentLengthParsing)?)
-            } else {
-                None
-            };
-
-            if content_length.is_none() {
-                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..])));
-    let status_code = get_status_code(&res)?;
-
-    if status_code.is_server_error() {
-        Err(Error::ServerResponse(status_code, body_string))
-    } else {
-        Ok(body_string)
-    }
-}
-
-/// Make an API request using the fully qualified command name.
-/// For example, full_command could be "vm.create" or "vmm.ping".
-pub fn simple_api_full_command_with_fds_and_response<T: Read + Write + ScmSocket>(
-    socket: &mut T,
-    method: &str,
-    full_command: &str,
-    request_body: Option<&str>,
-    request_fds: Vec<RawFd>,
-) -> Result<Option<String>, Error> {
-    socket
-        .send_with_fds(
-            &[format!(
-                "{method} /api/v1/{full_command} HTTP/1.1\r\nHost: localhost\r\nAccept: */*\r\n"
-            )
-            .as_bytes()],
-            &request_fds,
-        )
-        .map_err(Error::SocketSendFds)?;
-
-    if let Some(request_body) = request_body {
-        socket
-            .write_all(format!("Content-Length: {}\r\n", request_body.len()).as_bytes())
-            .map_err(Error::Socket)?;
-    }
-
-    socket.write_all(b"\r\n").map_err(Error::Socket)?;
-
-    if let Some(request_body) = request_body {
-        socket
-            .write_all(request_body.as_bytes())
-            .map_err(Error::Socket)?;
-    }
-
-    socket.flush().map_err(Error::Socket)?;
-
-    parse_http_response(socket)
-}
-
-pub fn simple_api_full_command_with_fds<T: Read + Write + ScmSocket>(
-    socket: &mut T,
-    method: &str,
-    full_command: &str,
-    request_body: Option<&str>,
-    request_fds: Vec<RawFd>,
-) -> Result<(), Error> {
-    let response = simple_api_full_command_with_fds_and_response(
-        socket,
-        method,
-        full_command,
-        request_body,
-        request_fds,
-    )?;
-
-    if response.is_some() {
-        println!("{}", response.unwrap());
-    }
-
-    Ok(())
-}
-
-pub fn simple_api_full_command<T: Read + Write + ScmSocket>(
-    socket: &mut T,
-    method: &str,
-    full_command: &str,
-    request_body: Option<&str>,
-) -> Result<(), Error> {
-    simple_api_full_command_with_fds(socket, method, full_command, request_body, Vec::new())
-}
-
-pub fn simple_api_full_command_and_response<T: Read + Write + ScmSocket>(
-    socket: &mut T,
-    method: &str,
-    full_command: &str,
-    request_body: Option<&str>,
-) -> Result<Option<String>, Error> {
-    simple_api_full_command_with_fds_and_response(
-        socket,
-        method,
-        full_command,
-        request_body,
-        Vec::new(),
-    )
-}
-
-pub fn simple_api_command_with_fds<T: Read + Write + ScmSocket>(
-    socket: &mut T,
-    method: &str,
-    c: &str,
-    request_body: Option<&str>,
-    request_fds: Vec<RawFd>,
-) -> Result<(), Error> {
-    // Create the full VM command. For VMM commands, use
-    // simple_api_full_command().
-    let full_command = format!("vm.{c}");
-
-    simple_api_full_command_with_fds(socket, method, &full_command, request_body, request_fds)
-}
-
-pub fn simple_api_command<T: Read + Write + ScmSocket>(
-    socket: &mut T,
-    method: &str,
-    c: &str,
-    request_body: Option<&str>,
-) -> Result<(), Error> {
-    simple_api_command_with_fds(socket, method, c, request_body, Vec::new())
-}

arch/Cargo.toml

@@ -1,29 +1,27 @@
 [package]
-authors = ["The Chromium OS Authors"]
-edition = "2021"
 name = "arch"
 version = "0.1.0"
+authors = ["The Chromium OS Authors"]
 
 [features]
 default = []
-kvm = ["hypervisor/kvm"]
-sev_snp = []
-tdx = []
 
 [dependencies]
-anyhow = "1.0.87"
-byteorder = "1.5.0"
-hypervisor = { path = "../hypervisor" }
-libc = "0.2.158"
-linux-loader = { workspace = true, features = ["bzimage", "elf", "pe"] }
-log = "0.4.22"
-serde = { version = "1.0.208", features = ["derive", "rc"] }
-thiserror = "1.0.62"
-uuid = "1.8.0"
-vm-memory = { workspace = true, features = ["backend-bitmap", "backend-mmap"] }
-vm-migration = { path = "../vm-migration" }
-vmm-sys-util = { workspace = true, features = ["with-serde"] }
+byteorder = "1.3.4"
+kvm-bindings = "0.2.0"
+kvm-ioctls = "0.5.0"
+libc = "0.2.66"
 
-[target.'cfg(target_arch = "aarch64")'.dependencies]
-fdt_parser = { version = "0.1.5", package = "fdt" }
-vm-fdt = { workspace = true }
+acpi_tables = { path = "../acpi_tables", optional = true }
+arch_gen = { path = "../arch_gen" }
+
+[dependencies.vm-memory]
+git = "https://github.com/rust-vmm/vm-memory"
+features = ["backend-mmap"]
+
+[dependencies.linux-loader]
+git = "https://github.com/rust-vmm/linux-loader"
+features = ["elf", "bzimage"]
+
+[dev-dependencies]
+rand = "0.7.3"

arch/src/aarch64/layout.rs

@@ -1,140 +1,7 @@
-// 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 AArch64 guest:
-//
-// Physical  +---------------------------------------------------------------+
-// address   |                                                               |
-// end       |                                                               |
-//           ~                   ~                       ~                   ~
-//           |                                                               |
-//           |                      Highmem PCI MMIO space                   |
-//           |                                                               |
-// RAM end   +---------------------------------------------------------------+
-// (dynamic, |                                                               |
-// including |                                                               |
-// hotplug   ~                   ~                       ~                   ~
-// memory)   |                                                               |
-//           |                            DRAM                               |
-//           |                                                               |
-//           |                                                               |
-// 4GB       +---------------------------------------------------------------+
-//           |                      32-bit devices hole                      |
-// 4GB-64M   +---------------------------------------------------------------+
-//           |                                                               |
-//           |                                                               |
-//           |                            DRAM                               |
-//           |                                                               |
-//           |                                                               |
-// 1GB       +---------------------------------------------------------------+
-//           |                                                               |
-//           |                        PCI MMCONFIG space                     |
-//           |                                                               |
-// 768 M     +---------------------------------------------------------------+
-//           |                                                               |
-//           |                                                               |
-//           |                           PCI MMIO space                      |
-//           |                                                               |
-// 256 M     +---------------------------------------------------------------|
-//           |                                                               |
-//           |                        Legacy devices space                   |
-//           |                                                               |
-// 144 M     +---------------------------------------------------------------|
-//           |                                                               |
-//           |                    Reserved (now GIC is here)                 |
-//           |                                                               |
-//  4  M     +---------------------------------------------------------------+
-//           |                          UEFI flash                           |
-// 0GB       +---------------------------------------------------------------+
-//
-//
-
-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;
-
-/// Below this address will reside the GIC, above this address will reside the MMIO devices.
-const MAPPED_IO_START: GuestAddress = GuestAddress(0x0900_0000);
-
-/// See kernel file arch/arm64/include/uapi/asm/kvm.h for the GIC related definitions.
-/// 0x08ff_0000 ~ 0x0900_0000 is reserved for GICv3 Distributor
-pub const GIC_V3_DIST_SIZE: u64 = 0x01_0000;
-pub const GIC_V3_DIST_START: GuestAddress = GuestAddress(MAPPED_IO_START.0 - GIC_V3_DIST_SIZE);
-/// Below 0x08ff_0000 is reserved for GICv3 Redistributor.
-/// The size defined here is for each vcpu.
-/// The total size is 'number_of_vcpu * GIC_V3_REDIST_SIZE'
-pub const GIC_V3_REDIST_SIZE: u64 = 0x02_0000;
-/// Below Redistributor area is GICv3 ITS
-pub const GIC_V3_ITS_SIZE: u64 = 0x02_0000;
-
-/// Space 0x0900_0000 ~ 0x0905_0000 is reserved for legacy devices.
-pub const LEGACY_SERIAL_MAPPED_IO_START: GuestAddress = MAPPED_IO_START;
-pub const LEGACY_RTC_MAPPED_IO_START: GuestAddress = GuestAddress(0x0901_0000);
-pub const LEGACY_GPIO_MAPPED_IO_START: GuestAddress = GuestAddress(0x0902_0000);
-
-/// 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 = 0x10000;
-
-/// 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 1 GiB, 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);
-
-/// 32-bit reserved area: 64MiB before 4GiB
-pub const MEM_32BIT_RESERVED_START: GuestAddress = GuestAddress(0xfc00_0000);
-pub const MEM_32BIT_RESERVED_SIZE: u64 = 0x0400_0000;
-
-/// TPM Address Range
-/// This Address range is specific to CRB Interface
-pub const TPM_START: GuestAddress = GuestAddress(0xfed4_0000);
-pub const TPM_SIZE: u64 = 0x1000;
-
-/// Start of 64-bit RAM.
-pub const RAM_64BIT_START: GuestAddress = GuestAddress(0x1_0000_0000);
-
-/// Kernel command line maximum size.
-/// As per `arch/arm64/include/uapi/asm/setup.h`.
-pub const CMDLINE_MAX_SIZE: usize = 2048;
-
-/// FDT is at the beginning of RAM.
-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
-pub const ACPI_START: GuestAddress = GuestAddress(RAM_START.0 + FDT_MAX_SIZE);
-pub const ACPI_MAX_SIZE: u64 = 0x20_0000;
-pub const RSDP_POINTER: GuestAddress = ACPI_START;
-
-/// Kernel start after FDT and ACPI
-pub const KERNEL_START: GuestAddress = GuestAddress(ACPI_START.0 + ACPI_MAX_SIZE);
-
-/// Pci high memory base
-pub const PCI_HIGH_BASE: GuestAddress = GuestAddress(0x2_0000_0000);
-
-// As per virt/kvm/arm/vgic/vgic-kvm-device.c we need
-// the number of interrupts our GIC will support to be:
-// * bigger than 32
-// * less than 1023 and
-// * a multiple of 32.
-// We are setting up our interrupt controller to support a maximum of 256 interrupts.
-/// First usable interrupt on aarch64
-pub const IRQ_BASE: u32 = 32;
-
-/// Number of supported interrupts
-pub const IRQ_NUM: u32 = 256;
+/// Kernel command line start address.
+pub const CMDLINE_START: usize = 0x0;
+/// Kernel command line start address maximum size.
+pub const CMDLINE_MAX_SIZE: usize = 0x0;

arch/src/aarch64/mod.rs

@@ -1,216 +1,27 @@
-// 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 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 memory_model::{GuestAddress, GuestMemory};
 
-use hypervisor::arch::aarch64::gic::Vgic;
-use log::{log_enabled, Level};
-use thiserror::Error;
-use vm_memory::{Address, GuestAddress, GuestMemory, GuestMemoryAtomic};
-
-pub use self::fdt::DeviceInfoForFdt;
-use crate::{DeviceType, GuestMemoryMmap, NumaNodes, PciSpaceInfo, RegionType};
-
-pub const _NSIG: i32 = 65;
-
-/// Errors thrown while configuring aarch64 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: {0}")]
-    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: {0}")]
-    RegsConfiguration(hypervisor::HypervisorCpuError),
-
-    /// Error configuring the MPIDR register
-    #[error("Error configuring the MPIDR register: {0}")]
-    VcpuRegMpidr(hypervisor::HypervisorCpuError),
-
-    /// Error initializing PMU for vcpu
-    #[error("Error initializing PMU for vcpu")]
-    VcpuInitPmu,
+/// Stub function that needs to be implemented when aarch64 functionality is added.
+pub fn arch_memory_regions(size: usize) -> Vec<(GuestAddress, usize, RegionType)> {
+    vec![(GuestAddress(0), size, RegionType::Ram)]
 }
 
-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.
-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: u8,
-    boot_setup: Option<(EntryPoint, &GuestMemoryAtomic<GuestMemoryMmap>)>,
-) -> super::Result<u64> {
-    if let Some((kernel_entry_point, _guest_memory)) = boot_setup {
-        vcpu.setup_regs(
-            id,
-            kernel_entry_point.entry_addr.raw_value(),
-            super::layout::FDT_START.raw_value(),
-        )
-        .map_err(Error::RegsConfiguration)?;
-    }
-
-    let mpidr = vcpu
-        .get_sys_reg(regs::MPIDR_EL1)
-        .map_err(Error::VcpuRegMpidr)?;
-    Ok(mpidr)
-}
-
-pub fn arch_memory_regions() -> Vec<(GuestAddress, usize, RegionType)> {
-    vec![
-        // 0 MiB ~ 256 MiB: UEFI, GIC 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 ~ 4032 MiB: RAM before the gap
-        (
-            layout::RAM_START,
-            layout::MEM_32BIT_RESERVED_START.unchecked_offset_from(layout::RAM_START) as usize,
-            RegionType::Ram,
-        ),
-        // 4GiB ~ inf: RAM after the gap
-        (layout::RAM_64BIT_START, usize::MAX, RegionType::Ram),
-        // Add the 32-bit reserved memory hole as a reserved region
-        (
-            layout::MEM_32BIT_RESERVED_START,
-            layout::MEM_32BIT_RESERVED_SIZE as usize,
-            RegionType::Reserved,
-        ),
-    ]
-}
-
-/// 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,
-    vcpu_mpidr: Vec<u64>,
-    vcpu_topology: Option<(u8, u8, u8)>,
-    device_info: &HashMap<(DeviceType, String), T, S>,
-    initrd: &Option<super::InitramfsConfig>,
-    pci_space_info: &[PciSpaceInfo],
-    virtio_iommu_bdf: Option<u32>,
-    gic_device: &Arc<Mutex<dyn Vgic>>,
-    numa_nodes: &NumaNodes,
-    pmu_supported: bool,
+/// Stub function that needs to be implemented when aarch64 functionality is added.
+pub fn configure_system(
+    _guest_mem: &GuestMemory,
+    _cmdline_addr: GuestAddress,
+    _cmdline_size: usize,
+    _num_cpus: u8,
+    _rsdp_addr: Option<GuestAddress>,
 ) -> super::Result<()> {
-    let fdt_final = fdt::create_fdt(
-        guest_mem,
-        cmdline,
-        vcpu_mpidr,
-        vcpu_topology,
-        device_info,
-        gic_device,
-        initrd,
-        pci_space_info,
-        numa_nodes,
-        virtio_iommu_bdf,
-        pmu_supported,
-    )
-    .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 {
-    let host_cpu_phys_bits = hypervisor.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.
-        40
-    } else {
-        host_cpu_phys_bits
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_arch_memory_regions_dram() {
-        let regions = arch_memory_regions();
-        assert_eq!(6, regions.len());
-        assert_eq!(layout::RAM_START, regions[3].0);
-        assert_eq!(RegionType::Ram, regions[3].2);
-        assert_eq!(RegionType::Reserved, regions[5].2);
-        assert_eq!(RegionType::Ram, regions[4].2);
-    }
+/// Stub function that needs to be implemented when aarch64 functionality is added.
+pub fn get_reserved_mem_addr() -> usize {
+    0
 }

arch/src/aarch64/regs.rs

@@ -1,43 +0,0 @@
-// 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

@@ -1,50 +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/lib.rs

@@ -1,62 +1,40 @@
-// Copyright 2020 Arm Limited (or its affiliates). All rights reserved.
-// Copyright © 2020, Oracle and/or its affiliates.
-//
 // Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 // SPDX-License-Identifier: Apache-2.0
 
-//! Implements platform specific functionality.
-//! Supported platforms: x86_64, aarch64.
+#![allow(
+    clippy::unreadable_literal,
+    clippy::redundant_static_lifetimes,
+    clippy::cast_lossless,
+    clippy::transmute_ptr_to_ptr,
+    clippy::cast_ptr_alignment
+)]
 
-#[macro_use]
-extern crate log;
+extern crate byteorder;
+extern crate kvm_bindings;
+extern crate libc;
 
-use std::collections::BTreeMap;
-use std::sync::Arc;
-use std::{fmt, result};
+#[cfg(feature = "acpi")]
+extern crate acpi_tables;
+extern crate arch_gen;
+extern crate kvm_ioctls;
+extern crate linux_loader;
+extern crate vm_memory;
 
-use serde::{Deserialize, Serialize};
-use thiserror::Error;
+use std::result;
 
-#[cfg(target_arch = "x86_64")]
-use crate::x86_64::SgxEpcSection;
-
-type GuestMemoryMmap = vm_memory::GuestMemoryMmap<vm_memory::bitmap::AtomicBitmap>;
-type GuestRegionMmap = vm_memory::GuestRegionMmap<vm_memory::bitmap::AtomicBitmap>;
-
-/// Type for returning error code.
-#[derive(Debug, Error)]
+#[derive(Debug)]
 pub enum Error {
     #[cfg(target_arch = "x86_64")]
-    #[error("Platform specific error (x86_64): {0:?}")]
-    PlatformSpecific(x86_64::Error),
-    #[cfg(target_arch = "aarch64")]
-    #[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")]
-    MemmapTableSetup,
-    #[error("The hvm_start_info structure extends past the end of guest memory")]
-    StartInfoPastRamEnd,
-    #[error("Error writing hvm_start_info to guest memory")]
-    StartInfoSetup,
-    #[error("Failed to compute initramfs address")]
-    InitramfsAddress,
-    #[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")]
+    /// X86_64 specific error triggered during system configuration.
+    X86_64Setup(x86_64::Error),
+    /// The zero page extends past the end of guest_mem.
     ZeroPagePastRamEnd,
+    /// Error writing the zero page of guest memory.
+    ZeroPageSetup(vm_memory::GuestMemoryError),
 }
-
-/// 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(PartialEq)]
 pub enum RegionType {
     /// RAM type
     Ram,
@@ -74,15 +52,13 @@ pub enum RegionType {
     Reserved,
 }
 
-/// Module for aarch64 related functionality.
 #[cfg(target_arch = "aarch64")]
 pub mod aarch64;
 
 #[cfg(target_arch = "aarch64")]
 pub use aarch64::{
-    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,
+    arch_memory_regions, configure_system, get_reserved_mem_addr, layout::CMDLINE_MAX_SIZE,
+    layout::CMDLINE_START,
 };
 
 #[cfg(target_arch = "x86_64")]
@@ -90,95 +66,5 @@ pub mod x86_64;
 
 #[cfg(target_arch = "x86_64")]
 pub use x86_64::{
-    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, CpuidConfig, CpuidFeatureEntry,
-    EntryPoint, _NSIG,
+    arch_memory_regions, configure_system, layout, layout::CMDLINE_MAX_SIZE, layout::CMDLINE_START,
 };
-
-/// Safe wrapper for `sysconf(_SC_PAGESIZE)`.
-#[cfg(target_arch = "x86_64")]
-#[inline(always)]
-fn pagesize() -> usize {
-    // SAFETY: Trivially safe
-    unsafe { libc::sysconf(libc::_SC_PAGESIZE) as usize }
-}
-
-#[derive(Clone, Default)]
-pub struct NumaNode {
-    pub memory_regions: Vec<Arc<GuestRegionMmap>>,
-    pub hotplug_regions: Vec<Arc<GuestRegionMmap>>,
-    pub cpus: Vec<u8>,
-    pub pci_segments: Vec<u16>,
-    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>;
-
-/// Type for passing information about the initramfs in the guest memory.
-pub struct InitramfsConfig {
-    /// Load address of initramfs in guest memory
-    pub address: vm_memory::GuestAddress,
-    /// Size of initramfs in guest memory
-    pub size: usize,
-}
-
-/// Types of devices that can get attached to this platform.
-#[derive(Clone, Debug, PartialEq, Eq, Hash, Copy)]
-pub enum DeviceType {
-    /// Device Type: Virtio.
-    Virtio(u32),
-    /// Device Type: Serial.
-    #[cfg(target_arch = "aarch64")]
-    Serial,
-    /// Device Type: RTC.
-    #[cfg(target_arch = "aarch64")]
-    Rtc,
-    /// Device Type: GPIO.
-    #[cfg(target_arch = "aarch64")]
-    Gpio,
-}
-
-/// Default (smallest) memory page size for the supported architectures.
-pub const PAGE_SIZE: usize = 4096;
-
-impl fmt::Display for DeviceType {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        write!(f, "{self:?}")
-    }
-}
-
-/// Structure to describe MMIO device information
-#[derive(Clone, Debug)]
-#[cfg(target_arch = "aarch64")]
-pub struct MmioDeviceInfo {
-    pub addr: u64,
-    pub len: u64,
-    pub irq: u32,
-}
-
-/// Structure to describe PCI space information
-#[derive(Clone, Debug)]
-#[cfg(target_arch = "aarch64")]
-pub struct PciSpaceInfo {
-    pub pci_segment_id: u16,
-    pub mmio_config_address: u64,
-    pub pci_device_space_start: u64,
-    pub pci_device_space_size: u64,
-}
-
-#[cfg(target_arch = "aarch64")]
-impl DeviceInfoForFdt for MmioDeviceInfo {
-    fn addr(&self) -> u64 {
-        self.addr
-    }
-    fn irq(&self) -> u32 {
-        self.irq
-    }
-    fn length(&self) -> u64 {
-        self.len
-    }
-}

arch/src/x86_64/gdt.rs

@@ -1,5 +1,3 @@
-// Copyright © 2020, Oracle and/or its affiliates.
-//
 // Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 // SPDX-License-Identifier: Apache-2.0
 //
@@ -8,51 +6,26 @@
 // found in the LICENSE-BSD-3-Clause file.
 
 // For GDT details see arch/x86/include/asm/segment.h
-use crate::arch::x86::SegmentRegister;
+
+use kvm_bindings::kvm_segment;
 
 /// Constructor for a conventional segment GDT (or LDT) entry. Derived from the kernel's segment.h.
 pub fn gdt_entry(flags: u16, base: u32, limit: u32) -> u64 {
-    (((base as u64) & 0xff000000u64) << (56 - 24))
+    ((((base as u64) & 0xff000000u64) << (56 - 24))
         | (((flags as u64) & 0x0000f0ffu64) << 40)
         | (((limit as u64) & 0x000f0000u64) << (48 - 16))
         | (((base as u64) & 0x00ffffffu64) << 16)
-        | ((limit as u64) & 0x0000ffffu64)
+        | ((limit as u64) & 0x0000ffffu64))
 }
 
 fn get_base(entry: u64) -> u64 {
-    (((entry) & 0xFF00000000000000) >> 32)
+    ((((entry) & 0xFF00000000000000) >> 32)
         | (((entry) & 0x000000FF00000000) >> 16)
-        | (((entry) & 0x00000000FFFF0000) >> 16)
+        | (((entry) & 0x00000000FFFF0000) >> 16))
 }
 
-// Extract the segment limit from the GDT segment descriptor.
-//
-// In a segment descriptor, the limit field is 20 bits, so it can directly describe
-// a range from 0 to 0xFFFFF (1MByte). When G flag is set (4-KByte page granularity) it
-// scales the value in the limit field by a factor of 2^12 (4Kbytes), making the effective
-// limit range from 0xFFF (4 KBytes) to 0xFFFF_FFFF (4 GBytes).
-//
-// However, the limit field in the VMCS definition is a 32 bit field, and the limit value is not
-// automatically scaled using the G flag. This means that for a desired range of 4GB for a
-// given segment, its limit must be specified as 0xFFFF_FFFF. Therefore the method of obtaining
-// the limit from the GDT entry is not sufficient, since it only provides 20 bits when 32 bits
-// are necessary. Fortunately, we can check if the G flag is set when extracting the limit since
-// the full GDT entry is passed as an argument, and perform the scaling of the limit value to
-// return the full 32 bit value.
-//
-// The scaling mentioned above is required when using PVH boot, since the guest boots in protected
-// (32-bit) mode and must be able to access the entire 32-bit address space. It does not cause issues
-// for the case of direct boot to 64-bit (long) mode, since in 64-bit mode the processor does not
-// perform runtime limit checking on code or data segments.
 fn get_limit(entry: u64) -> u32 {
-    let limit: u32 =
-        ((((entry) & 0x000F000000000000) >> 32) | ((entry) & 0x000000000000FFFF)) as u32;
-
-    // Perform manual limit scaling if G flag is set
-    match get_g(entry) {
-        0 => limit,
-        _ => (limit << 12) | 0xFFF, // G flag is either 0 or 1
-    }
+    ((((entry) & 0x000F000000000000) >> 32) | ((entry) & 0x000000000000FFFF)) as u32
 }
 
 fn get_g(entry: u64) -> u8 {
@@ -87,14 +60,14 @@ fn get_type(entry: u64) -> u8 {
     ((entry & 0x00000F0000000000) >> 40) as u8
 }
 
-/// Automatically build the struct for SET_SREGS from the kernel bit fields.
+/// Automatically build the kvm struct for SET_SREGS from the kernel bit fields.
 ///
 /// # Arguments
 ///
 /// * `entry` - The gdt entry.
 /// * `table_index` - Index of the entry in the gdt table.
-pub fn segment_from_gdt(entry: u64, table_index: u8) -> SegmentRegister {
-    SegmentRegister {
+pub fn kvm_segment_from_gdt(entry: u64, table_index: u8) -> kvm_segment {
+    kvm_segment {
         base: get_base(entry),
         limit: get_limit(entry),
         selector: (table_index * 8) as u16,
@@ -106,6 +79,7 @@ pub fn segment_from_gdt(entry: u64, table_index: u8) -> SegmentRegister {
         l: get_l(entry),
         g: get_g(entry),
         avl: get_avl(entry),
+        padding: 0,
         unusable: match get_p(entry) {
             0 => 1,
             _ => 0,
@@ -120,7 +94,7 @@ mod tests {
     #[test]
     fn field_parse() {
         let gdt = gdt_entry(0xA09B, 0x100000, 0xfffff);
-        let seg = segment_from_gdt(gdt, 0);
+        let seg = kvm_segment_from_gdt(gdt, 0);
         // 0xA09B
         // 'A'
         assert_eq!(0x1, seg.g);
@@ -135,7 +109,7 @@ mod tests {
         assert_eq!(0xB, seg.type_);
         // base and limit
         assert_eq!(0x100000, seg.base);
-        assert_eq!(0xffffffff, seg.limit);
+        assert_eq!(0xfffff, seg.limit);
         assert_eq!(0x0, seg.unusable);
     }
 }

arch/src/x86_64/interrupts.rs

@@ -5,35 +5,154 @@
 // 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::io::Cursor;
+use std::mem;
 use std::result;
-use std::sync::Arc;
 
-pub type Result<T> = result::Result<T, hypervisor::HypervisorCpuError>;
+use byteorder::{LittleEndian, ReadBytesExt, WriteBytesExt};
+
+use kvm_bindings::kvm_lapic_state;
+use kvm_ioctls;
+
+#[derive(Debug)]
+pub enum Error {
+    GetLapic(kvm_ioctls::Error),
+    SetLapic(kvm_ioctls::Error),
+}
+
+pub type Result<T> = result::Result<T, Error>;
 
 // Defines poached from apicdef.h kernel header.
-pub const APIC_LVT0: usize = 0x350;
-pub const APIC_LVT1: usize = 0x360;
-pub const APIC_MODE_NMI: u32 = 0x4;
-pub const APIC_MODE_EXTINT: u32 = 0x7;
+const APIC_LVT0: usize = 0x350;
+const APIC_LVT1: usize = 0x360;
+const APIC_MODE_NMI: u32 = 0x4;
+const APIC_MODE_EXTINT: u32 = 0x7;
 
-pub fn set_apic_delivery_mode(reg: u32, mode: u32) -> u32 {
-    ((reg) & !0x700) | ((mode) << 8)
+fn get_klapic_reg(klapic: &kvm_lapic_state, reg_offset: usize) -> u32 {
+    let sliceu8 = unsafe {
+        // This array is only accessed as parts of a u32 word, so interpret it as a u8 array.
+        // Cursors are only readable on arrays of u8, not i8(c_char).
+        mem::transmute::<&[i8], &[u8]>(&klapic.regs[reg_offset..])
+    };
+    let mut reader = Cursor::new(sliceu8);
+    // Following call can't fail if the offsets defined above are correct.
+    reader
+        .read_u32::<LittleEndian>()
+        .expect("Failed to read klapic register")
+}
+
+fn set_klapic_reg(klapic: &mut kvm_lapic_state, reg_offset: usize, value: u32) {
+    let sliceu8 = unsafe {
+        // This array is only accessed as parts of a u32 word, so interpret it as a u8 array.
+        // Cursors are only readable on arrays of u8, not i8(c_char).
+        mem::transmute::<&mut [i8], &mut [u8]>(&mut klapic.regs[reg_offset..])
+    };
+    let mut writer = Cursor::new(sliceu8);
+    // Following call can't fail if the offsets defined above are correct.
+    writer
+        .write_u32::<LittleEndian>(value)
+        .expect("Failed to write klapic register")
+}
+
+fn set_apic_delivery_mode(reg: u32, mode: u32) -> u32 {
+    (((reg) & !0x700) | ((mode) << 8))
 }
 
 /// Configures LAPICs.  LAPIC0 is set for external interrupts, LAPIC1 is set for NMI.
 ///
 /// # Arguments
 /// * `vcpu` - The VCPU object to configure.
-pub fn set_lint(vcpu: &Arc<dyn hypervisor::Vcpu>) -> Result<()> {
-    let mut klapic = vcpu.get_lapic()?;
+pub fn set_lint(vcpu: &kvm_ioctls::VcpuFd) -> Result<()> {
+    let mut klapic = vcpu.get_lapic().map_err(Error::GetLapic)?;
 
-    let lvt_lint0 = klapic.get_klapic_reg(APIC_LVT0);
-    klapic.set_klapic_reg(
+    let lvt_lint0 = get_klapic_reg(&klapic, APIC_LVT0);
+    set_klapic_reg(
+        &mut klapic,
         APIC_LVT0,
         set_apic_delivery_mode(lvt_lint0, APIC_MODE_EXTINT),
     );
-    let lvt_lint1 = klapic.get_klapic_reg(APIC_LVT1);
-    klapic.set_klapic_reg(APIC_LVT1, set_apic_delivery_mode(lvt_lint1, APIC_MODE_NMI));
+    let lvt_lint1 = get_klapic_reg(&klapic, APIC_LVT1);
+    set_klapic_reg(
+        &mut klapic,
+        APIC_LVT1,
+        set_apic_delivery_mode(lvt_lint1, APIC_MODE_NMI),
+    );
 
-    vcpu.set_lapic(&klapic)
+    vcpu.set_lapic(&klapic).map_err(Error::SetLapic)
+}
+
+#[cfg(test)]
+mod tests {
+    extern crate kvm_ioctls;
+    extern crate rand;
+    use self::rand::Rng;
+
+    use super::*;
+    use kvm_ioctls::Kvm;
+
+    const KVM_APIC_REG_SIZE: usize = 0x400;
+
+    #[test]
+    fn test_set_and_get_klapic_reg() {
+        let reg_offset = 0x340;
+        let mut klapic = kvm_lapic_state::default();
+        set_klapic_reg(&mut klapic, reg_offset, 3);
+        let value = get_klapic_reg(&klapic, reg_offset);
+        assert_eq!(value, 3);
+    }
+
+    #[test]
+    #[should_panic]
+    fn test_set_and_get_klapic_out_of_bounds() {
+        let reg_offset = KVM_APIC_REG_SIZE + 10;
+        let mut klapic = kvm_lapic_state::default();
+        set_klapic_reg(&mut klapic, reg_offset, 3);
+    }
+
+    #[test]
+    fn test_apic_delivery_mode() {
+        let mut rng = rand::thread_rng();
+        let mut v: Vec<u32> = (0..20).map(|_| rng.gen::<u32>()).collect();
+
+        v.iter_mut()
+            .for_each(|x| *x = set_apic_delivery_mode(*x, 2));
+        let after: Vec<u32> = v.iter().map(|x| ((*x & !0x700) | ((2) << 8))).collect();
+        assert_eq!(v, after);
+    }
+
+    #[test]
+    fn test_setlint() {
+        let kvm = kvm_ioctls::Kvm::new().unwrap();
+        assert!(kvm.check_extension(kvm_ioctls::Cap::Irqchip));
+        let vm = kvm.create_vm().unwrap();
+        //the get_lapic ioctl will fail if there is no irqchip created beforehand.
+        assert!(vm.create_irq_chip().is_ok());
+        let vcpu = vm.create_vcpu(0).unwrap();
+        let klapic_before: kvm_lapic_state = vcpu.get_lapic().unwrap();
+
+        // Compute the value that is expected to represent LVT0 and LVT1.
+        let lint0 = get_klapic_reg(&klapic_before, APIC_LVT0);
+        let lint1 = get_klapic_reg(&klapic_before, APIC_LVT1);
+        let lint0_mode_expected = set_apic_delivery_mode(lint0, APIC_MODE_EXTINT);
+        let lint1_mode_expected = set_apic_delivery_mode(lint1, APIC_MODE_NMI);
+
+        set_lint(&vcpu).unwrap();
+
+        // Compute the value that represents LVT0 and LVT1 after set_lint.
+        let klapic_actual: kvm_lapic_state = vcpu.get_lapic().unwrap();
+        let lint0_mode_actual = get_klapic_reg(&klapic_actual, APIC_LVT0);
+        let lint1_mode_actual = get_klapic_reg(&klapic_actual, APIC_LVT1);
+        assert_eq!(lint0_mode_expected, lint0_mode_actual);
+        assert_eq!(lint1_mode_expected, lint1_mode_actual);
+    }
+
+    #[test]
+    fn test_setlint_fails() {
+        let kvm = Kvm::new().unwrap();
+        let vm = kvm.create_vm().unwrap();
+        let vcpu = vm.create_vcpu(0).unwrap();
+        // 'get_lapic' ioctl triggered by the 'set_lint' function will fail if there is no
+        // irqchip created beforehand.
+        assert!(set_lint(&vcpu).is_err());
+    }
 }

arch/src/x86_64/layout.rs

@@ -1,5 +1,3 @@
-// Copyright © 2020, Oracle and/or its affiliates.
-//
 // Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 // SPDX-License-Identifier: Apache-2.0
 //
@@ -7,7 +5,7 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE-BSD-3-Clause file.
 
-use vm_memory::GuestAddress;
+use vm_memory::{GuestAddress, GuestUsize};
 
 /*
 
@@ -24,24 +22,10 @@ pub const LOW_RAM_START: GuestAddress = GuestAddress(0x0);
 
 // == Fixed addresses within the "Low RAM" range: ==
 
-// Location of EBDA address
-pub const EBDA_POINTER: GuestAddress = GuestAddress(0x40e);
-
 // Initial GDT/IDT needed to boot kernel
 pub const BOOT_GDT_START: GuestAddress = GuestAddress(0x500);
 pub const BOOT_IDT_START: GuestAddress = GuestAddress(0x520);
 
-/// Address for the hvm_start_info struct used in PVH boot
-pub const PVH_INFO_START: GuestAddress = GuestAddress(0x6000);
-
-/// Starting address of array of modules of hvm_modlist_entry type.
-/// Used to enable initrd support using the PVH boot ABI.
-pub const MODLIST_START: GuestAddress = GuestAddress(0x6040);
-
-/// Address of memory map table used in PVH boot. Can overlap
-/// with the zero page address since they are mutually exclusive.
-pub const MEMMAP_START: GuestAddress = GuestAddress(0x7000);
-
 /// The 'zero page', a.k.a linux kernel bootparams.
 pub const ZERO_PAGE_START: GuestAddress = GuestAddress(0x7000);
 
@@ -50,10 +34,9 @@ pub const BOOT_STACK_START: GuestAddress = GuestAddress(0x8000);
 pub const BOOT_STACK_POINTER: GuestAddress = GuestAddress(0x8ff0);
 
 // Initial pagetables.
-pub const PML5_START: GuestAddress = GuestAddress(0x9000);
-pub const PML4_START: GuestAddress = GuestAddress(0xa000);
-pub const PDPTE_START: GuestAddress = GuestAddress(0xb000);
-pub const PDE_START: GuestAddress = GuestAddress(0xc000);
+pub const PML4_START: GuestAddress = GuestAddress(0x9000);
+pub const PDPTE_START: GuestAddress = GuestAddress(0xa000);
+pub const PDE_START: GuestAddress = GuestAddress(0xb000);
 
 /// Kernel command line start address.
 pub const CMDLINE_START: GuestAddress = GuestAddress(0x20000);
@@ -73,8 +56,6 @@ pub const EBDA_START: GuestAddress = GuestAddress(0xa0000);
 // ACPI RSDP table
 pub const RSDP_POINTER: GuestAddress = EBDA_START;
 
-pub const SMBIOS_START: u64 = 0xf0000; // First possible location per the spec.
-
 // == End of "EBDA" range ==
 
 // ** High RAM (start: 1MiB, length: 3071MiB) **
@@ -82,43 +63,31 @@ pub const HIGH_RAM_START: GuestAddress = GuestAddress(0x100000);
 
 // == No fixed addresses in the "High RAM" range ==
 
-// ** 32-bit reserved area (start: 3GiB, length: 896MiB) **
+// ** 32-bit reserved area (start: 3GiB, length: 1GiB) **
 pub const MEM_32BIT_RESERVED_START: GuestAddress = GuestAddress(0xc000_0000);
-pub const MEM_32BIT_RESERVED_SIZE: u64 = PCI_MMCONFIG_SIZE + MEM_32BIT_DEVICES_SIZE;
+pub const MEM_32BIT_RESERVED_SIZE: GuestUsize = (1024 << 20);
 
 // == Fixed constants within the "32-bit reserved" range ==
 
 // Sub range: 32-bit PCI devices (start: 3GiB, length: 640Mib)
 pub const MEM_32BIT_DEVICES_START: GuestAddress = MEM_32BIT_RESERVED_START;
-pub const MEM_32BIT_DEVICES_SIZE: u64 = 640 << 20;
+pub const MEM_32BIT_DEVICES_SIZE: GuestUsize = (640 << 20);
 
 // PCI MMCONFIG space (start: after the device space, length: 256MiB)
 pub const PCI_MMCONFIG_START: GuestAddress =
     GuestAddress(MEM_32BIT_DEVICES_START.0 + MEM_32BIT_DEVICES_SIZE);
-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;
-
-// TSS is 3 pages after the PCI MMCONFIG space
-pub const KVM_TSS_START: GuestAddress = GuestAddress(PCI_MMCONFIG_START.0 + PCI_MMCONFIG_SIZE);
-pub const KVM_TSS_SIZE: u64 = (3 * 4) << 10;
-
-// Identity map is a one page region after the TSS
-pub const KVM_IDENTITY_MAP_START: GuestAddress = GuestAddress(KVM_TSS_START.0 + KVM_TSS_SIZE);
-pub const KVM_IDENTITY_MAP_SIZE: u64 = 4 << 10;
-
-/// TPM Address Range
-/// This Address range is specific to CRB Interface
-pub const TPM_START: GuestAddress = GuestAddress(0xfed4_0000);
-pub const TPM_SIZE: u64 = 0x1000;
+pub const PCI_MMCONFIG_SIZE: GuestUsize = (256 << 20);
 
 // IOAPIC
 pub const IOAPIC_START: GuestAddress = GuestAddress(0xfec0_0000);
-pub const IOAPIC_SIZE: u64 = 0x20;
+pub const IOAPIC_SIZE: GuestUsize = 0x20;
 
 // APIC
 pub const APIC_START: GuestAddress = GuestAddress(0xfee0_0000);
 
+/// Address for the TSS setup.
+pub const KVM_TSS_ADDRESS: GuestAddress = GuestAddress(0xfffb_d000);
+
 // == End of "32-bit reserved" range. ==
 
 // ** 64-bit RAM start (start: 4GiB, length: varies) **

arch/src/x86_64/mpspec.rs

@@ -1,114 +0,0 @@
-// 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.
-
-pub const MP_PROCESSOR: ::std::os::raw::c_uint = 0;
-pub const MP_BUS: ::std::os::raw::c_uint = 1;
-pub const MP_IOAPIC: ::std::os::raw::c_uint = 2;
-pub const MP_INTSRC: ::std::os::raw::c_uint = 3;
-pub const MP_LINTSRC: ::std::os::raw::c_uint = 4;
-pub const CPU_ENABLED: ::std::os::raw::c_uint = 1;
-pub const CPU_BOOTPROCESSOR: ::std::os::raw::c_uint = 2;
-pub const MPC_APIC_USABLE: ::std::os::raw::c_uint = 1;
-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 physptr: ::std::os::raw::c_uint,
-    pub length: ::std::os::raw::c_uchar,
-    pub specification: ::std::os::raw::c_uchar,
-    pub checksum: ::std::os::raw::c_uchar,
-    pub feature1: ::std::os::raw::c_uchar,
-    pub feature2: ::std::os::raw::c_uchar,
-    pub feature3: ::std::os::raw::c_uchar,
-    pub feature4: ::std::os::raw::c_uchar,
-    pub feature5: ::std::os::raw::c_uchar,
-}
-
-#[repr(C)]
-#[derive(Debug, Default, Copy, Clone)]
-pub struct mpc_table {
-    pub signature: [::std::os::raw::c_uchar; 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 oemptr: ::std::os::raw::c_uint,
-    pub oemsize: ::std::os::raw::c_ushort,
-    pub oemcount: ::std::os::raw::c_ushort,
-    pub lapic: ::std::os::raw::c_uint,
-    pub reserved: ::std::os::raw::c_uint,
-}
-
-#[repr(C)]
-#[derive(Debug, Default, Copy, Clone)]
-pub struct mpc_cpu {
-    pub type_: ::std::os::raw::c_uchar,
-    pub apicid: ::std::os::raw::c_uchar,
-    pub apicver: ::std::os::raw::c_uchar,
-    pub cpuflag: ::std::os::raw::c_uchar,
-    pub cpufeature: ::std::os::raw::c_uint,
-    pub featureflag: ::std::os::raw::c_uint,
-    pub reserved: [::std::os::raw::c_uint; 2usize],
-}
-
-#[repr(C)]
-#[derive(Debug, Default, Copy, Clone)]
-pub struct mpc_bus {
-    pub type_: ::std::os::raw::c_uchar,
-    pub busid: ::std::os::raw::c_uchar,
-    pub bustype: [::std::os::raw::c_uchar; 6usize],
-}
-
-#[repr(C)]
-#[derive(Debug, Default, Copy, Clone)]
-pub struct mpc_ioapic {
-    pub type_: ::std::os::raw::c_uchar,
-    pub apicid: ::std::os::raw::c_uchar,
-    pub apicver: ::std::os::raw::c_uchar,
-    pub flags: ::std::os::raw::c_uchar,
-    pub apicaddr: ::std::os::raw::c_uint,
-}
-
-#[repr(C)]
-#[derive(Debug, Default, Copy, Clone)]
-pub struct mpc_intsrc {
-    pub type_: ::std::os::raw::c_uchar,
-    pub irqtype: ::std::os::raw::c_uchar,
-    pub irqflag: ::std::os::raw::c_ushort,
-    pub srcbus: ::std::os::raw::c_uchar,
-    pub srcbusirq: ::std::os::raw::c_uchar,
-    pub dstapic: ::std::os::raw::c_uchar,
-    pub dstirq: ::std::os::raw::c_uchar,
-}
-
-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;
-
-#[repr(C)]
-#[derive(Debug, Default, Copy, Clone)]
-pub struct mpc_lintsrc {
-    pub type_: ::std::os::raw::c_uchar,
-    pub irqtype: ::std::os::raw::c_uchar,
-    pub irqflag: ::std::os::raw::c_ushort,
-    pub srcbusid: ::std::os::raw::c_uchar,
-    pub srcbusirq: ::std::os::raw::c_uchar,
-    pub destapic: ::std::os::raw::c_uchar,
-    pub destapiclint: ::std::os::raw::c_uchar,
-}
-
-#[repr(C)]
-#[derive(Debug, Default, Copy, Clone)]
-pub struct mpc_oemtable {
-    pub signature: [::std::os::raw::c_uchar; 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],
-}

arch/src/x86_64/mptable.rs

@@ -5,15 +5,16 @@
 // 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 std::io;
+use std::mem;
+use std::result;
+use std::slice;
 
-use libc::c_uchar;
-use thiserror::Error;
-use vm_memory::{Address, ByteValued, Bytes, GuestAddress, GuestMemory, GuestMemoryError};
+use libc::c_char;
 
-use crate::layout::{APIC_START, HIGH_RAM_START, IOAPIC_START};
-use crate::x86_64::{get_x2apic_id, mpspec};
-use crate::GuestMemoryMmap;
+use arch_gen::x86::mpspec;
+use layout::{APIC_START, IOAPIC_START, MPTABLE_START};
+use vm_memory::{Address, ByteValued, Bytes, GuestMemory, GuestMemoryError, GuestMemoryMmap};
 
 // This is a workaround to the Rust enforcement specifying that any implementation of a foreign
 // trait (in this case `ByteValued`) where:
@@ -35,55 +36,38 @@ struct MpcLintsrcWrapper(mpspec::mpc_lintsrc);
 #[derive(Copy, Clone, Default)]
 struct MpfIntelWrapper(mpspec::mpf_intel);
 
-// SAFETY: These `mpspec` wrapper types are only data, reading them from data is a safe initialization.
+// These `mpspec` wrapper types are only data, reading them from data is a safe initialization.
 unsafe impl ByteValued for MpcBusWrapper {}
-// SAFETY: see above
 unsafe impl ByteValued for MpcCpuWrapper {}
-// SAFETY: see above
 unsafe impl ByteValued for MpcIntsrcWrapper {}
-// SAFETY: see above
 unsafe impl ByteValued for MpcIoapicWrapper {}
-// SAFETY: see above
 unsafe impl ByteValued for MpcTableWrapper {}
-// SAFETY: see above
 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: {0}")]
     Clear(GuestMemoryError),
     /// Number of CPUs exceeds the maximum supported CPUs
-    #[error("Number of CPUs exceeds the maximum supported CPUs")]
     TooManyCpus,
     /// Failure to write the MP floating pointer.
-    #[error("Failure to write the MP floating pointer: {0}")]
     WriteMpfIntel(GuestMemoryError),
     /// Failure to write MP CPU entry.
-    #[error("Failure to write MP CPU entry: {0}")]
     WriteMpcCpu(GuestMemoryError),
     /// Failure to write MP ioapic entry.
-    #[error("Failure to write MP ioapic entry: {0}")]
     WriteMpcIoapic(GuestMemoryError),
     /// Failure to write MP bus entry.
-    #[error("Failure to write MP bus entry: {0}")]
     WriteMpcBus(GuestMemoryError),
     /// Failure to write MP interrupt source entry.
-    #[error("Failure to write MP interrupt source entry: {0}")]
     WriteMpcIntsrc(GuestMemoryError),
     /// Failure to write MP local interrupt source entry.
-    #[error("Failure to write MP local interrupt source entry: {0}")]
     WriteMpcLintsrc(GuestMemoryError),
     /// Failure to write MP table header.
-    #[error("Failure to write MP table header: {0}")]
     WriteMpcTable(GuestMemoryError),
 }
 
@@ -94,20 +78,25 @@ pub type Result<T> = result::Result<T, Error>;
 // 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>(v: &T) -> u8 {
-    // SAFETY: we are only reading the bytes within the size of the `T` reference `v`.
+    // Safe because 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;
     for i in v_slice.iter() {
@@ -132,32 +121,18 @@ fn compute_mp_size(num_cpus: u8) -> usize {
 }
 
 /// Performs setup of the MP table for the given `num_cpus`.
-pub fn setup_mptable(
-    offset: GuestAddress,
-    mem: &GuestMemoryMmap,
-    num_cpus: u8,
-    topology: Option<(u8, u8, u8)>,
-) -> Result<()> {
-    if num_cpus > 0 {
-        let cpu_id_max = num_cpus - 1;
-        let x2apic_id_max = get_x2apic_id(cpu_id_max.into(), topology);
-        if x2apic_id_max >= MAX_SUPPORTED_CPUS {
-            return Err(Error::TooManyCpus);
-        }
+pub fn setup_mptable(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.
-    let mut base_mp = offset;
+    let mut base_mp = MPTABLE_START;
 
     let mp_size = compute_mp_size(num_cpus);
 
-    if offset.unchecked_add(mp_size as u64) >= HIGH_RAM_START {
-        warn!("Skipping mptable creation due to insufficient space");
-        return Ok(());
-    }
-
     let mut checksum: u8 = 0;
-    let ioapicid: u8 = MAX_SUPPORTED_CPUS 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.
@@ -169,13 +144,13 @@ 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;
@@ -195,7 +170,7 @@ 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 as u32, 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 {
@@ -216,7 +191,7 @@ 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);
@@ -240,7 +215,7 @@ pub fn setup_mptable(
         let size = mem::size_of::<MpcIntsrcWrapper>();
         let mut mpc_intsrc = MpcIntsrcWrapper(mpspec::mpc_intsrc::default());
         mpc_intsrc.0.type_ = mpspec::MP_INTSRC as u8;
-        mpc_intsrc.0.irqtype = mpspec::MP_IRQ_SOURCE_TYPES_MP_INT as u8;
+        mpc_intsrc.0.irqtype = mpspec::mp_irq_source_types_mp_INT as u8;
         mpc_intsrc.0.irqflag = mpspec::MP_IRQDIR_DEFAULT as u16;
         mpc_intsrc.0.srcbus = 0;
         mpc_intsrc.0.srcbusirq = i;
@@ -255,7 +230,7 @@ pub fn setup_mptable(
         let size = mem::size_of::<MpcLintsrcWrapper>();
         let mut mpc_lintsrc = MpcLintsrcWrapper(mpspec::mpc_lintsrc::default());
         mpc_lintsrc.0.type_ = mpspec::MP_LINTSRC as u8;
-        mpc_lintsrc.0.irqtype = mpspec::MP_IRQ_SOURCE_TYPES_MP_EXT_INT as u8;
+        mpc_lintsrc.0.irqtype = mpspec::mp_irq_source_types_mp_ExtINT as u8;
         mpc_lintsrc.0.irqflag = mpspec::MP_IRQDIR_DEFAULT as u16;
         mpc_lintsrc.0.srcbusid = 0;
         mpc_lintsrc.0.srcbusirq = 0;
@@ -270,7 +245,7 @@ pub fn setup_mptable(
         let size = mem::size_of::<MpcLintsrcWrapper>();
         let mut mpc_lintsrc = MpcLintsrcWrapper(mpspec::mpc_lintsrc::default());
         mpc_lintsrc.0.type_ = mpspec::MP_LINTSRC as u8;
-        mpc_lintsrc.0.irqtype = mpspec::MP_IRQ_SOURCE_TYPES_MP_NMI as u8;
+        mpc_lintsrc.0.irqtype = mpspec::mp_irq_source_types_mp_NMI as u8;
         mpc_lintsrc.0.irqflag = mpspec::MP_IRQDIR_DEFAULT as u16;
         mpc_lintsrc.0.srcbusid = 0;
         mpc_lintsrc.0.srcbusirq = 0;
@@ -287,14 +262,14 @@ 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)?;
     }
@@ -304,11 +279,8 @@ 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 {
@@ -317,7 +289,7 @@ mod tests {
             mpspec::MP_IOAPIC => mem::size_of::<MpcIoapicWrapper>(),
             mpspec::MP_INTSRC => mem::size_of::<MpcIntsrcWrapper>(),
             mpspec::MP_LINTSRC => mem::size_of::<MpcLintsrcWrapper>(),
-            _ => panic!("unrecognized mpc table entry type: {type_}"),
+            _ => panic!("unrecognized mpc table entry type: {}", type_),
         }
     }
 
@@ -327,7 +299,7 @@ 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(&mem, num_cpus).unwrap();
     }
 
     #[test]
@@ -336,7 +308,7 @@ 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(&mem, num_cpus).is_err());
     }
 
     #[test]
@@ -345,7 +317,7 @@ 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(&mem, num_cpus).unwrap();
 
         let mpf_intel: MpfIntelWrapper = mem.read_obj(MPTABLE_START).unwrap();
 
@@ -361,31 +333,27 @@ 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(&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);
     }
@@ -399,7 +367,7 @@ mod tests {
         .unwrap();
 
         for i in 0..MAX_SUPPORTED_CPUS as u8 {
-            setup_mptable(MPTABLE_START, &mem, i, None).unwrap();
+            setup_mptable(&mem, i).unwrap();
 
             let mpf_intel: MpfIntelWrapper = mem.read_obj(MPTABLE_START).unwrap();
             let mpc_offset = GuestAddress(mpf_intel.0.physptr as GuestUsize);
@@ -432,7 +400,7 @@ mod tests {
         let mem =
             GuestMemoryMmap::from_ranges(&[(MPTABLE_START, compute_mp_size(cpus as u8))]).unwrap();
 
-        let result = setup_mptable(MPTABLE_START, &mem, cpus as u8, None);
-        result.unwrap_err();
+        let result = setup_mptable(&mem, cpus as u8);
+        assert!(result.is_err());
     }
 }

arch/src/x86_64/regs.rs

@@ -1,63 +1,47 @@
-// Copyright © 2020, Oracle and/or its affiliates.
-//
 // Copyright 2018 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 LICENSE-BSD-3-Clause file.
-use std::sync::Arc;
+
 use std::{mem, result};
 
-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 vm_memory::{Address, Bytes, GuestMemory, GuestMemoryError};
+use super::gdt::{gdt_entry, kvm_segment_from_gdt};
+use arch_gen::x86::msr_index;
+use kvm_bindings::{kvm_fpu, kvm_msr_entry, kvm_regs, kvm_sregs, Msrs};
+use kvm_ioctls::VcpuFd;
+use layout::{BOOT_GDT_START, BOOT_IDT_START, PDE_START, PDPTE_START, PML4_START};
+use vm_memory::{Address, Bytes, GuestMemory, GuestMemoryError, GuestMemoryMmap};
 
-use crate::layout::{
-    BOOT_GDT_START, BOOT_IDT_START, BOOT_STACK_POINTER, PVH_INFO_START, ZERO_PAGE_START,
-};
-use crate::{EntryPoint, GuestMemoryMmap};
+// MTRR constants
+const MTRR_ENABLE: u64 = 0x800; // IA32_MTRR_DEF_TYPE MSR: E (MTRRs enabled) flag, bit 11
+const MTRR_MEM_TYPE_WB: u64 = 0x6;
 
-#[derive(Debug, Error)]
+#[derive(Debug)]
 pub enum Error {
     /// Failed to get SREGs for this CPU.
-    #[error("Failed to get SREGs for this CPU: {0}")]
-    GetStatusRegisters(hypervisor::HypervisorCpuError),
+    GetStatusRegisters(kvm_ioctls::Error),
     /// Failed to set base registers for this CPU.
-    #[error("Failed to set base registers for this CPU: {0}")]
-    SetBaseRegisters(hypervisor::HypervisorCpuError),
+    SetBaseRegisters(kvm_ioctls::Error),
     /// Failed to configure the FPU.
-    #[error("Failed to configure the FPU: {0}")]
-    SetFpuRegisters(hypervisor::HypervisorCpuError),
+    SetFPURegisters(kvm_ioctls::Error),
     /// Setting up MSRs failed.
-    #[error("Setting up MSRs failed: {0}")]
-    SetModelSpecificRegisters(hypervisor::HypervisorCpuError),
+    SetModelSpecificRegisters(kvm_ioctls::Error),
     /// Failed to set SREGs for this CPU.
-    #[error("Failed to set SREGs for this CPU: {0}")]
-    SetStatusRegisters(hypervisor::HypervisorCpuError),
+    SetStatusRegisters(kvm_ioctls::Error),
     /// Checking the GDT address failed.
-    #[error("Checking the GDT address failed")]
-    CheckGdtAddr,
+    CheckGDTAddr,
     /// Writing the GDT to RAM failed.
-    #[error("Writing the GDT to RAM failed: {0}")]
-    WriteGdt(GuestMemoryError),
+    WriteGDT(GuestMemoryError),
     /// Writing the IDT to RAM failed.
-    #[error("Writing the IDT to RAM failed: {0}")]
-    WriteIdt(GuestMemoryError),
+    WriteIDT(GuestMemoryError),
     /// Writing PDPTE to RAM failed.
-    #[error("Writing PDPTE to RAM failed: {0}")]
-    WritePdpteAddress(GuestMemoryError),
+    WritePDPTEAddress(GuestMemoryError),
     /// Writing PDE to RAM failed.
-    #[error("Writing PDE to RAM failed: {0}")]
-    WritePdeAddress(GuestMemoryError),
+    WritePDEAddress(GuestMemoryError),
     /// Writing PML4 to RAM failed.
-    #[error("Writing PML4 to RAM failed: {0}")]
-    WritePml4Address(GuestMemoryError),
-    /// Writing PML5 to RAM failed.
-    #[error("Writing PML5 to RAM failed: {0}")]
-    WritePml5Address(GuestMemoryError),
+    WritePML4Address(GuestMemoryError),
 }
 
 pub type Result<T> = result::Result<T, Error>;
@@ -67,14 +51,14 @@ pub type Result<T> = result::Result<T, Error>;
 /// # Arguments
 ///
 /// * `vcpu` - Structure for the VCPU that holds the VCPU's fd.
-pub fn setup_fpu(vcpu: &Arc<dyn hypervisor::Vcpu>) -> Result<()> {
-    let fpu: FpuState = FpuState {
+pub fn setup_fpu(vcpu: &VcpuFd) -> Result<()> {
+    let fpu: kvm_fpu = kvm_fpu {
         fcw: 0x37f,
         mxcsr: 0x1f80,
         ..Default::default()
     };
 
-    vcpu.set_fpu(&fpu).map_err(Error::SetFpuRegisters)
+    vcpu.set_fpu(&fpu).map_err(Error::SetFPURegisters)
 }
 
 /// Configure Model Specific Registers (MSRs) for a given CPU.
@@ -82,8 +66,8 @@ pub fn setup_fpu(vcpu: &Arc<dyn hypervisor::Vcpu>) -> Result<()> {
 /// # Arguments
 ///
 /// * `vcpu` - Structure for the VCPU that holds the VCPU's fd.
-pub fn setup_msrs(vcpu: &Arc<dyn hypervisor::Vcpu>) -> Result<()> {
-    vcpu.set_msrs(&vcpu.boot_msr_entries())
+pub fn setup_msrs(vcpu: &VcpuFd) -> Result<()> {
+    vcpu.set_msrs(&create_msr_entries())
         .map_err(Error::SetModelSpecificRegisters)?;
 
     Ok(())
@@ -94,22 +78,19 @@ 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.
+/// * `boot_sp` - Starting stack pointer.
+/// * `boot_si` - Must point to zero page address per Linux ABI.
+pub fn setup_regs(vcpu: &VcpuFd, boot_ip: u64, boot_sp: u64, boot_si: u64) -> Result<()> {
+    let regs: kvm_regs = kvm_regs {
+        rflags: 0x0000000000000002u64,
+        rip: boot_ip,
+        rsp: boot_sp,
+        rbp: boot_sp,
+        rsi: boot_si,
+        ..Default::default()
     };
+
     vcpu.set_regs(&regs).map_err(Error::SetBaseRegisters)
 }
 
@@ -119,21 +100,31 @@ 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>) -> Result<()> {
-    let mut sregs: SpecialRegisters = vcpu.get_sregs().map_err(Error::GetStatusRegisters)?;
+pub fn setup_sregs(mem: &GuestMemoryMmap, vcpu: &VcpuFd) -> Result<()> {
+    let mut sregs: kvm_sregs = vcpu.get_sregs().map_err(Error::GetStatusRegisters)?;
+
     configure_segments_and_sregs(mem, &mut sregs)?;
+    setup_page_tables(mem, &mut sregs)?; // TODO(dgreid) - Can this be done once per system instead?
+
     vcpu.set_sregs(&sregs).map_err(Error::SetStatusRegisters)
 }
 
 const BOOT_GDT_MAX: usize = 4;
 
+const EFER_LMA: u64 = 0x400;
+const EFER_LME: u64 = 0x100;
+
+const X86_CR0_PE: u64 = 0x1;
+const X86_CR0_PG: u64 = 0x80000000;
+const X86_CR4_PAE: u64 = 0x20;
+
 fn write_gdt_table(table: &[u64], guest_mem: &GuestMemoryMmap) -> Result<()> {
     let boot_gdt_addr = BOOT_GDT_START;
     for (index, entry) in table.iter().enumerate() {
         let addr = guest_mem
             .checked_offset(boot_gdt_addr, index * mem::size_of::<u64>())
-            .ok_or(Error::CheckGdtAddr)?;
-        guest_mem.write_obj(*entry, addr).map_err(Error::WriteGdt)?;
+            .ok_or(Error::CheckGDTAddr)?;
+        guest_mem.write_obj(*entry, addr).map_err(Error::WriteGDT)?;
     }
     Ok(())
 }
@@ -142,26 +133,20 @@ fn write_idt_value(val: u64, guest_mem: &GuestMemoryMmap) -> Result<()> {
     let boot_idt_addr = BOOT_IDT_START;
     guest_mem
         .write_obj(val, boot_idt_addr)
-        .map_err(Error::WriteIdt)
+        .map_err(Error::WriteIDT)
 }
 
-pub fn configure_segments_and_sregs(
-    mem: &GuestMemoryMmap,
-    sregs: &mut SpecialRegisters,
-) -> Result<()> {
-    let gdt_table: [u64; BOOT_GDT_MAX] = {
-        // Configure GDT entries as specified by PVH boot protocol
-        [
-            gdt_entry(0, 0, 0),               // NULL
-            gdt_entry(0xc09b, 0, 0xffffffff), // CODE
-            gdt_entry(0xc093, 0, 0xffffffff), // DATA
-            gdt_entry(0x008b, 0, 0x67),       // TSS
-        ]
-    };
+fn configure_segments_and_sregs(mem: &GuestMemoryMmap, sregs: &mut kvm_sregs) -> Result<()> {
+    let gdt_table: [u64; BOOT_GDT_MAX as usize] = [
+        gdt_entry(0, 0, 0),            // NULL
+        gdt_entry(0xa09b, 0, 0xfffff), // CODE
+        gdt_entry(0xc093, 0, 0xfffff), // DATA
+        gdt_entry(0x808b, 0, 0xfffff), // TSS
+    ];
 
-    let code_seg = segment_from_gdt(gdt_table[1], 1);
-    let data_seg = segment_from_gdt(gdt_table[2], 2);
-    let tss_seg = segment_from_gdt(gdt_table[3], 3);
+    let code_seg = kvm_segment_from_gdt(gdt_table[1], 1);
+    let data_seg = kvm_segment_from_gdt(gdt_table[2], 2);
+    let tss_seg = kvm_segment_from_gdt(gdt_table[3], 3);
 
     // Write segments
     write_gdt_table(&gdt_table[..], mem)?;
@@ -180,20 +165,111 @@ pub fn configure_segments_and_sregs(
     sregs.ss = data_seg;
     sregs.tr = tss_seg;
 
-    sregs.cr0 = CR0_PE;
-    sregs.cr4 = 0;
+    /* 64-bit protected mode */
+    sregs.cr0 |= X86_CR0_PE;
+    sregs.efer |= EFER_LME | EFER_LMA;
 
     Ok(())
 }
 
+fn setup_page_tables(mem: &GuestMemoryMmap, sregs: &mut kvm_sregs) -> Result<()> {
+    // Puts PML4 right after zero page but aligned to 4k.
+
+    // Entry covering VA [0..512GB)
+    mem.write_obj(PDPTE_START.raw_value() | 0x03, PML4_START)
+        .map_err(Error::WritePML4Address)?;
+
+    // Entry covering VA [0..1GB)
+    mem.write_obj(PDE_START.raw_value() | 0x03, PDPTE_START)
+        .map_err(Error::WritePDPTEAddress)?;
+    // 512 2MB entries together covering VA [0..1GB). Note we are assuming
+    // CPU supports 2MB pages (/proc/cpuinfo has 'pse'). All modern CPUs do.
+    for i in 0..512 {
+        mem.write_obj((i << 21) + 0x83u64, PDE_START.unchecked_add(i * 8))
+            .map_err(Error::WritePDEAddress)?;
+    }
+
+    sregs.cr3 = PML4_START.raw_value();
+    sregs.cr4 |= X86_CR4_PAE;
+    sregs.cr0 |= X86_CR0_PG;
+    Ok(())
+}
+
+fn create_msr_entries() -> Msrs {
+    let mut entries = Vec::<kvm_msr_entry>::new();
+
+    entries.push(kvm_msr_entry {
+        index: msr_index::MSR_IA32_SYSENTER_CS,
+        data: 0x0,
+        ..Default::default()
+    });
+    entries.push(kvm_msr_entry {
+        index: msr_index::MSR_IA32_SYSENTER_ESP,
+        data: 0x0,
+        ..Default::default()
+    });
+    entries.push(kvm_msr_entry {
+        index: msr_index::MSR_IA32_SYSENTER_EIP,
+        data: 0x0,
+        ..Default::default()
+    });
+    // x86_64 specific msrs, we only run on x86_64 not x86.
+    entries.push(kvm_msr_entry {
+        index: msr_index::MSR_STAR,
+        data: 0x0,
+        ..Default::default()
+    });
+    entries.push(kvm_msr_entry {
+        index: msr_index::MSR_CSTAR,
+        data: 0x0,
+        ..Default::default()
+    });
+    entries.push(kvm_msr_entry {
+        index: msr_index::MSR_KERNEL_GS_BASE,
+        data: 0x0,
+        ..Default::default()
+    });
+    entries.push(kvm_msr_entry {
+        index: msr_index::MSR_SYSCALL_MASK,
+        data: 0x0,
+        ..Default::default()
+    });
+    entries.push(kvm_msr_entry {
+        index: msr_index::MSR_LSTAR,
+        data: 0x0,
+        ..Default::default()
+    });
+    // end of x86_64 specific code
+    entries.push(kvm_msr_entry {
+        index: msr_index::MSR_IA32_TSC,
+        data: 0x0,
+        ..Default::default()
+    });
+    entries.push(kvm_msr_entry {
+        index: msr_index::MSR_IA32_MISC_ENABLE,
+        data: msr_index::MSR_IA32_MISC_ENABLE_FAST_STRING as u64,
+        ..Default::default()
+    });
+    entries.push(kvm_msr_entry {
+        index: msr_index::MSR_MTRRdefType,
+        data: MTRR_ENABLE | MTRR_MEM_TYPE_WB,
+        ..Default::default()
+    });
+
+    Msrs::from_entries(&entries)
+}
+
 #[cfg(test)]
 mod tests {
-    use vm_memory::GuestAddress;
+    extern crate kvm_ioctls;
+    extern crate vm_memory;
 
     use super::*;
+    use kvm_ioctls::Kvm;
+    use vm_memory::{GuestAddress, GuestMemoryMmap};
 
     fn create_guest_mem() -> GuestMemoryMmap {
-        GuestMemoryMmap::from_ranges(&[(GuestAddress(0), 0x10000)]).unwrap()
+        GuestMemoryMmap::from_ranges(&vec![(GuestAddress(0), 0x10000)]).unwrap()
     }
 
     fn read_u64(gm: &GuestMemoryMmap, offset: GuestAddress) -> u64 {
@@ -202,12 +278,13 @@ mod tests {
 
     #[test]
     fn segments_and_sregs() {
-        let mut sregs: SpecialRegisters = Default::default();
+        let mut sregs: kvm_sregs = Default::default();
         let gm = create_guest_mem();
         configure_segments_and_sregs(&gm, &mut sregs).unwrap();
+
         assert_eq!(0x0, read_u64(&gm, BOOT_GDT_START));
         assert_eq!(
-            0xcf9b000000ffff,
+            0xaf9b000000ffff,
             read_u64(&gm, BOOT_GDT_START.unchecked_add(8))
         );
         assert_eq!(
@@ -215,23 +292,132 @@ mod tests {
             read_u64(&gm, BOOT_GDT_START.unchecked_add(16))
         );
         assert_eq!(
-            0x8b0000000067,
+            0x8f8b000000ffff,
             read_u64(&gm, BOOT_GDT_START.unchecked_add(24))
         );
         assert_eq!(0x0, read_u64(&gm, BOOT_IDT_START));
 
         assert_eq!(0, sregs.cs.base);
-        assert_eq!(0xffffffff, sregs.ds.limit);
+        assert_eq!(0xfffff, sregs.ds.limit);
         assert_eq!(0x10, sregs.es.selector);
         assert_eq!(1, sregs.fs.present);
         assert_eq!(1, sregs.gs.g);
         assert_eq!(0, sregs.ss.avl);
         assert_eq!(0, sregs.tr.base);
-        assert_eq!(0, sregs.tr.g);
-        assert_eq!(0x67, sregs.tr.limit);
-        assert_eq!(0xb, sregs.tr.type_);
+        assert_eq!(0xfffff, sregs.tr.limit);
         assert_eq!(0, sregs.tr.avl);
-        assert_eq!(CR0_PE, sregs.cr0);
-        assert_eq!(0, sregs.cr4);
+        assert_eq!(X86_CR0_PE, sregs.cr0);
+        assert_eq!(EFER_LME | EFER_LMA, sregs.efer);
+    }
+
+    #[test]
+    fn page_tables() {
+        let mut sregs: kvm_sregs = Default::default();
+        let gm = create_guest_mem();
+        setup_page_tables(&gm, &mut sregs).unwrap();
+
+        assert_eq!(0xa003, read_u64(&gm, PML4_START));
+        assert_eq!(0xb003, read_u64(&gm, PDPTE_START));
+        for i in 0..512 {
+            assert_eq!(
+                (i << 21) + 0x83u64,
+                read_u64(&gm, PDE_START.unchecked_add(i * 8))
+            );
+        }
+
+        assert_eq!(PML4_START.raw_value(), sregs.cr3);
+        assert_eq!(X86_CR4_PAE, sregs.cr4);
+        assert_eq!(X86_CR0_PG, sregs.cr0);
+    }
+
+    #[test]
+    fn test_setup_fpu() {
+        let kvm = Kvm::new().unwrap();
+        let vm = kvm.create_vm().unwrap();
+        let vcpu = vm.create_vcpu(0).unwrap();
+        setup_fpu(&vcpu).unwrap();
+
+        let expected_fpu: kvm_fpu = kvm_fpu {
+            fcw: 0x37f,
+            mxcsr: 0x1f80,
+            ..Default::default()
+        };
+        let actual_fpu: kvm_fpu = vcpu.get_fpu().unwrap();
+        // TODO: auto-generate kvm related structures with PartialEq on.
+        assert_eq!(expected_fpu.fcw, actual_fpu.fcw);
+        // Setting the mxcsr register from kvm_fpu inside setup_fpu does not influence anything.
+        // See 'kvm_arch_vcpu_ioctl_set_fpu' from arch/x86/kvm/x86.c.
+        // The mxcsr will stay 0 and the assert below fails. Decide whether or not we should
+        // remove it at all.
+        // assert!(expected_fpu.mxcsr == actual_fpu.mxcsr);
+    }
+
+    #[test]
+    fn test_setup_msrs() {
+        let kvm = Kvm::new().unwrap();
+        let vm = kvm.create_vm().unwrap();
+        let vcpu = vm.create_vcpu(0).unwrap();
+        setup_msrs(&vcpu).unwrap();
+
+        // This test will check against the last MSR entry configured (the tenth one).
+        // See create_msr_entries for details.
+        let mut msrs = Msrs::from_entries(&[kvm_msr_entry {
+            index: msr_index::MSR_IA32_MISC_ENABLE,
+            ..Default::default()
+        }]);
+
+        // get_msrs returns the number of msrs that it succeed in reading. We only want to read 1
+        // in this test case scenario.
+        let read_msrs = vcpu.get_msrs(&mut msrs).unwrap();
+        assert_eq!(read_msrs, 1);
+
+        // Official entries that were setup when we did setup_msrs. We need to assert that the
+        // tenth one (i.e the one with index msr_index::MSR_IA32_MISC_ENABLE has the data we
+        // expect.
+        let entry_vec = create_msr_entries();
+        assert_eq!(entry_vec.as_slice()[9], msrs.as_slice()[0]);
+    }
+
+    #[test]
+    fn test_setup_regs() {
+        let kvm = Kvm::new().unwrap();
+        let vm = kvm.create_vm().unwrap();
+        let vcpu = vm.create_vcpu(0).unwrap();
+
+        let expected_regs: kvm_regs = kvm_regs {
+            rflags: 0x0000000000000002u64,
+            rip: 1,
+            rsp: 2,
+            rbp: 2,
+            rsi: 3,
+            ..Default::default()
+        };
+
+        setup_regs(
+            &vcpu,
+            expected_regs.rip,
+            expected_regs.rsp,
+            expected_regs.rsi,
+        )
+        .unwrap();
+
+        let actual_regs: kvm_regs = vcpu.get_regs().unwrap();
+        assert_eq!(actual_regs, expected_regs);
+    }
+
+    #[test]
+    fn test_setup_sregs() {
+        let kvm = Kvm::new().unwrap();
+        let vm = kvm.create_vm().unwrap();
+        let vcpu = vm.create_vcpu(0).unwrap();
+
+        let mut expected_sregs: kvm_sregs = vcpu.get_sregs().unwrap();
+        let gm = create_guest_mem();
+        configure_segments_and_sregs(&gm, &mut expected_sregs).unwrap();
+        setup_page_tables(&gm, &mut expected_sregs).unwrap();
+
+        setup_sregs(&gm, &vcpu).unwrap();
+        let actual_sregs: kvm_sregs = vcpu.get_sregs().unwrap();
+        assert_eq!(expected_sregs, actual_sregs);
     }
 }

arch/src/x86_64/smbios.rs

@@ -1,307 +0,0 @@
-// Copyright © 2020 Intel Corporation
-//
-// Copyright 2019 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 std::{mem, result, slice};
-
-use thiserror::Error;
-use uuid::Uuid;
-use vm_memory::{Address, ByteValued, Bytes, GuestAddress};
-
-use crate::layout::SMBIOS_START;
-use crate::GuestMemoryMmap;
-
-#[derive(Debug, Error)]
-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: {0}")]
-    ParseUuid(uuid::Error),
-}
-
-pub type Result<T> = result::Result<T, Error>;
-
-// Constants sourced from SMBIOS Spec 3.2.0.
-const SM3_MAGIC_IDENT: &[u8; 5usize] = b"_SM3_";
-const BIOS_INFORMATION: u8 = 0;
-const SYSTEM_INFORMATION: u8 = 1;
-const OEM_STRINGS: u8 = 11;
-const END_OF_TABLE: u8 = 127;
-const PCI_SUPPORTED: u64 = 1 << 7;
-const IS_VIRTUAL_MACHINE: u8 = 1 << 4;
-
-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;
-    for i in v_slice.iter() {
-        checksum = checksum.wrapping_add(*i);
-    }
-    (!checksum).wrapping_add(1)
-}
-
-#[repr(C)]
-#[repr(packed)]
-#[derive(Default, Copy, Clone)]
-struct Smbios30Entrypoint {
-    signature: [u8; 5usize],
-    checksum: u8,
-    length: u8,
-    majorver: u8,
-    minorver: u8,
-    docrev: u8,
-    revision: u8,
-    reserved: u8,
-    max_size: u32,
-    physptr: u64,
-}
-
-#[repr(C)]
-#[repr(packed)]
-#[derive(Default, Copy, Clone)]
-struct SmbiosBiosInfo {
-    r#type: u8,
-    length: u8,
-    handle: u16,
-    vendor: u8,
-    version: u8,
-    start_addr: u16,
-    release_date: u8,
-    rom_size: u8,
-    characteristics: u64,
-    characteristics_ext1: u8,
-    characteristics_ext2: u8,
-}
-
-#[repr(C)]
-#[repr(packed)]
-#[derive(Default, Copy, Clone)]
-struct SmbiosSysInfo {
-    r#type: u8,
-    length: u8,
-    handle: u16,
-    manufacturer: u8,
-    product_name: u8,
-    version: u8,
-    serial_number: u8,
-    uuid: [u8; 16usize],
-    wake_up_type: u8,
-    sku: u8,
-    family: u8,
-}
-
-#[repr(C)]
-#[repr(packed)]
-#[derive(Default, Copy, Clone)]
-struct SmbiosOemStrings {
-    r#type: u8,
-    length: u8,
-    handle: u16,
-    count: u8,
-}
-
-#[repr(C)]
-#[repr(packed)]
-#[derive(Default, Copy, Clone)]
-struct SmbiosEndOfTable {
-    r#type: u8,
-    length: u8,
-    handle: u16,
-}
-
-// SAFETY: data structure only contain a series of integers
-unsafe impl ByteValued for Smbios30Entrypoint {}
-// SAFETY: data structure only contain a series of integers
-unsafe impl ByteValued for SmbiosBiosInfo {}
-// SAFETY: data structure only contain a series of integers
-unsafe impl ByteValued for SmbiosSysInfo {}
-// SAFETY: data structure only contain a series of integers
-unsafe impl ByteValued for SmbiosOemStrings {}
-// SAFETY: data structure only contain a series of integers
-unsafe impl ByteValued for SmbiosEndOfTable {}
-
-fn write_and_incr<T: ByteValued>(
-    mem: &GuestMemoryMmap,
-    val: T,
-    mut curptr: GuestAddress,
-) -> Result<GuestAddress> {
-    mem.write_obj(val, curptr).map_err(|_| Error::WriteData)?;
-    curptr = curptr
-        .checked_add(mem::size_of::<T>() as u64)
-        .ok_or(Error::NotEnoughMemory)?;
-    Ok(curptr)
-}
-
-fn write_string(
-    mem: &GuestMemoryMmap,
-    val: &str,
-    mut curptr: GuestAddress,
-) -> Result<GuestAddress> {
-    for c in val.as_bytes().iter() {
-        curptr = write_and_incr(mem, *c, curptr)?;
-    }
-    curptr = write_and_incr(mem, 0u8, curptr)?;
-    Ok(curptr)
-}
-
-pub fn setup_smbios(
-    mem: &GuestMemoryMmap,
-    serial_number: Option<&str>,
-    uuid: Option<&str>,
-    oem_strings: Option<&[&str]>,
-) -> Result<u64> {
-    let physptr = GuestAddress(SMBIOS_START)
-        .checked_add(mem::size_of::<Smbios30Entrypoint>() as u64)
-        .ok_or(Error::NotEnoughMemory)?;
-    let mut curptr = physptr;
-    let mut handle = 0;
-
-    {
-        handle += 1;
-        let smbios_biosinfo = SmbiosBiosInfo {
-            r#type: BIOS_INFORMATION,
-            length: mem::size_of::<SmbiosBiosInfo>() as u8,
-            handle,
-            vendor: 1,  // First string written in this section
-            version: 2, // Second string written in this section
-            characteristics: PCI_SUPPORTED,
-            characteristics_ext2: IS_VIRTUAL_MACHINE,
-            ..Default::default()
-        };
-        curptr = write_and_incr(mem, smbios_biosinfo, curptr)?;
-        curptr = write_string(mem, "cloud-hypervisor", curptr)?;
-        curptr = write_string(mem, "0", curptr)?;
-        curptr = write_and_incr(mem, 0u8, curptr)?;
-    }
-
-    {
-        handle += 1;
-
-        let uuid_number = uuid
-            .map(Uuid::parse_str)
-            .transpose()
-            .map_err(Error::ParseUuid)?
-            .unwrap_or(Uuid::nil());
-        let smbios_sysinfo = SmbiosSysInfo {
-            r#type: SYSTEM_INFORMATION,
-            length: mem::size_of::<SmbiosSysInfo>() as u8,
-            handle,
-            manufacturer: 1, // First string written in this section
-            product_name: 2, // Second string written in this section
-            serial_number: serial_number.map(|_| 3).unwrap_or_default(), // 3rd string
-            uuid: uuid_number.to_bytes_le(), // set uuid
-            ..Default::default()
-        };
-        curptr = write_and_incr(mem, smbios_sysinfo, curptr)?;
-        curptr = write_string(mem, "Cloud Hypervisor", curptr)?;
-        curptr = write_string(mem, "cloud-hypervisor", curptr)?;
-        if let Some(serial_number) = serial_number {
-            curptr = write_string(mem, serial_number, curptr)?;
-        }
-        curptr = write_and_incr(mem, 0u8, curptr)?;
-    }
-
-    if let Some(oem_strings) = oem_strings {
-        handle += 1;
-
-        let smbios_oemstrings = SmbiosOemStrings {
-            r#type: OEM_STRINGS,
-            length: mem::size_of::<SmbiosOemStrings>() as u8,
-            handle,
-            count: oem_strings.len() as u8,
-        };
-
-        curptr = write_and_incr(mem, smbios_oemstrings, curptr)?;
-
-        for s in oem_strings {
-            curptr = write_string(mem, s, curptr)?;
-        }
-
-        curptr = write_and_incr(mem, 0u8, curptr)?;
-    }
-
-    {
-        handle += 1;
-        let smbios_end = SmbiosEndOfTable {
-            r#type: END_OF_TABLE,
-            length: mem::size_of::<SmbiosEndOfTable>() as u8,
-            handle,
-        };
-        curptr = write_and_incr(mem, smbios_end, curptr)?;
-        curptr = write_and_incr(mem, 0u8, curptr)?;
-        curptr = write_and_incr(mem, 0u8, curptr)?;
-    }
-
-    {
-        let mut smbios_ep = Smbios30Entrypoint {
-            signature: *SM3_MAGIC_IDENT,
-            length: mem::size_of::<Smbios30Entrypoint>() as u8,
-            // SMBIOS rev 3.2.0
-            majorver: 0x03,
-            minorver: 0x02,
-            docrev: 0x00,
-            revision: 0x01, // SMBIOS 3.0
-            max_size: curptr.unchecked_offset_from(physptr) as u32,
-            physptr: physptr.0,
-            ..Default::default()
-        };
-        smbios_ep.checksum = compute_checksum(&smbios_ep);
-        mem.write_obj(smbios_ep, GuestAddress(SMBIOS_START))
-            .map_err(|_| Error::WriteSmbiosEp)?;
-    }
-
-    Ok(curptr.unchecked_offset_from(physptr) + std::mem::size_of::<Smbios30Entrypoint>() as u64)
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn struct_size() {
-        assert_eq!(
-            mem::size_of::<Smbios30Entrypoint>(),
-            0x18usize,
-            concat!("Size of: ", stringify!(Smbios30Entrypoint))
-        );
-        assert_eq!(
-            mem::size_of::<SmbiosBiosInfo>(),
-            0x14usize,
-            concat!("Size of: ", stringify!(SmbiosBiosInfo))
-        );
-        assert_eq!(
-            mem::size_of::<SmbiosSysInfo>(),
-            0x1busize,
-            concat!("Size of: ", stringify!(SmbiosSysInfo))
-        );
-    }
-
-    #[test]
-    fn entrypoint_checksum() {
-        let mem = GuestMemoryMmap::from_ranges(&[(GuestAddress(SMBIOS_START), 4096)]).unwrap();
-
-        setup_smbios(&mem, None, None, None).unwrap();
-
-        let smbios_ep: Smbios30Entrypoint = mem.read_obj(GuestAddress(SMBIOS_START)).unwrap();
-
-        assert_eq!(compute_checksum(&smbios_ep), 0);
-    }
-}

arch/src/x86_64/tdx/mod.rs

@@ -1,534 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-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: {0}")]
-    ReadDescriptor(#[source] std::io::Error),
-    #[error("Failed read TDVF descriptor offset: {0}")]
-    ReadDescriptorOffset(#[source] std::io::Error),
-    #[error("Failed read GUID table: {0}")]
-    ReadGuidTable(#[source] std::io::Error),
-    #[error("Invalid descriptor signature")]
-    InvalidDescriptorSignature,
-    #[error("Invalid descriptor size")]
-    InvalidDescriptorSize,
-    #[error("Invalid descriptor version")]
-    InvalidDescriptorVersion,
-    #[error("Failed to write HOB details to guest memory: {0}")]
-    GuestMemoryWriteHob(#[source] GuestMemoryError),
-    #[error("Failed to create Uuid: {0}")]
-    UuidCreation(#[source] uuid::Error),
-}
-
-const TABLE_FOOTER_GUID: &str = "96b582de-1fb2-45f7-baea-a366c55a082d";
-const TDVF_METADATA_OFFSET_GUID: &str = "e47a6535-984a-4798-865e-4685a7bf8ec2";
-
-// TDVF_DESCRIPTOR
-#[repr(packed)]
-#[derive(Default)]
-pub struct TdvfDescriptor {
-    signature: [u8; 4],
-    length: u32,
-    version: u32,
-    num_sections: u32, // NumberOfSectionEntry
-}
-
-// TDVF_SECTION
-#[repr(packed)]
-#[derive(Clone, Copy, Default, Debug)]
-pub struct TdvfSection {
-    pub data_offset: u32,
-    pub data_size: u32, // RawDataSize
-    pub address: u64,   // MemoryAddress
-    pub size: u64,      // MemoryDataSize
-    pub r#type: TdvfSectionType,
-    pub attributes: u32,
-}
-
-#[repr(u32)]
-#[derive(Clone, Copy, Debug, Default)]
-pub enum TdvfSectionType {
-    Bfv,
-    Cfv,
-    TdHob,
-    TempMem,
-    PermMem,
-    Payload,
-    PayloadParam,
-    #[default]
-    Reserved = 0xffffffff,
-}
-
-fn tdvf_descriptor_offset(file: &mut File) -> Result<(SeekFrom, bool), TdvfError> {
-    // Let's first try to identify the presence of the table footer GUID
-    file.seek(SeekFrom::End(-0x30))
-        .map_err(TdvfError::ReadGuidTable)?;
-    let mut table_footer_guid: [u8; 16] = [0; 16];
-    file.read_exact(&mut table_footer_guid)
-        .map_err(TdvfError::ReadGuidTable)?;
-    let uuid =
-        Uuid::from_slice_le(table_footer_guid.as_slice()).map_err(TdvfError::UuidCreation)?;
-    let expected_uuid = Uuid::from_str(TABLE_FOOTER_GUID).map_err(TdvfError::UuidCreation)?;
-    if uuid == expected_uuid {
-        // Retrieve the table size
-        file.seek(SeekFrom::End(-0x32))
-            .map_err(TdvfError::ReadGuidTable)?;
-        let mut table_size: [u8; 2] = [0; 2];
-        file.read_exact(&mut table_size)
-            .map_err(TdvfError::ReadGuidTable)?;
-        let table_size = u16::from_le_bytes(table_size) as usize;
-        let mut table: Vec<u8> = vec![0; table_size];
-
-        // Read the entire table
-        file.seek(SeekFrom::End(-(table_size as i64 + 0x20)))
-            .map_err(TdvfError::ReadGuidTable)?;
-        file.read_exact(table.as_mut_slice())
-            .map_err(TdvfError::ReadGuidTable)?;
-
-        // Let's start from the top and go backward down the table.
-        // We start after the footer GUID and the table length.
-        let mut offset = table_size - 18;
-
-        debug!("Parsing GUID structure");
-        while offset >= 18 {
-            let entry_uuid = Uuid::from_slice_le(&table[offset - 16..offset])
-                .map_err(TdvfError::UuidCreation)?;
-            let entry_size =
-                u16::from_le_bytes(table[offset - 18..offset - 16].try_into().unwrap()) as usize;
-            debug!(
-                "Entry GUID = {}, size = {}",
-                entry_uuid.hyphenated().to_string(),
-                entry_size
-            );
-
-            // Avoid going through an infinite loop if the entry size is 0
-            if entry_size == 0 {
-                break;
-            }
-
-            offset -= entry_size;
-
-            let expected_uuid =
-                Uuid::from_str(TDVF_METADATA_OFFSET_GUID).map_err(TdvfError::UuidCreation)?;
-            if entry_uuid == expected_uuid && entry_size == 22 {
-                return Ok((
-                    SeekFrom::End(
-                        -(u32::from_le_bytes(table[offset..offset + 4].try_into().unwrap()) as i64),
-                    ),
-                    true,
-                ));
-            }
-        }
-    }
-
-    // If we end up here, this means the firmware doesn't support the new way
-    // of exposing the TDVF descriptor offset through the table of GUIDs.
-    // That's why we fallback onto the deprecated method.
-
-    // The 32-bit offset to the TDVF metadata is located 32 bytes from
-    // the end of the file.
-    // See "TDVF Metadata Pointer" in "TDX Virtual Firmware Design Guide
-    file.seek(SeekFrom::End(-0x20))
-        .map_err(TdvfError::ReadDescriptorOffset)?;
-
-    let mut descriptor_offset: [u8; 4] = [0; 4];
-    file.read_exact(&mut descriptor_offset)
-        .map_err(TdvfError::ReadDescriptorOffset)?;
-
-    Ok((
-        SeekFrom::Start(u32::from_le_bytes(descriptor_offset) as u64),
-        false,
-    ))
-}
-
-pub fn parse_tdvf_sections(file: &mut File) -> Result<(Vec<TdvfSection>, bool), TdvfError> {
-    let (descriptor_offset, guid_found) = tdvf_descriptor_offset(file)?;
-
-    file.seek(descriptor_offset)
-        .map_err(TdvfError::ReadDescriptor)?;
-
-    let mut descriptor: TdvfDescriptor = Default::default();
-    // SAFETY: we read exactly the size of the descriptor header
-    file.read_exact(unsafe {
-        std::slice::from_raw_parts_mut(
-            &mut descriptor as *mut _ as *mut u8,
-            std::mem::size_of::<TdvfDescriptor>(),
-        )
-    })
-    .map_err(TdvfError::ReadDescriptor)?;
-
-    if &descriptor.signature != b"TDVF" {
-        return Err(TdvfError::InvalidDescriptorSignature);
-    }
-
-    if descriptor.length as usize
-        != std::mem::size_of::<TdvfDescriptor>()
-            + std::mem::size_of::<TdvfSection>() * descriptor.num_sections as usize
-    {
-        return Err(TdvfError::InvalidDescriptorSize);
-    }
-
-    if descriptor.version != 1 {
-        return Err(TdvfError::InvalidDescriptorVersion);
-    }
-
-    let mut sections = Vec::new();
-    sections.resize_with(descriptor.num_sections as usize, TdvfSection::default);
-
-    // SAFETY: we read exactly the advertised sections
-    file.read_exact(unsafe {
-        std::slice::from_raw_parts_mut(
-            sections.as_mut_ptr() as *mut u8,
-            descriptor.num_sections as usize * std::mem::size_of::<TdvfSection>(),
-        )
-    })
-    .map_err(TdvfError::ReadDescriptor)?;
-
-    Ok((sections, guid_found))
-}
-
-#[repr(u16)]
-#[derive(Copy, Clone, Debug, Default)]
-enum HobType {
-    Handoff = 0x1,
-    ResourceDescriptor = 0x3,
-    GuidExtension = 0x4,
-    #[default]
-    Unused = 0xfffe,
-    EndOfHobList = 0xffff,
-}
-
-#[repr(C)]
-#[derive(Copy, Clone, Default, Debug)]
-struct HobHeader {
-    r#type: HobType,
-    length: u16,
-    reserved: u32,
-}
-
-#[repr(C)]
-#[derive(Copy, Clone, Default, Debug)]
-struct HobHandoffInfoTable {
-    header: HobHeader,
-    version: u32,
-    boot_mode: u32,
-    efi_memory_top: u64,
-    efi_memory_bottom: u64,
-    efi_free_memory_top: u64,
-    efi_free_memory_bottom: u64,
-    efi_end_of_hob_list: u64,
-}
-
-#[repr(C)]
-#[derive(Copy, Clone, Default, Debug)]
-struct EfiGuid {
-    data1: u32,
-    data2: u16,
-    data3: u16,
-    data4: [u8; 8],
-}
-
-#[repr(C)]
-#[derive(Copy, Clone, Default, Debug)]
-struct HobResourceDescriptor {
-    header: HobHeader,
-    owner: EfiGuid,
-    resource_type: u32,
-    resource_attribute: u32,
-    physical_start: u64,
-    resource_length: u64,
-}
-
-#[repr(C)]
-#[derive(Copy, Clone, Default, Debug)]
-struct HobGuidType {
-    header: HobHeader,
-    name: EfiGuid,
-}
-
-#[repr(u32)]
-#[derive(Clone, Copy, Debug, Default)]
-pub enum PayloadImageType {
-    #[default]
-    ExecutablePayload,
-    BzImage,
-    RawVmLinux,
-}
-
-#[repr(C)]
-#[derive(Copy, Clone, Default, Debug)]
-pub struct PayloadInfo {
-    pub image_type: PayloadImageType,
-    pub entry_point: u64,
-}
-
-#[repr(C)]
-#[derive(Copy, Clone, Default, Debug)]
-struct TdPayload {
-    guid_type: HobGuidType,
-    payload_info: PayloadInfo,
-}
-
-// SAFETY: data structure only contain a series of integers
-unsafe impl ByteValued for HobHeader {}
-// SAFETY: data structure only contain a series of integers
-unsafe impl ByteValued for HobHandoffInfoTable {}
-// SAFETY: data structure only contain a series of integers
-unsafe impl ByteValued for HobResourceDescriptor {}
-// SAFETY: data structure only contain a series of integers
-unsafe impl ByteValued for HobGuidType {}
-// SAFETY: data structure only contain a series of integers
-unsafe impl ByteValued for PayloadInfo {}
-// SAFETY: data structure only contain a series of integers
-unsafe impl ByteValued for TdPayload {}
-
-pub struct TdHob {
-    start_offset: u64,
-    current_offset: u64,
-}
-
-fn align_hob(v: u64) -> u64 {
-    (v + 7) / 8 * 8
-}
-
-impl TdHob {
-    fn update_offset<T>(&mut self) {
-        self.current_offset = align_hob(self.current_offset + std::mem::size_of::<T>() as u64)
-    }
-
-    pub fn start(offset: u64) -> TdHob {
-        // Leave a gap to place the HandoffTable at the start as it can only be filled in later
-        let mut hob = TdHob {
-            start_offset: offset,
-            current_offset: offset,
-        };
-        hob.update_offset::<HobHandoffInfoTable>();
-        hob
-    }
-
-    pub fn finish(&mut self, mem: &GuestMemoryMmap) -> Result<(), TdvfError> {
-        // Write end
-        let end = HobHeader {
-            r#type: HobType::EndOfHobList,
-            length: std::mem::size_of::<HobHeader>() as u16,
-            reserved: 0,
-        };
-        info!("Writing HOB end {:x} {:x?}", self.current_offset, end);
-        mem.write_obj(end, GuestAddress(self.current_offset))
-            .map_err(TdvfError::GuestMemoryWriteHob)?;
-        self.update_offset::<HobHeader>();
-
-        // Write handoff, delayed as it needs end of HOB list
-        let efi_end_of_hob_list = self.current_offset;
-        let handoff = HobHandoffInfoTable {
-            header: HobHeader {
-                r#type: HobType::Handoff,
-                length: std::mem::size_of::<HobHandoffInfoTable>() as u16,
-                reserved: 0,
-            },
-            version: 0x9,
-            boot_mode: 0,
-            efi_memory_top: 0,
-            efi_memory_bottom: 0,
-            efi_free_memory_top: 0,
-            efi_free_memory_bottom: 0,
-            efi_end_of_hob_list,
-        };
-        info!("Writing HOB start {:x} {:x?}", self.start_offset, handoff);
-        mem.write_obj(handoff, GuestAddress(self.start_offset))
-            .map_err(TdvfError::GuestMemoryWriteHob)
-    }
-
-    pub fn add_resource(
-        &mut self,
-        mem: &GuestMemoryMmap,
-        physical_start: u64,
-        resource_length: u64,
-        resource_type: u32,
-        resource_attribute: u32,
-    ) -> Result<(), TdvfError> {
-        let resource_descriptor = HobResourceDescriptor {
-            header: HobHeader {
-                r#type: HobType::ResourceDescriptor,
-                length: std::mem::size_of::<HobResourceDescriptor>() as u16,
-                reserved: 0,
-            },
-            owner: EfiGuid::default(),
-            resource_type,
-            resource_attribute,
-            physical_start,
-            resource_length,
-        };
-        info!(
-            "Writing HOB resource {:x} {:x?}",
-            self.current_offset, resource_descriptor
-        );
-        mem.write_obj(resource_descriptor, GuestAddress(self.current_offset))
-            .map_err(TdvfError::GuestMemoryWriteHob)?;
-        self.update_offset::<HobResourceDescriptor>();
-        Ok(())
-    }
-
-    pub fn add_memory_resource(
-        &mut self,
-        mem: &GuestMemoryMmap,
-        physical_start: u64,
-        resource_length: u64,
-        ram: bool,
-        guid_found: bool,
-    ) -> Result<(), TdvfError> {
-        self.add_resource(
-            mem,
-            physical_start,
-            resource_length,
-            if ram {
-                if guid_found {
-                    0x7 /* EFI_RESOURCE_MEMORY_UNACCEPTED */
-                } else {
-                    0 /* EFI_RESOURCE_SYSTEM_MEMORY */
-                }
-            } else if guid_found {
-                0 /* EFI_RESOURCE_SYSTEM_MEMORY */
-            } else {
-                0x5 /*EFI_RESOURCE_MEMORY_RESERVED */
-            },
-            /* TODO:
-             * QEMU currently fills it in like this:
-             * EFI_RESOURCE_ATTRIBUTE_PRESENT | EFI_RESOURCE_ATTRIBUTE_INITIALIZED | EFI_RESOURCE_ATTRIBUTE_TESTED
-             * which differs from the spec (due to TDVF implementation issue?)
-             */
-            0x7,
-        )
-    }
-
-    pub fn add_mmio_resource(
-        &mut self,
-        mem: &GuestMemoryMmap,
-        physical_start: u64,
-        resource_length: u64,
-    ) -> Result<(), TdvfError> {
-        self.add_resource(
-            mem,
-            physical_start,
-            resource_length,
-            0x1, /* EFI_RESOURCE_MEMORY_MAPPED_IO */
-            /*
-             * EFI_RESOURCE_ATTRIBUTE_PRESENT | EFI_RESOURCE_ATTRIBUTE_INITIALIZED | EFI_RESOURCE_ATTRIBUTE_UNCACHEABLE
-             */
-            0x403,
-        )
-    }
-
-    pub fn add_acpi_table(
-        &mut self,
-        mem: &GuestMemoryMmap,
-        table_content: &[u8],
-    ) -> Result<(), TdvfError> {
-        // We already know the HobGuidType size is 8 bytes multiple, but we
-        // need the total size to be 8 bytes multiple. That is why the ACPI
-        // table size must be 8 bytes multiple as well.
-        let length = std::mem::size_of::<HobGuidType>() as u16
-            + align_hob(table_content.len() as u64) as u16;
-        let hob_guid_type = HobGuidType {
-            header: HobHeader {
-                r#type: HobType::GuidExtension,
-                length,
-                reserved: 0,
-            },
-            // ACPI_TABLE_HOB_GUID
-            // 0x6a0c5870, 0xd4ed, 0x44f4, {0xa1, 0x35, 0xdd, 0x23, 0x8b, 0x6f, 0xc, 0x8d }
-            name: EfiGuid {
-                data1: 0x6a0c_5870,
-                data2: 0xd4ed,
-                data3: 0x44f4,
-                data4: [0xa1, 0x35, 0xdd, 0x23, 0x8b, 0x6f, 0xc, 0x8d],
-            },
-        };
-        info!(
-            "Writing HOB ACPI table {:x} {:x?} {:x?}",
-            self.current_offset, hob_guid_type, table_content
-        );
-        mem.write_obj(hob_guid_type, GuestAddress(self.current_offset))
-            .map_err(TdvfError::GuestMemoryWriteHob)?;
-        let current_offset = self.current_offset + std::mem::size_of::<HobGuidType>() as u64;
-
-        // In case the table is quite large, let's make sure we can handle
-        // retrying until everything has been correctly copied.
-        let mut offset: usize = 0;
-        loop {
-            let bytes_written = mem
-                .write(
-                    &table_content[offset..],
-                    GuestAddress(current_offset + offset as u64),
-                )
-                .map_err(TdvfError::GuestMemoryWriteHob)?;
-            offset += bytes_written;
-            if offset >= table_content.len() {
-                break;
-            }
-        }
-        self.current_offset += length as u64;
-
-        Ok(())
-    }
-
-    pub fn add_payload(
-        &mut self,
-        mem: &GuestMemoryMmap,
-        payload_info: PayloadInfo,
-    ) -> Result<(), TdvfError> {
-        let payload = TdPayload {
-            guid_type: HobGuidType {
-                header: HobHeader {
-                    r#type: HobType::GuidExtension,
-                    length: std::mem::size_of::<TdPayload>() as u16,
-                    reserved: 0,
-                },
-                // HOB_PAYLOAD_INFO_GUID
-                // 0xb96fa412, 0x461f, 0x4be3, {0x8c, 0xd, 0xad, 0x80, 0x5a, 0x49, 0x7a, 0xc0
-                name: EfiGuid {
-                    data1: 0xb96f_a412,
-                    data2: 0x461f,
-                    data3: 0x4be3,
-                    data4: [0x8c, 0xd, 0xad, 0x80, 0x5a, 0x49, 0x7a, 0xc0],
-                },
-            },
-            payload_info,
-        };
-        info!(
-            "Writing HOB TD_PAYLOAD {:x} {:x?}",
-            self.current_offset, payload
-        );
-        mem.write_obj(payload, GuestAddress(self.current_offset))
-            .map_err(TdvfError::GuestMemoryWriteHob)?;
-        self.update_offset::<TdPayload>();
-
-        Ok(())
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    #[ignore]
-    fn test_parse_tdvf_sections() {
-        let mut f = std::fs::File::open("tdvf.fd").unwrap();
-        let (sections, _) = parse_tdvf_sections(&mut f).unwrap();
-        for section in sections {
-            eprintln!("{section:x?}")
-        }
-    }
-}

arch_gen/Cargo.lock

@@ -0,0 +1,6 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+[[package]]
+name = "arch_gen"
+version = "0.1.0"
+

arch_gen/Cargo.toml

@@ -0,0 +1,7 @@
+[package]
+name = "arch_gen"
+version = "0.1.0"
+authors = ["Amazon firecracker team <firecracker-devel@amazon.com>"]
+
+[dependencies]
+

arch_gen/src/lib.rs

@@ -0,0 +1,5 @@
+// Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+// SPDX-License-Identifier: Apache-2.0
+
+#[cfg(any(target_arch = "x86", target_arch = "x86_64"))]
+pub mod x86;

arch_gen/src/x86/mod.rs

@@ -0,0 +1,25 @@
+// Copyright 2018 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 LICENSE-BSD-3-Clause file.
+
+#[allow(non_upper_case_globals)]
+#[allow(non_camel_case_types)]
+#[allow(non_snake_case)]
+#[allow(
+    clippy::unreadable_literal,
+    clippy::redundant_static_lifetimes,
+    clippy::trivially_copy_pass_by_ref,
+    clippy::useless_transmute,
+    clippy::should_implement_trait,
+    clippy::transmute_ptr_to_ptr
+)]
+#[allow(non_camel_case_types)]
+#[allow(non_upper_case_globals)]
+#[allow(clippy::unreadable_literal, clippy::redundant_static_lifetimes)]
+pub mod mpspec;
+#[allow(non_upper_case_globals)]
+#[allow(clippy::unreadable_literal, clippy::redundant_static_lifetimes)]
+pub mod msr_index;

arch_gen/src/x86/mpspec.rs

@@ -0,0 +1,832 @@
+// 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.
+
+/* automatically generated by rust-bindgen */
+
+pub const MPC_SIGNATURE: &'static [u8; 5usize] = b"PCMP\x00";
+pub const MP_PROCESSOR: ::std::os::raw::c_uint = 0;
+pub const MP_BUS: ::std::os::raw::c_uint = 1;
+pub const MP_IOAPIC: ::std::os::raw::c_uint = 2;
+pub const MP_INTSRC: ::std::os::raw::c_uint = 3;
+pub const MP_LINTSRC: ::std::os::raw::c_uint = 4;
+pub const MP_TRANSLATION: ::std::os::raw::c_uint = 192;
+pub const CPU_ENABLED: ::std::os::raw::c_uint = 1;
+pub const CPU_BOOTPROCESSOR: ::std::os::raw::c_uint = 2;
+pub const CPU_STEPPING_MASK: ::std::os::raw::c_uint = 15;
+pub const CPU_MODEL_MASK: ::std::os::raw::c_uint = 240;
+pub const CPU_FAMILY_MASK: ::std::os::raw::c_uint = 3840;
+pub const BUSTYPE_EISA: &'static [u8; 5usize] = b"EISA\x00";
+pub const BUSTYPE_ISA: &'static [u8; 4usize] = b"ISA\x00";
+pub const BUSTYPE_INTERN: &'static [u8; 7usize] = b"INTERN\x00";
+pub const BUSTYPE_MCA: &'static [u8; 4usize] = b"MCA\x00";
+pub const BUSTYPE_VL: &'static [u8; 3usize] = b"VL\x00";
+pub const BUSTYPE_PCI: &'static [u8; 4usize] = b"PCI\x00";
+pub const BUSTYPE_PCMCIA: &'static [u8; 7usize] = b"PCMCIA\x00";
+pub const BUSTYPE_CBUS: &'static [u8; 5usize] = b"CBUS\x00";
+pub const BUSTYPE_CBUSII: &'static [u8; 7usize] = b"CBUSII\x00";
+pub const BUSTYPE_FUTURE: &'static [u8; 7usize] = b"FUTURE\x00";
+pub const BUSTYPE_MBI: &'static [u8; 4usize] = b"MBI\x00";
+pub const BUSTYPE_MBII: &'static [u8; 5usize] = b"MBII\x00";
+pub const BUSTYPE_MPI: &'static [u8; 4usize] = b"MPI\x00";
+pub const BUSTYPE_MPSA: &'static [u8; 5usize] = b"MPSA\x00";
+pub const BUSTYPE_NUBUS: &'static [u8; 6usize] = b"NUBUS\x00";
+pub const BUSTYPE_TC: &'static [u8; 3usize] = b"TC\x00";
+pub const BUSTYPE_VME: &'static [u8; 4usize] = b"VME\x00";
+pub const BUSTYPE_XPRESS: &'static [u8; 7usize] = b"XPRESS\x00";
+pub const MPC_APIC_USABLE: ::std::os::raw::c_uint = 1;
+pub const MP_IRQDIR_DEFAULT: ::std::os::raw::c_uint = 0;
+pub const MP_IRQDIR_HIGH: ::std::os::raw::c_uint = 1;
+pub const MP_IRQDIR_LOW: ::std::os::raw::c_uint = 3;
+pub const MP_APIC_ALL: ::std::os::raw::c_uint = 255;
+pub const MPC_OEM_SIGNATURE: &'static [u8; 5usize] = b"_OEM\x00";
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpf_intel {
+    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,
+    pub checksum: ::std::os::raw::c_uchar,
+    pub feature1: ::std::os::raw::c_uchar,
+    pub feature2: ::std::os::raw::c_uchar,
+    pub feature3: ::std::os::raw::c_uchar,
+    pub feature4: ::std::os::raw::c_uchar,
+    pub feature5: ::std::os::raw::c_uchar,
+}
+#[test]
+fn bindgen_test_layout_mpf_intel() {
+    assert_eq!(
+        ::std::mem::size_of::<mpf_intel>(),
+        16usize,
+        concat!("Size of: ", stringify!(mpf_intel))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpf_intel>(),
+        4usize,
+        concat!("Alignment of ", stringify!(mpf_intel))
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpf_intel)).signature as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(signature)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpf_intel)).physptr as *const _ as usize },
+        4usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(physptr)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpf_intel)).length as *const _ as usize },
+        8usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(length)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpf_intel)).specification as *const _ as usize },
+        9usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(specification)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpf_intel)).checksum as *const _ as usize },
+        10usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(checksum)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpf_intel)).feature1 as *const _ as usize },
+        11usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(feature1)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpf_intel)).feature2 as *const _ as usize },
+        12usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(feature2)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpf_intel)).feature3 as *const _ as usize },
+        13usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(feature3)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpf_intel)).feature4 as *const _ as usize },
+        14usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(feature4)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpf_intel)).feature5 as *const _ as usize },
+        15usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(feature5)
+        )
+    );
+}
+impl Clone for mpf_intel {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpc_table {
+    pub signature: [::std::os::raw::c_char; 4usize],
+    pub length: ::std::os::raw::c_ushort,
+    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,
+    pub lapic: ::std::os::raw::c_uint,
+    pub reserved: ::std::os::raw::c_uint,
+}
+#[test]
+fn bindgen_test_layout_mpc_table() {
+    assert_eq!(
+        ::std::mem::size_of::<mpc_table>(),
+        44usize,
+        concat!("Size of: ", stringify!(mpc_table))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpc_table>(),
+        4usize,
+        concat!("Alignment of ", stringify!(mpc_table))
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_table)).signature as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(signature)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_table)).length as *const _ as usize },
+        4usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(length)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_table)).spec as *const _ as usize },
+        6usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(spec)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_table)).checksum as *const _ as usize },
+        7usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(checksum)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_table)).oem as *const _ as usize },
+        8usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(oem)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_table)).productid as *const _ as usize },
+        16usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(productid)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_table)).oemptr as *const _ as usize },
+        28usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(oemptr)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_table)).oemsize as *const _ as usize },
+        32usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(oemsize)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_table)).oemcount as *const _ as usize },
+        34usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(oemcount)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_table)).lapic as *const _ as usize },
+        36usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(lapic)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_table)).reserved as *const _ as usize },
+        40usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(reserved)
+        )
+    );
+}
+impl Clone for mpc_table {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpc_cpu {
+    pub type_: ::std::os::raw::c_uchar,
+    pub apicid: ::std::os::raw::c_uchar,
+    pub apicver: ::std::os::raw::c_uchar,
+    pub cpuflag: ::std::os::raw::c_uchar,
+    pub cpufeature: ::std::os::raw::c_uint,
+    pub featureflag: ::std::os::raw::c_uint,
+    pub reserved: [::std::os::raw::c_uint; 2usize],
+}
+#[test]
+fn bindgen_test_layout_mpc_cpu() {
+    assert_eq!(
+        ::std::mem::size_of::<mpc_cpu>(),
+        20usize,
+        concat!("Size of: ", stringify!(mpc_cpu))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpc_cpu>(),
+        4usize,
+        concat!("Alignment of ", stringify!(mpc_cpu))
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_cpu)).type_ as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_cpu),
+            "::",
+            stringify!(type_)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_cpu)).apicid as *const _ as usize },
+        1usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_cpu),
+            "::",
+            stringify!(apicid)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_cpu)).apicver as *const _ as usize },
+        2usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_cpu),
+            "::",
+            stringify!(apicver)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_cpu)).cpuflag as *const _ as usize },
+        3usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_cpu),
+            "::",
+            stringify!(cpuflag)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_cpu)).cpufeature as *const _ as usize },
+        4usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_cpu),
+            "::",
+            stringify!(cpufeature)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_cpu)).featureflag as *const _ as usize },
+        8usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_cpu),
+            "::",
+            stringify!(featureflag)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_cpu)).reserved as *const _ as usize },
+        12usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_cpu),
+            "::",
+            stringify!(reserved)
+        )
+    );
+}
+impl Clone for mpc_cpu {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpc_bus {
+    pub type_: ::std::os::raw::c_uchar,
+    pub busid: ::std::os::raw::c_uchar,
+    pub bustype: [::std::os::raw::c_uchar; 6usize],
+}
+#[test]
+fn bindgen_test_layout_mpc_bus() {
+    assert_eq!(
+        ::std::mem::size_of::<mpc_bus>(),
+        8usize,
+        concat!("Size of: ", stringify!(mpc_bus))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpc_bus>(),
+        1usize,
+        concat!("Alignment of ", stringify!(mpc_bus))
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_bus)).type_ as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_bus),
+            "::",
+            stringify!(type_)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_bus)).busid as *const _ as usize },
+        1usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_bus),
+            "::",
+            stringify!(busid)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_bus)).bustype as *const _ as usize },
+        2usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_bus),
+            "::",
+            stringify!(bustype)
+        )
+    );
+}
+impl Clone for mpc_bus {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpc_ioapic {
+    pub type_: ::std::os::raw::c_uchar,
+    pub apicid: ::std::os::raw::c_uchar,
+    pub apicver: ::std::os::raw::c_uchar,
+    pub flags: ::std::os::raw::c_uchar,
+    pub apicaddr: ::std::os::raw::c_uint,
+}
+#[test]
+fn bindgen_test_layout_mpc_ioapic() {
+    assert_eq!(
+        ::std::mem::size_of::<mpc_ioapic>(),
+        8usize,
+        concat!("Size of: ", stringify!(mpc_ioapic))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpc_ioapic>(),
+        4usize,
+        concat!("Alignment of ", stringify!(mpc_ioapic))
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_ioapic)).type_ as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_ioapic),
+            "::",
+            stringify!(type_)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_ioapic)).apicid as *const _ as usize },
+        1usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_ioapic),
+            "::",
+            stringify!(apicid)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_ioapic)).apicver as *const _ as usize },
+        2usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_ioapic),
+            "::",
+            stringify!(apicver)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_ioapic)).flags as *const _ as usize },
+        3usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_ioapic),
+            "::",
+            stringify!(flags)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_ioapic)).apicaddr as *const _ as usize },
+        4usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_ioapic),
+            "::",
+            stringify!(apicaddr)
+        )
+    );
+}
+impl Clone for mpc_ioapic {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpc_intsrc {
+    pub type_: ::std::os::raw::c_uchar,
+    pub irqtype: ::std::os::raw::c_uchar,
+    pub irqflag: ::std::os::raw::c_ushort,
+    pub srcbus: ::std::os::raw::c_uchar,
+    pub srcbusirq: ::std::os::raw::c_uchar,
+    pub dstapic: ::std::os::raw::c_uchar,
+    pub dstirq: ::std::os::raw::c_uchar,
+}
+#[test]
+fn bindgen_test_layout_mpc_intsrc() {
+    assert_eq!(
+        ::std::mem::size_of::<mpc_intsrc>(),
+        8usize,
+        concat!("Size of: ", stringify!(mpc_intsrc))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpc_intsrc>(),
+        2usize,
+        concat!("Alignment of ", stringify!(mpc_intsrc))
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_intsrc)).type_ as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_intsrc),
+            "::",
+            stringify!(type_)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_intsrc)).irqtype as *const _ as usize },
+        1usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_intsrc),
+            "::",
+            stringify!(irqtype)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_intsrc)).irqflag as *const _ as usize },
+        2usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_intsrc),
+            "::",
+            stringify!(irqflag)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_intsrc)).srcbus as *const _ as usize },
+        4usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_intsrc),
+            "::",
+            stringify!(srcbus)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_intsrc)).srcbusirq as *const _ as usize },
+        5usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_intsrc),
+            "::",
+            stringify!(srcbusirq)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_intsrc)).dstapic as *const _ as usize },
+        6usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_intsrc),
+            "::",
+            stringify!(dstapic)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_intsrc)).dstirq as *const _ as usize },
+        7usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_intsrc),
+            "::",
+            stringify!(dstirq)
+        )
+    );
+}
+impl Clone for mpc_intsrc {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+pub const mp_irq_source_types_mp_INT: mp_irq_source_types = 0;
+pub const mp_irq_source_types_mp_NMI: mp_irq_source_types = 1;
+pub const mp_irq_source_types_mp_SMI: mp_irq_source_types = 2;
+pub const mp_irq_source_types_mp_ExtINT: mp_irq_source_types = 3;
+pub type mp_irq_source_types = ::std::os::raw::c_uint;
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpc_lintsrc {
+    pub type_: ::std::os::raw::c_uchar,
+    pub irqtype: ::std::os::raw::c_uchar,
+    pub irqflag: ::std::os::raw::c_ushort,
+    pub srcbusid: ::std::os::raw::c_uchar,
+    pub srcbusirq: ::std::os::raw::c_uchar,
+    pub destapic: ::std::os::raw::c_uchar,
+    pub destapiclint: ::std::os::raw::c_uchar,
+}
+#[test]
+fn bindgen_test_layout_mpc_lintsrc() {
+    assert_eq!(
+        ::std::mem::size_of::<mpc_lintsrc>(),
+        8usize,
+        concat!("Size of: ", stringify!(mpc_lintsrc))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpc_lintsrc>(),
+        2usize,
+        concat!("Alignment of ", stringify!(mpc_lintsrc))
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_lintsrc)).type_ as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_lintsrc),
+            "::",
+            stringify!(type_)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_lintsrc)).irqtype as *const _ as usize },
+        1usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_lintsrc),
+            "::",
+            stringify!(irqtype)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_lintsrc)).irqflag as *const _ as usize },
+        2usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_lintsrc),
+            "::",
+            stringify!(irqflag)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_lintsrc)).srcbusid as *const _ as usize },
+        4usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_lintsrc),
+            "::",
+            stringify!(srcbusid)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_lintsrc)).srcbusirq as *const _ as usize },
+        5usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_lintsrc),
+            "::",
+            stringify!(srcbusirq)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_lintsrc)).destapic as *const _ as usize },
+        6usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_lintsrc),
+            "::",
+            stringify!(destapic)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_lintsrc)).destapiclint as *const _ as usize },
+        7usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_lintsrc),
+            "::",
+            stringify!(destapiclint)
+        )
+    );
+}
+impl Clone for mpc_lintsrc {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpc_oemtable {
+    pub signature: [::std::os::raw::c_char; 4usize],
+    pub length: ::std::os::raw::c_ushort,
+    pub rev: ::std::os::raw::c_char,
+    pub checksum: ::std::os::raw::c_char,
+    pub mpc: [::std::os::raw::c_char; 8usize],
+}
+#[test]
+fn bindgen_test_layout_mpc_oemtable() {
+    assert_eq!(
+        ::std::mem::size_of::<mpc_oemtable>(),
+        16usize,
+        concat!("Size of: ", stringify!(mpc_oemtable))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpc_oemtable>(),
+        2usize,
+        concat!("Alignment of ", stringify!(mpc_oemtable))
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_oemtable)).signature as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_oemtable),
+            "::",
+            stringify!(signature)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_oemtable)).length as *const _ as usize },
+        4usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_oemtable),
+            "::",
+            stringify!(length)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_oemtable)).rev as *const _ as usize },
+        6usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_oemtable),
+            "::",
+            stringify!(rev)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_oemtable)).checksum as *const _ as usize },
+        7usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_oemtable),
+            "::",
+            stringify!(checksum)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*(0 as *const mpc_oemtable)).mpc as *const _ as usize },
+        8usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_oemtable),
+            "::",
+            stringify!(mpc)
+        )
+    );
+}
+impl Clone for mpc_oemtable {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+pub const mp_bustype_MP_BUS_ISA: mp_bustype = 1;
+pub const mp_bustype_MP_BUS_EISA: mp_bustype = 2;
+pub const mp_bustype_MP_BUS_PCI: mp_bustype = 3;
+pub type mp_bustype = ::std::os::raw::c_uint;

arch_gen/src/x86/msr_index.rs

@@ -1,6 +1,4 @@
 // 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.
 

block/Cargo.toml

@@ -1,30 +0,0 @@
-[package]
-authors = ["The Chromium OS Authors", "The Cloud Hypervisor Authors"]
-edition = "2021"
-name = "block"
-version = "0.1.0"
-
-[features]
-default = []
-io_uring = ["dep:io-uring"]
-
-[dependencies]
-byteorder = "1.5.0"
-crc-any = "2.4.4"
-io-uring = { version = "0.6.4", optional = true }
-libc = "0.2.158"
-log = "0.4.22"
-remain = "0.2.14"
-serde = { version = "1.0.208", features = ["derive"] }
-smallvec = "1.13.2"
-thiserror = "1.0.62"
-uuid = { version = "1.8.0", features = ["v4"] }
-virtio-bindings = { workspace = true, features = ["virtio-v5_0_0"] }
-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

@@ -1,61 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
-
-use thiserror::Error;
-use vmm_sys_util::eventfd::EventFd;
-
-use crate::DiskTopology;
-
-#[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),
-}
-
-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/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::vhd::VhdFooter;
-use crate::BlockBackend;
-
-#[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/fixed_vhd_async.rs

@@ -1,105 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-
-use std::fs::File;
-use std::os::unix::io::{AsRawFd, RawFd};
-
-use vmm_sys_util::eventfd::EventFd;
-
-use crate::async_io::{
-    AsyncIo, AsyncIoError, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult,
-};
-use crate::fixed_vhd::FixedVhd;
-use crate::raw_async::RawFileAsync;
-use crate::BlockBackend;
-
-pub struct FixedVhdDiskAsync(FixedVhd);
-
-impl FixedVhdDiskAsync {
-    pub fn new(file: File) -> std::io::Result<Self> {
-        Ok(Self(FixedVhd::new(file)?))
-    }
-}
-
-impl DiskFile for FixedVhdDiskAsync {
-    fn size(&mut self) -> DiskFileResult<u64> {
-        Ok(self.0.size().unwrap())
-    }
-
-    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())
-                .map_err(DiskFileError::NewAsyncIo)?,
-        ) as Box<dyn AsyncIo>)
-    }
-}
-
-pub struct FixedVhdAsync {
-    raw_file_async: RawFileAsync,
-    size: u64,
-}
-
-impl FixedVhdAsync {
-    pub fn new(fd: RawFd, ring_depth: u32, size: u64) -> std::io::Result<Self> {
-        let raw_file_async = RawFileAsync::new(fd, ring_depth)?;
-
-        Ok(FixedVhdAsync {
-            raw_file_async,
-            size,
-        })
-    }
-}
-
-impl AsyncIo for FixedVhdAsync {
-    fn notifier(&self) -> &EventFd {
-        self.raw_file_async.notifier()
-    }
-
-    fn read_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        if offset as u64 >= self.size {
-            return Err(AsyncIoError::ReadVectored(std::io::Error::new(
-                std::io::ErrorKind::InvalidData,
-                format!(
-                    "Invalid offset {}, can't be larger than file size {}",
-                    offset, self.size
-                ),
-            )));
-        }
-
-        self.raw_file_async.read_vectored(offset, iovecs, user_data)
-    }
-
-    fn write_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        if offset as u64 >= self.size {
-            return Err(AsyncIoError::WriteVectored(std::io::Error::new(
-                std::io::ErrorKind::InvalidData,
-                format!(
-                    "Invalid offset {}, can't be larger than file size {}",
-                    offset, self.size
-                ),
-            )));
-        }
-
-        self.raw_file_async
-            .write_vectored(offset, iovecs, user_data)
-    }
-
-    fn fsync(&mut self, user_data: Option<u64>) -> AsyncIoResult<()> {
-        self.raw_file_async.fsync(user_data)
-    }
-
-    fn next_completed_request(&mut self) -> Option<(u64, i32)> {
-        self.raw_file_async.next_completed_request()
-    }
-}

block/src/fixed_vhd_sync.rs

@@ -1,102 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-
-use std::fs::File;
-use std::os::unix::io::{AsRawFd, RawFd};
-
-use vmm_sys_util::eventfd::EventFd;
-
-use crate::async_io::{
-    AsyncIo, AsyncIoError, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult,
-};
-use crate::fixed_vhd::FixedVhd;
-use crate::raw_sync::RawFileSync;
-use crate::BlockBackend;
-
-pub struct FixedVhdDiskSync(FixedVhd);
-
-impl FixedVhdDiskSync {
-    pub fn new(file: File) -> std::io::Result<Self> {
-        Ok(Self(FixedVhd::new(file)?))
-    }
-}
-
-impl DiskFile for FixedVhdDiskSync {
-    fn size(&mut self) -> DiskFileResult<u64> {
-        Ok(self.0.size().unwrap())
-    }
-
-    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())
-                .map_err(DiskFileError::NewAsyncIo)?,
-        ) as Box<dyn AsyncIo>)
-    }
-}
-
-pub struct FixedVhdSync {
-    raw_file_sync: RawFileSync,
-    size: u64,
-}
-
-impl FixedVhdSync {
-    pub fn new(fd: RawFd, size: u64) -> std::io::Result<Self> {
-        Ok(FixedVhdSync {
-            raw_file_sync: RawFileSync::new(fd),
-            size,
-        })
-    }
-}
-
-impl AsyncIo for FixedVhdSync {
-    fn notifier(&self) -> &EventFd {
-        self.raw_file_sync.notifier()
-    }
-
-    fn read_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        if offset as u64 >= self.size {
-            return Err(AsyncIoError::ReadVectored(std::io::Error::new(
-                std::io::ErrorKind::InvalidData,
-                format!(
-                    "Invalid offset {}, can't be larger than file size {}",
-                    offset, self.size
-                ),
-            )));
-        }
-
-        self.raw_file_sync.read_vectored(offset, iovecs, user_data)
-    }
-
-    fn write_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        if offset as u64 >= self.size {
-            return Err(AsyncIoError::WriteVectored(std::io::Error::new(
-                std::io::ErrorKind::InvalidData,
-                format!(
-                    "Invalid offset {}, can't be larger than file size {}",
-                    offset, self.size
-                ),
-            )));
-        }
-
-        self.raw_file_sync.write_vectored(offset, iovecs, user_data)
-    }
-
-    fn fsync(&mut self, user_data: Option<u64>) -> AsyncIoResult<()> {
-        self.raw_file_sync.fsync(user_data)
-    }
-
-    fn next_completed_request(&mut self) -> Option<(u64, i32)> {
-        self.raw_file_sync.next_completed_request()
-    }
-}

block/src/lib.rs

@@ -1,891 +0,0 @@
-// Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
-//
-// 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.
-//
-// Copyright © 2020 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
-
-#[macro_use]
-extern crate log;
-
-pub mod async_io;
-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::{alloc_zeroed, dealloc, Layout};
-use std::collections::VecDeque;
-use std::fmt::Debug;
-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::sync::{Arc, MutexGuard};
-use std::time::Instant;
-use std::{cmp, result};
-
-#[cfg(feature = "io_uring")]
-use io_uring::{opcode, IoUring, Probe};
-use libc::{ioctl, S_IFBLK, S_IFMT};
-use serde::{Deserialize, Serialize};
-use smallvec::SmallVec;
-use thiserror::Error;
-use virtio_bindings::virtio_blk::*;
-use virtio_queue::DescriptorChain;
-use vm_memory::bitmap::Bitmap;
-use vm_memory::{
-    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, ioctl_ioc_nr};
-
-use crate::async_io::{AsyncIo, AsyncIoError, AsyncIoResult};
-use crate::fixed_vhd::FixedVhd;
-use crate::qcow::{QcowFile, RawFile};
-use crate::vhdx::{Vhdx, VhdxError};
-
-const SECTOR_SHIFT: u8 = 9;
-pub const SECTOR_SIZE: u64 = 0x01 << SECTOR_SHIFT;
-
-#[derive(Error, Debug)]
-pub enum Error {
-    #[error("Guest gave us bad memory addresses")]
-    GuestMemory(GuestMemoryError),
-    #[error("Guest gave us offsets that would have overflowed a usize")]
-    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")]
-    UnexpectedReadOnlyDescriptor,
-    #[error("Guest gave us too few descriptors in a descriptor chain")]
-    DescriptorChainTooShort,
-    #[error("Guest gave us a descriptor that was too short to use")]
-    DescriptorLengthTooSmall,
-    #[error("Failed to detect image type: {0}")]
-    DetectImageType(std::io::Error),
-    #[error("Failure in fixed vhd: {0}")]
-    FixedVhdError(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: {0}")]
-    QcowError(qcow::Error),
-    #[error("Failure in raw file: {0}")]
-    RawFileError(std::io::Error),
-    #[error("The requested operation does not support multiple descriptors")]
-    TooManyDescriptors,
-    #[error("Failure in vhdx: {0}")]
-    VhdxError(VhdxError),
-}
-
-fn build_device_id(disk_path: &Path) -> result::Result<String, Error> {
-    let blk_metadata = match disk_path.metadata() {
-        Err(_) => return Err(Error::GetFileMetadata),
-        Ok(m) => m,
-    };
-    // This is how kvmtool does it.
-    let device_id = format!(
-        "{}{}{}",
-        blk_metadata.st_dev(),
-        blk_metadata.st_rdev(),
-        blk_metadata.st_ino()
-    );
-    Ok(device_id)
-}
-
-pub fn build_serial(disk_path: &Path) -> Vec<u8> {
-    let mut default_serial = 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.");
-        }
-        Ok(m) => {
-            // The kernel only knows to read a maximum of VIRTIO_BLK_ID_BYTES.
-            // 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_serial
-}
-
-#[derive(Error, Debug)]
-pub enum ExecuteError {
-    #[error("Bad request: {0}")]
-    BadRequest(Error),
-    #[error("Failed to flush: {0}")]
-    Flush(io::Error),
-    #[error("Failed to read: {0}")]
-    Read(GuestMemoryError),
-    #[error("Failed to read_exact: {0}")]
-    ReadExact(io::Error),
-    #[error("Failed to seek: {0}")]
-    Seek(io::Error),
-    #[error("Failed to write: {0}")]
-    Write(GuestMemoryError),
-    #[error("Failed to write_all: {0}")]
-    WriteAll(io::Error),
-    #[error("Unsupported request: {0}")]
-    Unsupported(u32),
-    #[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 {
-            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::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,
-            ExecuteError::AsyncRead(_) => VIRTIO_BLK_S_IOERR,
-            ExecuteError::AsyncWrite(_) => VIRTIO_BLK_S_IOERR,
-            ExecuteError::AsyncFlush(_) => VIRTIO_BLK_S_IOERR,
-            ExecuteError::TemporaryBufferAllocation(_) => VIRTIO_BLK_S_IOERR,
-        };
-        status as u8
-    }
-}
-
-#[derive(Clone, Copy, Debug, PartialEq, Eq)]
-pub enum RequestType {
-    In,
-    Out,
-    Flush,
-    GetDeviceId,
-    Unsupported(u32),
-}
-
-pub fn request_type<B: Bitmap + 'static>(
-    mem: &vm_memory::GuestMemoryMmap<B>,
-    desc_addr: GuestAddress,
-) -> result::Result<RequestType, Error> {
-    let type_ = mem.read_obj(desc_addr).map_err(Error::GuestMemory)?;
-    match type_ {
-        VIRTIO_BLK_T_IN => Ok(RequestType::In),
-        VIRTIO_BLK_T_OUT => Ok(RequestType::Out),
-        VIRTIO_BLK_T_FLUSH => Ok(RequestType::Flush),
-        VIRTIO_BLK_T_GET_ID => Ok(RequestType::GetDeviceId),
-        t => Ok(RequestType::Unsupported(t)),
-    }
-}
-
-fn sector<B: Bitmap + 'static>(
-    mem: &vm_memory::GuestMemoryMmap<B>,
-    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,
-        None => return Err(Error::CheckedOffset(desc_addr, SECTOR_OFFSET)),
-    };
-
-    mem.read_obj(addr).map_err(Error::GuestMemory)
-}
-
-#[derive(Debug)]
-pub struct AlignedOperation {
-    origin_ptr: u64,
-    aligned_ptr: u64,
-    size: usize,
-    layout: Layout,
-}
-
-#[derive(Debug)]
-pub struct Request {
-    pub request_type: RequestType,
-    pub sector: u64,
-    pub data_descriptors: SmallVec<[(GuestAddress, u32); 1]>,
-    pub status_addr: GuestAddress,
-    pub writeback: bool,
-    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>>>,
-        access_platform: Option<&Arc<dyn AccessPlatform>>,
-    ) -> result::Result<Request, Error> {
-        let hdr_desc = desc_chain
-            .next()
-            .ok_or(Error::DescriptorChainTooShort)
-            .inspect_err(|_| {
-                error!("Missing head descriptor");
-            })?;
-
-        // The head contains the request type which MUST be readable.
-        if hdr_desc.is_write_only() {
-            return Err(Error::UnexpectedWriteOnlyDescriptor);
-        }
-
-        let hdr_desc_addr = hdr_desc
-            .addr()
-            .translate_gva(access_platform, hdr_desc.len() as usize);
-
-        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(1),
-            status_addr: GuestAddress(0),
-            writeback: true,
-            aligned_operations: SmallVec::with_capacity(1),
-            start: Instant::now(),
-        };
-
-        let status_desc;
-        let mut desc = desc_chain
-            .next()
-            .ok_or(Error::DescriptorChainTooShort)
-            .inspect_err(|_| {
-                error!("Only head descriptor present: request = {:?}", req);
-            })?;
-
-        if !desc.has_next() {
-            status_desc = desc;
-            // Only flush requests are allowed to skip the data descriptor.
-            if req.request_type != RequestType::Flush {
-                error!("Need a data descriptor: request = {:?}", req);
-                return Err(Error::DescriptorChainTooShort);
-            }
-        } else {
-            req.data_descriptors.reserve_exact(1);
-            while desc.has_next() {
-                if desc.is_write_only() && req.request_type == RequestType::Out {
-                    return Err(Error::UnexpectedWriteOnlyDescriptor);
-                }
-                if !desc.is_write_only() && req.request_type == RequestType::In {
-                    return Err(Error::UnexpectedReadOnlyDescriptor);
-                }
-                if !desc.is_write_only() && req.request_type == RequestType::GetDeviceId {
-                    return Err(Error::UnexpectedReadOnlyDescriptor);
-                }
-
-                req.data_descriptors.push((
-                    desc.addr()
-                        .translate_gva(access_platform, desc.len() as usize),
-                    desc.len(),
-                ));
-                desc = desc_chain
-                    .next()
-                    .ok_or(Error::DescriptorChainTooShort)
-                    .inspect_err(|_| {
-                        error!("DescriptorChain corrupted: request = {:?}", req);
-                    })?;
-            }
-            status_desc = desc;
-        }
-
-        // The status MUST always be writable.
-        if !status_desc.is_write_only() {
-            return Err(Error::UnexpectedReadOnlyDescriptor);
-        }
-
-        if status_desc.len() < 1 {
-            return Err(Error::DescriptorLengthTooSmall);
-        }
-
-        req.status_addr = status_desc
-            .addr()
-            .translate_gva(access_platform, status_desc.len() as usize);
-
-        Ok(req)
-    }
-
-    pub fn execute<T: Seek + Read + Write, B: Bitmap + 'static>(
-        &self,
-        disk: &mut T,
-        disk_nsectors: u64,
-        mem: &vm_memory::GuestMemoryMmap<B>,
-        serial: &[u8],
-    ) -> result::Result<u32, ExecuteError> {
-        disk.seek(SeekFrom::Start(self.sector << SECTOR_SHIFT))
-            .map_err(ExecuteError::Seek)?;
-        let mut len = 0;
-        for (data_addr, data_len) in &self.data_descriptors {
-            let mut top: u64 = u64::from(*data_len) / SECTOR_SIZE;
-            if u64::from(*data_len) % SECTOR_SIZE != 0 {
-                top += 1;
-            }
-            top = top
-                .checked_add(self.sector)
-                .ok_or(ExecuteError::BadRequest(Error::InvalidOffset))?;
-            if top > disk_nsectors {
-                return Err(ExecuteError::BadRequest(Error::InvalidOffset));
-            }
-
-            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)?;
-                    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)
-                        .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() {
-                        return Err(ExecuteError::BadRequest(Error::InvalidOffset));
-                    }
-                    mem.write_slice(serial, *data_addr)
-                        .map_err(ExecuteError::Write)?;
-                }
-                RequestType::Unsupported(t) => return Err(ExecuteError::Unsupported(t)),
-            };
-        }
-        Ok(len)
-    }
-
-    pub fn execute_async<B: Bitmap + 'static>(
-        &mut self,
-        mem: &vm_memory::GuestMemoryMmap<B>,
-        disk_nsectors: u64,
-        disk_image: &mut dyn AsyncIo,
-        serial: &[u8],
-        user_data: u64,
-    ) -> 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; 1]> =
-            SmallVec::with_capacity(self.data_descriptors.len());
-        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 {
-                top += 1;
-            }
-            top = top
-                .checked_add(sector)
-                .ok_or(ExecuteError::BadRequest(Error::InvalidOffset))?;
-            if top > disk_nsectors {
-                return Err(ExecuteError::BadRequest(Error::InvalidOffset));
-            }
-
-            let origin_ptr = mem
-                .get_slice(*data_addr, *data_len as usize)
-                .map_err(ExecuteError::GetHostAddress)?
-                .ptr_guard();
-
-            // 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) % 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() {
-                    return Err(ExecuteError::TemporaryBufferAllocation(
-                        io::Error::last_os_error(),
-                    ));
-                }
-
-                // We need to perform the copy beforehand in case we're writing
-                // data out.
-                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 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,
-                    aligned_ptr: aligned_ptr as u64,
-                    size: *data_len as usize,
-                    layout,
-                });
-
-                aligned_ptr as *mut libc::c_void
-            } else {
-                origin_ptr.as_ptr() as *mut libc::c_void
-            };
-
-            let iovec = libc::iovec {
-                iov_base,
-                iov_len: *data_len as libc::size_t,
-            };
-            iovecs.push(iovec);
-        }
-
-        // Queue operations expected to be submitted.
-        match request_type {
-            RequestType::In => {
-                for (data_addr, data_len) in &self.data_descriptors {
-                    mem.get_slice(*data_addr, *data_len as usize)
-                        .map_err(ExecuteError::GetHostAddress)?
-                        .bitmap()
-                        .mark_dirty(0, *data_len as usize);
-                }
-                disk_image
-                    .read_vectored(offset, &iovecs, user_data)
-                    .map_err(ExecuteError::AsyncRead)?;
-            }
-            RequestType::Out => {
-                disk_image
-                    .write_vectored(offset, &iovecs, user_data)
-                    .map_err(ExecuteError::AsyncWrite)?;
-            }
-            RequestType::Flush => {
-                disk_image
-                    .fsync(Some(user_data))
-                    .map_err(ExecuteError::AsyncFlush)?;
-            }
-            RequestType::GetDeviceId => {
-                let (data_addr, data_len) = if self.data_descriptors.len() == 1 {
-                    (self.data_descriptors[0].0, self.data_descriptors[0].1)
-                } else {
-                    return Err(ExecuteError::BadRequest(Error::TooManyDescriptors));
-                };
-                if (data_len as usize) < serial.len() {
-                    return Err(ExecuteError::BadRequest(Error::InvalidOffset));
-                }
-                mem.write_slice(serial, data_addr)
-                    .map_err(ExecuteError::Write)?;
-                return Ok(false);
-            }
-            RequestType::Unsupported(t) => return Err(ExecuteError::Unsupported(t)),
-        }
-
-        Ok(true)
-    }
-
-    pub fn complete_async(&mut self) -> result::Result<(), Error> {
-        for aligned_operation in self.aligned_operations.drain(..) {
-            // We need to perform the copy after the data has been read inside
-            // the aligned buffer in case we're reading data in.
-            if self.request_type == RequestType::In {
-                // SAFETY: origin buffer has been allocated with the
-                // proper size.
-                unsafe {
-                    std::ptr::copy(
-                        aligned_operation.aligned_ptr as *const u8,
-                        aligned_operation.origin_ptr as *mut u8,
-                        aligned_operation.size,
-                    )
-                };
-            }
-
-            // Free the temporary aligned buffer.
-            // SAFETY: aligned_ptr was allocated by alloc_zeroed with the same
-            // layout
-            unsafe {
-                dealloc(
-                    aligned_operation.aligned_ptr as *mut u8,
-                    aligned_operation.layout,
-                )
-            };
-        }
-
-        Ok(())
-    }
-
-    pub fn set_writeback(&mut self, writeback: bool) {
-        self.writeback = writeback
-    }
-}
-
-#[derive(Copy, Clone, Debug, Default, Serialize, Deserialize)]
-#[repr(C, packed)]
-pub struct VirtioBlockConfig {
-    pub capacity: u64,
-    pub size_max: u32,
-    pub seg_max: u32,
-    pub geometry: VirtioBlockGeometry,
-    pub blk_size: u32,
-    pub physical_block_exp: u8,
-    pub alignment_offset: u8,
-    pub min_io_size: u16,
-    pub opt_io_size: u32,
-    pub writeback: u8,
-    pub unused: u8,
-    pub num_queues: u16,
-    pub max_discard_sectors: u32,
-    pub max_discard_seg: u32,
-    pub discard_sector_alignment: u32,
-    pub max_write_zeroes_sectors: u32,
-    pub max_write_zeroes_seg: u32,
-    pub write_zeroes_may_unmap: u8,
-    pub unused1: [u8; 3],
-}
-#[derive(Copy, Clone, Debug, Default, Serialize, Deserialize)]
-#[repr(C, packed)]
-pub struct VirtioBlockGeometry {
-    pub cylinders: u16,
-    pub heads: u8,
-    pub sectors: u8,
-}
-
-// SAFETY: data structure only contain a series of integers
-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
-    }
-
-    #[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
-    }
-}
-
-pub trait AsyncAdaptor<F>
-where
-    F: Read + Write + Seek,
-{
-    fn read_vectored_sync(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-        eventfd: &EventFd,
-        completion_list: &mut VecDeque<(u64, i32)>,
-    ) -> AsyncIoResult<()> {
-        // Convert libc::iovec into IoSliceMut
-        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)
-            }));
-        }
-
-        let result = {
-            let mut file = self.file();
-
-            // Move the cursor to the right offset
-            file.seek(SeekFrom::Start(offset as u64))
-                .map_err(AsyncIoError::ReadVectored)?;
-
-            // Read vectored
-            file.read_vectored(slices.as_mut_slice())
-                .map_err(AsyncIoError::ReadVectored)?
-        };
-
-        completion_list.push_back((user_data, result as i32));
-        eventfd.write(1).unwrap();
-
-        Ok(())
-    }
-
-    fn write_vectored_sync(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-        eventfd: &EventFd,
-        completion_list: &mut VecDeque<(u64, i32)>,
-    ) -> AsyncIoResult<()> {
-        // Convert libc::iovec into IoSlice
-        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)
-            }));
-        }
-
-        let result = {
-            let mut file = self.file();
-
-            // Move the cursor to the right offset
-            file.seek(SeekFrom::Start(offset as u64))
-                .map_err(AsyncIoError::WriteVectored)?;
-
-            // Write vectored
-            file.write_vectored(slices.as_slice())
-                .map_err(AsyncIoError::WriteVectored)?
-        };
-
-        completion_list.push_back((user_data, result as i32));
-        eventfd.write(1).unwrap();
-
-        Ok(())
-    }
-
-    fn fsync_sync(
-        &mut self,
-        user_data: Option<u64>,
-        eventfd: &EventFd,
-        completion_list: &mut VecDeque<(u64, i32)>,
-    ) -> AsyncIoResult<()> {
-        let result: i32 = {
-            let mut file = self.file();
-
-            // Flush
-            file.flush().map_err(AsyncIoError::Fsync)?;
-
-            0
-        };
-
-        if let Some(user_data) = user_data {
-            completion_list.push_back((user_data, result));
-            eventfd.write(1).unwrap();
-        }
-
-        Ok(())
-    }
-
-    fn file(&mut self) -> MutexGuard<F>;
-}
-
-pub enum ImageType {
-    FixedVhd,
-    Qcow2,
-    Raw,
-    Vhdx,
-}
-
-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)?;
-
-    // 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 {
-        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 {
-        ImageType::Vhdx
-    } else {
-        ImageType::Raw
-    };
-
-    Ok(image_type)
-}
-
-pub trait BlockBackend: Read + Write + Seek + Send + Debug {
-    fn size(&self) -> Result<u64, Error>;
-}
-
-/// Inspect the image file type and create an appropriate disk file to match it.
-pub fn create_disk_file(mut file: File, direct_io: bool) -> Result<Box<dyn BlockBackend>, Error> {
-    let image_type = detect_image_type(&mut file).map_err(Error::DetectImageType)?;
-
-    Ok(match image_type {
-        ImageType::Qcow2 => {
-            Box::new(QcowFile::from(RawFile::new(file, direct_io)).map_err(Error::QcowError)?)
-                as Box<dyn BlockBackend>
-        }
-        ImageType::FixedVhd => {
-            Box::new(FixedVhd::new(file).map_err(Error::FixedVhdError)?) as Box<dyn BlockBackend>
-        }
-        ImageType::Vhdx => {
-            Box::new(Vhdx::new(file).map_err(Error::VhdxError)?) as Box<dyn BlockBackend>
-        }
-        ImageType::Raw => Box::new(RawFile::new(file, direct_io)) as Box<dyn BlockBackend>,
-    })
-}
-
-#[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/src/qcow/raw_file.rs

@@ -1,371 +0,0 @@
-// Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
-//
-// 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.
-//
-// Copyright © 2020 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
-
-use std::alloc::{alloc_zeroed, dealloc, Layout};
-use std::fs::{File, Metadata};
-use std::io::{self, Read, Seek, SeekFrom, Write};
-use std::os::unix::io::{AsRawFd, RawFd};
-use std::slice;
-
-use libc::c_void;
-use vmm_sys_util::seek_hole::SeekHole;
-use vmm_sys_util::write_zeroes::{PunchHole, WriteZeroesAt};
-
-use crate::BlockBackend;
-
-#[derive(Debug)]
-pub struct RawFile {
-    file: File,
-    alignment: usize,
-    position: u64,
-    direct_io: bool,
-}
-
-const BLK_ALIGNMENTS: [usize; 2] = [512, 4096];
-
-fn is_valid_alignment(fd: RawFd, alignment: usize) -> bool {
-    let layout = Layout::from_size_align(alignment, alignment).unwrap();
-    // SAFETY: layout has non-zero size
-    let ptr = unsafe { alloc_zeroed(layout) };
-    assert!(!ptr.is_null());
-
-    // SAFETY: FFI call
-    let ret = unsafe {
-        ::libc::pread(
-            fd,
-            ptr as *mut c_void,
-            alignment,
-            alignment.try_into().unwrap(),
-        )
-    };
-
-    // SAFETY: ptr was allocated by alloc_zeroed with layout
-    unsafe { dealloc(ptr, layout) };
-
-    ret >= 0
-}
-
-impl RawFile {
-    pub fn new(file: File, direct_io: bool) -> Self {
-        // Assume no alignment restrictions if we aren't using O_DIRECT.
-        let mut alignment = 0;
-        if direct_io {
-            for align in &BLK_ALIGNMENTS {
-                if is_valid_alignment(file.as_raw_fd(), *align) {
-                    alignment = *align;
-                    break;
-                }
-            }
-        }
-        RawFile {
-            file,
-            alignment,
-            position: 0,
-            direct_io,
-        }
-    }
-
-    fn round_up(&self, offset: u64) -> u64 {
-        let align: u64 = self.alignment.try_into().unwrap();
-        offset.div_ceil(align) * align
-    }
-
-    fn round_down(&self, offset: u64) -> u64 {
-        let align: u64 = self.alignment.try_into().unwrap();
-        (offset / align) * align
-    }
-
-    fn is_aligned(&self, buf: &[u8]) -> bool {
-        if self.alignment == 0 {
-            return true;
-        }
-
-        let align64: u64 = self.alignment.try_into().unwrap();
-
-        (self.position % align64 == 0)
-            && ((buf.as_ptr() as usize) % self.alignment == 0)
-            && (buf.len() % self.alignment == 0)
-    }
-
-    pub fn set_len(&self, size: u64) -> std::io::Result<()> {
-        self.file.set_len(size)
-    }
-
-    pub fn metadata(&self) -> std::io::Result<Metadata> {
-        self.file.metadata()
-    }
-
-    pub fn try_clone(&self) -> std::io::Result<RawFile> {
-        Ok(RawFile {
-            file: self.file.try_clone().expect("RawFile cloning failed"),
-            alignment: self.alignment,
-            position: self.position,
-            direct_io: self.direct_io,
-        })
-    }
-
-    pub fn sync_all(&self) -> std::io::Result<()> {
-        self.file.sync_all()
-    }
-
-    pub fn sync_data(&self) -> std::io::Result<()> {
-        self.file.sync_data()
-    }
-
-    pub fn is_direct(&self) -> bool {
-        self.direct_io
-    }
-}
-
-impl Read for RawFile {
-    fn read(&mut self, buf: &mut [u8]) -> std::io::Result<usize> {
-        if self.is_aligned(buf) {
-            match self.file.read(buf) {
-                Ok(r) => {
-                    self.position = self.position.checked_add(r.try_into().unwrap()).unwrap();
-                    Ok(r)
-                }
-                Err(e) => Err(e),
-            }
-        } else {
-            let rounded_pos: u64 = self.round_down(self.position);
-            let file_offset: usize = self
-                .position
-                .checked_sub(rounded_pos)
-                .unwrap()
-                .try_into()
-                .unwrap();
-            let buf_len: usize = buf.len();
-            let rounded_len: usize = self
-                .round_up(
-                    file_offset
-                        .checked_add(buf_len)
-                        .unwrap()
-                        .try_into()
-                        .unwrap(),
-                )
-                .try_into()
-                .unwrap();
-
-            let layout = Layout::from_size_align(rounded_len, self.alignment).unwrap();
-            // SAFETY: layout has non-zero size
-            let tmp_ptr = unsafe { alloc_zeroed(layout) };
-            if tmp_ptr.is_null() {
-                return Err(io::Error::last_os_error());
-            }
-
-            // SAFETY: tmp_ptr is valid and at least rounded_len long
-            let tmp_buf = unsafe { slice::from_raw_parts_mut(tmp_ptr, rounded_len) };
-
-            // This can eventually replaced with read_at once its interface
-            // has been stabilized.
-            // SAFETY: FFI call. All parameters are valid.
-            let ret = unsafe {
-                ::libc::pread64(
-                    self.file.as_raw_fd(),
-                    tmp_buf.as_mut_ptr() as *mut c_void,
-                    tmp_buf.len(),
-                    rounded_pos.try_into().unwrap(),
-                )
-            };
-            if ret < 0 {
-                // SAFETY: tmp_ptr was allocated by alloc_zeroed with layout
-                unsafe { dealloc(tmp_ptr, layout) };
-                return Err(io::Error::last_os_error());
-            }
-
-            let read: usize = ret.try_into().unwrap();
-            if read < file_offset {
-                // SAFETY: tmp_ptr was allocated by alloc_zeroed with layout
-                unsafe { dealloc(tmp_ptr, layout) };
-                return Ok(0);
-            }
-
-            let mut to_copy = read - file_offset;
-            if to_copy > buf_len {
-                to_copy = buf_len;
-            }
-
-            buf.copy_from_slice(&tmp_buf[file_offset..(file_offset + buf_len)]);
-            // SAFETY: tmp_ptr was allocated by alloc_zeroed with layout
-            unsafe { dealloc(tmp_ptr, layout) };
-
-            self.seek(SeekFrom::Current(to_copy.try_into().unwrap()))
-                .unwrap();
-            Ok(to_copy)
-        }
-    }
-}
-
-impl Write for RawFile {
-    fn write(&mut self, buf: &[u8]) -> std::io::Result<usize> {
-        if self.is_aligned(buf) {
-            match self.file.write(buf) {
-                Ok(r) => {
-                    self.position = self.position.checked_add(r.try_into().unwrap()).unwrap();
-                    Ok(r)
-                }
-                Err(e) => Err(e),
-            }
-        } else {
-            let rounded_pos: u64 = self.round_down(self.position);
-            let file_offset: usize = self
-                .position
-                .checked_sub(rounded_pos)
-                .unwrap()
-                .try_into()
-                .unwrap();
-            let buf_len: usize = buf.len();
-            let rounded_len: usize = self
-                .round_up(
-                    file_offset
-                        .checked_add(buf_len)
-                        .unwrap()
-                        .try_into()
-                        .unwrap(),
-                )
-                .try_into()
-                .unwrap();
-
-            let layout = Layout::from_size_align(rounded_len, self.alignment).unwrap();
-            // SAFETY: layout has non-zero size
-            let tmp_ptr = unsafe { alloc_zeroed(layout) };
-            if tmp_ptr.is_null() {
-                return Err(io::Error::last_os_error());
-            }
-
-            // SAFETY: tmp_ptr is at least rounded_len long
-            let tmp_buf = unsafe { slice::from_raw_parts_mut(tmp_ptr, rounded_len) };
-
-            // This can eventually replaced with read_at once its interface
-            // has been stabilized.
-            // SAFETY: FFI call
-            let ret = unsafe {
-                ::libc::pread64(
-                    self.file.as_raw_fd(),
-                    tmp_buf.as_mut_ptr() as *mut c_void,
-                    tmp_buf.len(),
-                    rounded_pos.try_into().unwrap(),
-                )
-            };
-            if ret < 0 {
-                // SAFETY: tmp_ptr was allocated by alloc_zeroed with layout
-                unsafe { dealloc(tmp_ptr, layout) };
-                return Err(io::Error::last_os_error());
-            };
-
-            tmp_buf[file_offset..(file_offset + buf_len)].copy_from_slice(buf);
-
-            // This can eventually replaced with write_at once its interface
-            // has been stabilized.
-            // SAFETY: FFI call
-            let ret = unsafe {
-                ::libc::pwrite64(
-                    self.file.as_raw_fd(),
-                    tmp_buf.as_ptr() as *const c_void,
-                    tmp_buf.len(),
-                    rounded_pos.try_into().unwrap(),
-                )
-            };
-
-            // SAFETY: tmp_ptr was allocated by alloc_zeroed with layout
-            unsafe { dealloc(tmp_ptr, layout) };
-
-            if ret < 0 {
-                return Err(io::Error::last_os_error());
-            }
-
-            let written: usize = ret.try_into().unwrap();
-            if written < file_offset {
-                Ok(0)
-            } else {
-                let mut to_seek = written - file_offset;
-                if to_seek > buf_len {
-                    to_seek = buf_len;
-                }
-
-                self.seek(SeekFrom::Current(to_seek.try_into().unwrap()))
-                    .unwrap();
-                Ok(to_seek)
-            }
-        }
-    }
-
-    fn flush(&mut self) -> std::io::Result<()> {
-        self.file.sync_all()
-    }
-}
-
-impl Seek for RawFile {
-    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 WriteZeroesAt for RawFile {
-    fn write_zeroes_at(&mut self, offset: u64, length: usize) -> std::io::Result<usize> {
-        self.file.write_zeroes_at(offset, length)
-    }
-}
-
-impl PunchHole for RawFile {
-    fn punch_hole(&mut self, offset: u64, length: u64) -> std::io::Result<()> {
-        self.file.punch_hole(offset, length)
-    }
-}
-
-impl SeekHole for RawFile {
-    fn seek_hole(&mut self, offset: u64) -> std::io::Result<Option<u64>> {
-        match self.file.seek_hole(offset) {
-            Ok(pos) => {
-                if let Some(p) = pos {
-                    self.position = p;
-                }
-                Ok(pos)
-            }
-            Err(e) => Err(e),
-        }
-    }
-
-    fn seek_data(&mut self, offset: u64) -> std::io::Result<Option<u64>> {
-        match self.file.seek_data(offset) {
-            Ok(pos) => {
-                if let Some(p) = pos {
-                    self.position = p;
-                }
-                Ok(pos)
-            }
-            Err(e) => Err(e),
-        }
-    }
-}
-
-impl BlockBackend for RawFile {
-    fn size(&self) -> std::result::Result<u64, crate::Error> {
-        Ok(self.metadata().map_err(crate::Error::RawFileError)?.len())
-    }
-}
-
-impl Clone for RawFile {
-    fn clone(&self) -> Self {
-        RawFile {
-            file: self.file.try_clone().expect("RawFile cloning failed"),
-            alignment: self.alignment,
-            position: self.position,
-            direct_io: self.direct_io,
-        }
-    }
-}

block/src/qcow_sync.rs

@@ -1,106 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
-
-use std::collections::VecDeque;
-use std::fs::File;
-use std::io::{Seek, SeekFrom};
-use std::sync::{Arc, Mutex, MutexGuard};
-
-use vmm_sys_util::eventfd::EventFd;
-
-use crate::async_io::{AsyncIo, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult};
-use crate::qcow::{QcowFile, RawFile, Result as QcowResult};
-use crate::AsyncAdaptor;
-
-pub struct QcowDiskSync {
-    qcow_file: Arc<Mutex<QcowFile>>,
-}
-
-impl QcowDiskSync {
-    pub fn new(file: File, direct_io: bool) -> QcowResult<Self> {
-        Ok(QcowDiskSync {
-            qcow_file: Arc::new(Mutex::new(QcowFile::from(RawFile::new(file, direct_io))?)),
-        })
-    }
-}
-
-impl DiskFile for QcowDiskSync {
-    fn size(&mut self) -> DiskFileResult<u64> {
-        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>)
-    }
-}
-
-pub struct QcowSync {
-    qcow_file: Arc<Mutex<QcowFile>>,
-    eventfd: EventFd,
-    completion_list: VecDeque<(u64, i32)>,
-}
-
-impl QcowSync {
-    pub fn new(qcow_file: Arc<Mutex<QcowFile>>) -> Self {
-        QcowSync {
-            qcow_file,
-            eventfd: EventFd::new(libc::EFD_NONBLOCK)
-                .expect("Failed creating EventFd for QcowSync"),
-            completion_list: VecDeque::new(),
-        }
-    }
-}
-
-impl AsyncAdaptor<QcowFile> for Arc<Mutex<QcowFile>> {
-    fn file(&mut self) -> MutexGuard<QcowFile> {
-        self.lock().unwrap()
-    }
-}
-
-impl AsyncIo for QcowSync {
-    fn notifier(&self) -> &EventFd {
-        &self.eventfd
-    }
-
-    fn read_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        self.qcow_file.read_vectored_sync(
-            offset,
-            iovecs,
-            user_data,
-            &self.eventfd,
-            &mut self.completion_list,
-        )
-    }
-
-    fn write_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        self.qcow_file.write_vectored_sync(
-            offset,
-            iovecs,
-            user_data,
-            &self.eventfd,
-            &mut self.completion_list,
-        )
-    }
-
-    fn fsync(&mut self, user_data: Option<u64>) -> AsyncIoResult<()> {
-        self.qcow_file
-            .fsync_sync(user_data, &self.eventfd, &mut self.completion_list)
-    }
-
-    fn next_completed_request(&mut self) -> Option<(u64, i32)> {
-        self.completion_list.pop_front()
-    }
-}

block/src/raw_async.rs

@@ -1,167 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
-
-use std::fs::File;
-use std::io::{Seek, SeekFrom};
-use std::os::unix::io::{AsRawFd, RawFd};
-
-use io_uring::{opcode, squeue, types, IoUring};
-use vmm_sys_util::eventfd::EventFd;
-
-use crate::async_io::{
-    AsyncIo, AsyncIoError, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult,
-};
-use crate::DiskTopology;
-
-pub struct RawFileDisk {
-    file: File,
-}
-
-impl RawFileDisk {
-    pub fn new(file: File) -> Self {
-        RawFileDisk { file }
-    }
-}
-
-impl DiskFile for RawFileDisk {
-    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(
-            RawFileAsync::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()
-        }
-    }
-}
-
-pub struct RawFileAsync {
-    fd: RawFd,
-    io_uring: IoUring,
-    eventfd: EventFd,
-}
-
-impl RawFileAsync {
-    pub fn new(fd: RawFd, ring_depth: u32) -> std::io::Result<Self> {
-        let io_uring = IoUring::new(ring_depth)?;
-        let eventfd = EventFd::new(libc::EFD_NONBLOCK)?;
-
-        // Register the io_uring eventfd that will notify when something in
-        // the completion queue is ready.
-        io_uring.submitter().register_eventfd(eventfd.as_raw_fd())?;
-
-        Ok(RawFileAsync {
-            fd,
-            io_uring,
-            eventfd,
-        })
-    }
-}
-
-impl AsyncIo for RawFileAsync {
-    fn notifier(&self) -> &EventFd {
-        &self.eventfd
-    }
-
-    fn read_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        let (submitter, mut sq, _) = self.io_uring.split();
-
-        // SAFETY: we know the file descriptor is valid and we
-        // relied on vm-memory to provide the buffer address.
-        let _ = unsafe {
-            sq.push(
-                &opcode::Readv::new(types::Fd(self.fd), iovecs.as_ptr(), iovecs.len() as u32)
-                    .offset(offset.try_into().unwrap())
-                    .build()
-                    .flags(squeue::Flags::ASYNC)
-                    .user_data(user_data),
-            )
-        };
-
-        // Update the submission queue and submit new operations to the
-        // io_uring instance.
-        sq.sync();
-        submitter.submit().map_err(AsyncIoError::ReadVectored)?;
-
-        Ok(())
-    }
-
-    fn write_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        let (submitter, mut sq, _) = self.io_uring.split();
-
-        // SAFETY: we know the file descriptor is valid and we
-        // relied on vm-memory to provide the buffer address.
-        let _ = unsafe {
-            sq.push(
-                &opcode::Writev::new(types::Fd(self.fd), iovecs.as_ptr(), iovecs.len() as u32)
-                    .offset(offset.try_into().unwrap())
-                    .build()
-                    .flags(squeue::Flags::ASYNC)
-                    .user_data(user_data),
-            )
-        };
-
-        // Update the submission queue and submit new operations to the
-        // io_uring instance.
-        sq.sync();
-        submitter.submit().map_err(AsyncIoError::WriteVectored)?;
-
-        Ok(())
-    }
-
-    fn fsync(&mut self, user_data: Option<u64>) -> AsyncIoResult<()> {
-        if let Some(user_data) = user_data {
-            let (submitter, mut sq, _) = self.io_uring.split();
-
-            // SAFETY: we know the file descriptor is valid.
-            let _ = unsafe {
-                sq.push(
-                    &opcode::Fsync::new(types::Fd(self.fd))
-                        .build()
-                        .flags(squeue::Flags::ASYNC)
-                        .user_data(user_data),
-                )
-            };
-
-            // Update the submission queue and submit new operations to the
-            // io_uring instance.
-            sq.sync();
-            submitter.submit().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)> {
-        self.io_uring
-            .completion()
-            .next()
-            .map(|entry| (entry.user_data(), entry.result()))
-    }
-}

block/src/raw_async_aio.rs

@@ -1,152 +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::async_io::{
-    AsyncIo, AsyncIoError, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult,
-};
-use crate::DiskTopology;
-
-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()
-        }
-    }
-}
-
-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/raw_sync.rs

@@ -1,137 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
-
-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::async_io::{
-    AsyncIo, AsyncIoError, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult,
-};
-use crate::DiskTopology;
-
-pub struct RawFileDiskSync {
-    file: File,
-}
-
-impl RawFileDiskSync {
-    pub fn new(file: File) -> Self {
-        RawFileDiskSync { file }
-    }
-}
-
-impl DiskFile for RawFileDiskSync {
-    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(RawFileSync::new(self.file.as_raw_fd())) 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()
-        }
-    }
-}
-
-pub struct RawFileSync {
-    fd: RawFd,
-    eventfd: EventFd,
-    completion_list: VecDeque<(u64, i32)>,
-}
-
-impl RawFileSync {
-    pub fn new(fd: RawFd) -> Self {
-        RawFileSync {
-            fd,
-            eventfd: EventFd::new(libc::EFD_NONBLOCK).expect("Failed creating EventFd for RawFile"),
-            completion_list: VecDeque::new(),
-        }
-    }
-}
-
-impl AsyncIo for RawFileSync {
-    fn notifier(&self) -> &EventFd {
-        &self.eventfd
-    }
-
-    fn read_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        // SAFETY: FFI call with valid arguments
-        let result = unsafe {
-            libc::preadv(
-                self.fd as libc::c_int,
-                iovecs.as_ptr(),
-                iovecs.len() as libc::c_int,
-                offset,
-            )
-        };
-        if result < 0 {
-            return Err(AsyncIoError::ReadVectored(std::io::Error::last_os_error()));
-        }
-
-        self.completion_list.push_back((user_data, result as i32));
-        self.eventfd.write(1).unwrap();
-
-        Ok(())
-    }
-
-    fn write_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        // SAFETY: FFI call with valid arguments
-        let result = unsafe {
-            libc::pwritev(
-                self.fd as libc::c_int,
-                iovecs.as_ptr(),
-                iovecs.len() as libc::c_int,
-                offset,
-            )
-        };
-        if result < 0 {
-            return Err(AsyncIoError::WriteVectored(std::io::Error::last_os_error()));
-        }
-
-        self.completion_list.push_back((user_data, result as i32));
-        self.eventfd.write(1).unwrap();
-
-        Ok(())
-    }
-
-    fn fsync(&mut self, user_data: Option<u64>) -> AsyncIoResult<()> {
-        // SAFETY: FFI call
-        let result = unsafe { libc::fsync(self.fd as libc::c_int) };
-        if result < 0 {
-            return Err(AsyncIoError::Fsync(std::io::Error::last_os_error()));
-        }
-
-        if let Some(user_data) = user_data {
-            self.completion_list.push_back((user_data, result));
-            self.eventfd.write(1).unwrap();
-        }
-
-        Ok(())
-    }
-
-    fn next_completed_request(&mut self) -> Option<(u64, i32)> {
-        self.completion_list.pop_front()
-    }
-}

block/src/vhd.rs

@@ -1,220 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-
-use std::fs::File;
-use std::io::{Seek, SeekFrom};
-
-use crate::{read_aligned_block_size, DiskTopology};
-
-#[derive(Clone, Copy)]
-pub struct VhdFooter {
-    cookie: u64,
-    features: u32,
-    file_format_version: u32,
-    data_offset: u64,
-    time_stamp: u32,
-    creator_application: u32,
-    creator_version: u32,
-    creator_host_os: u32,
-    original_size: u64,
-    current_size: u64,
-    disk_geometry: u32,
-    disk_type: u32,
-    checksum: u32,
-    unique_id: u128,
-    saved_state: u8,
-}
-
-impl VhdFooter {
-    pub fn new(file: &mut File) -> std::io::Result<VhdFooter> {
-        let blocksize = DiskTopology::probe(file)?.logical_block_size as usize;
-
-        // 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)?;
-
-        // We only care about the last sector
-        let offset = blocksize - 512;
-        let sector = &data[offset..];
-
-        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()),
-        })
-    }
-
-    pub fn cookie(&self) -> u64 {
-        self.cookie
-    }
-    pub fn features(&self) -> u32 {
-        self.features
-    }
-    pub fn file_format_version(&self) -> u32 {
-        self.file_format_version
-    }
-    pub fn data_offset(&self) -> u64 {
-        self.data_offset
-    }
-    pub fn time_stamp(&self) -> u32 {
-        self.time_stamp
-    }
-    pub fn creator_application(&self) -> u32 {
-        self.creator_application
-    }
-    pub fn creator_version(&self) -> u32 {
-        self.creator_version
-    }
-    pub fn creator_host_os(&self) -> u32 {
-        self.creator_host_os
-    }
-    pub fn original_size(&self) -> u64 {
-        self.original_size
-    }
-    pub fn current_size(&self) -> u64 {
-        self.current_size
-    }
-    pub fn disk_geometry(&self) -> u32 {
-        self.disk_geometry
-    }
-    pub fn disk_type(&self) -> u32 {
-        self.disk_type
-    }
-    pub fn checksum(&self) -> u32 {
-        self.checksum
-    }
-    pub fn unique_id(&self) -> u128 {
-        self.unique_id
-    }
-    pub fn saved_state(&self) -> u8 {
-        self.saved_state
-    }
-}
-
-/// Determine image type through file parsing.
-pub fn is_fixed_vhd(f: &mut File) -> std::io::Result<bool> {
-    let footer = VhdFooter::new(f)?;
-
-    // "conectix" => 0x636f6e6563746978
-    Ok(footer.cookie() == 0x636f6e6563746978
-        && footer.file_format_version() == 0x0001_0000
-        && footer.data_offset() == 0xffff_ffff_ffff_ffff
-        && footer.disk_type() == 0x2)
-}
-
-#[cfg(test)]
-mod tests {
-    use std::fs::File;
-    use std::io::{Seek, SeekFrom, Write};
-
-    use vmm_sys_util::tempfile::TempFile;
-
-    use super::{is_fixed_vhd, VhdFooter};
-
-    fn valid_fixed_vhd_footer() -> Vec<u8> {
-        vec![
-            0x63, 0x6f, 0x6e, 0x65, 0x63, 0x74, 0x69, 0x78, // cookie
-            0x00, 0x00, 0x00, 0x02, // features
-            0x00, 0x01, 0x00, 0x00, // file format version
-            0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, // data offset
-            0x27, 0xa6, 0xa6, 0x5d, // time stamp
-            0x71, 0x65, 0x6d, 0x75, // creator application
-            0x00, 0x05, 0x00, 0x03, // creator version
-            0x57, 0x69, 0x32, 0x6b, // creator host os
-            0x00, 0x00, 0x00, 0x00, 0x10, 0x00, 0x00, 0x00, // original size
-            0x00, 0x00, 0x00, 0x00, 0x10, 0x00, 0x00, 0x00, // current size
-            0x11, 0xe0, 0x10, 0x3f, // disk geometry
-            0x00, 0x00, 0x00, 0x02, // disk type
-            0x00, 0x00, 0x00, 0x00, // checksum
-            0x98, 0x7b, 0xb1, 0xcd, 0x84, 0x14, 0x41, 0xfc, 0xa4, 0xab, 0xd0, 0x69, 0x45, 0x2b,
-            0xf2, 0x23, // unique id
-            0x00, // saved state
-        ]
-    }
-
-    fn valid_dynamic_vhd_footer() -> Vec<u8> {
-        vec![
-            0x63, 0x6f, 0x6e, 0x65, 0x63, 0x74, 0x69, 0x78, // cookie
-            0x00, 0x00, 0x00, 0x02, // features
-            0x00, 0x01, 0x00, 0x00, // file format version
-            0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // data offset
-            0x27, 0xa6, 0xa6, 0x5d, // time stamp
-            0x71, 0x65, 0x6d, 0x75, // creator application
-            0x00, 0x05, 0x00, 0x03, // creator version
-            0x57, 0x69, 0x32, 0x6b, // creator host os
-            0x00, 0x00, 0x00, 0x00, 0x10, 0x00, 0x00, 0x00, // original size
-            0x00, 0x00, 0x00, 0x00, 0x10, 0x00, 0x00, 0x00, // current size
-            0x11, 0xe0, 0x10, 0x3f, // disk geometry
-            0x00, 0x00, 0x00, 0x03, // disk type
-            0x00, 0x00, 0x00, 0x00, // checksum
-            0x98, 0x7b, 0xb1, 0xcd, 0x84, 0x14, 0x41, 0xfc, 0xa4, 0xab, 0xd0, 0x69, 0x45, 0x2b,
-            0xf2, 0x23, // unique id
-            0x00, // saved state
-        ]
-    }
-
-    fn with_file<F>(footer: &[u8], mut testfn: F)
-    where
-        F: FnMut(File),
-    {
-        let mut disk_file: File = TempFile::new().unwrap().into_file();
-        disk_file.set_len(0x1000_0200).unwrap();
-        disk_file.seek(SeekFrom::Start(0x1000_0000)).unwrap();
-        disk_file.write_all(footer).unwrap();
-
-        testfn(disk_file); // File closed when the function exits.
-    }
-
-    #[test]
-    fn test_check_vhd_footer() {
-        with_file(&valid_fixed_vhd_footer(), |mut file: File| {
-            let vhd_footer = VhdFooter::new(&mut file).expect("Failed to create VHD footer");
-            assert_eq!(vhd_footer.cookie(), 0x636f_6e65_6374_6978);
-            assert_eq!(vhd_footer.features(), 0x0000_0002);
-            assert_eq!(vhd_footer.file_format_version(), 0x0001_0000);
-            assert_eq!(vhd_footer.data_offset(), 0xffff_ffff_ffff_ffff);
-            assert_eq!(vhd_footer.time_stamp(), 0x27a6_a65d);
-            assert_eq!(vhd_footer.creator_application(), 0x7165_6d75);
-            assert_eq!(vhd_footer.creator_version(), 0x0005_0003);
-            assert_eq!(vhd_footer.creator_host_os(), 0x5769_326b);
-            assert_eq!(vhd_footer.original_size(), 0x0000_0000_1000_0000);
-            assert_eq!(vhd_footer.current_size(), 0x0000_0000_1000_0000);
-            assert_eq!(vhd_footer.disk_geometry(), 0x11e0_103f);
-            assert_eq!(vhd_footer.disk_type(), 0x0000_0002);
-            assert_eq!(vhd_footer.checksum(), 0x0000_0000);
-            assert_eq!(
-                vhd_footer.unique_id(),
-                0x987b_b1cd_8414_41fc_a4ab_d069_452b_f223
-            );
-            assert_eq!(vhd_footer.saved_state(), 0x00);
-        });
-    }
-
-    #[test]
-    fn test_is_fixed_vhd() {
-        with_file(&valid_fixed_vhd_footer(), |mut file: File| {
-            assert!(is_fixed_vhd(&mut file).unwrap());
-        });
-    }
-
-    #[test]
-    fn test_is_not_fixed_vhd() {
-        with_file(&valid_dynamic_vhd_footer(), |mut file: File| {
-            assert!(!(is_fixed_vhd(&mut file).unwrap()));
-        });
-    }
-}

block/src/vhdx/mod.rs

@@ -1,236 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-
-use std::collections::btree_map::BTreeMap;
-use std::fs::File;
-use std::io::{Read, Seek, SeekFrom, Write};
-
-use byteorder::{BigEndian, ByteOrder};
-use remain::sorted;
-use thiserror::Error;
-use uuid::Uuid;
-
-use crate::vhdx::vhdx_bat::{BatEntry, VhdxBatError};
-use crate::vhdx::vhdx_header::{RegionInfo, RegionTableEntry, VhdxHeader, VhdxHeaderError};
-use crate::vhdx::vhdx_io::VhdxIoError;
-use crate::vhdx::vhdx_metadata::{DiskSpec, VhdxMetadataError};
-use crate::BlockBackend;
-
-mod vhdx_bat;
-mod vhdx_header;
-mod vhdx_io;
-mod vhdx_metadata;
-
-#[sorted]
-#[derive(Error, Debug)]
-pub enum VhdxError {
-    #[error("Not a VHDx file {0}")]
-    NotVhdx(#[source] VhdxHeaderError),
-    #[error("Failed to parse VHDx header {0}")]
-    ParseVhdxHeader(#[source] VhdxHeaderError),
-    #[error("Failed to parse VHDx metadata {0}")]
-    ParseVhdxMetadata(#[source] VhdxMetadataError),
-    #[error("Failed to parse VHDx region entries {0}")]
-    ParseVhdxRegionEntry(#[source] VhdxHeaderError),
-    #[error("Failed reading metadata {0}")]
-    ReadBatEntry(#[source] VhdxBatError),
-    #[error("Failed reading sector from disk {0}")]
-    ReadFailed(#[source] VhdxIoError),
-    #[error("Failed writing to sector on disk {0}")]
-    WriteFailed(#[source] VhdxIoError),
-}
-
-pub type Result<T> = std::result::Result<T, VhdxError>;
-
-#[derive(Debug)]
-pub struct Vhdx {
-    file: File,
-    vhdx_header: VhdxHeader,
-    region_entries: BTreeMap<u64, u64>,
-    bat_entry: RegionTableEntry,
-    mdr_entry: RegionTableEntry,
-    disk_spec: DiskSpec,
-    bat_entries: Vec<BatEntry>,
-    current_offset: u64,
-    first_write: bool,
-}
-
-impl Vhdx {
-    /// Parse the Vhdx header, BAT, and metadata from a file and store info
-    // in Vhdx structure.
-    pub fn new(mut file: File) -> Result<Vhdx> {
-        let vhdx_header = VhdxHeader::new(&mut file).map_err(VhdxError::ParseVhdxHeader)?;
-
-        let collected_entries = RegionInfo::new(
-            &mut file,
-            vhdx_header::REGION_TABLE_1_START,
-            vhdx_header.region_entry_count(),
-        )
-        .map_err(VhdxError::ParseVhdxRegionEntry)?;
-
-        let bat_entry = collected_entries.bat_entry;
-        let mdr_entry = collected_entries.mdr_entry;
-
-        let disk_spec =
-            DiskSpec::new(&mut file, &mdr_entry).map_err(VhdxError::ParseVhdxMetadata)?;
-        let bat_entries = BatEntry::collect_bat_entries(&mut file, &disk_spec, &bat_entry)
-            .map_err(VhdxError::ReadBatEntry)?;
-
-        Ok(Vhdx {
-            file,
-            vhdx_header,
-            region_entries: collected_entries.region_entries,
-            bat_entry,
-            mdr_entry,
-            disk_spec,
-            bat_entries,
-            current_offset: 0,
-            first_write: true,
-        })
-    }
-
-    pub fn virtual_disk_size(&self) -> u64 {
-        self.disk_spec.virtual_disk_size
-    }
-}
-
-impl Read for Vhdx {
-    /// Wrapper function to satisfy Read trait implementation for VHDx disk.
-    /// Convert the offset to sector index and buffer length to sector count.
-    fn read(&mut self, buf: &mut [u8]) -> std::result::Result<usize, std::io::Error> {
-        let sector_count = (buf.len() as u64).div_ceil(self.disk_spec.logical_sector_size as u64);
-        let sector_index = self.current_offset / self.disk_spec.logical_sector_size as u64;
-
-        vhdx_io::read(
-            &mut self.file,
-            buf,
-            &self.disk_spec,
-            &self.bat_entries,
-            sector_index,
-            sector_count,
-        )
-        .map_err(|e| {
-            std::io::Error::new(
-                std::io::ErrorKind::Other,
-                format!(
-                    "Failed reading {sector_count} sectors from VHDx at index {sector_index}: {e}"
-                ),
-            )
-        })
-    }
-}
-
-impl Write for Vhdx {
-    fn flush(&mut self) -> std::result::Result<(), std::io::Error> {
-        self.file.flush()
-    }
-
-    /// Wrapper function to satisfy Write trait implementation for VHDx disk.
-    /// Convert the offset to sector index and buffer length to sector count.
-    fn write(&mut self, buf: &[u8]) -> std::result::Result<usize, std::io::Error> {
-        let sector_count = (buf.len() as u64).div_ceil(self.disk_spec.logical_sector_size as u64);
-        let sector_index = self.current_offset / self.disk_spec.logical_sector_size as u64;
-
-        if self.first_write {
-            self.first_write = false;
-            self.vhdx_header.update(&mut self.file).map_err(|e| {
-                std::io::Error::new(
-                    std::io::ErrorKind::Other,
-                    format!("Failed to update VHDx header: {e}"),
-                )
-            })?;
-        }
-
-        vhdx_io::write(
-            &mut self.file,
-            buf,
-            &mut self.disk_spec,
-            self.bat_entry.file_offset,
-            &mut self.bat_entries,
-            sector_index,
-            sector_count,
-        )
-        .map_err(|e| {
-            std::io::Error::new(
-                std::io::ErrorKind::Other,
-                format!(
-                    "Failed writing {sector_count} sectors on VHDx at index {sector_index}: {e}"
-                ),
-            )
-        })
-    }
-}
-
-impl Seek for Vhdx {
-    /// Wrapper function to satisfy Seek trait implementation for VHDx disk.
-    /// Updates the offset field in the Vhdx struct.
-    fn seek(&mut self, pos: SeekFrom) -> std::io::Result<u64> {
-        let new_offset: Option<u64> = match pos {
-            SeekFrom::Start(off) => Some(off),
-            SeekFrom::End(off) => {
-                if off < 0 {
-                    0i64.checked_sub(off).and_then(|increment| {
-                        self.virtual_disk_size().checked_sub(increment as u64)
-                    })
-                } else {
-                    self.virtual_disk_size().checked_add(off as u64)
-                }
-            }
-            SeekFrom::Current(off) => {
-                if off < 0 {
-                    0i64.checked_sub(off)
-                        .and_then(|increment| self.current_offset.checked_sub(increment as u64))
-                } else {
-                    self.current_offset.checked_add(off as u64)
-                }
-            }
-        };
-
-        if let Some(o) = new_offset {
-            if o <= self.virtual_disk_size() {
-                self.current_offset = o;
-                return Ok(o);
-            }
-        }
-
-        Err(std::io::Error::new(
-            std::io::ErrorKind::InvalidData,
-            "Failed seek operation",
-        ))
-    }
-}
-
-impl BlockBackend for Vhdx {
-    fn size(&self) -> std::result::Result<u64, crate::Error> {
-        Ok(self.virtual_disk_size())
-    }
-}
-
-impl Clone for Vhdx {
-    fn clone(&self) -> Self {
-        Vhdx {
-            file: self.file.try_clone().unwrap(),
-            vhdx_header: self.vhdx_header.clone(),
-            region_entries: self.region_entries.clone(),
-            bat_entry: self.bat_entry,
-            mdr_entry: self.mdr_entry,
-            disk_spec: self.disk_spec.clone(),
-            bat_entries: self.bat_entries.clone(),
-            current_offset: self.current_offset,
-            first_write: self.first_write,
-        }
-    }
-}
-
-pub(crate) fn uuid_from_guid(buf: &[u8]) -> Uuid {
-    // The first 3 fields of UUID are stored in Big Endian format, and
-    // the last 8 bytes are stored as byte array. Therefore, we read the
-    // first 3 fields in Big Endian format instead of Little Endian.
-    Uuid::from_fields_le(
-        BigEndian::read_u32(&buf[0..4]),
-        BigEndian::read_u16(&buf[4..6]),
-        BigEndian::read_u16(&buf[6..8]),
-        buf[8..16].try_into().unwrap(),
-    )
-}

block/src/vhdx/vhdx_bat.rs

@@ -1,106 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-
-use std::fs::File;
-use std::io::{self, Seek, SeekFrom};
-use std::mem::size_of;
-
-use byteorder::{LittleEndian, ReadBytesExt, WriteBytesExt};
-use remain::sorted;
-use thiserror::Error;
-
-use crate::vhdx::vhdx_header::RegionTableEntry;
-use crate::vhdx::vhdx_metadata::DiskSpec;
-
-// Payload BAT Entry States
-pub const PAYLOAD_BLOCK_NOT_PRESENT: u64 = 0;
-pub const PAYLOAD_BLOCK_UNDEFINED: u64 = 1;
-pub const PAYLOAD_BLOCK_ZERO: u64 = 2;
-pub const PAYLOAD_BLOCK_UNMAPPED: u64 = 3;
-pub const PAYLOAD_BLOCK_FULLY_PRESENT: u64 = 6;
-pub const PAYLOAD_BLOCK_PARTIALLY_PRESENT: u64 = 7;
-
-// Mask for the BAT state
-pub const BAT_STATE_BIT_MASK: u64 = 0x07;
-// Mask for the offset within the file in units of 1 MB
-pub const BAT_FILE_OFF_MASK: u64 = 0xFFFFFFFFFFF00000;
-
-#[sorted]
-#[derive(Error, Debug)]
-pub enum VhdxBatError {
-    #[error("Invalid BAT entry")]
-    InvalidBatEntry,
-    #[error("Invalid BAT entry count")]
-    InvalidEntryCount,
-    #[error("Failed to read BAT entry {0}")]
-    ReadBat(#[source] io::Error),
-    #[error("Failed to write BAT entry {0}")]
-    WriteBat(#[source] io::Error),
-}
-
-pub type Result<T> = std::result::Result<T, VhdxBatError>;
-
-#[derive(Default, Clone, Debug)]
-pub struct BatEntry(pub u64);
-
-impl BatEntry {
-    // Read all BAT entries presented on the disk and insert them to a vector
-    pub fn collect_bat_entries(
-        f: &mut File,
-        disk_spec: &DiskSpec,
-        bat_entry: &RegionTableEntry,
-    ) -> Result<Vec<BatEntry>> {
-        let entry_count = BatEntry::calculate_entries(
-            disk_spec.block_size,
-            disk_spec.virtual_disk_size,
-            disk_spec.chunk_ratio,
-        );
-        if entry_count as usize > (bat_entry.length as usize / size_of::<BatEntry>()) {
-            return Err(VhdxBatError::InvalidEntryCount);
-        }
-
-        let mut bat: Vec<BatEntry> = Vec::with_capacity(bat_entry.length as usize);
-        let offset = bat_entry.file_offset;
-        for i in 0..entry_count {
-            f.seek(SeekFrom::Start(offset + i * size_of::<u64>() as u64))
-                .map_err(VhdxBatError::ReadBat)?;
-
-            let bat_entry = BatEntry(
-                f.read_u64::<LittleEndian>()
-                    .map_err(VhdxBatError::ReadBat)?,
-            );
-            bat.insert(i as usize, bat_entry);
-        }
-
-        Ok(bat)
-    }
-
-    // Calculate the number of entries in the BAT
-    fn calculate_entries(block_size: u32, virtual_disk_size: u64, chunk_ratio: u64) -> u64 {
-        let data_blocks_count = virtual_disk_size.div_ceil(block_size as u64);
-        data_blocks_count + (data_blocks_count - 1) / chunk_ratio
-    }
-
-    // Routine for writing BAT entries to the disk
-    pub fn write_bat_entries(
-        f: &mut File,
-        bat_offset: u64,
-        bat_entries: &[BatEntry],
-    ) -> Result<()> {
-        for i in 0..bat_entries.len() as u64 {
-            f.seek(SeekFrom::Start(bat_offset + i * size_of::<u64>() as u64))
-                .map_err(VhdxBatError::WriteBat)?;
-            let bat_entry = match bat_entries.get(i as usize) {
-                Some(entry) => entry.0,
-                None => {
-                    return Err(VhdxBatError::InvalidBatEntry);
-                }
-            };
-
-            f.write_u64::<LittleEndian>(bat_entry)
-                .map_err(VhdxBatError::WriteBat)?;
-        }
-        Ok(())
-    }
-}

block/src/vhdx/vhdx_header.rs

@@ -1,487 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-
-extern crate log;
-
-use std::collections::btree_map::BTreeMap;
-use std::fs::File;
-use std::io::{self, Read, Seek, SeekFrom, Write};
-use std::mem::size_of;
-
-use byteorder::{ByteOrder, LittleEndian, ReadBytesExt};
-use remain::sorted;
-use thiserror::Error;
-use uuid::Uuid;
-
-const VHDX_SIGN: u64 = 0x656C_6966_7864_6876; // "vhdxfile"
-const HEADER_SIGN: u32 = 0x6461_6568; // "head"
-const REGION_SIGN: u32 = 0x6967_6572; // "regi"
-
-const FILE_START: u64 = 0; // The first element
-const HEADER_1_START: u64 = 64 * 1024; // Header 1 start in Bytes
-const HEADER_2_START: u64 = 128 * 1024; // Header 2 start in Bytes
-pub const REGION_TABLE_1_START: u64 = 192 * 1024; // Region 1 start in Bytes
-const REGION_TABLE_2_START: u64 = 256 * 1024; // Region 2 start in Bytes
-
-const HEADER_SIZE: u64 = 4 * 1024; // Each header is 64 KiB, but only first 4 kiB contains info
-const REGION_SIZE: u64 = 64 * 1024; // Each region size is 64 KiB
-
-const REGION_ENTRY_REQUIRED: u32 = 1;
-
-const BAT_GUID: &str = "2DC27766-F623-4200-9D64-115E9BFD4A08"; // BAT GUID
-const MDR_GUID: &str = "8B7CA206-4790-4B9A-B8FE-575F050F886E"; // Metadata GUID
-
-#[sorted]
-#[derive(Error, Debug)]
-pub enum VhdxHeaderError {
-    #[error("Failed to calculate checksum")]
-    CalculateChecksum,
-    #[error("BAT entry is not unique")]
-    DuplicateBATEntry,
-    #[error("Metadata region entry is not unique")]
-    DuplicateMDREntry,
-    #[error("Checksum doesn't match for")]
-    InvalidChecksum(String),
-    #[error("Invalid entry count")]
-    InvalidEntryCount,
-    #[error("Not a valid VHDx header")]
-    InvalidHeaderSign,
-    #[error("Not a valid VHDx region")]
-    InvalidRegionSign,
-    #[error("Couldn't parse Uuid for region entry {0}")]
-    InvalidUuid(#[source] uuid::Error),
-    #[error("Not a VHDx file")]
-    InvalidVHDXSign,
-    #[error("No valid header found")]
-    NoValidHeader,
-    #[error("Cannot read checksum")]
-    ReadChecksum,
-    #[error("Failed to read File Type Identifier {0}")]
-    ReadFileTypeIdentifier(#[source] io::Error),
-    #[error("Failed to read headers {0}")]
-    ReadHeader(#[source] io::Error),
-    #[error("Failed to read metadata {0}")]
-    ReadMetadata(#[source] std::io::Error),
-    #[error("Failed to read region table entries {0}")]
-    ReadRegionTableEntries(#[source] io::Error),
-    #[error("Failed to read region table header {0}")]
-    ReadRegionTableHeader(#[source] io::Error),
-    #[error("Failed to read region entries")]
-    RegionEntryCollectionFailed,
-    #[error("Overlapping regions found")]
-    RegionOverlap,
-    #[error("Reserved region has non-zero value")]
-    ReservedIsNonZero,
-    #[error("Failed to seek in File Type Identifier {0}")]
-    SeekFileTypeIdentifier(#[source] io::Error),
-    #[error("Failed to seek in headers {0}")]
-    SeekHeader(#[source] io::Error),
-    #[error("Failed to seek in region table entries {0}")]
-    SeekRegionTableEntries(#[source] io::Error),
-    #[error("Failed to seek in region table header {0}")]
-    SeekRegionTableHeader(#[source] io::Error),
-    #[error("We do not recognize this entry")]
-    UnrecognizedRegionEntry,
-    #[error("Failed to write header {0}")]
-    WriteHeader(#[source] io::Error),
-}
-
-pub type Result<T> = std::result::Result<T, VhdxHeaderError>;
-
-#[derive(Clone, Debug)]
-pub struct FileTypeIdentifier {
-    pub _signature: u64,
-}
-
-impl FileTypeIdentifier {
-    /// Reads the File Type Identifier structure from a reference VHDx file
-    pub fn new(f: &mut File) -> Result<FileTypeIdentifier> {
-        f.seek(SeekFrom::Start(FILE_START))
-            .map_err(VhdxHeaderError::SeekFileTypeIdentifier)?;
-        let _signature = f
-            .read_u64::<LittleEndian>()
-            .map_err(VhdxHeaderError::ReadFileTypeIdentifier)?;
-        if _signature != VHDX_SIGN {
-            return Err(VhdxHeaderError::InvalidVHDXSign);
-        }
-
-        Ok(FileTypeIdentifier { _signature })
-    }
-}
-
-#[repr(packed)]
-#[derive(Clone, Copy, Debug)]
-pub struct Header {
-    pub signature: u32,
-    pub checksum: u32,
-    pub sequence_number: u64,
-    pub file_write_guid: u128,
-    pub data_write_guid: u128,
-    pub log_guid: u128,
-    pub log_version: u16,
-    pub version: u16,
-    pub log_length: u32,
-    pub log_offset: u64,
-}
-
-impl Header {
-    /// Reads the Header structure from a reference VHDx file
-    pub fn new(f: &mut File, start: u64) -> Result<Header> {
-        // Read the whole header into a buffer. We will need it for
-        // calculating checksum.
-        let mut buffer = [0; HEADER_SIZE as usize];
-        f.seek(SeekFrom::Start(start))
-            .map_err(VhdxHeaderError::SeekHeader)?;
-        f.read_exact(&mut buffer)
-            .map_err(VhdxHeaderError::ReadHeader)?;
-
-        // SAFETY: buffer is of correct size and has been successfully filled.
-        let header = unsafe { *(buffer.as_ptr() as *mut Header) };
-        if header.signature != HEADER_SIGN {
-            return Err(VhdxHeaderError::InvalidHeaderSign);
-        }
-
-        let new_checksum = calculate_checksum(&mut buffer, size_of::<u32>())?;
-        if header.checksum != new_checksum {
-            return Err(VhdxHeaderError::InvalidChecksum(String::from("Header")));
-        }
-
-        Ok(header)
-    }
-
-    /// Converts the header structure into a buffer
-    fn get_header_as_buffer(&self, buffer: &mut [u8; HEADER_SIZE as usize]) {
-        // SAFETY: self is a valid header.
-        let reference = unsafe {
-            std::slice::from_raw_parts(self as *const Header as *const u8, HEADER_SIZE as usize)
-        };
-        *buffer = reference.try_into().unwrap();
-    }
-
-    /// Creates and returns new updated header from the provided current header
-    pub fn update_header(
-        f: &mut File,
-        current_header: &Header,
-        change_data_guid: bool,
-        mut file_write_guid: u128,
-        start: u64,
-    ) -> Result<Header> {
-        let mut buffer = [0u8; HEADER_SIZE as usize];
-        let mut data_write_guid = current_header.data_write_guid;
-
-        if change_data_guid {
-            data_write_guid = Uuid::new_v4().as_u128();
-        }
-
-        if file_write_guid == 0 {
-            file_write_guid = current_header.file_write_guid;
-        }
-
-        let mut new_header = Header {
-            signature: current_header.signature,
-            checksum: 0,
-            sequence_number: current_header.sequence_number + 1,
-            file_write_guid,
-            data_write_guid,
-            log_guid: current_header.log_guid,
-            log_version: current_header.log_version,
-            version: current_header.version,
-            log_length: current_header.log_length,
-            log_offset: current_header.log_offset,
-        };
-
-        new_header.get_header_as_buffer(&mut buffer);
-        let mut crc = crc_any::CRC::crc32c();
-        crc.digest(&buffer);
-        new_header.checksum = crc.get_crc() as u32;
-        new_header.get_header_as_buffer(&mut buffer);
-
-        f.seek(SeekFrom::Start(start))
-            .map_err(VhdxHeaderError::SeekHeader)?;
-        f.write(&buffer).map_err(VhdxHeaderError::WriteHeader)?;
-
-        Ok(new_header)
-    }
-}
-
-#[repr(packed)]
-#[derive(Clone, Copy, Debug)]
-struct RegionTableHeader {
-    pub signature: u32,
-    pub checksum: u32,
-    pub entry_count: u32,
-    pub reserved: u32,
-}
-
-impl RegionTableHeader {
-    /// Reads the Region Table Header structure from a reference VHDx file
-    pub fn new(f: &mut File, start: u64) -> Result<RegionTableHeader> {
-        // Read the whole header into a buffer. We will need it for calculating
-        // checksum.
-        let mut buffer = [0u8; REGION_SIZE as usize];
-        f.seek(SeekFrom::Start(start))
-            .map_err(VhdxHeaderError::SeekRegionTableHeader)?;
-        f.read_exact(&mut buffer)
-            .map_err(VhdxHeaderError::ReadRegionTableHeader)?;
-
-        // SAFETY: buffer is of correct size and has been successfully filled.
-        let region_table_header = unsafe { *(buffer.as_ptr() as *mut RegionTableHeader) };
-        if region_table_header.signature != REGION_SIGN {
-            return Err(VhdxHeaderError::InvalidRegionSign);
-        }
-
-        let new_checksum = calculate_checksum(&mut buffer, size_of::<u32>())?;
-        if region_table_header.checksum != new_checksum {
-            return Err(VhdxHeaderError::InvalidChecksum(String::from("Region")));
-        }
-
-        if region_table_header.entry_count > 2047 {
-            return Err(VhdxHeaderError::InvalidEntryCount);
-        }
-
-        if region_table_header.reserved != 0 {
-            return Err(VhdxHeaderError::ReservedIsNonZero);
-        }
-
-        Ok(region_table_header)
-    }
-}
-
-pub struct RegionInfo {
-    pub bat_entry: RegionTableEntry,
-    pub mdr_entry: RegionTableEntry,
-    pub region_entries: BTreeMap<u64, u64>,
-}
-
-impl RegionInfo {
-    /// Collect all entries in a BTreeMap from the Region Table and identifies
-    /// BAT and metadata regions
-    pub fn new(f: &mut File, region_start: u64, entry_count: u32) -> Result<RegionInfo> {
-        let mut bat_entry: Option<RegionTableEntry> = None;
-        let mut mdr_entry: Option<RegionTableEntry> = None;
-
-        let mut offset = 0;
-        let mut region_entries = BTreeMap::new();
-
-        let mut buffer = [0; REGION_SIZE as usize];
-        // Seek after the Region Table Header
-        f.seek(SeekFrom::Start(
-            region_start + size_of::<RegionTableHeader>() as u64,
-        ))
-        .map_err(VhdxHeaderError::SeekRegionTableEntries)?;
-        f.read_exact(&mut buffer)
-            .map_err(VhdxHeaderError::ReadRegionTableEntries)?;
-
-        for _ in 0..entry_count {
-            let entry =
-                RegionTableEntry::new(&buffer[offset..offset + size_of::<RegionTableEntry>()])?;
-
-            offset += size_of::<RegionTableEntry>();
-            let start = entry.file_offset;
-            let end = start + entry.length as u64;
-
-            for (region_ent_start, region_ent_end) in region_entries.iter() {
-                if !((start >= *region_ent_start) || (end <= *region_ent_end)) {
-                    return Err(VhdxHeaderError::RegionOverlap);
-                }
-            }
-
-            region_entries.insert(entry.file_offset, entry.file_offset + entry.length as u64);
-
-            if entry.guid == Uuid::parse_str(BAT_GUID).map_err(VhdxHeaderError::InvalidUuid)? {
-                if bat_entry.is_none() {
-                    bat_entry = Some(entry);
-                    continue;
-                }
-                return Err(VhdxHeaderError::DuplicateBATEntry);
-            }
-
-            if entry.guid == Uuid::parse_str(MDR_GUID).map_err(VhdxHeaderError::InvalidUuid)? {
-                if mdr_entry.is_none() {
-                    mdr_entry = Some(entry);
-                    continue;
-                }
-                return Err(VhdxHeaderError::DuplicateMDREntry);
-            }
-
-            if (entry.required & REGION_ENTRY_REQUIRED) == 1 {
-                // This implementation doesn't recognize this field.
-                // Therefore, according to the spec, we are throwing an error.
-                return Err(VhdxHeaderError::UnrecognizedRegionEntry);
-            }
-        }
-
-        if bat_entry.is_none() || mdr_entry.is_none() {
-            region_entries.clear();
-            return Err(VhdxHeaderError::RegionEntryCollectionFailed);
-        }
-
-        // It's safe to unwrap as we checked both entries have been filled.
-        // Otherwise, an error is already returned.
-        let bat_entry = bat_entry.unwrap();
-        let mdr_entry = mdr_entry.unwrap();
-
-        Ok(RegionInfo {
-            bat_entry,
-            mdr_entry,
-            region_entries,
-        })
-    }
-}
-
-#[repr(packed)]
-#[derive(Clone, Copy, Debug)]
-pub struct RegionTableEntry {
-    pub guid: Uuid,
-    pub file_offset: u64,
-    pub length: u32,
-    pub required: u32,
-}
-
-impl RegionTableEntry {
-    /// Reads one Region Entry from a Region Table index that starts from 0
-    pub fn new(buffer: &[u8]) -> Result<RegionTableEntry> {
-        assert!(buffer.len() == std::mem::size_of::<RegionTableEntry>());
-        // SAFETY: the assertion above makes sure the buffer size is correct.
-        let mut region_table_entry = unsafe { *(buffer.as_ptr() as *mut RegionTableEntry) };
-
-        let uuid = crate::vhdx::uuid_from_guid(buffer);
-        region_table_entry.guid = uuid;
-
-        Ok(region_table_entry)
-    }
-}
-
-enum HeaderNo {
-    First,
-    Second,
-}
-
-/// Contains the information from the header of a VHDx file
-#[derive(Clone, Debug)]
-pub struct VhdxHeader {
-    _file_type_identifier: FileTypeIdentifier,
-    header_1: Header,
-    header_2: Header,
-    region_table_1: RegionTableHeader,
-    _region_table_2: RegionTableHeader,
-}
-
-impl VhdxHeader {
-    /// Creates a VhdxHeader from a reference to a file
-    pub fn new(f: &mut File) -> Result<VhdxHeader> {
-        let _file_type_identifier: FileTypeIdentifier = FileTypeIdentifier::new(f)?;
-        let header_1 = Header::new(f, HEADER_1_START);
-        let header_2 = Header::new(f, HEADER_2_START);
-
-        let mut file_write_guid: u128 = 0;
-        let metadata = f.metadata().map_err(VhdxHeaderError::ReadMetadata)?;
-        if !metadata.permissions().readonly() {
-            file_write_guid = Uuid::new_v4().as_u128();
-        }
-
-        let (header_1, header_2) =
-            VhdxHeader::update_headers(f, header_1, header_2, file_write_guid)?;
-        Ok(VhdxHeader {
-            _file_type_identifier,
-            header_1,
-            header_2,
-            region_table_1: RegionTableHeader::new(f, REGION_TABLE_1_START)?,
-            _region_table_2: RegionTableHeader::new(f, REGION_TABLE_2_START)?,
-        })
-    }
-
-    /// Identify the current header and return both headers along with an
-    /// integer indicating the current header.
-    fn current_header(
-        header_1: Result<Header>,
-        header_2: Result<Header>,
-    ) -> Result<(HeaderNo, Header)> {
-        let header_1 = header_1.ok();
-        let header_2 = header_2.ok();
-
-        match (header_1, header_2) {
-            (None, None) => Err(VhdxHeaderError::NoValidHeader),
-            (Some(header_1), None) => Ok((HeaderNo::First, header_1)),
-            (None, Some(header_2)) => Ok((HeaderNo::Second, header_2)),
-            (Some(header_1), Some(header_2)) => {
-                if header_1.sequence_number >= header_2.sequence_number {
-                    Ok((HeaderNo::First, header_1))
-                } else {
-                    Ok((HeaderNo::Second, header_2))
-                }
-            }
-        }
-    }
-
-    /// This takes two headers and update the noncurrent header with the
-    /// current one. Returns both headers as a tuple sequenced the way it was
-    /// received from the parameter list.
-    fn update_header(
-        f: &mut File,
-        header_1: Result<Header>,
-        header_2: Result<Header>,
-        guid: u128,
-    ) -> Result<(Header, Header)> {
-        let (header_no, current_header) = VhdxHeader::current_header(header_1, header_2)?;
-
-        match header_no {
-            HeaderNo::First => {
-                let other_header =
-                    Header::update_header(f, &current_header, true, guid, HEADER_2_START)?;
-                Ok((current_header, other_header))
-            }
-            HeaderNo::Second => {
-                let other_header =
-                    Header::update_header(f, &current_header, true, guid, HEADER_1_START)?;
-                Ok((other_header, current_header))
-            }
-        }
-    }
-
-    // Update the provided headers according to the spec
-    fn update_headers(
-        f: &mut File,
-        header_1: Result<Header>,
-        header_2: Result<Header>,
-        guid: u128,
-    ) -> Result<(Header, Header)> {
-        // According to the spec, update twice
-        let (header_1, header_2) = VhdxHeader::update_header(f, header_1, header_2, guid)?;
-        VhdxHeader::update_header(f, Ok(header_1), Ok(header_2), guid)
-    }
-
-    pub fn update(&mut self, f: &mut File) -> Result<()> {
-        let headers = VhdxHeader::update_headers(f, Ok(self.header_1), Ok(self.header_2), 0)?;
-        self.header_1 = headers.0;
-        self.header_2 = headers.1;
-        Ok(())
-    }
-
-    pub fn region_entry_count(&self) -> u32 {
-        self.region_table_1.entry_count
-    }
-}
-
-/// Calculates the checksum of a buffer that itself contains its checksum
-/// Therefore, before calculating, the existing checksum is retrieved and the
-/// corresponding field is made zero. After the calculation, the existing checksum
-/// is put back to the buffer.
-pub fn calculate_checksum(buffer: &mut [u8], csum_offset: usize) -> Result<u32> {
-    // Read the checksum into a mutable slice
-    let csum_buf = &mut buffer[csum_offset..csum_offset + 4];
-    // Convert the checksum chunk into a u32 integer
-    let orig_csum = LittleEndian::read_u32(csum_buf);
-    // Zero the checksum in the buffer
-    LittleEndian::write_u32(csum_buf, 0);
-    // Calculate the checksum on the resulting buffer
-    let mut crc = crc_any::CRC::crc32c();
-    crc.digest(&buffer);
-    let new_csum = crc.get_crc() as u32;
-
-    // Put back the original checksum in the buffer
-    LittleEndian::write_u32(&mut buffer[csum_offset..csum_offset + 4], orig_csum);
-
-    Ok(new_csum)
-}

block/src/vhdx/vhdx_io.rs

@@ -1,226 +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> {
-    let mut read_count: usize = 0;
-
-    while sector_count > 0 {
-        if disk_spec.has_parent {
-            return Err(VhdxIoError::UnsupportedMode);
-        } else {
-            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> {
-    let mut write_count: usize = 0;
-
-    while sector_count > 0 {
-        if disk_spec.has_parent {
-            return Err(VhdxIoError::UnsupportedMode);
-        } else {
-            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/src/vhdx/vhdx_metadata.rs

@@ -1,325 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-
-use std::fs::File;
-use std::io::{self, Read, Seek, SeekFrom};
-use std::mem::size_of;
-
-use byteorder::{LittleEndian, ReadBytesExt};
-use remain::sorted;
-use thiserror::Error;
-use uuid::Uuid;
-
-use crate::vhdx::vhdx_header::RegionTableEntry;
-
-const METADATA_SIGN: u64 = 0x6174_6164_6174_656D;
-const METADATA_ENTRY_SIZE: usize = 32;
-const METADATA_MAX_ENTRIES: u16 = 2047;
-// The size including the table header and entries
-const METADATA_TABLE_MAX_SIZE: usize = METADATA_ENTRY_SIZE * (METADATA_MAX_ENTRIES as usize + 1);
-
-const METADATA_FLAGS_IS_REQUIRED: u32 = 0x04;
-
-pub const BLOCK_SIZE_MIN: u32 = 1 << 20; // 1 MiB
-const BLOCK_SIZE_MAX: u32 = 256 << 20; // 256 MiB
-const MAX_SECTORS_PER_BLOCK: u64 = 1 << 23;
-
-const BLOCK_HAS_PARENT: u32 = 0x02; // Has a parent or a backing file
-
-// GUID for known metadata items
-const METADATA_FILE_PARAMETER: &str = "CAA16737-FA36-4D43-B3B6-33F0AA44E76B";
-const METADATA_VIRTUAL_DISK_SIZE: &str = "2FA54224-CD1B-4876-B211-5DBED83BF4B8";
-const METADATA_VIRTUAL_DISK_ID: &str = "BECA12AB-B2E6-4523-93EF-C309E000C746";
-const METADATA_LOGICAL_SECTOR_SIZE: &str = "8141BF1D-A96F-4709-BA47-F233A8FAAB5F";
-const METADATA_PHYSICAL_SECTOR_SIZE: &str = "CDA348C7-445D-4471-9CC9-E9885251C556";
-const METADATA_PARENT_LOCATOR: &str = "A8D35F2D-B30B-454D-ABF7-D3D84834AB0C";
-
-const METADATA_FILE_PARAMETER_PRESENT: u16 = 0x01;
-const METADATA_VIRTUAL_DISK_SIZE_PRESENT: u16 = 0x02;
-const METADATA_VIRTUAL_DISK_ID_PRESENT: u16 = 0x04;
-const METADATA_LOGICAL_SECTOR_SIZE_PRESENT: u16 = 0x08;
-const METADATA_PHYSICAL_SECTOR_SIZE_PRESENT: u16 = 0x10;
-const METADATA_PARENT_LOCATOR_PRESENT: u16 = 0x20;
-
-const METADATA_ALL_PRESENT: u16 = METADATA_FILE_PARAMETER_PRESENT
-    | METADATA_VIRTUAL_DISK_SIZE_PRESENT
-    | METADATA_VIRTUAL_DISK_ID_PRESENT
-    | METADATA_LOGICAL_SECTOR_SIZE_PRESENT
-    | METADATA_PHYSICAL_SECTOR_SIZE_PRESENT;
-
-const METADATA_LENGTH_MAX: u32 = 1 << 20; // 1 MiB
-
-#[sorted]
-#[derive(Error, Debug)]
-pub enum VhdxMetadataError {
-    #[error("Invalid block size count")]
-    InvalidBlockSize,
-    #[error("Invalid metadata entry count")]
-    InvalidEntryCount,
-    #[error("Invalid logical sector size")]
-    InvalidLogicalSectorSize,
-    #[error("Invalid metadata ID")]
-    InvalidMetadataItem,
-    #[error("Invalid metadata length")]
-    InvalidMetadataLength,
-    #[error("Metadata sign doesn't match")]
-    InvalidMetadataSign,
-    #[error("Invalid physical sector size")]
-    InvalidPhysicalSectorSize,
-    #[error("Invalid UUID")]
-    InvalidUuid(#[source] uuid::Error),
-    #[error("Invalid value")]
-    InvalidValue,
-    #[error("Not all required metadata found")]
-    MissingMetadata,
-    #[error("Failed to read metadata headers {0}")]
-    ReadMetadata(#[source] io::Error),
-    #[error("Reserved region has non-zero value")]
-    ReservedIsNonZero,
-    #[error("This implementation doesn't support this metadata flag")]
-    UnsupportedFlag,
-}
-
-pub type Result<T> = std::result::Result<T, VhdxMetadataError>;
-
-#[derive(Default, Clone, Debug)]
-pub struct DiskSpec {
-    pub disk_id: u128,
-    pub image_size: u64,
-    pub block_size: u32,
-    pub has_parent: bool,
-    pub sectors_per_block: u32,
-    pub virtual_disk_size: u64,
-    pub logical_sector_size: u32,
-    pub physical_sector_size: u32,
-    pub chunk_ratio: u64,
-    pub total_sectors: u64,
-}
-
-impl DiskSpec {
-    /// Parse all metadata from the provided file and store info in DiskSpec
-    /// structure.
-    pub fn new(f: &mut File, metadata_region: &RegionTableEntry) -> Result<DiskSpec> {
-        let mut disk_spec = DiskSpec::default();
-        let mut metadata_presence: u16 = 0;
-        let mut offset = 0;
-        let metadata = f.metadata().map_err(VhdxMetadataError::ReadMetadata)?;
-        disk_spec.image_size = metadata.len();
-
-        let mut buffer = [0u8; METADATA_TABLE_MAX_SIZE];
-        f.seek(SeekFrom::Start(metadata_region.file_offset))
-            .map_err(VhdxMetadataError::ReadMetadata)?;
-        f.read_exact(&mut buffer)
-            .map_err(VhdxMetadataError::ReadMetadata)?;
-
-        let metadata_header =
-            MetadataTableHeader::new(&buffer[0..size_of::<MetadataTableHeader>()])?;
-
-        offset += size_of::<MetadataTableHeader>();
-        for _ in 0..metadata_header.entry_count {
-            let metadata_entry =
-                MetadataTableEntry::new(&buffer[offset..offset + size_of::<MetadataTableEntry>()])?;
-
-            f.seek(SeekFrom::Start(
-                metadata_region.file_offset + metadata_entry.offset as u64,
-            ))
-            .map_err(VhdxMetadataError::ReadMetadata)?;
-
-            if metadata_entry.item_id
-                == Uuid::parse_str(METADATA_FILE_PARAMETER)
-                    .map_err(VhdxMetadataError::InvalidUuid)?
-            {
-                disk_spec.block_size = f
-                    .read_u32::<LittleEndian>()
-                    .map_err(VhdxMetadataError::ReadMetadata)?;
-
-                // MUST be at least 1 MiB and not greater than 256 MiB
-                if disk_spec.block_size < BLOCK_SIZE_MIN || disk_spec.block_size > BLOCK_SIZE_MAX {
-                    return Err(VhdxMetadataError::InvalidBlockSize);
-                }
-
-                // MUST be power of 2
-                if !disk_spec.block_size.is_power_of_two() {
-                    return Err(VhdxMetadataError::InvalidBlockSize);
-                }
-
-                let bits = f
-                    .read_u32::<LittleEndian>()
-                    .map_err(VhdxMetadataError::ReadMetadata)?;
-                disk_spec.has_parent = bits & BLOCK_HAS_PARENT != 0;
-
-                metadata_presence |= METADATA_FILE_PARAMETER_PRESENT;
-            } else if metadata_entry.item_id
-                == Uuid::parse_str(METADATA_VIRTUAL_DISK_SIZE)
-                    .map_err(VhdxMetadataError::InvalidUuid)?
-            {
-                disk_spec.virtual_disk_size = f
-                    .read_u64::<LittleEndian>()
-                    .map_err(VhdxMetadataError::ReadMetadata)?;
-
-                metadata_presence |= METADATA_VIRTUAL_DISK_SIZE_PRESENT;
-            } else if metadata_entry.item_id
-                == Uuid::parse_str(METADATA_VIRTUAL_DISK_ID)
-                    .map_err(VhdxMetadataError::InvalidUuid)?
-            {
-                disk_spec.disk_id = f
-                    .read_u128::<LittleEndian>()
-                    .map_err(VhdxMetadataError::ReadMetadata)?;
-
-                metadata_presence |= METADATA_VIRTUAL_DISK_ID_PRESENT;
-            } else if metadata_entry.item_id
-                == Uuid::parse_str(METADATA_LOGICAL_SECTOR_SIZE)
-                    .map_err(VhdxMetadataError::InvalidUuid)?
-            {
-                disk_spec.logical_sector_size = f
-                    .read_u32::<LittleEndian>()
-                    .map_err(VhdxMetadataError::ReadMetadata)?;
-                if !(disk_spec.logical_sector_size == 512 || disk_spec.logical_sector_size == 4096)
-                {
-                    return Err(VhdxMetadataError::InvalidLogicalSectorSize);
-                }
-
-                metadata_presence |= METADATA_LOGICAL_SECTOR_SIZE_PRESENT;
-            } else if metadata_entry.item_id
-                == Uuid::parse_str(METADATA_PHYSICAL_SECTOR_SIZE)
-                    .map_err(VhdxMetadataError::InvalidUuid)?
-            {
-                disk_spec.physical_sector_size = f
-                    .read_u32::<LittleEndian>()
-                    .map_err(VhdxMetadataError::ReadMetadata)?;
-                if !(disk_spec.physical_sector_size == 512
-                    || disk_spec.physical_sector_size == 4096)
-                {
-                    return Err(VhdxMetadataError::InvalidPhysicalSectorSize);
-                }
-
-                metadata_presence |= METADATA_PHYSICAL_SECTOR_SIZE_PRESENT;
-            } else if metadata_entry.item_id
-                == Uuid::parse_str(METADATA_PARENT_LOCATOR)
-                    .map_err(VhdxMetadataError::InvalidUuid)?
-            {
-                metadata_presence |= METADATA_PARENT_LOCATOR_PRESENT;
-            } else {
-                return Err(VhdxMetadataError::InvalidMetadataItem);
-            }
-
-            if (metadata_entry.flag_bits & METADATA_FLAGS_IS_REQUIRED) == 0 {
-                return Err(VhdxMetadataError::UnsupportedFlag);
-            }
-            offset += size_of::<MetadataTableEntry>();
-        }
-
-        // Check if all required metadata are present
-        if metadata_presence != METADATA_ALL_PRESENT {
-            return Err(VhdxMetadataError::MissingMetadata);
-        }
-        // Check if the virtual disk size is a multiple of the logical sector
-        // size.
-        if ((metadata_presence & METADATA_LOGICAL_SECTOR_SIZE_PRESENT) != 0)
-            && (disk_spec.virtual_disk_size % disk_spec.logical_sector_size as u64 != 0)
-        {
-            return Err(VhdxMetadataError::InvalidBlockSize);
-        }
-
-        disk_spec.sectors_per_block =
-            DiskSpec::sectors_per_block(disk_spec.block_size, disk_spec.logical_sector_size)?;
-
-        disk_spec.chunk_ratio =
-            DiskSpec::chunk_ratio(disk_spec.block_size, disk_spec.logical_sector_size)?;
-
-        disk_spec.total_sectors =
-            disk_spec.virtual_disk_size / disk_spec.logical_sector_size as u64;
-
-        Ok(disk_spec)
-    }
-
-    /// Calculates the number of sectors per block
-    fn sectors_per_block(block_size: u32, logical_sector_size: u32) -> Result<u32> {
-        let sectors_per_block = block_size / logical_sector_size;
-
-        if !sectors_per_block.is_power_of_two() {
-            return Err(VhdxMetadataError::InvalidValue);
-        }
-
-        Ok(sectors_per_block)
-    }
-
-    /// Calculate the chunk ratio
-    fn chunk_ratio(block_size: u32, logical_sector_size: u32) -> Result<u64> {
-        let chunk_ratio = (MAX_SECTORS_PER_BLOCK * logical_sector_size as u64) / block_size as u64;
-
-        if !chunk_ratio.is_power_of_two() {
-            return Err(VhdxMetadataError::InvalidValue);
-        }
-
-        Ok(chunk_ratio)
-    }
-}
-
-#[repr(packed)]
-#[derive(Default, Debug, Clone, Copy)]
-struct MetadataTableHeader {
-    signature: u64,
-    reserved: u16,
-    entry_count: u16,
-    _reserved2: [u8; 20],
-}
-
-impl MetadataTableHeader {
-    pub fn new(buffer: &[u8]) -> Result<MetadataTableHeader> {
-        assert!(buffer.len() == std::mem::size_of::<MetadataTableHeader>());
-        // SAFETY: the assertion above makes sure the buffer size is correct.
-        let metadata_table_header = unsafe { *(buffer.as_ptr() as *mut MetadataTableHeader) };
-
-        if metadata_table_header.signature != METADATA_SIGN {
-            return Err(VhdxMetadataError::InvalidMetadataSign);
-        }
-
-        if metadata_table_header.entry_count > METADATA_MAX_ENTRIES {
-            return Err(VhdxMetadataError::InvalidEntryCount);
-        }
-
-        if metadata_table_header.reserved != 0 {
-            return Err(VhdxMetadataError::ReservedIsNonZero);
-        }
-
-        Ok(metadata_table_header)
-    }
-}
-
-#[repr(packed)]
-#[derive(Default, Debug, Clone, Copy)]
-pub struct MetadataTableEntry {
-    item_id: Uuid,
-    offset: u32,
-    length: u32,
-    flag_bits: u32,
-    reserved: u32,
-}
-
-impl MetadataTableEntry {
-    /// Parse one metadata entry from the buffer
-    fn new(buffer: &[u8]) -> Result<MetadataTableEntry> {
-        assert!(buffer.len() == std::mem::size_of::<MetadataTableEntry>());
-        // SAFETY: the assertion above makes sure the buffer size is correct.
-        let mut metadata_table_entry = unsafe { *(buffer.as_ptr() as *mut MetadataTableEntry) };
-
-        let uuid = crate::vhdx::uuid_from_guid(buffer);
-        metadata_table_entry.item_id = uuid;
-
-        if metadata_table_entry.length > METADATA_LENGTH_MAX {
-            return Err(VhdxMetadataError::InvalidMetadataLength);
-        }
-
-        if metadata_table_entry.length == 0 && metadata_table_entry.offset != 0 {
-            return Err(VhdxMetadataError::InvalidMetadataLength);
-        }
-
-        if metadata_table_entry.reserved != 0 {
-            return Err(VhdxMetadataError::ReservedIsNonZero);
-        }
-
-        Ok(metadata_table_entry)
-    }
-}

block/src/vhdx_sync.rs

@@ -1,105 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-
-use std::collections::VecDeque;
-use std::fs::File;
-use std::sync::{Arc, Mutex, MutexGuard};
-
-use vmm_sys_util::eventfd::EventFd;
-
-use crate::async_io::{AsyncIo, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult};
-use crate::vhdx::{Result as VhdxResult, Vhdx};
-use crate::AsyncAdaptor;
-
-pub struct VhdxDiskSync {
-    vhdx_file: Arc<Mutex<Vhdx>>,
-}
-
-impl VhdxDiskSync {
-    pub fn new(f: File) -> VhdxResult<Self> {
-        Ok(VhdxDiskSync {
-            vhdx_file: Arc::new(Mutex::new(Vhdx::new(f)?)),
-        })
-    }
-}
-
-impl DiskFile for VhdxDiskSync {
-    fn size(&mut self) -> DiskFileResult<u64> {
-        Ok(self.vhdx_file.lock().unwrap().virtual_disk_size())
-    }
-
-    fn new_async_io(&self, _ring_depth: u32) -> DiskFileResult<Box<dyn AsyncIo>> {
-        Ok(
-            Box::new(VhdxSync::new(self.vhdx_file.clone()).map_err(DiskFileError::NewAsyncIo)?)
-                as Box<dyn AsyncIo>,
-        )
-    }
-}
-
-pub struct VhdxSync {
-    vhdx_file: Arc<Mutex<Vhdx>>,
-    eventfd: EventFd,
-    completion_list: VecDeque<(u64, i32)>,
-}
-
-impl VhdxSync {
-    pub fn new(vhdx_file: Arc<Mutex<Vhdx>>) -> std::io::Result<Self> {
-        Ok(VhdxSync {
-            vhdx_file,
-            eventfd: EventFd::new(libc::EFD_NONBLOCK)?,
-            completion_list: VecDeque::new(),
-        })
-    }
-}
-
-impl AsyncAdaptor<Vhdx> for Arc<Mutex<Vhdx>> {
-    fn file(&mut self) -> MutexGuard<Vhdx> {
-        self.lock().unwrap()
-    }
-}
-
-impl AsyncIo for VhdxSync {
-    fn notifier(&self) -> &EventFd {
-        &self.eventfd
-    }
-
-    fn read_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        self.vhdx_file.read_vectored_sync(
-            offset,
-            iovecs,
-            user_data,
-            &self.eventfd,
-            &mut self.completion_list,
-        )
-    }
-
-    fn write_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: &[libc::iovec],
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        self.vhdx_file.write_vectored_sync(
-            offset,
-            iovecs,
-            user_data,
-            &self.eventfd,
-            &mut self.completion_list,
-        )
-    }
-
-    fn fsync(&mut self, user_data: Option<u64>) -> AsyncIoResult<()> {
-        self.vhdx_file
-            .fsync_sync(user_data, &self.eventfd, &mut self.completion_list)
-    }
-
-    fn next_completed_request(&mut self) -> Option<(u64, i32)> {
-        self.completion_list.pop_front()
-    }
-}

build.rs

@@ -1,24 +0,0 @@
-// Copyright © 2020 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-//
-
-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() {
-        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.
-    // Particularly, this is used from src/main.rs to display the exact
-    // version.
-    println!("cargo:rustc-env=BUILD_VERSION={version}");
-}

devices/Cargo.toml

@@ -1,37 +1,22 @@
 [package]
-authors = ["The Chromium OS Authors"]
-edition = "2021"
 name = "devices"
 version = "0.1.0"
+authors = ["The Chromium OS Authors"]
 
 [dependencies]
-acpi_tables = { workspace = true }
-anyhow = "1.0.87"
-arch = { path = "../arch" }
-bitflags = "2.6.0"
-byteorder = "1.5.0"
-event_monitor = { path = "../event_monitor" }
-hypervisor = { path = "../hypervisor" }
-libc = "0.2.158"
-log = "0.4.22"
-num_enum = "0.7.2"
-pci = { path = "../pci" }
-serde = { version = "1.0.208", features = ["derive"] }
-thiserror = "1.0.62"
-tpm = { path = "../tpm" }
-vm-allocator = { path = "../vm-allocator" }
+bitflags = "1.2.1"
+byteorder = "1.3.4"
+epoll = "4.1.0"
+libc = "0.2.66"
+log = "0.4.8"
 vm-device = { path = "../vm-device" }
-vm-memory = { workspace = true, features = [
-  "backend-atomic",
-  "backend-bitmap",
-  "backend-mmap",
-] }
-vm-migration = { path = "../vm-migration" }
-vmm-sys-util = { workspace = true }
+vm-memory = { git = "https://github.com/rust-vmm/vm-memory" }
+vmm-sys-util = "0.4.0"
 
-[target.'cfg(target_arch = "aarch64")'.dependencies]
-arch = { path = "../arch" }
+[dev-dependencies]
+tempfile = "3.1.0"
 
 [features]
 default = []
-pvmemcontrol = []
+acpi = []
+cmos = []

devices/src/acpi.rs

@@ -3,39 +3,24 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
-use std::sync::atomic::{AtomicBool, Ordering};
-use std::sync::{Arc, Barrier};
-use std::thread;
-use std::time::Instant;
-
-use acpi_tables::{aml, Aml, AmlSink};
+use std::sync::Arc;
 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;
+use BusDevice;
+use HotPlugNotificationFlags;
 
 /// 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,
         }
     }
 }
@@ -44,69 +29,51 @@ impl AcpiShutdownDevice {
 impl BusDevice for AcpiShutdownDevice {
     // Spec has all fields as zero
     fn read(&mut self, _base: u64, _offset: u64, data: &mut [u8]) {
-        data.fill(0)
+        for i in data.iter_mut() {
+            *i = 0;
+        }
     }
 
-    fn write(&mut self, _base: u64, _offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
+    fn write(&mut self, _base: u64, _offset: u64, data: &[u8]) {
         if data[0] == 1 {
-            info!("ACPI Reboot signalled");
+            debug!("ACPI Reboot signalled");
             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;
         const SLEEP_STATUS_EN_BIT: u8 = 5;
         const SLEEP_VALUE_BIT: u8 = 2;
         if data[0] == (S5_SLEEP_VALUE << SLEEP_VALUE_BIT) | (1 << SLEEP_STATUS_EN_BIT) {
-            info!("ACPI Shutdown signalled");
+            debug!("ACPI Shutdown signalled");
+            extern crate bitflags;
             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
     }
 }
 
 /// A device for handling ACPI GED event generation
-pub struct AcpiGedDevice {
-    interrupt: Arc<dyn InterruptSourceGroup>,
-    notification_type: AcpiNotificationFlags,
+pub struct AcpiGEDDevice {
+    interrupt: Arc<Box<dyn InterruptSourceGroup>>,
+    notification_type: HotPlugNotificationFlags,
     ged_irq: u32,
-    address: GuestAddress,
 }
 
-impl AcpiGedDevice {
-    pub fn new(
-        interrupt: Arc<dyn InterruptSourceGroup>,
-        ged_irq: u32,
-        address: GuestAddress,
-    ) -> AcpiGedDevice {
-        AcpiGedDevice {
+impl AcpiGEDDevice {
+    pub fn new(interrupt: Arc<Box<dyn InterruptSourceGroup>>, ged_irq: u32) -> AcpiGEDDevice {
+        AcpiGEDDevice {
             interrupt,
-            notification_type: AcpiNotificationFlags::NO_DEVICES_CHANGED,
+            notification_type: HotPlugNotificationFlags::NO_DEVICES_CHANGED,
             ged_irq,
-            address,
         }
     }
 
     pub fn notify(
         &mut self,
-        notification_type: AcpiNotificationFlags,
+        notification_type: HotPlugNotificationFlags,
     ) -> Result<(), std::io::Error> {
         self.notification_type |= notification_type;
         self.interrupt.trigger(0)
@@ -118,139 +85,12 @@ impl AcpiGedDevice {
 }
 
 // I/O port reports what type of notification was made
-impl BusDevice for AcpiGedDevice {
+impl BusDevice for AcpiGEDDevice {
     // Spec has all fields as zero
     fn read(&mut self, _base: u64, _offset: u64, data: &mut [u8]) {
         data[0] = self.notification_type.bits();
-        self.notification_type = AcpiNotificationFlags::NO_DEVICES_CHANGED;
-    }
-}
-
-impl Aml for AcpiGedDevice {
-    fn to_aml_bytes(&self, sink: &mut dyn AmlSink) {
-        aml::Device::new(
-            "_SB_.GEC_".into(),
-            vec![
-                &aml::Name::new("_HID".into(), &aml::EISAName::new("PNP0A06")),
-                &aml::Name::new("_UID".into(), &"Generic Event Controller"),
-                &aml::Name::new(
-                    "_CRS".into(),
-                    &aml::ResourceTemplate::new(vec![&aml::AddressSpace::new_memory(
-                        aml::AddressSpaceCacheable::NotCacheable,
-                        true,
-                        self.address.0,
-                        self.address.0 + GED_DEVICE_ACPI_SIZE as u64 - 1,
-                        None,
-                    )]),
-                ),
-                &aml::OpRegion::new(
-                    "GDST".into(),
-                    aml::OpRegionSpace::SystemMemory,
-                    &(self.address.0 as usize),
-                    &GED_DEVICE_ACPI_SIZE,
-                ),
-                &aml::Field::new(
-                    "GDST".into(),
-                    aml::FieldAccessType::Byte,
-                    aml::FieldLockRule::NoLock,
-                    aml::FieldUpdateRule::WriteAsZeroes,
-                    vec![aml::FieldEntry::Named(*b"GDAT", 8)],
-                ),
-                &aml::Method::new(
-                    "ESCN".into(),
-                    0,
-                    true,
-                    vec![
-                        &aml::Store::new(&aml::Local(0), &aml::Path::new("GDAT")),
-                        &aml::And::new(&aml::Local(1), &aml::Local(0), &aml::ONE),
-                        &aml::If::new(
-                            &aml::Equal::new(&aml::Local(1), &aml::ONE),
-                            vec![&aml::MethodCall::new("\\_SB_.CPUS.CSCN".into(), vec![])],
-                        ),
-                        &aml::And::new(&aml::Local(1), &aml::Local(0), &2usize),
-                        &aml::If::new(
-                            &aml::Equal::new(&aml::Local(1), &2usize),
-                            vec![&aml::MethodCall::new("\\_SB_.MHPC.MSCN".into(), vec![])],
-                        ),
-                        &aml::And::new(&aml::Local(1), &aml::Local(0), &4usize),
-                        &aml::If::new(
-                            &aml::Equal::new(&aml::Local(1), &4usize),
-                            vec![&aml::MethodCall::new("\\_SB_.PHPR.PSCN".into(), vec![])],
-                        ),
-                        &aml::And::new(&aml::Local(1), &aml::Local(0), &8usize),
-                        &aml::If::new(
-                            &aml::Equal::new(&aml::Local(1), &8usize),
-                            vec![&aml::Notify::new(
-                                &aml::Path::new("\\_SB_.PWRB"),
-                                &0x80usize,
-                            )],
-                        ),
-                    ],
-                ),
-            ],
-        )
-        .to_aml_bytes(sink);
-        aml::Device::new(
-            "_SB_.GED_".into(),
-            vec![
-                &aml::Name::new("_HID".into(), &"ACPI0013"),
-                &aml::Name::new("_UID".into(), &aml::ZERO),
-                &aml::Name::new(
-                    "_CRS".into(),
-                    &aml::ResourceTemplate::new(vec![&aml::Interrupt::new(
-                        true,
-                        true,
-                        false,
-                        false,
-                        self.ged_irq,
-                    )]),
-                ),
-                &aml::Method::new(
-                    "_EVT".into(),
-                    1,
-                    true,
-                    vec![&aml::MethodCall::new("\\_SB_.GEC_.ESCN".into(), vec![])],
-                ),
-            ],
-        )
-        .to_aml_bytes(sink)
-    }
-}
-
-pub struct AcpiPmTimerDevice {
-    start: Instant,
-}
-
-impl AcpiPmTimerDevice {
-    pub fn new() -> Self {
-        Self {
-            start: Instant::now(),
-        }
-    }
-}
-
-impl Default for AcpiPmTimerDevice {
-    fn default() -> Self {
-        Self::new()
-    }
-}
-
-impl BusDevice for AcpiPmTimerDevice {
-    fn read(&mut self, _base: u64, _offset: u64, data: &mut [u8]) {
-        if data.len() != std::mem::size_of::<u32>() {
-            warn!("Invalid sized read of PM timer: {}", data.len());
-            return;
-        }
-        let now = Instant::now();
-        let since = now.duration_since(self.start);
-        let nanos = since.as_nanos();
-
-        const PM_TIMER_FREQUENCY_HZ: u128 = 3_579_545;
-        const NANOS_PER_SECOND: u128 = 1_000_000_000;
-
-        let counter = (nanos * PM_TIMER_FREQUENCY_HZ) / NANOS_PER_SECOND;
-        let counter: u32 = (counter & 0xffff_ffff) as u32;
-
-        data.copy_from_slice(&counter.to_le_bytes());
+        self.notification_type = HotPlugNotificationFlags::NO_DEVICES_CHANGED;
     }
+
+    fn write(&mut self, _base: u64, _offset: u64, _data: &[u8]) {}
 }

devices/src/bus.rs

@@ -7,9 +7,9 @@
 
 //! Handles routing to devices in an address space.
 
-use std::cmp::Ordering;
+use std::cmp::{Ord, Ordering, PartialEq, PartialOrd};
 use std::collections::btree_map::BTreeMap;
-use std::sync::{Arc, Barrier, Mutex, RwLock, Weak};
+use std::sync::{Arc, Mutex, RwLock};
 use std::{convert, error, fmt, io, result};
 
 /// Trait for devices that respond to reads or writes in an arbitrary address space.
@@ -21,34 +21,9 @@ pub trait BusDevice: Send {
     /// Reads at `offset` from this device
     fn read(&mut self, base: u64, offset: u64, data: &mut [u8]) {}
     /// Writes at `offset` into this device
-    fn write(&mut self, base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
-        None
-    }
-}
-
-#[allow(unused_variables)]
-pub trait BusDeviceSync: Send + Sync {
-    /// Reads at `offset` from this device
-    fn read(&self, base: u64, offset: u64, data: &mut [u8]) {}
-    /// Writes at `offset` into this device
-    fn write(&self, base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
-        None
-    }
-}
-
-impl<B: BusDevice> BusDeviceSync for Mutex<B> {
-    /// Reads at `offset` from this device
-    fn read(&self, base: u64, offset: u64, data: &mut [u8]) {
-        self.lock()
-            .expect("Failed to acquire device lock")
-            .read(base, offset, data)
-    }
-    /// Writes at `offset` into this device
-    fn write(&self, base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
-        self.lock()
-            .expect("Failed to acquire device lock")
-            .write(base, offset, data)
-    }
+    fn write(&mut self, base: u64, offset: u64, data: &[u8]) {}
+    /// Triggers the `irq_mask` interrupt on this device
+    fn interrupt(&self, irq_mask: u32) {}
 }
 
 #[derive(Debug)]
@@ -65,7 +40,7 @@ pub type Result<T> = result::Result<T, Error>;
 
 impl fmt::Display for Error {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        write!(f, "bus_error: {self:?}")
+        write!(f, "bus_error: {:?}", self)
     }
 }
 
@@ -110,7 +85,7 @@ impl Ord for BusRange {
 
 impl PartialOrd for BusRange {
     fn partial_cmp(&self, other: &BusRange) -> Option<Ordering> {
-        Some(self.cmp(other))
+        self.base.partial_cmp(&other.base)
     }
 }
 
@@ -120,7 +95,7 @@ impl PartialOrd for BusRange {
 /// only restriction is that no two devices can overlap in this address space.
 #[derive(Default)]
 pub struct Bus {
-    devices: RwLock<BTreeMap<BusRange, Weak<dyn BusDeviceSync>>>,
+    devices: RwLock<BTreeMap<BusRange, Arc<Mutex<dyn BusDevice>>>>,
 }
 
 impl Bus {
@@ -131,16 +106,17 @@ impl Bus {
         }
     }
 
-    fn first_before(&self, addr: u64) -> Option<(BusRange, Arc<dyn BusDeviceSync>)> {
+    fn first_before(&self, addr: u64) -> Option<(BusRange, Arc<Mutex<dyn BusDevice>>)> {
         let devices = self.devices.read().unwrap();
         let (range, dev) = devices
             .range(..=BusRange { base: addr, len: 1 })
-            .next_back()?;
-        dev.upgrade().map(|d| (*range, d.clone()))
+            .rev()
+            .next()?;
+        Some((*range, dev.clone()))
     }
 
     #[allow(clippy::type_complexity)]
-    fn resolve(&self, addr: u64) -> Option<(u64, u64, Arc<dyn BusDeviceSync>)> {
+    pub fn resolve(&self, addr: u64) -> Option<(u64, u64, Arc<Mutex<dyn BusDevice>>)> {
         if let Some((range, dev)) = self.first_before(addr) {
             let offset = addr - range.base;
             if offset < range.len {
@@ -150,7 +126,8 @@ impl Bus {
         None
     }
 
-    pub fn insert(&self, device: Arc<dyn BusDeviceSync>, base: u64, len: u64) -> Result<()> {
+    /// Puts the given device at the given address space.
+    pub fn insert(&self, device: Arc<Mutex<dyn BusDevice>>, base: u64, len: u64) -> Result<()> {
         if len == 0 {
             return Err(Error::ZeroSizedRange);
         }
@@ -170,7 +147,7 @@ impl Bus {
             .devices
             .write()
             .unwrap()
-            .insert(BusRange { base, len }, Arc::downgrade(&device))
+            .insert(BusRange { base, len }, device)
             .is_some()
         {
             return Err(Error::Overlap);
@@ -194,24 +171,6 @@ impl Bus {
         Ok(())
     }
 
-    /// Removes all entries referencing the given device.
-    pub fn remove_by_device(&self, device: &Arc<dyn BusDeviceSync>) -> Result<()> {
-        let mut device_list = self.devices.write().unwrap();
-        let mut remove_key_list = Vec::new();
-
-        for (key, value) in device_list.iter() {
-            if Arc::ptr_eq(&value.upgrade().unwrap(), device) {
-                remove_key_list.push(*key);
-            }
-        }
-
-        for key in remove_key_list.iter() {
-            device_list.remove(key);
-        }
-
-        Ok(())
-    }
-
     /// Updates the address range for an existing device.
     pub fn update_range(
         &self,
@@ -237,25 +196,30 @@ impl Bus {
     /// Reads data from the device that owns the range containing `addr` and puts it into `data`.
     ///
     /// Returns true on success, otherwise `data` is untouched.
-    pub fn read(&self, addr: u64, data: &mut [u8]) -> Result<()> {
+    pub fn read(&self, addr: u64, data: &mut [u8]) -> bool {
         if let Some((base, offset, dev)) = self.resolve(addr) {
             // OK to unwrap as lock() failing is a serious error condition and should panic.
-            dev.read(base, offset, data);
-            Ok(())
+            dev.lock()
+                .expect("Failed to acquire device lock")
+                .read(base, offset, data);
+            true
         } else {
-            Err(Error::MissingAddressRange)
+            false
         }
     }
 
     /// Writes `data` to the device that owns the range containing `addr`.
     ///
     /// Returns true on success, otherwise `data` is untouched.
-    pub fn write(&self, addr: u64, data: &[u8]) -> Result<Option<Arc<Barrier>>> {
+    pub fn write(&self, addr: u64, data: &[u8]) -> bool {
         if let Some((base, offset, dev)) = self.resolve(addr) {
             // OK to unwrap as lock() failing is a serious error condition and should panic.
-            Ok(dev.write(base, offset, data))
+            dev.lock()
+                .expect("Failed to acquire device lock")
+                .write(base, offset, data);
+            true
         } else {
-            Err(Error::MissingAddressRange)
+            false
         }
     }
 }
@@ -265,81 +229,77 @@ mod tests {
     use super::*;
 
     struct DummyDevice;
-    impl BusDeviceSync for DummyDevice {}
+    impl BusDevice for DummyDevice {}
 
     struct ConstantDevice;
-    impl BusDeviceSync for ConstantDevice {
-        fn read(&self, _base: u64, offset: u64, data: &mut [u8]) {
+    impl BusDevice for ConstantDevice {
+        fn read(&mut self, _base: u64, offset: u64, data: &mut [u8]) {
             for (i, v) in data.iter_mut().enumerate() {
                 *v = (offset as u8) + (i as u8);
             }
         }
 
-        fn write(&self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
+        fn write(&mut self, _base: u64, offset: u64, data: &[u8]) {
             for (i, v) in data.iter().enumerate() {
                 assert_eq!(*v, (offset as u8) + (i as u8))
             }
-
-            None
         }
     }
 
     #[test]
     fn bus_insert() {
         let bus = Bus::new();
-        let dummy = Arc::new(DummyDevice);
-        bus.insert(dummy.clone(), 0x10, 0).unwrap_err();
-        bus.insert(dummy.clone(), 0x10, 0x10).unwrap();
+        let dummy = Arc::new(Mutex::new(DummyDevice));
+        assert!(bus.insert(dummy.clone(), 0x10, 0).is_err());
+        assert!(bus.insert(dummy.clone(), 0x10, 0x10).is_ok());
 
         let result = bus.insert(dummy.clone(), 0x0f, 0x10);
-        assert_eq!(format!("{result:?}"), "Err(Overlap)");
+        assert!(result.is_err());
+        assert_eq!(format!("{:?}", result), "Err(Overlap)");
 
-        bus.insert(dummy.clone(), 0x10, 0x10).unwrap_err();
-        bus.insert(dummy.clone(), 0x10, 0x15).unwrap_err();
-        bus.insert(dummy.clone(), 0x12, 0x15).unwrap_err();
-        bus.insert(dummy.clone(), 0x12, 0x01).unwrap_err();
-        bus.insert(dummy.clone(), 0x0, 0x20).unwrap_err();
-        bus.insert(dummy.clone(), 0x20, 0x05).unwrap();
-        bus.insert(dummy.clone(), 0x25, 0x05).unwrap();
-        bus.insert(dummy, 0x0, 0x10).unwrap();
+        assert!(bus.insert(dummy.clone(), 0x10, 0x10).is_err());
+        assert!(bus.insert(dummy.clone(), 0x10, 0x15).is_err());
+        assert!(bus.insert(dummy.clone(), 0x12, 0x15).is_err());
+        assert!(bus.insert(dummy.clone(), 0x12, 0x01).is_err());
+        assert!(bus.insert(dummy.clone(), 0x0, 0x20).is_err());
+        assert!(bus.insert(dummy.clone(), 0x20, 0x05).is_ok());
+        assert!(bus.insert(dummy.clone(), 0x25, 0x05).is_ok());
+        assert!(bus.insert(dummy.clone(), 0x0, 0x10).is_ok());
     }
 
     #[test]
-    #[allow(clippy::redundant_clone)]
     fn bus_read_write() {
         let bus = Bus::new();
-        let dummy = Arc::new(DummyDevice);
-        bus.insert(dummy.clone(), 0x10, 0x10).unwrap();
-        bus.read(0x10, &mut [0, 0, 0, 0]).unwrap();
-        bus.write(0x10, &[0, 0, 0, 0]).unwrap();
-        bus.read(0x11, &mut [0, 0, 0, 0]).unwrap();
-        bus.write(0x11, &[0, 0, 0, 0]).unwrap();
-        bus.read(0x16, &mut [0, 0, 0, 0]).unwrap();
-        bus.write(0x16, &[0, 0, 0, 0]).unwrap();
-        bus.read(0x20, &mut [0, 0, 0, 0]).unwrap_err();
-        bus.write(0x20, &[0, 0, 0, 0]).unwrap_err();
-        bus.read(0x06, &mut [0, 0, 0, 0]).unwrap_err();
-        bus.write(0x06, &[0, 0, 0, 0]).unwrap_err();
+        let dummy = Arc::new(Mutex::new(DummyDevice));
+        assert!(bus.insert(dummy.clone(), 0x10, 0x10).is_ok());
+        assert!(bus.read(0x10, &mut [0, 0, 0, 0]));
+        assert!(bus.write(0x10, &[0, 0, 0, 0]));
+        assert!(bus.read(0x11, &mut [0, 0, 0, 0]));
+        assert!(bus.write(0x11, &[0, 0, 0, 0]));
+        assert!(bus.read(0x16, &mut [0, 0, 0, 0]));
+        assert!(bus.write(0x16, &[0, 0, 0, 0]));
+        assert!(!bus.read(0x20, &mut [0, 0, 0, 0]));
+        assert!(!bus.write(0x20, &mut [0, 0, 0, 0]));
+        assert!(!bus.read(0x06, &mut [0, 0, 0, 0]));
+        assert!(!bus.write(0x06, &mut [0, 0, 0, 0]));
     }
 
     #[test]
-    #[allow(clippy::redundant_clone)]
     fn bus_read_write_values() {
         let bus = Bus::new();
-        let dummy = Arc::new(ConstantDevice);
-        bus.insert(dummy.clone(), 0x10, 0x10).unwrap();
+        let dummy = Arc::new(Mutex::new(ConstantDevice));
+        assert!(bus.insert(dummy.clone(), 0x10, 0x10).is_ok());
 
         let mut values = [0, 1, 2, 3];
-        bus.read(0x10, &mut values).unwrap();
+        assert!(bus.read(0x10, &mut values));
         assert_eq!(values, [0, 1, 2, 3]);
-        bus.write(0x10, &values).unwrap();
-        bus.read(0x15, &mut values).unwrap();
+        assert!(bus.write(0x10, &values));
+        assert!(bus.read(0x15, &mut values));
         assert_eq!(values, [5, 6, 7, 8]);
-        bus.write(0x15, &values).unwrap();
+        assert!(bus.write(0x15, &values));
     }
 
     #[test]
-    #[allow(clippy::redundant_clone)]
     fn busrange_cmp() {
         let range = BusRange { base: 0x10, len: 2 };
         assert_eq!(range, BusRange { base: 0x10, len: 3 });
@@ -352,10 +312,11 @@ mod tests {
 
         let bus = Bus::new();
         let mut data = [1, 2, 3, 4];
-        let device = Arc::new(DummyDevice);
-        bus.insert(device.clone(), 0x10, 0x10).unwrap();
-        bus.write(0x10, &data).unwrap();
-        bus.read(0x10, &mut data).unwrap();
+        assert!(bus
+            .insert(Arc::new(Mutex::new(DummyDevice)), 0x10, 0x10)
+            .is_ok());
+        assert!(bus.write(0x10, &mut data));
+        assert!(bus.read(0x10, &mut data));
         assert_eq!(data, [1, 2, 3, 4]);
     }
 

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

@@ -1,179 +0,0 @@
-// 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 anyhow::anyhow;
-use arch::layout;
-use hypervisor::arch::aarch64::gic::{Vgic, VgicConfig};
-use hypervisor::{CpuState, GicState};
-use vm_device::interrupt::{
-    InterruptIndex, InterruptManager, InterruptSourceConfig, InterruptSourceGroup,
-    LegacyIrqSourceConfig, MsiIrqGroupConfig,
-};
-use vm_memory::address::Address;
-use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, 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;
-pub const GIC_SNAPSHOT_ID: &str = "gic-v3-its";
-
-// Gic (Generic Interrupt 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
-// service.
-pub struct Gic {
-    interrupt_source_group: Arc<dyn InterruptSourceGroup>,
-    // The hypervisor agnostic virtual GIC
-    vgic: Option<Arc<Mutex<dyn Vgic>>>,
-}
-
-impl Gic {
-    pub fn new(
-        vcpu_count: u8,
-        interrupt_manager: Arc<dyn InterruptManager<GroupConfig = MsiIrqGroupConfig>>,
-        vm: Arc<dyn hypervisor::Vm>,
-    ) -> Result<Gic> {
-        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 vgic = vm
-            .create_vgic(Gic::create_default_config(vcpu_count as u64))
-            .map_err(Error::CreateGic)?;
-
-        let gic = Gic {
-            interrupt_source_group,
-            vgic: Some(vgic),
-        };
-        gic.enable()?;
-
-        Ok(gic)
-    }
-
-    pub fn restore_vgic(
-        &mut self,
-        state: Option<GicState>,
-        saved_vcpu_states: &[CpuState],
-    ) -> Result<()> {
-        self.set_gicr_typers(saved_vcpu_states);
-        self.vgic
-            .clone()
-            .unwrap()
-            .lock()
-            .unwrap()
-            .set_state(&state.unwrap())
-            .map_err(Error::RestoreGic)
-    }
-
-    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 GIC
-        //   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) -> VgicConfig {
-        let redists_size = layout::GIC_V3_REDIST_SIZE * vcpu_count;
-        let redists_addr = layout::GIC_V3_DIST_START.raw_value() - redists_size;
-        VgicConfig {
-            vcpu_count,
-            dist_addr: layout::GIC_V3_DIST_START.raw_value(),
-            dist_size: layout::GIC_V3_DIST_SIZE,
-            redists_addr,
-            redists_size,
-            msi_addr: redists_addr - layout::GIC_V3_ITS_SIZE,
-            msi_size: layout::GIC_V3_ITS_SIZE,
-            nr_irqs: layout::IRQ_NUM,
-        }
-    }
-
-    pub fn get_vgic(&mut self) -> Result<Arc<Mutex<dyn Vgic>>> {
-        Ok(self.vgic.clone().unwrap())
-    }
-
-    pub fn set_gicr_typers(&mut self, vcpu_states: &[CpuState]) {
-        let vgic = self.vgic.as_ref().unwrap().clone();
-        vgic.lock().unwrap().set_gicr_typers(vcpu_states);
-    }
-}
-
-impl InterruptController for Gic {
-    // 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 Gic {
-    fn id(&self) -> String {
-        GIC_SNAPSHOT_ID.to_string()
-    }
-
-    fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        let vgic = self.vgic.as_ref().unwrap().clone();
-        let state = vgic.lock().unwrap().state().unwrap();
-        Snapshot::new_from_state(&state)
-    }
-}
-
-impl Pausable for Gic {
-    fn pause(&mut self) -> std::result::Result<(), MigratableError> {
-        // Flush tables to guest RAM
-        let vgic = self.vgic.as_ref().unwrap().clone();
-        vgic.lock().unwrap().save_data_tables().map_err(|e| {
-            MigratableError::Pause(anyhow!(
-                "Could not save GICv3ITS GIC pending tables {:?}",
-                e
-            ))
-        })?;
-        Ok(())
-    }
-}
-impl Transportable for Gic {}
-impl Migratable for Gic {}

devices/src/interrupt_controller.rs

@@ -1,76 +0,0 @@
-// Copyright 2020, ARM Limited.
-//
-// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
-
-use std::{io, result};
-
-use thiserror::Error;
-use vmm_sys_util::eventfd::EventFd;
-
-#[derive(Debug, Error)]
-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: {0}")]
-    CreateInterruptSourceGroup(io::Error),
-    /// Failed triggering the interrupt.
-    #[error("Failed triggering the interrupt: {0}")]
-    TriggerInterrupt(io::Error),
-    /// Failed masking the interrupt.
-    #[error("Failed masking the interrupt: {0}")]
-    MaskInterrupt(io::Error),
-    /// Failed unmasking the interrupt.
-    #[error("Failed unmasking the interrupt: {0}")]
-    UnmaskInterrupt(io::Error),
-    /// Failed updating the interrupt.
-    #[error("Failed updating the interrupt: {0}")]
-    UpdateInterrupt(io::Error),
-    /// Failed enabling the interrupt.
-    #[error("Failed enabling the interrupt: {0}")]
-    EnableInterrupt(io::Error),
-    #[cfg(target_arch = "aarch64")]
-    /// Failed creating GIC device.
-    #[error("Failed creating GIC device: {0}")]
-    CreateGic(hypervisor::HypervisorVmError),
-    #[cfg(target_arch = "aarch64")]
-    /// Failed restoring GIC device.
-    #[error("Failed restoring GIC device: {0}")]
-    RestoreGic(hypervisor::arch::aarch64::gic::Error),
-}
-
-type Result<T> = result::Result<T, Error>;
-
-pub struct MsiMessage {
-    // Message Address Register
-    //   31-20: Base address. Fixed value (0x0FEE)
-    //   19-12: Destination ID
-    //   11-4:  Reserved
-    //   3:     Redirection Hint indication
-    //   2:     Destination Mode
-    //   1-0:   Reserved
-    pub addr: u32,
-    // Message Data Register
-    //   32-16: Reserved
-    //   15:    Trigger Mode. 0 = Edge, 1 = Level
-    //   14:    Level. 0 = Deassert, 1 = Assert
-    //   13-11: Reserved
-    //   10-8:  Delivery Mode
-    //   7-0:   Vector
-    pub data: u32,
-}
-
-// Introduce trait InterruptController to uniform the interrupt
-// service provided for devices.
-// Device manager uses this trait without caring whether it is a
-// IOAPIC (X86) or GIC (Arm).
-pub trait InterruptController: Send {
-    fn service_irq(&mut self, irq: usize) -> Result<()>;
-    #[cfg(target_arch = "x86_64")]
-    fn end_of_interrupt(&mut self, vec: u8);
-    fn notifier(&self, irq: usize) -> Option<EventFd>;
-}

devices/src/ioapic.rs

@@ -9,21 +9,38 @@
 // 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 std::result;
-use std::sync::{Arc, Barrier};
-
+use crate::BusDevice;
 use byteorder::{ByteOrder, LittleEndian};
-use serde::{Deserialize, Serialize};
+use std::io;
+use std::result;
+use std::sync::Arc;
 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 vmm_sys_util::eventfd::EventFd;
 
-use super::interrupt_controller::{Error, InterruptController};
+#[derive(Debug)]
+pub enum Error {
+    /// Invalid destination mode.
+    InvalidDestinationMode,
+    /// Invalid trigger mode.
+    InvalidTriggerMode,
+    /// Invalid delivery mode.
+    InvalidDeliveryMode,
+    /// Failed creating the interrupt source group.
+    CreateInterruptSourceGroup(io::Error),
+    /// Failed triggering the interrupt.
+    TriggerInterrupt(io::Error),
+    /// Failed masking the interrupt.
+    MaskInterrupt(io::Error),
+    /// Failed unmasking the interrupt.
+    UnmaskInterrupt(io::Error),
+    /// Failed updating the interrupt.
+    UpdateInterrupt(io::Error),
+    /// Failed enabling the interrupt.
+    EnableInterrupt(io::Error),
+}
 
 type Result<T> = result::Result<T, Error>;
 
@@ -63,12 +80,10 @@ fn trigger_mode(entry: RedirectionTableEntry) -> u8 {
 fn interrupt_mask(entry: RedirectionTableEntry) -> u8 {
     ((entry >> 16) & 0x1u64) as u8
 }
-fn destination_field(entry: RedirectionTableEntry) -> u8 {
-    // When the destination mode is physical, the destination field should only
-    // be defined through bits 56-59, as defined in the IOAPIC specification.
-    // But from the APIC specification, the APIC ID is always defined on 8 bits
-    // no matter which destination mode is selected. That's why we always
-    // retrieve the destination field based on bits 56-63.
+fn destination_field_physical(entry: RedirectionTableEntry) -> u8 {
+    ((entry >> 56) & 0xfu64) as u8
+}
+fn destination_field_logical(entry: RedirectionTableEntry) -> u8 {
     ((entry >> 56) & 0xffu64) as u8
 }
 fn set_delivery_status(entry: &mut RedirectionTableEntry, val: u8) {
@@ -84,6 +99,25 @@ fn set_remote_irr(entry: &mut RedirectionTableEntry, val: u8) {
     *entry |= u64::from(val & 0x1) << 14;
 }
 
+pub struct MsiMessage {
+    // Message Address Register
+    //   31-20: Base address. Fixed value (0x0FEE)
+    //   19-12: Destination ID
+    //   11-4:  Reserved
+    //   3:     Redirection Hint indication
+    //   2:     Destination Mode
+    //   1-0:   Reserved
+    pub addr: u32,
+    // Message Data Register
+    //   32-16: Reserved
+    //   15:    Trigger Mode. 0 = Edge, 1 = Level
+    //   14:    Level. 0 = Deassert, 1 = Assert
+    //   13-11: Reserved
+    //   10-8:  Delivery Mode
+    //   7-0:   Vector
+    pub data: u32,
+}
+
 pub const NUM_IOAPIC_PINS: usize = 24;
 const IOAPIC_VERSION_ID: u32 = 0x0017_0011;
 
@@ -98,6 +132,12 @@ const IOWIN_OFF: u8 = 0x10;
 const IOWIN_SCALE: u8 = 0x2;
 const REG_MAX_OFFSET: u8 = IOWIN_OFF + (NUM_IOAPIC_PINS as u8 * 2) - 1;
 
+#[repr(u8)]
+enum DestinationMode {
+    Physical = 0,
+    Logical = 1,
+}
+
 #[repr(u8)]
 enum TriggerMode {
     Edge = 0,
@@ -108,9 +148,9 @@ enum TriggerMode {
 enum DeliveryMode {
     Fixed = 0b000,
     Lowest = 0b001,
-    Smi = 0b010,        // System management interrupt
+    SMI = 0b010,        // System management interrupt
     RemoteRead = 0b011, // This is no longer supported by intel.
-    Nmi = 0b100,        // Non maskable interrupt
+    NMI = 0b100,        // Non maskable interrupt
     Init = 0b101,
     Startup = 0b110,
     External = 0b111,
@@ -126,30 +166,16 @@ fn decode_irq_from_selector(selector: u8) -> (usize, bool) {
 }
 
 pub struct Ioapic {
-    id: String,
-    id_reg: u32,
+    id: u32,
     reg_sel: u32,
     reg_entries: [RedirectionTableEntry; NUM_IOAPIC_PINS],
-    used_entries: [bool; NUM_IOAPIC_PINS],
     apic_address: GuestAddress,
-    interrupt_source_group: Arc<dyn InterruptSourceGroup>,
-}
-
-#[derive(Serialize, Deserialize)]
-pub struct IoapicState {
-    id_reg: u32,
-    reg_sel: u32,
-    reg_entries: [RedirectionTableEntry; NUM_IOAPIC_PINS],
-    used_entries: [bool; NUM_IOAPIC_PINS],
-    apic_address: u64,
+    interrupt_source_group: Arc<Box<dyn InterruptSourceGroup>>,
 }
 
 impl BusDevice for Ioapic {
     fn read(&mut self, _base: u64, offset: u64, data: &mut [u8]) {
-        if data.len() != std::mem::size_of::<u32>() {
-            warn!("Invalid read size on IOAPIC: {}", data.len());
-            return;
-        }
+        assert!(data.len() == 4);
 
         debug!("IOAPIC_R @ offset 0x{:x}", offset);
 
@@ -165,11 +191,8 @@ impl BusDevice for Ioapic {
         LittleEndian::write_u32(data, value);
     }
 
-    fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
-        if data.len() != std::mem::size_of::<u32>() {
-            warn!("Invalid write size on IOAPIC: {}", data.len());
-            return None;
-        }
+    fn write(&mut self, _base: u64, offset: u64, data: &[u8]) {
+        assert!(data.len() == 4);
 
         debug!("IOAPIC_W @ offset 0x{:x}", offset);
 
@@ -182,162 +205,77 @@ impl BusDevice for Ioapic {
                 error!("IOAPIC: failed writing at offset {}", offset);
             }
         }
-        None
     }
 }
 
 impl Ioapic {
     pub fn new(
-        id: String,
         apic_address: GuestAddress,
         interrupt_manager: Arc<dyn InterruptManager<GroupConfig = MsiIrqGroupConfig>>,
-        state: Option<IoapicState>,
     ) -> Result<Ioapic> {
         let interrupt_source_group = interrupt_manager
             .create_group(MsiIrqGroupConfig {
-                base: 0,
+                base: 0 as InterruptIndex,
                 count: NUM_IOAPIC_PINS as InterruptIndex,
             })
             .map_err(Error::CreateInterruptSourceGroup)?;
 
-        let (id_reg, reg_sel, reg_entries, used_entries, apic_address) = if let Some(state) = &state
-        {
-            (
-                state.id_reg,
-                state.reg_sel,
-                state.reg_entries,
-                state.used_entries,
-                GuestAddress(state.apic_address),
-            )
-        } else {
-            (
-                0,
-                0,
-                [0x10000; NUM_IOAPIC_PINS],
-                [false; NUM_IOAPIC_PINS],
-                apic_address,
-            )
-        };
+        interrupt_source_group
+            .enable()
+            .map_err(Error::EnableInterrupt)?;
 
-        // The IOAPIC is created with entries already masked. The guest will be
-        // in charge of unmasking them if/when necessary.
-        let ioapic = Ioapic {
-            id,
-            id_reg,
-            reg_sel,
-            reg_entries,
-            used_entries,
+        Ok(Ioapic {
+            id: 0,
+            reg_sel: 0,
+            reg_entries: [0; NUM_IOAPIC_PINS],
             apic_address,
             interrupt_source_group,
-        };
-
-        // When restoring the Ioapic, we must enable used entries.
-        if state.is_some() {
-            for (irq, entry) in ioapic.used_entries.iter().enumerate() {
-                if *entry {
-                    ioapic.update_entry(irq, false)?;
-                }
-            }
-
-            ioapic
-                .interrupt_source_group
-                .set_gsi()
-                .map_err(Error::UpdateInterrupt)?;
-        }
-
-        Ok(ioapic)
+        })
     }
 
-    fn ioapic_write(&mut self, val: u32) {
-        debug!("IOAPIC_W reg 0x{:x}, val 0x{:x}", self.reg_sel, val);
-
-        match self.reg_sel as u8 {
-            IOAPIC_REG_VERSION => {
-                if val == 0 {
-                    // Windows writes zero here (see #1791)
-                } else {
-                    error!(
-                        "IOAPIC: invalid write to version register (0x{:x}): 0x{:x}",
-                        self.reg_sel, val
-                    );
-                }
-            }
-            IOAPIC_REG_ID => self.id_reg = (val >> 24) & 0xf,
-            IOWIN_OFF..=REG_MAX_OFFSET => {
-                let (index, is_high_bits) = decode_irq_from_selector(self.reg_sel as u8);
-                if index > NUM_IOAPIC_PINS {
-                    warn!("IOAPIC index out of range: {}", index);
-                    return;
-                }
-                if is_high_bits {
-                    self.reg_entries[index] &= 0xffff_ffff;
-                    self.reg_entries[index] |= u64::from(val) << 32;
-                } else {
-                    // Ensure not to override read-only bits:
-                    // - Delivery Status (bit 12)
-                    // - Remote IRR (bit 14)
-                    self.reg_entries[index] &= 0xffff_ffff_0000_5000;
-                    self.reg_entries[index] |= u64::from(val) & 0xffff_afff;
-                }
-                // The entry must be updated through the interrupt source
-                // group.
-                if let Err(e) = self.update_entry(index, true) {
-                    error!("Failed updating IOAPIC entry: {:?}", e);
-                }
-                // Store the information this IRQ is now being used.
-                self.used_entries[index] = true;
-            }
-            _ => error!(
-                "IOAPIC: invalid write to register offset 0x{:x}",
-                self.reg_sel
-            ),
-        }
-    }
-
-    fn ioapic_read(&self) -> u32 {
-        debug!("IOAPIC_R reg 0x{:x}", self.reg_sel);
-
-        match self.reg_sel as u8 {
-            IOAPIC_REG_VERSION => IOAPIC_VERSION_ID,
-            IOAPIC_REG_ID | IOAPIC_REG_ARBITRATION_ID => (self.id_reg & 0xf) << 24,
-            IOWIN_OFF..=REG_MAX_OFFSET => {
-                let (index, is_high_bits) = decode_irq_from_selector(self.reg_sel as u8);
-                if index > NUM_IOAPIC_PINS {
-                    warn!("IOAPIC index out of range: {}", index);
-                    return 0;
-                }
-                if is_high_bits {
-                    (self.reg_entries[index] >> 32) as u32
-                } else {
-                    (self.reg_entries[index] & 0xffff_ffff) as u32
-                }
-            }
-            _ => {
-                error!(
-                    "IOAPIC: invalid read from register offset 0x{:x}",
-                    self.reg_sel
-                );
-                0
+    // The ioapic must be informed about EOIs in order to deassert interrupts
+    // already sent.
+    pub fn end_of_interrupt(&mut self, vec: u8) {
+        for i in 0..NUM_IOAPIC_PINS {
+            let entry = &mut self.reg_entries[i];
+            // Clear Remote IRR bit
+            if vector(*entry) == vec && trigger_mode(*entry) == 1 {
+                set_remote_irr(entry, 0);
             }
         }
     }
 
-    fn state(&self) -> IoapicState {
-        IoapicState {
-            id_reg: self.id_reg,
-            reg_sel: self.reg_sel,
-            reg_entries: self.reg_entries,
-            used_entries: self.used_entries,
-            apic_address: self.apic_address.0,
+    // This should be called anytime an interrupt needs to be injected into the
+    // running guest.
+    pub fn service_irq(&mut self, irq: usize) -> Result<()> {
+        let entry = &mut self.reg_entries[irq];
+
+        self.interrupt_source_group
+            .trigger(irq as InterruptIndex)
+            .map_err(Error::TriggerInterrupt)?;
+        debug!("Interrupt successfully delivered");
+
+        // If trigger mode is level sensitive, set the Remote IRR bit.
+        // It will be cleared when the EOI is received.
+        if trigger_mode(*entry) == 1 {
+            set_remote_irr(entry, 1);
         }
+        // Clear the Delivery Status bit
+        set_delivery_status(entry, 0);
+
+        Ok(())
     }
 
-    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
         let destination_mode = destination_mode(entry);
-        let destination_id = destination_field(entry);
+        let destination_id: u8 = match destination_mode {
+            x if x == DestinationMode::Physical as u8 => destination_field_physical(entry),
+            x if x == DestinationMode::Logical as u8 => destination_field_logical(entry),
+            _ => return Err(Error::InvalidDestinationMode),
+        };
 
         // When this bit is set, the message is directed to the processor with
         // the lowest interrupt priority among processors that can receive the
@@ -362,9 +300,9 @@ impl Ioapic {
         match delivery_mode {
             x if (x == DeliveryMode::Fixed as u8)
                 || (x == DeliveryMode::Lowest as u8)
-                || (x == DeliveryMode::Smi as u8)
+                || (x == DeliveryMode::SMI as u8)
                 || (x == DeliveryMode::RemoteRead as u8)
-                || (x == DeliveryMode::Nmi as u8)
+                || (x == DeliveryMode::NMI as u8)
                 || (x == DeliveryMode::Init as u8)
                 || (x == DeliveryMode::Startup as u8)
                 || (x == DeliveryMode::External as u8) => {}
@@ -381,71 +319,70 @@ impl Ioapic {
             high_addr: 0x0,
             low_addr,
             data,
-            devid: 0,
         };
 
         self.interrupt_source_group
-            .update(
-                irq as InterruptIndex,
-                InterruptSourceConfig::MsiIrq(config),
-                interrupt_mask(entry) == 1,
-                set_gsi,
-            )
+            .update(irq as InterruptIndex, InterruptSourceConfig::MsiIrq(config))
             .map_err(Error::UpdateInterrupt)?;
 
+        if interrupt_mask(entry) == 1 {
+            self.interrupt_source_group
+                .mask(irq as InterruptIndex)
+                .map_err(Error::MaskInterrupt)?;
+        } else {
+            self.interrupt_source_group
+                .unmask(irq as InterruptIndex)
+                .map_err(Error::UnmaskInterrupt)?;
+        }
+
         Ok(())
     }
-}
 
-impl InterruptController for Ioapic {
-    // The ioapic must be informed about EOIs in order to deassert interrupts
-    // already sent.
-    fn end_of_interrupt(&mut self, vec: u8) {
-        for i in 0..NUM_IOAPIC_PINS {
-            let entry = &mut self.reg_entries[i];
-            // Clear Remote IRR bit
-            if vector(*entry) == vec && trigger_mode(*entry) == 1 {
-                set_remote_irr(entry, 0);
+    fn ioapic_write(&mut self, val: u32) {
+        debug!("IOAPIC_W reg 0x{:x}, val 0x{:x}", self.reg_sel, val);
+
+        match self.reg_sel as u8 {
+            IOAPIC_REG_ID => self.id = (val >> 24) & 0xf,
+            IOWIN_OFF..=REG_MAX_OFFSET => {
+                let (index, is_high_bits) = decode_irq_from_selector(self.reg_sel as u8);
+                if is_high_bits {
+                    self.reg_entries[index] &= 0xffff_ffff;
+                    self.reg_entries[index] |= u64::from(val) << 32;
+                } else {
+                    // Ensure not to override read-only bits:
+                    // - Delivery Status (bit 12)
+                    // - Remote IRR (bit 14)
+                    self.reg_entries[index] &= 0xffff_ffff_0000_5000;
+                    self.reg_entries[index] |= u64::from(val) & 0xffff_afff;
+                }
+                // The entry must be updated through the interrupt source
+                // group.
+                if let Err(e) = self.update_entry(index) {
+                    error!("Failed updating IOAPIC entry: {:?}", e);
+                }
+            }
+            _ => error!("IOAPIC: invalid write to register offset"),
+        }
+    }
+
+    fn ioapic_read(&self) -> u32 {
+        debug!("IOAPIC_R reg 0x{:x}", self.reg_sel);
+
+        match self.reg_sel as u8 {
+            IOAPIC_REG_VERSION => IOAPIC_VERSION_ID,
+            IOAPIC_REG_ID | IOAPIC_REG_ARBITRATION_ID => (self.id & 0xf) << 24,
+            IOWIN_OFF..=REG_MAX_OFFSET => {
+                let (index, is_high_bits) = decode_irq_from_selector(self.reg_sel as u8);
+                if is_high_bits {
+                    (self.reg_entries[index] >> 32) as u32
+                } else {
+                    (self.reg_entries[index] & 0xffff_ffff) as u32
+                }
+            }
+            _ => {
+                error!("IOAPIC: invalid read from register offset");
+                0
             }
         }
     }
-
-    // This should be called anytime an interrupt needs to be injected into the
-    // running guest.
-    fn service_irq(&mut self, irq: usize) -> Result<()> {
-        let entry = &mut self.reg_entries[irq];
-
-        self.interrupt_source_group
-            .trigger(irq as InterruptIndex)
-            .map_err(Error::TriggerInterrupt)?;
-        debug!("Interrupt {irq} successfully delivered");
-
-        // If trigger mode is level sensitive, set the Remote IRR bit.
-        // It will be cleared when the EOI is received.
-        if trigger_mode(*entry) == 1 {
-            set_remote_irr(entry, 1);
-        }
-        // Clear the Delivery Status bit
-        set_delivery_status(entry, 0);
-
-        Ok(())
-    }
-
-    fn notifier(&self, irq: usize) -> Option<EventFd> {
-        self.interrupt_source_group.notifier(irq as InterruptIndex)
-    }
 }
-
-impl Snapshottable for Ioapic {
-    fn id(&self) -> String {
-        self.id.clone()
-    }
-
-    fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        Snapshot::new_from_state(&self.state())
-    }
-}
-
-impl Pausable for Ioapic {}
-impl Transportable for Ioapic {}
-impl Migratable for Ioapic {}

devices/src/legacy/cmos.rs

@@ -1,20 +1,12 @@
 // 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::{gmtime_r, time, time_t, tm};
 use std::cmp::min;
-use std::sync::atomic::{AtomicBool, Ordering};
-use std::sync::{Arc, Barrier};
-use std::{mem, thread};
+use std::mem;
 
-// https://github.com/rust-lang/libc/issues/1848
-#[cfg_attr(target_env = "musl", allow(deprecated))]
-use libc::time_t;
-use libc::{clock_gettime, gmtime_r, timespec, tm, CLOCK_REALTIME};
-use vm_device::BusDevice;
-use vmm_sys_util::eventfd::EventFd;
+use crate::BusDevice;
 
 const INDEX_MASK: u8 = 0x7f;
 const INDEX_OFFSET: u64 = 0x0;
@@ -25,20 +17,13 @@ const DATA_LEN: usize = 128;
 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) -> Cmos {
         let mut data = [0u8; DATA_LEN];
 
         // Extended memory from 16 MB to 4 GB in units of 64 KB
@@ -55,44 +40,21 @@ impl Cmos {
         data[0x5c] = (high_mem >> 8) as u8;
         data[0x5d] = (high_mem >> 16) as u8;
 
-        Cmos {
-            index: 0,
-            data,
-            reset_evt,
-            vcpus_kill_signalled,
-        }
+        Cmos { index: 0, data }
     }
 }
 
 impl BusDevice for Cmos {
-    fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
+    fn write(&mut self, _base: u64, offset: u64, data: &[u8]) {
         if data.len() != 1 {
-            warn!("Invalid write size on CMOS device: {}", data.len());
-            return None;
+            return;
         }
 
         match offset {
-            INDEX_OFFSET => self.index = data[0],
-            DATA_OFFSET => {
-                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]
-                }
-            }
-            o => warn!("bad write offset on CMOS device: {}", o),
-        };
-        None
+            INDEX_OFFSET => self.index = data[0] & INDEX_MASK,
+            DATA_OFFSET => self.data[self.index as usize] = data[0],
+            o => panic!("bad write offset on CMOS device: {}", o),
+        }
     }
 
     fn read(&mut self, _base: u64, offset: u64, data: &mut [u8]) {
@@ -102,7 +64,6 @@ impl BusDevice for Cmos {
         }
 
         if data.len() != 1 {
-            warn!("Invalid read size on CMOS device: {}", data.len());
             return;
         }
 
@@ -116,19 +77,14 @@ impl BusDevice for Cmos {
                 let day;
                 let month;
                 let year;
-                // SAFETY: The clock_gettime and gmtime_r calls are safe as long as the structs they are
-                // given are large enough, and neither of them fail. It is safe to zero initialize
-                // the tm and timespec struct because it contains only plain data.
-                let update_in_progress = unsafe {
-                    let mut timespec: timespec = mem::zeroed();
-                    clock_gettime(CLOCK_REALTIME, &mut timespec as *mut _);
-
-                    // https://github.com/rust-lang/libc/issues/1848
-                    #[cfg_attr(target_env = "musl", allow(deprecated))]
-                    let now: time_t = timespec.tv_sec;
+                // The time and gmtime_r calls are safe as long as the structs they are given are
+                // large enough, and neither of them fail. It is safe to zero initialize the tm
+                // struct because it contains only plain data.
+                unsafe {
                     let mut tm: tm = mem::zeroed();
+                    let mut now: time_t = 0;
+                    time(&mut now as *mut _);
                     gmtime_r(&now, &mut tm as *mut _);
-
                     // The following lines of code are safe but depend on tm being in scope.
                     seconds = tm.tm_sec;
                     minutes = tm.tm_min;
@@ -137,11 +93,6 @@ impl BusDevice for Cmos {
                     day = tm.tm_mday;
                     month = tm.tm_mon + 1;
                     year = tm.tm_year;
-
-                    // Update in Progress bit held for last 224us of each second
-                    const NANOSECONDS_PER_SECOND: i64 = 1_000_000_000;
-                    const UIP_HOLD_LENGTH: i64 = 8 * NANOSECONDS_PER_SECOND / 32768;
-                    timespec.tv_nsec >= (NANOSECONDS_PER_SECOND - UIP_HOLD_LENGTH)
                 };
                 match self.index {
                     0x00 => to_bcd(seconds as u8),
@@ -151,11 +102,6 @@ impl BusDevice for Cmos {
                     0x07 => to_bcd(day as u8),
                     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,
-                    // Bit 0-6 are reserved and must be 0.
-                    // Bit 7 must be 1 (CMOS has power)
-                    0x0d => 1 << 7,
                     0x32 => to_bcd(((year + 1900) / 100) as u8),
                     _ => {
                         // self.index is always guaranteed to be in range via INDEX_MASK.
@@ -163,10 +109,7 @@ impl BusDevice for Cmos {
                     }
                 }
             }
-            o => {
-                warn!("bad read offset on CMOS device: {}", o);
-                0
-            }
+            o => panic!("bad read offset on CMOS device: {}", o),
         }
     }
 }

devices/src/legacy/debug_port.rs

@@ -1,87 +0,0 @@
-// Copyright © 2022 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-//
-
-use std::fmt;
-use std::time::Instant;
-
-use vm_device::BusDevice;
-
-/// Debug I/O port, see:
-/// https://www.intel.com/content/www/us/en/support/articles/000005500/boards-and-kits.html
-///
-/// Since we're not a physical platform, we can freely assign code ranges for
-/// debugging specific parts of our virtual platform.
-pub enum DebugIoPortRange {
-    Firmware,
-    Bootloader,
-    Kernel,
-    Userspace,
-    Custom,
-}
-
-#[cfg(target_arch = "x86_64")]
-const DEBUG_IOPORT_PREFIX: &str = "Debug I/O port";
-
-#[cfg(target_arch = "x86_64")]
-impl DebugIoPortRange {
-    fn from_u8(value: u8) -> DebugIoPortRange {
-        match value {
-            0x00..=0x1f => DebugIoPortRange::Firmware,
-            0x20..=0x3f => DebugIoPortRange::Bootloader,
-            0x40..=0x5f => DebugIoPortRange::Kernel,
-            0x60..=0x7f => DebugIoPortRange::Userspace,
-            _ => DebugIoPortRange::Custom,
-        }
-    }
-}
-
-#[cfg(target_arch = "x86_64")]
-impl fmt::Display for DebugIoPortRange {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        match self {
-            DebugIoPortRange::Firmware => write!(f, "{DEBUG_IOPORT_PREFIX}: Firmware"),
-            DebugIoPortRange::Bootloader => write!(f, "{DEBUG_IOPORT_PREFIX}: Bootloader"),
-            DebugIoPortRange::Kernel => write!(f, "{DEBUG_IOPORT_PREFIX}: Kernel"),
-            DebugIoPortRange::Userspace => write!(f, "{DEBUG_IOPORT_PREFIX}: Userspace"),
-            DebugIoPortRange::Custom => write!(f, "{DEBUG_IOPORT_PREFIX}: Custom"),
-        }
-    }
-}
-
-pub struct DebugPort {
-    timestamp: Instant,
-}
-
-impl DebugPort {
-    pub fn new(timestamp: Instant) -> Self {
-        Self { timestamp }
-    }
-}
-
-impl BusDevice for DebugPort {
-    fn read(&mut self, _base: u64, _offset: u64, _data: &mut [u8]) {
-        error!("Invalid read to debug port")
-    }
-
-    fn write(
-        &mut self,
-        _base: u64,
-        _offset: u64,
-        data: &[u8],
-    ) -> Option<std::sync::Arc<std::sync::Barrier>> {
-        let elapsed = self.timestamp.elapsed();
-
-        let code = data[0];
-        warn!(
-            "[{} code 0x{:x}] {}.{:>06} seconds",
-            DebugIoPortRange::from_u8(code),
-            code,
-            elapsed.as_secs(),
-            elapsed.as_micros()
-        );
-
-        None
-    }
-}

devices/src/legacy/fwdebug.rs

@@ -1,44 +0,0 @@
-// 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 LICENSE-BSD-3-Clause file.
-//
-// Copyright © 2020 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
-//
-
-use std::sync::{Arc, Barrier};
-
-use vm_device::BusDevice;
-
-/// Provides firmware debug output via I/O port controls
-#[derive(Default)]
-pub struct FwDebugDevice {}
-
-impl FwDebugDevice {
-    pub fn new() -> Self {
-        Self {}
-    }
-}
-
-/// FwDebugDevice sits on the I/O bus as 0x402 and receives ASCII characters
-impl BusDevice for FwDebugDevice {
-    /// Upon read return the magic value to indicate that there is a debug port
-    fn read(&mut self, _base: u64, _offset: u64, data: &mut [u8]) {
-        if data.len() == 1 {
-            data[0] = 0xe9
-        } else {
-            error!("Invalid read size on debug port: {}", data.len())
-        }
-    }
-
-    fn write(&mut self, _base: u64, _offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
-        if data.len() == 1 {
-            print!("{}", data[0] as char);
-        } else {
-            error!("Invalid write size on debug port: {}", data.len())
-        }
-
-        None
-    }
-}

devices/src/legacy/gpio_pl061.rs

@@ -1,456 +0,0 @@
-// Copyright 2021 Arm Limited (or its affiliates). All rights reserved.
-//
-// SPDX-License-Identifier: Apache-2.0
-
-//! ARM PrimeCell General Purpose Input/Output(PL061)
-//!
-//! 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::interrupt::InterruptSourceGroup;
-use vm_device::BusDevice;
-use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
-
-use crate::{read_le_u32, write_le_u32};
-
-const OFS_DATA: u64 = 0x400; // Data Register
-const GPIODIR: u64 = 0x400; // Direction Register
-const GPIOIS: u64 = 0x404; // Interrupt Sense Register
-const GPIOIBE: u64 = 0x408; // Interrupt Both Edges Register
-const GPIOIEV: u64 = 0x40c; // Interrupt Event Register
-const GPIOIE: u64 = 0x410; // Interrupt Mask Register
-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.
-const GPIO_ID: [u8; 8] = [0x61, 0x10, 0x14, 0x00, 0x0d, 0xf0, 0x05, 0xb1];
-// ID Margins
-const GPIO_ID_LOW: u64 = 0xfe0;
-const GPIO_ID_HIGH: u64 = 0x1000;
-
-const N_GPIOS: u32 = 8;
-
-#[derive(Debug, Error)]
-pub enum Error {
-    #[error("Bad Write Offset: {0}")]
-    BadWriteOffset(u64),
-    #[error("GPIO interrupt disabled by guest driver.")]
-    GpioInterruptDisabled,
-    #[error("Could not trigger GPIO interrupt: {0}.")]
-    GpioInterruptFailure(io::Error),
-    #[error("Invalid GPIO Input key triggered: {0}.")]
-    GpioTriggerKeyFailure(u32),
-}
-
-type Result<T> = result::Result<T, Error>;
-
-/// A GPIO device following the PL061 specification.
-pub struct Gpio {
-    id: String,
-    // Data Register
-    data: u32,
-    old_in_data: u32,
-    // Direction Register
-    dir: u32,
-    // Interrupt Sense Register
-    isense: u32,
-    // Interrupt Both Edges Register
-    ibe: u32,
-    // Interrupt Event Register
-    iev: u32,
-    // Interrupt Mask Register
-    im: u32,
-    // Raw Interrupt Status Register
-    istate: u32,
-    // Mode Control Select Register
-    afsel: u32,
-    // GPIO irq_field
-    interrupt: Arc<dyn InterruptSourceGroup>,
-}
-
-#[derive(Serialize, Deserialize)]
-pub struct GpioState {
-    data: u32,
-    old_in_data: u32,
-    dir: u32,
-    isense: u32,
-    ibe: u32,
-    iev: u32,
-    im: u32,
-    istate: u32,
-    afsel: u32,
-}
-
-impl Gpio {
-    /// Constructs an PL061 GPIO device.
-    pub fn new(
-        id: String,
-        interrupt: Arc<dyn InterruptSourceGroup>,
-        state: Option<GpioState>,
-    ) -> Self {
-        let (data, old_in_data, dir, isense, ibe, iev, im, istate, afsel) =
-            if let Some(state) = state {
-                (
-                    state.data,
-                    state.old_in_data,
-                    state.dir,
-                    state.isense,
-                    state.ibe,
-                    state.iev,
-                    state.im,
-                    state.istate,
-                    state.afsel,
-                )
-            } else {
-                (0, 0, 0, 0, 0, 0, 0, 0, 0)
-            };
-
-        Self {
-            id,
-            data,
-            old_in_data,
-            dir,
-            isense,
-            ibe,
-            iev,
-            im,
-            istate,
-            afsel,
-            interrupt,
-        }
-    }
-
-    fn state(&self) -> GpioState {
-        GpioState {
-            data: self.data,
-            old_in_data: self.old_in_data,
-            dir: self.dir,
-            isense: self.isense,
-            ibe: self.ibe,
-            iev: self.iev,
-            im: self.im,
-            istate: self.istate,
-            afsel: self.afsel,
-        }
-    }
-
-    fn pl061_internal_update(&mut self) {
-        // FIXME:
-        //  Missing Output Interrupt Emulation.
-
-        // Input Edging Interrupt Emulation.
-        let changed = (self.old_in_data ^ self.data) & !self.dir;
-        if changed > 0 {
-            self.old_in_data = self.data;
-            for i in 0..N_GPIOS {
-                let mask = (1 << i) as u32;
-                if (changed & mask) > 0 {
-                    // Bits set high in GPIOIS(Interrupt sense register) configure the corresponding
-                    // pins to detect levels, otherwise, detect edges.
-                    if (self.isense & mask) == 0 {
-                        if (self.ibe & mask) > 0 {
-                            // Bits set high in GPIOIBE(Interrupt both-edges register) configure the corresponding
-                            // pins to detect both falling and rising edges.
-                            // Clearing a bit configures the pin to be controlled by GPIOIEV.
-                            self.istate |= mask;
-                        } else {
-                            // Bits set to high in GPIOIEV(Interrupt event register) configure the
-                            // corresponding pin to detect rising edges, otherwise, detect falling edges.
-                            self.istate |= !(self.data ^ self.iev) & mask;
-                        }
-                    }
-                }
-            }
-        }
-
-        // Input Level Interrupt Emulation.
-        self.istate |= !(self.data ^ self.iev) & self.isense;
-    }
-
-    fn handle_write(&mut self, offset: u64, val: u32) -> Result<()> {
-        if offset < OFS_DATA {
-            // In order to write to data register, the corresponding bits in the mask, resulting
-            // from the offsite[9:2], must be HIGH. otherwise the bit values remain unchanged.
-            let mask = (offset >> 2) as u32 & self.dir;
-            self.data = (self.data & !mask) | (val & mask);
-        } else {
-            match offset {
-                GPIODIR => {
-                    /* Direction Register */
-                    self.dir = val & 0xff;
-                }
-                GPIOIS => {
-                    /* Interrupt Sense Register */
-                    self.isense = val & 0xff;
-                }
-                GPIOIBE => {
-                    /* Interrupt Both Edges Register */
-                    self.ibe = val & 0xff;
-                }
-                GPIOIEV => {
-                    /* Interrupt Event Register */
-                    self.iev = val & 0xff;
-                }
-                GPIOIE => {
-                    /* Interrupt Mask Register */
-                    self.im = val & 0xff;
-                }
-                GPIOIC => {
-                    /* Interrupt Clear Register */
-                    self.istate &= !val;
-                }
-                GPIOAFSEL => {
-                    /* Mode Control Select Register */
-                    self.afsel = val & 0xff;
-                }
-                o => {
-                    return Err(Error::BadWriteOffset(o));
-                }
-            }
-        }
-        Ok(())
-    }
-
-    pub fn trigger_key(&mut self, key: u32) -> Result<()> {
-        let mask = (1 << key) as u32;
-        if (!self.dir & mask) > 0 {
-            // emulate key event
-            // By default, Input Pin is configured to detect both rising and falling edges.
-            // So reverse the input pin data to generate a pulse.
-            self.data |= !(self.data & mask) & mask;
-            self.pl061_internal_update();
-
-            match self.trigger_gpio_interrupt() {
-                Ok(_) | Err(Error::GpioInterruptDisabled) => return Ok(()),
-                Err(e) => return Err(e),
-            }
-        }
-
-        Err(Error::GpioTriggerKeyFailure(key))
-    }
-
-    fn trigger_gpio_interrupt(&self) -> Result<()> {
-        // Bits set to high in GPIOIE(Interrupt mask register) allow the corresponding pins to
-        // trigger their individual interrupts and then the combined GPIOINTR line.
-        if (self.istate & self.im) == 0 {
-            warn!("Failed to trigger GPIO input interrupt (disabled by guest OS)");
-            return Err(Error::GpioInterruptDisabled);
-        }
-        self.interrupt
-            .trigger(0)
-            .map_err(Error::GpioInterruptFailure)?;
-        Ok(())
-    }
-}
-
-impl BusDevice for Gpio {
-    fn read(&mut self, _base: u64, offset: u64, data: &mut [u8]) {
-        let value;
-        let mut read_ok = true;
-
-        if (GPIO_ID_LOW..GPIO_ID_HIGH).contains(&offset) {
-            let index = ((offset - GPIO_ID_LOW) >> 2) as usize;
-            value = u32::from(GPIO_ID[index]);
-        } else if offset < OFS_DATA {
-            value = self.data & ((offset >> 2) as u32)
-        } else {
-            value = match offset {
-                GPIODIR => self.dir,
-                GPIOIS => self.isense,
-                GPIOIBE => self.ibe,
-                GPIOIEV => self.iev,
-                GPIOIE => self.im,
-                GPIORIE => self.istate,
-                GPIOMIS => self.istate & self.im,
-                GPIOAFSEL => self.afsel,
-                _ => {
-                    read_ok = false;
-                    0
-                }
-            };
-        }
-
-        if read_ok && data.len() <= 4 {
-            write_le_u32(data, value);
-        } else {
-            warn!(
-                "Invalid GPIO PL061 read: offset {}, data length {}",
-                offset,
-                data.len()
-            );
-        }
-    }
-
-    fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
-        if data.len() <= 4 {
-            let value = read_le_u32(data);
-            if let Err(e) = self.handle_write(offset, value) {
-                warn!("Failed to write to GPIO PL061 device: {}", e);
-            }
-        } else {
-            warn!(
-                "Invalid GPIO PL061 write: offset {}, data length {}",
-                offset,
-                data.len()
-            );
-        }
-
-        None
-    }
-}
-
-impl Snapshottable for Gpio {
-    fn id(&self) -> String {
-        self.id.clone()
-    }
-
-    fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        Snapshot::new_from_state(&self.state())
-    }
-}
-
-impl Pausable for Gpio {}
-impl Transportable for Gpio {}
-impl Migratable for Gpio {}
-
-#[cfg(test)]
-mod tests {
-    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;
-
-    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,
-            _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())
-        }
-    }
-
-    impl TestInterrupt {
-        fn new(event_fd: EventFd) -> Self {
-            TestInterrupt { event_fd }
-        }
-    }
-
-    #[test]
-    fn test_gpio_read_write_and_event() {
-        let intr_evt = EventFd::new(libc::EFD_NONBLOCK).unwrap();
-        let mut gpio = Gpio::new(
-            String::from(GPIO_NAME),
-            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
-            None,
-        );
-        let mut data = [0; 4];
-
-        // Read and write to the GPIODIR register.
-        // Set pin 0 output pin.
-        write_le_u32(&mut data, 1);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIODIR, &data);
-        gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIODIR, &mut data);
-        let v = read_le_u32(&data);
-        assert_eq!(v, 1);
-
-        // Read and write to the GPIODATA register.
-        write_le_u32(&mut data, 1);
-        // Set pin 0 high.
-        let offset = 0x00000004_u64;
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, offset, &data);
-        gpio.read(LEGACY_GPIO_MAPPED_IO_START, offset, &mut data);
-        let v = read_le_u32(&data);
-        assert_eq!(v, 1);
-
-        // Read and write to the GPIOIS register.
-        // Configure pin 0 detecting level interrupt.
-        write_le_u32(&mut data, 1);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIS, &data);
-        gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOIS, &mut data);
-        let v = read_le_u32(&data);
-        assert_eq!(v, 1);
-
-        // Read and write to the GPIOIBE register.
-        // Configure pin 1 detecting both falling and rising edges.
-        write_le_u32(&mut data, 2);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIBE, &data);
-        gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOIBE, &mut data);
-        let v = read_le_u32(&data);
-        assert_eq!(v, 2);
-
-        // Read and write to the GPIOIEV register.
-        // Configure pin 2 detecting both falling and rising edges.
-        write_le_u32(&mut data, 4);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIEV, &data);
-        gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOIEV, &mut data);
-        let v = read_le_u32(&data);
-        assert_eq!(v, 4);
-
-        // Read and write to the GPIOIE register.
-        // Configure pin 0...2 capable of triggering their individual interrupts
-        // and then the combined GPIOINTR line.
-        write_le_u32(&mut data, 7);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIE, &data);
-        gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOIE, &mut data);
-        let v = read_le_u32(&data);
-        assert_eq!(v, 7);
-
-        let mask = 0x00000002_u32;
-        // emulate an rising pulse in pin 1.
-        gpio.data |= !(gpio.data & mask) & mask;
-        gpio.pl061_internal_update();
-        // The interrupt line on pin 1 should be on.
-        // Read the GPIOMIS register.
-        gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOMIS, &mut data);
-        let v = read_le_u32(&data);
-        assert_eq!(v, 2);
-
-        // Read and Write to the GPIOIC register.
-        // clear interrupt in pin 1.
-        write_le_u32(&mut data, 2);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIC, &data);
-        gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOIC, &mut data);
-        let v = read_le_u32(&data);
-        assert_eq!(v, 2);
-
-        // Attempts to write beyond the writable space.
-        write_le_u32(&mut data, 0);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIO_ID_LOW, &data);
-
-        let mut data = [0; 4];
-        gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIO_ID_LOW, &mut data);
-        let index = GPIO_ID_LOW + 3;
-        assert_eq!(data[0], GPIO_ID[((index - GPIO_ID_LOW) >> 2) as usize]);
-    }
-}

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;
 
+use BusDevice;
+
 /// 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 }
     }
 }
 
@@ -41,21 +32,12 @@ impl BusDevice for I8042Device {
         }
     }
 
-    fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
+    fn write(&mut self, _base: u64, offset: u64, data: &[u8]) {
         if data.len() == 1 && data[0] == 0xfe && offset == 3 {
-            info!("i8042 reset signalled");
+            debug!("i8042 reset signalled");
             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

@@ -5,32 +5,12 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE-BSD-3-Clause file.
 
+#[cfg(feature = "cmos")]
 mod cmos;
-#[cfg(target_arch = "x86_64")]
-mod debug_port;
-#[cfg(target_arch = "x86_64")]
-mod fwdebug;
-#[cfg(target_arch = "aarch64")]
-mod gpio_pl061;
 mod i8042;
-#[cfg(target_arch = "aarch64")]
-mod rtc_pl031;
 mod serial;
-#[cfg(target_arch = "aarch64")]
-mod uart_pl011;
 
+#[cfg(feature = "cmos")]
 pub use self::cmos::Cmos;
-#[cfg(target_arch = "x86_64")]
-pub use self::debug_port::DebugPort;
-#[cfg(target_arch = "x86_64")]
-pub use self::fwdebug::FwDebugDevice;
-#[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;