build: Release v41.0

Signed-off-by: Rob Bradford <rbradford@rivosinc.com>

.github/workflows/audit.yaml

@@ -4,12 +4,13 @@ on:
     paths: 
       - '**/Cargo.toml'
       - '**/Cargo.lock'
+
 jobs:
   security_audit:
     name: Audit
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: actions-rs/audit-check@v1
+      - uses: actions-rust-lang/audit@v1
         with:
           token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/build.yaml

@@ -1,9 +1,11 @@
 name: Cloud Hypervisor Build
-on: [pull_request, create]
+on: [pull_request, merge_group]
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
 
 jobs:
   build:
-    if: github.event_name == 'pull_request'
     name: Build
     runs-on: ubuntu-latest
     strategy:
@@ -13,7 +15,7 @@ jobs:
           - stable
           - beta
           - nightly
-          - "1.70"
+          - "1.77.0"
         target:
           - x86_64-unknown-linux-gnu
           - x86_64-unknown-linux-musl
@@ -27,11 +29,10 @@ jobs:
         run: sudo apt install -y musl-tools
 
       - name: Install Rust toolchain (${{ matrix.rust }})
-        uses: actions-rs/toolchain@v1
+        uses: dtolnay/rust-toolchain@stable
         with:
           toolchain: ${{ matrix.rust }}
           target: ${{ matrix.target }}
-          override: true
 
       - name: Build (default features)
         run: cargo rustc --locked --bin cloud-hypervisor -- -D warnings -D clippy::undocumented_unsafe_blocks
@@ -48,6 +49,9 @@ jobs:
       - name: Build (default features + guest_debug)
         run: cargo rustc --locked --bin cloud-hypervisor --features "guest_debug" -- -D warnings -D clippy::undocumented_unsafe_blocks
 
+      - name: Build (default features + pvmemcontrol)
+        run: cargo rustc --locked --bin cloud-hypervisor --features "pvmemcontrol" -- -D warnings -D clippy::undocumented_unsafe_blocks
+
       - name: Build (mshv)
         run: cargo rustc --locked --bin cloud-hypervisor --no-default-features --features "mshv"  -- -D warnings -D clippy::undocumented_unsafe_blocks
 

.github/workflows/dco.yaml

@@ -1,8 +1,9 @@
 name: DCO
-on:
-  pull_request:
+on: [pull_request, merge_group]
+
 jobs:
   check:
+    name: DCO Check ("Signed-Off-By")
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v4
@@ -11,6 +12,7 @@ jobs:
       with:
         python-version: '3.x'
     - name: Check DCO
+      if: ${{ github.event_name == 'pull_request' }}
       env:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       run: |

.github/workflows/docker-image.yaml

@@ -1,11 +1,13 @@
 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
@@ -39,7 +41,7 @@ jobs:
           images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
           # generate Docker tags based on the following events/attributes
           tags: |
-            type=raw,value={{date 'YYYYMMDD'}}-0
+            type=raw,value=20240507-0
             type=sha
 
       - name: Build and push

.github/workflows/fuzz-build.yaml

@@ -1,9 +1,11 @@
 name: Cloud Hypervisor Cargo Fuzz Build
-on: [pull_request, create]
+on: [pull_request, merge_group]
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
 
 jobs:
   build:
-    if: github.event_name == 'pull_request'
     name: Cargo Fuzz Build
     runs-on: ubuntu-latest
     strategy:
@@ -18,11 +20,10 @@ jobs:
       - name: Code checkout
         uses: actions/checkout@v4
       - name: Install Rust toolchain (${{ matrix.rust }})
-        uses: actions-rs/toolchain@v1
+        uses: dtolnay/rust-toolchain@stable
         with:
             toolchain: ${{ matrix.rust }}
             target: ${{ matrix.target }}
-            override: true
       - name: Install Cargo fuzz
         run: cargo install cargo-fuzz
       - name: Fuzz Build

.github/workflows/gitlint.yaml

@@ -1,5 +1,4 @@
 name: Commit messages check
-
 on:
   pull_request:
 

.github/workflows/hadolint.yaml

@@ -1,5 +1,4 @@
 name: Lint Dockerfile
-
 on:
   push:
     paths:

.github/workflows/integration-arm64.yaml

@@ -0,0 +1,54 @@
+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: focal-arm64
+    steps:
+      - name: Fix workspace permissions
+        run: sudo chown -R github-runner:github-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/ focal 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

@@ -0,0 +1,22 @@
+name: Cloud Hypervisor Tests (Metrics)
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  build:
+    name: Tests (Metrics)
+    runs-on: jammy-metrics
+    env:
+      METRICS_PUBLISH_KEY: ${{ secrets.METRICS_PUBLISH_KEY }}
+    steps:
+      - name: Code checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: Run metrics tests
+        timeout-minutes: 60
+        run: scripts/dev_cli.sh tests --metrics -- -- --report-file /root/workloads/metrics.json
+      - name: Upload metrics report
+        run: 'curl -X PUT https://ch-metrics.azurewebsites.net/api/publishmetrics -H "x-functions-key: $METRICS_PUBLISH_KEY" -T ~/workloads/metrics.json'

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

@@ -0,0 +1,28 @@
+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' || 'jammy-rate-limiter' }}
+    env:
+      AUTH_DOWNLOAD_TOKEN: ${{ secrets.AUTH_DOWNLOAD_TOKEN }}
+    steps:
+      - name: Fix workspace permissions
+        if: ${{ github.event_name != 'pull_request' }}
+        run: sudo chown -R github-runner:github-runner ${GITHUB_WORKSPACE}
+      - name: Code checkout
+        if: ${{ github.event_name != 'pull_request' }}
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - 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-sgx.yaml

@@ -0,0 +1,32 @@
+name: Cloud Hypervisor Tests (SGX)
+on: [merge_group, pull_request]
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build:
+    name: Tests (SGX)
+    runs-on: ${{ github.event_name == 'pull_request' && 'ubuntu-latest' || 'jammy-sgx' }}
+    env:
+      AUTH_DOWNLOAD_TOKEN: ${{ secrets.AUTH_DOWNLOAD_TOKEN }}
+    steps:
+      - name: Fix workspace permissions
+        if: ${{ github.event_name != 'pull_request' }}
+        run: sudo chown -R github-runner:github-runner ${GITHUB_WORKSPACE}
+      - name: Code checkout
+        if: ${{ github.event_name != 'pull_request' }}
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: Run SGX integration tests
+        if: ${{ github.event_name != 'pull_request' }}
+        timeout-minutes: 10
+        run: scripts/dev_cli.sh tests --integration-sgx
+      - name: Run SGX integration tests for musl
+        if: ${{ github.event_name != 'pull_request' }}
+        timeout-minutes: 10
+        run: scripts/dev_cli.sh tests --integration-sgx --libc musl
+      - name: Skipping build for PR
+        if: ${{ github.event_name == 'pull_request' }}
+        run: echo "Skipping build for PR"

.github/workflows/integration-vfio.yaml

@@ -0,0 +1,32 @@
+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' || 'jammy-vfio' }}
+    env:
+      AUTH_DOWNLOAD_TOKEN: ${{ secrets.AUTH_DOWNLOAD_TOKEN }}
+    steps:
+      - name: Fix workspace permissions
+        if: ${{ github.event_name != 'pull_request' }}
+        run: sudo chown -R github-runner:github-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
+      - 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

@@ -0,0 +1,50 @@
+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

@@ -0,0 +1,52 @@
+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

@@ -1,7 +1,5 @@
 name: Cloud Hypervisor OpenAPI Validation
-
-on:
-  pull_request:
+on: [pull_request, merge_group]
 
 jobs:
   Validate:

.github/workflows/quality.yaml

@@ -1,9 +1,11 @@
 name: Cloud Hypervisor Quality Checks
-on: [pull_request, create]
+on: [pull_request, merge_group]
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
 
 jobs:
   build:
-    if: github.event_name == 'pull_request'
     name: Quality (clippy, rustfmt)
     runs-on: ubuntu-latest
     continue-on-error: ${{ matrix.experimental }}
@@ -46,8 +48,8 @@ jobs:
           override: true
           components: rustfmt, clippy
 
-      - name: Debug Check (default features)
-        if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
+      - 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 }})
@@ -78,6 +80,13 @@ jobs:
           command: clippy
           args: --target=${{ matrix.target }} --locked --all --all-targets --tests --examples --features "guest_debug" -- -D warnings -D clippy::undocumented_unsafe_blocks
 
+      - name: Clippy (default features + 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
+
       - name: Clippy (default features + tracing)
         uses: actions-rs/cargo@v1
         with:

.github/workflows/release.yaml

@@ -1,134 +1,69 @@
 name: Cloud Hypervisor Release
-on: [pull_request, create]
+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 == 'pull_request'
-    name: 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: Install Rust toolchain (x86_64-unknown-linux-gnu)
-        uses: actions-rs/toolchain@v1
+      - name: Build ${{ matrix.platform.target }}
+        uses: houseabsolute/actions-rust-cross@v0
         with:
-          toolchain: "1.70"
-          target: x86_64-unknown-linux-gnu
-      - name: Install Rust toolchain (x86_64-unknown-linux-musl)
-        uses: actions-rs/toolchain@v1
-        with:
-          toolchain: "1.70"
-          target: x86_64-unknown-linux-musl
-      - name: Build
-        uses: actions-rs/cargo@v1
-        with:
-          toolchain: "1.70"
           command: build
-          args: --all --release --features mshv --target=x86_64-unknown-linux-gnu
-      - name: Static Build
-        uses: actions-rs/cargo@v1
-        with:
-          toolchain: "1.70"
-          command: build
-          args: --all --release --features mshv --target=x86_64-unknown-linux-musl
-      - name: Install Rust toolchain (aarch64-unknown-linux-musl)
-        uses: actions-rs/toolchain@v1
-        with:
-          toolchain: "1.70"
-          target: aarch64-unknown-linux-musl
-          override: true
-      - name: Create Release
+          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'
-        id: create_release
-        uses: actions/create-release@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          tag_name: ${{ github.ref }}
-          release_name: ${{ github.ref }}
-          draft: true
-          prerelease: true
-      - name: Upload cloud-hypervisor
+        shell: bash
+        run: |
+          cp target/${{ 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'
-        id: upload-release-cloud-hypervisor
-        uses: actions/upload-release-asset@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        uses: actions/upload-artifact@v3
         with:
-          upload_url: ${{ steps.create_release.outputs.upload_url }}
-          asset_path: target/x86_64-unknown-linux-gnu/release/cloud-hypervisor
-          asset_name: cloud-hypervisor
-          asset_content_type: application/octet-stream
-      - name: Upload static cloud-hypervisor
-        if: github.event_name == 'create' && github.event.ref_type == 'tag'
-        id: upload-release-static-cloud-hypervisor
-        uses: actions/upload-release-asset@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          upload_url: ${{ steps.create_release.outputs.upload_url }}
-          asset_path: target/x86_64-unknown-linux-musl/release/cloud-hypervisor
-          asset_name: cloud-hypervisor-static
-          asset_content_type: application/octet-stream
-      - name: Upload ch-remote
-        if: github.event_name == 'create' && github.event.ref_type == 'tag'
-        id: upload-release-ch-remote
-        uses: actions/upload-release-asset@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          upload_url: ${{ steps.create_release.outputs.upload_url }}
-          asset_path: target/x86_64-unknown-linux-gnu/release/ch-remote
-          asset_name: ch-remote
-          asset_content_type: application/octet-stream
-      - name: Upload static-ch-remote
-        if: github.event_name == 'create' && github.event.ref_type == 'tag'
-        id: upload-release-static-ch-remote
-        uses: actions/upload-release-asset@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          upload_url: ${{ steps.create_release.outputs.upload_url }}
-          asset_path: target/x86_64-unknown-linux-musl/release/ch-remote
-          asset_name: ch-remote-static
-          asset_content_type: application/octet-stream
-      - name: Clean build tree ahead of cross build
-        uses: actions-rs/cargo@v1
-        with:
-          command: clean
-      - name: Static Build (AArch64)
-        uses: actions-rs/cargo@v1
-        with:
-          use-cross: true
-          command: build
-          args: --all --release --target=aarch64-unknown-linux-musl
-      - name: Upload static AArch64 cloud-hypervisor
-        if: github.event_name == 'create' && github.event.ref_type == 'tag'
-        id: upload-release-static-aarch64-cloud-hypervisor
-        uses: actions/upload-release-asset@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          upload_url: ${{ steps.create_release.outputs.upload_url }}
-          asset_path: target/aarch64-unknown-linux-musl/release/cloud-hypervisor
-          asset_name: cloud-hypervisor-static-aarch64
-          asset_content_type: application/octet-stream
-      - name: Upload static AArch64 ch-remote
-        if: github.event_name == 'create' && github.event.ref_type == 'tag'
-        id: upload-release-static-aarch64-ch-remote
-        uses: actions/upload-release-asset@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          upload_url: ${{ steps.create_release.outputs.upload_url }}
-          asset_path: target/aarch64-unknown-linux-musl/release/ch-remote
-          asset_name: ch-remote-static-aarch64
-          asset_content_type: application/octet-stream
+          name: 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
@@ -136,16 +71,25 @@ jobs:
           mkdir .cargo
           cargo vendor > .cargo/config.toml
       - name: Create vendored source archive
-        working-directory: ../
-        run: tar cJf cloud-hypervisor-${{ github.event.ref }}.tar.xz cloud-hypervisor-${{ github.event.ref }}
+        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'
+        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-release-asset@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        uses: actions/upload-artifact@v3
         with:
-          upload_url: ${{ steps.create_release.outputs.upload_url }}
-          asset_path: ../cloud-hypervisor-${{ github.event.ref }}.tar.xz
-          asset_name: cloud-hypervisor-${{ github.event.ref }}.tar.xz
-          asset_content_type: application/x-xz
+          path: cloud-hypervisor-${{ 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

@@ -0,0 +1,12 @@
+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

@@ -1,7 +1,7 @@
 name: Shell scripts check
-
 on:
   pull_request:
+  merge_group:
   push:
     branches:
       - main

.github/workflows/taplo.yaml

@@ -0,0 +1,21 @@
+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

.reuse/dep5

@@ -0,0 +1,12 @@
+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

.taplo.toml

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

CONTRIBUTING.md

@@ -112,5 +112,5 @@ Fixes #88
 Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
 ```
 
-Then, after the corresponding PR is merged, Github will automatically close that issue when parsing the
+Then, after the corresponding PR is merged, GitHub will automatically close that issue when parsing the
 [commit message](https://help.github.com/articles/closing-issues-via-commit-messages/).

Cargo.toml

@@ -1,13 +1,13 @@
 [package]
-name = "cloud-hypervisor"
-version = "38.0.0"
 authors = ["The Cloud Hypervisor Authors"]
-edition = "2021"
-default-run = "cloud-hypervisor"
 build = "build.rs"
-license = "LICENSE-APACHE & LICENSE-BSD-3-Clause"
-description = "Open source Virtual Machine Monitor (VMM) that runs on top of KVM"
+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 = "41.0.0"
 # Minimum buildable version:
 # Keep in sync with version in .github/workflows/build.yaml
 # Policy on MSRV (see #4318):
@@ -15,92 +15,88 @@ homepage = "https://github.com/cloud-hypervisor/cloud-hypervisor"
 # 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 = "1.70"
+rust-version = "1.77.0"
 
 [profile.release]
-lto = true
 codegen-units = 1
+lto = true
 opt-level = "s"
 strip = true
 
 [profile.profiling]
+debug = true
 inherits = "release"
 strip = false
-debug = true
 
 [dependencies]
-anyhow = "1.0.79"
+anyhow = "1.0.86"
 api_client = { path = "api_client" }
-clap = { version = "4.4.7", features = ["string"] }
+clap = { version = "4.5.4", features = ["string"] }
 dhat = { version = "0.3.3", optional = true }
 epoll = "4.3.3"
 event_monitor = { path = "event_monitor" }
 hypervisor = { path = "hypervisor" }
-libc = "0.2.153"
-log = { version = "0.4.20", features = ["std"] }
+libc = "0.2.155"
+log = { version = "0.4.22", features = ["std"] }
 option_parser = { path = "option_parser" }
 seccompiler = "0.4.0"
-serde_json = "1.0.109"
+serde_json = "1.0.120"
 signal-hook = "0.3.17"
-thiserror = "1.0.52"
-tpm = { path = "tpm"}
+thiserror = "1.0.62"
+tpm = { path = "tpm" }
 tracer = { path = "tracer" }
+vm-memory = "0.14.1"
 vmm = { path = "vmm" }
 vmm-sys-util = "0.12.1"
-vm-memory = "0.14.0"
-zbus = { version = "3.11.1", optional = true }
-
-# List of patched crates
-[patch.crates-io]
-kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.7.0" }
-versionize_derive = { git = "https://github.com/cloud-hypervisor/versionize_derive", branch = "ch-0.1.6" }
+zbus = { version = "4.1.2", optional = true }
 
 [dev-dependencies]
-dirs = "5.0.0"
+dirs = "5.0.1"
 net_util = { path = "net_util" }
 once_cell = "1.19.0"
-serde_json = "1.0.109"
+serde_json = "1.0.120"
 test_infra = { path = "test_infra" }
 wait-timeout = "0.2.0"
 
 # Please adjust `vmm::feature_list()` accordingly when changing the
 # feature list below
 [features]
-default = ["kvm", "io_uring"]
-dbus_api = ["zbus", "vmm/dbus_api"]
-dhat-heap = ["dhat"] # For heap profiling
+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 = ["vmm/igvm", "mshv"]
+igvm = ["mshv", "vmm/igvm"]
 io_uring = ["vmm/io_uring"]
 kvm = ["vmm/kvm"]
 mshv = ["vmm/mshv"]
-sev_snp = ["igvm", "vmm/sev_snp", "mshv"]
+pvmemcontrol = ["vmm/pvmemcontrol"]
+sev_snp = ["igvm", "mshv", "vmm/sev_snp"]
 tdx = ["vmm/tdx"]
-tracing = ["vmm/tracing", "tracer/tracing"]
+tracing = ["tracer/tracing", "vmm/tracing"]
 
 [workspace]
 members = [
-    "api_client",
-    "arch",
-    "block",
-    "devices",
-    "event_monitor",
-    "hypervisor",
-    "net_gen",
-    "net_util",
-    "option_parser",
-    "pci",
-    "performance-metrics",
-    "rate_limiter",
-    "serial_buffer",
-    "test_infra",
-    "tracer",
-    "vhost_user_block",
-    "vhost_user_net",
-    "virtio-devices",
-    "vmm",
-    "vm-allocator",
-    "vm-device",
-    "vm-migration",
-    "vm-virtio"
+  "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",
 ]

Jenkinsfile

@@ -1,530 +0,0 @@
-def runWorkers = true
-pipeline {
-    agent none
-    options {
-        timeout(time: 4, unit: 'HOURS')
-    }
-    stages {
-        stage('Early checks') {
-            agent { node { label 'built-in' } }
-            stages {
-                stage('Checkout') {
-                    steps {
-                        checkout scm
-                    }
-                }
-                stage('Check if worker build can be skipped') {
-                    when {
-                        expression {
-                            return skipWorkerBuild()
-                        }
-                    }
-                    steps {
-                        script {
-                            runWorkers = false
-                            echo 'No changes requiring a build'
-                        }
-                    }
-                }
-                stage('Check for RFC/WIP builds') {
-                    when {
-                        changeRequest comparator: 'REGEXP', title: '.*(rfc|RFC|wip|WIP).*'
-                        beforeAgent true
-                    }
-                    steps {
-                        error('Failing as this is marked as a WIP or RFC PR.')
-                    }
-                }
-                stage('Cancel older builds') {
-                    when { not { branch 'main' } }
-                    steps {
-                        cancelPreviousBuilds()
-                    }
-                }
-            }
-        }
-        stage('Build') {
-            parallel {
-                stage('Worker build') {
-                    agent { node { label 'jammy' } }
-                    when {
-                        beforeAgent true
-                        expression {
-                            return runWorkers
-                        }
-                    }
-                    environment {
-                        AUTH_DOWNLOAD_TOKEN = credentials('8a26fd74-d40e-414c-9132-ff3f867806ef')
-                    }
-                    stages {
-                        stage('Checkout') {
-                            steps {
-                                checkout scm
-                            }
-                        }
-                        stage('Prepare environment') {
-                            steps {
-                                sh 'scripts/prepare_vdpa.sh'
-                            }
-                        }
-                        stage('Run unit tests') {
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --unit'
-                            }
-                        }
-                        stage('Run integration tests') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration'
-                            }
-                        }
-                        stage('Run live-migration integration tests') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration-live-migration'
-                            }
-                        }
-                        stage('Run unit tests for musl') {
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --unit --libc musl'
-                            }
-                        }
-                        stage('Run integration tests for musl') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration --libc musl'
-                            }
-                        }
-                        stage('Run live-migration integration tests for musl') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration-live-migration --libc musl'
-                            }
-                        }
-                    }
-                }
-                stage('Worker build - AMD') {
-                    agent { node { label 'jammy-amd' } }
-                    when {
-                        beforeAgent true
-                        expression {
-                            return runWorkers
-                        }
-                    }
-                    environment {
-                        AUTH_DOWNLOAD_TOKEN = credentials('8a26fd74-d40e-414c-9132-ff3f867806ef')
-                    }
-                    stages {
-                        stage('Checkout') {
-                            steps {
-                                checkout scm
-                            }
-                        }
-                        stage('Prepare environment') {
-                            steps {
-                                sh 'scripts/prepare_vdpa.sh'
-                            }
-                        }
-                        stage('Run integration tests') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration'
-                            }
-                        }
-                        stage('Run live-migration integration tests') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration-live-migration'
-                            }
-                        }
-                        stage('Run integration tests for musl') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration --libc musl'
-                            }
-                        }
-                        stage('Run live-migration integration tests for musl') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration-live-migration --libc musl'
-                            }
-                        }
-                    }
-                }
-                stage('AArch64 worker build') {
-                    agent { node { label 'bionic-arm64' } }
-                    when {
-                        beforeAgent true
-                        expression {
-                            return runWorkers
-                        }
-                    }
-                    environment {
-                            AZURE_CONNECTION_STRING = credentials('46b4e7d6-315f-4cc1-8333-b58780863b9b')
-                    }
-                    stages {
-                        stage('Checkout') {
-                            steps {
-                                checkout scm
-                            }
-                        }
-                        stage('Run unit tests') {
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --unit --libc musl'
-                            }
-                        }
-                        stage('Run integration tests') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration --libc musl'
-                            }
-                        }
-                        stage('Install azure-cli') {
-                            steps {
-                                installAzureCli('focal', 'arm64')
-                            }
-                        }
-                        stage('Download Windows image') {
-                            steps {
-                                sh '''#!/bin/bash -x
-                                    IMG_BASENAME=windows-11-iot-enterprise-aarch64.raw
-                                    IMG_PATH=$HOME/workloads/$IMG_BASENAME
-                                    IMG_GZ_PATH=$HOME/workloads/$IMG_BASENAME.gz
-                                    IMG_GZ_BLOB_NAME=windows-11-iot-enterprise-aarch64-9-min.raw.gz
-                                    cp "scripts/$IMG_BASENAME.sha1" "$HOME/workloads/"
-                                    pushd "$HOME/workloads"
-                                    if sha1sum "$IMG_BASENAME.sha1" --check; then
-                                        exit
-                                    fi
-                                    popd
-                                    mkdir -p "$HOME/workloads"
-                                    az storage blob download \
-                                        --container-name private-images \
-                                        --file "$IMG_GZ_PATH" \
-                                        --name "$IMG_GZ_BLOB_NAME" \
-                                        --connection-string "$AZURE_CONNECTION_STRING"
-                                    gzip -d $IMG_GZ_PATH
-                                '''
-                            }
-                        }
-                        stage('Run Windows guest integration tests') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --integration-windows --libc musl'
-                            }
-                        }
-                    }
-                    post {
-                        always {
-                            sh "sudo chown -R jenkins.jenkins ${WORKSPACE}"
-                            deleteDir()
-                        }
-                    }
-                }
-                stage('Worker build - Windows guest') {
-                    agent { node { label 'jammy' } }
-                    when {
-                        beforeAgent true
-                        expression {
-                            return runWorkers
-                        }
-                    }
-                    environment {
-                            AZURE_CONNECTION_STRING = credentials('46b4e7d6-315f-4cc1-8333-b58780863b9b')
-                    }
-                    stages {
-                        stage('Checkout') {
-                            steps {
-                                checkout scm
-                            }
-                        }
-                        stage('Install azure-cli') {
-                            steps {
-                                installAzureCli('jammy', 'amd64')
-                            }
-                        }
-                        stage('Download assets') {
-                            steps {
-                                sh "mkdir ${env.HOME}/workloads"
-                                sh 'az storage blob download --container-name private-images --file "$HOME/workloads/windows-server-2022-amd64-2.raw" --name windows-server-2022-amd64-2.raw --connection-string "$AZURE_CONNECTION_STRING"'
-                            }
-                        }
-                        stage('Run Windows guest integration tests') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --integration-windows'
-                            }
-                        }
-                        stage('Run Windows guest integration tests for musl') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --integration-windows --libc musl'
-                            }
-                        }
-                    }
-                }
-                stage('Worker build - Metrics') {
-                    agent { node { label 'jammy-metrics' } }
-                    when {
-                        branch 'main'
-                        beforeAgent true
-                        expression {
-                            return runWorkers
-                        }
-                    }
-                    environment {
-                        METRICS_PUBLISH_KEY = credentials('52e0945f-ce7a-43d1-87af-67d1d87cc40f')
-                    }
-                    stages {
-                        stage('Checkout') {
-                            steps {
-                                checkout scm
-                            }
-                        }
-                        stage('Run metrics tests') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --metrics -- -- --report-file /root/workloads/metrics.json'
-                            }
-                        }
-                        stage('Upload metrics report') {
-                            steps {
-                                sh 'curl -X PUT https://cloud-hypervisor-metrics.azurewebsites.net/api/publishmetrics -H "x-functions-key: $METRICS_PUBLISH_KEY" -T ~/workloads/metrics.json'
-                            }
-                        }
-                    }
-                }
-                stage('Worker build - Rate Limiter') {
-                    agent { node { label 'focal-metrics' } }
-                    when {
-                        branch 'main'
-                        beforeAgent true
-                        expression {
-                            return runWorkers
-                        }
-                    }
-                    stages {
-                        stage('Checkout') {
-                            steps {
-                                checkout scm
-                            }
-                        }
-                        stage('Run rate-limiter integration tests') {
-                            options {
-                                timeout(time: 10, unit: 'MINUTES')
-                            }
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --integration-rate-limiter'
-                            }
-                        }
-                    }
-                }
-                stage('Worker build - SGX') {
-                    agent { node { label 'jammy-sgx' } }
-                    when {
-                        beforeAgent true
-                        allOf {
-                            branch 'main'
-                            expression {
-                                return runWorkers
-                            }
-                        }
-                    }
-                    environment {
-                        AUTH_DOWNLOAD_TOKEN = credentials('8a26fd74-d40e-414c-9132-ff3f867806ef')
-                    }
-                    stages {
-                        stage('Checkout') {
-                            steps {
-                                checkout scm
-                            }
-                        }
-                        stage('Run SGX integration tests') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --integration-sgx'
-                            }
-                        }
-                        stage('Run SGX integration tests for musl') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --integration-sgx --libc musl'
-                            }
-                        }
-                    }
-                    post {
-                        always {
-                            sh "sudo chown -R jenkins.jenkins ${WORKSPACE}"
-                            deleteDir()
-                        }
-                    }
-                }
-                stage('Worker build - VFIO') {
-                    agent { node { label 'jammy-vfio' } }
-                    when {
-                        beforeAgent true
-                        allOf {
-                            branch 'main'
-                            expression {
-                                return runWorkers
-                            }
-                        }
-                    }
-                    environment {
-                        AUTH_DOWNLOAD_TOKEN = credentials('8a26fd74-d40e-414c-9132-ff3f867806ef')
-                    }
-                    stages {
-                        stage('Checkout') {
-                            steps {
-                                checkout scm
-                            }
-                        }
-                        stage('Run VFIO integration tests') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --integration-vfio'
-                            }
-                        }
-                        stage('Run VFIO integration tests for musl') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --integration-vfio --libc musl'
-                            }
-                        }
-                    }
-                    post {
-                        always {
-                            sh "sudo chown -R jenkins.jenkins ${WORKSPACE}"
-                            deleteDir()
-                        }
-                    }
-                }
-            }
-        }
-    }
-    post {
-        regression {
-            script {
-                if (env.BRANCH_NAME == 'main') {
-                    slackSend(color: '#ff0000', message: '"main" branch build is now failing', channel: '#jenkins-ci')
-                }
-            }
-        }
-        fixed {
-            script {
-                if (env.BRANCH_NAME == 'main') {
-                    slackSend(color: '#00ff00', message: '"main" branch build is now fixed', channel: '#jenkins-ci')
-                }
-            }
-        }
-    }
-}
-
-def cancelPreviousBuilds() {
-    // Check for other instances of this particular build, cancel any that are older than the current one
-    def jobName = env.JOB_NAME
-    def currentBuildNumber = env.BUILD_NUMBER.toInteger()
-    def currentJob = Jenkins.instance.getItemByFullName(jobName)
-
-    // Loop through all instances of this particular job/branch
-    for (def build : currentJob.builds) {
-        if (build.isBuilding() && (build.number.toInteger() < currentBuildNumber)) {
-            echo "Older build still queued. Sending kill signal to build number: ${build.number}"
-            build.doStop()
-        }
-    }
-}
-
-def installAzureCli(distro, arch) {
-    sh 'sudo apt install -y ca-certificates curl apt-transport-https lsb-release gnupg'
-    sh 'curl -sL https://packages.microsoft.com/keys/microsoft.asc | gpg --dearmor | sudo tee /etc/apt/trusted.gpg.d/microsoft.gpg > /dev/null'
-    sh "echo \"deb [arch=${arch}] https://packages.microsoft.com/repos/azure-cli/ ${distro} main\" | sudo tee /etc/apt/sources.list.d/azure-cli.list"
-    sh 'sudo apt update'
-    sh 'sudo apt install -y azure-cli'
-}
-
-def boolean skipWorkerBuild() {
-    if (env.CHANGE_TARGET == null) {
-        return false
-    }
-
-    if (sh(
-        returnStatus: true,
-        script: "git diff --name-only origin/${env.CHANGE_TARGET}... | grep -v '\\.md'"
-    ) != 0) {
-        return true
-    }
-
-    if (sh(
-        returnStatus: true,
-        script: "git diff --name-only origin/${env.CHANGE_TARGET}... | grep -v -E 'fuzz/'"
-    ) != 0) {
-        return true
-    }
-
-    if (sh(
-        returnStatus: true,
-        script: "git diff --name-only origin/${env.CHANGE_TARGET}... | grep -v -E '.github/'"
-    ) != 0) {
-        return true
-    }
-
-    if (sh(
-        returnStatus: true,
-        script: "git diff --name-only origin/${env.CHANGE_TARGET}... | grep -v '^\\.'"
-    ) != 0) {
-        return true
-    }
-
-    if (sh(
-        returnStatus: true,
-        script: "git diff --name-only origin/${env.CHANGE_TARGET}... | grep -v 'gitlint'"
-    ) != 0) {
-        return true
-    }
-
-    return false
-}

LICENSES/CC-BY-4.0.txt

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

README.md

@@ -108,7 +108,7 @@ do not wish to use the pre-built binaries.
 ## Booting Linux
 
 Cloud Hypervisor supports direct kernel boot (the x86-64 kernel requires the kernel
-built with PVH support) or booting via a firmware (either [Rust Hypervisor
+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`.)
 
@@ -175,7 +175,7 @@ $ ./cloud-hypervisor \
 
 #### Building your Kernel
 
-Cloud Hypervisor also supports direct kernel boot. For x86-64, a `vmlinux` ELF kernel (compiled with PVH support) is needed. In order to support development there is a custom branch; however provided the required options are enabled any recent kernel will suffice.
+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.
 
 To build the kernel:
 

api_client/Cargo.toml

@@ -1,8 +1,9 @@
 [package]
-name = "api_client"
-version = "0.1.0"
 authors = ["The Cloud Hypervisor Authors"]
 edition = "2021"
+name = "api_client"
+version = "0.1.0"
 
 [dependencies]
+thiserror = "1.0.62"
 vmm-sys-util = "0.12.1"

api_client/src/lib.rs

@@ -3,41 +3,27 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
-use std::fmt;
 use std::io::{Read, Write};
 use std::os::unix::io::RawFd;
+use thiserror::Error;
 use vmm_sys_util::sock_ctrl_msg::ScmSocket;
 
-#[derive(Debug)]
+#[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:?}")]
     ServerResponse(StatusCode, Option<String>),
 }
 
-impl fmt::Display for Error {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        use Error::*;
-        match self {
-            Socket(e) => write!(f, "Error writing to or reading from HTTP socket: {e}"),
-            SocketSendFds(e) => write!(f, "Error writing to or reading from HTTP socket: {e}"),
-            StatusCodeParsing(e) => write!(f, "Error parsing HTTP status code: {e}"),
-            MissingProtocol => write!(f, "HTTP output is missing protocol statement"),
-            ContentLengthParsing(e) => write!(f, "Error parsing HTTP Content-Length field: {e}"),
-            ServerResponse(s, o) => {
-                if let Some(o) = o {
-                    write!(f, "Server responded with an error: {s:?}: {o}")
-                } else {
-                    write!(f, "Server responded with an error: {s:?}")
-                }
-            }
-        }
-    }
-}
-
 #[derive(Clone, Copy, Debug)]
 pub enum StatusCode {
     Continue,

arch/Cargo.toml

@@ -1,30 +1,32 @@
 [package]
-name = "arch"
-version = "0.1.0"
 authors = ["The Chromium OS Authors"]
 edition = "2021"
+name = "arch"
+version = "0.1.0"
 
 [features]
 default = []
+kvm = []
 sev_snp = []
 tdx = []
 
 [dependencies]
-anyhow = "1.0.79"
-byteorder = "1.4.3"
+anyhow = "1.0.86"
+byteorder = "1.5.0"
 hypervisor = { path = "../hypervisor" }
-libc = "0.2.153"
-linux-loader = { version = "0.11.0", features = ["elf", "bzimage", "pe"] }
-log = "0.4.20"
-serde = { version = "1.0.196", features = ["rc", "derive"] }
-thiserror = "1.0.52"
-uuid = "1.3.4"
-versionize = "0.2.0"
-versionize_derive = "0.1.6"
-vm-memory = { version = "0.14.0", features = ["backend-mmap", "backend-bitmap"] }
+libc = "0.2.155"
+linux-loader = { version = "0.11.0", features = ["bzimage", "elf", "pe"] }
+log = "0.4.22"
+serde = { version = "1.0.197", features = ["derive", "rc"] }
+thiserror = "1.0.62"
+uuid = "1.8.0"
+vm-memory = { version = "0.14.1", features = [
+  "backend-bitmap",
+  "backend-mmap",
+] }
 vm-migration = { path = "../vm-migration" }
 vmm-sys-util = { version = "0.12.1", features = ["with-serde"] }
 
 [target.'cfg(target_arch = "aarch64")'.dependencies]
-fdt_parser = { version = "0.1.4", package = "fdt" }
+fdt_parser = { version = "0.1.5", package = "fdt" }
 vm-fdt = { git = "https://github.com/rust-vmm/vm-fdt", branch = "main" }

arch/src/aarch64/fdt.rs

@@ -26,6 +26,7 @@ use super::layout::{
 };
 use std::fs;
 use std::path::Path;
+use thiserror::Error;
 use vm_fdt::{FdtWriter, FdtWriterResult};
 use vm_memory::{Address, Bytes, GuestMemory, GuestMemoryError, GuestMemoryRegion};
 
@@ -80,9 +81,10 @@ pub trait DeviceInfoForFdt {
 }
 
 /// Errors thrown while configuring the Flattened Device Tree for aarch64.
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum Error {
     /// Failure in writing FDT in memory.
+    #[error("Failure in writing FDT in memory: {0}")]
     WriteFdtToMemory(GuestMemoryError),
 }
 type Result<T> = result::Result<T, Error>;
@@ -523,7 +525,7 @@ fn create_memory_node(
                 let memory_region_size: u64 = memory_region.size() as u64;
                 mem_reg_prop.push(memory_region_start_addr);
                 mem_reg_prop.push(memory_region_size);
-                // Set the node address the first non-zero regison address
+                // Set the node address the first non-zero region address
                 if node_memory_addr == 0 {
                     node_memory_addr = memory_region_start_addr;
                 }
@@ -569,7 +571,7 @@ fn create_memory_node(
 
         if ram_regions.len() > 2 {
             panic!(
-                "There should be up to two non-continuous regions, devidided by the
+                "There should be up to two non-continuous regions, divided by the
                     gap at the end of 32bit address space."
             );
         }
@@ -894,7 +896,7 @@ fn create_pci_nodes(
     for pci_device_info_elem in pci_device_info.iter() {
         // EDK2 requires the PCIe high space above 4G address.
         // The actual space in CLH follows the RAM. If the RAM space is small, the PCIe high space
-        // could fall bellow 4G.
+        // could fall below 4G.
         // Here we cut off PCI device space below 8G in FDT to workaround the EDK2 check.
         // But the address written in ACPI is not impacted.
         let (pci_device_base_64bit, pci_device_size_64bit) =

arch/src/aarch64/mod.rs

@@ -16,35 +16,42 @@ use crate::{DeviceType, GuestMemoryMmap, NumaNodes, PciSpaceInfo, RegionType};
 use hypervisor::arch::aarch64::gic::Vgic;
 use log::{log_enabled, Level};
 use std::collections::HashMap;
-use std::convert::TryInto;
 use std::fmt::Debug;
 use std::sync::{Arc, Mutex};
+use thiserror::Error;
 use vm_memory::{Address, GuestAddress, GuestMemory, GuestMemoryAtomic};
 
 pub const _NSIG: i32 = 65;
 
 /// Errors thrown while configuring aarch64 system.
-#[derive(Debug)]
+#[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,
 }
 

arch/src/aarch64/uefi.rs

@@ -1,20 +1,27 @@
 // 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)]
+#[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>;

arch/src/lib.rs

@@ -18,9 +18,6 @@ use std::fmt;
 use std::result;
 use std::sync::Arc;
 use thiserror::Error;
-use versionize::{VersionMap, Versionize, VersionizeError, VersionizeResult};
-use versionize_derive::Versionize;
-use vm_migration::VersionMapped;
 
 type GuestMemoryMmap = vm_memory::GuestMemoryMmap<vm_memory::bitmap::AtomicBitmap>;
 type GuestRegionMmap = vm_memory::GuestRegionMmap<vm_memory::bitmap::AtomicBitmap>;
@@ -48,13 +45,17 @@ pub enum Error {
     ModlistSetup(#[source] vm_memory::GuestMemoryError),
     #[error("RSDP extends past the end of guest memory")]
     RsdpPastRamEnd,
+    #[error("Failed to setup Zero Page for bzImage")]
+    ZeroPageSetup(#[source] vm_memory::GuestMemoryError),
+    #[error("Zero Page for bzImage past RAM end")]
+    ZeroPagePastRamEnd,
 }
 
 /// Type for returning public functions outcome.
 pub type Result<T> = result::Result<T, Error>;
 
 /// Type for memory region types.
-#[derive(Clone, Copy, PartialEq, Eq, Debug, Serialize, Deserialize, Versionize)]
+#[derive(Clone, Copy, PartialEq, Eq, Debug, Serialize, Deserialize)]
 pub enum RegionType {
     /// RAM type
     Ram,
@@ -72,8 +73,6 @@ pub enum RegionType {
     Reserved,
 }
 
-impl VersionMapped for RegionType {}
-
 /// Module for aarch64 related functionality.
 #[cfg(target_arch = "aarch64")]
 pub mod aarch64;

arch/src/x86_64/mod.rs

@@ -17,11 +17,13 @@ use crate::InitramfsConfig;
 use crate::RegionType;
 use hypervisor::arch::x86::{CpuIdEntry, CPUID_FLAG_VALID_INDEX};
 use hypervisor::{CpuVendor, HypervisorCpuError, HypervisorError};
+use linux_loader::loader::bootparam::{boot_params, setup_header};
 use linux_loader::loader::elf::start_info::{
     hvm_memmap_table_entry, hvm_modlist_entry, hvm_start_info,
 };
 use std::collections::BTreeMap;
 use std::mem;
+use thiserror::Error;
 use vm_memory::{
     Address, Bytes, GuestAddress, GuestAddressSpace, GuestMemory, GuestMemoryAtomic,
     GuestMemoryRegion, GuestUsize,
@@ -32,6 +34,7 @@ use std::arch::x86_64;
 pub mod tdx;
 
 // CPUID feature bits
+#[cfg(feature = "kvm")]
 const TSC_DEADLINE_TIMER_ECX_BIT: u8 = 24; // tsc deadline timer ecx bit.
 const HYPERVISOR_ECX_BIT: u8 = 31; // Hypervisor ecx bit.
 const MTRR_EDX_BIT: u8 = 12; // Hypervisor ecx bit.
@@ -63,6 +66,8 @@ pub const _NSIG: i32 = 65;
 pub struct EntryPoint {
     /// Address in guest memory where the guest must start execution
     pub entry_addr: GuestAddress,
+    /// This field is used for bzImage to fill the zero page
+    pub setup_header: Option<setup_header>,
 }
 
 const E820_RAM: u32 = 1;
@@ -124,62 +129,84 @@ pub struct CpuidConfig {
     pub amx: bool,
 }
 
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum Error {
     /// Error writing MP table to memory.
+    #[error("Error writing MP table to memory: {0}")]
     MpTableSetup(mptable::Error),
 
     /// Error configuring the general purpose registers
+    #[error("Error configuring the general purpose registers: {0}")]
     RegsConfiguration(regs::Error),
 
     /// Error configuring the special registers
+    #[error("Error configuring the special registers: {0}")]
     SregsConfiguration(regs::Error),
 
     /// Error configuring the floating point related registers
+    #[error("Error configuring the floating point related registers: {0}")]
     FpuConfiguration(regs::Error),
 
     /// Error configuring the MSR registers
+    #[error("Error configuring the MSR registers: {0}")]
     MsrsConfiguration(regs::Error),
 
     /// Failed to set supported CPUs.
+    #[error("Failed to set supported CPUs: {0}")]
     SetSupportedCpusFailed(anyhow::Error),
 
     /// Cannot set the local interruption due to bad configuration.
+    #[error("Cannot set the local interruption due to bad configuration: {0}")]
     LocalIntConfiguration(anyhow::Error),
 
     /// Error setting up SMBIOS table
+    #[error("Error setting up SMBIOS table: {0}")]
     SmbiosSetup(smbios::Error),
 
     /// Could not find any SGX EPC section
+    #[error("Could not find any SGX EPC section")]
     NoSgxEpcSection,
 
     /// Missing SGX CPU feature
+    #[error("Missing SGX CPU feature")]
     MissingSgxFeature,
 
     /// Missing SGX_LC CPU feature
+    #[error("Missing SGX_LC CPU feature")]
     MissingSgxLaunchControlFeature,
 
     /// Error getting supported CPUID through the hypervisor (kvm/mshv) API
+    #[error("Error getting supported CPUID through the hypervisor API: {0}")]
     CpuidGetSupported(HypervisorError),
 
     /// Error populating CPUID with KVM HyperV emulation details
+    #[error("Error populating CPUID with KVM HyperV emulation details: {0}")]
     CpuidKvmHyperV(vmm_sys_util::fam::Error),
 
     /// Error populating CPUID with CPU identification
+    #[error("Error populating CPUID with CPU identification: {0}")]
     CpuidIdentification(vmm_sys_util::fam::Error),
 
     /// Error checking CPUID compatibility
+    #[error("Error checking CPUID compatibility")]
     CpuidCheckCompatibility,
 
     // Error writing EBDA address
+    #[error("Error writing EBDA address: {0}")]
     EbdaSetup(vm_memory::GuestMemoryError),
 
     // Error getting CPU TSC frequency
+    #[error("Error getting CPU TSC frequency: {0}")]
     GetTscFrequency(HypervisorCpuError),
 
     /// Error retrieving TDX capabilities through the hypervisor (kvm/mshv) API
     #[cfg(feature = "tdx")]
+    #[error("Error retrieving TDX capabilities through the hypervisor API: {0}")]
     TdxCapabilities(HypervisorError),
+
+    /// Failed to configure E820 map for bzImage
+    #[error("Failed to configure E820 map for bzImage")]
+    E820Configuration,
 }
 
 impl From<Error> for super::Error {
@@ -551,7 +578,7 @@ impl CpuidFeatureEntry {
             if !entry_compatible {
                 error!(
                     "Detected incompatible CPUID entry: leaf={:#02x} (subleaf={:#02x}), register='{:?}', \
-                    compatilbe_check='{:?}', source VM feature='{:#04x}', destination VM feature'{:#04x}'.",
+                    compatible_check='{:?}', source VM feature='{:#04x}', destination VM feature'{:#04x}'.",
                     entry.function, entry.index, entry.feature_reg,
                     entry.compatible_check, src_vm_feature, dest_vm_feature
                     );
@@ -593,17 +620,8 @@ pub fn generate_common_cpuid(
         "Generating guest CPUID for with physical address size: {}",
         config.phys_bits
     );
-    let cpuid_patches = vec![
-        // Patch tsc deadline timer bit
-        CpuidPatch {
-            function: 1,
-            index: 0,
-            flags_bit: None,
-            eax_bit: None,
-            ebx_bit: None,
-            ecx_bit: Some(TSC_DEADLINE_TIMER_ECX_BIT),
-            edx_bit: None,
-        },
+    #[allow(unused_mut)]
+    let mut cpuid_patches = vec![
         // Patch hypervisor bit
         CpuidPatch {
             function: 1,
@@ -626,6 +644,23 @@ pub fn generate_common_cpuid(
         },
     ];
 
+    #[cfg(feature = "kvm")]
+    if matches!(
+        hypervisor.hypervisor_type(),
+        hypervisor::HypervisorType::Kvm
+    ) {
+        // Patch tsc deadline timer bit
+        cpuid_patches.push(CpuidPatch {
+            function: 1,
+            index: 0,
+            flags_bit: None,
+            eax_bit: None,
+            ebx_bit: None,
+            ecx_bit: Some(TSC_DEADLINE_TIMER_ECX_BIT),
+            edx_bit: None,
+        });
+    }
+
     // Supported CPUID
     let mut cpuid = hypervisor
         .get_supported_cpuid()
@@ -676,6 +711,20 @@ pub fn generate_common_cpuid(
                     }
                 }
             }
+            // Copy host L1 cache details if not populated by KVM
+            0x8000_0005 => {
+                if entry.eax == 0 && entry.ebx == 0 && entry.ecx == 0 && entry.edx == 0 {
+                    // SAFETY: cpuid called with valid leaves
+                    if unsafe { std::arch::x86_64::__cpuid(0x8000_0000).eax } >= 0x8000_0005 {
+                        // SAFETY: cpuid called with valid leaves
+                        let leaf = unsafe { std::arch::x86_64::__cpuid(0x8000_0005) };
+                        entry.eax = leaf.eax;
+                        entry.ebx = leaf.ebx;
+                        entry.ecx = leaf.ecx;
+                        entry.edx = leaf.edx;
+                    }
+                }
+            }
             // Copy host L2 cache details if not populated by KVM
             0x8000_0006 => {
                 if entry.eax == 0 && entry.ebx == 0 && entry.ecx == 0 && entry.edx == 0 {
@@ -794,12 +843,17 @@ pub fn configure_vcpu(
         CpuidPatch::set_cpuid_reg(&mut cpuid, 0x8000_001e, Some(0), CpuidReg::EAX, x2apic_id);
     }
 
-    // Set ApicId in cpuid for each vcpu
-    // SAFETY: get host cpuid when eax=1
-    let mut cpu_ebx = unsafe { core::arch::x86_64::__cpuid(1) }.ebx;
-    cpu_ebx &= 0xffffff;
-    cpu_ebx |= x2apic_id << 24;
-    CpuidPatch::set_cpuid_reg(&mut cpuid, 0x1, None, CpuidReg::EBX, cpu_ebx);
+    // Set ApicId in cpuid for each vcpu - found in cpuid ebx when eax = 1
+    let mut apic_id_patched = false;
+    for entry in &mut cpuid {
+        if entry.function == 1 {
+            entry.ebx &= 0xffffff;
+            entry.ebx |= x2apic_id << 24;
+            apic_id_patched = true;
+            break;
+        }
+    }
+    assert!(apic_id_patched);
 
     if let Some(t) = topology {
         update_cpuid_topology(&mut cpuid, t.0, t.1, t.2, cpu_vendor, id);
@@ -842,8 +896,7 @@ pub fn configure_vcpu(
 
     regs::setup_msrs(vcpu).map_err(Error::MsrsConfiguration)?;
     if let Some((kernel_entry_point, guest_memory)) = boot_setup {
-        regs::setup_regs(vcpu, kernel_entry_point.entry_addr.raw_value())
-            .map_err(Error::RegsConfiguration)?;
+        regs::setup_regs(vcpu, kernel_entry_point).map_err(Error::RegsConfiguration)?;
         regs::setup_fpu(vcpu).map_err(Error::FpuConfiguration)?;
         regs::setup_sregs(&guest_memory.memory(), vcpu).map_err(Error::SregsConfiguration)?;
     }
@@ -892,8 +945,10 @@ pub fn arch_memory_regions() -> Vec<(GuestAddress, usize, RegionType)> {
 pub fn configure_system(
     guest_mem: &GuestMemoryMmap,
     cmdline_addr: GuestAddress,
+    cmdline_size: usize,
     initramfs: &Option<InitramfsConfig>,
     _num_cpus: u8,
+    setup_header: Option<setup_header>,
     rsdp_addr: Option<GuestAddress>,
     sgx_epc_region: Option<SgxEpcRegion>,
     serial_number: Option<&str>,
@@ -921,13 +976,24 @@ pub fn configure_system(
         }
     }
 
-    configure_pvh(
-        guest_mem,
-        cmdline_addr,
-        initramfs,
-        rsdp_addr,
-        sgx_epc_region,
-    )
+    match setup_header {
+        Some(hdr) => configure_32bit_entry(
+            guest_mem,
+            cmdline_addr,
+            cmdline_size,
+            initramfs,
+            hdr,
+            rsdp_addr,
+            sgx_epc_region,
+        ),
+        None => configure_pvh(
+            guest_mem,
+            cmdline_addr,
+            initramfs,
+            rsdp_addr,
+            sgx_epc_region,
+        ),
+    }
 }
 
 type RamRange = (u64, u64);
@@ -1132,6 +1198,113 @@ fn configure_pvh(
     Ok(())
 }
 
+fn configure_32bit_entry(
+    guest_mem: &GuestMemoryMmap,
+    cmdline_addr: GuestAddress,
+    cmdline_size: usize,
+    initramfs: &Option<InitramfsConfig>,
+    setup_hdr: setup_header,
+    rsdp_addr: Option<GuestAddress>,
+    sgx_epc_region: Option<SgxEpcRegion>,
+) -> super::Result<()> {
+    const KERNEL_LOADER_OTHER: u8 = 0xff;
+
+    // Use the provided setup header
+    let mut params = boot_params {
+        hdr: setup_hdr,
+        ..Default::default()
+    };
+
+    // Common bootparams settings
+    if params.hdr.type_of_loader == 0 {
+        params.hdr.type_of_loader = KERNEL_LOADER_OTHER;
+    }
+    params.hdr.cmd_line_ptr = cmdline_addr.raw_value() as u32;
+    params.hdr.cmdline_size = cmdline_size as u32;
+
+    if let Some(initramfs_config) = initramfs {
+        params.hdr.ramdisk_image = initramfs_config.address.raw_value() as u32;
+        params.hdr.ramdisk_size = initramfs_config.size as u32;
+    }
+
+    add_e820_entry(&mut params, 0, layout::EBDA_START.raw_value(), E820_RAM)?;
+
+    let mem_end = guest_mem.last_addr();
+    if mem_end < layout::MEM_32BIT_RESERVED_START {
+        add_e820_entry(
+            &mut params,
+            layout::HIGH_RAM_START.raw_value(),
+            mem_end.unchecked_offset_from(layout::HIGH_RAM_START) + 1,
+            E820_RAM,
+        )?;
+    } else {
+        add_e820_entry(
+            &mut params,
+            layout::HIGH_RAM_START.raw_value(),
+            layout::MEM_32BIT_RESERVED_START.unchecked_offset_from(layout::HIGH_RAM_START),
+            E820_RAM,
+        )?;
+        if mem_end > layout::RAM_64BIT_START {
+            add_e820_entry(
+                &mut params,
+                layout::RAM_64BIT_START.raw_value(),
+                mem_end.unchecked_offset_from(layout::RAM_64BIT_START) + 1,
+                E820_RAM,
+            )?;
+        }
+    }
+
+    add_e820_entry(
+        &mut params,
+        layout::PCI_MMCONFIG_START.0,
+        layout::PCI_MMCONFIG_SIZE,
+        E820_RESERVED,
+    )?;
+
+    if let Some(sgx_epc_region) = sgx_epc_region {
+        add_e820_entry(
+            &mut params,
+            sgx_epc_region.start().raw_value(),
+            sgx_epc_region.size(),
+            E820_RESERVED,
+        )?;
+    }
+
+    if let Some(rsdp_addr) = rsdp_addr {
+        params.acpi_rsdp_addr = rsdp_addr.0;
+    }
+
+    let zero_page_addr = layout::ZERO_PAGE_START;
+    guest_mem
+        .checked_offset(zero_page_addr, mem::size_of::<boot_params>())
+        .ok_or(super::Error::ZeroPagePastRamEnd)?;
+    guest_mem
+        .write_obj(params, zero_page_addr)
+        .map_err(super::Error::ZeroPageSetup)?;
+
+    Ok(())
+}
+
+/// Add an e820 region to the e820 map.
+/// Returns Ok(()) if successful, or an error if there is no space left in the map.
+fn add_e820_entry(
+    params: &mut boot_params,
+    addr: u64,
+    size: u64,
+    mem_type: u32,
+) -> Result<(), Error> {
+    if params.e820_entries >= params.e820_table.len() as u8 {
+        return Err(Error::E820Configuration);
+    }
+
+    params.e820_table[params.e820_entries as usize].addr = addr;
+    params.e820_table[params.e820_entries as usize].size = size;
+    params.e820_table[params.e820_entries as usize].type_ = mem_type;
+    params.e820_entries += 1;
+
+    Ok(())
+}
+
 fn add_memmap_entry(memmap: &mut Vec<hvm_memmap_table_entry>, addr: u64, size: u64, mem_type: u32) {
     // Add the table entry to the vector
     memmap.push(hvm_memmap_table_entry {
@@ -1378,6 +1551,7 @@ fn update_cpuid_sgx(
 #[cfg(test)]
 mod tests {
     use super::*;
+    use linux_loader::loader::bootparam::boot_e820_entry;
 
     #[test]
     fn regions_base_addr() {
@@ -1394,8 +1568,10 @@ mod tests {
         let config_err = configure_system(
             &gm,
             GuestAddress(0),
+            0,
             &None,
             1,
+            None,
             Some(layout::RSDP_POINTER),
             None,
             None,
@@ -1417,6 +1593,7 @@ mod tests {
         configure_system(
             &gm,
             GuestAddress(0),
+            0,
             &None,
             no_vcpus,
             None,
@@ -1425,6 +1602,7 @@ mod tests {
             None,
             None,
             None,
+            None,
         )
         .unwrap();
 
@@ -1445,6 +1623,7 @@ mod tests {
         configure_system(
             &gm,
             GuestAddress(0),
+            0,
             &None,
             no_vcpus,
             None,
@@ -1453,12 +1632,14 @@ mod tests {
             None,
             None,
             None,
+            None,
         )
         .unwrap();
 
         configure_system(
             &gm,
             GuestAddress(0),
+            0,
             &None,
             no_vcpus,
             None,
@@ -1467,10 +1648,51 @@ mod tests {
             None,
             None,
             None,
+            None,
         )
         .unwrap();
     }
 
+    #[test]
+    fn test_add_e820_entry() {
+        let e820_table = [(boot_e820_entry {
+            addr: 0x1,
+            size: 4,
+            type_: 1,
+        }); 128];
+
+        let expected_params = boot_params {
+            e820_table,
+            e820_entries: 1,
+            ..Default::default()
+        };
+
+        let mut params: boot_params = Default::default();
+        add_e820_entry(
+            &mut params,
+            e820_table[0].addr,
+            e820_table[0].size,
+            e820_table[0].type_,
+        )
+        .unwrap();
+        assert_eq!(
+            format!("{:?}", params.e820_table[0]),
+            format!("{:?}", expected_params.e820_table[0])
+        );
+        assert_eq!(params.e820_entries, expected_params.e820_entries);
+
+        // Exercise the scenario where the field storing the length of the e820 entry table is
+        // is bigger than the allocated memory.
+        params.e820_entries = params.e820_table.len() as u8 + 1;
+        assert!(add_e820_entry(
+            &mut params,
+            e820_table[0].addr,
+            e820_table[0].size,
+            e820_table[0].type_
+        )
+        .is_err());
+    }
+
     #[test]
     fn test_add_memmap_entry() {
         let mut memmap: Vec<hvm_memmap_table_entry> = Vec::new();

arch/src/x86_64/mpspec.rs

@@ -1,4 +1,6 @@
 // Copyright 2017 The Chromium OS Authors. All rights reserved.
+//
+// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE-BSD-3-Clause file.
 
@@ -15,7 +17,7 @@ pub const MP_IRQDIR_DEFAULT: ::std::os::raw::c_uint = 0;
 #[repr(C)]
 #[derive(Debug, Default, Copy, Clone)]
 pub struct mpf_intel {
-    pub signature: [::std::os::raw::c_char; 4usize],
+    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,
@@ -30,12 +32,12 @@ pub struct mpf_intel {
 #[repr(C)]
 #[derive(Debug, Default, Copy, Clone)]
 pub struct mpc_table {
-    pub signature: [::std::os::raw::c_char; 4usize],
+    pub signature: [::std::os::raw::c_uchar; 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 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,
@@ -104,9 +106,9 @@ pub struct mpc_lintsrc {
 #[repr(C)]
 #[derive(Debug, Default, Copy, Clone)]
 pub struct mpc_oemtable {
-    pub signature: [::std::os::raw::c_char; 4usize],
+    pub signature: [::std::os::raw::c_uchar; 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],
+    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

@@ -8,10 +8,11 @@
 use crate::layout::{APIC_START, HIGH_RAM_START, IOAPIC_START};
 use crate::x86_64::{get_x2apic_id, mpspec};
 use crate::GuestMemoryMmap;
-use libc::c_char;
+use libc::c_uchar;
 use std::mem;
 use std::result;
 use std::slice;
+use thiserror::Error;
 use vm_memory::{Address, ByteValued, Bytes, GuestAddress, GuestMemory, GuestMemoryError};
 
 // This is a workaround to the Rust enforcement specifying that any implementation of a foreign
@@ -49,29 +50,40 @@ unsafe impl ByteValued for MpcLintsrcWrapper {}
 // SAFETY: see above
 unsafe impl ByteValued for MpfIntelWrapper {}
 
-#[derive(Debug)]
+#[derive(Debug, Error)]
 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),
 }
 
@@ -82,18 +94,13 @@ 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_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 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 APIC_VERSION: u8 = 0x14;
 const CPU_STEPPING: u32 = 0x600;
 const CPU_FEATURE_APIC: u32 = 0x200;
@@ -168,7 +175,7 @@ pub fn setup_mptable(
     {
         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;
@@ -209,7 +216,7 @@ 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);
@@ -280,14 +287,14 @@ 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) as i8;
+        mpc_table.0.checksum = (!checksum).wrapping_add(1);
         mem.write_obj(mpc_table, table_base)
             .map_err(Error::WriteMpcTable)?;
     }
@@ -300,8 +307,7 @@ mod tests {
     use super::*;
     use crate::layout::MPTABLE_START;
     use vm_memory::{
-        bitmap::BitmapSlice, GuestAddress, GuestUsize, VolatileMemoryError, VolatileSlice,
-        WriteVolatile,
+        bitmap::BitmapSlice, GuestUsize, VolatileMemoryError, VolatileSlice, WriteVolatile,
     };
 
     fn table_entry_size(type_: u8) -> usize {

arch/src/x86_64/regs.rs

@@ -6,40 +6,55 @@
 // 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 crate::layout::{BOOT_GDT_START, BOOT_IDT_START, PVH_INFO_START};
-use crate::GuestMemoryMmap;
+use crate::layout::{
+    BOOT_GDT_START, BOOT_IDT_START, BOOT_STACK_POINTER, PVH_INFO_START, ZERO_PAGE_START,
+};
+use crate::{EntryPoint, GuestMemoryMmap};
 use hypervisor::arch::x86::gdt::{gdt_entry, segment_from_gdt};
 use hypervisor::arch::x86::regs::CR0_PE;
 use hypervisor::arch::x86::{FpuState, SpecialRegisters, StandardRegisters};
 use std::sync::Arc;
 use std::{mem, result};
+use thiserror::Error;
 use vm_memory::{Address, Bytes, GuestMemory, GuestMemoryError};
 
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum Error {
     /// Failed to get SREGs for this CPU.
+    #[error("Failed to get SREGs for this CPU: {0}")]
     GetStatusRegisters(hypervisor::HypervisorCpuError),
     /// Failed to set base registers for this CPU.
+    #[error("Failed to set base registers for this CPU: {0}")]
     SetBaseRegisters(hypervisor::HypervisorCpuError),
     /// Failed to configure the FPU.
+    #[error("Failed to configure the FPU: {0}")]
     SetFpuRegisters(hypervisor::HypervisorCpuError),
     /// Setting up MSRs failed.
+    #[error("Setting up MSRs failed: {0}")]
     SetModelSpecificRegisters(hypervisor::HypervisorCpuError),
     /// Failed to set SREGs for this CPU.
+    #[error("Failed to set SREGs for this CPU: {0}")]
     SetStatusRegisters(hypervisor::HypervisorCpuError),
     /// Checking the GDT address failed.
+    #[error("Checking the GDT address failed")]
     CheckGdtAddr,
     /// Writing the GDT to RAM failed.
+    #[error("Writing the GDT to RAM failed: {0}")]
     WriteGdt(GuestMemoryError),
     /// Writing the IDT to RAM failed.
+    #[error("Writing the IDT to RAM failed: {0}")]
     WriteIdt(GuestMemoryError),
     /// Writing PDPTE to RAM failed.
+    #[error("Writing PDPTE to RAM failed: {0}")]
     WritePdpteAddress(GuestMemoryError),
     /// Writing PDE to RAM failed.
+    #[error("Writing PDE to RAM failed: {0}")]
     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),
 }
 
@@ -77,13 +92,22 @@ pub fn setup_msrs(vcpu: &Arc<dyn hypervisor::Vcpu>) -> Result<()> {
 /// # Arguments
 ///
 /// * `vcpu` - Structure for the VCPU that holds the VCPU's fd.
-/// * `boot_ip` - Starting instruction pointer.
-pub fn setup_regs(vcpu: &Arc<dyn hypervisor::Vcpu>, boot_ip: u64) -> Result<()> {
-    let regs = StandardRegisters {
-        rflags: 0x0000000000000002u64,
-        rbx: PVH_INFO_START.raw_value(),
-        rip: boot_ip,
-        ..Default::default()
+/// * `entry_point` - Description of the boot entry to set up.
+pub fn setup_regs(vcpu: &Arc<dyn hypervisor::Vcpu>, entry_point: EntryPoint) -> Result<()> {
+    let regs = match entry_point.setup_header {
+        None => StandardRegisters {
+            rflags: 0x0000000000000002u64,
+            rip: entry_point.entry_addr.raw_value(),
+            rbx: PVH_INFO_START.raw_value(),
+            ..Default::default()
+        },
+        Some(_) => StandardRegisters {
+            rflags: 0x0000000000000002u64,
+            rip: entry_point.entry_addr.raw_value(),
+            rsp: BOOT_STACK_POINTER.raw_value(),
+            rsi: ZERO_PAGE_START.raw_value(),
+            ..Default::default()
+        },
     };
     vcpu.set_regs(&regs).map_err(Error::SetBaseRegisters)
 }
@@ -164,7 +188,6 @@ pub fn configure_segments_and_sregs(
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::GuestMemoryMmap;
     use vm_memory::GuestAddress;
 
     fn create_guest_mem() -> GuestMemoryMmap {

arch/src/x86_64/smbios.rs

@@ -8,53 +8,36 @@
 
 use crate::layout::SMBIOS_START;
 use crate::GuestMemoryMmap;
-use std::fmt::{self, Display};
 use std::mem;
 use std::result;
 use std::slice;
+use thiserror::Error;
 use uuid::Uuid;
 use vm_memory::ByteValued;
 use vm_memory::{Address, Bytes, GuestAddress};
 
-#[derive(Debug)]
+#[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),
 }
 
-impl std::error::Error for Error {}
-
-impl Display for Error {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        use self::Error::*;
-
-        let description = match self {
-            NotEnoughMemory => {
-                "There was too little guest memory to store the SMBIOS table".to_string()
-            }
-            AddressOverflow => {
-                "The SMBIOS table has too little address space to be stored".to_string()
-            }
-            Clear => "Failure while zeroing out the memory for the SMBIOS table".to_string(),
-            WriteSmbiosEp => "Failure to write SMBIOS entrypoint structure".to_string(),
-            WriteData => "Failure to write additional data to memory".to_string(),
-            ParseUuid(e) => format!("Failure to parse uuid: {e}"),
-        };
-
-        write!(f, "SMBIOS error: {description}")
-    }
-}
-
 pub type Result<T> = result::Result<T, Error>;
 
 // Constants sourced from SMBIOS Spec 3.2.0.

block/Cargo.toml

@@ -1,27 +1,30 @@
 [package]
+authors = ["The Chromium OS Authors", "The Cloud Hypervisor Authors"]
+edition = "2021"
 name = "block"
 version = "0.1.0"
-edition = "2021"
-authors = ["The Cloud Hypervisor Authors", "The Chromium OS Authors"]
 
 [features]
 default = []
 io_uring = ["dep:io-uring"]
 
 [dependencies]
-byteorder = "1.4.3"
+byteorder = "1.5.0"
 crc-any = "2.4.4"
-io-uring = { version = "0.6.2", optional = true }
-libc = "0.2.153"
-log = "0.4.20"
-remain = "0.2.11"
-smallvec = "1.13.1"
-thiserror = "1.0.52"
-uuid = { version = "1.3.4", features = ["v4"] }
-versionize = "0.2.0"
-versionize_derive = "0.1.6"
-virtio-bindings = { version = "0.2.0", features = ["virtio-v5_0_0"] }
-virtio-queue = "0.11.0"
-vm-memory = { version = "0.14.0", features = ["backend-mmap", "backend-atomic", "backend-bitmap"] }
+io-uring = { version = "0.6.3", optional = true }
+libc = "0.2.155"
+log = "0.4.22"
+remain = "0.2.14"
+serde = { version = "1.0.197", features = ["derive"] }
+smallvec = "1.13.2"
+thiserror = "1.0.62"
+uuid = { version = "1.8.0", features = ["v4"] }
+virtio-bindings = { version = "0.2.2", features = ["virtio-v5_0_0"] }
+virtio-queue = "0.12.0"
+vm-memory = { version = "0.14.1", features = [
+  "backend-atomic",
+  "backend-bitmap",
+  "backend-mmap",
+] }
 vm-virtio = { path = "../vm-virtio" }
 vmm-sys-util = "0.12.1"

block/src/lib.rs

@@ -37,11 +37,11 @@ use crate::vhdx::{Vhdx, VhdxError};
 #[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 std::alloc::{alloc_zeroed, dealloc, Layout};
 use std::cmp;
 use std::collections::VecDeque;
-use std::convert::TryInto;
 use std::fmt::Debug;
 use std::fs::File;
 use std::io::{self, IoSlice, IoSliceMut, Read, Seek, SeekFrom, Write};
@@ -53,21 +53,17 @@ use std::sync::Arc;
 use std::sync::MutexGuard;
 use std::time::Instant;
 use thiserror::Error;
-use versionize::{VersionMap, Versionize, VersionizeResult};
-use versionize_derive::Versionize;
 use virtio_bindings::virtio_blk::*;
 use virtio_queue::DescriptorChain;
 use vm_memory::{
-    bitmap::AtomicBitmap, bitmap::Bitmap, ByteValued, Bytes, GuestAddress, GuestMemory,
-    GuestMemoryError, GuestMemoryLoadGuard,
+    bitmap::Bitmap, ByteValued, Bytes, GuestAddress, GuestMemory, GuestMemoryError,
+    GuestMemoryLoadGuard,
 };
 use vm_virtio::{AccessPlatform, Translatable};
 use vmm_sys_util::aio;
 use vmm_sys_util::eventfd::EventFd;
 use vmm_sys_util::{ioctl_io_nr, ioctl_ioc_nr};
 
-type GuestMemoryMmap = vm_memory::GuestMemoryMmap<AtomicBitmap>;
-
 const SECTOR_SHIFT: u8 = 9;
 pub const SECTOR_SIZE: u64 = 0x01 << SECTOR_SHIFT;
 
@@ -168,8 +164,8 @@ pub enum ExecuteError {
 }
 
 impl ExecuteError {
-    pub fn status(&self) -> u32 {
-        match *self {
+    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,
@@ -184,7 +180,8 @@ impl ExecuteError {
             ExecuteError::AsyncWrite(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::AsyncFlush(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::TemporaryBufferAllocation(_) => VIRTIO_BLK_S_IOERR,
-        }
+        };
+        status as u8
     }
 }
 
@@ -197,8 +194,8 @@ pub enum RequestType {
     Unsupported(u32),
 }
 
-pub fn request_type(
-    mem: &GuestMemoryMmap,
+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)?;
@@ -211,7 +208,10 @@ pub fn request_type(
     }
 }
 
-fn sector(mem: &GuestMemoryMmap, desc_addr: GuestAddress) -> result::Result<u64, Error> {
+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,
@@ -241,16 +241,15 @@ pub struct Request {
 }
 
 impl Request {
-    pub fn parse(
-        desc_chain: &mut DescriptorChain<GuestMemoryLoadGuard<GuestMemoryMmap>>,
+    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)
-            .map_err(|e| {
+            .inspect_err(|_| {
                 error!("Missing head descriptor");
-                e
             })?;
 
         // The head contains the request type which MUST be readable.
@@ -276,9 +275,8 @@ impl Request {
         let mut desc = desc_chain
             .next()
             .ok_or(Error::DescriptorChainTooShort)
-            .map_err(|e| {
+            .inspect_err(|_| {
                 error!("Only head descriptor present: request = {:?}", req);
-                e
             })?;
 
         if !desc.has_next() {
@@ -309,9 +307,8 @@ impl Request {
                 desc = desc_chain
                     .next()
                     .ok_or(Error::DescriptorChainTooShort)
-                    .map_err(|e| {
+                    .inspect_err(|_| {
                         error!("DescriptorChain corrupted: request = {:?}", req);
-                        e
                     })?;
             }
             status_desc = desc;
@@ -333,11 +330,11 @@ impl Request {
         Ok(req)
     }
 
-    pub fn execute<T: Seek + Read + Write>(
+    pub fn execute<T: Seek + Read + Write, B: Bitmap + 'static>(
         &self,
         disk: &mut T,
         disk_nsectors: u64,
-        mem: &GuestMemoryMmap,
+        mem: &vm_memory::GuestMemoryMmap<B>,
         serial: &[u8],
     ) -> result::Result<u32, ExecuteError> {
         disk.seek(SeekFrom::Start(self.sector << SECTOR_SHIFT))
@@ -390,9 +387,9 @@ impl Request {
         Ok(len)
     }
 
-    pub fn execute_async(
+    pub fn execute_async<B: Bitmap + 'static>(
         &mut self,
-        mem: &GuestMemoryMmap,
+        mem: &vm_memory::GuestMemoryMmap<B>,
         disk_nsectors: u64,
         disk_image: &mut dyn AsyncIo,
         serial: &[u8],
@@ -545,7 +542,7 @@ impl Request {
     }
 }
 
-#[derive(Copy, Clone, Debug, Default, Versionize)]
+#[derive(Copy, Clone, Debug, Default, Serialize, Deserialize)]
 #[repr(C, packed)]
 pub struct VirtioBlockConfig {
     pub capacity: u64,
@@ -568,7 +565,7 @@ pub struct VirtioBlockConfig {
     pub write_zeroes_may_unmap: u8,
     pub unused1: [u8; 3],
 }
-#[derive(Copy, Clone, Debug, Default, Versionize)]
+#[derive(Copy, Clone, Debug, Default, Serialize, Deserialize)]
 #[repr(C, packed)]
 pub struct VirtioBlockGeometry {
     pub cylinders: u16,
@@ -660,7 +657,9 @@ where
         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(*iovec) }));
+            slices.push(IoSliceMut::new(unsafe {
+                std::mem::transmute::<libc::iovec, &mut [u8]>(*iovec)
+            }));
         }
 
         let result = {
@@ -693,7 +692,9 @@ where
         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(*iovec) }));
+            slices.push(IoSlice::new(unsafe {
+                std::mem::transmute::<libc::iovec, &mut [u8]>(*iovec)
+            }));
         }
 
         let result = {

block/src/qcow/mod.rs

@@ -1,6 +1,8 @@
 // Copyright 2018 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
 
 mod qcow_raw_file;
 mod raw_file;
@@ -17,11 +19,11 @@ use byteorder::{BigEndian, ReadBytesExt, WriteBytesExt};
 use libc::{EINVAL, ENOSPC, ENOTSUP};
 use remain::sorted;
 use std::cmp::{max, min};
-use std::fmt::{self, Display};
 use std::fs::OpenOptions;
 use std::io::{self, Read, Seek, SeekFrom, Write};
 use std::mem::size_of;
 use std::str;
+use thiserror::Error;
 use vmm_sys_util::{
     file_traits::FileSetLen, file_traits::FileSync, seek_hole::SeekHole, write_zeroes::PunchHole,
     write_zeroes::WriteZeroesAt,
@@ -29,106 +31,98 @@ use vmm_sys_util::{
 
 pub use crate::qcow::raw_file::RawFile;
 
+/// Nesting depth limit for disk formats that can open other disk files.
+const MAX_NESTING_DEPTH: u32 = 10;
+
 #[sorted]
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum Error {
+    #[error("Backing file io error: {0}")]
     BackingFileIo(io::Error),
-    BackingFileOpen(Box<crate::Error>),
+    #[error("Backing file open error: {0}")]
+    BackingFileOpen(Box<Error>),
+    #[error("Backing file name is too long: {0} bytes over")]
     BackingFileTooLong(usize),
+    #[error("Compressed blocks not supported")]
     CompressedBlocksNotSupported,
+    #[error("Failed to evict cache: {0}")]
     EvictingCache(io::Error),
+    #[error("File larger than max of {}: {0}", MAX_QCOW_FILE_SIZE)]
     FileTooBig(u64),
+    #[error("Failed to get file size: {0}")]
     GettingFileSize(io::Error),
+    #[error("Failed to get refcount: {0}")]
     GettingRefcount(refcount::Error),
+    #[error("Failed to parse filename: {0}")]
     InvalidBackingFileName(str::Utf8Error),
+    #[error("Invalid cluster index")]
     InvalidClusterIndex,
+    #[error("Invalid cluster size")]
     InvalidClusterSize,
+    #[error("Invalid index")]
     InvalidIndex,
+    #[error("Invalid L1 table offset")]
     InvalidL1TableOffset,
+    #[error("Invalid L1 table size: {0}")]
     InvalidL1TableSize(u32),
+    #[error("Invalid magic")]
     InvalidMagic,
+    #[error("Invalid offset: {0}")]
     InvalidOffset(u64),
+    #[error("Invalid refcount table offset")]
     InvalidRefcountTableOffset,
+    #[error("Invalid refcount table size: {0}")]
     InvalidRefcountTableSize(u64),
+    #[error("Maximum disk nesting depth exceeded")]
+    MaxNestingDepthExceeded,
+    #[error("No free clusters")]
     NoFreeClusters,
+    #[error("No refcount clusters")]
     NoRefcountClusters,
+    #[error("Not enough space for refcounts")]
     NotEnoughSpaceForRefcounts,
+    #[error("Failed to open file {0}")]
     OpeningFile(io::Error),
+    #[error("Failed to read data: {0}")]
     ReadingData(io::Error),
+    #[error("Failed to read header: {0}")]
     ReadingHeader(io::Error),
+    #[error("Failed to read pointers: {0}")]
     ReadingPointers(io::Error),
+    #[error("Failed to read ref count block: {0}")]
     ReadingRefCountBlock(refcount::Error),
+    #[error("Failed to read ref counts: {0}")]
     ReadingRefCounts(io::Error),
+    #[error("Failed to rebuild ref counts: {0}")]
     RebuildingRefCounts(io::Error),
+    #[error("Refcount table offset past file end")]
     RefcountTableOffEnd,
+    #[error("Too many clusters specified for refcount")]
     RefcountTableTooLarge,
+    #[error("Failed to seek file: {0}")]
     SeekingFile(io::Error),
+    #[error("Failed to set file size: {0}")]
     SettingFileSize(io::Error),
+    #[error("Failed to set refcount refcount: {0}")]
     SettingRefcountRefcount(io::Error),
+    #[error("Size too small for number of clusters")]
     SizeTooSmallForNumberOfClusters,
+    #[error("L1 entry table too large: {0}")]
     TooManyL1Entries(u64),
+    #[error("Ref count table too large: {0}")]
     TooManyRefcounts(u64),
+    #[error("Unsupported refcount order")]
     UnsupportedRefcountOrder,
+    #[error("Unsupported version: {0}")]
     UnsupportedVersion(u32),
+    #[error("Failed to write data: {0}")]
     WritingData(io::Error),
+    #[error("Failed to write header: {0}")]
     WritingHeader(io::Error),
 }
 
 pub type Result<T> = std::result::Result<T, Error>;
 
-impl Display for Error {
-    #[remain::check]
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        use self::Error::*;
-
-        #[sorted]
-        match self {
-            BackingFileIo(e) => write!(f, "backing file io error: {}", e),
-            BackingFileOpen(e) => write!(f, "backing file open error: {}", *e),
-            BackingFileTooLong(len) => {
-                write!(f, "backing file name is too long: {} bytes over", len)
-            }
-            CompressedBlocksNotSupported => write!(f, "compressed blocks not supported"),
-            EvictingCache(e) => write!(f, "failed to evict cache: {e}"),
-            FileTooBig(size) => write!(f, "file larger than max of {MAX_QCOW_FILE_SIZE}: {size}"),
-            GettingFileSize(e) => write!(f, "failed to get file size: {e}"),
-            GettingRefcount(e) => write!(f, "failed to get refcount: {e}"),
-            InvalidBackingFileName(e) => write!(f, "failed to parse filename: {}", e),
-            InvalidClusterIndex => write!(f, "invalid cluster index"),
-            InvalidClusterSize => write!(f, "invalid cluster size"),
-            InvalidIndex => write!(f, "invalid index"),
-            InvalidL1TableOffset => write!(f, "invalid L1 table offset"),
-            InvalidL1TableSize(size) => write!(f, "invalid L1 table size {size}"),
-            InvalidMagic => write!(f, "invalid magic"),
-            InvalidOffset(_) => write!(f, "invalid offset"),
-            InvalidRefcountTableOffset => write!(f, "invalid refcount table offset"),
-            InvalidRefcountTableSize(size) => write!(f, "invalid refcount table size: {size}"),
-            NoFreeClusters => write!(f, "no free clusters"),
-            NoRefcountClusters => write!(f, "no refcount clusters"),
-            NotEnoughSpaceForRefcounts => write!(f, "not enough space for refcounts"),
-            OpeningFile(e) => write!(f, "failed to open file: {e}"),
-            ReadingData(e) => write!(f, "failed to read data: {e}"),
-            ReadingHeader(e) => write!(f, "failed to read header: {e}"),
-            ReadingPointers(e) => write!(f, "failed to read pointers: {e}"),
-            ReadingRefCountBlock(e) => write!(f, "failed to read ref count block: {e}"),
-            ReadingRefCounts(e) => write!(f, "failed to read ref counts: {e}"),
-            RebuildingRefCounts(e) => write!(f, "failed to rebuild ref counts: {e}"),
-            RefcountTableOffEnd => write!(f, "refcount table offset past file end"),
-            RefcountTableTooLarge => write!(f, "too many clusters specified for refcount table"),
-            SeekingFile(e) => write!(f, "failed to seek file: {e}"),
-            SettingFileSize(e) => write!(f, "failed to set file size: {e}"),
-            SettingRefcountRefcount(e) => write!(f, "failed to set refcount refcount: {e}"),
-            SizeTooSmallForNumberOfClusters => write!(f, "size too small for number of clusters"),
-            TooManyL1Entries(count) => write!(f, "l1 entry table too large: {count}"),
-            TooManyRefcounts(count) => write!(f, "ref count table too large: {count}"),
-            UnsupportedRefcountOrder => write!(f, "unsupported refcount order"),
-            UnsupportedVersion(v) => write!(f, "unsupported version: {v}"),
-            WritingData(e) => write!(f, "failed to write data: {e}"),
-            WritingHeader(e) => write!(f, "failed to write header: {e}"),
-        }
-    }
-}
-
 pub enum ImageType {
     Raw,
     Qcow2,
@@ -445,12 +439,20 @@ pub struct QcowFile {
     // List of unreferenced clusters available to be used. unref clusters become available once the
     // removal of references to them have been synced to disk.
     avail_clusters: Vec<u64>,
-    backing_file: Option<Box<dyn BlockBackend>>,
+    backing_file: Option<Box<Self>>,
 }
 
 impl QcowFile {
     /// Creates a QcowFile from `file`. File must be a valid qcow2 image.
-    pub fn from(mut file: RawFile) -> Result<QcowFile> {
+    ///
+    /// Additionally, max nesting depth of this qcow2 image will be set to default value 10.
+    pub fn from(file: RawFile) -> Result<QcowFile> {
+        Self::from_with_nesting_depth(file, MAX_NESTING_DEPTH)
+    }
+
+    /// Creates a QcowFile from `file` and with a max nesting depth. File must be a valid qcow2
+    /// image.
+    pub fn from_with_nesting_depth(mut file: RawFile, max_nesting_depth: u32) -> Result<QcowFile> {
         let header = QcowHeader::new(&mut file)?;
 
         // Only v2 and v3 files are supported.
@@ -477,14 +479,20 @@ impl QcowFile {
         let direct_io = file.is_direct();
 
         let backing_file = if let Some(backing_file_path) = header.backing_file_path.as_ref() {
+            if max_nesting_depth == 0 {
+                return Err(Error::MaxNestingDepthExceeded);
+            }
             let path = backing_file_path.clone();
             let backing_raw_file = OpenOptions::new()
                 .read(true)
                 .open(path)
                 .map_err(Error::BackingFileIo)?;
-            let backing_file = crate::create_disk_file(backing_raw_file, direct_io)
-                .map_err(|e| Error::BackingFileOpen(Box::new(e)))?;
-            Some(backing_file)
+            let backing_file = Self::from_with_nesting_depth(
+                RawFile::new(backing_raw_file, direct_io),
+                max_nesting_depth - 1,
+            )
+            .map_err(|e| Error::BackingFileOpen(Box::new(e)))?;
+            Some(Box::new(backing_file))
         } else {
             None
         };
@@ -632,20 +640,22 @@ impl QcowFile {
         file: RawFile,
         version: u32,
         backing_file_name: &str,
+        backing_file_max_nesting_depth: u32,
     ) -> Result<QcowFile> {
         let direct_io = file.is_direct();
         let backing_raw_file = OpenOptions::new()
             .read(true)
             .open(backing_file_name)
             .map_err(Error::BackingFileIo)?;
-        let backing_file = crate::create_disk_file(backing_raw_file, direct_io)
-            .map_err(|e| Error::BackingFileOpen(Box::new(e)))?;
-        let size = backing_file
-            .size()
-            .map_err(|e| Error::BackingFileOpen(Box::new(e)))?;
+        let backing_file = Self::from_with_nesting_depth(
+            RawFile::new(backing_raw_file, direct_io),
+            backing_file_max_nesting_depth,
+        )
+        .map_err(|e| Error::BackingFileOpen(Box::new(e)))?;
+        let size = backing_file.virtual_size();
         let header = QcowHeader::create_for_size_and_path(version, size, Some(backing_file_name))?;
         let mut result = QcowFile::new_from_header(file, header)?;
-        result.backing_file = Some(backing_file);
+        result.backing_file = Some(Box::new(backing_file));
         Ok(result)
     }
 
@@ -673,7 +683,7 @@ impl QcowFile {
         Ok(qcow)
     }
 
-    pub fn set_backing_file(&mut self, backing: Option<Box<dyn BlockBackend>>) {
+    pub fn set_backing_file(&mut self, backing: Option<Box<Self>>) {
         self.backing_file = backing;
     }
 
@@ -1211,7 +1221,7 @@ impl QcowFile {
     }
 
     // Allocate and initialize a new data cluster. Returns the offset of the
-    // cluster in to the file on success.
+    // cluster into the file on success.
     fn append_data_cluster(&mut self, initial_data: Option<Vec<u8>>) -> std::io::Result<u64> {
         let new_addr: u64 = self.get_new_cluster(initial_data)?;
         // The cluster refcount starts at one indicating it is used but doesn't need COW.
@@ -1629,7 +1639,7 @@ impl PunchHole for QcowFile {
         let mut remaining = length;
         let mut offset = offset;
         while remaining > 0 {
-            let chunk_length = min(remaining, std::usize::MAX as u64) as usize;
+            let chunk_length = min(remaining, usize::MAX as u64) as usize;
             self.deallocate_bytes(offset, chunk_length)?;
             remaining -= chunk_length as u64;
             offset += chunk_length as u64;
@@ -1789,11 +1799,17 @@ where
 /// Copy the contents of a disk image in `src_file` into `dst_file`.
 /// The type of `src_file` is automatically detected, and the output file type is
 /// determined by `dst_type`.
-pub fn convert(mut src_file: RawFile, dst_file: RawFile, dst_type: ImageType) -> Result<()> {
+pub fn convert(
+    mut src_file: RawFile,
+    dst_file: RawFile,
+    dst_type: ImageType,
+    src_max_nesting_depth: u32,
+) -> Result<()> {
     let src_type = detect_image_type(&mut src_file)?;
     match src_type {
         ImageType::Qcow2 => {
-            let mut src_reader = QcowFile::from(src_file)?;
+            let mut src_reader =
+                QcowFile::from_with_nesting_depth(src_file, src_max_nesting_depth)?;
             convert_reader(&mut src_reader, dst_file, dst_type)
         }
         ImageType::Raw => {
@@ -1822,7 +1838,9 @@ pub fn detect_image_type(file: &mut RawFile) -> Result<ImageType> {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use std::io::{Read, Seek, SeekFrom, Write};
+    use std::fs::File;
+    use std::path::Path;
+    use vmm_sys_util::tempdir::TempDir;
     use vmm_sys_util::tempfile::TempFile;
     use vmm_sys_util::write_zeroes::WriteZeroes;
 
@@ -2022,6 +2040,82 @@ mod tests {
         assert_eq!(read_header.backing_file_path, header.backing_file_path);
     }
 
+    #[test]
+    fn no_backing_file() {
+        // `backing_file` is `None`
+        let header = QcowHeader::create_for_size_and_path(3, 0x10_0000, None)
+            .expect("Failed to create header.");
+        let mut disk_file: RawFile = RawFile::new(TempFile::new().unwrap().into_file(), false);
+        header
+            .write_to(&mut disk_file)
+            .expect("Failed to write header to shm.");
+        disk_file.rewind().unwrap();
+        // The maximum nesting depth is 0, which means backing file is not allowed.
+        let res = QcowFile::from_with_nesting_depth(disk_file, 0);
+        assert!(res.is_ok());
+    }
+
+    #[test]
+    fn disable_backing_file() {
+        // `backing_file` is `Some`
+        let header =
+            QcowHeader::create_for_size_and_path(3, 0x10_0000, Some("/path/to/backing/file"))
+                .expect("Failed to create header.");
+        let mut disk_file: RawFile = RawFile::new(TempFile::new().unwrap().into_file(), false);
+        header
+            .write_to(&mut disk_file)
+            .expect("Failed to write header to shm.");
+        disk_file.rewind().unwrap();
+        // The maximum nesting depth is 0, which means backing file is not allowed.
+        let res = QcowFile::from_with_nesting_depth(disk_file, 0);
+        assert!(res.is_err());
+        assert!(matches!(res.unwrap_err(), Error::MaxNestingDepthExceeded));
+    }
+
+    /// Create a qcow2 file with itself as its backing file.
+    ///
+    /// Without configuration `max_nesting_depth`, this will cause infinite recursion when loading
+    /// the file until stack overflow.
+    fn new_self_referential_qcow(path: &Path) -> Result<()> {
+        let header = QcowHeader::create_for_size_and_path(3, 0x10_0000, path.to_str())?;
+        let mut disk_file = RawFile::new(
+            File::create(path).expect("Failed to create image file."),
+            false,
+        );
+        header.write_to(&mut disk_file)?;
+        Ok(())
+    }
+
+    #[test]
+    fn max_nesting_backing() {
+        let test_dir = TempDir::new_with_prefix("/tmp/ch").unwrap();
+        let img_path = test_dir.as_path().join("test.img");
+
+        new_self_referential_qcow(img_path.as_path()).unwrap();
+
+        let err = QcowFile::from_with_nesting_depth(
+            RawFile::new(
+                File::open(img_path.as_path()).expect("Failed to open qcow image file"),
+                false,
+            ),
+            MAX_NESTING_DEPTH,
+        )
+        .expect_err("Opening qcow file with itself as backing file should fail.");
+
+        // This type of error is complex. For comparing easily, we can check if it contains the
+        // type name after formatting.
+        assert!(format!("{err:?}").contains(&format!("{:?}", Error::MaxNestingDepthExceeded)));
+        // This should recursively call the function ten times before throwing an error, and the
+        // error `BackingFileOpen` should also be repeated ten times.
+        assert_eq!(
+            format!("{err:?}")
+                .matches("BackingFileOpen")
+                .collect::<Vec<_>>()
+                .len() as u32,
+            MAX_NESTING_DEPTH,
+        );
+    }
+
     #[test]
     fn invalid_magic() {
         let invalid_header = vec![0x51u8, 0x46, 0x4a, 0xfb];

block/src/qcow/qcow_raw_file.rs

@@ -1,6 +1,8 @@
 // Copyright 2018 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 super::RawFile;
 use byteorder::{BigEndian, ReadBytesExt, WriteBytesExt};

block/src/qcow/raw_file.rs

@@ -11,7 +11,6 @@
 use crate::BlockBackend;
 use libc::c_void;
 use std::alloc::{alloc_zeroed, dealloc, Layout};
-use std::convert::TryInto;
 use std::fs::{File, Metadata};
 use std::io::{self, Read, Seek, SeekFrom, Write};
 use std::os::unix::io::{AsRawFd, RawFd};

block/src/qcow/refcount.rs

@@ -1,51 +1,40 @@
 // Copyright 2018 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::fmt::{self, Display};
 use std::io;
 
 use libc::EINVAL;
+use thiserror::Error;
 
 use crate::qcow::{
     qcow_raw_file::QcowRawFile,
     vec_cache::{CacheMap, Cacheable, VecCache},
 };
 
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum Error {
     /// `EvictingCache` - Error writing a refblock from the cache to disk.
+    #[error("Failed to write a refblock from the cache to disk: {0}")]
     EvictingRefCounts(io::Error),
     /// `InvalidIndex` - Address requested isn't within the range of the disk.
+    #[error("Address requested is not within the range of the disk")]
     InvalidIndex,
     /// `NeedCluster` - Handle this error by reading the cluster and calling the function again.
+    #[error("Cluster with addr={0} needs to be read")]
     NeedCluster(u64),
     /// `NeedNewCluster` - Handle this error by allocating a cluster and calling the function again.
+    #[error("New cluster needs to be allocated for refcounts")]
     NeedNewCluster,
-    /// `ReadingRefCounts` - Error reading the file in to the refcount cache.
+    /// `ReadingRefCounts` - Error reading the file into the refcount cache.
+    #[error("Failed to read the file into the refcount cache: {0}")]
     ReadingRefCounts(io::Error),
 }
 
 pub type Result<T> = std::result::Result<T, Error>;
 
-impl Display for Error {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        use self::Error::*;
-
-        match self {
-            EvictingRefCounts(e) => {
-                write!(f, "failed to write a refblock from the cache to disk: {e}")
-            }
-            InvalidIndex => write!(f, "address requested is not within the range of the disk"),
-            NeedCluster(addr) => write!(f, "cluster with addr={addr} needs to be read"),
-            NeedNewCluster => write!(f, "new cluster needs to be allocated for refcounts"),
-            ReadingRefCounts(e) => {
-                write!(f, "failed to read the file into the refcount cache: {e}")
-            }
-        }
-    }
-}
-
 /// Represents the refcount entries for an open qcow file.
 #[derive(Clone, Debug)]
 pub struct RefCount {

block/src/qcow/vec_cache.rs

@@ -1,6 +1,8 @@
 // Copyright 2018 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::collections::hash_map::IterMut;
 use std::collections::HashMap;

block/src/vhd.rs

@@ -3,7 +3,6 @@
 // SPDX-License-Identifier: Apache-2.0
 
 use crate::{read_aligned_block_size, DiskTopology};
-use std::convert::TryInto;
 use std::fs::File;
 use std::io::{Seek, SeekFrom};
 

block/src/vhdx/vhdx_header.rs

@@ -7,7 +7,6 @@ extern crate log;
 use byteorder::{ByteOrder, LittleEndian, ReadBytesExt};
 use remain::sorted;
 use std::collections::btree_map::BTreeMap;
-use std::convert::TryInto;
 use std::fs::File;
 use std::io::{self, Read, Seek, SeekFrom, Write};
 use std::mem::size_of;
@@ -91,7 +90,7 @@ pub type Result<T> = std::result::Result<T, VhdxHeaderError>;
 
 #[derive(Clone, Debug)]
 pub struct FileTypeIdentifier {
-    pub signature: u64,
+    pub _signature: u64,
 }
 
 impl FileTypeIdentifier {
@@ -99,14 +98,14 @@ impl FileTypeIdentifier {
     pub fn new(f: &mut File) -> Result<FileTypeIdentifier> {
         f.seek(SeekFrom::Start(FILE_START))
             .map_err(VhdxHeaderError::SeekFileTypeIdentifier)?;
-        let signature = f
+        let _signature = f
             .read_u64::<LittleEndian>()
             .map_err(VhdxHeaderError::ReadFileTypeIdentifier)?;
-        if signature != VHDX_SIGN {
+        if _signature != VHDX_SIGN {
             return Err(VhdxHeaderError::InvalidVHDXSign);
         }
 
-        Ok(FileTypeIdentifier { signature })
+        Ok(FileTypeIdentifier { _signature })
     }
 }
 
@@ -128,7 +127,7 @@ pub struct Header {
 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 in to a buffer. We will need it for
+        // 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))
@@ -471,7 +470,7 @@ impl VhdxHeader {
 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 in to a u32 integer
+    // 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);

devices/Cargo.toml

@@ -1,27 +1,31 @@
 [package]
-name = "devices"
-version = "0.1.0"
 authors = ["The Chromium OS Authors"]
 edition = "2021"
+name = "devices"
+version = "0.1.0"
 
 [dependencies]
-acpi_tables = { git = "https://github.com/rust-vmm/acpi_tables", branch = "main"  }
-anyhow = "1.0.79"
+acpi_tables = { git = "https://github.com/rust-vmm/acpi_tables", branch = "main" }
+anyhow = "1.0.86"
 arch = { path = "../arch" }
-bitflags = "2.4.1"
-byteorder = "1.4.3"
+bitflags = "2.6.0"
+byteorder = "1.5.0"
 event_monitor = { path = "../event_monitor" }
 hypervisor = { path = "../hypervisor" }
-libc = "0.2.153"
-log = "0.4.20"
+libc = "0.2.155"
+log = "0.4.22"
+num_enum = "0.7.2"
 pci = { path = "../pci" }
-thiserror = "1.0.52"
+serde = { version = "1.0.197", features = ["derive"] }
+thiserror = "1.0.62"
 tpm = { path = "../tpm" }
-versionize = "0.2.0"
-versionize_derive = "0.1.6"
 vm-allocator = { path = "../vm-allocator" }
 vm-device = { path = "../vm-device" }
-vm-memory = "0.14.0"
+vm-memory = { version = "0.14.1", features = [
+  "backend-atomic",
+  "backend-bitmap",
+  "backend-mmap",
+] }
 vm-migration = { path = "../vm-migration" }
 vmm-sys-util = "0.12.1"
 
@@ -30,3 +34,4 @@ arch = { path = "../arch" }
 
 [features]
 default = []
+pvmemcontrol = []

devices/src/interrupt_controller.rs

@@ -4,31 +4,42 @@
 
 use std::io;
 use std::result;
+use thiserror::Error;
 use vmm_sys_util::eventfd::EventFd;
 
-#[derive(Debug)]
+#[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),
 }
 

devices/src/ioapic.rs

@@ -11,19 +11,16 @@
 
 use super::interrupt_controller::{Error, InterruptController};
 use byteorder::{ByteOrder, LittleEndian};
+use serde::{Deserialize, Serialize};
 use std::result;
 use std::sync::{Arc, Barrier};
-use versionize::{VersionMap, Versionize, VersionizeResult};
-use versionize_derive::Versionize;
 use vm_device::interrupt::{
     InterruptIndex, InterruptManager, InterruptSourceConfig, InterruptSourceGroup,
     MsiIrqGroupConfig, MsiIrqSourceConfig,
 };
 use vm_device::BusDevice;
 use vm_memory::GuestAddress;
-use vm_migration::{
-    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
-};
+use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
 use vmm_sys_util::eventfd::EventFd;
 
 type Result<T> = result::Result<T, Error>;
@@ -136,7 +133,7 @@ pub struct Ioapic {
     interrupt_source_group: Arc<dyn InterruptSourceGroup>,
 }
 
-#[derive(Versionize)]
+#[derive(Serialize, Deserialize)]
 pub struct IoapicState {
     id_reg: u32,
     reg_sel: u32,
@@ -144,7 +141,6 @@ pub struct IoapicState {
     used_entries: [bool; NUM_IOAPIC_PINS],
     apic_address: u64,
 }
-impl VersionMapped for IoapicState {}
 
 impl BusDevice for Ioapic {
     fn read(&mut self, _base: u64, offset: u64, data: &mut [u8]) {
@@ -420,7 +416,7 @@ impl InterruptController for Ioapic {
         self.interrupt_source_group
             .trigger(irq as InterruptIndex)
             .map_err(Error::TriggerInterrupt)?;
-        debug!("Interrupt successfully delivered");
+        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.
@@ -444,7 +440,7 @@ impl Snapshottable for Ioapic {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        Snapshot::new_from_versioned_state(&self.state())
+        Snapshot::new_from_state(&self.state())
     }
 }
 

devices/src/legacy/cmos.rs

@@ -1,6 +1,8 @@
 // Copyright 2017 The Chromium OS Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
+//
+// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
 use libc::{clock_gettime, gmtime_r, timespec, tm, CLOCK_REALTIME};
 use std::cmp::min;

devices/src/legacy/gpio_pl061.rs

@@ -8,16 +8,14 @@
 //!
 
 use crate::{read_le_u32, write_le_u32};
+use serde::{Deserialize, Serialize};
+use std::io;
 use std::result;
 use std::sync::{Arc, Barrier};
-use std::{fmt, io};
-use versionize::{VersionMap, Versionize, VersionizeResult};
-use versionize_derive::Versionize;
+use thiserror::Error;
 use vm_device::interrupt::InterruptSourceGroup;
 use vm_device::BusDevice;
-use vm_migration::{
-    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
-};
+use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
 
 const OFS_DATA: u64 = 0x400; // Data Register
 const GPIODIR: u64 = 0x400; // Direction Register
@@ -40,29 +38,18 @@ const GPIO_ID_HIGH: u64 = 0x1000;
 
 const N_GPIOS: u32 = 8;
 
-#[derive(Debug)]
+#[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),
 }
 
-impl fmt::Display for Error {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        match self {
-            Error::BadWriteOffset(offset) => write!(f, "Bad Write Offset: {offset}"),
-            Error::GpioInterruptDisabled => write!(f, "GPIO interrupt disabled by guest driver.",),
-            Error::GpioInterruptFailure(ref e) => {
-                write!(f, "Could not trigger GPIO interrupt: {e}.")
-            }
-            Error::GpioTriggerKeyFailure(key) => {
-                write!(f, "Invalid GPIO Input key triggered: {key}.")
-            }
-        }
-    }
-}
-
 type Result<T> = result::Result<T, Error>;
 
 /// A GPIO device following the PL061 specification.
@@ -89,7 +76,7 @@ pub struct Gpio {
     interrupt: Arc<dyn InterruptSourceGroup>,
 }
 
-#[derive(Versionize)]
+#[derive(Serialize, Deserialize)]
 pub struct GpioState {
     data: u32,
     old_in_data: u32,
@@ -102,8 +89,6 @@ pub struct GpioState {
     afsel: u32,
 }
 
-impl VersionMapped for GpioState {}
-
 impl Gpio {
     /// Constructs an PL061 GPIO device.
     pub fn new(
@@ -328,7 +313,7 @@ impl Snapshottable for Gpio {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        Snapshot::new_from_versioned_state(&self.state())
+        Snapshot::new_from_state(&self.state())
     }
 }
 
@@ -339,8 +324,6 @@ impl Migratable for Gpio {}
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::{read_le_u32, write_le_u32};
-    use std::sync::Arc;
     use vm_device::interrupt::{InterruptIndex, InterruptSourceConfig};
     use vmm_sys_util::eventfd::EventFd;
 

devices/src/legacy/i8042.rs

@@ -1,6 +1,8 @@
 // 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},

devices/src/legacy/rtc_pl031.rs

@@ -9,10 +9,10 @@
 //! a real-time clock input.
 //!
 use crate::{read_le_u32, write_le_u32};
-use std::fmt;
 use std::sync::{Arc, Barrier};
 use std::time::Instant;
 use std::{io, result};
+use thiserror::Error;
 use vm_device::interrupt::InterruptSourceGroup;
 use vm_device::BusDevice;
 
@@ -39,21 +39,14 @@ const AMBA_ID_HIGH: u64 = 0x1000;
 /// Constant to convert seconds to nanoseconds.
 pub const NANOS_PER_SECOND: u64 = 1_000_000_000;
 
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum Error {
+    #[error("Bad Write Offset: {0}")]
     BadWriteOffset(u64),
+    #[error("Failed to trigger interrupt: {0}")]
     InterruptFailure(io::Error),
 }
 
-impl fmt::Display for Error {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        match self {
-            Error::BadWriteOffset(offset) => write!(f, "Bad Write Offset: {offset}"),
-            Error::InterruptFailure(e) => write!(f, "Failed to trigger interrupt: {e}"),
-        }
-    }
-}
-
 type Result<T> = result::Result<T, Error>;
 
 /// Wrapper over `libc::clockid_t` to specify Linux Kernel clock source.
@@ -79,98 +72,6 @@ impl From<ClockType> for libc::clockid_t {
     }
 }
 
-/// Structure representing the date in local time with nanosecond precision.
-pub struct LocalTime {
-    /// Seconds in current minute.
-    sec: i32,
-    /// Minutes in current hour.
-    min: i32,
-    /// Hours in current day, 24H format.
-    hour: i32,
-    /// Days in current month.
-    mday: i32,
-    /// Months in current year.
-    mon: i32,
-    /// Years passed since 1900 BC.
-    year: i32,
-    /// Nanoseconds in current second.
-    nsec: i64,
-}
-
-impl LocalTime {
-    /// Returns the [LocalTime](struct.LocalTime.html) structure for the calling moment.
-    #[cfg(test)]
-    pub fn now() -> LocalTime {
-        let mut timespec = libc::timespec {
-            tv_sec: 0,
-            tv_nsec: 0,
-        };
-        let mut tm: libc::tm = libc::tm {
-            tm_sec: 0,
-            tm_min: 0,
-            tm_hour: 0,
-            tm_mday: 0,
-            tm_mon: 0,
-            tm_year: 0,
-            tm_wday: 0,
-            tm_yday: 0,
-            tm_isdst: 0,
-            tm_gmtoff: 0,
-            tm_zone: std::ptr::null(),
-        };
-
-        // SAFETY: the parameters are valid.
-        unsafe {
-            libc::clock_gettime(libc::CLOCK_REALTIME, &mut timespec);
-            libc::localtime_r(&timespec.tv_sec, &mut tm);
-        }
-
-        LocalTime {
-            sec: tm.tm_sec,
-            min: tm.tm_min,
-            hour: tm.tm_hour,
-            mday: tm.tm_mday,
-            mon: tm.tm_mon,
-            year: tm.tm_year,
-            nsec: timespec.tv_nsec,
-        }
-    }
-}
-
-impl fmt::Display for LocalTime {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        write!(
-            f,
-            "{}-{:02}-{:02}T{:02}:{:02}:{:02}.{:09}",
-            self.year + 1900,
-            self.mon + 1,
-            self.mday,
-            self.hour,
-            self.min,
-            self.sec,
-            self.nsec
-        )
-    }
-}
-
-/// Holds a micro-second resolution timestamp with both the real time and cpu time.
-#[derive(Clone)]
-pub struct TimestampUs {
-    /// Real time in microseconds.
-    pub time_us: u64,
-    /// Cpu time in microseconds.
-    pub cputime_us: u64,
-}
-
-impl Default for TimestampUs {
-    fn default() -> TimestampUs {
-        TimestampUs {
-            time_us: get_time(ClockType::Monotonic) / 1000,
-            cputime_us: get_time(ClockType::ProcessCpu) / 1000,
-        }
-    }
-}
-
 /// Returns a timestamp in nanoseconds based on the provided clock type.
 ///
 /// # Arguments
@@ -329,15 +230,78 @@ impl BusDevice for Rtc {
 mod tests {
     use super::*;
     use crate::{
-        read_be_u16, read_be_u32, read_le_i32, read_le_u16, read_le_u32, read_le_u64, write_be_u16,
-        write_be_u32, write_le_i32, write_le_u16, write_le_u32, write_le_u64,
+        read_be_u16, read_be_u32, read_le_i32, read_le_u16, read_le_u64, write_be_u16,
+        write_be_u32, write_le_i32, write_le_u16, write_le_u64,
     };
-    use std::sync::Arc;
     use vm_device::interrupt::{InterruptIndex, InterruptSourceConfig};
     use vmm_sys_util::eventfd::EventFd;
 
     const LEGACY_RTC_MAPPED_IO_START: u64 = 0x0901_0000;
 
+    struct LocalTime {
+        sec: i32,
+        min: i32,
+        hour: i32,
+        mday: i32,
+        mon: i32,
+        year: i32,
+        nsec: i64,
+    }
+
+    impl LocalTime {
+        fn now() -> LocalTime {
+            let mut timespec = libc::timespec {
+                tv_sec: 0,
+                tv_nsec: 0,
+            };
+            let mut tm: libc::tm = libc::tm {
+                tm_sec: 0,
+                tm_min: 0,
+                tm_hour: 0,
+                tm_mday: 0,
+                tm_mon: 0,
+                tm_year: 0,
+                tm_wday: 0,
+                tm_yday: 0,
+                tm_isdst: 0,
+                tm_gmtoff: 0,
+                tm_zone: std::ptr::null(),
+            };
+
+            // SAFETY: the parameters are valid.
+            unsafe {
+                libc::clock_gettime(libc::CLOCK_REALTIME, &mut timespec);
+                libc::localtime_r(&timespec.tv_sec, &mut tm);
+            }
+
+            LocalTime {
+                sec: tm.tm_sec,
+                min: tm.tm_min,
+                hour: tm.tm_hour,
+                mday: tm.tm_mday,
+                mon: tm.tm_mon,
+                year: tm.tm_year,
+                nsec: timespec.tv_nsec,
+            }
+        }
+    }
+
+    impl std::fmt::Display for LocalTime {
+        fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+            write!(
+                f,
+                "{}-{:02}-{:02}T{:02}:{:02}:{:02}.{:09}",
+                self.year + 1900,
+                self.mon + 1,
+                self.mday,
+                self.hour,
+                self.min,
+                self.sec,
+                self.nsec
+            )
+        }
+    }
+
     #[test]
     fn test_get_time() {
         for _ in 0..1000 {

devices/src/legacy/serial.rs

@@ -5,16 +5,13 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE-BSD-3-Clause file.
 
+use serde::{Deserialize, Serialize};
 use std::collections::VecDeque;
 use std::sync::{Arc, Barrier};
 use std::{io, result};
-use versionize::{VersionMap, Versionize, VersionizeResult};
-use versionize_derive::Versionize;
 use vm_device::interrupt::InterruptSourceGroup;
 use vm_device::BusDevice;
-use vm_migration::{
-    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
-};
+use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
 use vmm_sys_util::errno::Result;
 
 const LOOP_SIZE: usize = 0x40;
@@ -74,7 +71,7 @@ pub struct Serial {
     out: Option<Box<dyn io::Write + Send>>,
 }
 
-#[derive(Versionize)]
+#[derive(Serialize, Deserialize)]
 pub struct SerialState {
     interrupt_enable: u8,
     interrupt_identification: u8,
@@ -86,7 +83,6 @@ pub struct SerialState {
     baud_divisor: u16,
     in_buffer: Vec<u8>,
 }
-impl VersionMapped for SerialState {}
 
 impl Serial {
     pub fn new(
@@ -334,7 +330,7 @@ impl Snapshottable for Serial {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        Snapshot::new_from_versioned_state(&self.state())
+        Snapshot::new_from_state(&self.state())
     }
 }
 
@@ -345,8 +341,7 @@ impl Migratable for Serial {}
 #[cfg(test)]
 mod tests {
     use super::*;
-    use std::io;
-    use std::sync::{Arc, Mutex};
+    use std::sync::Mutex;
     use vm_device::interrupt::{InterruptIndex, InterruptSourceConfig};
     use vmm_sys_util::eventfd::EventFd;
 
@@ -416,14 +411,11 @@ mod tests {
             None,
         );
 
-        serial.write(0, DATA as u64, &[b'x', b'y']);
-        serial.write(0, DATA as u64, &[b'a']);
-        serial.write(0, DATA as u64, &[b'b']);
-        serial.write(0, DATA as u64, &[b'c']);
-        assert_eq!(
-            serial_out.buf.lock().unwrap().as_slice(),
-            &[b'a', b'b', b'c']
-        );
+        serial.write(0, DATA as u64, b"xy");
+        serial.write(0, DATA as u64, b"a");
+        serial.write(0, DATA as u64, b"b");
+        serial.write(0, DATA as u64, b"c");
+        assert_eq!(serial_out.buf.lock().unwrap().as_slice(), b"abc");
     }
 
     #[test]
@@ -441,7 +433,7 @@ mod tests {
         // counter doesn't change (for 0 it blocks)
         assert!(intr_evt.write(1).is_ok());
         serial.write(0, IER as u64, &[IER_RECV_BIT]);
-        serial.queue_input_bytes(&[b'a', b'b', b'c']).unwrap();
+        serial.queue_input_bytes(b"abc").unwrap();
 
         assert_eq!(intr_evt.read().unwrap(), 2);
 
@@ -478,7 +470,7 @@ mod tests {
         // counter doesn't change (for 0 it blocks)
         assert!(intr_evt.write(1).is_ok());
         serial.write(0, IER as u64, &[IER_THR_BIT]);
-        serial.write(0, DATA as u64, &[b'a']);
+        serial.write(0, DATA as u64, b"a");
 
         assert_eq!(intr_evt.read().unwrap(), 2);
         let mut data = [0u8];
@@ -520,9 +512,9 @@ mod tests {
         );
 
         serial.write(0, MCR as u64, &[MCR_LOOP_BIT]);
-        serial.write(0, DATA as u64, &[b'a']);
-        serial.write(0, DATA as u64, &[b'b']);
-        serial.write(0, DATA as u64, &[b'c']);
+        serial.write(0, DATA as u64, b"a");
+        serial.write(0, DATA as u64, b"b");
+        serial.write(0, DATA as u64, b"c");
 
         let mut data = [0u8];
         serial.read(0, MSR as u64, &mut data[..]);

devices/src/legacy/uart_pl011.rs

@@ -7,18 +7,15 @@
 //!
 
 use crate::{read_le_u32, write_le_u32};
+use serde::{Deserialize, Serialize};
 use std::collections::VecDeque;
-use std::fmt;
 use std::sync::{Arc, Barrier};
 use std::time::Instant;
 use std::{io, result};
-use versionize::{VersionMap, Versionize, VersionizeResult};
-use versionize_derive::Versionize;
+use thiserror::Error;
 use vm_device::interrupt::InterruptSourceGroup;
 use vm_device::BusDevice;
-use vm_migration::{
-    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
-};
+use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
 
 /* Registers */
 const UARTDR: u64 = 0;
@@ -48,27 +45,20 @@ const PL011_ID: [u8; 8] = [0x11, 0x10, 0x14, 0x00, 0x0d, 0xf0, 0x05, 0xb1];
 const AMBA_ID_LOW: u64 = 0x3f8;
 const AMBA_ID_HIGH: u64 = 0x401;
 
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum Error {
+    #[error("pl011_write: Bad Write Offset: {0}")]
     BadWriteOffset(u64),
+    #[error("pl011: DMA not implemented.")]
     DmaNotImplemented,
+    #[error("Failed to trigger interrupt: {0}")]
     InterruptFailure(io::Error),
+    #[error("Failed to write: {0}")]
     WriteAllFailure(io::Error),
+    #[error("Failed to flush: {0}")]
     FlushFailure(io::Error),
 }
 
-impl fmt::Display for Error {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        match self {
-            Error::BadWriteOffset(offset) => write!(f, "pl011_write: Bad Write Offset: {offset}"),
-            Error::DmaNotImplemented => write!(f, "pl011: DMA not implemented."),
-            Error::InterruptFailure(e) => write!(f, "Failed to trigger interrupt: {e}"),
-            Error::WriteAllFailure(e) => write!(f, "Failed to write: {e}"),
-            Error::FlushFailure(e) => write!(f, "Failed to flush: {e}"),
-        }
-    }
-}
-
 type Result<T> = result::Result<T, Error>;
 
 /// A PL011 device following the PL011 specification.
@@ -94,7 +84,7 @@ pub struct Pl011 {
     timestamp: std::time::Instant,
 }
 
-#[derive(Versionize)]
+#[derive(Serialize, Deserialize)]
 pub struct Pl011State {
     flags: u32,
     lcr: u32,
@@ -113,8 +103,6 @@ pub struct Pl011State {
     read_trigger: u32,
 }
 
-impl VersionMapped for Pl011State {}
-
 impl Pl011 {
     /// Constructs an AMBA PL011 UART device.
     pub fn new(
@@ -454,7 +442,7 @@ impl Snapshottable for Pl011 {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        Snapshot::new_from_versioned_state(&self.state())
+        Snapshot::new_from_state(&self.state())
     }
 }
 
@@ -465,8 +453,7 @@ impl Migratable for Pl011 {}
 #[cfg(test)]
 mod tests {
     use super::*;
-    use std::io;
-    use std::sync::{Arc, Mutex};
+    use std::sync::Mutex;
     use vm_device::interrupt::{InterruptIndex, InterruptSourceConfig};
     use vmm_sys_util::eventfd::EventFd;
 
@@ -537,14 +524,11 @@ mod tests {
             None,
         );
 
-        pl011.write(0, UARTDR, &[b'x', b'y']);
-        pl011.write(0, UARTDR, &[b'a']);
-        pl011.write(0, UARTDR, &[b'b']);
-        pl011.write(0, UARTDR, &[b'c']);
-        assert_eq!(
-            pl011_out.buf.lock().unwrap().as_slice(),
-            &[b'x', b'a', b'b', b'c']
-        );
+        pl011.write(0, UARTDR, b"xy");
+        pl011.write(0, UARTDR, b"a");
+        pl011.write(0, UARTDR, b"b");
+        pl011.write(0, UARTDR, b"c");
+        assert_eq!(pl011_out.buf.lock().unwrap().as_slice(), b"xabc");
     }
 
     #[test]
@@ -562,7 +546,7 @@ mod tests {
         // write 1 to the interrupt event fd, so that read doesn't block in case the event fd
         // counter doesn't change (for 0 it blocks)
         assert!(intr_evt.write(1).is_ok());
-        pl011.queue_input_bytes(&[b'a', b'b', b'c']).unwrap();
+        pl011.queue_input_bytes(b"abc").unwrap();
 
         assert_eq!(intr_evt.read().unwrap(), 2);
 

devices/src/lib.rs

@@ -23,6 +23,8 @@ pub mod interrupt_controller;
 #[cfg(target_arch = "x86_64")]
 pub mod ioapic;
 pub mod legacy;
+#[cfg(feature = "pvmemcontrol")]
+pub mod pvmemcontrol;
 pub mod pvpanic;
 pub mod tpm;
 

devices/src/pvmemcontrol.rs

@@ -0,0 +1,819 @@
+// Copyright © 2024 Google LLC
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+use num_enum::TryFromPrimitive;
+use pci::{
+    BarReprogrammingParams, PciBarConfiguration, PciBarPrefetchable, PciBarRegionType,
+    PciClassCode, PciConfiguration, PciDevice, PciDeviceError, PciHeaderType, PciSubclass,
+};
+use std::{
+    collections::HashMap,
+    ffi::CString,
+    io, result,
+    sync::{Arc, Barrier, Mutex, RwLock},
+};
+use thiserror::Error;
+use vm_allocator::{page_size::get_page_size, AddressAllocator, SystemAllocator};
+use vm_device::{BusDeviceSync, Resource};
+use vm_memory::{
+    bitmap::AtomicBitmap, Address, ByteValued, Bytes, GuestAddress, GuestAddressSpace, GuestMemory,
+    GuestMemoryAtomic, GuestMemoryError, GuestMemoryMmap, Le32, Le64,
+};
+use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
+
+const PVMEMCONTROL_VENDOR_ID: u16 = 0x1ae0;
+const PVMEMCONTROL_DEVICE_ID: u16 = 0x0087;
+
+const PVMEMCONTROL_SUBSYSTEM_VENDOR_ID: u16 = 0x1ae0;
+const PVMEMCONTROL_SUBSYSTEM_ID: u16 = 0x011F;
+
+const MAJOR_VERSION: u64 = 1;
+const MINOR_VERSION: u64 = 0;
+
+#[derive(Error, Debug)]
+pub enum Error {
+    // device errors
+    #[error("Guest gave us bad memory addresses: {0}")]
+    GuestMemory(#[source] GuestMemoryError),
+    #[error("Guest sent us invalid request")]
+    InvalidRequest,
+
+    #[error("Guest sent us invalid command: {0}")]
+    InvalidCommand(u32),
+    #[error("Guest sent us invalid connection: {0}")]
+    InvalidConnection(u32),
+
+    // pvmemcontrol errors
+    #[error("Request contains invalid arguments: {0}")]
+    InvalidArgument(u64),
+    #[error("Unknown function code: {0}")]
+    UnknownFunctionCode(u64),
+    #[error("Libc call fail: {0}")]
+    LibcFail(#[source] std::io::Error),
+}
+
+#[derive(Copy, Clone)]
+enum PvmemcontrolSubclass {
+    Other = 0x80,
+}
+
+impl PciSubclass for PvmemcontrolSubclass {
+    fn get_register_value(&self) -> u8 {
+        *self as u8
+    }
+}
+
+/// commands have 0 as the most significant byte
+#[repr(u32)]
+#[derive(PartialEq, Eq, Copy, Clone, TryFromPrimitive)]
+enum PvmemcontrolTransportCommand {
+    Reset = 0x060f_e6d2,
+    Register = 0x0e35_9539,
+    Ready = 0x0ca8_d227,
+    Disconnect = 0x030f_5da0,
+    Ack = 0x03cf_5196,
+    Error = 0x01fb_a249,
+}
+
+#[repr(C)]
+#[derive(Copy, Clone)]
+struct PvmemcontrolTransportRegister {
+    buf_phys_addr: Le64,
+}
+
+#[repr(C)]
+#[derive(Copy, Clone)]
+struct PvmemcontrolTransportRegisterResponse {
+    command: Le32,
+    _padding: u32,
+}
+
+#[repr(C)]
+#[derive(Copy, Clone)]
+union PvmemcontrolTransportUnion {
+    register: PvmemcontrolTransportRegister,
+    register_response: PvmemcontrolTransportRegisterResponse,
+    unit: (),
+}
+
+#[repr(C)]
+#[derive(Copy, Clone)]
+struct PvmemcontrolTransport {
+    payload: PvmemcontrolTransportUnion,
+    command: PvmemcontrolTransportCommand,
+}
+
+const PVMEMCONTROL_DEVICE_MMIO_SIZE: u64 = std::mem::size_of::<PvmemcontrolTransport>() as u64;
+const PVMEMCONTROL_DEVICE_MMIO_ALIGN: u64 = std::mem::align_of::<PvmemcontrolTransport>() as u64;
+
+impl PvmemcontrolTransport {
+    fn ack() -> Self {
+        PvmemcontrolTransport {
+            payload: PvmemcontrolTransportUnion { unit: () },
+            command: PvmemcontrolTransportCommand::Ack,
+        }
+    }
+
+    fn error() -> Self {
+        PvmemcontrolTransport {
+            payload: PvmemcontrolTransportUnion { unit: () },
+            command: PvmemcontrolTransportCommand::Error,
+        }
+    }
+
+    fn register_response(command: u32) -> Self {
+        PvmemcontrolTransport {
+            payload: PvmemcontrolTransportUnion {
+                register_response: PvmemcontrolTransportRegisterResponse {
+                    command: command.into(),
+                    _padding: 0,
+                },
+            },
+            command: PvmemcontrolTransportCommand::Ack,
+        }
+    }
+
+    unsafe fn as_register(self) -> PvmemcontrolTransportRegister {
+        self.payload.register
+    }
+}
+
+// SAFETY: Contains no references and does not have compiler-inserted padding
+unsafe impl ByteValued for PvmemcontrolTransportUnion {}
+// SAFETY: Contains no references and does not have compiler-inserted padding
+unsafe impl ByteValued for PvmemcontrolTransport {}
+
+#[repr(u64)]
+#[derive(Copy, Clone, TryFromPrimitive, Debug)]
+enum FunctionCode {
+    Info = 0,
+    Dontneed = 1,
+    Remove = 2,
+    Free = 3,
+    Pageout = 4,
+    Dontdump = 5,
+    SetVMAAnonName = 6,
+    Mlock = 7,
+    Munlock = 8,
+    MprotectNone = 9,
+    MprotectR = 10,
+    MprotectW = 11,
+    MprotectRW = 12,
+    Mergeable = 13,
+    Unmergeable = 14,
+}
+
+#[repr(C)]
+#[derive(Copy, Clone, Debug, Default)]
+struct PvmemcontrolReq {
+    func_code: Le64,
+    addr: Le64,
+    length: Le64,
+    arg: Le64,
+}
+
+// SAFETY: it only has data and has no implicit padding.
+unsafe impl ByteValued for PvmemcontrolReq {}
+
+#[repr(C)]
+#[derive(Copy, Clone, Default)]
+struct PvmemcontrolResp {
+    ret_errno: Le32,
+    ret_code: Le32,
+    ret_value: Le64,
+    arg0: Le64,
+    arg1: Le64,
+}
+
+impl std::fmt::Debug for PvmemcontrolResp {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        let PvmemcontrolResp {
+            ret_errno,
+            ret_code,
+            ..
+        } = self;
+        write!(
+            f,
+            "PvmemcontrolResp {{ ret_errno: {}, ret_code: {}, .. }}",
+            ret_errno.to_native(),
+            ret_code.to_native()
+        )
+    }
+}
+
+// SAFETY: it only has data and has no implicit padding.
+unsafe impl ByteValued for PvmemcontrolResp {}
+
+/// The guest connections start at 0x8000_0000, which has a leading 1 in
+/// the most significant byte, this ensures it does not conflict with
+/// any of the transport commands
+#[derive(Hash, Clone, Copy, PartialEq, Eq, Debug)]
+pub struct GuestConnection {
+    command: u32,
+}
+
+impl Default for GuestConnection {
+    fn default() -> Self {
+        GuestConnection::new(0x8000_0000)
+    }
+}
+
+impl GuestConnection {
+    fn new(command: u32) -> Self {
+        Self { command }
+    }
+
+    fn next(&self) -> Self {
+        let GuestConnection { command } = *self;
+
+        if command == u32::MAX {
+            GuestConnection::default()
+        } else {
+            GuestConnection::new(command + 1)
+        }
+    }
+}
+
+impl TryFrom<u32> for GuestConnection {
+    type Error = Error;
+
+    fn try_from(value: u32) -> Result<Self, Self::Error> {
+        if (value & 0x8000_0000) != 0 {
+            Ok(GuestConnection::new(value))
+        } else {
+            Err(Error::InvalidConnection(value))
+        }
+    }
+}
+
+struct PercpuInitState {
+    port_buf_map: HashMap<GuestConnection, GuestAddress>,
+    next_conn: GuestConnection,
+}
+
+impl PercpuInitState {
+    fn new() -> Self {
+        PercpuInitState {
+            port_buf_map: HashMap::new(),
+            next_conn: GuestConnection::default(),
+        }
+    }
+}
+
+enum PvmemcontrolState {
+    PercpuInit(PercpuInitState),
+    Ready(HashMap<GuestConnection, GuestAddress>),
+    Broken,
+}
+
+pub struct PvmemcontrolDevice {
+    transport: PvmemcontrolTransport,
+    state: PvmemcontrolState,
+}
+
+impl PvmemcontrolDevice {
+    fn new(transport: PvmemcontrolTransport, state: PvmemcontrolState) -> Self {
+        PvmemcontrolDevice { transport, state }
+    }
+}
+
+impl PvmemcontrolDevice {
+    fn register_percpu_buf(
+        guest_memory: &GuestMemoryAtomic<GuestMemoryMmap<AtomicBitmap>>,
+        mut state: PercpuInitState,
+        PvmemcontrolTransportRegister { buf_phys_addr }: PvmemcontrolTransportRegister,
+    ) -> Self {
+        // access to this address is checked
+        let buf_phys_addr = GuestAddress(buf_phys_addr.into());
+        if !guest_memory.memory().check_range(
+            buf_phys_addr,
+            std::mem::size_of::<PvmemcontrolResp>().max(std::mem::size_of::<PvmemcontrolReq>()),
+        ) {
+            warn!("guest sent invalid phys addr {:#x}", buf_phys_addr.0);
+            return PvmemcontrolDevice::new(
+                PvmemcontrolTransport::error(),
+                PvmemcontrolState::Broken,
+            );
+        }
+
+        let conn = {
+            // find an available port+byte combination, and fail if full
+            let mut next_conn = state.next_conn;
+            while state.port_buf_map.contains_key(&next_conn) {
+                next_conn = next_conn.next();
+                if next_conn == state.next_conn {
+                    warn!("connections exhausted");
+                    return PvmemcontrolDevice::new(
+                        PvmemcontrolTransport::error(),
+                        PvmemcontrolState::Broken,
+                    );
+                }
+            }
+            next_conn
+        };
+        state.next_conn = conn.next();
+        state.port_buf_map.insert(conn, buf_phys_addr);
+
+        // inform guest of the connection
+        let response = PvmemcontrolTransport::register_response(conn.command);
+
+        PvmemcontrolDevice::new(response, PvmemcontrolState::PercpuInit(state))
+    }
+
+    fn reset() -> Self {
+        PvmemcontrolDevice::new(
+            PvmemcontrolTransport::ack(),
+            PvmemcontrolState::PercpuInit(PercpuInitState::new()),
+        )
+    }
+
+    fn error() -> Self {
+        PvmemcontrolDevice::new(PvmemcontrolTransport::error(), PvmemcontrolState::Broken)
+    }
+
+    fn ready(PercpuInitState { port_buf_map, .. }: PercpuInitState) -> Self {
+        PvmemcontrolDevice::new(
+            PvmemcontrolTransport::ack(),
+            PvmemcontrolState::Ready(port_buf_map),
+        )
+    }
+
+    fn run_command(
+        &mut self,
+        guest_memory: &GuestMemoryAtomic<GuestMemoryMmap<AtomicBitmap>>,
+        command: PvmemcontrolTransportCommand,
+    ) {
+        let state = std::mem::replace(&mut self.state, PvmemcontrolState::Broken);
+
+        *self = match command {
+            PvmemcontrolTransportCommand::Reset => Self::reset(),
+            PvmemcontrolTransportCommand::Register => {
+                if let PvmemcontrolState::PercpuInit(state) = state {
+                    // SAFETY: By device protocol. If driver is wrong the device
+                    // can enter a Broken state, but the behavior is still sound.
+                    Self::register_percpu_buf(guest_memory, state, unsafe {
+                        self.transport.as_register()
+                    })
+                } else {
+                    debug!("received register without reset");
+                    Self::error()
+                }
+            }
+            PvmemcontrolTransportCommand::Ready => {
+                if let PvmemcontrolState::PercpuInit(state) = state {
+                    Self::ready(state)
+                } else {
+                    debug!("received ready without reset");
+                    Self::error()
+                }
+            }
+            PvmemcontrolTransportCommand::Disconnect => Self::error(),
+            PvmemcontrolTransportCommand::Ack => {
+                debug!("received ack as command");
+                Self::error()
+            }
+            PvmemcontrolTransportCommand::Error => {
+                debug!("received error as command");
+                Self::error()
+            }
+        }
+    }
+
+    /// read from the transport
+    fn read_transport(&self, offset: u64, data: &mut [u8]) {
+        self.transport
+            .as_slice()
+            .iter()
+            .skip(offset as usize)
+            .zip(data.iter_mut())
+            .for_each(|(src, dest)| *dest = *src)
+    }
+
+    /// can only write to transport payload
+    /// command is a special register that needs separate dispatching
+    fn write_transport(&mut self, offset: u64, data: &[u8]) {
+        self.transport
+            .payload
+            .as_mut_slice()
+            .iter_mut()
+            .skip(offset as usize)
+            .zip(data.iter())
+            .for_each(|(dest, src)| *dest = *src)
+    }
+
+    fn find_connection(&self, conn: GuestConnection) -> Option<GuestAddress> {
+        match &self.state {
+            PvmemcontrolState::Ready(map) => map.get(&conn).copied(),
+            _ => None,
+        }
+    }
+}
+
+pub struct PvmemcontrolBusDevice {
+    mem: GuestMemoryAtomic<GuestMemoryMmap<AtomicBitmap>>,
+    dev: RwLock<PvmemcontrolDevice>,
+}
+
+pub struct PvmemcontrolPciDevice {
+    id: String,
+    configuration: PciConfiguration,
+    bar_regions: Vec<PciBarConfiguration>,
+}
+
+impl PvmemcontrolBusDevice {
+    /// f is called with the host address of `range_base` and only when
+    /// [`range_base`, `range_base` + `range_len`) is present in the guest
+    fn operate_on_memory_range<F>(&self, addr: u64, length: u64, f: F) -> result::Result<(), Error>
+    where
+        F: FnOnce(*mut libc::c_void, libc::size_t) -> libc::c_int,
+    {
+        let memory = self.mem.memory();
+        let range_base = GuestAddress(addr);
+        let range_len = usize::try_from(length).map_err(|_| Error::InvalidRequest)?;
+
+        // assume guest memory is not interleaved with vmm memory on the host.
+        if !memory.check_range(range_base, range_len) {
+            return Err(Error::GuestMemory(GuestMemoryError::InvalidGuestAddress(
+                range_base,
+            )));
+        }
+        let hva = memory
+            .get_host_address(range_base)
+            .map_err(Error::GuestMemory)?;
+        let res = f(hva as *mut libc::c_void, range_len as libc::size_t);
+        if res != 0 {
+            return Err(Error::LibcFail(io::Error::last_os_error()));
+        }
+        Ok(())
+    }
+
+    fn madvise(&self, addr: u64, length: u64, advice: libc::c_int) -> result::Result<(), Error> {
+        // SAFETY: [`base`, `base` + `len`) is guest memory
+        self.operate_on_memory_range(addr, length, |base, len| unsafe {
+            libc::madvise(base, len, advice)
+        })
+    }
+
+    fn mlock(&self, addr: u64, length: u64, on_default: bool) -> result::Result<(), Error> {
+        // SAFETY: [`base`, `base` + `len`) is guest memory
+        self.operate_on_memory_range(addr, length, |base, len| unsafe {
+            libc::mlock2(base, len, if on_default { libc::MLOCK_ONFAULT } else { 0 })
+        })
+    }
+
+    fn munlock(&self, addr: u64, length: u64) -> result::Result<(), Error> {
+        // SAFETY: [`base`, `base` + `len`) is guest memory
+        self.operate_on_memory_range(addr, length, |base, len| unsafe {
+            libc::munlock(base, len)
+        })
+    }
+
+    fn mprotect(
+        &self,
+        addr: u64,
+        length: u64,
+        protection: libc::c_int,
+    ) -> result::Result<(), Error> {
+        // SAFETY: [`base`, `base` + `len`) is guest memory
+        self.operate_on_memory_range(addr, length, |base, len| unsafe {
+            libc::mprotect(base, len, protection)
+        })
+    }
+
+    fn set_vma_anon_name(&self, addr: u64, length: u64, name: u64) -> result::Result<(), Error> {
+        let name = (name != 0).then(|| CString::new(format!("pvmemcontrol-{}", name)).unwrap());
+        let name_ptr = if let Some(name) = &name {
+            name.as_ptr()
+        } else {
+            std::ptr::null()
+        };
+        debug!("addr {:X} length {} name {:?}", addr, length, name);
+
+        // SAFETY: [`base`, `base` + `len`) is guest memory
+        self.operate_on_memory_range(addr, length, |base, len| unsafe {
+            libc::prctl(
+                libc::PR_SET_VMA,
+                libc::PR_SET_VMA_ANON_NAME,
+                base,
+                len,
+                name_ptr,
+            )
+        })
+    }
+
+    fn process_request(
+        &self,
+        func_code: FunctionCode,
+        addr: u64,
+        length: u64,
+        arg: u64,
+    ) -> Result<PvmemcontrolResp, Error> {
+        let result = match func_code {
+            FunctionCode::Info => {
+                return Ok(PvmemcontrolResp {
+                    ret_errno: 0.into(),
+                    ret_code: 0.into(),
+                    ret_value: get_page_size().into(),
+                    arg0: MAJOR_VERSION.into(),
+                    arg1: MINOR_VERSION.into(),
+                })
+            }
+            FunctionCode::Dontneed => self.madvise(addr, length, libc::MADV_DONTNEED),
+            FunctionCode::Remove => self.madvise(addr, length, libc::MADV_REMOVE),
+            FunctionCode::Free => self.madvise(addr, length, libc::MADV_FREE),
+            FunctionCode::Pageout => self.madvise(addr, length, libc::MADV_PAGEOUT),
+            FunctionCode::Dontdump => self.madvise(addr, length, libc::MADV_DONTDUMP),
+            FunctionCode::SetVMAAnonName => self.set_vma_anon_name(addr, length, arg),
+            FunctionCode::Mlock => self.mlock(addr, length, false),
+            FunctionCode::Munlock => self.munlock(addr, length),
+            FunctionCode::MprotectNone => self.mprotect(addr, length, libc::PROT_NONE),
+            FunctionCode::MprotectR => self.mprotect(addr, length, libc::PROT_READ),
+            FunctionCode::MprotectW => self.mprotect(addr, length, libc::PROT_WRITE),
+            FunctionCode::MprotectRW => {
+                self.mprotect(addr, length, libc::PROT_READ | libc::PROT_WRITE)
+            }
+            FunctionCode::Mergeable => self.madvise(addr, length, libc::MADV_MERGEABLE),
+            FunctionCode::Unmergeable => self.madvise(addr, length, libc::MADV_UNMERGEABLE),
+        };
+        result.map(|_| PvmemcontrolResp::default())
+    }
+
+    fn handle_request(
+        &self,
+        PvmemcontrolReq {
+            func_code,
+            addr,
+            length,
+            arg,
+        }: PvmemcontrolReq,
+    ) -> Result<PvmemcontrolResp, Error> {
+        let (func_code, addr, length, arg) = (
+            func_code.to_native(),
+            addr.to_native(),
+            length.to_native(),
+            arg.to_native(),
+        );
+
+        let resp_or_err = FunctionCode::try_from(func_code)
+            .map_err(|_| Error::UnknownFunctionCode(func_code))
+            .and_then(|func_code| self.process_request(func_code, addr, length, arg));
+
+        let resp = match resp_or_err {
+            Ok(resp) => resp,
+            Err(e) => match e {
+                Error::InvalidArgument(arg) => PvmemcontrolResp {
+                    ret_errno: (libc::EINVAL as u32).into(),
+                    ret_code: (arg as u32).into(),
+                    ..Default::default()
+                },
+                Error::LibcFail(err) => PvmemcontrolResp {
+                    ret_errno: (err.raw_os_error().unwrap_or(libc::EFAULT) as u32).into(),
+                    ret_code: 0u32.into(),
+                    ..Default::default()
+                },
+                Error::UnknownFunctionCode(func_code) => PvmemcontrolResp {
+                    ret_errno: (libc::EOPNOTSUPP as u32).into(),
+                    ret_code: (func_code as u32).into(),
+                    ..Default::default()
+                },
+                Error::GuestMemory(err) => {
+                    warn!("{}", err);
+                    PvmemcontrolResp {
+                        ret_errno: (libc::EINVAL as u32).into(),
+                        ret_code: (func_code as u32).into(),
+                        ..Default::default()
+                    }
+                }
+                // device error, stop responding
+                other => return Err(other),
+            },
+        };
+        Ok(resp)
+    }
+
+    fn handle_pvmemcontrol_request(&self, guest_addr: GuestAddress) {
+        let request: PvmemcontrolReq = if let Ok(x) = self.mem.memory().read_obj(guest_addr) {
+            x
+        } else {
+            warn!("cannot read from guest address {:#x}", guest_addr.0);
+            return;
+        };
+
+        let response: PvmemcontrolResp = match self.handle_request(request) {
+            Ok(x) => x,
+            Err(e) => {
+                warn!("cannot process request {:?} with error {}", request, e);
+                return;
+            }
+        };
+
+        if self.mem.memory().write_obj(response, guest_addr).is_err() {
+            warn!("cannot write to guest address {:#x}", guest_addr.0);
+        }
+    }
+
+    fn handle_guest_write(&self, offset: u64, data: &[u8]) {
+        if offset as usize != std::mem::offset_of!(PvmemcontrolTransport, command) {
+            if data.len() != 4 && data.len() != 8 {
+                warn!("guest write is not 4 or 8 bytes long");
+                return;
+            }
+            self.dev.write().unwrap().write_transport(offset, data);
+            return;
+        }
+        let data = if data.len() == 4 {
+            let mut d = [0u8; 4];
+            d.iter_mut()
+                .zip(data.iter())
+                .for_each(|(d, data)| *d = *data);
+            d
+        } else {
+            warn!("guest write with non u32 at command register");
+            return;
+        };
+        let data_cmd = u32::from_le_bytes(data);
+        let command = PvmemcontrolTransportCommand::try_from(data_cmd);
+
+        match command {
+            Ok(command) => self.dev.write().unwrap().run_command(&self.mem, command),
+            Err(_) => {
+                GuestConnection::try_from(data_cmd)
+                    .and_then(|conn| {
+                        self.dev
+                            .read()
+                            .unwrap()
+                            .find_connection(conn)
+                            .ok_or(Error::InvalidConnection(conn.command))
+                    })
+                    .map(|gpa| self.handle_pvmemcontrol_request(gpa))
+                    .unwrap_or_else(|err| warn!("{:?}", err));
+            }
+        }
+    }
+
+    fn handle_guest_read(&self, offset: u64, data: &mut [u8]) {
+        self.dev.read().unwrap().read_transport(offset, data)
+    }
+}
+
+impl PvmemcontrolDevice {
+    pub fn make_device(
+        id: String,
+        mem: GuestMemoryAtomic<GuestMemoryMmap<AtomicBitmap>>,
+    ) -> (PvmemcontrolPciDevice, PvmemcontrolBusDevice) {
+        let dev = RwLock::new(PvmemcontrolDevice::error());
+        let mut configuration = PciConfiguration::new(
+            PVMEMCONTROL_VENDOR_ID,
+            PVMEMCONTROL_DEVICE_ID,
+            0x1,
+            PciClassCode::BaseSystemPeripheral,
+            &PvmemcontrolSubclass::Other,
+            None,
+            PciHeaderType::Device,
+            PVMEMCONTROL_SUBSYSTEM_VENDOR_ID,
+            PVMEMCONTROL_SUBSYSTEM_ID,
+            None,
+            None,
+        );
+        let command: [u8; 2] = [0x03, 0x01]; // memory, io, SERR#
+
+        configuration.write_config_register(1, 0, &command);
+        (
+            PvmemcontrolPciDevice {
+                id,
+                configuration,
+                bar_regions: Vec::new(),
+            },
+            PvmemcontrolBusDevice { mem, dev },
+        )
+    }
+}
+
+impl PciDevice for PvmemcontrolPciDevice {
+    fn write_config_register(
+        &mut self,
+        reg_idx: usize,
+        offset: u64,
+        data: &[u8],
+    ) -> Option<Arc<Barrier>> {
+        self.configuration
+            .write_config_register(reg_idx, offset, data);
+        None
+    }
+
+    fn read_config_register(&mut self, reg_idx: usize) -> u32 {
+        self.configuration.read_config_register(reg_idx)
+    }
+
+    fn as_any(&mut self) -> &mut dyn std::any::Any {
+        self
+    }
+
+    fn id(&self) -> Option<String> {
+        Some(self.id.clone())
+    }
+
+    fn detect_bar_reprogramming(
+        &mut self,
+        reg_idx: usize,
+        data: &[u8],
+    ) -> Option<BarReprogrammingParams> {
+        self.configuration.detect_bar_reprogramming(reg_idx, data)
+    }
+
+    fn allocate_bars(
+        &mut self,
+        _allocator: &Arc<Mutex<SystemAllocator>>,
+        mmio32_allocator: &mut AddressAllocator,
+        _mmio64_allocator: &mut AddressAllocator,
+        resources: Option<Vec<Resource>>,
+    ) -> Result<Vec<PciBarConfiguration>, PciDeviceError> {
+        let mut bars = Vec::new();
+        let region_type = PciBarRegionType::Memory32BitRegion;
+        let bar_id = 0;
+        let region_size = PVMEMCONTROL_DEVICE_MMIO_SIZE;
+        let restoring = resources.is_some();
+        let bar_addr = mmio32_allocator
+            .allocate(None, region_size, Some(PVMEMCONTROL_DEVICE_MMIO_ALIGN))
+            .ok_or(PciDeviceError::IoAllocationFailed(region_size))?;
+
+        let bar = PciBarConfiguration::default()
+            .set_index(bar_id as usize)
+            .set_address(bar_addr.raw_value())
+            .set_size(region_size)
+            .set_region_type(region_type)
+            .set_prefetchable(PciBarPrefetchable::NotPrefetchable);
+
+        if !restoring {
+            self.configuration
+                .add_pci_bar(&bar)
+                .map_err(|e| PciDeviceError::IoRegistrationFailed(bar_addr.raw_value(), e))?;
+        }
+
+        bars.push(bar);
+        self.bar_regions.clone_from(&bars);
+        Ok(bars)
+    }
+
+    fn free_bars(
+        &mut self,
+        _allocator: &mut SystemAllocator,
+        mmio32_allocator: &mut AddressAllocator,
+        _mmio64_allocator: &mut AddressAllocator,
+    ) -> Result<(), PciDeviceError> {
+        for bar in self.bar_regions.drain(..) {
+            mmio32_allocator.free(GuestAddress(bar.addr()), bar.size())
+        }
+        Ok(())
+    }
+
+    fn move_bar(&mut self, old_base: u64, new_base: u64) -> result::Result<(), io::Error> {
+        for bar in self.bar_regions.iter_mut() {
+            if bar.addr() == old_base {
+                *bar = bar.set_address(new_base);
+            }
+        }
+        Ok(())
+    }
+}
+
+impl Pausable for PvmemcontrolPciDevice {
+    fn pause(&mut self) -> std::result::Result<(), MigratableError> {
+        Ok(())
+    }
+
+    fn resume(&mut self) -> std::result::Result<(), MigratableError> {
+        Ok(())
+    }
+}
+
+impl Snapshottable for PvmemcontrolPciDevice {
+    fn id(&self) -> String {
+        self.id.clone()
+    }
+
+    fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
+        let mut snapshot = Snapshot::new_from_state(&())?;
+
+        // Snapshot PciConfiguration
+        snapshot.add_snapshot(self.configuration.id(), self.configuration.snapshot()?);
+
+        Ok(snapshot)
+    }
+}
+
+impl Transportable for PvmemcontrolPciDevice {}
+impl Migratable for PvmemcontrolPciDevice {}
+
+impl BusDeviceSync for PvmemcontrolBusDevice {
+    fn read(&self, _base: u64, offset: u64, data: &mut [u8]) {
+        self.handle_guest_read(offset, data)
+    }
+
+    fn write(&self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
+        self.handle_guest_write(offset, data);
+        None
+    }
+}

devices/src/pvpanic.rs

@@ -9,18 +9,15 @@ use pci::{
     PciClassCode, PciConfiguration, PciDevice, PciDeviceError, PciHeaderType, PciSubclass,
     PCI_CONFIGURATION_ID,
 };
+use serde::{Deserialize, Serialize};
 use std::any::Any;
 use std::result;
 use std::sync::{Arc, Barrier, Mutex};
 use thiserror::Error;
-use versionize::{VersionMap, Versionize, VersionizeResult};
-use versionize_derive::Versionize;
 use vm_allocator::{AddressAllocator, SystemAllocator};
 use vm_device::{BusDevice, Resource};
 use vm_memory::{Address, GuestAddress};
-use vm_migration::{
-    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
-};
+use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
 
 const PVPANIC_VENDOR_ID: u16 = 0x1b36;
 const PVPANIC_DEVICE_ID: u16 = 0x0011;
@@ -60,23 +57,20 @@ pub struct PvPanicDevice {
     bar_regions: Vec<PciBarConfiguration>,
 }
 
-#[derive(Versionize)]
+#[derive(Serialize, Deserialize)]
 pub struct PvPanicDeviceState {
     events: u8,
 }
 
-impl VersionMapped for PvPanicDeviceState {}
-
 impl PvPanicDevice {
     pub fn new(id: String, snapshot: Option<Snapshot>) -> Result<Self, PvPanicError> {
         let pci_configuration_state =
-            vm_migration::versioned_state_from_id(snapshot.as_ref(), PCI_CONFIGURATION_ID)
-                .map_err(|e| {
-                    PvPanicError::RetrievePciConfigurationState(anyhow!(
-                        "Failed to get PciConfigurationState from Snapshot: {}",
-                        e
-                    ))
-                })?;
+            vm_migration::state_from_id(snapshot.as_ref(), PCI_CONFIGURATION_ID).map_err(|e| {
+                PvPanicError::RetrievePciConfigurationState(anyhow!(
+                    "Failed to get PciConfigurationState from Snapshot: {}",
+                    e
+                ))
+            })?;
 
         let mut configuration = PciConfiguration::new(
             PVPANIC_VENDOR_ID,
@@ -97,7 +91,7 @@ impl PvPanicDevice {
 
         let state: Option<PvPanicDeviceState> = snapshot
             .as_ref()
-            .map(|s| s.to_versioned_state())
+            .map(|s| s.to_state())
             .transpose()
             .map_err(|e| {
                 PvPanicError::CreatePvPanicDevice(anyhow!(
@@ -210,7 +204,7 @@ impl PciDevice for PvPanicDevice {
         }
 
         bars.push(bar);
-        self.bar_regions = bars.clone();
+        self.bar_regions.clone_from(&bars);
 
         Ok(bars)
     }
@@ -259,7 +253,7 @@ impl Snapshottable for PvPanicDevice {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        let mut snapshot = Snapshot::new_from_versioned_state(&self.state())?;
+        let mut snapshot = Snapshot::new_from_state(&self.state())?;
 
         // Snapshot PciConfiguration
         snapshot.add_snapshot(self.configuration.id(), self.configuration.snapshot()?);

devices/src/tpm.rs

@@ -450,7 +450,7 @@ impl BusDevice for Tpm {
                         );
                     }
                     _ => {
-                        error!("Invalid value passed to CRTL_REQ register");
+                        error!("Invalid value passed to CTRL_REQ register");
                         return None;
                     }
                 },

docs/api.md

@@ -110,6 +110,7 @@ The Cloud Hypervisor API exposes the following actions through its endpoints:
 | Add vsock device to the VM         | `/vm.add-vsock`         | `/schemas/VsockConfig`          | `/schemas/PciDeviceInfo` | The VM is booted                                       |
 | Remove device from the VM          | `/vm.remove-device`     | `/schemas/VmRemoveDevice`       | N/A                      | The VM is booted                                       |
 | Dump the VM counters               | `/vm.counters`          | N/A                             | `/schemas/VmCounters`    | The VM is booted                                       |
+| Inject an NMI                      | `/vm.nmi`               | N/A                             | N/A                      | The VM is booted                                       |
 | Prepare to receive a migration     | `/vm.receive-migration` | `/schemas/ReceiveMigrationData` | N/A                      | N/A                                                    |
 | Start to send migration to target  | `/vm.send-migration`    | `/schemas/SendMigrationData`    | N/A                      | The VM is booted and (shared mem or hugepages enabled) |
 
@@ -269,7 +270,7 @@ definition in XML format:
 ### Command Line Interface
 
 The Cloud Hypervisor Command Line Interface (CLI) can only be used for launching
-the Cloud Hypervisor binary, i.e. it can not be used for controlling the VMM or
+the Cloud Hypervisor binary, i.e. it cannot be used for controlling the VMM or
 the launched VM once they're up and running.
 
 If you want to inspect the VMM, or control the VM after launching Cloud

docs/custom-image.md

@@ -159,10 +159,10 @@ as we might need to update the direct kernel boot command line, replacing
 
 Update all references to the previous image name to the new one.
 
-## NVIDIA image for VFIO baremetal CI
+## NVIDIA image for VFIO bare-metal CI
 
 Here we are going to describe how to create a cloud image that contains the
-necessary NVIDIA drivers for our VFIO baremetal CI.
+necessary NVIDIA drivers for our VFIO bare-metal CI.
 
 ### Download base image
 
@@ -170,7 +170,7 @@ We usually start from one of the custom cloud image we have previously created
 but we can use a stock cloud image as well.
 
 ```bash
-wget https://cloud-hypervisor.azureedge.net/jammy-server-cloudimg-amd64-custom-20230119-0.raw
+wget https://ch-images.azureedge.net/jammy-server-cloudimg-amd64-custom-20230119-0.raw
 mv jammy-server-cloudimg-amd64-custom-20230119-0.raw jammy-server-cloudimg-amd64-nvidia.raw
 ```
 
@@ -326,4 +326,4 @@ VM will be booted with this image.
 
 ```
 sudo cloud-init clean
-```
+```

docs/fuzzing.md

@@ -2,7 +2,7 @@
 
 Cloud Hypervisor uses [cargo-fuzz](https://github.com/rust-fuzz/cargo-fuzz) for fuzzing individual components.
 
-The fuzzers are are in the `fuzz/fuzz_targets` directory
+The fuzzers are in the `fuzz/fuzz_targets` directory
 
 ## Preparation
 

docs/hotplug.md

@@ -53,7 +53,7 @@ On-line CPU(s) list:             0-7
 
 After a reboot the added CPUs will remain.
 
-Removing CPUs works similarly by reducing the number in the "desired_vcpus" field of the reisze API. The CPUs will be automatically offlined inside the guest so there is no need to run any commands inside the guest:
+Removing CPUs works similarly by reducing the number in the "desired_vcpus" field of the resize API. The CPUs will be automatically offlined inside the guest so there is no need to run any commands inside the guest:
 
 ```shell
 ./ch-remote --api-socket=/tmp/ch-socket resize --cpus 2

docs/iommu.md

@@ -39,7 +39,7 @@ Another reason for having a virtual IOMMU is to allow passing physical devices
 from the host through multiple layers of virtualization. Let's take as example
 a system with a physical IOMMU running a VM with a virtual IOMMU. The
 implementation of the virtual IOMMU is responsible for updating the physical
-DMA Remapping table (DMAR) everytime the DMA mapping changes. This must happen
+DMA Remapping table (DMAR) every time the DMA mapping changes. This must happen
 through the VFIO framework on the host as this is the only userspace interface
 to interact with a physical IOMMU.
 
@@ -124,7 +124,7 @@ On AArch64 architecture, the virtual IOMMU can still be used even if ACPI is not
 enabled. But the effect is different with what the aforementioned test showed.
 
 When ACPI is disabled, virtual IOMMU is supported through Flattened Device Tree
-(FDT). In this case, the guest kernel can not tell which device should be
+(FDT). In this case, the guest kernel cannot tell which device should be
 IOMMU-attached and which should not. No matter how many devices you attached to
 the virtual IOMMU by setting `iommu=on` option, all the devices on the PCI bus
 will be attached to the virtual IOMMU (except the IOMMU itself). Each of the

docs/landlock.md

@@ -0,0 +1,105 @@
+# Sandboxing using Landlock
+
+Landlock is a lightweight mechanism to allow unprivileged applications to
+sandbox themselves.
+
+During initial stages of running, applications can define the set of resources
+(mostly files) they need to access during their lifetime. All such rules are
+used to create a ruleset. Once the ruleset is applied, the process cannot access
+any resources outside of the ruleset during its lifetime, even if it were
+compromised.
+
+Under the scope of `read` and `write` access, Landlock currently allows some
+additional accesses (eg: for now, access to extended file attributes is always
+allowed). Eventually, Landlock will only allow accesses similar to Unix
+permissions.
+
+## Host Setup
+
+Landlock should be enabled in Host kernel to use it with cloud-hypervisor.
+Please following [Kernel-Support](https://docs.kernel.org/userspace-api/landlock.html#kernel-support) link to enable Landlock on Host kernel.
+
+
+Landlock support can be checked with following command:
+```
+$ sudo dmesg | grep -w  landlock
+[    0.000000] landlock: Up and running.
+```
+Linux kernel confirms Landlock support with above message in dmesg.
+
+## Enable Landlock
+
+At the time of enabling Landlock, Cloud-Hypervisor process needs the complete
+list of files it accesses over its lifetime. So, Landlock is enabled `vm_create`
+stage of guest boot.
+
+### Command Line
+Append `--landlock` to Cloud-Hypervisor's command line to enable Landlock
+support.
+
+If you expect guest to access additional paths after it boots
+(ex: during hotplug), those paths can be passed using `--landlock-rules` command
+line parameter.
+
+### API
+Landlock can also be enabled during `vm.create` request by passing a config like below:
+
+```
+{
+...
+    "landlock_enable": true,
+    "landlock_rules": [
+      {
+        "path": "/tmp/disk1",
+        "access": "rw"
+      },
+      {
+        "path": "/tmp/disk2",
+        "access": "rw"
+      }
+    ]
+...
+}
+```
+
+
+## Usage Examples
+
+To enable Landlock:
+
+```
+./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" \
+	--cpus boot=4 \
+	--memory size=1024M \
+	--net "tap=,mac=,ip=,mask=" \
+	--landlock
+```
+Hotplugging any new file-backed resources to above guest will result in
+**Permission Denied** error.
+
+To enable Landlock with hotplug support:
+
+```
+./cloud-hypervisor \
+	--api-socket /tmpXXXX/ch.socket \
+	--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" \
+	--cpus boot=4 \
+	--memory size=1024M \
+	--net "tap=,mac=,ip=,mask=" \
+	--landlock \
+	--landlock-rules path="/path/to/hotplug1",access="rw" path="/path/to/hotplug2",access="rw"
+
+./ch-remote --api-socket /tmpXXXX/ch.socket \
+	add-disk "path=/path/to/hotplug/blk.raw"
+```
+
+`--landlock-rules` accepts file or directory paths among its options.
+
+# References
+
+* https://landlock.io/

docs/memory.md

@@ -466,7 +466,7 @@ List of virtual CPUs attached to the guest NUMA node identified by the
 `guest_numa_id` option. This allows for describing a list of CPUs which
 must be seen by the guest as belonging to the NUMA node `guest_numa_id`.
 
-One can use this option for a fine grained description of the NUMA topology
+One can use this option for a fine-grained description of the NUMA topology
 regarding the CPUs associated with it, which might help the guest run more
 efficiently.
 
@@ -573,7 +573,7 @@ _Example_
 ### PCI bus
 
 Cloud Hypervisor supports guests with one or more PCI segments. The default PCI segment always
-has affinity to NUMA node 0. Be default, all other PCI segments have afffinity to NUMA node 0.
+has affinity to NUMA node 0. Be default, all other PCI segments have affinity to NUMA node 0.
 The user may configure the NUMA affinity for any additional PCI segments.
 
 _Example_

docs/performance_metrics.md

@@ -8,6 +8,8 @@ e.g. `dev_cli.sh`. The only prerequisite is [Docker installation](https://docs.d
 Please note that upon its first invocation, this script will pull a
 fairly large container image.
 
+## Run the Performance Tests
+
 To generate metrics data for all available performance tests (including
 boot time, block I/O throughput, and network throughput & latency) and
 output the result into a json file:
@@ -27,3 +29,92 @@ To generate metrics data for selected performance tests, e.g. boot time only:
 ```
 $ ./scripts/dev_cli.sh tests --metrics -- -- --report-file /tmp/metrics.json --test-filter boot_time
 ```
+
+To set custom timeout or test iterations for all performance tests:
+
+```
+$ ./scripts/dev_cli.sh tests --metrics -- -- --timeout 5 --iterations 10
+```
+
+## Performance Tests Details
+
+The following table lists the supported performance tests with default
+timeout and number of iterations. The `timeout` defines the maximum
+execution time of each test for each iteration. The `iteration` defines
+how many times a test needs to be executed to generate the final metrics
+data.
+
+| **Type**   | **Metric**                                 | **Timeout(s)** | **Iterations** |
+|------------|--------------------------------------------|----------------|----------------|
+| Boot Time  | boot_time_ms                               | 2              | 10             |
+|            | boot_time_pmem_ms                          | 2              | 10             |
+|            | boot_time_16_vcpus_ms                      | 2              | 10             |
+|            | boot_time_16_vcpus_pmem_ms                 | 2              | 10             |
+| Virtio Net | virtio_net_latency_us                      | 10             | 5              |
+|            | virtio_net_throughput_single_queue_rx_gbps | 10             | 5              |
+|            | virtio_net_throughput_single_queue_tx_gbps | 10             | 5              |
+|            | virtio_net_throughput_multi_queue_rx_gbps  | 10             | 5              |
+|            | virtio_net_throughput_multi_queue_tx_gbps  | 10             | 5              |
+| Block      | block_read_MiBps                           | 10             | 5              |
+|            | block_write_MiBps                          | 10             | 5              |
+|            | block_random_read_MiBps                    | 10             | 5              |
+|            | block_random_write_MiBps                   | 10             | 5              |
+|            | block_multi_queue_read_MiBps               | 10             | 5              |
+|            | block_multi_queue_write_MiBps              | 10             | 5              |
+|            | block_multi_queue_random_read_MiBps        | 10             | 5              |
+|            | block_multi_queue_random_write_MiBps       | 10             | 5              |
+|            | block_read_IOPS                            | 10             | 5              |
+|            | block_write_IOPS                           | 10             | 5              |
+|            | block_random_read_IOPS                     | 10             | 5              |
+|            | block_random_write_IOPS                    | 10             | 5              |
+|            | block_multi_queue_read_IOPS                | 10             | 5              |
+|            | block_multi_queue_write_IOPS               | 10             | 5              |
+|            | block_multi_queue_random_read_IOPS         | 10             | 5              |
+|            | block_multi_queue_random_write_IOPS        | 10             | 5              |
+| Other      | restore_latency_time_ms                    | 2              | 10             |
+
+## Output Format
+
+Performance-metrics output the result into a json file if `report-file`
+param is set. The fields included in JSON include:
+
+| Field Name         | Content                                  |
+|--------------------|------------------------------------------|
+| git_human_readable | Recent tag information of git repository |
+| git_revision       | Commit id of HEAD                        |
+| git_commit_date    | Commit date of HEAD                      |
+| date               | Date for executing the program           |
+| results            | A list of metrics                        |
+
+## Example
+
+Here is an example of generating metrics data for the boot time using
+`pmem`:
+
+```bash
+$ ./scripts/dev_cli.sh tests --metrics -- -- --test-filter boot_time_pmem_ms
+```
+
+Here is a sample output:
+
+```json
+{
+  "git_human_readable": "v40.0",
+  "git_revision": "e9b263975786abbf895469b93dfc00f21ce39a88",
+  "git_commit_date": "Fri Jun 21 08:40:44 2024 +0000",
+  "date": "Tue Jul 16 16:35:29 UTC 2024",
+  "results": [
+    {
+      "name": "boot_time_pmem_ms",
+      "mean": 105.9461,
+      "std_dev": 7.140993312558129,
+      "max": 120.01499999999999,
+      "min": 92.37600000000002
+    }
+  ]
+}
+```
+
+Note that the metrics data above is for illustration purpose only and
+does not represent the actual performance of Cloud Hypervisor on your
+system.

docs/releases.md

@@ -95,7 +95,7 @@ E - EOL
 
 ```
 
-### LTS Stablity Considerations
+### LTS Stability Considerations
 
 An LTS release is just a `MAJOR` release for which point releases are made for
 longer following the same rules for what can be backported to a `POINT` release.

docs/snapshot_restore.md

@@ -63,7 +63,7 @@ component in the state it was left before the snapshot occurred.
 ## Restore a Cloud Hypervisor VM
 
 Given that one has access to an existing snapshot in `/home/foo/snapshot`,
-it is possible to create a new VM based on this snapshot with the following 
+it is possible to create a new VM based on this snapshot with the following
 command:
 
 ```bash
@@ -93,6 +93,21 @@ start using it.
 At this point, the VM is fully restored and is identical to the VM which was
 snapshot earlier.
 
+## Restore a VM with new Net FDs
+For a VM created with FDs explicitly passed to NetConfig, a set of valid FDs
+need to be provided along with the VM restore command in the following syntax:
+
+```bash
+# First terminal
+./cloud-hypervisor --api-socket /tmp/cloud-hypervisor.sock
+
+# Second terminal
+./ch-remote --api-socket=/tmp/cloud-hypervisor.sock restore source_url=file:///home/foo/snapshot net_fds=[net1@[23,24],net2@[25,26]]
+```
+In the example above, the net device with id `net1` will be backed by FDs '23'
+and '24', and the net device with id `net2` will be backed by FDs '25' and '26'
+from the restored VM.
+
 ## Limitations
 
 VFIO devices and Intel SGX are out of scope.

docs/tracing.md

@@ -37,6 +37,6 @@ generating traces of the boot. These can be relocated for focus tracing on a
 narrow part of the code base.
 
 A `tracer::trace_point!()` macro is also provided for an instantaneous trace
-point however this is not in use in the code base currently nor is handled by
+point however this is neither in use in the code base currently nor is handled by
 the visualisation script due to the difficulty in representation in the SVG.
 

docs/vfio.md

@@ -122,4 +122,64 @@ $ ls /sys/kernel/iommu_groups/22/devices/
 
 This means these two devices are under the same IOMMU group 22. In such case,
 it is important to bind both devices to VFIO and pass them both through the
-VM, otherwise this could cause some functional and security issues.
+VM, otherwise this could cause some functional and security issues.
+
+### Advanced Configuration Options
+
+When using NVIDIA GPUs in a VFIO passthrough configuration, advanced
+configuration options are supported to enable GPUDirect P2P DMA over
+PCIe. When enabled, loads and stores between GPUs use native PCIe
+peer-to-peer transactions instead of a shared memory buffer. This drastically
+decreases P2P latency between GPUs. This functionality is supported by
+cloud-hypervisor on NVIDIA Turing, Ampere, Hopper, and Lovelace GPUs.
+
+The NVIDIA driver does not enable GPUDirect P2P over PCIe within guests
+by default because hardware support for routing P2P TLP between PCIe root
+ports is optional. PCIe P2P should always be supported between devices
+on the same PCIe switch. The `x_nv_gpudirect_clique` config argument may
+be used to signal support for PCIe P2P traffic between NVIDIA VFIO endpoints.
+The guest driver assumes that P2P traffic is supported between all endpoints
+that are part of the same clique.
+```
+--device path=/sys/bus/pci/devices/0000:01:00.0/,x_nv_gpudirect_clique=0
+```
+
+The following command can be run on the guest to verify that GPUDirect P2P is
+correctly enabled.
+```
+nvidia-smi topo -p2p r
+ 	GPU0	GPU1	GPU2	GPU3	GPU4	GPU5	GPU6	GPU7	
+ GPU0	X	OK	OK	OK	OK	OK	OK	OK	
+ GPU1	OK	X	OK	OK	OK	OK	OK	OK	
+ GPU2	OK	OK	X	OK	OK	OK	OK	OK	
+ GPU3	OK	OK	OK	X	OK	OK	OK	OK	
+ GPU4	OK	OK	OK	OK	X	OK	OK	OK	
+ GPU5	OK	OK	OK	OK	OK	X	OK	OK	
+ GPU6	OK	OK	OK	OK	OK	OK	X	OK	
+ GPU7	OK	OK	OK	OK	OK	OK	OK	X	
+```
+
+Some VFIO devices have a 32-bit mmio BAR. When using many such devices, it is
+possible to exhaust the 32-bit mmio space available on a PCI segment. The
+following example demonstrates an example device with a 16 MiB 32-bit mmio BAR.
+```
+lspci -s 0000:01:00.0  -v
+0000:01:00.0 3D controller: NVIDIA Corporation Device 26b9 (rev a1)
+    [...]
+    Memory at f9000000 (32-bit, non-prefetchable) [size=16M]
+    Memory at 46000000000 (64-bit, prefetchable) [size=64G]
+    Memory at 48040000000 (64-bit, prefetchable) [size=32M]
+    [...]
+```
+
+When using multiple PCI segments, the 32-bit mmio address space available to
+be allocated to VFIO devices is equally split between all PCI segments by
+default. This can be tuned with the `--pci-segment` flag. The following example
+demonstrates a guest with two PCI segments. 2/3 of the 32-bit mmio address
+space is available for use by devices on PCI segment 0 and 1/3 of the 32-bit
+mmio address space is available for use by devices on PCI segment 1.
+```
+--platform num_pci_segments=2
+--pci-segment pci_segment=0,mmio32_aperture_weight=2
+--pci-segment pci_segment=1,mmio32_aperture_weight=1
+```

docs/vsock.md

@@ -1,6 +1,6 @@
 # VSOCK support
 
-VSOCK provides a way for guest and host to communicate through a socket. VSOCK sockets support both stream and datagram types.
+VSOCK provides a way for guest and host to communicate through a socket. `cloud-hypervisor` only supports stream VSOCK sockets.
 
 The `virtio-vsock` is based on the [Firecracker](https://github.com/firecracker-microvm/firecracker/blob/main/docs/vsock.md) implementation, where additional details can be found.
 

event_monitor/Cargo.toml

@@ -1,12 +1,12 @@
 [package]
-name = "event_monitor"
-version = "0.1.0"
 authors = ["The Cloud Hypervisor Authors"]
 edition = "2021"
+name = "event_monitor"
+version = "0.1.0"
 
 [dependencies]
-flume = "0.10.14"
-libc = "0.2.153"
+flume = "0.11.0"
+libc = "0.2.155"
 once_cell = "1.19.0"
-serde = { version = "1.0.196", features = ["rc", "derive"] }
-serde_json = "1.0.109"
+serde = { version = "1.0.197", features = ["derive", "rc"] }
+serde_json = "1.0.120"

fuzz/Cargo.toml

@@ -1,139 +1,133 @@
 [package]
-name = "cloud-hypervisor-fuzz"
-version = "0.0.0"
 authors = ["Automatically generated"]
-publish = false
 edition = "2021"
+name = "cloud-hypervisor-fuzz"
+publish = false
+version = "0.0.0"
 
 [package.metadata]
 cargo-fuzz = true
 
 [features]
 igvm = []
+pvmemcontrol = []
 
 [dependencies]
 block = { path = "../block" }
 devices = { path = "../devices" }
-epoll = "4.3.1"
-libc = "0.2.152"
+epoll = "4.3.3"
+libc = "0.2.155"
 libfuzzer-sys = "0.4.7"
-linux-loader = { version = "0.11.0", features = ["elf", "bzimage", "pe"] }
+linux-loader = { version = "0.11.0", features = ["bzimage", "elf", "pe"] }
 micro_http = { git = "https://github.com/firecracker-microvm/micro-http", branch = "main" }
 net_util = { path = "../net_util" }
 once_cell = "1.19.0"
 seccompiler = "0.4.0"
 virtio-devices = { path = "../virtio-devices" }
-virtio-queue = "0.11.0"
-vmm = { path = "../vmm" }
-vmm-sys-util = "0.12.1"
-vm-memory = "0.14.0"
-vm-migration = { path = "../vm-migration" }
+virtio-queue = "0.12.0"
 vm-device = { path = "../vm-device" }
+vm-memory = "0.14.1"
+vm-migration = { path = "../vm-migration" }
 vm-virtio = { path = "../vm-virtio" }
-
-[dependencies.cloud-hypervisor]
-path = ".."
-
-[patch.crates-io]
-kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.7.0" }
-versionize_derive = { git = "https://github.com/cloud-hypervisor/versionize_derive", branch = "ch-0.1.6" }
+vmm = { path = "../vmm", features = ["guest_debug"] }
+vmm-sys-util = "0.12.1"
 
 # Prevent this from interfering with workspaces
 [workspace]
 members = ["."]
 
 [[bin]]
+doc = false
 name = "balloon"
 path = "fuzz_targets/balloon.rs"
 test = false
-doc = false
 
 [[bin]]
+doc = false
 name = "block"
 path = "fuzz_targets/block.rs"
 test = false
-doc = false
 
 [[bin]]
+doc = false
 name = "cmos"
 path = "fuzz_targets/cmos.rs"
 test = false
-doc = false
 
 [[bin]]
+doc = false
 name = "console"
 path = "fuzz_targets/console.rs"
 test = false
-doc = false
 
 [[bin]]
+doc = false
 name = "http_api"
 path = "fuzz_targets/http_api.rs"
 test = false
-doc = false
 
 [[bin]]
+doc = false
 name = "iommu"
 path = "fuzz_targets/iommu.rs"
 test = false
-doc = false
 
 [[bin]]
+doc = false
 name = "linux_loader"
 path = "fuzz_targets/linux_loader.rs"
 test = false
-doc = false
 
 [[bin]]
+doc = false
 name = "linux_loader_cmdline"
 path = "fuzz_targets/linux_loader_cmdline.rs"
 test = false
-doc = false
 
 [[bin]]
+doc = false
 name = "mem"
 path = "fuzz_targets/mem.rs"
 test = false
-doc = false
 
 [[bin]]
+doc = false
 name = "net"
 path = "fuzz_targets/net.rs"
 test = false
-doc = false
 
 [[bin]]
+doc = false
 name = "pmem"
 path = "fuzz_targets/pmem.rs"
 test = false
-doc = false
 
 [[bin]]
+doc = false
 name = "qcow"
 path = "fuzz_targets/qcow.rs"
 test = false
-doc = false
 
 [[bin]]
+doc = false
 name = "rng"
 path = "fuzz_targets/rng.rs"
 test = false
-doc = false
 
 [[bin]]
+doc = false
 name = "serial"
 path = "fuzz_targets/serial.rs"
 test = false
-doc = false
 
 [[bin]]
+doc = false
 name = "vhdx"
 path = "fuzz_targets/vhdx.rs"
 test = false
-doc = false
 
 [[bin]]
+doc = false
 name = "watchdog"
 path = "fuzz_targets/watchdog.rs"
 test = false
-doc = false

fuzz/fuzz_targets/http_api.rs

@@ -105,7 +105,7 @@ impl RequestHandler for StubApiRequestHandler {
         Ok(())
     }
 
-    #[cfg(all(target_arch = "x86_64", feature = "guest_debug"))]
+    #[cfg(target_arch = "x86_64")]
     fn vm_coredump(&mut self, _: &str) -> Result<(), VmError> {
         Ok(())
     }
@@ -180,16 +180,20 @@ impl RequestHandler for StubApiRequestHandler {
                 vdpa: None,
                 vsock: None,
                 pvpanic: false,
+                #[cfg(feature = "pvmemcontrol")]
+                pvmemcontrol: None,
                 iommu: false,
                 #[cfg(target_arch = "x86_64")]
                 sgx_epc: None,
                 numa: None,
                 watchdog: false,
-                #[cfg(feature = "guest_debug")]
                 gdb: false,
+                pci_segments: None,
                 platform: None,
                 tpm: None,
                 preserved_fds: None,
+                landlock_enable: false,
+                landlock_rules: None,
             })),
             state: VmState::Running,
             memory_actual_size: 0,
@@ -273,6 +277,10 @@ impl RequestHandler for StubApiRequestHandler {
     fn vm_send_migration(&mut self, _: VmSendMigrationData) -> Result<(), MigratableError> {
         Ok(())
     }
+
+    fn vm_nmi(&mut self) -> Result<(), VmError> {
+        Ok(())
+    }
 }
 
 fn http_receiver_stub(exit_evt: EventFd, api_evt: EventFd, api_receiver: Receiver<ApiRequest>) {

fuzz/fuzz_targets/qcow.rs

@@ -1,6 +1,8 @@
 // Copyright 2018 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
 
 #![no_main]
 use libfuzzer_sys::fuzz_target;

hypervisor/Cargo.toml

@@ -1,39 +1,47 @@
 [package]
-name = "hypervisor"
-version = "0.1.0"
 authors = ["Microsoft Authors"]
 edition = "2021"
 license = "Apache-2.0 OR BSD-3-Clause"
+name = "hypervisor"
+version = "0.1.0"
 
 [features]
-kvm = ["kvm-ioctls", "kvm-bindings", "vfio-ioctls/kvm"]
-mshv = ["mshv-ioctls", "mshv-bindings", "vfio-ioctls/mshv", "iced-x86"]
-sev_snp = ["igvm_parser", "igvm_defs"]
+kvm = ["kvm-bindings", "kvm-ioctls", "vfio-ioctls/kvm"]
+mshv = ["iced-x86", "mshv-bindings", "mshv-ioctls", "vfio-ioctls/mshv"]
+sev_snp = ["igvm", "igvm_defs"]
 tdx = []
 
 [dependencies]
-anyhow = "1.0.79"
-byteorder = "1.4.3"
-igvm_defs = { git = "https://github.com/microsoft/igvm", branch = "main", package = "igvm_defs", optional  = true }
-igvm_parser = { git = "https://github.com/microsoft/igvm", branch = "main", package = "igvm", optional  = true }
-libc = "0.2.153"
-log = "0.4.20"
-kvm-ioctls = { version = "0.16.0", optional = true }
-kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.7.0", features = ["with-serde", "fam-wrappers"], optional  = true }
-mshv-bindings = { git = "https://github.com/rust-vmm/mshv", branch = "main", features = ["with-serde", "fam-wrappers"], optional  = true }
-mshv-ioctls = { git = "https://github.com/rust-vmm/mshv", branch = "main", optional  = true}
-serde = { version = "1.0.196", features = ["rc", "derive"] }
-serde_with = { version = "3.4.0", default-features = false, features = ["macros"] }
+anyhow = "1.0.86"
+byteorder = "1.5.0"
+igvm = { version = "0.3.3", optional = true }
+igvm_defs = { version = "0.3.1", optional = true }
+kvm-bindings = { version = "0.8.1", optional = true, features = ["serde"] }
+kvm-ioctls = { version = "0.17.0", optional = true }
+libc = "0.2.155"
+log = "0.4.22"
+mshv-bindings = { git = "https://github.com/rust-vmm/mshv", tag = "v0.2.0", features = [
+  "fam-wrappers",
+  "with-serde",
+], optional = true }
+mshv-ioctls = { git = "https://github.com/rust-vmm/mshv", tag = "v0.2.0", optional = true }
+serde = { version = "1.0.197", features = ["derive", "rc"] }
+serde_with = { version = "3.9.0", default-features = false, features = [
+  "macros",
+] }
+thiserror = "1.0.62"
 vfio-ioctls = { git = "https://github.com/rust-vmm/vfio", branch = "main", default-features = false }
-vm-memory = { version = "0.14.0", features = ["backend-mmap", "backend-atomic"] }
+vm-memory = { version = "0.14.1", features = [
+  "backend-atomic",
+  "backend-mmap",
+] }
 vmm-sys-util = { version = "0.12.1", features = ["with-serde"] }
-thiserror = "1.0.52"
 
 [target.'cfg(target_arch = "x86_64")'.dependencies.iced-x86]
-optional = true
-version = "1.20.0"
 default-features = false
-features = ["std", "decoder", "op_code_info", "instr_info", "fast_fmt"]
+features = ["decoder", "fast_fmt", "instr_info", "op_code_info", "std"]
+optional = true
+version = "1.21.0"
 
 [dev-dependencies]
-env_logger = "0.10.1"
+env_logger = "0.11.3"

hypervisor/src/arch/aarch64/gic.rs

@@ -1,17 +1,23 @@
 // Copyright 2022 Arm Limited (or its affiliates). All rights reserved.
+//
+// SPDX-License-Identifier: Apache-2.0
 
 use crate::{CpuState, GicState, HypervisorDeviceError, HypervisorVmError};
 use std::any::Any;
 use std::result;
+use thiserror::Error;
 
 /// Errors thrown while setting up the VGIC.
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum Error {
     /// Error while calling KVM ioctl for setting up the global interrupt controller.
+    #[error("Failed creating GIC device: {0}")]
     CreateGic(HypervisorVmError),
     /// Error while setting device attributes for the GIC.
+    #[error("Failed setting device attributes for the GIC: {0}")]
     SetDeviceAttribute(HypervisorDeviceError),
     /// Error while getting device attributes for the GIC.
+    #[error("Failed getting device attributes for the GIC: {0}")]
     GetDeviceAttribute(HypervisorDeviceError),
 }
 pub type Result<T> = result::Result<T, Error>;

hypervisor/src/arch/aarch64/mod.rs

@@ -1,3 +1,5 @@
 // Copyright 2022 Arm Limited (or its affiliates). All rights reserved.
+//
+// SPDX-License-Identifier: Apache-2.0
 
 pub mod gic;

hypervisor/src/arch/emulator/mod.rs

@@ -137,14 +137,6 @@ pub trait PlatformEmulator {
     ///
     fn set_cpu_state(&self, cpu_id: usize, state: Self::CpuState) -> Result<(), PlatformError>;
 
-    /// Translate a guest virtual address into a physical one
-    ///
-    /// # Arguments
-    ///
-    /// * `gva` - Guest virtual address to translate.
-    ///
-    fn gva_to_gpa(&self, gva: u64) -> Result<u64, PlatformError>;
-
     /// Fetch instruction bytes from memory.
     ///
     /// # Arguments

hypervisor/src/arch/x86/emulator/instructions/cmp.rs

@@ -10,10 +10,8 @@
 // CMP-Compare Two Operands
 //
 
-use crate::arch::emulator::{EmulationError, PlatformEmulator};
 use crate::arch::x86::emulator::instructions::*;
 use crate::arch::x86::regs::*;
-use crate::arch::x86::Exception;
 
 // CMP affects OF, SF, ZF, AF, PF and CF
 const FLAGS_MASK: u64 = CF | PF | AF | ZF | SF | OF;
@@ -211,8 +209,6 @@ impl<T: CpuStateManager> InstructionHandler<T> for Cmp_rm64_imm8 {
 
 #[cfg(test)]
 mod tests {
-    #![allow(unused_mut)]
-
     use super::*;
     use crate::arch::x86::emulator::mock_vmm::*;
 

hypervisor/src/arch/x86/emulator/instructions/mod.rs

@@ -13,6 +13,7 @@ pub mod cmp;
 pub mod mov;
 pub mod movs;
 pub mod or;
+pub mod stos;
 
 fn get_op<T: CpuStateManager>(
     insn: &Instruction,

hypervisor/src/arch/x86/emulator/instructions/mov.rs

@@ -12,9 +12,7 @@
 //   Copies the second operand (source operand) to the first operand (destination operand).
 //
 
-use crate::arch::emulator::{EmulationError, PlatformEmulator};
 use crate::arch::x86::emulator::instructions::*;
-use crate::arch::x86::Exception;
 
 macro_rules! mov_rm_r {
     ($bound:ty) => {
@@ -271,7 +269,6 @@ impl<T: CpuStateManager> InstructionHandler<T> for Mov_RAX_moffs64 {
 
 #[cfg(test)]
 mod tests {
-    #![allow(unused_mut)]
     use super::*;
     use crate::arch::x86::emulator::mock_vmm::*;
 

hypervisor/src/arch/x86/emulator/instructions/movs.rs

@@ -10,10 +10,8 @@
 // MOVS - Move Data from String to String
 //
 
-use crate::arch::emulator::{EmulationError, PlatformEmulator};
 use crate::arch::x86::emulator::instructions::*;
 use crate::arch::x86::regs::DF;
-use crate::arch::x86::Exception;
 
 macro_rules! movs {
     ($bound:ty) => {
@@ -42,7 +40,7 @@ macro_rules! movs {
             let len = std::mem::size_of::<$bound>();
 
             while count > 0 {
-                let mut memory: [u8; 4] = [0; 4];
+                let mut memory: [u8; 8] = [0; 8];
 
                 let src = state
                     .linearize(Register::DS, rsi, false)
@@ -85,6 +83,11 @@ macro_rules! movs {
     };
 }
 
+pub struct Movsq_m64_m64;
+impl<T: CpuStateManager> InstructionHandler<T> for Movsq_m64_m64 {
+    movs!(u64);
+}
+
 pub struct Movsd_m32_m32;
 impl<T: CpuStateManager> InstructionHandler<T> for Movsd_m32_m32 {
     movs!(u32);
@@ -102,10 +105,43 @@ impl<T: CpuStateManager> InstructionHandler<T> for Movsb_m8_m8 {
 
 #[cfg(test)]
 mod tests {
-    #![allow(unused_mut)]
     use super::*;
     use crate::arch::x86::emulator::mock_vmm::*;
 
+    #[test]
+    fn test_rep_movsq_m64_m64() {
+        let ip: u64 = 0x1000;
+        let memory: [u8; 32] = [
+            0x78, 0x56, 0x34, 0x12, // 0x12345678
+            0xdd, 0xcc, 0xbb, 0xaa, // 0xaabbccdd
+            0xa5, 0x5a, 0xa5, 0x5a, // 0x5aa55aa5
+            0xcd, 0xcd, 0xcd, 0xcd, // 0xcdcdcdcd
+            0x00, 0x00, 0x00, 0x00, // 0x00000000
+            0x00, 0x00, 0x00, 0x00, // 0x00000000
+            0x00, 0x00, 0x00, 0x00, // 0x00000000
+            0x00, 0x00, 0x00, 0x00, // 0x00000000
+        ];
+        let insn = [0xf3, 0x48, 0xa5]; // rep movsq
+        let regs = vec![
+            (Register::ECX, 2),
+            (Register::ESI, 0),
+            (Register::EDI, 0x10),
+        ];
+        let mut data = [0u8; 8];
+
+        let mut vmm = MockVmm::new(ip, regs, Some((0, &memory)));
+
+        assert!(vmm.emulate_first_insn(0, &insn).is_ok());
+
+        vmm.read_memory(0x10, &mut data).unwrap();
+        assert_eq!(0xaabbccdd12345678, <u64>::from_le_bytes(data));
+        vmm.read_memory(0x18, &mut data).unwrap();
+        assert_eq!(0xcdcdcdcd5aa55aa5, <u64>::from_le_bytes(data));
+        // The rest should be default value 0 from MockVmm
+        vmm.read_memory(0x20, &mut data).unwrap();
+        assert_eq!(0x0, <u64>::from_le_bytes(data));
+    }
+
     #[test]
     fn test_rep_movsd_m32_m32() {
         let ip: u64 = 0x1000;

hypervisor/src/arch/x86/emulator/instructions/or.rs

@@ -10,9 +10,7 @@
 // OR - Logical inclusive OR
 //
 
-use crate::arch::emulator::{EmulationError, PlatformEmulator};
 use crate::arch::x86::emulator::instructions::*;
-use crate::arch::x86::Exception;
 
 macro_rules! or_rm_r {
     ($bound:ty) => {
@@ -52,7 +50,6 @@ impl<T: CpuStateManager> InstructionHandler<T> for Or_rm8_r8 {
 
 #[cfg(test)]
 mod tests {
-    #![allow(unused_mut)]
     use super::*;
 
     use crate::arch::x86::emulator::mock_vmm::*;

hypervisor/src/arch/x86/emulator/instructions/stos.rs

@@ -0,0 +1,236 @@
+//
+// Copyright © 2024 Microsoft
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+#![allow(non_camel_case_types)]
+
+//
+// STOS - Store String
+//
+
+use crate::arch::x86::emulator::instructions::*;
+use crate::arch::x86::regs::DF;
+
+macro_rules! stos {
+    ($bound:ty) => {
+        fn emulate(
+            &self,
+            insn: &Instruction,
+            state: &mut T,
+            platform: &mut dyn PlatformEmulator<CpuState = T>,
+        ) -> Result<(), EmulationError<Exception>> {
+            let mut count: u64 = if insn.has_rep_prefix() {
+                state
+                    .read_reg(Register::ECX)
+                    .map_err(|e| EmulationError::InvalidOperand(anyhow!(e)))?
+            } else {
+                1
+            };
+
+            let rax = state
+                .read_reg(Register::RAX)
+                .map_err(|e| EmulationError::InvalidOperand(anyhow!(e)))?;
+
+            let mut rdi = state
+                .read_reg(Register::RDI)
+                .map_err(|e| EmulationError::InvalidOperand(anyhow!(e)))?;
+
+            let df = (state.flags() & DF) != 0;
+            let len = std::mem::size_of::<$bound>();
+            let rax_bytes = rax.to_le_bytes();
+
+            while count > 0 {
+                let dst = state
+                    .linearize(Register::ES, rdi, true)
+                    .map_err(|e| EmulationError::InvalidOperand(anyhow!(e)))?;
+
+                platform
+                    .write_memory(dst, &rax_bytes[0..len])
+                    .map_err(EmulationError::PlatformEmulationError)?;
+
+                if df {
+                    rdi = rdi.wrapping_sub(len as u64);
+                } else {
+                    rdi = rdi.wrapping_add(len as u64);
+                }
+                count -= 1;
+            }
+
+            if insn.has_rep_prefix() {
+                state
+                    .write_reg(Register::ECX, 0)
+                    .map_err(|e| EmulationError::InvalidOperand(anyhow!(e)))?;
+            }
+
+            Ok(())
+        }
+    };
+}
+
+pub struct Stosq_m64_RAX;
+impl<T: CpuStateManager> InstructionHandler<T> for Stosq_m64_RAX {
+    stos!(u64);
+}
+
+pub struct Stosd_m32_EAX;
+impl<T: CpuStateManager> InstructionHandler<T> for Stosd_m32_EAX {
+    stos!(u32);
+}
+
+pub struct Stosw_m16_AX;
+impl<T: CpuStateManager> InstructionHandler<T> for Stosw_m16_AX {
+    stos!(u16);
+}
+
+pub struct Stosb_m8_AL;
+impl<T: CpuStateManager> InstructionHandler<T> for Stosb_m8_AL {
+    stos!(u8);
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::arch::x86::emulator::mock_vmm::*;
+
+    #[test]
+    fn test_rep_stosb() {
+        let ip: u64 = 0x1000;
+        let memory: [u8; 12] = [
+            0x78, 0x56, 0x34, 0x12, // 0x12345678
+            0xdd, 0xcc, 0xbb, 0xaa, // 0xaabbccdd
+            0xa5, 0x5a, 0xa5, 0x5a, // 0x5aa55aa5
+        ];
+        let insn = [0xf3, 0xaa]; // rep stosb
+        let regs = vec![
+            (Register::ECX, 3),
+            (Register::EDI, 0x0),
+            (Register::RAX, 0x123456ff),
+        ];
+        let mut data = [0u8; 4];
+
+        let mut vmm = MockVmm::new(ip, regs, Some((0, &memory)));
+
+        assert!(vmm.emulate_first_insn(0, &insn).is_ok());
+
+        vmm.read_memory(0, &mut data).unwrap();
+        assert_eq!(0x12ffffff, <u32>::from_le_bytes(data));
+        vmm.read_memory(4, &mut data).unwrap();
+        assert_eq!(0xaabbccdd, <u32>::from_le_bytes(data));
+        vmm.read_memory(8, &mut data).unwrap();
+        assert_eq!(0x5aa55aa5, <u32>::from_le_bytes(data));
+    }
+
+    #[test]
+    fn test_stosw() {
+        let ip: u64 = 0x1000;
+        let memory: [u8; 4] = [
+            0x78, 0x56, 0x34, 0x12, // 0x12345678
+        ];
+        let insn = [0x66, 0xab]; // stosw
+        let regs = vec![(Register::EDI, 0x1), (Register::AX, 0xaabb)];
+        let mut data = [0u8; 4];
+
+        let mut vmm = MockVmm::new(ip, regs, Some((0, &memory)));
+
+        assert!(vmm.emulate_first_insn(0, &insn).is_ok());
+
+        vmm.read_memory(0x0, &mut data).unwrap();
+        assert_eq!(0x12aabb78, <u32>::from_le_bytes(data));
+        // The rest should be default value 0 from MockVmm
+        vmm.read_memory(0x4, &mut data).unwrap();
+        assert_eq!(0x0, <u32>::from_le_bytes(data));
+        vmm.read_memory(0x8 + 8, &mut data).unwrap();
+        assert_eq!(0x0, <u32>::from_le_bytes(data));
+    }
+
+    #[test]
+    fn test_rep_stosw() {
+        let ip: u64 = 0x1000;
+        let memory: [u8; 8] = [
+            0x78, 0x56, 0x34, 0x12, // 0x12345678
+            0x00, 0x00, 0x00, 0x00, // 0x00000000
+        ];
+        let insn = [0x66, 0xf3, 0xab]; // rep stosw
+        let regs = vec![
+            (Register::ECX, 2),
+            (Register::EDI, 0x2),
+            (Register::AX, 0xaabb),
+        ];
+        let mut data = [0u8; 4];
+
+        let mut vmm = MockVmm::new(ip, regs, Some((0, &memory)));
+
+        assert!(vmm.emulate_first_insn(0, &insn).is_ok());
+
+        vmm.read_memory(0x0, &mut data).unwrap();
+        assert_eq!(0xaabb5678, <u32>::from_le_bytes(data));
+        vmm.read_memory(0x4, &mut data).unwrap();
+        assert_eq!(0x0000aabb, <u32>::from_le_bytes(data));
+        vmm.read_memory(0x8, &mut data).unwrap();
+        assert_eq!(0x0, <u32>::from_le_bytes(data));
+    }
+
+    #[test]
+    fn test_rep_stosd() {
+        let ip: u64 = 0x1000;
+        let memory: [u8; 12] = [
+            0x78, 0x56, 0x34, 0x12, // 0x12345678
+            0x00, 0x00, 0x00, 0x00, // 0x00000000
+            0x00, 0x00, 0x00, 0x00, // 0x00000000
+        ];
+        let insn = [0xf3, 0xab]; // rep stosd
+        let regs = vec![
+            (Register::ECX, 2),
+            (Register::EDI, 0x8),
+            (Register::EAX, 0xaabbccdd),
+        ];
+        let mut data = [0u8; 4];
+
+        let mut vmm = MockVmm::new(ip, regs, Some((0, &memory)));
+
+        // Go backwards this time
+        let mut state = vmm.cpu_state(0).unwrap();
+        state.set_flags(state.flags() | DF);
+        vmm.set_cpu_state(0, state).unwrap();
+
+        assert!(vmm.emulate_first_insn(0, &insn).is_ok());
+
+        vmm.read_memory(0x0, &mut data).unwrap();
+        assert_eq!(0x12345678, <u32>::from_le_bytes(data));
+        vmm.read_memory(0x4, &mut data).unwrap();
+        assert_eq!(0xaabbccdd, <u32>::from_le_bytes(data));
+        vmm.read_memory(0x8, &mut data).unwrap();
+        assert_eq!(0xaabbccdd, <u32>::from_le_bytes(data));
+        vmm.read_memory(0xc, &mut data).unwrap();
+        assert_eq!(0x0, <u32>::from_le_bytes(data));
+    }
+
+    #[test]
+    fn test_rep_stosq() {
+        let ip: u64 = 0x1000;
+        let memory: [u8; 8] = [
+            0x78, 0x56, 0x34, 0x12, // 0x12345678
+            0x00, 0x00, 0x00, 0x00, // 0x00000000
+        ];
+        let insn = [0xf3, 0x48, 0xab]; // rep stosq
+        let regs = vec![
+            (Register::ECX, 2),
+            (Register::RDI, 0x0),
+            (Register::RAX, 0x11223344aabbccdd),
+        ];
+        let mut data = [0u8; 8];
+
+        let mut vmm = MockVmm::new(ip, regs, Some((0, &memory)));
+
+        assert!(vmm.emulate_first_insn(0, &insn).is_ok());
+
+        vmm.read_memory(0x0, &mut data).unwrap();
+        assert_eq!(0x11223344aabbccdd, <u64>::from_le_bytes(data));
+        vmm.read_memory(0x8, &mut data).unwrap();
+        assert_eq!(0x11223344aabbccdd, <u64>::from_le_bytes(data));
+        vmm.read_memory(0x10, &mut data).unwrap();
+        assert_eq!(0x0, <u64>::from_le_bytes(data));
+    }
+}

hypervisor/src/arch/x86/emulator/mod.rs

@@ -135,7 +135,7 @@ pub trait CpuStateManager: Clone {
                     .checked_add(segment_register.base)
                     .ok_or_else(|| {
                         PlatformError::InvalidAddress(anyhow!(
-                            "Logical address {:#x} can not be linearized with segment {:#x?}",
+                            "Logical address {:#x} cannot be linearized with segment {:#x?}",
                             logical_addr,
                             segment_register
                         ))
@@ -148,7 +148,7 @@ pub trait CpuStateManager: Clone {
                 // Must not write to a read-only segment.
                 if segment_type_ro(segment_type) && write {
                     return Err(PlatformError::InvalidAddress(anyhow!(
-                        "Can not write to a read-only segment"
+                        "Cannot write to a read-only segment"
                     )));
                 }
 
@@ -532,11 +532,17 @@ impl<'a, T: CpuStateManager> Emulator<'a, T> {
             (mov, Mov_moffs64_RAX),
             (mov, Mov_RAX_moffs64),
             // MOVS
+            (movs, Movsq_m64_m64),
             (movs, Movsd_m32_m32),
             (movs, Movsw_m16_m16),
             (movs, Movsb_m8_m8),
             // OR
-            (or, Or_rm8_r8)
+            (or, Or_rm8_r8),
+            // STOS
+            (stos, Stosb_m8_AL),
+            (stos, Stosw_m16_AX),
+            (stos, Stosd_m32_EAX),
+            (stos, Stosq_m64_RAX)
         );
 
         handler
@@ -561,7 +567,7 @@ impl<'a, T: CpuStateManager> Emulator<'a, T> {
 
         decoder.set_ip(state.ip());
 
-        while decoder.can_decode() && !stop_emulation {
+        while !stop_emulation {
             decoder.decode_out(&mut insn);
 
             if decoder.last_error() == DecoderError::NoMoreBytes {
@@ -588,6 +594,7 @@ impl<'a, T: CpuStateManager> Emulator<'a, T> {
                 // Once we have the new stream, we must create a new decoder
                 // and emulate one last instruction from the last decoded IP.
                 decoder = Decoder::new(64, &fetched_insn_stream, DecoderOptions::NONE);
+                decoder.set_ip(last_decoded_ip);
                 decoder.decode_out(&mut insn);
                 if decoder.last_error() != DecoderError::None {
                     return Err(EmulationError::InstructionFetchingError(anyhow!(
@@ -595,8 +602,6 @@ impl<'a, T: CpuStateManager> Emulator<'a, T> {
                         insn_format!(insn)
                     )));
                 }
-
-                stop_emulation = true;
             }
 
             // Emulate the decoded instruction
@@ -648,13 +653,9 @@ impl<'a, T: CpuStateManager> Emulator<'a, T> {
 
 #[cfg(test)]
 mod mock_vmm {
-    #![allow(unused_mut)]
-
     use super::*;
-    use crate::arch::emulator::{EmulationError, PlatformEmulator};
-    use crate::arch::x86::emulator::{Emulator, EmulatorCpuState as CpuState};
+    use crate::arch::x86::emulator::EmulatorCpuState as CpuState;
     use crate::arch::x86::gdt::{gdt_entry, segment_from_gdt};
-    use crate::arch::x86::Exception;
     use std::sync::{Arc, Mutex};
 
     #[derive(Debug, Clone)]
@@ -755,10 +756,6 @@ mod mock_vmm {
             Ok(())
         }
 
-        fn gva_to_gpa(&self, gva: u64) -> Result<u64, PlatformError> {
-            Ok(gva)
-        }
-
         fn fetch(&self, ip: u64, instruction_bytes: &mut [u8]) -> Result<(), PlatformError> {
             let rip = self
                 .state
@@ -772,16 +769,80 @@ mod mock_vmm {
 
 #[cfg(test)]
 mod tests {
-    #![allow(unused_mut)]
     use super::*;
     use crate::arch::x86::emulator::mock_vmm::*;
 
+    #[test]
+    // Emulate executing an empty stream. Instructions should be fetched from
+    // memory.
+    //
+    // mov rax, 0x1000
+    // mov rbx, qword ptr [rax+10h]
+    fn test_empty_instruction_stream() {
+        let target_rax: u64 = 0x1000;
+        let target_rbx: u64 = 0x1234567812345678;
+        let ip: u64 = 0x1000;
+        let cpu_id = 0;
+        let memory = [
+            // Code at IP
+            0x48, 0xc7, 0xc0, 0x00, 0x10, 0x00, 0x00, // mov rax, 0x1000
+            0x48, 0x8b, 0x58, 0x10, // mov rbx, qword ptr [rax+10h]
+            // Padding
+            0x00, 0x00, 0x00, 0x00, 0x00, // Padding is all zeroes
+            // Data at IP + 0x10 (0x1234567812345678 in LE)
+            0x78, 0x56, 0x34, 0x12, 0x78, 0x56, 0x34, 0x12,
+        ];
+
+        let mut vmm = MockVmm::new(ip, vec![], Some((ip, &memory)));
+        assert!(vmm.emulate_insn(cpu_id, &[], Some(2)).is_ok());
+
+        let rax: u64 = vmm
+            .cpu_state(cpu_id)
+            .unwrap()
+            .read_reg(Register::RAX)
+            .unwrap();
+        assert_eq!(rax, target_rax);
+
+        let rbx: u64 = vmm
+            .cpu_state(cpu_id)
+            .unwrap()
+            .read_reg(Register::RBX)
+            .unwrap();
+        assert_eq!(rbx, target_rbx);
+    }
+
+    #[test]
+    // Emulate executing an empty stream. Instructions should be fetched from
+    // memory. The emulation should abort.
+    //
+    // mov rax, 0x1000
+    // mov rbx, qword ptr [rax+10h]
+    // ... garbage ...
+    fn test_empty_instruction_stream_bad() {
+        let ip: u64 = 0x1000;
+        let cpu_id = 0;
+        let memory = [
+            // Code at IP
+            0x48, 0xc7, 0xc0, 0x00, 0x10, 0x00, 0x00, // mov rax, 0x1000
+            0x48, 0x8b, 0x58, 0x10, // mov rbx, qword ptr [rax+10h]
+            // Padding
+            0xff, 0xff, 0xff, 0xff, 0xff, // Garbage
+            // Data at IP + 0x10 (0x1234567812345678 in LE)
+            0x78, 0x56, 0x34, 0x12, 0x78, 0x56, 0x34, 0x12,
+        ];
+
+        let mut vmm = MockVmm::new(ip, vec![], Some((ip, &memory)));
+        assert!(vmm.emulate_insn(cpu_id, &[], None).is_err());
+    }
+
     #[test]
     // Emulate truncated instruction stream, which should cause a fetch.
     //
     // mov rax, 0x1000
+    // mov rbx, qword ptr [rax+10h]
     // Test with a first instruction truncated.
     fn test_fetch_first_instruction() {
+        let target_rax: u64 = 0x1000;
         let ip: u64 = 0x1000;
         let cpu_id = 0;
         let memory = [
@@ -806,7 +867,7 @@ mod tests {
             .unwrap()
             .read_reg(Register::RAX)
             .unwrap();
-        assert_eq!(rax, ip);
+        assert_eq!(rax, target_rax);
     }
 
     #[test]
@@ -844,6 +905,52 @@ mod tests {
         assert_eq!(rbx, target_rax);
     }
 
+    #[test]
+    // Emulate only one instruction.
+    //
+    // mov rax, 0x1000
+    // mov rbx, qword ptr [rax+10h]
+    // The emulation should stop after the first instruction.
+    fn test_emulate_one_instruction() {
+        let target_rax: u64 = 0x1000;
+        let ip: u64 = 0x1000;
+        let cpu_id = 0;
+        let memory = [
+            // Code at IP
+            0x48, 0xc7, 0xc0, 0x00, 0x10, 0x00, 0x00, // mov rax, 0x1000
+            0x48, 0x8b, 0x58, 0x10, // mov rbx, qword ptr [rax+10h]
+            // Padding
+            0x00, 0x00, 0x00, 0x00, 0x00, // Padding is all zeroes
+            // Data at IP + 0x10 (0x1234567812345678 in LE)
+            0x78, 0x56, 0x34, 0x12, 0x78, 0x56, 0x34, 0x12,
+        ];
+        let insn = [
+            0x48, 0xc7, 0xc0, 0x00, 0x10, 0x00, 0x00, // mov rax, 0x1000
+            0x48, 0x8b, 0x58, 0x10, // mov rbx, qword ptr [rax+10h]
+        ];
+
+        let mut vmm = MockVmm::new(ip, vec![], Some((ip, &memory)));
+        assert!(vmm.emulate_insn(cpu_id, &insn, Some(1)).is_ok());
+
+        let new_ip: u64 = vmm.cpu_state(cpu_id).unwrap().ip();
+        assert_eq!(new_ip, ip + 0x7 /* length of mov rax,0x1000 */);
+
+        let rax: u64 = vmm
+            .cpu_state(cpu_id)
+            .unwrap()
+            .read_reg(Register::RAX)
+            .unwrap();
+        assert_eq!(rax, target_rax);
+
+        // The second instruction is not executed so RBX should be zero.
+        let rbx: u64 = vmm
+            .cpu_state(cpu_id)
+            .unwrap()
+            .read_reg(Register::RBX)
+            .unwrap();
+        assert_eq!(rbx, 0);
+    }
+
     #[test]
     // Emulate truncated instruction stream, which should cause a fetch.
     //

hypervisor/src/arch/x86/mod.rs

@@ -53,7 +53,6 @@ pub enum Exception {
 pub mod regs;
 
 #[derive(Debug, Default, Copy, Clone, PartialEq, Eq)]
-#[cfg_attr(feature = "with-serde", derive(Deserialize, Serialize))]
 pub struct SegmentRegister {
     pub base: u64,
     pub limit: u32,
@@ -174,7 +173,6 @@ macro_rules! msr_data {
 }
 
 #[derive(Debug, Default, Copy, Clone, PartialEq, Eq)]
-#[cfg_attr(feature = "with-serde", derive(Deserialize, Serialize))]
 pub struct StandardRegisters {
     pub rax: u64,
     pub rbx: u64,
@@ -197,14 +195,12 @@ pub struct StandardRegisters {
 }
 
 #[derive(Debug, Default, Copy, Clone, PartialEq, Eq)]
-#[cfg_attr(feature = "with-serde", derive(Deserialize, Serialize))]
 pub struct DescriptorTable {
     pub base: u64,
     pub limit: u16,
 }
 
 #[derive(Debug, Default, Copy, Clone, PartialEq, Eq)]
-#[cfg_attr(feature = "with-serde", derive(Deserialize, Serialize))]
 pub struct SpecialRegisters {
     pub cs: SegmentRegister,
     pub ds: SegmentRegister,

hypervisor/src/arch/x86/msr_index.rs

@@ -1,4 +1,6 @@
 // Copyright 2017 The Chromium OS Authors. All rights reserved.
+//
+// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE-BSD-3-Clause file.
 

hypervisor/src/cpu.rs

@@ -107,14 +107,28 @@ pub enum HypervisorCpuError {
     ///
     /// Setting Saved Processor Extended States error
     ///
+    #[cfg(feature = "kvm")]
     #[error("Failed to set Saved Processor Extended States: {0}")]
     SetXsaveState(#[source] anyhow::Error),
     ///
     /// Getting Saved Processor Extended States error
     ///
+    #[cfg(feature = "kvm")]
     #[error("Failed to get Saved Processor Extended States: {0}")]
     GetXsaveState(#[source] anyhow::Error),
     ///
+    /// Getting the VP state components error
+    ///
+    #[cfg(feature = "mshv")]
+    #[error("Failed to get VP State Components: {0}")]
+    GetAllVpStateComponents(#[source] anyhow::Error),
+    ///
+    /// Setting the VP state components error
+    ///
+    #[cfg(feature = "mshv")]
+    #[error("Failed to set VP State Components: {0}")]
+    SetAllVpStateComponents(#[source] anyhow::Error),
+    ///
     /// Setting Extended Control Registers error
     ///
     #[error("Failed to set Extended Control Registers: {0}")]
@@ -278,18 +292,17 @@ pub enum HypervisorCpuError {
     #[cfg(feature = "sev_snp")]
     #[error("Failed to set sev control register: {0}")]
     SetSevControlRegister(#[source] anyhow::Error),
+
+    /// Error injecting NMI
+    ///
+    #[error("Failed to inject NMI")]
+    Nmi(#[source] anyhow::Error),
 }
 
 #[derive(Debug)]
-pub enum VmExit<'a> {
-    #[cfg(target_arch = "x86_64")]
-    IoOut(u16 /* port */, &'a [u8] /* data */),
-    #[cfg(target_arch = "x86_64")]
-    IoIn(u16 /* port */, &'a mut [u8] /* data */),
+pub enum VmExit {
     #[cfg(target_arch = "x86_64")]
     IoapicEoi(u8 /* vector */),
-    MmioRead(u64 /* address */, &'a mut [u8]),
-    MmioWrite(u64 /* address */, &'a [u8]),
     Ignore,
     Reset,
     Shutdown,
@@ -505,4 +518,10 @@ pub trait Vcpu: Send + Sync {
     fn set_sev_control_register(&self, _reg: u64) -> Result<()> {
         unimplemented!()
     }
+
+    #[cfg(target_arch = "x86_64")]
+    ///
+    /// Trigger NMI interrupt
+    ///
+    fn nmi(&self) -> Result<()>;
 }

hypervisor/src/hypervisor.rs

@@ -21,8 +21,6 @@ use std::sync::Arc;
 use thiserror::Error;
 
 #[derive(Error, Debug)]
-///
-///
 pub enum HypervisorError {
     ///
     /// Hypervisor availability check error
@@ -168,7 +166,7 @@ pub trait Hypervisor: Send + Sync {
                 CpuVendor::AMD
             } else {
                 // Not known yet, the corresponding manufacturer manual should contain the
-                // necesssary info. See also https://wiki.osdev.org/CPUID#CPU_Vendor_ID_String
+                // necessary info. See also https://wiki.osdev.org/CPUID#CPU_Vendor_ID_String
                 CpuVendor::default()
             }
         }

hypervisor/src/kvm/aarch64/gic/dist_regs.rs

@@ -77,46 +77,61 @@ static VGIC_DIST_REGS: &[DistReg] = &[
     VGIC_DIST_REG!(GICD_IPRIORITYR, 8, 0),
 ];
 
-fn dist_attr_access(gic: &DeviceFd, offset: u32, val: &u32, set: bool) -> Result<()> {
+fn dist_attr_set(gic: &DeviceFd, offset: u32, val: u32) -> Result<()> {
+    let gic_dist_attr = kvm_device_attr {
+        group: KVM_DEV_ARM_VGIC_GRP_DIST_REGS,
+        attr: offset as u64,
+        addr: &val as *const u32 as u64,
+        flags: 0,
+    };
+
+    gic.set_device_attr(&gic_dist_attr).map_err(|e| {
+        Error::SetDeviceAttribute(HypervisorDeviceError::SetDeviceAttribute(e.into()))
+    })?;
+
+    Ok(())
+}
+
+fn dist_attr_get(gic: &DeviceFd, offset: u32) -> Result<u32> {
+    let mut val = 0;
+
     let mut gic_dist_attr = kvm_device_attr {
         group: KVM_DEV_ARM_VGIC_GRP_DIST_REGS,
         attr: offset as u64,
-        addr: val as *const u32 as u64,
+        addr: &mut val as *mut u32 as u64,
         flags: 0,
     };
-    if set {
-        gic.set_device_attr(&gic_dist_attr).map_err(|e| {
-            Error::SetDeviceAttribute(HypervisorDeviceError::SetDeviceAttribute(e.into()))
-        })?;
-    } else {
-        gic.get_device_attr(&mut gic_dist_attr).map_err(|e| {
-            Error::GetDeviceAttribute(HypervisorDeviceError::GetDeviceAttribute(e.into()))
-        })?;
-    }
-    Ok(())
+
+    // get_device_attr should be marked as unsafe, and will be in future.
+    // SAFETY: gic_dist_attr.addr is safe to write to.
+    gic.get_device_attr(&mut gic_dist_attr).map_err(|e| {
+        Error::GetDeviceAttribute(HypervisorDeviceError::GetDeviceAttribute(e.into()))
+    })?;
+
+    Ok(val)
 }
 
 /// Get the distributor control register.
 pub fn read_ctlr(gic: &DeviceFd) -> Result<u32> {
-    let val: u32 = 0;
-    dist_attr_access(gic, GICD_CTLR, &val, false)?;
-    Ok(val)
+    dist_attr_get(gic, GICD_CTLR)
 }
 
 /// Set the distributor control register.
 pub fn write_ctlr(gic: &DeviceFd, val: u32) -> Result<()> {
-    dist_attr_access(gic, GICD_CTLR, &val, true)
+    dist_attr_set(gic, GICD_CTLR, val)
 }
 
 fn get_interrupts_num(gic: &DeviceFd) -> Result<u32> {
-    let num_irq = 0;
+    let mut num_irq = 0;
 
     let mut nr_irqs_attr = kvm_device_attr {
         group: KVM_DEV_ARM_VGIC_GRP_NR_IRQS,
         attr: 0,
-        addr: &num_irq as *const u32 as u64,
+        addr: &mut num_irq as *mut u32 as u64,
         flags: 0,
     };
+    // get_device_attr should be marked as unsafe, and will be in future.
+    // SAFETY: nr_irqs_attr.addr is safe to write to.
     gic.get_device_attr(&mut nr_irqs_attr).map_err(|e| {
         Error::GetDeviceAttribute(HypervisorDeviceError::GetDeviceAttribute(e.into()))
     })?;
@@ -158,8 +173,7 @@ pub fn set_dist_regs(gic: &DeviceFd, state: &[u32]) -> Result<()> {
         let end = compute_reg_len(gic, dreg, base)?;
 
         while base < end {
-            let val = state[idx];
-            dist_attr_access(gic, base, &val, true)?;
+            dist_attr_set(gic, base, state[idx])?;
             idx += 1;
             base += REG_SIZE as u32;
         }
@@ -175,9 +189,7 @@ pub fn get_dist_regs(gic: &DeviceFd) -> Result<Vec<u32>> {
         let end = compute_reg_len(gic, dreg, base)?;
 
         while base < end {
-            let val: u32 = 0;
-            dist_attr_access(gic, base, &val, false)?;
-            state.push(val);
+            state.push(dist_attr_get(gic, base)?);
             base += REG_SIZE as u32;
         }
     }

hypervisor/src/kvm/aarch64/gic/icc_regs.rs

@@ -79,23 +79,38 @@ static VGIC_ICC_REGS: &[u64] = &[
     SYS_ICC_AP1R3_EL1,
 ];
 
-fn icc_attr_access(gic: &DeviceFd, offset: u64, typer: u64, val: &u32, set: bool) -> Result<()> {
+fn icc_attr_set(gic: &DeviceFd, offset: u64, typer: u64, val: u32) -> Result<()> {
+    let gic_icc_attr = kvm_device_attr {
+        group: KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS,
+        attr: ((typer & KVM_DEV_ARM_VGIC_V3_MPIDR_MASK) | offset), // this needs the mpidr
+        addr: &val as *const u32 as u64,
+        flags: 0,
+    };
+
+    gic.set_device_attr(&gic_icc_attr).map_err(|e| {
+        Error::SetDeviceAttribute(HypervisorDeviceError::SetDeviceAttribute(e.into()))
+    })?;
+
+    Ok(())
+}
+
+fn icc_attr_get(gic: &DeviceFd, offset: u64, typer: u64) -> Result<u32> {
+    let mut val = 0;
+
     let mut gic_icc_attr = kvm_device_attr {
         group: KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS,
         attr: ((typer & KVM_DEV_ARM_VGIC_V3_MPIDR_MASK) | offset), // this needs the mpidr
-        addr: val as *const u32 as u64,
+        addr: &mut val as *mut u32 as u64,
         flags: 0,
     };
-    if set {
-        gic.set_device_attr(&gic_icc_attr).map_err(|e| {
-            Error::SetDeviceAttribute(HypervisorDeviceError::SetDeviceAttribute(e.into()))
-        })?;
-    } else {
-        gic.get_device_attr(&mut gic_icc_attr).map_err(|e| {
-            Error::GetDeviceAttribute(HypervisorDeviceError::GetDeviceAttribute(e.into()))
-        })?;
-    }
-    Ok(())
+
+    // get_device_attr should be marked as unsafe, and will be in future.
+    // SAFETY: gic_icc_attr.addr is safe to write to.
+    gic.get_device_attr(&mut gic_icc_attr).map_err(|e| {
+        Error::GetDeviceAttribute(HypervisorDeviceError::GetDeviceAttribute(e.into()))
+    })?;
+
+    Ok(val)
 }
 
 /// Get ICC registers.
@@ -107,10 +122,9 @@ pub fn get_icc_regs(gic: &DeviceFd, gicr_typer: &[u64]) -> Result<Vec<u32>> {
     for ix in gicr_typer {
         let i = *ix;
         for icc_offset in VGIC_ICC_REGS {
-            let val = 0;
             if *icc_offset == SYS_ICC_CTLR_EL1 {
                 // calculate priority bits by reading the ctrl_el1 register.
-                icc_attr_access(gic, *icc_offset, i, &val, false)?;
+                let val = icc_attr_get(gic, *icc_offset, i)?;
                 // The priority bits are found in the ICC_CTLR_EL1 register (bits from  10:8).
                 // See page 194 from https://static.docs.arm.com/ihi0069/c/IHI0069C_gic_
                 // architecture_specification.pdf.
@@ -130,8 +144,7 @@ pub fn get_icc_regs(gic: &DeviceFd, gicr_typer: &[u64]) -> Result<Vec<u32>> {
             // 7 bits of priority.
             else if *icc_offset == SYS_ICC_AP0R1_EL1 || *icc_offset == SYS_ICC_AP1R1_EL1 {
                 if num_priority_bits >= 6 {
-                    icc_attr_access(gic, *icc_offset, i, &val, false)?;
-                    state.push(val);
+                    state.push(icc_attr_get(gic, *icc_offset, i)?);
                 }
             } else if *icc_offset == SYS_ICC_AP0R2_EL1
                 || *icc_offset == SYS_ICC_AP0R3_EL1
@@ -139,12 +152,10 @@ pub fn get_icc_regs(gic: &DeviceFd, gicr_typer: &[u64]) -> Result<Vec<u32>> {
                 || *icc_offset == SYS_ICC_AP1R3_EL1
             {
                 if num_priority_bits == 7 {
-                    icc_attr_access(gic, *icc_offset, i, &val, false)?;
-                    state.push(val);
+                    state.push(icc_attr_get(gic, *icc_offset, i)?);
                 }
             } else {
-                icc_attr_access(gic, *icc_offset, i, &val, false)?;
-                state.push(val);
+                state.push(icc_attr_get(gic, *icc_offset, i)?);
             }
         }
     }
@@ -165,7 +176,7 @@ pub fn set_icc_regs(gic: &DeviceFd, gicr_typer: &[u64], state: &[u32]) -> Result
             }
             if *icc_offset == SYS_ICC_AP0R1_EL1 || *icc_offset == SYS_ICC_AP1R1_EL1 {
                 if num_priority_bits >= 6 {
-                    icc_attr_access(gic, *icc_offset, i, &state[idx], true)?;
+                    icc_attr_set(gic, *icc_offset, i, state[idx])?;
                     idx += 1;
                 }
                 continue;
@@ -176,12 +187,12 @@ pub fn set_icc_regs(gic: &DeviceFd, gicr_typer: &[u64], state: &[u32]) -> Result
                 || *icc_offset == SYS_ICC_AP1R3_EL1
             {
                 if num_priority_bits == 7 {
-                    icc_attr_access(gic, *icc_offset, i, &state[idx], true)?;
+                    icc_attr_set(gic, *icc_offset, i, state[idx])?;
                     idx += 1;
                 }
                 continue;
             }
-            icc_attr_access(gic, *icc_offset, i, &state[idx], true)?;
+            icc_attr_set(gic, *icc_offset, i, state[idx])?;
             idx += 1;
         }
     }

hypervisor/src/kvm/aarch64/gic/mod.rs

@@ -1,4 +1,6 @@
 // Copyright 2022 Arm Limited (or its affiliates). All rights reserved.
+//
+// SPDX-License-Identifier: Apache-2.0
 
 mod dist_regs;
 mod icc_regs;
@@ -6,7 +8,7 @@ mod redist_regs;
 
 use crate::arch::aarch64::gic::{Error, Result, Vgic, VgicConfig};
 use crate::device::HypervisorDeviceError;
-use crate::kvm::{kvm_bindings, KvmVm};
+use crate::kvm::KvmVm;
 use crate::{CpuState, Vm};
 use dist_regs::{get_dist_regs, read_ctlr, set_dist_regs, write_ctlr};
 use icc_regs::{get_icc_regs, set_icc_regs};
@@ -14,7 +16,6 @@ use kvm_ioctls::DeviceFd;
 use redist_regs::{construct_gicr_typers, get_redist_regs, set_redist_regs};
 use serde::{Deserialize, Serialize};
 use std::any::Any;
-use std::convert::TryInto;
 
 const GITS_CTLR: u32 = 0x0000;
 const GITS_IIDR: u32 = 0x0004;
@@ -23,34 +24,38 @@ const GITS_CWRITER: u32 = 0x0088;
 const GITS_CREADR: u32 = 0x0090;
 const GITS_BASER: u32 = 0x0100;
 
-/// Access an ITS device attribute.
-///
-/// This is a helper function to get/set the ITS device attribute depending
-/// the bool parameter `set` provided.
-pub fn gicv3_its_attr_access(
-    its_device: &DeviceFd,
-    group: u32,
-    attr: u32,
-    val: &u64,
-    set: bool,
-) -> Result<()> {
+fn gicv3_its_attr_set(its_device: &DeviceFd, group: u32, attr: u32, val: u64) -> Result<()> {
+    let gicv3_its_attr = kvm_bindings::kvm_device_attr {
+        group,
+        attr: attr as u64,
+        addr: &val as *const u64 as u64,
+        flags: 0,
+    };
+
+    its_device
+        .set_device_attr(&gicv3_its_attr)
+        .map_err(|e| Error::SetDeviceAttribute(HypervisorDeviceError::SetDeviceAttribute(e.into())))
+}
+
+fn gicv3_its_attr_get(its_device: &DeviceFd, group: u32, attr: u32) -> Result<u64> {
+    let mut val = 0;
+
     let mut gicv3_its_attr = kvm_bindings::kvm_device_attr {
         group,
         attr: attr as u64,
-        addr: val as *const u64 as u64,
+        addr: &mut val as *mut u64 as u64,
         flags: 0,
     };
-    if set {
-        its_device.set_device_attr(&gicv3_its_attr).map_err(|e| {
-            Error::SetDeviceAttribute(HypervisorDeviceError::SetDeviceAttribute(e.into()))
-        })
-    } else {
-        its_device
-            .get_device_attr(&mut gicv3_its_attr)
-            .map_err(|e| {
-                Error::GetDeviceAttribute(HypervisorDeviceError::GetDeviceAttribute(e.into()))
-            })
-    }
+
+    // get_device_attr should be marked as unsafe, and will be in future.
+    // SAFETY: gicv3_its_attr.addr is safe to write to.
+    its_device
+        .get_device_attr(&mut gicv3_its_attr)
+        .map_err(|e| {
+            Error::GetDeviceAttribute(HypervisorDeviceError::GetDeviceAttribute(e.into()))
+        })?;
+
+    Ok(val)
 }
 
 /// Function that saves/restores ITS tables into guest RAM.
@@ -323,60 +328,43 @@ impl Vgic for KvmGicV3Its {
 
         let icc_state = get_icc_regs(&self.device, &gicr_typers)?;
 
-        let its_baser_state: [u64; 8] = [0; 8];
+        let mut its_baser_state: [u64; 8] = [0; 8];
         for i in 0..8 {
-            gicv3_its_attr_access(
+            its_baser_state[i as usize] = gicv3_its_attr_get(
                 self.its_device.as_ref().unwrap(),
                 kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
                 GITS_BASER + i * 8,
-                &its_baser_state[i as usize],
-                false,
             )?;
         }
 
-        let its_ctlr_state: u64 = 0;
-        gicv3_its_attr_access(
+        let its_ctlr_state = gicv3_its_attr_get(
             self.its_device.as_ref().unwrap(),
             kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
             GITS_CTLR,
-            &its_ctlr_state,
-            false,
         )?;
 
-        let its_cbaser_state: u64 = 0;
-        gicv3_its_attr_access(
+        let its_cbaser_state = gicv3_its_attr_get(
             self.its_device.as_ref().unwrap(),
             kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
             GITS_CBASER,
-            &its_cbaser_state,
-            false,
         )?;
 
-        let its_creadr_state: u64 = 0;
-        gicv3_its_attr_access(
+        let its_creadr_state = gicv3_its_attr_get(
             self.its_device.as_ref().unwrap(),
             kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
             GITS_CREADR,
-            &its_creadr_state,
-            false,
         )?;
 
-        let its_cwriter_state: u64 = 0;
-        gicv3_its_attr_access(
+        let its_cwriter_state = gicv3_its_attr_get(
             self.its_device.as_ref().unwrap(),
             kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
             GITS_CWRITER,
-            &its_cwriter_state,
-            false,
         )?;
 
-        let its_iidr_state: u64 = 0;
-        gicv3_its_attr_access(
+        let its_iidr_state = gicv3_its_attr_get(
             self.its_device.as_ref().unwrap(),
             kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
             GITS_IIDR,
-            &its_iidr_state,
-            false,
         )?;
 
         Ok(Gicv3ItsState {
@@ -406,57 +394,51 @@ impl Vgic for KvmGicV3Its {
         set_icc_regs(&self.device, &gicr_typers, &state.icc)?;
 
         //Restore GICv3ITS registers
-        gicv3_its_attr_access(
+        gicv3_its_attr_set(
             self.its_device.as_ref().unwrap(),
             kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
             GITS_IIDR,
-            &state.its_iidr,
-            true,
+            state.its_iidr,
         )?;
 
-        gicv3_its_attr_access(
+        gicv3_its_attr_set(
             self.its_device.as_ref().unwrap(),
             kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
             GITS_CBASER,
-            &state.its_cbaser,
-            true,
+            state.its_cbaser,
         )?;
 
-        gicv3_its_attr_access(
+        gicv3_its_attr_set(
             self.its_device.as_ref().unwrap(),
             kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
             GITS_CREADR,
-            &state.its_creadr,
-            true,
+            state.its_creadr,
         )?;
 
-        gicv3_its_attr_access(
+        gicv3_its_attr_set(
             self.its_device.as_ref().unwrap(),
             kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
             GITS_CWRITER,
-            &state.its_cwriter,
-            true,
+            state.its_cwriter,
         )?;
 
         for i in 0..8 {
-            gicv3_its_attr_access(
+            gicv3_its_attr_set(
                 self.its_device.as_ref().unwrap(),
                 kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
                 GITS_BASER + i * 8,
-                &state.its_baser[i as usize],
-                true,
+                state.its_baser[i as usize],
             )?;
         }
 
         // Restore ITS tables
         gicv3_its_tables_access(self.its_device.as_ref().unwrap(), false)?;
 
-        gicv3_its_attr_access(
+        gicv3_its_attr_set(
             self.its_device.as_ref().unwrap(),
             kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
             GITS_CTLR,
-            &state.its_ctlr,
-            true,
+            state.its_ctlr,
         )
     }