build: Update for v0.14.1 bug fix release

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

.github/ISSUE_TEMPLATE/bug_report.md

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

.github/dependabot.yml

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

.github/workflows/build.yaml

@@ -13,7 +13,6 @@ jobs:
           - stable
           - beta
           - nightly
-          - "1.62"
         target:
           - x86_64-unknown-linux-gnu
           - x86_64-unknown-linux-musl
@@ -23,36 +22,23 @@ jobs:
         with:
           fetch-depth: 0
 
-      - name: Install musl-gcc
-        run: sudo apt install -y musl-tools
-
       - name: Install Rust toolchain (${{ matrix.rust }})
         uses: actions-rs/toolchain@v1
         with:
-          toolchain: ${{ matrix.rust }}
-          target: ${{ matrix.target }}
-          override: true
+            toolchain: ${{ matrix.rust }}
+            target: ${{ matrix.target }}
+            override: true
 
-      - name: Build (default features)
-        run: cargo rustc --locked --bin cloud-hypervisor -- -D warnings
+      - name: Debug Check (default features)
+        run: |
+          git rev-list origin/master..$GITHUB_SHA | xargs -t -I % sh -c 'git checkout %; cargo check --all --target=${{ matrix.target }}'
+          git checkout $GITHUB_SHA
+
+      - name: Build (acpi,kvm)
+        run: cargo rustc --bin cloud-hypervisor --no-default-features --features "acpi,kvm"  -- -D warnings
 
       - name: Build (kvm)
-        run: cargo rustc --locked --bin cloud-hypervisor --no-default-features --features "kvm"  -- -D warnings
-
-      - name: Build (default features + tdx)
-        run: cargo rustc --locked --bin cloud-hypervisor --features "tdx" -- -D warnings
-
-      - name: Build (default features + guest_debug)
-        run: cargo rustc --locked --bin cloud-hypervisor --features "guest_debug" -- -D warnings
-
-      - name: Build (mshv)
-        run: cargo rustc --locked --bin cloud-hypervisor --no-default-features --features "mshv"  -- -D warnings
-
-      - name: Build (mshv + kvm)
-        run: cargo rustc --locked --bin cloud-hypervisor --no-default-features --features "mshv,kvm"  -- -D warnings
-
+        run: cargo rustc --bin cloud-hypervisor --no-default-features --features "kvm"  -- -D warnings
+        
       - name: Release Build (default features)
-        run: cargo build --locked --all --release --target=${{ matrix.target }}
-
-      - name: Check build did not modify any files
-        run: test -z "$(git status --porcelain)"
+        run: cargo build --all --release --target=${{ matrix.target }}

.github/workflows/dco.yaml

@@ -1,18 +0,0 @@
-name: DCO
-on:
-  pull_request:
-jobs:
-  check:
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v2
-    - name: Set up Python 3.x
-      uses: actions/setup-python@v1
-      with:
-        python-version: '3.x'
-    - name: Check DCO
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      run: |
-        pip3 install -U dco-check
-        dco-check -e "49699333+dependabot[bot]@users.noreply.github.com"

.github/workflows/docker-image.yaml

@@ -1,10 +1,8 @@
-name: Cloud Hypervisor's Docker image update
+name: Cloud-Hypervisor's Docker image update
 
 on:
   push:
-    branches: main
-    paths: resources/Dockerfile
-  pull_request:
+    branches: master
     paths: resources/Dockerfile
 
 jobs:
@@ -21,39 +19,18 @@ jobs:
         uses: docker/setup-buildx-action@v1
 
       - name: Login to DockerHub
-        if: ${{ github.event_name == 'push' }}
         uses: docker/login-action@v1 
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
-      - name: Docker meta
-        id: meta
-        uses: docker/metadata-action@v3
-        with:
-          # list of Docker images to use as base name for tags
-          images: cloudhypervisor/dev
-          # generate Docker tags based on the following events/attributes
-          tags: |
-            type=raw,value={{date 'YYYYMMDD'}}-0
-            type=sha
-
       - name: Build and push
-        if: ${{ github.event_name == 'push' }}
         uses: docker/build-push-action@v2
         with:
           file: ./resources/Dockerfile
           platforms: linux/amd64,linux/arm64
           push: true
-          tags: ${{ steps.meta.outputs.tags }}
-
-      - name: Build only
-        if: ${{ github.event_name == 'pull_request' }}
-        uses: docker/build-push-action@v2
-        with:
-          file: ./resources/Dockerfile
-          platforms: linux/amd64,linux/arm64
-          tags: ${{ steps.meta.outputs.tags }}
+          tags: cloudhypervisor/dev:latest
 
       - name: Image digest
         run: echo ${{ steps.docker_build.outputs.digest }}

.github/workflows/fuzz-build.yaml

@@ -22,8 +22,6 @@ jobs:
             target: ${{ matrix.target }}
             override: true
       - name: Install Cargo fuzz
-        # Temporary fix for cargo-fuzz on latest nightly: https://github.com/rust-fuzz/cargo-fuzz/issues/276
-        #run: cargo install cargo-fuzz
-        run: cargo install --git https://github.com/rust-fuzz/cargo-fuzz --rev b4df3e58f767b5cad8d1aa6753961003f56f3609
+        run: cargo install -f cargo-fuzz
       - name: Cargo Fuzz Build
         run: cargo fuzz build

.github/workflows/quality-aarch64.yaml

@@ -0,0 +1,34 @@
+name: Cloud Hypervisor Quality Checks
+on: [pull_request, create]
+
+jobs:
+  build:
+    if: github.event_name == 'pull_request'
+    name: Quality (clippy, rustfmt)
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        rust:
+          - stable
+        target:
+          - aarch64-unknown-linux-gnu
+    steps:
+      - name: Code checkout
+        uses: actions/checkout@v2
+      - name: Install Rust toolchain (${{ matrix.rust }})
+        uses: actions-rs/toolchain@v1
+        with:
+            toolchain: ${{ matrix.rust }}
+            target: ${{ matrix.target }}
+            override: true
+            components: rustfmt, clippy
+      - name: Install arm64 libfdt
+        run: wget http://ftp.us.debian.org/debian/pool/main/d/device-tree-compiler/libfdt-dev_1.6.0-1_arm64.deb && dpkg-deb -xv libfdt-dev_1.6.0-1_arm64.deb ./tlibfdtdev && mkdir -p target/debug/deps && sudo cp ./tlibfdtdev/usr/lib/aarch64-linux-gnu/libfdt.a target/debug/deps/libfdt.a && echo "libfdt installed"
+      - name: Formatting (rustfmt)
+        run: cargo fmt -- --check
+      - name: Clippy (kvm)
+        uses: actions-rs/cargo@v1
+        with:
+          use-cross: true
+          command: clippy
+          args: --target=${{ matrix.target }} --no-default-features --features "kvm" -- -D warnings

.github/workflows/quality.yaml

@@ -6,29 +6,15 @@ jobs:
     if: github.event_name == 'pull_request'
     name: Quality (clippy, rustfmt)
     runs-on: ubuntu-latest
-    continue-on-error: ${{ matrix.experimental }}
     strategy:
-      fail-fast: false
       matrix:
         rust:
           - stable
         target:
           - x86_64-unknown-linux-gnu
-          - aarch64-unknown-linux-gnu
-        experimental: [false]
-        include:
-          - rust: beta
-            target: x86_64-unknown-linux-gnu
-            experimental: true
-          - rust: beta
-            target: aarch64-unknown-linux-gnu
-            experimental: true
     steps:
       - name: Code checkout
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-
+        uses: actions/checkout@v2
       - name: Install Rust toolchain (${{ matrix.rust }})
         uses: actions-rs/toolchain@v1
         with:
@@ -37,68 +23,29 @@ jobs:
           override: true
           components: rustfmt, clippy
 
-      - name: Debug Check (default features)
-        if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
-        run: |
-          set -e
-          commits=$(git rev-list origin/${{ github.base_ref }}..${{ github.sha }})
-          for commit in $commits; do git checkout $commit; cargo check --tests --all --target=${{ matrix.target }}; done
-          git checkout ${{ github.sha }}
-
       - name: Formatting (rustfmt)
         run: cargo fmt -- --check
 
+      - name: Clippy (all features,kvm)
+        run: cargo clippy --all --all-targets --no-default-features --tests --features "common,kvm" -- -D warnings
+
+      - name: Clippy (all features,mshv)
+        run: cargo clippy --all --all-targets --no-default-features --tests --features "common,mshv" -- -D warnings
+
+      - name: Clippy (acpi,kvm)
+        run: cargo clippy --all --all-targets --no-default-features --tests --features "acpi,kvm" -- -D warnings
+
+      - name: Clippy (acpi,kvm,tdx)
+        run: cargo clippy --all --all-targets --no-default-features --tests --features "acpi,kvm,tdx" -- -D warnings
+
       - name: Clippy (kvm)
-        uses: actions-rs/cargo@v1
-        with:
-          use-cross: ${{ matrix.target != 'x86_64-unknown-linux-gnu' }}
-          command: clippy
-          args: --locked --all --all-targets --no-default-features --tests --features "kvm" -- -D warnings
+        run: cargo clippy --all --all-targets --no-default-features --tests --features "kvm" -- -D warnings
 
-      - name: Clippy (default features)
-        uses: actions-rs/cargo@v1
-        with:
-          use-cross: ${{ matrix.target != 'x86_64-unknown-linux-gnu' }}
-          command: clippy
-          args: --locked --all --all-targets --tests -- -D warnings
-
-      - name: Clippy (default features + guest_debug)
-        uses: actions-rs/cargo@v1
-        with:
-          use-cross: ${{ matrix.target != 'x86_64-unknown-linux-gnu' }}
-          command: clippy
-          args: --locked --all --all-targets --tests --features "guest_debug" -- -D warnings
-
-      - name: Clippy (default features + tracing)
-        uses: actions-rs/cargo@v1
-        with:
-          use-cross: ${{ matrix.target != 'x86_64-unknown-linux-gnu' }}
-          command: clippy
-          args: --locked --all --all-targets --tests --features "tracing" -- -D warnings
+      - name: Clippy (acpi,mshv)
+        run: cargo clippy --all --all-targets --no-default-features --tests --features "acpi,mshv" -- -D warnings
 
       - name: Clippy (mshv)
-        if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
-        uses: actions-rs/cargo@v1
-        with:
-          use-cross: ${{ matrix.target != 'x86_64-unknown-linux-gnu' }}
-          command: clippy
-          args: --locked --all --all-targets --no-default-features --tests --features "mshv" -- -D warnings
+        run: cargo clippy --all --all-targets --no-default-features --tests --features "mshv" -- -D warnings
 
-      - name: Clippy (mshv + kvm)
-        if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
-        uses: actions-rs/cargo@v1
-        with:
-          use-cross: ${{ matrix.target != 'x86_64-unknown-linux-gnu' }}
-          command: clippy
-          args: --locked --all --all-targets --no-default-features --tests --features "mshv,kvm" -- -D warnings
-
-      - name: Clippy (kvm + tdx)
-        if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
-        uses: actions-rs/cargo@v1
-        with:
-          use-cross: ${{ matrix.target != 'x86_64-unknown-linux-gnu' }}
-          command: clippy
-          args: --locked --all --all-targets --no-default-features --tests --features "tdx,kvm" -- -D warnings
-
-      - name: Check build did not modify any files
-        run: test -z "$(git status --porcelain)"
+      - name: Clippy (integration tests)
+        run: cargo clippy --all --all-targets --tests --features "integration_tests" -- -D warnings

.github/workflows/release.yaml

@@ -1,48 +1,31 @@
 name: Cloud Hypervisor Release
-on: [pull_request, create]
+on: [create]
 
 jobs:
   release:
-    if: (github.event_name == 'create' && github.event.ref_type == 'tag') || github.event_name == 'pull_request'
+    if: github.event_name == 'create' && github.event.ref_type == 'tag'
     name: Release
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
         uses: actions/checkout@v2
-      - name: Install musl-gcc
-        run: sudo apt install -y musl-tools
-      - name: Create release directory
-        run: rsync -rv --exclude=.git . ../cloud-hypervisor-${{ github.event.ref }}
       - name: Install Rust toolchain (x86_64-unknown-linux-gnu)
         uses: actions-rs/toolchain@v1
         with:
-          toolchain: "1.62"
-          target: x86_64-unknown-linux-gnu
+            toolchain: stable
+            target: x86_64-unknown-linux-gnu
       - name: Install Rust toolchain (x86_64-unknown-linux-musl)
         uses: actions-rs/toolchain@v1
         with:
-          toolchain: "1.62"
-          target: x86_64-unknown-linux-musl
+            toolchain: stable
+            target: x86_64-unknown-linux-musl
       - name: Build
-        uses: actions-rs/cargo@v1
-        with:
-            toolchain: "1.62"
-            command: build
-            args: --all --release --target=x86_64-unknown-linux-gnu
+        run: cargo build --all --release --target=x86_64-unknown-linux-gnu
       - name: Static Build
-        uses: actions-rs/cargo@v1
-        with:
-            toolchain: "1.62"
-            command: build
-            args: --all --release --target=x86_64-unknown-linux-musl
-      - name: Install Rust toolchain (aarch64-unknown-linux-musl)
-        uses: actions-rs/toolchain@v1
-        with:
-          toolchain: "1.62"
-          target: aarch64-unknown-linux-musl
-          override: true
+        run: cargo build --all --release --target=x86_64-unknown-linux-musl
+      - name: Strip cloud-hypervisor binaries
+        run: strip target/*/release/cloud-hypervisor
       - name: Create Release
-        if: github.event_name == 'create' && github.event.ref_type == 'tag'
         id: create_release
         uses: actions/create-release@v1
         env:
@@ -53,7 +36,6 @@ jobs:
           draft: true
           prerelease: true
       - name: Upload cloud-hypervisor
-        if: github.event_name == 'create' && github.event.ref_type == 'tag'
         id: upload-release-cloud-hypervisor
         uses: actions/upload-release-asset@v1
         env:
@@ -64,7 +46,6 @@ jobs:
           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:
@@ -75,7 +56,6 @@ jobs:
           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:
@@ -85,67 +65,3 @@ jobs:
           asset_path: target/x86_64-unknown-linux-gnu/release/ch-remote
           asset_name: ch-remote
           asset_content_type: application/octet-stream
-      - name: Upload static-ch-remote
-        if: github.event_name == 'create' && github.event.ref_type == 'tag'
-        id: upload-release-static-ch-remote
-        uses: actions/upload-release-asset@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          upload_url: ${{ steps.create_release.outputs.upload_url }}
-          asset_path: target/x86_64-unknown-linux-musl/release/ch-remote
-          asset_name: ch-remote-static
-          asset_content_type: application/octet-stream
-      - name: Clean build tree ahead of cross build
-        uses: actions-rs/cargo@v1
-        with:
-          command: clean
-      - name: Static Build (AArch64)
-        uses: actions-rs/cargo@v1
-        with:
-          use-cross: true
-          command: build
-          args: --all --release --target=aarch64-unknown-linux-musl
-      - name: Upload static AArch64 cloud-hypervisor
-        if: github.event_name == 'create' && github.event.ref_type == 'tag'
-        id: upload-release-static-aarch64-cloud-hypervisor
-        uses: actions/upload-release-asset@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          upload_url: ${{ steps.create_release.outputs.upload_url }}
-          asset_path: target/aarch64-unknown-linux-musl/release/cloud-hypervisor
-          asset_name: cloud-hypervisor-static-aarch64
-          asset_content_type: application/octet-stream
-      - name: Upload static AArch64 ch-remote
-        if: github.event_name == 'create' && github.event.ref_type == 'tag'
-        id: upload-release-static-aarch64-ch-remote
-        uses: actions/upload-release-asset@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          upload_url: ${{ steps.create_release.outputs.upload_url }}
-          asset_path: target/aarch64-unknown-linux-musl/release/ch-remote
-          asset_name: ch-remote-static-aarch64
-          asset_content_type: application/octet-stream
-      - name: Vendor
-        working-directory: ../cloud-hypervisor-${{ github.event.ref }}
-        run: |
-          mkdir ../vendor-cargo-home
-          export CARGO_HOME=$(realpath ../vendor-cargo-home)
-          mkdir .cargo
-          cargo vendor > .cargo/config.toml
-      - name: Create vendored source archive
-        working-directory: ../
-        run: tar cJf cloud-hypervisor-${{ github.event.ref }}.tar.xz cloud-hypervisor-${{ github.event.ref }}
-      - name: Upload cloud-hypervisor vendored source archive
-        if: github.event_name == 'create' && github.event.ref_type == 'tag'
-        id: upload-release-cloud-hypervisor-vendored-sources
-        uses: actions/upload-release-asset@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        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

.gitignore

@@ -1,7 +1,5 @@
 /build
-/.cargo
 /target
 **/*.rs.bk
 **/Cargo.lock
 **/rusty-tags.vi
-/rpm/SOURCES

.rustfmt.toml

@@ -1 +1 @@
-edition = "2021"
+edition = "2018"

CODEOWNERS

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

CONTRIBUTING.md

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

Cargo.toml

@@ -1,78 +1,72 @@
 [package]
 name = "cloud-hypervisor"
-version = "28.3.0"
+version = "0.14.1"
 authors = ["The Cloud Hypervisor Authors"]
-edition = "2021"
+edition = "2018"
 default-run = "cloud-hypervisor"
 build = "build.rs"
 license = "LICENSE-APACHE & LICENSE-BSD-3-Clause"
 description = "Open source Virtual Machine Monitor (VMM) that runs on top of KVM"
 homepage = "https://github.com/cloud-hypervisor/cloud-hypervisor"
-# Minimum buildable version:
-# Keep in sync with version in .github/workflows/build.yaml
-# Policy on MSRV (see #4318):
-# Can only be bumped by:
-# a.) A dependency requires it, 
-# b.) If we want to use a new feature and that MSRV is at least 6 months old,
-# c.) There is a security issue that is addressed by the toolchain update.
-rust-version = "1.62"
 
 [profile.release]
 lto = true
-codegen-units = 1
-opt-level = "s"
-strip = true
 
 [dependencies]
-anyhow = "1.0.66"
+anyhow = "1.0.39"
 api_client = { path = "api_client" }
-clap = { version = "4.0.29", features = ["wrap_help","cargo","string"] }
+clap = { version = "2.33.3", features = ["wrap_help"] }
 epoll = "4.3.1"
 event_monitor = { path = "event_monitor" }
 hypervisor = { path = "hypervisor" }
-libc = "0.2.138"
-log = { version = "0.4.17", features = ["std"] }
+libc = "0.2.91"
+log = { version = "0.4.14", features = ["std"] }
 option_parser = { path = "option_parser" }
-seccompiler = "0.3.0"
-serde_json = "1.0.89"
-signal-hook = "0.3.14"
-thiserror = "1.0.37"
-tpm = { path = "tpm"}
-tracer = { path = "tracer" }
+seccomp = { git = "https://github.com/firecracker-microvm/firecracker", tag = "v0.22.0" }
+serde_json = "1.0.64"
+signal-hook = "0.3.7"
+thiserror = "1.0.24"
 vmm = { path = "vmm" }
-vmm-sys-util = "0.11.0"
-vm-memory = "0.10.0"
+vmm-sys-util = "0.8.0"
+vm-memory = "0.5.0"
 
 [build-dependencies]
-clap = { version = "4.0.29", features = ["cargo"] }
+clap = { version = "2.33.3", features = ["wrap_help"] }
 
 # List of patched crates
 [patch.crates-io]
-kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.6.0-tdx" }
-kvm-ioctls = { git = "https://github.com/rust-vmm/kvm-ioctls", branch = "main" }
-versionize_derive = { git = "https://github.com/cloud-hypervisor/versionize_derive", branch = "ch" }
+kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.4.0", features = ["with-serde", "fam-wrappers"] }
 
 [dev-dependencies]
-dirs = "4.0.0"
+credibility = "0.1.3"
+dirs = "3.0.1"
+lazy_static= "1.4.0"
 net_util = { path = "net_util" }
-once_cell = "1.16.0"
-serde_json = "1.0.89"
+serde_json = "1.0.64"
 test_infra = { path = "test_infra" }
 wait-timeout = "0.2.0"
 
 [features]
-default = ["kvm"]
-guest_debug = ["vmm/guest_debug"]
+default = ["acpi", "cmos", "io_uring", "kvm"]
+# Common features for all hypervisors
+common = ["acpi", "cmos", "fwdebug", "io_uring"]
+acpi = ["vmm/acpi"]
+cmos = ["vmm/cmos"]
+fwdebug = ["vmm/fwdebug"]
 kvm = ["vmm/kvm"]
 mshv = ["vmm/mshv"]
+io_uring = ["vmm/io_uring"]
 tdx = ["vmm/tdx"]
-tracing = ["vmm/tracing", "tracer/tracing"]
+
+# Integration tests require a special environment to run in
+integration_tests = []
 
 [workspace]
 members = [
     "acpi_tables",
     "api_client",
     "arch",
+    "arch_gen",
     "block_util",
     "devices",
     "event_monitor",
@@ -81,14 +75,8 @@ members = [
     "net_util",
     "option_parser",
     "pci",
-    "performance-metrics",
     "qcow",
-    "rate_limiter",
-    "serial_buffer",
-    "test_infra",
-    "tracer",
-    "vfio_user",
-    "vhdx",
+    "vhost_user_backend",
     "vhost_user_block",
     "vhost_user_net",
     "virtio-devices",
@@ -98,3 +86,4 @@ members = [
     "vm-migration",
     "vm-virtio"
 ]
+exclude = ["test_infra"]

Jenkinsfile

@@ -1,348 +1,247 @@
-def runWorkers = true
-pipeline {
-    agent none
-    stages {
-        stage('Early checks') {
-            agent { node { label 'built-in' } }
-            stages {
-                stage('Checkout') {
-                    steps {
-                        checkout scm
-                    }
-                }
-                stage('Check for documentation only changes') {
-                    when {
-                        expression {
-                            return docsFileOnly()
-                        }
-                    }
-                    steps {
-                        script {
-                            runWorkers = false
-                            echo 'Documentation only changes, no need to run the CI'
-                        }
-                    }
-                }
-                stage('Check for fuzzer files only changes') {
-                    when {
-                        expression {
-                            return fuzzFileOnly()
-                        }
-                    }
-                    steps {
-                        script {
-                            runWorkers = false
-                            echo 'Fuzzer cargo files only changes, no need to run the CI'
-                        }
-                    }
-                }
-                stage('Check for RFC/WIP builds') {
-                    when {
-                        changeRequest comparator: 'REGEXP', title: '.*(rfc|RFC|wip|WIP).*'
-                        beforeAgent true
-                    }
-                    steps {
-                        error('Failing as this is marked as a WIP or RFC PR.')
-                    }
-                }
-                stage('Cancel older builds') {
-                    when { not { branch 'main' } }
-                    steps {
-                        cancelPreviousBuilds()
-                    }
-                }
-            }
-        }
-        stage('Build') {
-            parallel {
-                stage('Worker build') {
-                    agent { node { label 'jammy' } }
-                    when {
-                        beforeAgent true
-                        expression {
-                            return runWorkers
-                        }
-                    }
-                    stages {
-                        stage('Checkout') {
-                            steps {
-                                checkout scm
-                            }
-                        }
-                        stage('Prepare environment') {
-                            steps {
-                                sh 'scripts/prepare_vdpa.sh'
-                            }
-                        }
-                        stage('Run OpenAPI tests') {
-                            steps {
-                                sh 'scripts/run_openapi_tests.sh'
-                            }
-                        }
-                        stage('Run unit tests') {
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --unit'
-                            }
-                        }
-                        stage('Run integration tests') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration'
-                            }
-                        }
-                        stage('Run live-migration integration tests') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration-live-migration'
-                            }
-                        }
-                        stage('Run unit tests for musl') {
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --unit --libc musl'
-                            }
-                        }
-                        stage('Run integration tests for musl') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration --libc musl'
-                            }
-                        }
-                        stage('Run live-migration integration tests for musl') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration-live-migration --libc musl'
-                            }
-                        }
-                    }
-                }
-                stage('AArch64 worker build') {
-                    agent { node { label 'bionic-arm64' } }
-                    when {
-                        beforeAgent true
-                        expression {
-                            return runWorkers
-                        }
-                    }
-                    environment {
-                            AZURE_CONNECTION_STRING = credentials('46b4e7d6-315f-4cc1-8333-b58780863b9b')
-                    }
-                    stages {
-                        stage('Checkout') {
-                            steps {
-                                checkout scm
-                            }
-                        }
-                        stage('Run unit tests') {
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --unit --libc musl'
-                            }
-                        }
-                        stage('Run integration tests') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration --libc musl'
-                            }
-                        }
-                        stage('Install azure-cli') {
-                            steps {
-                                installAzureCli('bionic', 'arm64')
-                            }
-                        }
-                        stage('Download Windows image') {
-                            steps {
-                                sh '''#!/bin/bash -x
-                                    IMG_BASENAME=windows-11-iot-enterprise-aarch64.raw
-                                    IMG_PATH=$HOME/workloads/$IMG_BASENAME
-                                    IMG_GZ_PATH=$HOME/workloads/$IMG_BASENAME.gz
-                                    IMG_GZ_BLOB_NAME=windows-11-iot-enterprise-aarch64-9-min.raw.gz
-                                    cp "scripts/$IMG_BASENAME.sha1" "$HOME/workloads/"
-                                    pushd "$HOME/workloads"
-                                    if sha1sum "$IMG_BASENAME.sha1" --check; then
-                                        exit
-                                    fi
-                                    popd
-                                    mkdir -p "$HOME/workloads"
-                                    az storage blob download \
-                                        --container-name private-images \
-                                        --file "$IMG_GZ_PATH" \
-                                        --name "$IMG_GZ_BLOB_NAME" \
-                                        --connection-string "$AZURE_CONNECTION_STRING"
-                                    gzip -d $IMG_GZ_PATH
-                                '''
-                            }
-                        }
-                        stage('Run Windows guest integration tests') {
-                            options {
-                                timeout(time: 1, unit: 'HOURS')
-                            }
-                            steps {
-                                sh 'scripts/dev_cli.sh tests --integration-windows --libc musl'
-                            }
-                        }
-                    }
-                    post {
-                        always {
-                            sh "sudo chown -R jenkins.jenkins ${WORKSPACE}"
-                            deleteDir()
-                        }
-                    }
-                }
-                stage('Worker build - Windows guest') {
-                    agent { node { label 'jammy' } }
-                    when {
-                        beforeAgent true
-                        expression {
-                            return runWorkers
-                        }
-                    }
-                    environment {
-                            AZURE_CONNECTION_STRING = credentials('46b4e7d6-315f-4cc1-8333-b58780863b9b')
-                    }
-                    stages {
-                        stage('Checkout') {
-                            steps {
-                                checkout scm
-                            }
-                        }
-                        stage('Install azure-cli') {
-                            steps {
-                                installAzureCli('jammy', 'amd64')
-                            }
-                        }
-                        stage('Download assets') {
-                            steps {
-                                sh "mkdir ${env.HOME}/workloads"
-                                sh 'az storage blob download --container-name private-images --file "$HOME/workloads/windows-server-2019.raw" --name windows-server-2019.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'
-                            }
-                        }
-                    }
-                }
-            }
-        }
-    }
-    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')
-                }
-            }
-        }
-    }
+pipeline{
+	agent none
+	stages {
+		stage ('Early checks') {
+			agent { node { label 'master' } }
+			stages {
+				stage ('Check for RFC/WIP builds') {
+					when {
+  						changeRequest comparator: 'REGEXP', title: '.*(rfc|RFC|wip|WIP).*'
+  						beforeAgent true
+					}
+					steps {
+						error("Failing as this is marked as a WIP or RFC PR.")
+					}
+				}
+				stage ('Cancel older builds') {
+					when { not { branch 'master' } }
+					steps {
+						cancelPreviousBuilds()
+					}
+				}
+			}
+		}
+		stage ('Build') {
+            		parallel {
+				stage ('Worker build') {
+					agent { node { label 'groovy' } }
+					stages {
+						stage ('Checkout') {
+							steps {
+								checkout scm
+							}
+						}
+						stage ('Run OpenAPI tests') {
+							steps {
+								sh "scripts/run_openapi_tests.sh"
+							}
+						}
+						stage ('Run unit tests') {
+							steps {
+								sh "scripts/dev_cli.sh tests --unit"
+							}
+						}
+						stage ('Run integration tests') {
+							options {
+								timeout(time: 1, unit: 'HOURS')
+							}
+							steps {
+								sh "scripts/dev_cli.sh tests --integration"
+							}
+						}
+					}
+				}
+				stage ('AArch64 worker build') {
+					agent { node { label 'bionic-arm64' } }
+					stages {
+						stage ('Checkout') {
+							steps {
+								checkout scm
+							}
+						}
+						stage ('Run unit tests') {
+							steps {
+								sh "scripts/dev_cli.sh tests --unit"
+							}
+						}
+						stage ('Run integration tests') {
+							options {
+								timeout(time: 1, unit: 'HOURS')
+							}
+							steps {
+								sh "scripts/dev_cli.sh tests --integration"
+							}
+						}
+					}
+					post {
+						always {
+							sh "sudo chown -R jenkins.jenkins ${WORKSPACE}"
+							deleteDir()
+						}
+					}
+				}
+				stage ('Worker build (musl)') {
+					agent { node { label 'groovy' } }
+					stages {
+						stage ('Checkout') {
+							steps {
+								checkout scm
+							}
+						}
+						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 "scripts/dev_cli.sh tests --integration --libc musl"
+							}
+						}
+					}
+				}
+				stage ('Worker build SGX') {
+					agent { node { label 'bionic-sgx' } }
+					when { branch 'master' }
+					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 'bionic-vfio' } }
+					when { branch 'master' }
+					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()
+						}
+					}
+				}
+				stage ('Worker build - Windows guest') {
+					agent { node { label 'groovy-win' } }
+					stages {
+						stage ('Checkout') {
+							steps {
+								checkout scm
+							}
+						}
+						stage ('Download assets') {
+							steps {
+								sh "mkdir ${env.HOME}/workloads"
+								azureDownload(storageCredentialId: 'ch-image-store',
+											  containerName: 'private-images',
+											  includeFilesPattern: 'OVMF-4b47d0c6c8.fd',
+											  downloadType: 'container',
+											  downloadDirLoc: "${env.HOME}/workloads")
+								azureDownload(storageCredentialId: 'ch-image-store',
+											  containerName: 'private-images',
+											  includeFilesPattern: 'windows-server-2019.raw',
+											  downloadType: 'container',
+											  downloadDirLoc: "${env.HOME}/workloads")
+							}
+						}
+						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"
+							}
+						}
+					}
+				}
+			}
+		}
+	}
+	post {
+		regression {
+			script {
+				if (env.BRANCH_NAME == 'master') {
+					slackSend (color: '#ff0000', message: '"master" branch build is now failing')
+				}
+			}
+		}
+		fixed {
+			script {
+				if (env.BRANCH_NAME == 'master') {
+					slackSend (color: '#00ff00', message: '"master" branch build is now fixed')
+				}
+			}
+		}
+	}
 }
 
 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)
+	// 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/ ${distro} main\" | sudo tee /etc/apt/sources.list.d/azure-cli.list"
-    sh 'sudo apt update'
-    sh 'sudo apt install -y azure-cli'
-}
-
-def boolean docsFileOnly() {
-    if (env.CHANGE_TARGET == null) {
-        return false
-    }
-
-    return sh(
-        returnStatus: true,
-        script: "git diff --name-only origin/${env.CHANGE_TARGET}... | grep -v '\\.md'"
-    ) != 0
-}
-
-def boolean fuzzFileOnly() {
-    if (env.CHANGE_TARGET == null) {
-        return false
-    }
-
-    return sh(
-        returnStatus: true,
-        script: "git diff --name-only origin/${env.CHANGE_TARGET}... | grep -v -E 'fuzz/'"
-    ) != 0
+		// 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()
+			}
+		}
 }

MAINTAINERS.md

@@ -1,7 +1,6 @@
 # Maintainers
 
-- Sebastien Boeuf - @sboeuf
-- Robert Bradford - @rbradford
-- Samuel Ortiz - @sameo
-- Wei Liu - @liuw
-- Michael Zhao - @michael2012z
+- Sebastien Boeuf <sebastien.boeuf@intel.com> @sboeuf
+- Robert Bradford <robert.bradford@intel.com> @rbradford
+- Samuel Ortiz <sameo@linux.intel.com> @sameo
+- Chao P Peng <chao.p.peng@linux.intel.com> @chao-p

README.md

@@ -1,52 +1,42 @@
+[![Build Status](https://travis-ci.com/cloud-hypervisor/cloud-hypervisor.svg?branch=master)](https://travis-ci.com/cloud-hypervisor/cloud-hypervisor)
+
 - [1. What is Cloud Hypervisor?](#1-what-is-cloud-hypervisor)
   - [Objectives](#objectives)
     - [High Level](#high-level)
     - [Architectures](#architectures)
     - [Guest OS](#guest-os)
 - [2. Getting Started](#2-getting-started)
-  - [Host OS](#host-os)
-  - [Use Pre-built Binaries](#use-pre-built-binaries)
-  - [Packages](#packages)
-  - [Building from Source](#building-from-source)
-  - [Booting Linux](#booting-linux)
-    - [Firmware Booting](#firmware-booting)
-    - [Custom Kernel and Disk Image](#custom-kernel-and-disk-image)
-      - [Building your Kernel](#building-your-kernel)
+  - [Clone and build](#clone-and-build)
+    - [Containerized builds and tests](#containerized-builds-and-tests)
+  - [Run](#run)
+    - [Cloud image](#cloud-image)
+    - [Custom kernel and disk image](#custom-kernel-and-disk-image)
+      - [Building your kernel](#building-your-kernel)
       - [Disk image](#disk-image)
       - [Booting the guest VM](#booting-the-guest-vm)
 - [3. Status](#3-status)
   - [Hot Plug](#hot-plug)
   - [Device Model](#device-model)
-  - [Roadmap](#roadmap)
-- [4. Relationship with _Rust VMM_ Project](#4-relationship-with-rust-vmm-project)
-  - [Differences with Firecracker and crosvm](#differences-with-firecracker-and-crosvm)
+  - [TODO](#todo)
+- [4. `rust-vmm` project dependency](#4-rust-vmm-project-dependency)
+  - [Firecracker and crosvm](#firecracker-and-crosvm)
 - [5. Community](#5-community)
   - [Contribute](#contribute)
-  - [Slack](#slack)
-  - [Mailing list](#mailing-list)
-  - [Security issues](#security-issues)
+  - [Join us](#join-us)
 
 # 1. What is Cloud Hypervisor?
 
-Cloud Hypervisor is an open source Virtual Machine Monitor (VMM) that runs on
-top of the [KVM](https://www.kernel.org/doc/Documentation/virtual/kvm/api.txt)
-hypervisor and the Microsoft Hypervisor (MSHV).
+Cloud Hypervisor is an open source Virtual Machine Monitor (VMM) that runs on top of [KVM](https://www.kernel.org/doc/Documentation/virtual/kvm/api.txt).
+The project focuses on exclusively running modern, cloud workloads, on top of a limited set of hardware architectures and platforms.
+Cloud workloads refers to those that are usually run by customers inside a cloud provider. For our purposes this means modern operating systems with most I/O handled by paravirtualised devices (i.e. virtio), no requirement for legacy devices, and 64-bit CPUs.
 
-The project focuses on running modern, _Cloud Workloads_, on specific, common,
-hardware architectures. In this case _Cloud Workloads_ refers to those that are
-run by customers inside a Cloud Service Provider. This means modern operating
-systems with most I/O handled by
-paravirtualised devices (e.g. _virtio_), no requirement for legacy devices, and
-64-bit CPUs.
-
-Cloud Hypervisor is implemented in [Rust](https://www.rust-lang.org/) and is
-based on the [Rust VMM](https://github.com/rust-vmm) crates.
+Cloud Hypervisor is implemented in [Rust](https://www.rust-lang.org/) and is based on the [rust-vmm](https://github.com/rust-vmm) crates.
 
 ## Objectives
 
 ### High Level
 
-- Runs on KVM or MSHV
+- KVM based
 - Minimal emulation
 - Low latency
 - Low memory footprint
@@ -59,168 +49,185 @@ based on the [Rust VMM](https://github.com/rust-vmm) crates.
 
 ### Architectures
 
-Cloud Hypervisor supports the `x86-64` and `AArch64` architectures. There are
-minor differences in functionality between the two architectures
-(see [#1125](https://github.com/cloud-hypervisor/cloud-hypervisor/issues/1125)).
+Cloud Hypervisor supports the `x86-64` and `AArch64` architectures. There are some small differences in functionality between the two architectures (see [#1125](https://github.com/cloud-hypervisor/cloud-hypervisor/issues/1125)).
 
 ### Guest OS
 
-Cloud Hypervisor supports `64-bit Linux` and Windows 10/Windows Server 2019.
+Cloud Hypervisor supports `64-bit Linux` with support for _modern_ 64-bit Windows guests currently under development.
 
 # 2. Getting Started
 
-The following sections describe how to build and run Cloud Hypervisor on the
-`x86-64` platform. For getting started on the `AArch64` platform, please refer
-to the
-[AArch64 documentation](docs/arm64.md).
-
-## Host OS
-
-For required KVM functionality the minimum host kernel version is 4.11.  For
-adequate performance the minimum recommended host kernel version is 5.6. The
-majority of the CI currently tests with kernel version 5.15.
-
-## Use Pre-built Binaries
-
-The recommended approach to getting started with Cloud Hypervisor is by using a
-pre-built binary. Binaries are available for the [latest
-release](https://github.com/cloud-hypervisor/cloud-hypervisor/releases/latest).
-Use `cloud-hypervisor-static` for `x86-64` or `cloud-hypervisor-static-aarch64`
-for `AArch64` platform.
-
-## Packages
-
-For convenience, packages are also available targeting some popular Linux
-distributions. This is thanks to the [Open Build
-Service](https://build.opensuse.org). The [OBS
-README](https://github.com/cloud-hypervisor/obs-packaging) explains how to
-enable the repository in a supported Linux distribution and install Cloud Hypervisor
-and accompanying packages. Please report any packaging issues in the
-[obs-packaging](https://github.com/cloud-hypervisor/obs-packaging) repository.
-
-## Building from Source
-
-Please see the [instructions for building from source](docs/building.md) if you
-do not wish to use the pre-built binaries.
-
-## Booting Linux
-
-The instructions below are for the `x86-64` platform. For `AArch64` please see
-the [AArch64 specific documentation](docs/arm64.md).
-
-Cloud Hypervisor supports direct kernel boot (if the kernel is built with PVH
-support) or booting via a firmware (either [Rust Hypervisor
-Firmware](https://github.com/cloud-hypervisor/rust-hypervisor-firmware) or an
-edk2 UEFI firmware called `CLOUDHV`.)
-
-Binary builds of the firmware files are available for the latest release of
-[Rust Hyperivor
-Firmware](https://github.com/cloud-hypervisor/rust-hypervisor-firmware/releases/latest)
-and [our edk2
-repository](https://github.com/cloud-hypervisor/edk2/releases/latest)
-
-The choice of firmware depends on your guest OS choice; some experimentation
-may be required.
-
-### Firmware Booting
-
-Cloud Hypervisor supports booting disk images containing all needed components
-to run cloud workloads, a.k.a. cloud images. 
-
-The following sample commands will download an Ubuntu Cloud image, converting
-it into a format that Cloud Hypervisor can use and a firmware to boot the image
-with.
+We create a folder to build and run `cloud-hypervisor` at `$HOME/cloud-hypervisor`
 
 ```shell
+$ export CLOUDH=$HOME/cloud-hypervisor
+$ mkdir $CLOUDH
+```
+
+## Install prerequisites
+
+You need to install some prerequisite packages in order to build and test Cloud Hypervisor.
+Here, all the steps are based on Ubuntu, for other Linux distributions please replace the
+package manager and package name.
+
+```shell
+# Install git
+$ sudo apt install git
+# Install rust tool chain
+$ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
+# Install build-essential
+$ sudo apt install build-essential
+# If you want to build statically linked binary please add musl target
+$ rustup target add x86_64-unknown-linux-musl
+```
+
+## Clone and build
+
+First you need to clone and build the cloud-hypervisor repo:
+
+```shell
+$ pushd $CLOUDH
+$ git clone https://github.com/cloud-hypervisor/cloud-hypervisor.git
+$ cd cloud-hypervisor
+$ cargo build --release
+
+# We need to give the cloud-hypervisor binary the NET_ADMIN capabilities for it to set TAP interfaces up on the host.
+$ sudo setcap cap_net_admin+ep ./target/release/cloud-hypervisor
+
+# If you want to build statically linked binary
+$ cargo build --release --target=x86_64-unknown-linux-musl --all
+$ popd
+```
+
+This will build a `cloud-hypervisor` binary under `$CLOUDH/cloud-hypervisor/target/release/cloud-hypervisor`.
+
+### Containerized builds and tests
+
+If you want to build and test Cloud Hypervisor without having to install all the
+required dependencies (The rust toolchain, cargo tools, etc), you can also use
+Cloud Hypervisor's development script: `dev_cli.sh`. Please note that upon its
+first invocation, this script will pull a fairly large container image.
+
+For example, to build the Cloud Hypervisor release binary:
+
+```shell
+$ pushd $CLOUDH
+$ cd cloud-hypervisor
+$ ./scripts/dev_cli.sh build --release
+```
+
+With `dev_cli.sh`, one can also run the Cloud Hypervisor CI locally. This can be
+very convenient for debugging CI errors without having to fully rely on the
+Cloud Hypervisor CI infrastructure.
+
+For example, to run the Cloud Hypervisor unit tests:
+
+```shell
+$ ./scripts/dev_cli.sh tests --unit
+```
+
+Run the `./scripts/dev_cli.sh --help` command to view all the supported
+development script commands and their related options.
+
+## Run
+
+You can run a guest VM by either using an existing cloud image or booting into your own kernel and disk image.
+
+### Cloud image
+
+Cloud Hypervisor supports booting disk images containing all needed
+components to run cloud workloads, a.k.a. cloud images. To do that we rely on
+the [Rust Hypervisor
+Firmware](https://github.com/cloud-hypervisor/rust-hypervisor-firmware) project to provide
+an ELF
+formatted KVM firmware for `cloud-hypervisor` to directly boot into.
+
+We need to get the latest `rust-hypervisor-firmware` release and also a working cloud image. Here we will use a Ubuntu image:
+
+```shell
+$ pushd $CLOUDH
 $ wget https://cloud-images.ubuntu.com/focal/current/focal-server-cloudimg-amd64.img
 $ qemu-img convert -p -f qcow2 -O raw focal-server-cloudimg-amd64.img focal-server-cloudimg-amd64.raw
-$ wget https://github.com/cloud-hypervisor/rust-hypervisor-firmware/releases/download/0.4.2/hypervisor-fw
+$ wget https://github.com/cloud-hypervisor/rust-hypervisor-firmware/releases/download/0.3.0/hypervisor-fw
+$ popd
 ```
 
-The Ubuntu cloud images do not ship with a default password so it necessary to
-use a `cloud-init` disk image to customise the image on the first boot. A basic
-`cloud-init` image is generated by this [script](scripts/create-cloud-init.sh).
-This seeds the image with a default username/password of `cloud/cloud123`. It
-is only necessary to add this disk image on the first boot.
-
 ```shell
-$ sudo setcap cap_net_admin+ep ./cloud-hypervisor
-$ ./create-cloud-init.sh
-$ ./cloud-hypervisor \
+$ pushd $CLOUDH
+$ sudo setcap cap_net_admin+ep ./cloud-hypervisor/target/release/cloud-hypervisor
+$ ./cloud-hypervisor/target/release/cloud-hypervisor \
 	--kernel ./hypervisor-fw \
-	--disk path=focal-server-cloudimg-amd64.raw path=/tmp/ubuntu-cloudinit.img \
-	--cpus boot=4 \
-	--memory size=1024M \
-	--net "tap=,mac=,ip=,mask="
-```
-
-If access to the firmware messages or interaction with the boot loader (e.g.
-GRUB) is required then it necessary to switch to the serial console instead of
-`virtio-console`.
-
-```shell
-$ ./cloud-hypervisor \
-	--kernel ./hypervisor-fw \
-	--disk path=focal-server-cloudimg-amd64.raw path=/tmp/ubuntu-cloudinit.img \
+	--disk path=focal-server-cloudimg-amd64.raw \
 	--cpus boot=4 \
 	--memory size=1024M \
 	--net "tap=,mac=,ip=,mask=" \
-	--serial tty \
-	--console off
+	--rng
+$ popd
 ```
 
-### Custom Kernel and Disk Image
+Multiple arguments can be given to the `--disk` parameter.
 
-#### Building your Kernel
+### Custom kernel and disk image
 
-Cloud Hypervisor also supports direct kernel boot into a `vmlinux` ELF kernel (compiled with PVH support). In order to support development there is a custom branch; however provided the required options are enabled any recent kernel will suffice.
+#### Building your kernel
+
+Cloud Hypervisor also supports direct kernel boot into a `vmlinux` ELF kernel or `bzImage`. In order to support virtio-fs and virtio-iommu we have our own development branch. You are of course able to use your own kernel but these instructions will continue with the version that we develop and test against.
 
 To build the kernel:
 
 ```shell
+
 # Clone the Cloud Hypervisor Linux branch
-$ git clone --depth 1 https://github.com/cloud-hypervisor/linux.git -b ch-5.15.12 linux-cloud-hypervisor
+$ pushd $CLOUDH
+$ git clone --depth 1 https://github.com/cloud-hypervisor/linux.git -b virtio-fs-virtio-iommu-virtio-mem-5.6-rc4 linux-cloud-hypervisor
 $ pushd linux-cloud-hypervisor
+
 # Use the cloud-hypervisor kernel config to build your kernel
-$ wget https://raw.githubusercontent.com/cloud-hypervisor/cloud-hypervisor/main/resources/linux-config-x86_64
-$ cp linux-config-x86_64 .config
-$ KCFLAGS="-Wa,-mx86-used-note=no" make bzImage -j `nproc`
+$ cp $CLOUDH/cloud-hypervisor/resources/linux-config-x86_64 .config
+$ make bzImage -j `nproc`
 $ popd
 ```
 
-The `vmlinux` kernel image will then be located at
-`linux-cloud-hypervisor/arch/x86/boot/compressed/vmlinux.bin`.
+The `vmlinux` kernel image will then be located at `linux-cloud-hypervisor/arch/x86/boot/compressed/vmlinux.bin`.
 
 #### Disk image
 
-For the disk image the same Ubuntu image as before can be used. This contains
-an `ext4` root filesystem.
+For the disk image, we will use a Ubuntu cloud image that contains a root partition:
 
 ```shell
+$ pushd $CLOUDH
 $ wget https://cloud-images.ubuntu.com/focal/current/focal-server-cloudimg-amd64.img
 $ qemu-img convert -p -f qcow2 -O raw focal-server-cloudimg-amd64.img focal-server-cloudimg-amd64.raw
+$ popd
 ```
 
 #### Booting the guest VM
 
-These sample commands boot the disk image using the custom kernel whilst also
-supplying the desired kernel command line.
+Now we can directly boot into our custom kernel and make it use the Ubuntu root partition.
+If we want to have 4 vCPUs and 512 MBytes of memory:
 
 ```shell
-$ sudo setcap cap_net_admin+ep ./cloud-hypervisor
-$ ./create-cloud-init.sh
-$ ./cloud-hypervisor \
+$ pushd $CLOUDH
+$ sudo setcap cap_net_admin+ep ./cloud-hypervisor/target/release/cloud-hypervisor
+$ ./cloud-hypervisor/target/release/cloud-hypervisor \
 	--kernel ./linux-cloud-hypervisor/arch/x86/boot/compressed/vmlinux.bin \
-	--disk path=focal-server-cloudimg-amd64.raw path=/tmp/ubuntu-cloudinit.img \
+	--disk path=focal-server-cloudimg-amd64.raw \
 	--cmdline "console=hvc0 root=/dev/vda1 rw" \
 	--cpus boot=4 \
 	--memory size=1024M \
-	--net "tap=,mac=,ip=,mask="
+	--net "tap=,mac=,ip=,mask=" \
+	--rng
 ```
 
-If earlier kernel messages are required the serial console should be used instead of `virtio-console`.
+The above example use the `virtio-console` device as the guest console, and this
+device may not be enabled soon enough by the guest kernel to get early kernel
+debug messages.
 
-```./cloud-hypervisor \
+When in need for earlier debug messages, using the legacy serial device based
+console is preferred:
+
+```
+$ ./cloud-hypervisor/target/release/cloud-hypervisor \
 	--kernel ./linux-cloud-hypervisor/arch/x86/boot/compressed/vmlinux.bin \
 	--console off \
 	--serial tty \
@@ -228,119 +235,85 @@ If earlier kernel messages are required the serial console should be used instea
 	--cmdline "console=ttyS0 root=/dev/vda1 rw" \
 	--cpus boot=4 \
 	--memory size=1024M \
-	--net "tap=,mac=,ip=,mask="
+	--net "tap=,mac=,ip=,mask=" \
+	--rng
 ```
 
 # 3. Status
 
-Cloud Hypervisor is under active development. The following stability
-guarantees are currently made:
+Cloud Hypervisor is under active development. No API or feature stability is guaranteed.
 
-* The API (including command line options) will not be removed or changed in a
-  breaking way without a minimum of 2 major releases notice. Where possible
-  warnings will be given about the use of deprecated functionality and the
-  deprecations will be documented in the release notes.
+As of 2020-07-02, the following cloud images are supported:
 
-* Point releases will be made between individual releases where there are
-  substantial bug fixes or security issues that need to be fixed. These point
-  releases will only include bug fixes.
+- [Ubuntu Bionic](https://cloud-images.ubuntu.com/bionic/current/) (cloudimg)
+- [Ubuntu Focal](https://cloud-images.ubuntu.com/focal/current/) (cloudimg)
 
-Currently the following items are **not** guaranteed across updates:
-
-* Snapshot/restore is not supported across different versions
-* Live migration is not supported across different versions
-* The following features are considered experimental and may change
-  substantially between releases: TDX, vfio-user, vDPA.
-
-Further details can be found in the [release documentation](docs/releases.md).
-
-As of 2022-10-13, the following cloud images are supported:
-
-- [Ubuntu Bionic](https://cloud-images.ubuntu.com/bionic/current/) (bionic-server-cloudimg-amd64.img)
-- [Ubuntu Focal](https://cloud-images.ubuntu.com/focal/current/) (focal-server-cloudimg-amd64.img)
-- [Ubuntu Jammy](https://cloud-images.ubuntu.com/jammy/current/) (jammy-server-cloudimg-amd64.img )
-- [Fedora 36](https://fedora.mirrorservice.org/fedora/linux/releases/36/Cloud/x86_64/images/) (Fedora-Cloud-Base-36-1.5.x86_64.raw.xz)
-
-Direct kernel boot to userspace should work with a rootfs from most
-distributions although you may need to enable exotic filesystem types in the
-reference kernel configuration (e.g. XFS or btrfs.)
+Direct kernel boot to userspace should work with a rootfs from most distributions.
 
 ## Hot Plug
 
-Cloud Hypervisor supports hotplug of CPUs, passthrough devices (VFIO),
-`virtio-{net,block,pmem,fs,vsock}` and memory resizing. This
-[document](docs/hotplug.md) details how to add devices to a running VM.
+Cloud Hypervisor supports hotplug of CPUs, passthrough devices (VFIO), `virtio-{net,block,pmem,fs,vsock}` and memory resizing. This [document](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/hotplug.md) details how to add devices to
+a running VM.
 
 ## Device Model
 
-Details of the device model can be found in this
-[documentation](docs/device_model.md).
+Details of the device model can be found in this [documentation](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/device_model.md).
 
-## Roadmap
+## TODO
 
-The project roadmap is tracked through a [GitHub
-project](https://github.com/orgs/cloud-hypervisor/projects/6).
+We are not tracking the Cloud Hypervisor TODO list from a specific git tracked file but through
+[github issues](https://github.com/cloud-hypervisor/cloud-hypervisor/issues/new) instead.
 
-# 4. Relationship with _Rust VMM_ Project
+# 4. `rust-vmm` project dependency
 
-In order to satisfy the design goal of having a high-performance,
-security-focused hypervisor the decision was made to use the
-[Rust](https://www.rust-lang.org/) programming language. The language's strong
-focus on memory and thread safety makes it an ideal candidate for implementing
-VMMs.
+In order to satisfy the design goal of having a high-performance, security-focused hypervisor the decision
+was made to use the [Rust](https://www.rust-lang.org/) programming language.
+The language's strong focus on memory and thread safety makes it an ideal candidate for implementing VMMs.
 
-Instead of implementing the VMM components from scratch, Cloud Hypervisor is
-importing the [Rust VMM](https://github.com/rust-vmm) crates, and sharing code
-and architecture together with other VMMs like e.g. Amazon's
-[Firecracker](https://firecracker-microvm.github.io/) and Google's
-[crosvm](https://chromium.googlesource.com/chromiumos/platform/crosvm/).
+Instead of implementing the VMM components from scratch, Cloud Hypervisor is importing the [rust-vmm](https://github.com/rust-vmm)
+crates, and sharing code and architecture together with other VMMs like e.g. Amazon's [Firecracker](https://firecracker-microvm.github.io/)
+and Google's [crosvm](https://chromium.googlesource.com/chromiumos/platform/crosvm/).
 
-Cloud Hypervisor embraces the _Rust VMM_ project's goals, which is to be able
-to share and re-use as many virtualization crates as possible.
+Cloud Hypervisor embraces the rust-vmm project goals, which is to be able to share and re-use
+as many virtualization crates as possible. As such, the Cloud Hypervisor relationship with the rust-vmm
+project is twofold:
 
-## Differences with Firecracker and crosvm
+1. It will use as much of the rust-vmm code as possible. Any new rust-vmm crate that's relevant to the project
+   goals will be integrated as soon as possible.
+2. As it is likely that the rust-vmm project will lack some of the features that Cloud Hypervisor needs (e.g. ACPI,
+   VFIO, vhost-user, etc), we will be using the Cloud Hypervisor VMM to implement and test them, and contribute them
+   back to the rust-vmm project.
 
-A large part of the Cloud Hypervisor code is based on either the Firecracker or
-the crosvm project's implementations. Both of these are VMMs written in Rust
-with a focus on safety and security, like Cloud Hypervisor.
+## Firecracker and crosvm
 
-The goal of the Cloud Hypervisor project differs from the aforementioned
-projects in that it aims to be a general purpose VMM for _Cloud Workloads_ and
-not limited to container/serverless or client workloads.
+A large part of the Cloud Hypervisor code is based on either the Firecracker or the crosvm projects implementations.
+Both of these are VMMs written in Rust with a focus on safety and security, like Cloud Hypervisor.
 
-The Cloud Hypervisor community thanks the communities of both the Firecracker
-and crosvm projects for their excellent work.
+However we want to emphasize that the Cloud Hypervisor project is neither a fork nor a reimplementation of any of those
+projects. The goals and use cases we're trying to meet are different.
+We're aiming at supporting cloud workloads, i.e. those modern, full Linux distribution images currently being run by
+Cloud Service Provider (CSP) tenants.
+
+Our primary target is not to support client or serverless use cases, and as such our code base already diverges
+from the crosvm and Firecracker ones. As we add more features to support our use cases, we believe that the divergence
+will increase while at the same time sharing as much of the fundamental virtualization code through the rust-vmm project
+crates as possible.
 
 # 5. Community
 
-The Cloud Hypervisor project follows the governance, and community guidelines
-described in the [Community](https://github.com/cloud-hypervisor/community)
-repository.
+The Cloud Hypervisor project follows the governance, and community guidelines described in
+the [Community](https://github.com/cloud-hypervisor/community) repository.
 
 ## Contribute
 
-The project strongly believes in building a global, diverse and collaborative
-community around the Cloud Hypervisor project. Anyone who is interested in
-[contributing](CONTRIBUTING.md) to the project is welcome to participate.
+We are working on building a global, diverse and collaborative community around the Cloud Hypervisor project.
+Anyone who is interested in [contributing](CONTRIBUTING.md) to the project is welcome to participate.
 
-Contributing to a open source project like Cloud Hypervisor covers a lot more
-than just sending code. Testing, documentation, pull request
-reviews, bug reports, feature requests, project improvement suggestions, etc,
-are all equal and welcome means of contribution. See the
-[CONTRIBUTING](CONTRIBUTING.md) document for more details.
+We believe that contributing to a open source project like Cloud Hypervisor covers a lot more than just sending
+code. Testing, documentation, pull request reviews, bug reports, feature requests, project improvement suggestions,
+etc, are all equal and welcome means of contribution. See the [CONTRIBUTING](CONTRIBUTING.md) document for more details.
 
-## Slack
+## Join us
 
 Get an [invite to our Slack channel](https://join.slack.com/t/cloud-hypervisor/shared_invite/enQtNjY3MTE3MDkwNDQ4LWQ1MTA1ZDVmODkwMWQ1MTRhYzk4ZGNlN2UwNTI3ZmFlODU0OTcwOWZjMTkwZDExYWE3YjFmNzgzY2FmNDAyMjI)
 and [join us on Slack](https://cloud-hypervisor.slack.com/).
-
-## Mailing list
-
-Please report bugs using the [GitHub issue
-tracker](https://github.com/cloud-hypervisor/cloud-hypervisor/issues) but for
-broader community discussions you may use our [mailing
-list](https://lists.cloudhypervisor.org/g/dev/).
-
-## Security issues
-
-Please contact the maintainers listed in the MAINTAINERS.md file with security issues.

acpi_tables/Cargo.toml

@@ -2,7 +2,8 @@
 name = "acpi_tables"
 version = "0.1.0"
 authors = ["The Cloud Hypervisor Authors"]
-edition = "2021"
+edition = "2018"
 
 [dependencies]
-vm-memory = "0.10.0"
+vm-memory = "0.5.0"
+

acpi_tables/src/aml.rs

@@ -6,23 +6,15 @@
 use std::marker::PhantomData;
 
 pub trait Aml {
-    fn append_aml_bytes(&self, _v: &mut Vec<u8>) {
-        unimplemented!()
-    }
-
-    fn to_aml_bytes(&self) -> Vec<u8> {
-        let mut v = Vec::new();
-        self.append_aml_bytes(&mut v);
-        v
-    }
+    fn to_aml_bytes(&self) -> Vec<u8>;
 }
 
 pub const ZERO: Zero = Zero {};
 pub struct Zero {}
 
 impl Aml for Zero {
-    fn append_aml_bytes(&self, v: &mut Vec<u8>) {
-        v.push(0u8)
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        vec![0u8]
     }
 }
 
@@ -30,8 +22,8 @@ pub const ONE: One = One {};
 pub struct One {}
 
 impl Aml for One {
-    fn append_aml_bytes(&self, v: &mut Vec<u8>) {
-        v.push(1u8)
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        vec![1u8]
     }
 }
 
@@ -39,8 +31,8 @@ pub const ONES: Ones = Ones {};
 pub struct Ones {}
 
 impl Aml for Ones {
-    fn append_aml_bytes(&self, v: &mut Vec<u8>) {
-        v.push(0xffu8)
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        vec![0xffu8]
     }
 }
 
@@ -50,7 +42,9 @@ pub struct Path {
 }
 
 impl Aml for Path {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
+
         if self.root {
             bytes.push(b'\\');
         }
@@ -68,8 +62,10 @@ impl Aml for Path {
         };
 
         for part in self.name_parts.clone().iter_mut() {
-            bytes.extend_from_slice(part.as_ref());
+            bytes.append(&mut part.to_vec());
         }
+
+        bytes
     }
 }
 
@@ -98,36 +94,40 @@ impl From<&str> for Path {
 pub type Byte = u8;
 
 impl Aml for Byte {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x0a); /* BytePrefix */
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x0a]; /* BytePrefix */
         bytes.push(*self);
+        bytes
     }
 }
 
 pub type Word = u16;
 
 impl Aml for Word {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x0b); /* WordPrefix */
-        bytes.extend_from_slice(&self.to_le_bytes())
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x0bu8]; /* WordPrefix */
+        bytes.append(&mut self.to_le_bytes().to_vec());
+        bytes
     }
 }
 
 pub type DWord = u32;
 
 impl Aml for DWord {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x0c); /* DWordPrefix */
-        bytes.extend_from_slice(&self.to_le_bytes())
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x0c]; /* DWordPrefix */
+        bytes.append(&mut self.to_le_bytes().to_vec());
+        bytes
     }
 }
 
 pub type QWord = u64;
 
 impl Aml for QWord {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x0e); /* QWordPrefix */
-        bytes.extend_from_slice(&self.to_le_bytes())
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x0e]; /* QWordPrefix */
+        bytes.append(&mut self.to_le_bytes().to_vec());
+        bytes
     }
 }
 
@@ -136,18 +136,16 @@ pub struct Name {
 }
 
 impl Aml for Name {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        // TODO: Refactor this to make more efficient but there are
-        // lifetime/ownership challenges.
-        bytes.extend_from_slice(&self.bytes.clone())
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        self.bytes.clone()
     }
 }
 
 impl Name {
     pub fn new(path: Path, inner: &dyn Aml) -> Self {
         let mut bytes = vec![0x08]; /* NameOp */
-        path.append_aml_bytes(&mut bytes);
-        inner.append_aml_bytes(&mut bytes);
+        bytes.append(&mut path.to_aml_bytes());
+        bytes.append(&mut inner.to_aml_bytes());
         Name { bytes }
     }
 }
@@ -157,17 +155,21 @@ pub struct Package<'a> {
 }
 
 impl<'a> Aml for Package<'a> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        let mut tmp = vec![self.children.len() as u8];
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![self.children.len() as u8];
         for child in &self.children {
-            child.append_aml_bytes(&mut tmp);
+            bytes.append(&mut child.to_aml_bytes());
         }
 
-        let pkg_length = create_pkg_length(&tmp, true);
+        let mut pkg_length = create_pkg_length(&bytes, true);
+        pkg_length.reverse();
+        for byte in pkg_length {
+            bytes.insert(0, byte);
+        }
 
-        bytes.push(0x12); /* PackageOp */
-        bytes.extend_from_slice(&pkg_length);
-        bytes.extend_from_slice(&tmp);
+        bytes.insert(0, 0x12); /* PackageOp */
+
+        bytes
     }
 }
 
@@ -255,46 +257,51 @@ impl EisaName {
 }
 
 impl Aml for EisaName {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        self.value.append_aml_bytes(bytes)
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        self.value.to_aml_bytes()
+    }
+}
+
+fn create_integer(v: usize) -> Vec<u8> {
+    if v <= u8::max_value().into() {
+        (v as u8).to_aml_bytes()
+    } else if v <= u16::max_value().into() {
+        (v as u16).to_aml_bytes()
+    } else if v <= u32::max_value() as usize {
+        (v as u32).to_aml_bytes()
+    } else {
+        (v as u64).to_aml_bytes()
     }
 }
 
 pub type Usize = usize;
 
 impl Aml for Usize {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        if *self <= u8::max_value().into() {
-            (*self as u8).append_aml_bytes(bytes)
-        } else if *self <= u16::max_value().into() {
-            (*self as u16).append_aml_bytes(bytes)
-        } else if *self <= u32::max_value() as usize {
-            (*self as u32).append_aml_bytes(bytes)
-        } else {
-            (*self as u64).append_aml_bytes(bytes)
-        }
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        create_integer(*self)
     }
 }
 
-fn append_aml_string(v: &str, bytes: &mut Vec<u8>) {
-    bytes.push(0x0D); /* String Op */
-    bytes.extend_from_slice(v.as_bytes());
-    bytes.push(0x0); /* NullChar */
+fn create_aml_string(v: &str) -> Vec<u8> {
+    let mut data = vec![0x0D]; /* String Op */
+    data.extend_from_slice(v.as_bytes());
+    data.push(0x0); /* NullChar */
+    data
 }
 
 pub type AmlStr = &'static str;
 
 impl Aml for AmlStr {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        append_aml_string(self, bytes)
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        create_aml_string(self)
     }
 }
 
 pub type AmlString = String;
 
 impl Aml for AmlString {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        append_aml_string(self, bytes)
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        create_aml_string(self)
     }
 }
 
@@ -303,31 +310,36 @@ pub struct ResourceTemplate<'a> {
 }
 
 impl<'a> Aml for ResourceTemplate<'a> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        let mut tmp = Vec::new();
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
+
         // Add buffer data
         for child in &self.children {
-            child.append_aml_bytes(&mut tmp);
+            bytes.append(&mut child.to_aml_bytes());
         }
 
         // Mark with end and mark checksum as as always valid
-        tmp.push(0x79); /* EndTag */
-        tmp.push(0); /* zero checksum byte */
+        bytes.push(0x79); /* EndTag */
+        bytes.push(0); /* zero checksum byte */
 
         // Buffer length is an encoded integer including buffer data
         // and EndTag and checksum byte
-        let mut buffer_length = tmp.len().to_aml_bytes();
+        let mut buffer_length = bytes.len().to_aml_bytes();
         buffer_length.reverse();
         for byte in buffer_length {
-            tmp.insert(0, byte);
+            bytes.insert(0, byte);
         }
 
         // PkgLength is everything else
-        let pkg_length = create_pkg_length(&tmp, true);
+        let mut pkg_length = create_pkg_length(&bytes, true);
+        pkg_length.reverse();
+        for byte in pkg_length {
+            bytes.insert(0, byte);
+        }
 
-        bytes.push(0x11); /* BufferOp */
-        bytes.extend_from_slice(&pkg_length);
-        bytes.extend_from_slice(&tmp);
+        bytes.insert(0, 0x11); /* BufferOp */
+
+        bytes
     }
 }
 
@@ -354,13 +366,15 @@ impl Memory32Fixed {
 }
 
 impl Aml for Memory32Fixed {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x86); /* Memory32Fixed */
-        bytes.extend_from_slice(&9u16.to_le_bytes());
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x86]; /* Memory32Fixed */
+        bytes.append(&mut 9u16.to_le_bytes().to_vec());
+
         // 9 bytes of payload
         bytes.push(self.read_write as u8);
-        bytes.extend_from_slice(&self.base.to_le_bytes());
-        bytes.extend_from_slice(&self.length.to_le_bytes());
+        bytes.append(&mut self.base.to_le_bytes().to_vec());
+        bytes.append(&mut self.length.to_le_bytes().to_vec());
+        bytes
     }
 }
 
@@ -416,7 +430,7 @@ impl<T> AddressSpace<T> {
 
     fn push_header(&self, bytes: &mut Vec<u8>, descriptor: u8, length: usize) {
         bytes.push(descriptor); /* Word Address Space Descriptor */
-        bytes.extend_from_slice(&(length as u16).to_le_bytes());
+        bytes.append(&mut (length as u16).to_le_bytes().to_vec());
         bytes.push(self.r#type as u8); /* type */
         let generic_flags = 1 << 2 /* Min Fixed */ | 1 << 3; /* Max Fixed */
         bytes.push(generic_flags);
@@ -425,53 +439,65 @@ impl<T> AddressSpace<T> {
 }
 
 impl Aml for AddressSpace<u16> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
+
         self.push_header(
-            bytes,
+            &mut bytes,
             0x88,                               /* Word Address Space Descriptor */
             3 + 5 * std::mem::size_of::<u16>(), /* 3 bytes of header + 5 u16 fields */
         );
 
-        bytes.extend_from_slice(&0u16.to_le_bytes()); /* Granularity */
-        bytes.extend_from_slice(&self.min.to_le_bytes()); /* Min */
-        bytes.extend_from_slice(&self.max.to_le_bytes()); /* Max */
-        bytes.extend_from_slice(&0u16.to_le_bytes()); /* Translation */
+        bytes.append(&mut 0u16.to_le_bytes().to_vec()); /* Granularity */
+        bytes.append(&mut self.min.to_le_bytes().to_vec()); /* Min */
+        bytes.append(&mut self.max.to_le_bytes().to_vec()); /* Max */
+        bytes.append(&mut 0u16.to_le_bytes().to_vec()); /* Translation */
         let len = self.max - self.min + 1;
-        bytes.extend_from_slice(&len.to_le_bytes()); /* Length */
+        bytes.append(&mut len.to_le_bytes().to_vec()); /* Length */
+
+        bytes
     }
 }
 
 impl Aml for AddressSpace<u32> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
+
         self.push_header(
-            bytes,
+            &mut bytes,
             0x87,                               /* DWord Address Space Descriptor */
             3 + 5 * std::mem::size_of::<u32>(), /* 3 bytes of header + 5 u32 fields */
         );
 
-        bytes.extend_from_slice(&0u32.to_le_bytes()); /* Granularity */
-        bytes.extend_from_slice(&self.min.to_le_bytes()); /* Min */
-        bytes.extend_from_slice(&self.max.to_le_bytes()); /* Max */
-        bytes.extend_from_slice(&0u32.to_le_bytes()); /* Translation */
+        bytes.append(&mut 0u32.to_le_bytes().to_vec()); /* Granularity */
+        bytes.append(&mut self.min.to_le_bytes().to_vec()); /* Min */
+        bytes.append(&mut self.max.to_le_bytes().to_vec()); /* Max */
+        bytes.append(&mut 0u32.to_le_bytes().to_vec()); /* Translation */
         let len = self.max - self.min + 1;
-        bytes.extend_from_slice(&len.to_le_bytes()); /* Length */
+        bytes.append(&mut len.to_le_bytes().to_vec()); /* Length */
+
+        bytes
     }
 }
 
 impl Aml for AddressSpace<u64> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
+
         self.push_header(
-            bytes,
+            &mut bytes,
             0x8A,                               /* QWord Address Space Descriptor */
             3 + 5 * std::mem::size_of::<u64>(), /* 3 bytes of header + 5 u64 fields */
         );
 
-        bytes.extend_from_slice(&0u64.to_le_bytes()); /* Granularity */
-        bytes.extend_from_slice(&self.min.to_le_bytes()); /* Min */
-        bytes.extend_from_slice(&self.max.to_le_bytes()); /* Max */
-        bytes.extend_from_slice(&0u64.to_le_bytes()); /* Translation */
+        bytes.append(&mut 0u64.to_le_bytes().to_vec()); /* Granularity */
+        bytes.append(&mut self.min.to_le_bytes().to_vec()); /* Min */
+        bytes.append(&mut self.max.to_le_bytes().to_vec()); /* Max */
+        bytes.append(&mut 0u64.to_le_bytes().to_vec()); /* Translation */
         let len = self.max - self.min + 1;
-        bytes.extend_from_slice(&len.to_le_bytes()); /* Length */
+        bytes.append(&mut len.to_le_bytes().to_vec()); /* Length */
+
+        bytes
     }
 }
 
@@ -494,13 +520,16 @@ impl Io {
 }
 
 impl Aml for Io {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x47); /* Io Port Descriptor */
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x47]; /* Io Port Descriptor */
+
         bytes.push(1); /* IODecode16 */
-        bytes.extend_from_slice(&self.min.to_le_bytes());
-        bytes.extend_from_slice(&self.max.to_le_bytes());
+        bytes.append(&mut self.min.to_le_bytes().to_vec());
+        bytes.append(&mut self.max.to_le_bytes().to_vec());
         bytes.push(self.alignment);
         bytes.push(self.length);
+
+        bytes
     }
 }
 
@@ -531,16 +560,18 @@ impl Interrupt {
 }
 
 impl Aml for Interrupt {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x89); /* Extended IRQ Descriptor */
-        bytes.extend_from_slice(&6u16.to_le_bytes());
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x89]; /* Extended IRQ Descriptor */
+        bytes.append(&mut 6u16.to_le_bytes().to_vec());
         let flags = (self.shared as u8) << 3
             | (self.active_low as u8) << 2
             | (self.edge_triggered as u8) << 1
             | self.consumer as u8;
         bytes.push(flags);
         bytes.push(1u8); /* count */
-        bytes.extend_from_slice(&self.number.to_le_bytes());
+        bytes.append(&mut self.number.to_le_bytes().to_vec());
+
+        bytes
     }
 }
 
@@ -550,20 +581,22 @@ pub struct Device<'a> {
 }
 
 impl<'a> Aml for Device<'a> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        let mut tmp = Vec::new();
-        self.path.append_aml_bytes(&mut tmp);
-
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
+        bytes.append(&mut self.path.to_aml_bytes());
         for child in &self.children {
-            child.append_aml_bytes(&mut tmp);
+            bytes.append(&mut child.to_aml_bytes());
         }
 
-        let pkg_length = create_pkg_length(&tmp, true);
+        let mut pkg_length = create_pkg_length(&bytes, true);
+        pkg_length.reverse();
+        for byte in pkg_length {
+            bytes.insert(0, byte);
+        }
 
-        bytes.push(0x5b); /* ExtOpPrefix */
-        bytes.push(0x82); /* DeviceOp */
-        bytes.extend_from_slice(&pkg_length);
-        bytes.extend_from_slice(&tmp);
+        bytes.insert(0, 0x82); /* DeviceOp */
+        bytes.insert(0, 0x5b); /* ExtOpPrefix */
+        bytes
     }
 }
 
@@ -579,18 +612,21 @@ pub struct Scope<'a> {
 }
 
 impl<'a> Aml for Scope<'a> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        let mut tmp = Vec::new();
-        self.path.append_aml_bytes(&mut tmp);
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
+        bytes.append(&mut self.path.to_aml_bytes());
         for child in &self.children {
-            child.append_aml_bytes(&mut tmp);
+            bytes.append(&mut child.to_aml_bytes());
         }
 
-        let pkg_length = create_pkg_length(&tmp, true);
+        let mut pkg_length = create_pkg_length(&bytes, true);
+        pkg_length.reverse();
+        for byte in pkg_length {
+            bytes.insert(0, byte);
+        }
 
-        bytes.push(0x10); /* ScopeOp */
-        bytes.extend_from_slice(&pkg_length);
-        bytes.extend_from_slice(&tmp)
+        bytes.insert(0, 0x10); /* ScopeOp */
+        bytes
     }
 }
 
@@ -619,20 +655,23 @@ impl<'a> Method<'a> {
 }
 
 impl<'a> Aml for Method<'a> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        let mut tmp = Vec::new();
-        self.path.append_aml_bytes(&mut tmp);
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
+        bytes.append(&mut self.path.to_aml_bytes());
         let flags: u8 = (self.args & 0x7) | (self.serialized as u8) << 3;
-        tmp.push(flags);
+        bytes.push(flags);
         for child in &self.children {
-            child.append_aml_bytes(&mut tmp);
+            bytes.append(&mut child.to_aml_bytes());
         }
 
-        let pkg_length = create_pkg_length(&tmp, true);
+        let mut pkg_length = create_pkg_length(&bytes, true);
+        pkg_length.reverse();
+        for byte in pkg_length {
+            bytes.insert(0, byte);
+        }
 
-        bytes.push(0x14); /* MethodOp */
-        bytes.extend_from_slice(&pkg_length);
-        bytes.extend_from_slice(&tmp)
+        bytes.insert(0, 0x14); /* MethodOp */
+        bytes
     }
 }
 
@@ -647,9 +686,10 @@ impl<'a> Return<'a> {
 }
 
 impl<'a> Aml for Return<'a> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0xa4); /* ReturnOp */
-        self.value.append_aml_bytes(bytes);
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0xa4]; /* ReturnOp */
+        bytes.append(&mut self.value.to_aml_bytes());
+        bytes
     }
 }
 
@@ -692,40 +732,43 @@ impl Field {
     ) -> Self {
         Field {
             path,
-            fields,
             access_type,
             update_rule,
+            fields,
         }
     }
 }
 
 impl Aml for Field {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        let mut tmp = Vec::new();
-        self.path.append_aml_bytes(&mut tmp);
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
+        bytes.append(&mut self.path.to_aml_bytes());
 
         let flags: u8 = self.access_type as u8 | (self.update_rule as u8) << 5;
-        tmp.push(flags);
+        bytes.push(flags);
 
         for field in self.fields.iter() {
             match field {
                 FieldEntry::Named(name, length) => {
-                    tmp.extend_from_slice(name);
-                    tmp.extend_from_slice(&create_pkg_length(&vec![0; *length], false));
+                    bytes.extend_from_slice(name);
+                    bytes.append(&mut create_pkg_length(&vec![0; *length], false));
                 }
                 FieldEntry::Reserved(length) => {
-                    tmp.push(0x0);
-                    tmp.extend_from_slice(&create_pkg_length(&vec![0; *length], false));
+                    bytes.push(0x0);
+                    bytes.append(&mut create_pkg_length(&vec![0; *length], false));
                 }
             }
         }
 
-        let pkg_length = create_pkg_length(&tmp, true);
+        let mut pkg_length = create_pkg_length(&bytes, true);
+        pkg_length.reverse();
+        for byte in pkg_length {
+            bytes.insert(0, byte);
+        }
 
-        bytes.push(0x5b); /* ExtOpPrefix */
-        bytes.push(0x81); /* FieldOp */
-        bytes.extend_from_slice(&pkg_length);
-        bytes.extend_from_slice(&tmp)
+        bytes.insert(0, 0x81); /* FieldOp */
+        bytes.insert(0, 0x5b); /* ExtOpPrefix */
+        bytes
     }
 }
 
@@ -762,13 +805,15 @@ impl OpRegion {
 }
 
 impl Aml for OpRegion {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x5b); /* ExtOpPrefix */
-        bytes.push(0x80); /* OpRegionOp */
-        self.path.append_aml_bytes(bytes);
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
+        bytes.append(&mut self.path.to_aml_bytes());
         bytes.push(self.space as u8);
-        self.offset.append_aml_bytes(bytes); /* RegionOffset */
-        self.length.append_aml_bytes(bytes); /* RegionLen */
+        bytes.extend_from_slice(&self.offset.to_aml_bytes()); /* RegionOffset */
+        bytes.extend_from_slice(&self.length.to_aml_bytes()); /* RegionLen */
+        bytes.insert(0, 0x80); /* OpRegionOp */
+        bytes.insert(0, 0x5b); /* ExtOpPrefix */
+        bytes
     }
 }
 
@@ -787,24 +832,27 @@ impl<'a> If<'a> {
 }
 
 impl<'a> Aml for If<'a> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        let mut tmp = Vec::new();
-        self.predicate.append_aml_bytes(&mut tmp);
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
+        bytes.extend_from_slice(&self.predicate.to_aml_bytes());
         for child in self.if_children.iter() {
-            child.append_aml_bytes(&mut tmp);
+            bytes.extend_from_slice(&child.to_aml_bytes());
         }
 
-        let pkg_length = create_pkg_length(&tmp, true);
+        let mut pkg_length = create_pkg_length(&bytes, true);
+        pkg_length.reverse();
+        for byte in pkg_length {
+            bytes.insert(0, byte);
+        }
 
-        bytes.push(0xa0); /* IfOp */
-        bytes.extend_from_slice(&pkg_length);
-        bytes.extend_from_slice(&tmp);
+        bytes.insert(0, 0xa0); /* IfOp */
+        bytes
     }
 }
 
 pub struct Equal<'a> {
-    left: &'a dyn Aml,
     right: &'a dyn Aml,
+    left: &'a dyn Aml,
 }
 
 impl<'a> Equal<'a> {
@@ -814,16 +862,17 @@ impl<'a> Equal<'a> {
 }
 
 impl<'a> Aml for Equal<'a> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x93); /* LEqualOp */
-        self.left.append_aml_bytes(bytes);
-        self.right.append_aml_bytes(bytes);
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x93]; /* LEqualOp */
+        bytes.extend_from_slice(&self.left.to_aml_bytes());
+        bytes.extend_from_slice(&self.right.to_aml_bytes());
+        bytes
     }
 }
 
 pub struct LessThan<'a> {
-    left: &'a dyn Aml,
     right: &'a dyn Aml,
+    left: &'a dyn Aml,
 }
 
 impl<'a> LessThan<'a> {
@@ -833,28 +882,33 @@ impl<'a> LessThan<'a> {
 }
 
 impl<'a> Aml for LessThan<'a> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x95); /* LLessOp */
-        self.left.append_aml_bytes(bytes);
-        self.right.append_aml_bytes(bytes);
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x95]; /* LLessOp */
+        bytes.extend_from_slice(&self.left.to_aml_bytes());
+        bytes.extend_from_slice(&self.right.to_aml_bytes());
+        bytes
     }
 }
 
 pub struct Arg(pub u8);
 
 impl Aml for Arg {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
         assert!(self.0 <= 6);
         bytes.push(0x68 + self.0); /* Arg0Op */
+        bytes
     }
 }
 
 pub struct Local(pub u8);
 
 impl Aml for Local {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
         assert!(self.0 <= 7);
         bytes.push(0x60 + self.0); /* Local0Op */
+        bytes
     }
 }
 
@@ -870,10 +924,11 @@ impl<'a> Store<'a> {
 }
 
 impl<'a> Aml for Store<'a> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x70); /* StoreOp */
-        self.value.append_aml_bytes(bytes);
-        self.name.append_aml_bytes(bytes);
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x70]; /* StoreOp */
+        bytes.extend_from_slice(&self.value.to_aml_bytes());
+        bytes.extend_from_slice(&self.name.to_aml_bytes());
+        bytes
     }
 }
 
@@ -889,11 +944,12 @@ impl Mutex {
 }
 
 impl Aml for Mutex {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x5b); /* ExtOpPrefix */
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x5b]; /* ExtOpPrefix */
         bytes.push(0x01); /* MutexOp */
-        self.path.append_aml_bytes(bytes);
+        bytes.extend_from_slice(&self.path.to_aml_bytes());
         bytes.push(self.sync_level);
+        bytes
     }
 }
 
@@ -909,11 +965,12 @@ impl Acquire {
 }
 
 impl Aml for Acquire {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x5b); /* ExtOpPrefix */
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x5b]; /* ExtOpPrefix */
         bytes.push(0x23); /* AcquireOp */
-        self.mutex.append_aml_bytes(bytes);
+        bytes.extend_from_slice(&self.mutex.to_aml_bytes());
         bytes.extend_from_slice(&self.timeout.to_le_bytes());
+        bytes
     }
 }
 
@@ -928,10 +985,11 @@ impl Release {
 }
 
 impl Aml for Release {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x5b); /* ExtOpPrefix */
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x5b]; /* ExtOpPrefix */
         bytes.push(0x27); /* ReleaseOp */
-        self.mutex.append_aml_bytes(bytes);
+        bytes.extend_from_slice(&self.mutex.to_aml_bytes());
+        bytes
     }
 }
 
@@ -947,10 +1005,11 @@ impl<'a> Notify<'a> {
 }
 
 impl<'a> Aml for Notify<'a> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x86); /* NotifyOp */
-        self.object.append_aml_bytes(bytes);
-        self.value.append_aml_bytes(bytes);
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x86]; /* NotifyOp */
+        bytes.extend_from_slice(&self.object.to_aml_bytes());
+        bytes.extend_from_slice(&self.value.to_aml_bytes());
+        bytes
     }
 }
 
@@ -969,18 +1028,21 @@ impl<'a> While<'a> {
 }
 
 impl<'a> Aml for While<'a> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        let mut tmp = Vec::new();
-        self.predicate.append_aml_bytes(&mut tmp);
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
+        bytes.extend_from_slice(&self.predicate.to_aml_bytes());
         for child in self.while_children.iter() {
-            child.append_aml_bytes(&mut tmp)
+            bytes.extend_from_slice(&child.to_aml_bytes());
         }
 
-        let pkg_length = create_pkg_length(&tmp, true);
+        let mut pkg_length = create_pkg_length(&bytes, true);
+        pkg_length.reverse();
+        for byte in pkg_length {
+            bytes.insert(0, byte);
+        }
 
-        bytes.push(0xa2); /* WhileOp */
-        bytes.extend_from_slice(&pkg_length);
-        bytes.extend_from_slice(&tmp);
+        bytes.insert(0, 0xa2); /* WhileOp */
+        bytes
     }
 }
 
@@ -994,16 +1056,17 @@ macro_rules! binary_op {
 
         impl<'a> $name<'a> {
             pub fn new(target: &'a dyn Aml, a: &'a dyn Aml, b: &'a dyn Aml) -> Self {
-                $name { a, b, target }
+                $name { target, a, b }
             }
         }
 
         impl<'a> Aml for $name<'a> {
-            fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-                bytes.push($opcode); /* Op for the binary operator */
-                self.a.append_aml_bytes(bytes);
-                self.b.append_aml_bytes(bytes);
-                self.target.append_aml_bytes(bytes);
+            fn to_aml_bytes(&self) -> Vec<u8> {
+                let mut bytes = vec![$opcode]; /* Op for the binary operator */
+                bytes.extend_from_slice(&self.a.to_aml_bytes());
+                bytes.extend_from_slice(&self.b.to_aml_bytes());
+                bytes.extend_from_slice(&self.target.to_aml_bytes());
+                bytes
             }
         }
     };
@@ -1038,11 +1101,13 @@ impl<'a> MethodCall<'a> {
 }
 
 impl<'a> Aml for MethodCall<'a> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        self.name.append_aml_bytes(bytes);
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
+        bytes.extend_from_slice(&self.name.to_aml_bytes());
         for arg in self.args.iter() {
-            arg.append_aml_bytes(bytes);
+            bytes.extend_from_slice(&arg.to_aml_bytes());
         }
+        bytes
     }
 }
 
@@ -1057,16 +1122,20 @@ impl Buffer {
 }
 
 impl Aml for Buffer {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        let mut tmp = Vec::new();
-        self.data.len().append_aml_bytes(&mut tmp);
-        tmp.extend_from_slice(&self.data);
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = Vec::new();
+        bytes.extend_from_slice(&self.data.len().to_aml_bytes());
+        bytes.extend_from_slice(&self.data);
 
-        let pkg_length = create_pkg_length(&tmp, true);
+        let mut pkg_length = create_pkg_length(&bytes, true);
+        pkg_length.reverse();
+        for byte in pkg_length {
+            bytes.insert(0, byte);
+        }
 
-        bytes.push(0x11); /* BufferOp */
-        bytes.extend_from_slice(&pkg_length);
-        bytes.extend_from_slice(&tmp);
+        bytes.insert(0, 0x11); /* BufferOp */
+
+        bytes
     }
 }
 
@@ -1089,20 +1158,22 @@ impl<'a, T> CreateField<'a, T> {
 }
 
 impl<'a> Aml for CreateField<'a, u64> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x8f); /* CreateQWordFieldOp */
-        self.buffer.append_aml_bytes(bytes);
-        self.offset.append_aml_bytes(bytes);
-        self.field.append_aml_bytes(bytes);
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x8f]; /* CreateQWordFieldOp */
+        bytes.extend_from_slice(&self.buffer.to_aml_bytes());
+        bytes.extend_from_slice(&self.offset.to_aml_bytes());
+        bytes.extend_from_slice(&self.field.to_aml_bytes());
+        bytes
     }
 }
 
 impl<'a> Aml for CreateField<'a, u32> {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
-        bytes.push(0x8a); /* CreateDWordFieldOp */
-        self.buffer.append_aml_bytes(bytes);
-        self.offset.append_aml_bytes(bytes);
-        self.field.append_aml_bytes(bytes);
+    fn to_aml_bytes(&self) -> Vec<u8> {
+        let mut bytes = vec![0x8a]; /* CreateDWordFieldOp */
+        bytes.extend_from_slice(&self.buffer.to_aml_bytes());
+        bytes.extend_from_slice(&self.offset.to_aml_bytes());
+        bytes.extend_from_slice(&self.field.to_aml_bytes());
+        bytes
     }
 }
 
@@ -1392,13 +1463,13 @@ mod tests {
 
     #[test]
     fn test_pkg_length() {
-        assert_eq!(create_pkg_length(&[0u8; 62], true), vec![63]);
+        assert_eq!(create_pkg_length(&[0u8; 62].to_vec(), true), vec![63]);
         assert_eq!(
-            create_pkg_length(&[0u8; 64], true),
+            create_pkg_length(&[0u8; 64].to_vec(), true),
             vec![1 << 6 | (66 & 0xf), 66 >> 4]
         );
         assert_eq!(
-            create_pkg_length(&[0u8; 4096], true),
+            create_pkg_length(&[0u8; 4096].to_vec(), true),
             vec![
                 2 << 6 | (4099 & 0xf) as u8,
                 (4099 >> 4) as u8,

acpi_tables/src/rsdp.rs

@@ -19,7 +19,6 @@ pub struct Rsdp {
     _reserved: [u8; 3],
 }
 
-// SAFETY: Rsdp only contains a series of integers
 unsafe impl ByteValued for Rsdp {}
 
 impl Rsdp {
@@ -37,7 +36,7 @@ impl Rsdp {
         };
 
         rsdp.checksum = super::generate_checksum(&rsdp.as_slice()[0..19]);
-        rsdp.extended_checksum = super::generate_checksum(rsdp.as_slice());
+        rsdp.extended_checksum = super::generate_checksum(&rsdp.as_slice());
         rsdp
     }
 

acpi_tables/src/sdt.rs

@@ -4,7 +4,6 @@
 //
 
 #[repr(packed)]
-#[derive(Clone, Copy)]
 pub struct GenericAddress {
     pub address_space_id: u8,
     pub register_bit_width: u8,
@@ -23,15 +22,6 @@ impl GenericAddress {
             address: u64::from(address),
         }
     }
-    pub fn mmio_address<T>(address: u64) -> Self {
-        GenericAddress {
-            address_space_id: 0,
-            register_bit_width: 8 * std::mem::size_of::<T>() as u8,
-            register_bit_offset: 0,
-            access_size: std::mem::size_of::<T>() as u8,
-            address,
-        }
-    }
 }
 
 pub struct Sdt {
@@ -76,7 +66,7 @@ impl Sdt {
     }
 
     pub fn as_slice(&self) -> &[u8] {
-        self.data.as_slice()
+        &self.data.as_slice()
     }
 
     pub fn append<T>(&mut self, value: T) {

api_client/Cargo.toml

@@ -2,7 +2,4 @@
 name = "api_client"
 version = "0.1.0"
 authors = ["The Cloud Hypervisor Authors"]
-edition = "2021"
-
-[dependencies]
-vmm-sys-util = "0.11.0"
+edition = "2018"

api_client/src/lib.rs

@@ -5,13 +5,10 @@
 
 use std::fmt;
 use std::io::{Read, Write};
-use std::os::unix::io::RawFd;
-use vmm_sys_util::sock_ctrl_msg::ScmSocket;
 
 #[derive(Debug)]
 pub enum Error {
     Socket(std::io::Error),
-    SocketSendFds(vmm_sys_util::errno::Error),
     StatusCodeParsing(std::num::ParseIntError),
     MissingProtocol,
     ContentLengthParsing(std::num::ParseIntError),
@@ -22,16 +19,15 @@ 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}"),
+            Socket(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}"),
+            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}")
+                    write!(f, "Server responded with an error: {:?}: {}", s, o)
                 } else {
-                    write!(f, "Server responded with an error: {s:?}")
+                    write!(f, "Server responded with an error: {:?}", s)
                 }
             }
         }
@@ -79,9 +75,12 @@ impl StatusCode {
 }
 
 fn get_header<'a>(res: &'a str, header: &'a str) -> Option<&'a str> {
-    let header_str = format!("{header}: ");
-    res.find(&header_str)
-        .map(|o| &res[o + header_str.len()..o + res[o..].find('\r').unwrap()])
+    let header_str = format!("{}: ", header);
+    if let Some(o) = res.find(&header_str) {
+        Some(&res[o + header_str.len()..o + res[o..].find('\r').unwrap()])
+    } else {
+        None
+    }
 }
 
 fn get_status_code(res: &str) -> Result<StatusCode, Error> {
@@ -101,10 +100,6 @@ fn parse_http_response(socket: &mut dyn Read) -> Result<Option<String>, Error> {
     loop {
         let mut bytes = vec![0; 256];
         let count = socket.read(&mut bytes).map_err(Error::Socket)?;
-        // If the return value is 0, the peer has performed an orderly shutdown.
-        if count == 0 {
-            break;
-        }
         res.push_str(std::str::from_utf8(&bytes[0..count]).unwrap());
 
         // End of headers
@@ -131,7 +126,7 @@ fn parse_http_response(socket: &mut dyn Read) -> Result<Option<String>, Error> {
             }
         }
     }
-    let body_string = content_length.and(body_offset.map(|o| String::from(&res[o..])));
+    let body_string = content_length.and(Some(String::from(&res[body_offset.unwrap()..])));
     let status_code = get_status_code(&res)?;
 
     if status_code.is_server_error() {
@@ -141,24 +136,21 @@ fn parse_http_response(socket: &mut dyn Read) -> Result<Option<String>, Error> {
     }
 }
 
-/// Make an API request using the fully qualified command name.
-/// For example, full_command could be "vm.create" or "vmm.ping".
-pub fn simple_api_full_command_with_fds_and_response<T: Read + Write + ScmSocket>(
+pub fn simple_api_command<T: Read + Write>(
     socket: &mut T,
     method: &str,
-    full_command: &str,
+    c: &str,
     request_body: Option<&str>,
-    request_fds: Vec<RawFd>,
-) -> Result<Option<String>, Error> {
+) -> Result<(), Error> {
     socket
-        .send_with_fds(
-            &[format!(
-                "{method} /api/v1/{full_command} HTTP/1.1\r\nHost: localhost\r\nAccept: */*\r\n"
+        .write_all(
+            format!(
+                "{} /api/v1/vm.{} HTTP/1.1\r\nHost: localhost\r\nAccept: */*\r\n",
+                method, c
             )
-            .as_bytes()],
-            &request_fds,
+            .as_bytes(),
         )
-        .map_err(Error::SocketSendFds)?;
+        .map_err(Error::Socket)?;
 
     if let Some(request_body) = request_body {
         socket
@@ -176,74 +168,8 @@ pub fn simple_api_full_command_with_fds_and_response<T: Read + Write + ScmSocket
 
     socket.flush().map_err(Error::Socket)?;
 
-    parse_http_response(socket)
-}
-
-pub fn simple_api_full_command_with_fds<T: Read + Write + ScmSocket>(
-    socket: &mut T,
-    method: &str,
-    full_command: &str,
-    request_body: Option<&str>,
-    request_fds: Vec<RawFd>,
-) -> Result<(), Error> {
-    let response = simple_api_full_command_with_fds_and_response(
-        socket,
-        method,
-        full_command,
-        request_body,
-        request_fds,
-    )?;
-
-    if response.is_some() {
-        println!("{}", response.unwrap());
+    if let Some(body) = parse_http_response(socket)? {
+        println!("{}", body);
     }
-
     Ok(())
 }
-
-pub fn simple_api_full_command<T: Read + Write + ScmSocket>(
-    socket: &mut T,
-    method: &str,
-    full_command: &str,
-    request_body: Option<&str>,
-) -> Result<(), Error> {
-    simple_api_full_command_with_fds(socket, method, full_command, request_body, Vec::new())
-}
-
-pub fn simple_api_full_command_and_response<T: Read + Write + ScmSocket>(
-    socket: &mut T,
-    method: &str,
-    full_command: &str,
-    request_body: Option<&str>,
-) -> Result<Option<String>, Error> {
-    simple_api_full_command_with_fds_and_response(
-        socket,
-        method,
-        full_command,
-        request_body,
-        Vec::new(),
-    )
-}
-
-pub fn simple_api_command_with_fds<T: Read + Write + ScmSocket>(
-    socket: &mut T,
-    method: &str,
-    c: &str,
-    request_body: Option<&str>,
-    request_fds: Vec<RawFd>,
-) -> Result<(), Error> {
-    // Create the full VM command. For VMM commands, use
-    // simple_api_full_command().
-    let full_command = format!("vm.{c}");
-
-    simple_api_full_command_with_fds(socket, method, &full_command, request_body, request_fds)
-}
-
-pub fn simple_api_command<T: Read + Write + ScmSocket>(
-    socket: &mut T,
-    method: &str,
-    c: &str,
-    request_body: Option<&str>,
-) -> Result<(), Error> {
-    simple_api_command_with_fds(socket, method, c, request_body, Vec::new())
-}

arch/Cargo.toml

@@ -2,28 +2,25 @@
 name = "arch"
 version = "0.1.0"
 authors = ["The Chromium OS Authors"]
-edition = "2021"
 
 [features]
 default = []
+acpi = ["acpi_tables"]
 tdx = []
 
 [dependencies]
-anyhow = "1.0.66"
+acpi_tables = { path = "../acpi_tables", optional = true }
+anyhow = "1.0"
+arch_gen = { path = "../arch_gen" }
 byteorder = "1.4.3"
 hypervisor = { path = "../hypervisor" }
-libc = "0.2.138"
-linux-loader = { version = "0.8.1", features = ["elf", "bzimage", "pe"] }
-log = "0.4.17"
-serde = { version = "1.0.150", features = ["rc", "derive"] }
-thiserror = "1.0.37"
-uuid = "1.2.2"
-versionize = "0.1.9"
-versionize_derive = "0.1.4"
-vm-memory = { version = "0.10.0", features = ["backend-mmap", "backend-bitmap"] }
+libc = "0.2.91"
+linux-loader = { version = "0.3.0", features = ["elf", "bzimage", "pe"] }
+log = "0.4.14"
+serde = {version = ">=1.0.27", features = ["rc"] }
+serde_derive = ">=1.0.27"
+serde_json = ">=1.0.9"
+thiserror = "1.0"
+vm-memory = { version = "0.5.0", features = ["backend-mmap"] }
 vm-migration = { path = "../vm-migration" }
-vmm-sys-util = { version = "0.11.0", features = ["with-serde"] }
 
-[target.'cfg(target_arch = "aarch64")'.dependencies]
-fdt_parser = { version = "0.1.4", package = "fdt" }
-vm-fdt = { git = "https://github.com/rust-vmm/vm-fdt", branch = "main" }

arch/src/aarch64/gic/dist_regs.rs

@@ -1,12 +1,12 @@
 // Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 // SPDX-License-Identifier: Apache-2.0
 
-use crate::arch::aarch64::gic::{Error, Result};
-use crate::device::HypervisorDeviceError;
-use crate::kvm::kvm_bindings::{
+use super::{Error, Result};
+use crate::layout::IRQ_BASE;
+use hypervisor::kvm::kvm_bindings::{
     kvm_device_attr, KVM_DEV_ARM_VGIC_GRP_DIST_REGS, KVM_DEV_ARM_VGIC_GRP_NR_IRQS,
 };
-use kvm_ioctls::DeviceFd;
+use std::sync::Arc;
 
 /*
  Distributor registers as detailed at page 456 from
@@ -63,7 +63,7 @@ macro_rules! VGIC_DIST_REG {
 
 // List with relevant distributor registers that we will be restoring.
 // Order is taken from qemu.
-static VGIC_DIST_REGS: &[DistReg] = &[
+static VGIC_DIST_REGS: &'static [DistReg] = &[
     VGIC_DIST_REG!(GICD_STATUSR, 0, 4),
     VGIC_DIST_REG!(GICD_ICENABLER, 1, 0),
     VGIC_DIST_REG!(GICD_ISENABLER, 1, 0),
@@ -77,7 +77,12 @@ 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_access(
+    gic: &Arc<dyn hypervisor::Device>,
+    offset: u32,
+    val: &u32,
+    set: bool,
+) -> Result<()> {
     let mut gic_dist_attr = kvm_device_attr {
         group: KVM_DEV_ARM_VGIC_GRP_DIST_REGS,
         attr: offset as u64,
@@ -85,30 +90,28 @@ fn dist_attr_access(gic: &DeviceFd, offset: u32, val: &u32, set: bool) -> Result
         flags: 0,
     };
     if set {
-        gic.set_device_attr(&gic_dist_attr).map_err(|e| {
-            Error::SetDeviceAttribute(HypervisorDeviceError::SetDeviceAttribute(e.into()))
-        })?;
+        gic.set_device_attr(&gic_dist_attr)
+            .map_err(Error::SetDeviceAttribute)?;
     } else {
-        gic.get_device_attr(&mut gic_dist_attr).map_err(|e| {
-            Error::GetDeviceAttribute(HypervisorDeviceError::GetDeviceAttribute(e.into()))
-        })?;
+        gic.get_device_attr(&mut gic_dist_attr)
+            .map_err(Error::GetDeviceAttribute)?;
     }
     Ok(())
 }
 
 /// Get the distributor control register.
-pub fn read_ctlr(gic: &DeviceFd) -> Result<u32> {
+pub fn read_ctlr(gic: &Arc<dyn hypervisor::Device>) -> Result<u32> {
     let val: u32 = 0;
     dist_attr_access(gic, GICD_CTLR, &val, false)?;
     Ok(val)
 }
 
 /// Set the distributor control register.
-pub fn write_ctlr(gic: &DeviceFd, val: u32) -> Result<()> {
+pub fn write_ctlr(gic: &Arc<dyn hypervisor::Device>, val: u32) -> Result<()> {
     dist_attr_access(gic, GICD_CTLR, &val, true)
 }
 
-fn get_interrupts_num(gic: &DeviceFd) -> Result<u32> {
+fn get_interrupts_num(gic: &Arc<dyn hypervisor::Device>) -> Result<u32> {
     let num_irq = 0;
 
     let mut nr_irqs_attr = kvm_device_attr {
@@ -117,18 +120,12 @@ fn get_interrupts_num(gic: &DeviceFd) -> Result<u32> {
         addr: &num_irq as *const u32 as u64,
         flags: 0,
     };
-    gic.get_device_attr(&mut nr_irqs_attr).map_err(|e| {
-        Error::GetDeviceAttribute(HypervisorDeviceError::GetDeviceAttribute(e.into()))
-    })?;
+    gic.get_device_attr(&mut nr_irqs_attr)
+        .map_err(Error::GetDeviceAttribute)?;
     Ok(num_irq)
 }
 
-fn compute_reg_len(gic: &DeviceFd, reg: &DistReg, base: u32) -> Result<u32> {
-    // FIXME:
-    // Redefine some GIC constants to avoid the dependency on `layout` crate.
-    // This is temporary solution, will be fixed in future refactoring.
-    const LAYOUT_IRQ_BASE: u32 = 32;
-
+fn compute_reg_len(gic: &Arc<dyn hypervisor::Device>, reg: &DistReg, base: u32) -> Result<u32> {
     let mut end = base;
     let num_irq = get_interrupts_num(gic)?;
     if reg.length > 0 {
@@ -141,8 +138,8 @@ fn compute_reg_len(gic: &DeviceFd, reg: &DistReg, base: u32) -> Result<u32> {
         // This is the type of register that takes into account the number of interrupts
         // that the model has. It is also the type of register where
         // a register relates to multiple interrupts.
-        end = base + (reg.bpi as u32 * (num_irq - LAYOUT_IRQ_BASE) / 8);
-        if reg.bpi as u32 * (num_irq - LAYOUT_IRQ_BASE) % 8 > 0 {
+        end = base + (reg.bpi as u32 * (num_irq - IRQ_BASE) / 8);
+        if reg.bpi as u32 * (num_irq - IRQ_BASE) % 8 > 0 {
             end += REG_SIZE as u32;
         }
     }
@@ -150,12 +147,12 @@ fn compute_reg_len(gic: &DeviceFd, reg: &DistReg, base: u32) -> Result<u32> {
 }
 
 /// Set distributor registers of the GIC.
-pub fn set_dist_regs(gic: &DeviceFd, state: &[u32]) -> Result<()> {
+pub fn set_dist_regs(gic: &Arc<dyn hypervisor::Device>, state: &[u32]) -> Result<()> {
     let mut idx = 0;
 
     for dreg in VGIC_DIST_REGS {
         let mut base = dreg.base + REG_SIZE as u32 * dreg.bpi as u32;
-        let end = compute_reg_len(gic, dreg, base)?;
+        let end = compute_reg_len(gic, &dreg, base)?;
 
         while base < end {
             let val = state[idx];
@@ -167,12 +164,12 @@ pub fn set_dist_regs(gic: &DeviceFd, state: &[u32]) -> Result<()> {
     Ok(())
 }
 /// Get distributor registers of the GIC.
-pub fn get_dist_regs(gic: &DeviceFd) -> Result<Vec<u32>> {
+pub fn get_dist_regs(gic: &Arc<dyn hypervisor::Device>) -> Result<Vec<u32>> {
     let mut state = Vec::new();
 
     for dreg in VGIC_DIST_REGS {
         let mut base = dreg.base + REG_SIZE as u32 * dreg.bpi as u32;
-        let end = compute_reg_len(gic, dreg, base)?;
+        let end = compute_reg_len(gic, &dreg, base)?;
 
         while base < end {
             let val: u32 = 0;

arch/src/aarch64/gic/gicv3.rs

@@ -0,0 +1,275 @@
+// Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+// SPDX-License-Identifier: Apache-2.0
+
+pub mod kvm {
+    use crate::aarch64::gic::dist_regs::{get_dist_regs, read_ctlr, set_dist_regs, write_ctlr};
+    use crate::aarch64::gic::icc_regs::{get_icc_regs, set_icc_regs};
+    use crate::aarch64::gic::kvm::{save_pending_tables, KvmGicDevice};
+    use crate::aarch64::gic::redist_regs::{get_redist_regs, set_redist_regs};
+    use crate::aarch64::gic::GicDevice;
+    use crate::layout;
+    use anyhow::anyhow;
+    use hypervisor::kvm::kvm_bindings;
+    use std::any::Any;
+    use std::convert::TryInto;
+    use std::sync::Arc;
+    use std::{boxed::Box, result};
+    use vm_migration::{
+        Migratable, MigratableError, Pausable, Snapshot, SnapshotDataSection, Snapshottable,
+        Transportable,
+    };
+
+    /// Errors thrown while saving/restoring the GICv3.
+    #[derive(Debug)]
+    pub enum Error {
+        /// Error in saving RDIST pending tables into guest RAM.
+        SavePendingTables(crate::aarch64::gic::Error),
+        /// Error in saving GIC distributor registers.
+        SaveDistributorRegisters(crate::aarch64::gic::Error),
+        /// Error in restoring GIC distributor registers.
+        RestoreDistributorRegisters(crate::aarch64::gic::Error),
+        /// Error in saving GIC distributor control registers.
+        SaveDistributorCtrlRegisters(crate::aarch64::gic::Error),
+        /// Error in restoring GIC distributor control registers.
+        RestoreDistributorCtrlRegisters(crate::aarch64::gic::Error),
+        /// Error in saving GIC redistributor registers.
+        SaveRedistributorRegisters(crate::aarch64::gic::Error),
+        /// Error in restoring GIC redistributor registers.
+        RestoreRedistributorRegisters(crate::aarch64::gic::Error),
+        /// Error in saving GIC CPU interface registers.
+        SaveIccRegisters(crate::aarch64::gic::Error),
+        /// Error in restoring GIC CPU interface registers.
+        RestoreIccRegisters(crate::aarch64::gic::Error),
+    }
+
+    type Result<T> = result::Result<T, Error>;
+
+    pub struct KvmGicV3 {
+        /// The hypervisor agnostic device
+        device: Arc<dyn hypervisor::Device>,
+
+        /// Vector holding values of GICR_TYPER for each vCPU
+        gicr_typers: Vec<u64>,
+
+        /// GIC device properties, to be used for setting up the fdt entry
+        properties: [u64; 4],
+
+        /// Number of CPUs handled by the device
+        vcpu_count: u64,
+    }
+
+    #[derive(Serialize, Deserialize)]
+    pub struct Gicv3State {
+        dist: Vec<u32>,
+        rdist: Vec<u32>,
+        icc: Vec<u32>,
+        // special register that enables interrupts and affinity routing
+        gicd_ctlr: u32,
+    }
+
+    impl KvmGicV3 {
+        // Unfortunately bindgen omits defines that are based on other defines.
+        // See arch/arm64/include/uapi/asm/kvm.h file from the linux kernel.
+        pub const SZ_64K: u64 = 0x0001_0000;
+        const KVM_VGIC_V3_DIST_SIZE: u64 = KvmGicV3::SZ_64K;
+        const KVM_VGIC_V3_REDIST_SIZE: u64 = (2 * KvmGicV3::SZ_64K);
+
+        // Device trees specific constants
+        pub const ARCH_GIC_V3_MAINT_IRQ: u32 = 9;
+
+        /// Get the address of the GIC distributor.
+        pub fn get_dist_addr() -> u64 {
+            layout::MAPPED_IO_START - KvmGicV3::KVM_VGIC_V3_DIST_SIZE
+        }
+
+        /// Get the size of the GIC distributor.
+        pub fn get_dist_size() -> u64 {
+            KvmGicV3::KVM_VGIC_V3_DIST_SIZE
+        }
+
+        /// Get the address of the GIC redistributors.
+        pub fn get_redists_addr(vcpu_count: u64) -> u64 {
+            KvmGicV3::get_dist_addr() - KvmGicV3::get_redists_size(vcpu_count)
+        }
+
+        /// Get the size of the GIC redistributors.
+        pub fn get_redists_size(vcpu_count: u64) -> u64 {
+            vcpu_count * KvmGicV3::KVM_VGIC_V3_REDIST_SIZE
+        }
+
+        /// Save the state of GIC.
+        fn state(&self, gicr_typers: &[u64]) -> Result<Gicv3State> {
+            // Flush redistributors pending tables to guest RAM.
+            save_pending_tables(&self.device()).map_err(Error::SavePendingTables)?;
+
+            let gicd_ctlr =
+                read_ctlr(&self.device()).map_err(Error::SaveDistributorCtrlRegisters)?;
+
+            let dist_state =
+                get_dist_regs(&self.device()).map_err(Error::SaveDistributorRegisters)?;
+
+            let rdist_state = get_redist_regs(&self.device(), &gicr_typers)
+                .map_err(Error::SaveRedistributorRegisters)?;
+
+            let icc_state =
+                get_icc_regs(&self.device(), &gicr_typers).map_err(Error::SaveIccRegisters)?;
+
+            Ok(Gicv3State {
+                dist: dist_state,
+                rdist: rdist_state,
+                icc: icc_state,
+                gicd_ctlr,
+            })
+        }
+
+        /// Restore the state of GIC.
+        fn set_state(&mut self, gicr_typers: &[u64], state: &Gicv3State) -> Result<()> {
+            write_ctlr(&self.device(), state.gicd_ctlr)
+                .map_err(Error::RestoreDistributorCtrlRegisters)?;
+
+            set_dist_regs(&self.device(), &state.dist)
+                .map_err(Error::RestoreDistributorRegisters)?;
+
+            set_redist_regs(&self.device(), gicr_typers, &state.rdist)
+                .map_err(Error::RestoreRedistributorRegisters)?;
+
+            set_icc_regs(&self.device(), &gicr_typers, &state.icc)
+                .map_err(Error::RestoreIccRegisters)?;
+
+            Ok(())
+        }
+    }
+
+    impl GicDevice for KvmGicV3 {
+        fn device(&self) -> &Arc<dyn hypervisor::Device> {
+            &self.device
+        }
+
+        fn fdt_compatibility(&self) -> &str {
+            "arm,gic-v3"
+        }
+
+        fn fdt_maint_irq(&self) -> u32 {
+            KvmGicV3::ARCH_GIC_V3_MAINT_IRQ
+        }
+
+        fn device_properties(&self) -> &[u64] {
+            &self.properties
+        }
+
+        fn vcpu_count(&self) -> u64 {
+            self.vcpu_count
+        }
+
+        fn set_gicr_typers(&mut self, gicr_typers: Vec<u64>) {
+            self.gicr_typers = gicr_typers;
+        }
+
+        fn as_any_concrete_mut(&mut self) -> &mut dyn Any {
+            self
+        }
+    }
+
+    impl KvmGicDevice for KvmGicV3 {
+        fn version() -> u32 {
+            kvm_bindings::kvm_device_type_KVM_DEV_TYPE_ARM_VGIC_V3
+        }
+
+        fn create_device(
+            device: Arc<dyn hypervisor::Device>,
+            vcpu_count: u64,
+        ) -> Box<dyn GicDevice> {
+            Box::new(KvmGicV3 {
+                device,
+                gicr_typers: vec![0; vcpu_count.try_into().unwrap()],
+                properties: [
+                    KvmGicV3::get_dist_addr(),
+                    KvmGicV3::get_dist_size(),
+                    KvmGicV3::get_redists_addr(vcpu_count),
+                    KvmGicV3::get_redists_size(vcpu_count),
+                ],
+                vcpu_count,
+            })
+        }
+
+        fn init_device_attributes(
+            _vm: &Arc<dyn hypervisor::Vm>,
+            gic_device: &dyn GicDevice,
+        ) -> crate::aarch64::gic::Result<()> {
+            /* Setting up the distributor attribute.
+             We are placing the GIC below 1GB so we need to substract the size of the distributor.
+            */
+            Self::set_device_attribute(
+                gic_device.device(),
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ADDR,
+                u64::from(kvm_bindings::KVM_VGIC_V3_ADDR_TYPE_DIST),
+                &KvmGicV3::get_dist_addr() as *const u64 as u64,
+                0,
+            )?;
+
+            /* Setting up the redistributors' attribute.
+            We are calculating here the start of the redistributors address. We have one per CPU.
+            */
+            Self::set_device_attribute(
+                gic_device.device(),
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ADDR,
+                u64::from(kvm_bindings::KVM_VGIC_V3_ADDR_TYPE_REDIST),
+                &KvmGicV3::get_redists_addr(gic_device.vcpu_count()) as *const u64 as u64,
+                0,
+            )?;
+
+            Ok(())
+        }
+    }
+
+    pub const GIC_V3_SNAPSHOT_ID: &str = "gic-v3";
+    impl Snapshottable for KvmGicV3 {
+        fn id(&self) -> String {
+            GIC_V3_SNAPSHOT_ID.to_string()
+        }
+
+        fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
+            let gicr_typers = self.gicr_typers.clone();
+            let snapshot = serde_json::to_vec(&self.state(&gicr_typers).unwrap())
+                .map_err(|e| MigratableError::Snapshot(e.into()))?;
+
+            let mut gic_v3_snapshot = Snapshot::new(self.id().as_str());
+            gic_v3_snapshot.add_data_section(SnapshotDataSection {
+                id: format!("{}-section", self.id()),
+                snapshot,
+            });
+
+            Ok(gic_v3_snapshot)
+        }
+
+        fn restore(&mut self, snapshot: Snapshot) -> std::result::Result<(), MigratableError> {
+            if let Some(gic_v3_section) = snapshot
+                .snapshot_data
+                .get(&format!("{}-section", self.id()))
+            {
+                let gic_v3_state = match serde_json::from_slice(&gic_v3_section.snapshot) {
+                    Ok(state) => state,
+                    Err(error) => {
+                        return Err(MigratableError::Restore(anyhow!(
+                            "Could not deserialize GICv3 {}",
+                            error
+                        )))
+                    }
+                };
+
+                let gicr_typers = self.gicr_typers.clone();
+                return self.set_state(&gicr_typers, &gic_v3_state).map_err(|e| {
+                    MigratableError::Restore(anyhow!("Could not restore GICv3 state {:?}", e))
+                });
+            }
+
+            Err(MigratableError::Restore(anyhow!(
+                "Could not find GICv3 snapshot section"
+            )))
+        }
+    }
+
+    impl Pausable for KvmGicV3 {}
+    impl Transportable for KvmGicV3 {}
+    impl Migratable for KvmGicV3 {}
+}

arch/src/aarch64/gic/gicv3_its.rs

@@ -0,0 +1,147 @@
+// Copyright 2020 ARM Limited
+// SPDX-License-Identifier: Apache-2.0
+
+pub mod kvm {
+    use std::any::Any;
+    use std::convert::TryInto;
+    use std::sync::Arc;
+    use std::{boxed::Box, result};
+    type Result<T> = result::Result<T, Error>;
+    use crate::aarch64::gic::gicv3::kvm::KvmGicV3;
+    use crate::aarch64::gic::kvm::KvmGicDevice;
+    use crate::aarch64::gic::{Error, GicDevice};
+    use hypervisor::kvm::kvm_bindings;
+
+    pub struct KvmGicV3Its {
+        /// The hypervisor agnostic device
+        device: Arc<dyn hypervisor::Device>,
+
+        /// Vector holding values of GICR_TYPER for each vCPU
+        gicr_typers: Vec<u64>,
+
+        /// GIC device properties, to be used for setting up the fdt entry
+        gic_properties: [u64; 4],
+
+        /// MSI device properties, to be used for setting up the fdt entry
+        msi_properties: [u64; 2],
+
+        /// Number of CPUs handled by the device
+        vcpu_count: u64,
+    }
+
+    impl KvmGicV3Its {
+        const KVM_VGIC_V3_ITS_SIZE: u64 = (2 * KvmGicV3::SZ_64K);
+
+        fn get_msi_size() -> u64 {
+            KvmGicV3Its::KVM_VGIC_V3_ITS_SIZE
+        }
+
+        fn get_msi_addr(vcpu_count: u64) -> u64 {
+            KvmGicV3::get_redists_addr(vcpu_count) - KvmGicV3Its::get_msi_size()
+        }
+    }
+
+    impl GicDevice for KvmGicV3Its {
+        fn device(&self) -> &Arc<dyn hypervisor::Device> {
+            &self.device
+        }
+
+        fn fdt_compatibility(&self) -> &str {
+            "arm,gic-v3"
+        }
+
+        fn msi_compatible(&self) -> bool {
+            true
+        }
+
+        fn msi_compatibility(&self) -> &str {
+            "arm,gic-v3-its"
+        }
+
+        fn fdt_maint_irq(&self) -> u32 {
+            KvmGicV3::ARCH_GIC_V3_MAINT_IRQ
+        }
+
+        fn msi_properties(&self) -> &[u64] {
+            &self.msi_properties
+        }
+
+        fn device_properties(&self) -> &[u64] {
+            &self.gic_properties
+        }
+
+        fn vcpu_count(&self) -> u64 {
+            self.vcpu_count
+        }
+
+        fn set_gicr_typers(&mut self, gicr_typers: Vec<u64>) {
+            self.gicr_typers = gicr_typers;
+        }
+
+        fn as_any_concrete_mut(&mut self) -> &mut dyn Any {
+            self
+        }
+    }
+
+    impl KvmGicDevice for KvmGicV3Its {
+        fn version() -> u32 {
+            KvmGicV3::version()
+        }
+
+        fn create_device(
+            device: Arc<dyn hypervisor::Device>,
+            vcpu_count: u64,
+        ) -> Box<dyn GicDevice> {
+            Box::new(KvmGicV3Its {
+                device,
+                gicr_typers: vec![0; vcpu_count.try_into().unwrap()],
+                gic_properties: [
+                    KvmGicV3::get_dist_addr(),
+                    KvmGicV3::get_dist_size(),
+                    KvmGicV3::get_redists_addr(vcpu_count),
+                    KvmGicV3::get_redists_size(vcpu_count),
+                ],
+                msi_properties: [
+                    KvmGicV3Its::get_msi_addr(vcpu_count),
+                    KvmGicV3Its::get_msi_size(),
+                ],
+                vcpu_count,
+            })
+        }
+
+        fn init_device_attributes(
+            vm: &Arc<dyn hypervisor::Vm>,
+            gic_device: &dyn GicDevice,
+        ) -> Result<()> {
+            KvmGicV3::init_device_attributes(vm, gic_device)?;
+
+            let mut its_device = kvm_bindings::kvm_create_device {
+                type_: kvm_bindings::kvm_device_type_KVM_DEV_TYPE_ARM_VGIC_ITS,
+                fd: 0,
+                flags: 0,
+            };
+
+            let its_fd = vm
+                .create_device(&mut its_device)
+                .map_err(Error::CreateGic)?;
+
+            Self::set_device_attribute(
+                &its_fd,
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ADDR,
+                u64::from(kvm_bindings::KVM_VGIC_ITS_ADDR_TYPE),
+                &KvmGicV3Its::get_msi_addr(gic_device.vcpu_count()) as *const u64 as u64,
+                0,
+            )?;
+
+            Self::set_device_attribute(
+                &its_fd,
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_CTRL,
+                u64::from(kvm_bindings::KVM_DEV_ARM_VGIC_CTRL_INIT),
+                0,
+                0,
+            )?;
+
+            Ok(())
+        }
+    }
+}

arch/src/aarch64/gic/icc_regs.rs

@@ -1,16 +1,14 @@
-// Copyright 2022 Arm Limited (or its affiliates). All rights reserved.
 // Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 // SPDX-License-Identifier: Apache-2.0
 
-use crate::arch::aarch64::gic::{Error, Result};
-use crate::device::HypervisorDeviceError;
-use crate::kvm::kvm_bindings::{
+use super::{Error, Result};
+use hypervisor::kvm::kvm_bindings::{
     kvm_device_attr, KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS, KVM_REG_ARM64_SYSREG_CRM_MASK,
     KVM_REG_ARM64_SYSREG_CRM_SHIFT, KVM_REG_ARM64_SYSREG_CRN_MASK, KVM_REG_ARM64_SYSREG_CRN_SHIFT,
     KVM_REG_ARM64_SYSREG_OP0_MASK, KVM_REG_ARM64_SYSREG_OP0_SHIFT, KVM_REG_ARM64_SYSREG_OP1_MASK,
     KVM_REG_ARM64_SYSREG_OP1_SHIFT, KVM_REG_ARM64_SYSREG_OP2_MASK, KVM_REG_ARM64_SYSREG_OP2_SHIFT,
 };
-use kvm_ioctls::DeviceFd;
+use std::sync::Arc;
 
 const KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT: u32 = 32;
 const KVM_DEV_ARM_VGIC_V3_MPIDR_MASK: u64 = 0xffffffff << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT as u64;
@@ -61,7 +59,7 @@ SYS_ICC_AP1Rn_EL1!(SYS_ICC_AP1R1_EL1, 1);
 SYS_ICC_AP1Rn_EL1!(SYS_ICC_AP1R2_EL1, 2);
 SYS_ICC_AP1Rn_EL1!(SYS_ICC_AP1R3_EL1, 3);
 
-static VGIC_ICC_REGS: &[u64] = &[
+static VGIC_ICC_REGS: &'static [u64] = &[
     SYS_ICC_SRE_EL1,
     SYS_ICC_CTLR_EL1,
     SYS_ICC_IGRPEN0_EL1,
@@ -79,7 +77,13 @@ 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_access(
+    gic: &Arc<dyn hypervisor::Device>,
+    offset: u64,
+    typer: u64,
+    val: &u32,
+    set: bool,
+) -> Result<()> {
     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
@@ -87,19 +91,18 @@ fn icc_attr_access(gic: &DeviceFd, offset: u64, typer: u64, val: &u32, set: bool
         flags: 0,
     };
     if set {
-        gic.set_device_attr(&gic_icc_attr).map_err(|e| {
-            Error::SetDeviceAttribute(HypervisorDeviceError::SetDeviceAttribute(e.into()))
-        })?;
+        #[allow(clippy::unnecessary_mut_passed)]
+        gic.set_device_attr(&mut gic_icc_attr)
+            .map_err(Error::SetDeviceAttribute)?;
     } else {
-        gic.get_device_attr(&mut gic_icc_attr).map_err(|e| {
-            Error::GetDeviceAttribute(HypervisorDeviceError::GetDeviceAttribute(e.into()))
-        })?;
+        gic.get_device_attr(&mut gic_icc_attr)
+            .map_err(Error::GetDeviceAttribute)?;
     }
     Ok(())
 }
 
 /// Get ICC registers.
-pub fn get_icc_regs(gic: &DeviceFd, gicr_typer: &[u64]) -> Result<Vec<u32>> {
+pub fn get_icc_regs(gic: &Arc<dyn hypervisor::Device>, gicr_typer: &[u64]) -> Result<Vec<u32>> {
     let mut state: Vec<u32> = Vec::new();
     // We need this for the ICC_AP<m>R<n>_EL1 registers.
     let mut num_priority_bits = 0;
@@ -152,7 +155,11 @@ pub fn get_icc_regs(gic: &DeviceFd, gicr_typer: &[u64]) -> Result<Vec<u32>> {
 }
 
 /// Set ICC registers.
-pub fn set_icc_regs(gic: &DeviceFd, gicr_typer: &[u64], state: &[u32]) -> Result<()> {
+pub fn set_icc_regs(
+    gic: &Arc<dyn hypervisor::Device>,
+    gicr_typer: &[u64],
+    state: &[u32],
+) -> Result<()> {
     let mut num_priority_bits = 0;
     let mut idx = 0;
     for ix in gicr_typer {

arch/src/aarch64/gic/mod.rs

@@ -0,0 +1,211 @@
+// Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+// SPDX-License-Identifier: Apache-2.0
+
+pub mod dist_regs;
+pub mod gicv3;
+pub mod gicv3_its;
+pub mod icc_regs;
+pub mod redist_regs;
+
+pub use self::dist_regs::{get_dist_regs, read_ctlr, set_dist_regs, write_ctlr};
+pub use self::icc_regs::{get_icc_regs, set_icc_regs};
+pub use self::redist_regs::{get_redist_regs, set_redist_regs};
+use std::any::Any;
+use std::result;
+use std::sync::Arc;
+
+/// Errors thrown while setting up the GIC.
+#[derive(Debug)]
+pub enum Error {
+    /// Error while calling KVM ioctl for setting up the global interrupt controller.
+    CreateGic(hypervisor::HypervisorVmError),
+    /// Error while setting device attributes for the GIC.
+    SetDeviceAttribute(hypervisor::HypervisorDeviceError),
+    /// Error while getting device attributes for the GIC.
+    GetDeviceAttribute(hypervisor::HypervisorDeviceError),
+}
+type Result<T> = result::Result<T, Error>;
+
+pub trait GicDevice: Send {
+    /// Returns the hypervisor agnostic Device of the GIC device
+    fn device(&self) -> &Arc<dyn hypervisor::Device>;
+
+    /// Returns the fdt compatibility property of the device
+    fn fdt_compatibility(&self) -> &str;
+
+    /// Returns the maint_irq fdt property of the device
+    fn fdt_maint_irq(&self) -> u32;
+
+    /// Returns an array with GIC device properties
+    fn device_properties(&self) -> &[u64];
+
+    /// Returns the number of vCPUs this GIC handles
+    fn vcpu_count(&self) -> u64;
+
+    /// Returns whether the GIC device is MSI compatible or not
+    fn msi_compatible(&self) -> bool {
+        false
+    }
+
+    /// Returns the MSI compatibility property of the device
+    fn msi_compatibility(&self) -> &str {
+        ""
+    }
+
+    /// Returns the MSI reg property of the device
+    fn msi_properties(&self) -> &[u64] {
+        &[]
+    }
+
+    /// Get the values of GICR_TYPER for each vCPU.
+    fn set_gicr_typers(&mut self, gicr_typers: Vec<u64>);
+
+    /// Downcast the trait object to its concrete type.
+    fn as_any_concrete_mut(&mut self) -> &mut dyn Any;
+}
+
+pub mod kvm {
+    use super::GicDevice;
+    use super::Result;
+    use crate::aarch64::gic::gicv3_its::kvm::KvmGicV3Its;
+    use crate::layout;
+    use hypervisor::kvm::kvm_bindings;
+    use std::boxed::Box;
+    use std::sync::Arc;
+
+    /// Trait for GIC devices.
+    pub trait KvmGicDevice: Send + Sync + GicDevice {
+        /// Returns the GIC version of the device
+        fn version() -> u32;
+
+        /// Create the GIC device object
+        fn create_device(
+            device: Arc<dyn hypervisor::Device>,
+            vcpu_count: u64,
+        ) -> Box<dyn GicDevice>;
+
+        /// Setup the device-specific attributes
+        fn init_device_attributes(
+            vm: &Arc<dyn hypervisor::Vm>,
+            gic_device: &dyn GicDevice,
+        ) -> Result<()>;
+
+        /// Initialize a GIC device
+        fn init_device(vm: &Arc<dyn hypervisor::Vm>) -> Result<Arc<dyn hypervisor::Device>> {
+            let mut gic_device = kvm_bindings::kvm_create_device {
+                type_: Self::version(),
+                fd: 0,
+                flags: 0,
+            };
+
+            vm.create_device(&mut gic_device)
+                .map_err(super::Error::CreateGic)
+        }
+
+        /// Set a GIC device attribute
+        fn set_device_attribute(
+            device: &Arc<dyn hypervisor::Device>,
+            group: u32,
+            attr: u64,
+            addr: u64,
+            flags: u32,
+        ) -> Result<()> {
+            let attr = kvm_bindings::kvm_device_attr {
+                group,
+                attr,
+                addr,
+                flags,
+            };
+            device
+                .set_device_attr(&attr)
+                .map_err(super::Error::SetDeviceAttribute)?;
+
+            Ok(())
+        }
+
+        /// Get a GIC device attribute
+        fn get_device_attribute(
+            device: &Arc<dyn hypervisor::Device>,
+            group: u32,
+            attr: u64,
+            addr: u64,
+            flags: u32,
+        ) -> Result<()> {
+            let mut attr = kvm_bindings::kvm_device_attr {
+                group,
+                attr,
+                addr,
+                flags,
+            };
+            device
+                .get_device_attr(&mut attr)
+                .map_err(super::Error::GetDeviceAttribute)?;
+
+            Ok(())
+        }
+
+        /// Finalize the setup of a GIC device
+        fn finalize_device(gic_device: &dyn GicDevice) -> Result<()> {
+            /* We need to tell the kernel how many irqs to support with this vgic.
+             * See the `layout` module for details.
+             */
+            let nr_irqs: u32 = layout::IRQ_MAX - layout::IRQ_BASE + 1;
+            let nr_irqs_ptr = &nr_irqs as *const u32;
+            Self::set_device_attribute(
+                gic_device.device(),
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_NR_IRQS,
+                0,
+                nr_irqs_ptr as u64,
+                0,
+            )?;
+
+            /* Finalize the GIC.
+             * See https://code.woboq.org/linux/linux/virt/kvm/arm/vgic/vgic-kvm-device.c.html#211.
+             */
+            Self::set_device_attribute(
+                gic_device.device(),
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_CTRL,
+                u64::from(kvm_bindings::KVM_DEV_ARM_VGIC_CTRL_INIT),
+                0,
+                0,
+            )?;
+
+            Ok(())
+        }
+
+        /// Method to initialize the GIC device
+        #[allow(clippy::new_ret_no_self)]
+        fn new(vm: &Arc<dyn hypervisor::Vm>, vcpu_count: u64) -> Result<Box<dyn GicDevice>> {
+            let vgic_fd = Self::init_device(vm)?;
+
+            let device = Self::create_device(vgic_fd, vcpu_count);
+
+            Self::init_device_attributes(vm, &*device)?;
+
+            Self::finalize_device(&*device)?;
+
+            Ok(device)
+        }
+    }
+
+    /// Create a GICv3-ITS device.
+    ///
+    pub fn create_gic(vm: &Arc<dyn hypervisor::Vm>, vcpu_count: u64) -> Result<Box<dyn GicDevice>> {
+        debug!("creating a GICv3-ITS");
+        KvmGicV3Its::new(vm, vcpu_count)
+    }
+
+    /// Function that saves RDIST pending tables into guest RAM.
+    ///
+    /// The tables get flushed to guest RAM whenever the VM gets stopped.
+    pub fn save_pending_tables(gic: &Arc<dyn hypervisor::Device>) -> Result<()> {
+        let init_gic_attr = kvm_bindings::kvm_device_attr {
+            group: kvm_bindings::KVM_DEV_ARM_VGIC_GRP_CTRL,
+            attr: u64::from(kvm_bindings::KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES),
+            addr: 0,
+            flags: 0,
+        };
+        gic.set_device_attr(&init_gic_attr)
+            .map_err(super::Error::SetDeviceAttribute)
+    }
+}

arch/src/aarch64/gic/redist_regs.rs

@@ -1,18 +1,9 @@
-// Copyright 2022 Arm Limited (or its affiliates). All rights reserved.
 // Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 // SPDX-License-Identifier: Apache-2.0
 
-use crate::arch::aarch64::gic::{Error, Result};
-use crate::device::HypervisorDeviceError;
-use crate::kvm::kvm_bindings::{
-    kvm_device_attr, KVM_DEV_ARM_VGIC_GRP_REDIST_REGS, KVM_REG_ARM64, KVM_REG_ARM64_SYSREG,
-    KVM_REG_ARM64_SYSREG_OP0_MASK, KVM_REG_ARM64_SYSREG_OP0_SHIFT, KVM_REG_ARM64_SYSREG_OP2_MASK,
-    KVM_REG_ARM64_SYSREG_OP2_SHIFT, KVM_REG_SIZE_U64,
-};
-use crate::kvm::Register;
-use crate::kvm::VcpuKvmState;
-use crate::CpuState;
-use kvm_ioctls::DeviceFd;
+use super::{Error, Result};
+use hypervisor::kvm::kvm_bindings::{kvm_device_attr, KVM_DEV_ARM_VGIC_GRP_REDIST_REGS};
+use std::sync::Arc;
 
 // Relevant redistributor registers that we want to save/restore.
 const GICR_CTLR: u32 = 0x0000;
@@ -39,12 +30,6 @@ const GICR_ICFGR0: u32 = GICR_SGI_OFFSET + 0x0C00;
 const KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT: u32 = 32;
 const KVM_DEV_ARM_VGIC_V3_MPIDR_MASK: u64 = 0xffffffff << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT as u64;
 
-const KVM_ARM64_SYSREG_MPIDR_EL1: u64 = KVM_REG_ARM64 as u64
-    | KVM_REG_SIZE_U64 as u64
-    | KVM_REG_ARM64_SYSREG as u64
-    | (((3_u64) << KVM_REG_ARM64_SYSREG_OP0_SHIFT) & KVM_REG_ARM64_SYSREG_OP0_MASK as u64)
-    | (((5_u64) << KVM_REG_ARM64_SYSREG_OP2_SHIFT) & KVM_REG_ARM64_SYSREG_OP2_MASK as u64);
-
 /// This is how we represent the registers of a distributor.
 /// It is relrvant their offset from the base address of the
 /// distributor.
@@ -75,16 +60,16 @@ macro_rules! VGIC_RDIST_REG {
 }
 
 // List with relevant distributor registers that we will be restoring.
-static VGIC_RDIST_REGS: &[RdistReg] = &[
+static VGIC_RDIST_REGS: &'static [RdistReg] = &[
+    VGIC_RDIST_REG!(GICR_CTLR, 4),
     VGIC_RDIST_REG!(GICR_STATUSR, 4),
     VGIC_RDIST_REG!(GICR_WAKER, 4),
     VGIC_RDIST_REG!(GICR_PROPBASER, 8),
     VGIC_RDIST_REG!(GICR_PENDBASER, 8),
-    VGIC_RDIST_REG!(GICR_CTLR, 4),
 ];
 
 // List with relevant distributor registers that we will be restoring.
-static VGIC_SGI_REGS: &[RdistReg] = &[
+static VGIC_SGI_REGS: &'static [RdistReg] = &[
     VGIC_RDIST_REG!(GICR_IGROUPR0, 4),
     VGIC_RDIST_REG!(GICR_ICENABLER0, 4),
     VGIC_RDIST_REG!(GICR_ISENABLER0, 4),
@@ -96,30 +81,35 @@ static VGIC_SGI_REGS: &[RdistReg] = &[
     VGIC_RDIST_REG!(GICR_IPRIORITYR0, 32),
 ];
 
-fn redist_attr_access(gic: &DeviceFd, offset: u32, typer: u64, val: &u32, set: bool) -> Result<()> {
-    let mut gic_redist_attr = kvm_device_attr {
+fn redist_attr_access(
+    gic: &Arc<dyn hypervisor::Device>,
+    offset: u32,
+    typer: u64,
+    val: &u32,
+    set: bool,
+) -> Result<()> {
+    let mut gic_dist_attr = kvm_device_attr {
         group: KVM_DEV_ARM_VGIC_GRP_REDIST_REGS,
         attr: (typer & KVM_DEV_ARM_VGIC_V3_MPIDR_MASK) | (offset as u64), // this needs the mpidr
         addr: val as *const u32 as u64,
         flags: 0,
     };
     if set {
-        gic.set_device_attr(&gic_redist_attr).map_err(|e| {
-            Error::SetDeviceAttribute(HypervisorDeviceError::SetDeviceAttribute(e.into()))
-        })?;
+        #[allow(clippy::unnecessary_mut_passed)]
+        gic.set_device_attr(&mut gic_dist_attr)
+            .map_err(Error::SetDeviceAttribute)?;
     } else {
-        gic.get_device_attr(&mut gic_redist_attr).map_err(|e| {
-            Error::GetDeviceAttribute(HypervisorDeviceError::GetDeviceAttribute(e.into()))
-        })?;
+        gic.get_device_attr(&mut gic_dist_attr)
+            .map_err(Error::GetDeviceAttribute)?;
     }
     Ok(())
 }
 
 fn access_redists_aux(
-    gic: &DeviceFd,
+    gic: &Arc<dyn hypervisor::Device>,
     gicr_typer: &[u64],
     state: &mut Vec<u32>,
-    reg_list: &[RdistReg],
+    reg_list: &'static [RdistReg],
     idx: &mut usize,
     set: bool,
 ) -> Result<()> {
@@ -146,24 +136,28 @@ fn access_redists_aux(
 }
 
 /// Get redistributor registers.
-pub fn get_redist_regs(gic: &DeviceFd, gicr_typer: &[u64]) -> Result<Vec<u32>> {
+pub fn get_redist_regs(gic: &Arc<dyn hypervisor::Device>, gicr_typer: &[u64]) -> Result<Vec<u32>> {
     let mut state = Vec::new();
     let mut idx: usize = 0;
     access_redists_aux(
         gic,
-        gicr_typer,
+        &gicr_typer,
         &mut state,
         VGIC_RDIST_REGS,
         &mut idx,
         false,
     )?;
 
-    access_redists_aux(gic, gicr_typer, &mut state, VGIC_SGI_REGS, &mut idx, false)?;
+    access_redists_aux(gic, &gicr_typer, &mut state, VGIC_SGI_REGS, &mut idx, false)?;
     Ok(state)
 }
 
 /// Set redistributor registers.
-pub fn set_redist_regs(gic: &DeviceFd, gicr_typer: &[u64], state: &[u32]) -> Result<()> {
+pub fn set_redist_regs(
+    gic: &Arc<dyn hypervisor::Device>,
+    gicr_typer: &[u64],
+    state: &[u32],
+) -> Result<()> {
     let mut idx: usize = 0;
     let mut mut_state = state.to_owned();
     access_redists_aux(
@@ -183,35 +177,3 @@ pub fn set_redist_regs(gic: &DeviceFd, gicr_typer: &[u64], state: &[u32]) -> Res
         true,
     )
 }
-
-pub fn construct_gicr_typers(vcpu_states: &[CpuState]) -> Vec<u64> {
-    /* Pre-construct the GICR_TYPER:
-     * For our implementation:
-     *  Top 32 bits are the affinity value of the associated CPU
-     *  CommonLPIAff == 01 (redistributors with same Aff3 share LPI table)
-     *  Processor_Number == CPU index starting from 0
-     *  DPGS == 0 (GICR_CTLR.DPG* not supported)
-     *  Last == 1 if this is the last redistributor in a series of
-     *            contiguous redistributor pages
-     *  DirectLPI == 0 (direct injection of LPIs not supported)
-     *  VLPIS == 0 (virtual LPIs not supported)
-     *  PLPIS == 0 (physical LPIs not supported)
-     */
-    let mut gicr_typers: Vec<u64> = Vec::new();
-    for (index, state) in vcpu_states.iter().enumerate() {
-        let state: VcpuKvmState = state.clone().into();
-        let last = (index == vcpu_states.len() - 1) as u64;
-        // state.sys_regs is a big collection of system registers, including MIPDR_EL1
-        let mpidr: Vec<Register> = state
-            .sys_regs
-            .into_iter()
-            .filter(|reg| reg.id == KVM_ARM64_SYSREG_MPIDR_EL1)
-            .collect();
-        //calculate affinity
-        let mut cpu_affid = mpidr[0].addr & 1095233437695;
-        cpu_affid = ((cpu_affid & 0xFF00000000) >> 8) | (cpu_affid & 0xFFFFFF);
-        gicr_typers.push((cpu_affid << 32) | (1 << 24) | (index as u64) << 8 | (last << 4));
-    }
-
-    gicr_typers
-}

arch/src/aarch64/layout.rs

@@ -3,7 +3,7 @@
 // SPDX-License-Identifier: Apache-2.0
 
 //
-// Memory layout of AArch64 guest:
+// Memory layout of Aarch64 guest:
 //
 // Physical  +---------------------------------------------------------------+
 // address   |                                                               |
@@ -19,21 +19,15 @@
 // memory)   |                                                               |
 //           |                            DRAM                               |
 //           |                                                               |
+// 2GB       +---------------------------------------------------------------+
 //           |                                                               |
-// 4GB       +---------------------------------------------------------------+
-//           |                      32-bit devices hole                      |
-// 4GB-64M   +---------------------------------------------------------------+
+//           |                           Reserved                            |
 //           |                                                               |
-//           |                                                               |
-//           |                            DRAM                               |
-//           |                                                               |
-//           |                                                               |
-// 1GB       +---------------------------------------------------------------+
+// 1G+256M   +---------------------------------------------------------------+
 //           |                                                               |
 //           |                        PCI MMCONFIG space                     |
 //           |                                                               |
-// 768 M     +---------------------------------------------------------------+
-//           |                                                               |
+// 1GB       +---------------------------------------------------------------+
 //           |                                                               |
 //           |                           PCI MMIO space                      |
 //           |                                                               |
@@ -45,86 +39,40 @@
 //           |                                                               |
 //           |                    Reserved (now GIC is here)                 |
 //           |                                                               |
-//  4  M     +---------------------------------------------------------------+
-//           |                          UEFI flash                           |
 // 0GB       +---------------------------------------------------------------+
 //
 //
 
 use vm_memory::GuestAddress;
 
-/// 0x0 ~ 0x40_0000 (4 MiB) is reserved to UEFI
-/// UEFI binary size is required less than 3 MiB, reserving 4 MiB is enough.
-pub const UEFI_START: GuestAddress = GuestAddress(0);
-pub const UEFI_SIZE: u64 = 0x040_0000;
-
 /// Below this address will reside the GIC, above this address will reside the MMIO devices.
-const MAPPED_IO_START: GuestAddress = GuestAddress(0x0900_0000);
+pub const MAPPED_IO_START: u64 = 0x0900_0000;
 
-/// See kernel file arch/arm64/include/uapi/asm/kvm.h for the GIC related definitions.
-/// 0x08ff_0000 ~ 0x0900_0000 is reserved for GICv3 Distributor
-pub const GIC_V3_DIST_SIZE: u64 = 0x01_0000;
-pub const GIC_V3_DIST_START: GuestAddress = GuestAddress(MAPPED_IO_START.0 - GIC_V3_DIST_SIZE);
-/// Below 0x08ff_0000 is reserved for GICv3 Redistributor.
-/// The size defined here is for each vcpu.
-/// The total size is 'number_of_vcpu * GIC_V3_REDIST_SIZE'
-pub const GIC_V3_REDIST_SIZE: u64 = 0x02_0000;
-/// Below Redistributor area is GICv3 ITS
-pub const GIC_V3_ITS_SIZE: u64 = 0x02_0000;
+/// Space 0x0900_0000 ~ 0x1000_0000 is reserved for legacy devices.
+pub const LEGACY_SERIAL_MAPPED_IO_START: u64 = 0x0900_0000;
+pub const LEGACY_RTC_MAPPED_IO_START: u64 = 0x0901_0000;
+pub const LEGACY_GPIO_MAPPED_IO_START: u64 = 0x0902_0000;
 
-/// Space 0x0900_0000 ~ 0x0905_0000 is reserved for legacy devices.
-pub const LEGACY_SERIAL_MAPPED_IO_START: GuestAddress = MAPPED_IO_START;
-pub const LEGACY_RTC_MAPPED_IO_START: GuestAddress = GuestAddress(0x0901_0000);
-pub const LEGACY_GPIO_MAPPED_IO_START: GuestAddress = GuestAddress(0x0902_0000);
+/// Legacy space will be allocated at once whiling setting up legacy devices.
+pub const LEGACY_DEVICES_MAPPED_IO_SIZE: u64 = 0x0700_0000;
 
-/// Space 0x0905_0000 ~ 0x0906_0000 is reserved for pcie io address
-pub const MEM_PCI_IO_START: GuestAddress = GuestAddress(0x0905_0000);
-pub const MEM_PCI_IO_SIZE: u64 = 0x10000;
-
-/// Starting from 0x1000_0000 (256MiB) to 0x3000_0000 (768MiB) is used for PCIE MMIO
+/// Starting from 0x1000_0000 (256MiB), the 768MiB (ends at 1 GiB) is used for PCIE MMIO
 pub const MEM_32BIT_DEVICES_START: GuestAddress = GuestAddress(0x1000_0000);
-pub const MEM_32BIT_DEVICES_SIZE: u64 = 0x2000_0000;
+pub const MEM_32BIT_DEVICES_SIZE: u64 = 0x3000_0000;
 
 /// PCI MMCONFIG space (start: after the device space at 1 GiB, length: 256MiB)
-pub const PCI_MMCONFIG_START: GuestAddress = GuestAddress(0x3000_0000);
+pub const PCI_MMCONFIG_START: GuestAddress = GuestAddress(0x4000_0000);
 pub const PCI_MMCONFIG_SIZE: u64 = 256 << 20;
-// One bus with potentially 256 devices (32 slots x 8 functions).
-pub const PCI_MMIO_CONFIG_SIZE_PER_SEGMENT: u64 = 4096 * 256;
 
-/// Start of RAM.
-pub const RAM_START: GuestAddress = GuestAddress(0x4000_0000);
-
-/// 32-bit reserved area: 64MiB before 4GiB
-pub const MEM_32BIT_RESERVED_START: GuestAddress = GuestAddress(0xfc00_0000);
-pub const MEM_32BIT_RESERVED_SIZE: u64 = 0x0400_0000;
-
-/// TPM Address Range
-/// This Address range is specific to CRB Interface
-pub const TPM_START: GuestAddress = GuestAddress(0xfed4_0000);
-pub const TPM_SIZE: u64 = 0x1000;
-
-/// Start of 64-bit RAM.
-pub const RAM_64BIT_START: GuestAddress = GuestAddress(0x1_0000_0000);
+/// Start of RAM on 64 bit ARM.
+pub const RAM_64BIT_START: u64 = 0x8000_0000;
 
 /// Kernel command line maximum size.
 /// As per `arch/arm64/include/uapi/asm/setup.h`.
 pub const CMDLINE_MAX_SIZE: usize = 2048;
 
-/// FDT is at the beginning of RAM.
 /// Maximum size of the device tree blob as specified in https://www.kernel.org/doc/Documentation/arm64/booting.txt.
-pub const FDT_START: GuestAddress = RAM_START;
-pub const FDT_MAX_SIZE: u64 = 0x20_0000;
-
-/// Put ACPI table above dtb
-pub const ACPI_START: GuestAddress = GuestAddress(RAM_START.0 + FDT_MAX_SIZE);
-pub const ACPI_MAX_SIZE: u64 = 0x20_0000;
-pub const RSDP_POINTER: GuestAddress = ACPI_START;
-
-/// Kernel start after FDT and ACPI
-pub const KERNEL_START: GuestAddress = GuestAddress(ACPI_START.0 + ACPI_MAX_SIZE);
-
-/// Pci high memory base
-pub const PCI_HIGH_BASE: GuestAddress = GuestAddress(0x2_0000_0000);
+pub const FDT_MAX_SIZE: usize = 0x20_0000;
 
 // As per virt/kvm/arm/vgic/vgic-kvm-device.c we need
 // the number of interrupts our GIC will support to be:
@@ -132,8 +80,8 @@ pub const PCI_HIGH_BASE: GuestAddress = GuestAddress(0x2_0000_0000);
 // * less than 1023 and
 // * a multiple of 32.
 // We are setting up our interrupt controller to support a maximum of 256 interrupts.
-/// First usable interrupt on aarch64
-pub const IRQ_BASE: u32 = 32;
+/// First usable interrupt on aarch64.
+pub const IRQ_BASE: u32 = 0;
 
-/// Number of supported interrupts
-pub const IRQ_NUM: u32 = 256;
+/// Last usable interrupt on aarch64.
+pub const IRQ_MAX: u32 = 255;

arch/src/aarch64/mod.rs

@@ -4,51 +4,48 @@
 
 /// Module for the flattened device tree.
 pub mod fdt;
+/// Module for the global interrupt controller configuration.
+pub mod gic;
 /// Layout for this aarch64 system.
 pub mod layout;
-/// Module for system registers definition
+/// Logic for configuring aarch64 registers.
 pub mod regs;
-/// Module for loading UEFI binary.
-pub mod uefi;
 
 pub use self::fdt::DeviceInfoForFdt;
-use crate::{DeviceType, GuestMemoryMmap, NumaNodes, PciSpaceInfo, RegionType};
-use hypervisor::arch::aarch64::gic::Vgic;
-use log::{log_enabled, Level};
+use crate::DeviceType;
+use crate::RegionType;
+use aarch64::gic::GicDevice;
 use std::collections::HashMap;
-use std::convert::TryInto;
+use std::ffi::CStr;
 use std::fmt::Debug;
-use std::sync::{Arc, Mutex};
-use vm_memory::{Address, GuestAddress, GuestMemory, GuestUsize};
+use std::sync::Arc;
+use vm_memory::{
+    Address, GuestAddress, GuestAddressSpace, GuestMemory, GuestMemoryAtomic, GuestMemoryMmap,
+    GuestUsize,
+};
 
 /// Errors thrown while configuring aarch64 system.
 #[derive(Debug)]
 pub enum Error {
     /// Failed to create a FDT.
-    SetupFdt,
-
-    /// Failed to write FDT to memory.
-    WriteFdtToMemory(fdt::Error),
+    SetupFdt(fdt::Error),
 
     /// Failed to create a GIC.
-    SetupGic,
+    SetupGic(gic::Error),
 
     /// Failed to compute the initramfs address.
     InitramfsAddress,
 
     /// Error configuring the general purpose registers
-    RegsConfiguration(hypervisor::HypervisorCpuError),
+    RegsConfiguration(regs::Error),
 
     /// Error configuring the MPIDR register
     VcpuRegMpidr(hypervisor::HypervisorCpuError),
-
-    /// Error initializing PMU for vcpu
-    VcpuInitPmu,
 }
 
 impl From<Error> for super::Error {
     fn from(e: Error) -> super::Error {
-        super::Error::PlatformSpecific(e)
+        super::Error::AArch64Setup(e)
     }
 }
 
@@ -62,117 +59,84 @@ pub struct EntryPoint {
 
 /// Configure the specified VCPU, and return its MPIDR.
 pub fn configure_vcpu(
-    vcpu: &Arc<dyn hypervisor::Vcpu>,
+    fd: &Arc<dyn hypervisor::Vcpu>,
     id: u8,
     kernel_entry_point: Option<EntryPoint>,
+    vm_memory: &GuestMemoryAtomic<GuestMemoryMmap>,
 ) -> super::Result<u64> {
     if let Some(kernel_entry_point) = kernel_entry_point {
-        vcpu.setup_regs(
+        regs::setup_regs(
+            fd,
             id,
             kernel_entry_point.entry_addr.raw_value(),
-            super::layout::FDT_START.raw_value(),
+            &vm_memory.memory(),
         )
         .map_err(Error::RegsConfiguration)?;
     }
 
-    let mpidr = vcpu
-        .get_sys_reg(regs::MPIDR_EL1)
-        .map_err(Error::VcpuRegMpidr)?;
+    let mpidr = fd.read_mpidr().map_err(Error::VcpuRegMpidr)?;
     Ok(mpidr)
 }
 
 pub fn arch_memory_regions(size: GuestUsize) -> Vec<(GuestAddress, usize, RegionType)> {
-    let mut regions = vec![
-        // 0 MiB ~ 256 MiB: UEFI, GIC and legacy devices
+    vec![
+        // 0 ~ 256 MiB: Reserved
         (
             GuestAddress(0),
             layout::MEM_32BIT_DEVICES_START.0 as usize,
             RegionType::Reserved,
         ),
-        // 256 MiB ~ 768 MiB: MMIO space
+        // 256 MiB ~ 1 G: MMIO space
         (
             layout::MEM_32BIT_DEVICES_START,
             layout::MEM_32BIT_DEVICES_SIZE as usize,
             RegionType::SubRegion,
         ),
-        // 768 MiB ~ 1 GiB: reserved. The leading 256M for PCIe MMCONFIG space
+        // 1G  ~ 2G: reserved. The leading 256M for PCIe MMCONFIG space
         (
             layout::PCI_MMCONFIG_START,
-            layout::PCI_MMCONFIG_SIZE as usize,
+            (layout::RAM_64BIT_START - layout::PCI_MMCONFIG_START.0) as usize,
             RegionType::Reserved,
         ),
-    ];
-
-    let ram_32bit_space_size =
-        layout::MEM_32BIT_RESERVED_START.unchecked_offset_from(layout::RAM_START);
-
-    // RAM space
-    // Case1: guest memory fits before the gap
-    if size as u64 <= ram_32bit_space_size {
-        regions.push((layout::RAM_START, size as usize, RegionType::Ram));
-    // Case2: guest memory extends beyond the gap
-    } else {
-        // Push memory before the gap
-        regions.push((
-            layout::RAM_START,
-            ram_32bit_space_size as usize,
+        (
+            GuestAddress(layout::RAM_64BIT_START),
+            size as usize,
             RegionType::Ram,
-        ));
-        // Other memory is placed after 4GiB
-        regions.push((
-            layout::RAM_64BIT_START,
-            (size - ram_32bit_space_size) as usize,
-            RegionType::Ram,
-        ));
-    }
-
-    // Add the 32-bit reserved memory hole as a reserved region
-    regions.push((
-        layout::MEM_32BIT_RESERVED_START,
-        layout::MEM_32BIT_RESERVED_SIZE as usize,
-        RegionType::Reserved,
-    ));
-
-    regions
+        ),
+    ]
 }
 
 /// Configures the system and should be called once per vm before starting vcpu threads.
+///
+/// # Arguments
+///
+/// * `guest_mem` - The memory to be used by the guest.
+/// * `num_cpus` - Number of virtual CPUs the guest will have.
 #[allow(clippy::too_many_arguments)]
 pub fn configure_system<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::BuildHasher>(
+    vm: &Arc<dyn hypervisor::Vm>,
     guest_mem: &GuestMemoryMmap,
-    cmdline: &str,
+    cmdline_cstring: &CStr,
+    vcpu_count: u64,
     vcpu_mpidr: Vec<u64>,
-    vcpu_topology: Option<(u8, u8, u8)>,
     device_info: &HashMap<(DeviceType, String), T, S>,
     initrd: &Option<super::InitramfsConfig>,
-    pci_space_info: &[PciSpaceInfo],
-    virtio_iommu_bdf: Option<u32>,
-    gic_device: &Arc<Mutex<dyn Vgic>>,
-    numa_nodes: &NumaNodes,
-    pmu_supported: bool,
-) -> super::Result<()> {
-    let fdt_final = fdt::create_fdt(
+    pci_space_address: &(u64, u64),
+) -> super::Result<Box<dyn GicDevice>> {
+    let gic_device = gic::kvm::create_gic(vm, vcpu_count).map_err(Error::SetupGic)?;
+
+    fdt::create_fdt(
         guest_mem,
-        cmdline,
+        cmdline_cstring,
         vcpu_mpidr,
-        vcpu_topology,
         device_info,
-        gic_device,
+        &*gic_device,
         initrd,
-        pci_space_info,
-        numa_nodes,
-        virtio_iommu_bdf,
-        pmu_supported,
+        pci_space_address,
     )
-    .map_err(|_| Error::SetupFdt)?;
+    .map_err(Error::SetupFdt)?;
 
-    if log_enabled!(Level::Debug) {
-        fdt::print_fdt(&fdt_final);
-    }
-
-    fdt::write_fdt_to_memory(fdt_final, guest_mem).map_err(Error::WriteFdtToMemory)?;
-
-    Ok(())
+    Ok(gic_device)
 }
 
 /// Returns the memory address where the initramfs could be loaded.
@@ -181,33 +145,57 @@ pub fn initramfs_load_addr(
     initramfs_size: usize,
 ) -> super::Result<u64> {
     let round_to_pagesize = |size| (size + (super::PAGE_SIZE - 1)) & !(super::PAGE_SIZE - 1);
-    match guest_mem
-        .last_addr()
-        .checked_sub(round_to_pagesize(initramfs_size) as u64 - 1)
+    match GuestAddress(get_fdt_addr(&guest_mem))
+        .checked_sub(round_to_pagesize(initramfs_size) as u64)
     {
         Some(offset) => {
             if guest_mem.address_in_range(offset) {
                 Ok(offset.raw_value())
             } else {
-                Err(super::Error::PlatformSpecific(Error::InitramfsAddress))
+                Err(super::Error::AArch64Setup(Error::InitramfsAddress))
             }
         }
-        None => Err(super::Error::PlatformSpecific(Error::InitramfsAddress)),
+        None => Err(super::Error::AArch64Setup(Error::InitramfsAddress)),
     }
 }
 
-pub fn get_host_cpu_phys_bits() -> u8 {
-    // A dummy hypervisor created only for querying the host IPA size and will
-    // be freed after the query.
-    let hv = hypervisor::new().unwrap();
-    let host_cpu_phys_bits = hv.get_host_ipa_limit().try_into().unwrap();
-    if host_cpu_phys_bits == 0 {
-        // Host kernel does not support `get_host_ipa_limit`,
-        // we return the default value 40 here.
-        40
-    } else {
-        host_cpu_phys_bits
+/// Returns the memory address where the kernel could be loaded.
+pub fn get_kernel_start() -> u64 {
+    layout::RAM_64BIT_START
+}
+
+// Auxiliary function to get the address where the device tree blob is loaded.
+fn get_fdt_addr(mem: &GuestMemoryMmap) -> u64 {
+    // If the memory allocated is smaller than the size allocated for the FDT,
+    // we return the start of the DRAM so that
+    // we allow the code to try and load the FDT.
+
+    if let Some(addr) = mem.last_addr().checked_sub(layout::FDT_MAX_SIZE as u64 - 1) {
+        if mem.address_in_range(addr) {
+            return addr.raw_value();
+        }
     }
+
+    layout::RAM_64BIT_START
+}
+
+pub fn get_host_cpu_phys_bits() -> u8 {
+    // The value returned here is used to determine the physical address space size
+    // for a VM (IPA size).
+    // In recent kernel versions, the maximum IPA size supported by the host can be
+    // known by querying cap KVM_CAP_ARM_VM_IPA_SIZE. And the IPA size for a
+    // guest can be configured smaller.
+    // But in Cloud-Hypervisor we simply use the maximum value for the VM.
+    // Reference https://lwn.net/Articles/766767/.
+    //
+    // The correct way to query KVM_CAP_ARM_VM_IPA_SIZE is via rust-vmm/kvm-ioctls,
+    // which wraps all IOCTL's and provides easy interface to user hypervisors.
+    // For now the cap hasn't been supported. A separate patch will be submitted to
+    // rust-vmm to add it.
+    // So a hardcoded value is used here as a temporary solution.
+    // It will be replace once rust-vmm/kvm-ioctls is ready.
+    //
+    40
 }
 
 #[cfg(test)]
@@ -215,26 +203,40 @@ mod tests {
     use super::*;
 
     #[test]
-    fn test_arch_memory_regions_dram_2gb() {
-        let regions = arch_memory_regions((1usize << 31) as u64); //2GB
-        assert_eq!(5, regions.len());
-        assert_eq!(layout::RAM_START, regions[3].0);
-        assert_eq!((1usize << 31), regions[3].1);
+    fn test_arch_memory_regions_dram() {
+        let regions = arch_memory_regions((1usize << 32) as u64); //4GB
+        assert_eq!(4, regions.len());
+        assert_eq!(GuestAddress(layout::RAM_64BIT_START), regions[3].0);
+        assert_eq!(1usize << 32, regions[3].1);
         assert_eq!(RegionType::Ram, regions[3].2);
-        assert_eq!(RegionType::Reserved, regions[4].2);
     }
 
     #[test]
-    fn test_arch_memory_regions_dram_4gb() {
-        let regions = arch_memory_regions((1usize << 32) as u64); //4GB
-        let ram_32bit_space_size =
-            layout::MEM_32BIT_RESERVED_START.unchecked_offset_from(layout::RAM_START) as usize;
-        assert_eq!(6, regions.len());
-        assert_eq!(layout::RAM_START, regions[3].0);
-        assert_eq!(ram_32bit_space_size as usize, regions[3].1);
-        assert_eq!(RegionType::Ram, regions[3].2);
-        assert_eq!(RegionType::Reserved, regions[5].2);
-        assert_eq!(RegionType::Ram, regions[4].2);
-        assert_eq!(((1usize << 32) - ram_32bit_space_size), regions[4].1);
+    fn test_get_fdt_addr() {
+        let mut regions = Vec::new();
+
+        regions.push((
+            GuestAddress(layout::RAM_64BIT_START),
+            (layout::FDT_MAX_SIZE - 0x1000) as usize,
+        ));
+        let mem = GuestMemoryMmap::from_ranges(&regions).expect("Cannot initialize memory");
+        assert_eq!(get_fdt_addr(&mem), layout::RAM_64BIT_START);
+        regions.clear();
+
+        regions.push((
+            GuestAddress(layout::RAM_64BIT_START),
+            (layout::FDT_MAX_SIZE) as usize,
+        ));
+        let mem = GuestMemoryMmap::from_ranges(&regions).expect("Cannot initialize memory");
+        assert_eq!(get_fdt_addr(&mem), layout::RAM_64BIT_START);
+        regions.clear();
+
+        regions.push((
+            GuestAddress(layout::RAM_64BIT_START),
+            (layout::FDT_MAX_SIZE + 0x1000) as usize,
+        ));
+        let mem = GuestMemoryMmap::from_ranges(&regions).expect("Cannot initialize memory");
+        assert_eq!(get_fdt_addr(&mem), 0x1000 + layout::RAM_64BIT_START);
+        regions.clear();
     }
 }

arch/src/aarch64/regs.rs

@@ -1,44 +1,81 @@
-// Copyright 2022 Arm Limited (or its affiliates). All rights reserved.
+// Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 // SPDX-License-Identifier: Apache-2.0
+//
+// Portions Copyright 2017 The Chromium OS Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the THIRD-PARTY file.
 
-///
-/// AArch64 system register encoding:
-/// See https://developer.arm.com/documentation/ddi0487 (chapter D12)
-///
-///   31      22  21 20 19 18 16 15 12 11  8 7   5 4  0
-///  +----------+---+-----+-----+-----+-----+-----+----+
-///  |1101010100| L | op0 | op1 | CRn | CRm | op2 | Rt |
-///  +----------+---+-----+-----+-----+-----+-----+----+
-///
-/// Notes:
-/// - L and Rt are reserved as implementation defined fields, ignored.
-///
-const SYSREG_HEAD: u32 = 0b1101010100u32 << 22;
-const SYSREG_OP0_SHIFT: u32 = 19;
-const SYSREG_OP0_MASK: u32 = 0b11u32 << 19;
-const SYSREG_OP1_SHIFT: u32 = 16;
-const SYSREG_OP1_MASK: u32 = 0b111u32 << 16;
-const SYSREG_CRN_SHIFT: u32 = 12;
-const SYSREG_CRN_MASK: u32 = 0b1111u32 << 12;
-const SYSREG_CRM_SHIFT: u32 = 8;
-const SYSREG_CRM_MASK: u32 = 0b1111u32 << 8;
-const SYSREG_OP2_SHIFT: u32 = 5;
-const SYSREG_OP2_MASK: u32 = 0b111u32 << 5;
+use super::get_fdt_addr;
+use hypervisor::kvm::kvm_bindings::{
+    kvm_regs, user_pt_regs, KVM_REG_ARM64, KVM_REG_ARM_CORE, KVM_REG_SIZE_U64,
+};
+use hypervisor::{arm64_core_reg_id, offset__of};
+use std::sync::Arc;
+use std::{mem, result};
+use vm_memory::GuestMemoryMmap;
 
-/// Define the ID of system registers
-#[macro_export]
-macro_rules! arm64_sys_reg {
-    ($name: tt, $op0: tt, $op1: tt, $crn: tt, $crm: tt, $op2: tt) => {
-        pub const $name: u32 = SYSREG_HEAD
-            | ((($op0 as u32) << SYSREG_OP0_SHIFT) & SYSREG_OP0_MASK as u32)
-            | ((($op1 as u32) << SYSREG_OP1_SHIFT) & SYSREG_OP1_MASK as u32)
-            | ((($crn as u32) << SYSREG_CRN_SHIFT) & SYSREG_CRN_MASK as u32)
-            | ((($crm as u32) << SYSREG_CRM_SHIFT) & SYSREG_CRM_MASK as u32)
-            | ((($op2 as u32) << SYSREG_OP2_SHIFT) & SYSREG_OP2_MASK as u32);
-    };
+/// Errors thrown while setting aarch64 registers.
+#[derive(Debug)]
+pub enum Error {
+    /// Failed to set core register (PC, PSTATE or general purpose ones).
+    SetCoreRegister(hypervisor::HypervisorCpuError),
+    /// Failed to get a system register.
+    GetSysRegister(hypervisor::HypervisorCpuError),
 }
+type Result<T> = result::Result<T, Error>;
 
-arm64_sys_reg!(MPIDR_EL1, 3, 0, 0, 0, 5);
-arm64_sys_reg!(ID_AA64MMFR0_EL1, 3, 0, 0, 7, 0);
-arm64_sys_reg!(TTBR1_EL1, 3, 0, 2, 0, 1);
-arm64_sys_reg!(TCR_EL1, 3, 0, 2, 0, 2);
+#[allow(non_upper_case_globals)]
+// PSR (Processor State Register) bits.
+// Taken from arch/arm64/include/uapi/asm/ptrace.h.
+const PSR_MODE_EL1h: u64 = 0x0000_0005;
+const PSR_F_BIT: u64 = 0x0000_0040;
+const PSR_I_BIT: u64 = 0x0000_0080;
+const PSR_A_BIT: u64 = 0x0000_0100;
+const PSR_D_BIT: u64 = 0x0000_0200;
+// Taken from arch/arm64/kvm/inject_fault.c.
+const PSTATE_FAULT_BITS_64: u64 = PSR_MODE_EL1h | PSR_A_BIT | PSR_F_BIT | PSR_I_BIT | PSR_D_BIT;
+
+/// Configure core registers for a given CPU.
+///
+/// # Arguments
+///
+/// * `vcpu` - Structure for the VCPU that holds the VCPU's fd.
+/// * `cpu_id` - Index of current vcpu.
+/// * `boot_ip` - Starting instruction pointer.
+/// * `mem` - Reserved DRAM for current VM.
+pub fn setup_regs(
+    vcpu: &Arc<dyn hypervisor::Vcpu>,
+    cpu_id: u8,
+    boot_ip: u64,
+    mem: &GuestMemoryMmap,
+) -> Result<()> {
+    let kreg_off = offset__of!(kvm_regs, regs);
+
+    // Get the register index of the PSTATE (Processor State) register.
+    let pstate = offset__of!(user_pt_regs, pstate) + kreg_off;
+    vcpu.set_reg(
+        arm64_core_reg_id!(KVM_REG_SIZE_U64, pstate),
+        PSTATE_FAULT_BITS_64,
+    )
+    .map_err(Error::SetCoreRegister)?;
+
+    // Other vCPUs are powered off initially awaiting PSCI wakeup.
+    if cpu_id == 0 {
+        // Setting the PC (Processor Counter) to the current program address (kernel address).
+        let pc = offset__of!(user_pt_regs, pc) + kreg_off;
+        vcpu.set_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, pc), boot_ip as u64)
+            .map_err(Error::SetCoreRegister)?;
+
+        // Last mandatory thing to set -> the address pointing to the FDT (also called DTB).
+        // "The device tree blob (dtb) must be placed on an 8-byte boundary and must
+        // not exceed 2 megabytes in size." -> https://www.kernel.org/doc/Documentation/arm64/booting.txt.
+        // We are choosing to place it the end of DRAM. See `get_fdt_addr`.
+        let regs0 = offset__of!(user_pt_regs, regs) + kreg_off;
+        vcpu.set_reg(
+            arm64_core_reg_id!(KVM_REG_SIZE_U64, regs0),
+            get_fdt_addr(mem) as u64,
+        )
+        .map_err(Error::SetCoreRegister)?;
+    }
+    Ok(())
+}

arch/src/aarch64/uefi.rs

@@ -1,41 +0,0 @@
-// Copyright 2020 Arm Limited (or its affiliates). All rights reserved.
-
-use std::io::{Read, Seek, SeekFrom};
-use std::result;
-use vm_memory::{Bytes, GuestAddress, GuestMemory};
-
-/// Errors thrown while loading UEFI binary
-#[derive(Debug)]
-pub enum Error {
-    /// Unable to seek to UEFI image start.
-    SeekUefiStart,
-    /// Unable to seek to UEFI image end.
-    SeekUefiEnd,
-    /// UEFI image too big.
-    UefiTooBig,
-    /// Unable to read UEFI image
-    ReadUefiImage,
-}
-type Result<T> = result::Result<T, Error>;
-
-pub fn load_uefi<F, M: GuestMemory>(
-    guest_mem: &M,
-    guest_addr: GuestAddress,
-    uefi_image: &mut F,
-) -> Result<()>
-where
-    F: Read + Seek,
-{
-    let uefi_size = uefi_image
-        .seek(SeekFrom::End(0))
-        .map_err(|_| Error::SeekUefiEnd)? as usize;
-
-    // edk2 image on virtual platform is smaller than 3M
-    if uefi_size > 0x300000 {
-        return Err(Error::UefiTooBig);
-    }
-    uefi_image.rewind().map_err(|_| Error::SeekUefiStart)?;
-    guest_mem
-        .read_exact_from(guest_addr, uefi_image, uefi_size)
-        .map_err(|_| Error::ReadUefiImage)
-}

arch/src/lib.rs

@@ -6,47 +6,56 @@
 
 //! Implements platform specific functionality.
 //! Supported platforms: x86_64, aarch64.
+#![allow(clippy::transmute_ptr_to_ptr, clippy::redundant_static_lifetimes)]
 
+extern crate anyhow;
+extern crate byteorder;
+extern crate hypervisor;
+extern crate libc;
 #[macro_use]
 extern crate log;
+#[cfg(feature = "acpi")]
+extern crate acpi_tables;
+extern crate arch_gen;
+extern crate linux_loader;
+extern crate serde;
+extern crate vm_memory;
+extern crate vm_migration;
+#[cfg(target_arch = "aarch64")]
+#[macro_use]
+extern crate serde_derive;
+extern crate serde_json;
+extern crate thiserror;
 
-#[cfg(target_arch = "x86_64")]
-use crate::x86_64::SgxEpcSection;
-use serde::{Deserialize, Serialize};
-use std::collections::BTreeMap;
 use std::fmt;
 use std::result;
-use std::sync::Arc;
-use thiserror::Error;
-use versionize::{VersionMap, Versionize, VersionizeError, VersionizeResult};
-use versionize_derive::Versionize;
-use vm_migration::VersionMapped;
-
-type GuestMemoryMmap = vm_memory::GuestMemoryMmap<vm_memory::bitmap::AtomicBitmap>;
-type GuestRegionMmap = vm_memory::GuestRegionMmap<vm_memory::bitmap::AtomicBitmap>;
 
 /// Type for returning error code.
-#[derive(Debug, Error)]
+#[derive(Debug)]
 pub enum Error {
     #[cfg(target_arch = "x86_64")]
-    #[error("Platform specific error (x86_64): {0:?}")]
-    PlatformSpecific(x86_64::Error),
+    /// X86_64 specific error triggered during system configuration.
+    X86_64Setup(x86_64::Error),
     #[cfg(target_arch = "aarch64")]
-    #[error("Platform specific error (aarch64): {0:?}")]
-    PlatformSpecific(aarch64::Error),
-    #[error("The memory map table extends past the end of guest memory")]
+    /// AArch64 specific error triggered during system configuration.
+    AArch64Setup(aarch64::Error),
+    /// The zero page extends past the end of guest_mem.
+    ZeroPagePastRamEnd,
+    /// Error writing the zero page of guest memory.
+    ZeroPageSetup(vm_memory::GuestMemoryError),
+    /// The memory map table extends past the end of guest memory.
     MemmapTablePastRamEnd,
-    #[error("Error writing memory map table to guest memory")]
+    /// Error writing memory map table to guest memory.
     MemmapTableSetup,
-    #[error("The hvm_start_info structure extends past the end of guest memory")]
+    /// The hvm_start_info structure extends past the end of guest memory.
     StartInfoPastRamEnd,
-    #[error("Error writing hvm_start_info to guest memory")]
+    /// Error writing hvm_start_info to guest memory.
     StartInfoSetup,
-    #[error("Failed to compute initramfs address")]
+    /// Failed to compute initramfs address.
     InitramfsAddress,
-    #[error("Error writing module entry to guest memory: {0}")]
-    ModlistSetup(#[source] vm_memory::GuestMemoryError),
-    #[error("RSDP extends past the end of guest memory")]
+    /// Error writing module entry to guest memory.
+    ModlistSetup(vm_memory::GuestMemoryError),
+    /// RSDP Beyond Guest Memory
     RsdpPastRamEnd,
 }
 
@@ -54,7 +63,7 @@ pub enum Error {
 pub type Result<T> = result::Result<T, Error>;
 
 /// Type for memory region types.
-#[derive(Clone, Copy, PartialEq, Eq, Debug, Serialize, Deserialize, Versionize)]
+#[derive(PartialEq, Debug)]
 pub enum RegionType {
     /// RAM type
     Ram,
@@ -72,8 +81,6 @@ pub enum RegionType {
     Reserved,
 }
 
-impl VersionMapped for RegionType {}
-
 /// Module for aarch64 related functionality.
 #[cfg(target_arch = "aarch64")]
 pub mod aarch64;
@@ -81,8 +88,8 @@ pub mod aarch64;
 #[cfg(target_arch = "aarch64")]
 pub use aarch64::{
     arch_memory_regions, configure_system, configure_vcpu, fdt::DeviceInfoForFdt,
-    get_host_cpu_phys_bits, initramfs_load_addr, layout, layout::CMDLINE_MAX_SIZE,
-    layout::IRQ_BASE, uefi, EntryPoint,
+    get_host_cpu_phys_bits, get_kernel_start, initramfs_load_addr, layout,
+    layout::CMDLINE_MAX_SIZE, layout::IRQ_BASE, layout::IRQ_MAX, EntryPoint,
 };
 
 #[cfg(target_arch = "x86_64")]
@@ -90,9 +97,9 @@ pub mod x86_64;
 
 #[cfg(target_arch = "x86_64")]
 pub use x86_64::{
-    arch_memory_regions, configure_system, configure_vcpu, generate_common_cpuid,
-    get_host_cpu_phys_bits, initramfs_load_addr, layout, layout::CMDLINE_MAX_SIZE,
-    layout::CMDLINE_START, regs, CpuidFeatureEntry, EntryPoint,
+    arch_memory_regions, configure_system, configure_vcpu, get_host_cpu_phys_bits,
+    initramfs_load_addr, layout, layout::CMDLINE_MAX_SIZE, layout::CMDLINE_START, regs,
+    BootProtocol, CpuidPatch, CpuidReg, EntryPoint,
 };
 
 /// Safe wrapper for `sysconf(_SC_PAGESIZE)`.
@@ -103,19 +110,6 @@ fn pagesize() -> usize {
     unsafe { libc::sysconf(libc::_SC_PAGESIZE) as usize }
 }
 
-#[derive(Clone, Default)]
-pub struct NumaNode {
-    pub memory_regions: Vec<Arc<GuestRegionMmap>>,
-    pub hotplug_regions: Vec<Arc<GuestRegionMmap>>,
-    pub cpus: Vec<u8>,
-    pub distances: BTreeMap<u32, u8>,
-    pub memory_zones: Vec<String>,
-    #[cfg(target_arch = "x86_64")]
-    pub sgx_epc_sections: Vec<SgxEpcSection>,
-}
-
-pub type NumaNodes = BTreeMap<u32, NumaNode>;
-
 /// Type for passing information about the initramfs in the guest memory.
 pub struct InitramfsConfig {
     /// Load address of initramfs in guest memory
@@ -145,7 +139,7 @@ pub const PAGE_SIZE: usize = 4096;
 
 impl fmt::Display for DeviceType {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        write!(f, "{self:?}")
+        write!(f, "{:?}", self)
     }
 }
 
@@ -154,20 +148,9 @@ impl fmt::Display for DeviceType {
 #[cfg(target_arch = "aarch64")]
 pub struct MmioDeviceInfo {
     pub addr: u64,
-    pub len: u64,
     pub irq: u32,
 }
 
-/// Structure to describe PCI space information
-#[derive(Clone, Debug)]
-#[cfg(target_arch = "aarch64")]
-pub struct PciSpaceInfo {
-    pub pci_segment_id: u16,
-    pub mmio_config_address: u64,
-    pub pci_device_space_start: u64,
-    pub pci_device_space_size: u64,
-}
-
 #[cfg(target_arch = "aarch64")]
 impl DeviceInfoForFdt for MmioDeviceInfo {
     fn addr(&self) -> u64 {
@@ -177,6 +160,6 @@ impl DeviceInfoForFdt for MmioDeviceInfo {
         self.irq
     }
     fn length(&self) -> u64 {
-        self.len
+        4096
     }
 }

arch/src/x86_64/interrupts.rs

@@ -5,9 +5,19 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE-BSD-3-Clause file.
 
+use byteorder::{LittleEndian, ReadBytesExt, WriteBytesExt};
+use hypervisor::x86_64::LapicState;
+use std::io::Cursor;
+use std::mem;
 use std::result;
 use std::sync::Arc;
 
+#[derive(Debug)]
+pub enum Error {
+    GetLapic(anyhow::Error),
+    SetLapic(anyhow::Error),
+}
+
 pub type Result<T> = result::Result<T, hypervisor::HypervisorCpuError>;
 
 // Defines poached from apicdef.h kernel header.
@@ -16,6 +26,32 @@ pub const APIC_LVT1: usize = 0x360;
 pub const APIC_MODE_NMI: u32 = 0x4;
 pub const APIC_MODE_EXTINT: u32 = 0x7;
 
+pub fn get_klapic_reg(klapic: &LapicState, reg_offset: usize) -> u32 {
+    let sliceu8 = unsafe {
+        // This array is only accessed as parts of a u32 word, so interpret it as a u8 array.
+        // Cursors are only readable on arrays of u8, not i8(c_char).
+        mem::transmute::<&[i8], &[u8]>(&klapic.regs[reg_offset..])
+    };
+    let mut reader = Cursor::new(sliceu8);
+    // Following call can't fail if the offsets defined above are correct.
+    reader
+        .read_u32::<LittleEndian>()
+        .expect("Failed to read klapic register")
+}
+
+pub fn set_klapic_reg(klapic: &mut LapicState, reg_offset: usize, value: u32) {
+    let sliceu8 = unsafe {
+        // This array is only accessed as parts of a u32 word, so interpret it as a u8 array.
+        // Cursors are only readable on arrays of u8, not i8(c_char).
+        mem::transmute::<&mut [i8], &mut [u8]>(&mut klapic.regs[reg_offset..])
+    };
+    let mut writer = Cursor::new(sliceu8);
+    // Following call can't fail if the offsets defined above are correct.
+    writer
+        .write_u32::<LittleEndian>(value)
+        .expect("Failed to write klapic register")
+}
+
 pub fn set_apic_delivery_mode(reg: u32, mode: u32) -> u32 {
     ((reg) & !0x700) | ((mode) << 8)
 }
@@ -27,13 +63,60 @@ pub fn set_apic_delivery_mode(reg: u32, mode: u32) -> u32 {
 pub fn set_lint(vcpu: &Arc<dyn hypervisor::Vcpu>) -> Result<()> {
     let mut klapic = vcpu.get_lapic()?;
 
-    let lvt_lint0 = klapic.get_klapic_reg(APIC_LVT0);
-    klapic.set_klapic_reg(
+    let lvt_lint0 = get_klapic_reg(&klapic, APIC_LVT0);
+    set_klapic_reg(
+        &mut klapic,
         APIC_LVT0,
         set_apic_delivery_mode(lvt_lint0, APIC_MODE_EXTINT),
     );
-    let lvt_lint1 = klapic.get_klapic_reg(APIC_LVT1);
-    klapic.set_klapic_reg(APIC_LVT1, set_apic_delivery_mode(lvt_lint1, APIC_MODE_NMI));
+    let lvt_lint1 = get_klapic_reg(&klapic, APIC_LVT1);
+    set_klapic_reg(
+        &mut klapic,
+        APIC_LVT1,
+        set_apic_delivery_mode(lvt_lint1, APIC_MODE_NMI),
+    );
 
     vcpu.set_lapic(&klapic)
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    const KVM_APIC_REG_SIZE: usize = 0x400;
+
+    #[test]
+    fn test_set_and_get_klapic_reg() {
+        let reg_offset = 0x340;
+        let mut klapic = LapicState::default();
+        set_klapic_reg(&mut klapic, reg_offset, 3);
+        let value = get_klapic_reg(&klapic, reg_offset);
+        assert_eq!(value, 3);
+    }
+
+    #[test]
+    #[should_panic]
+    fn test_set_and_get_klapic_out_of_bounds() {
+        let reg_offset = KVM_APIC_REG_SIZE + 10;
+        let mut klapic = LapicState::default();
+        set_klapic_reg(&mut klapic, reg_offset, 3);
+    }
+
+    #[test]
+    fn test_apic_delivery_mode() {
+        let mut v: Vec<u32> = Vec::new();
+        v.resize(20, 0);
+
+        unsafe {
+            assert_eq!(
+                libc::getrandom(v.as_mut_ptr() as *mut _ as *mut libc::c_void, 80, 0),
+                80
+            );
+        }
+
+        v.iter_mut()
+            .for_each(|x| *x = set_apic_delivery_mode(*x, 2));
+        let after: Vec<u32> = v.iter().map(|x| ((*x & !0x700) | ((2) << 8))).collect();
+        assert_eq!(v, after);
+    }
+}

arch/src/x86_64/layout.rs

@@ -24,9 +24,6 @@ pub const LOW_RAM_START: GuestAddress = GuestAddress(0x0);
 
 // == Fixed addresses within the "Low RAM" range: ==
 
-// Location of EBDA address
-pub const EBDA_POINTER: GuestAddress = GuestAddress(0x40e);
-
 // Initial GDT/IDT needed to boot kernel
 pub const BOOT_GDT_START: GuestAddress = GuestAddress(0x500);
 pub const BOOT_IDT_START: GuestAddress = GuestAddress(0x520);
@@ -82,9 +79,9 @@ pub const HIGH_RAM_START: GuestAddress = GuestAddress(0x100000);
 
 // == No fixed addresses in the "High RAM" range ==
 
-// ** 32-bit reserved area (start: 3GiB, length: 896MiB) **
+// ** 32-bit reserved area (start: 3GiB, length: 1GiB) **
 pub const MEM_32BIT_RESERVED_START: GuestAddress = GuestAddress(0xc000_0000);
-pub const MEM_32BIT_RESERVED_SIZE: u64 = PCI_MMCONFIG_SIZE + MEM_32BIT_DEVICES_SIZE;
+pub const MEM_32BIT_RESERVED_SIZE: u64 = 1024 << 20;
 
 // == Fixed constants within the "32-bit reserved" range ==
 
@@ -96,21 +93,6 @@ pub const MEM_32BIT_DEVICES_SIZE: u64 = 640 << 20;
 pub const PCI_MMCONFIG_START: GuestAddress =
     GuestAddress(MEM_32BIT_DEVICES_START.0 + MEM_32BIT_DEVICES_SIZE);
 pub const PCI_MMCONFIG_SIZE: u64 = 256 << 20;
-// One bus with potentially 256 devices (32 slots x 8 functions).
-pub const PCI_MMIO_CONFIG_SIZE_PER_SEGMENT: u64 = 4096 * 256;
-
-// TSS is 3 pages after the PCI MMCONFIG space
-pub const KVM_TSS_START: GuestAddress = GuestAddress(PCI_MMCONFIG_START.0 + PCI_MMCONFIG_SIZE);
-pub const KVM_TSS_SIZE: u64 = (3 * 4) << 10;
-
-// Identity map is a one page region after the TSS
-pub const KVM_IDENTITY_MAP_START: GuestAddress = GuestAddress(KVM_TSS_START.0 + KVM_TSS_SIZE);
-pub const KVM_IDENTITY_MAP_SIZE: u64 = 4 << 10;
-
-/// TPM Address Range
-/// This Address range is specific to CRB Interface
-pub const TPM_START: GuestAddress = GuestAddress(0xfed4_0000);
-pub const TPM_SIZE: u64 = 0x1000;
 
 // IOAPIC
 pub const IOAPIC_START: GuestAddress = GuestAddress(0xfec0_0000);
@@ -119,6 +101,9 @@ pub const IOAPIC_SIZE: u64 = 0x20;
 // APIC
 pub const APIC_START: GuestAddress = GuestAddress(0xfee0_0000);
 
+/// Address for the TSS setup.
+pub const KVM_TSS_ADDRESS: GuestAddress = GuestAddress(0xfffb_d000);
+
 // == End of "32-bit reserved" range. ==
 
 // ** 64-bit RAM start (start: 4GiB, length: varies) **

arch/src/x86_64/mpspec.rs

@@ -1,112 +0,0 @@
-// 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.
-
-pub const MP_PROCESSOR: ::std::os::raw::c_uint = 0;
-pub const MP_BUS: ::std::os::raw::c_uint = 1;
-pub const MP_IOAPIC: ::std::os::raw::c_uint = 2;
-pub const MP_INTSRC: ::std::os::raw::c_uint = 3;
-pub const MP_LINTSRC: ::std::os::raw::c_uint = 4;
-pub const CPU_ENABLED: ::std::os::raw::c_uint = 1;
-pub const CPU_BOOTPROCESSOR: ::std::os::raw::c_uint = 2;
-pub const MPC_APIC_USABLE: ::std::os::raw::c_uint = 1;
-pub const MP_IRQDIR_DEFAULT: ::std::os::raw::c_uint = 0;
-
-#[repr(C)]
-#[derive(Debug, Default, Copy, Clone)]
-pub struct mpf_intel {
-    pub signature: [::std::os::raw::c_char; 4usize],
-    pub physptr: ::std::os::raw::c_uint,
-    pub length: ::std::os::raw::c_uchar,
-    pub specification: ::std::os::raw::c_uchar,
-    pub checksum: ::std::os::raw::c_uchar,
-    pub feature1: ::std::os::raw::c_uchar,
-    pub feature2: ::std::os::raw::c_uchar,
-    pub feature3: ::std::os::raw::c_uchar,
-    pub feature4: ::std::os::raw::c_uchar,
-    pub feature5: ::std::os::raw::c_uchar,
-}
-
-#[repr(C)]
-#[derive(Debug, Default, Copy, Clone)]
-pub struct mpc_table {
-    pub signature: [::std::os::raw::c_char; 4usize],
-    pub length: ::std::os::raw::c_ushort,
-    pub spec: ::std::os::raw::c_char,
-    pub checksum: ::std::os::raw::c_char,
-    pub oem: [::std::os::raw::c_char; 8usize],
-    pub productid: [::std::os::raw::c_char; 12usize],
-    pub oemptr: ::std::os::raw::c_uint,
-    pub oemsize: ::std::os::raw::c_ushort,
-    pub oemcount: ::std::os::raw::c_ushort,
-    pub lapic: ::std::os::raw::c_uint,
-    pub reserved: ::std::os::raw::c_uint,
-}
-
-#[repr(C)]
-#[derive(Debug, Default, Copy, Clone)]
-pub struct mpc_cpu {
-    pub type_: ::std::os::raw::c_uchar,
-    pub apicid: ::std::os::raw::c_uchar,
-    pub apicver: ::std::os::raw::c_uchar,
-    pub cpuflag: ::std::os::raw::c_uchar,
-    pub cpufeature: ::std::os::raw::c_uint,
-    pub featureflag: ::std::os::raw::c_uint,
-    pub reserved: [::std::os::raw::c_uint; 2usize],
-}
-
-#[repr(C)]
-#[derive(Debug, Default, Copy, Clone)]
-pub struct mpc_bus {
-    pub type_: ::std::os::raw::c_uchar,
-    pub busid: ::std::os::raw::c_uchar,
-    pub bustype: [::std::os::raw::c_uchar; 6usize],
-}
-
-#[repr(C)]
-#[derive(Debug, Default, Copy, Clone)]
-pub struct mpc_ioapic {
-    pub type_: ::std::os::raw::c_uchar,
-    pub apicid: ::std::os::raw::c_uchar,
-    pub apicver: ::std::os::raw::c_uchar,
-    pub flags: ::std::os::raw::c_uchar,
-    pub apicaddr: ::std::os::raw::c_uint,
-}
-
-#[repr(C)]
-#[derive(Debug, Default, Copy, Clone)]
-pub struct mpc_intsrc {
-    pub type_: ::std::os::raw::c_uchar,
-    pub irqtype: ::std::os::raw::c_uchar,
-    pub irqflag: ::std::os::raw::c_ushort,
-    pub srcbus: ::std::os::raw::c_uchar,
-    pub srcbusirq: ::std::os::raw::c_uchar,
-    pub dstapic: ::std::os::raw::c_uchar,
-    pub dstirq: ::std::os::raw::c_uchar,
-}
-
-pub const MP_IRQ_SOURCE_TYPES_MP_INT: ::std::os::raw::c_uint = 0;
-pub const MP_IRQ_SOURCE_TYPES_MP_NMI: ::std::os::raw::c_uint = 1;
-pub const MP_IRQ_SOURCE_TYPES_MP_EXT_INT: ::std::os::raw::c_uint = 3;
-
-#[repr(C)]
-#[derive(Debug, Default, Copy, Clone)]
-pub struct mpc_lintsrc {
-    pub type_: ::std::os::raw::c_uchar,
-    pub irqtype: ::std::os::raw::c_uchar,
-    pub irqflag: ::std::os::raw::c_ushort,
-    pub srcbusid: ::std::os::raw::c_uchar,
-    pub srcbusirq: ::std::os::raw::c_uchar,
-    pub destapic: ::std::os::raw::c_uchar,
-    pub destapiclint: ::std::os::raw::c_uchar,
-}
-
-#[repr(C)]
-#[derive(Debug, Default, Copy, Clone)]
-pub struct mpc_oemtable {
-    pub signature: [::std::os::raw::c_char; 4usize],
-    pub length: ::std::os::raw::c_ushort,
-    pub rev: ::std::os::raw::c_char,
-    pub checksum: ::std::os::raw::c_char,
-    pub mpc: [::std::os::raw::c_char; 8usize],
-}

arch/src/x86_64/mptable.rs

@@ -5,15 +5,18 @@
 // 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::{APIC_START, HIGH_RAM_START, IOAPIC_START};
-use crate::x86_64::mpspec;
-use crate::GuestMemoryMmap;
-use libc::c_char;
 use std::io;
 use std::mem;
 use std::result;
 use std::slice;
-use vm_memory::{Address, ByteValued, Bytes, GuestAddress, GuestMemory, GuestMemoryError};
+
+use libc::c_char;
+
+use arch_gen::x86::mpspec;
+use layout::{APIC_START, HIGH_RAM_START, IOAPIC_START};
+use vm_memory::{
+    Address, ByteValued, Bytes, GuestAddress, GuestMemory, GuestMemoryError, GuestMemoryMmap,
+};
 
 // This is a workaround to the Rust enforcement specifying that any implementation of a foreign
 // trait (in this case `ByteValued`) where:
@@ -35,7 +38,7 @@ struct MpcLintsrcWrapper(mpspec::mpc_lintsrc);
 #[derive(Copy, Clone, Default)]
 struct MpfIntelWrapper(mpspec::mpf_intel);
 
-// SAFETY: These `mpspec` wrapper types are only data, reading them from data is a safe initialization.
+// These `mpspec` wrapper types are only data, reading them from data is a safe initialization.
 unsafe impl ByteValued for MpcBusWrapper {}
 unsafe impl ByteValued for MpcCpuWrapper {}
 unsafe impl ByteValued for MpcIntsrcWrapper {}
@@ -219,7 +222,7 @@ pub fn setup_mptable(offset: GuestAddress, mem: &GuestMemoryMmap, num_cpus: u8)
         let size = mem::size_of::<MpcIntsrcWrapper>();
         let mut mpc_intsrc = MpcIntsrcWrapper(mpspec::mpc_intsrc::default());
         mpc_intsrc.0.type_ = mpspec::MP_INTSRC as u8;
-        mpc_intsrc.0.irqtype = mpspec::MP_IRQ_SOURCE_TYPES_MP_INT as u8;
+        mpc_intsrc.0.irqtype = mpspec::mp_irq_source_types_mp_INT as u8;
         mpc_intsrc.0.irqflag = mpspec::MP_IRQDIR_DEFAULT as u16;
         mpc_intsrc.0.srcbus = 0;
         mpc_intsrc.0.srcbusirq = i;
@@ -234,7 +237,7 @@ pub fn setup_mptable(offset: GuestAddress, mem: &GuestMemoryMmap, num_cpus: u8)
         let size = mem::size_of::<MpcLintsrcWrapper>();
         let mut mpc_lintsrc = MpcLintsrcWrapper(mpspec::mpc_lintsrc::default());
         mpc_lintsrc.0.type_ = mpspec::MP_LINTSRC as u8;
-        mpc_lintsrc.0.irqtype = mpspec::MP_IRQ_SOURCE_TYPES_MP_EXT_INT as u8;
+        mpc_lintsrc.0.irqtype = mpspec::mp_irq_source_types_mp_ExtINT as u8;
         mpc_lintsrc.0.irqflag = mpspec::MP_IRQDIR_DEFAULT as u16;
         mpc_lintsrc.0.srcbusid = 0;
         mpc_lintsrc.0.srcbusirq = 0;
@@ -249,7 +252,7 @@ pub fn setup_mptable(offset: GuestAddress, mem: &GuestMemoryMmap, num_cpus: u8)
         let size = mem::size_of::<MpcLintsrcWrapper>();
         let mut mpc_lintsrc = MpcLintsrcWrapper(mpspec::mpc_lintsrc::default());
         mpc_lintsrc.0.type_ = mpspec::MP_LINTSRC as u8;
-        mpc_lintsrc.0.irqtype = mpspec::MP_IRQ_SOURCE_TYPES_MP_NMI as u8;
+        mpc_lintsrc.0.irqtype = mpspec::mp_irq_source_types_mp_NMI as u8;
         mpc_lintsrc.0.irqflag = mpspec::MP_IRQDIR_DEFAULT as u16;
         mpc_lintsrc.0.srcbusid = 0;
         mpc_lintsrc.0.srcbusirq = 0;
@@ -284,7 +287,7 @@ pub fn setup_mptable(offset: GuestAddress, mem: &GuestMemoryMmap, num_cpus: u8)
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::layout::MPTABLE_START;
+    use layout::MPTABLE_START;
     use vm_memory::{GuestAddress, GuestUsize};
 
     fn table_entry_size(type_: u8) -> usize {
@@ -294,7 +297,7 @@ mod tests {
             mpspec::MP_IOAPIC => mem::size_of::<MpcIoapicWrapper>(),
             mpspec::MP_INTSRC => mem::size_of::<MpcIntsrcWrapper>(),
             mpspec::MP_LINTSRC => mem::size_of::<MpcLintsrcWrapper>(),
-            _ => panic!("unrecognized mpc table entry type: {type_}"),
+            _ => panic!("unrecognized mpc table entry type: {}", type_),
         }
     }
 

arch/src/x86_64/regs.rs

@@ -6,14 +6,17 @@
 // 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 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 vm_memory::{Address, Bytes, GuestMemory, GuestMemoryError};
+
+use super::BootProtocol;
+use hypervisor::arch::x86::gdt::{gdt_entry, segment_from_gdt};
+use hypervisor::arch::x86::regs::*;
+use hypervisor::x86_64::{FpuState, SpecialRegisters, StandardRegisters};
+use layout::{
+    BOOT_GDT_START, BOOT_IDT_START, PDE_START, PDPTE_START, PML4_START, PML5_START, PVH_INFO_START,
+};
+use vm_memory::{Address, Bytes, GuestMemory, GuestMemoryError, GuestMemoryMmap};
 
 #[derive(Debug)]
 pub enum Error {
@@ -66,7 +69,7 @@ pub fn setup_fpu(vcpu: &Arc<dyn hypervisor::Vcpu>) -> Result<()> {
 ///
 /// * `vcpu` - Structure for the VCPU that holds the VCPU's fd.
 pub fn setup_msrs(vcpu: &Arc<dyn hypervisor::Vcpu>) -> Result<()> {
-    vcpu.set_msrs(&vcpu.boot_msr_entries())
+    vcpu.set_msrs(&hypervisor::x86_64::boot_msr_entries())
         .map_err(Error::SetModelSpecificRegisters)?;
 
     Ok(())
@@ -78,12 +81,32 @@ pub fn setup_msrs(vcpu: &Arc<dyn hypervisor::Vcpu>) -> Result<()> {
 ///
 /// * `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()
+/// * `boot_sp` - Starting stack pointer.
+/// * `boot_si` - Must point to zero page address per Linux ABI.
+pub fn setup_regs(
+    vcpu: &Arc<dyn hypervisor::Vcpu>,
+    boot_ip: u64,
+    boot_sp: u64,
+    boot_si: u64,
+    boot_prot: BootProtocol,
+) -> Result<()> {
+    let regs: StandardRegisters = match boot_prot {
+        // Configure regs as required by PVH boot protocol.
+        BootProtocol::PvhBoot => StandardRegisters {
+            rflags: 0x0000000000000002u64,
+            rbx: PVH_INFO_START.raw_value(),
+            rip: boot_ip,
+            ..Default::default()
+        },
+        // Configure regs as required by Linux 64-bit boot protocol.
+        BootProtocol::LinuxBoot => StandardRegisters {
+            rflags: 0x0000000000000002u64,
+            rip: boot_ip,
+            rsp: boot_sp,
+            rbp: boot_sp,
+            rsi: boot_si,
+            ..Default::default()
+        },
     };
     vcpu.set_regs(&regs).map_err(Error::SetBaseRegisters)
 }
@@ -94,9 +117,19 @@ pub fn setup_regs(vcpu: &Arc<dyn hypervisor::Vcpu>, boot_ip: u64) -> Result<()>
 ///
 /// * `mem` - The memory that will be passed to the guest.
 /// * `vcpu` - Structure for the VCPU that holds the VCPU's fd.
-pub fn setup_sregs(mem: &GuestMemoryMmap, vcpu: &Arc<dyn hypervisor::Vcpu>) -> Result<()> {
+pub fn setup_sregs(
+    mem: &GuestMemoryMmap,
+    vcpu: &Arc<dyn hypervisor::Vcpu>,
+    boot_prot: BootProtocol,
+) -> Result<()> {
     let mut sregs: SpecialRegisters = vcpu.get_sregs().map_err(Error::GetStatusRegisters)?;
-    configure_segments_and_sregs(mem, &mut sregs)?;
+
+    configure_segments_and_sregs(mem, &mut sregs, boot_prot)?;
+
+    if let BootProtocol::LinuxBoot = boot_prot {
+        setup_page_tables(mem, &mut sregs)?; // TODO(dgreid) - Can this be done once per system instead?
+    }
+
     vcpu.set_sregs(&sregs).map_err(Error::SetStatusRegisters)
 }
 
@@ -123,15 +156,27 @@ fn write_idt_value(val: u64, guest_mem: &GuestMemoryMmap) -> Result<()> {
 pub fn configure_segments_and_sregs(
     mem: &GuestMemoryMmap,
     sregs: &mut SpecialRegisters,
+    boot_prot: BootProtocol,
 ) -> Result<()> {
-    let gdt_table: [u64; BOOT_GDT_MAX] = {
-        // Configure GDT entries as specified by PVH boot protocol
-        [
-            gdt_entry(0, 0, 0),               // NULL
-            gdt_entry(0xc09b, 0, 0xffffffff), // CODE
-            gdt_entry(0xc093, 0, 0xffffffff), // DATA
-            gdt_entry(0x008b, 0, 0x67),       // TSS
-        ]
+    let gdt_table: [u64; BOOT_GDT_MAX as usize] = match boot_prot {
+        BootProtocol::PvhBoot => {
+            // Configure GDT entries as specified by PVH boot protocol
+            [
+                gdt_entry(0, 0, 0),               // NULL
+                gdt_entry(0xc09b, 0, 0xffffffff), // CODE
+                gdt_entry(0xc093, 0, 0xffffffff), // DATA
+                gdt_entry(0x008b, 0, 0x67),       // TSS
+            ]
+        }
+        BootProtocol::LinuxBoot => {
+            // Configure GDT entries as specified by Linux 64bit boot protocol
+            [
+                gdt_entry(0, 0, 0),            // NULL
+                gdt_entry(0xa09b, 0, 0xfffff), // CODE
+                gdt_entry(0xc093, 0, 0xfffff), // DATA
+                gdt_entry(0x808b, 0, 0xfffff), // TSS
+            ]
+        }
     };
 
     let code_seg = segment_from_gdt(gdt_table[1], 1);
@@ -155,17 +200,61 @@ pub fn configure_segments_and_sregs(
     sregs.ss = data_seg;
     sregs.tr = tss_seg;
 
-    sregs.cr0 = CR0_PE;
-    sregs.cr4 = 0;
+    match boot_prot {
+        BootProtocol::PvhBoot => {
+            sregs.cr0 = CR0_PE;
+            sregs.cr4 = 0;
+        }
+        BootProtocol::LinuxBoot => {
+            /* 64-bit protected mode */
+            sregs.cr0 |= CR0_PE;
+            sregs.efer |= EFER_LME | EFER_LMA;
+        }
+    }
+
+    Ok(())
+}
+
+pub fn setup_page_tables(mem: &GuestMemoryMmap, sregs: &mut SpecialRegisters) -> Result<()> {
+    // Puts PML5 or PML4 right after zero page but aligned to 4k.
+    if unsafe { std::arch::x86_64::__cpuid(7).ecx } & (1 << 16) != 0 {
+        // Entry covering VA [0..256TB)
+        mem.write_obj(PML4_START.raw_value() | 0x03, PML5_START)
+            .map_err(Error::WritePml5Address)?;
+
+        sregs.cr3 = PML5_START.raw_value();
+        sregs.cr4 |= CR4_LA57;
+    } else {
+        sregs.cr3 = PML4_START.raw_value();
+    }
+
+    // Entry covering VA [0..512GB)
+    mem.write_obj(PDPTE_START.raw_value() | 0x03, PML4_START)
+        .map_err(Error::WritePml4Address)?;
+
+    // Entry covering VA [0..1GB)
+    mem.write_obj(PDE_START.raw_value() | 0x03, PDPTE_START)
+        .map_err(Error::WritePdpteAddress)?;
+
+    // 512 2MB entries together covering VA [0..1GB). Note we are assuming
+    // CPU supports 2MB pages (/proc/cpuinfo has 'pse'). All modern CPUs do.
+    for i in 0..512 {
+        mem.write_obj((i << 21) + 0x83u64, PDE_START.unchecked_add(i * 8))
+            .map_err(Error::WritePdeAddress)?;
+    }
+
+    sregs.cr4 |= CR4_PAE;
+    sregs.cr0 |= CR0_PG;
 
     Ok(())
 }
 
 #[cfg(test)]
 mod tests {
+    extern crate vm_memory;
+
     use super::*;
-    use crate::GuestMemoryMmap;
-    use vm_memory::GuestAddress;
+    use vm_memory::{GuestAddress, GuestMemoryMmap};
 
     fn create_guest_mem() -> GuestMemoryMmap {
         GuestMemoryMmap::from_ranges(&[(GuestAddress(0), 0x10000)]).unwrap()
@@ -179,7 +268,36 @@ mod tests {
     fn segments_and_sregs() {
         let mut sregs: SpecialRegisters = Default::default();
         let gm = create_guest_mem();
-        configure_segments_and_sregs(&gm, &mut sregs).unwrap();
+        configure_segments_and_sregs(&gm, &mut sregs, BootProtocol::LinuxBoot).unwrap();
+
+        assert_eq!(0x0, read_u64(&gm, BOOT_GDT_START));
+        assert_eq!(
+            0xaf9b000000ffff,
+            read_u64(&gm, BOOT_GDT_START.unchecked_add(8))
+        );
+        assert_eq!(
+            0xcf93000000ffff,
+            read_u64(&gm, BOOT_GDT_START.unchecked_add(16))
+        );
+        assert_eq!(
+            0x8f8b000000ffff,
+            read_u64(&gm, BOOT_GDT_START.unchecked_add(24))
+        );
+        assert_eq!(0x0, read_u64(&gm, BOOT_IDT_START));
+
+        assert_eq!(0, sregs.cs.base);
+        assert_eq!(0xffffffff, sregs.ds.limit);
+        assert_eq!(0x10, sregs.es.selector);
+        assert_eq!(1, sregs.fs.present);
+        assert_eq!(1, sregs.gs.g);
+        assert_eq!(0, sregs.ss.avl);
+        assert_eq!(0, sregs.tr.base);
+        assert_eq!(0xffffffff, sregs.tr.limit);
+        assert_eq!(0, sregs.tr.avl);
+        assert_eq!(CR0_PE, sregs.cr0);
+        assert_eq!(EFER_LME | EFER_LMA, sregs.efer);
+
+        configure_segments_and_sregs(&gm, &mut sregs, BootProtocol::PvhBoot).unwrap();
         assert_eq!(0x0, read_u64(&gm, BOOT_GDT_START));
         assert_eq!(
             0xcf9b000000ffff,
@@ -209,4 +327,31 @@ mod tests {
         assert_eq!(CR0_PE, sregs.cr0);
         assert_eq!(0, sregs.cr4);
     }
+
+    #[test]
+    fn page_tables() {
+        let mut sregs: SpecialRegisters = Default::default();
+        let gm = create_guest_mem();
+        setup_page_tables(&gm, &mut sregs).unwrap();
+
+        if unsafe { std::arch::x86_64::__cpuid(7).ecx } & (1 << 16) != 0 {
+            assert_eq!(0xa003, read_u64(&gm, PML5_START));
+        }
+        assert_eq!(0xb003, read_u64(&gm, PML4_START));
+        assert_eq!(0xc003, read_u64(&gm, PDPTE_START));
+        for i in 0..512 {
+            assert_eq!(
+                (i << 21) + 0x83u64,
+                read_u64(&gm, PDE_START.unchecked_add(i * 8))
+            );
+        }
+
+        if unsafe { std::arch::x86_64::__cpuid(7).ecx } & (1 << 16) != 0 {
+            assert_eq!(PML5_START.raw_value(), sregs.cr3);
+        } else {
+            assert_eq!(PML4_START.raw_value(), sregs.cr3);
+        }
+        assert_eq!(CR4_PAE, sregs.cr4);
+        assert_eq!(CR0_PG, sregs.cr0);
+    }
 }

arch/src/x86_64/smbios.rs

@@ -6,16 +6,15 @@
 //
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
-use crate::layout::SMBIOS_START;
-use crate::GuestMemoryMmap;
+use layout::SMBIOS_START;
 use std::fmt::{self, Display};
 use std::mem;
 use std::result;
 use std::slice;
-use uuid::Uuid;
 use vm_memory::ByteValued;
-use vm_memory::{Address, Bytes, GuestAddress};
+use vm_memory::{Address, Bytes, GuestAddress, GuestMemoryMmap};
 
+#[allow(unused_variables)]
 #[derive(Debug)]
 pub enum Error {
     /// There was too little guest memory to store the entire SMBIOS table.
@@ -28,8 +27,6 @@ pub enum Error {
     WriteSmbiosEp,
     /// Failure to write additional data to memory
     WriteData,
-    /// Failure to parse uuid, uuid format may be error
-    ParseUuid(uuid::Error),
 }
 
 impl std::error::Error for Error {}
@@ -39,19 +36,14 @@ impl Display for Error {
         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}"),
+            NotEnoughMemory => "There was too little guest memory to store the SMBIOS table",
+            AddressOverflow => "The SMBIOS table has too little address space to be stored",
+            Clear => "Failure while zeroing out the memory for the SMBIOS table",
+            WriteSmbiosEp => "Failure to write SMBIOS entrypoint structure",
+            WriteData => "Failure to write additional data to memory",
         };
 
-        write!(f, "SMBIOS error: {description}")
+        write!(f, "SMBIOS error: {}", description)
     }
 }
 
@@ -61,7 +53,6 @@ pub type Result<T> = result::Result<T, Error>;
 const SM3_MAGIC_IDENT: &[u8; 5usize] = b"_SM3_";
 const BIOS_INFORMATION: u8 = 0;
 const SYSTEM_INFORMATION: u8 = 1;
-const OEM_STRINGS: u8 = 11;
 const END_OF_TABLE: u8 = 127;
 const PCI_SUPPORTED: u64 = 1 << 7;
 const IS_VIRTUAL_MACHINE: u8 = 1 << 4;
@@ -76,81 +67,75 @@ fn compute_checksum<T: Copy>(v: &T) -> u8 {
     (!checksum).wrapping_add(1)
 }
 
-#[repr(C)]
 #[repr(packed)]
-#[derive(Default, Copy, Clone)]
-struct Smbios30Entrypoint {
-    signature: [u8; 5usize],
-    checksum: u8,
-    length: u8,
-    majorver: u8,
-    minorver: u8,
-    docrev: u8,
-    revision: u8,
-    reserved: u8,
-    max_size: u32,
-    physptr: u64,
+#[derive(Default, Copy)]
+pub struct Smbios30Entrypoint {
+    pub signature: [u8; 5usize],
+    pub checksum: u8,
+    pub length: u8,
+    pub majorver: u8,
+    pub minorver: u8,
+    pub docrev: u8,
+    pub revision: u8,
+    pub reserved: u8,
+    pub max_size: u32,
+    pub physptr: u64,
 }
-
-#[repr(C)]
-#[repr(packed)]
-#[derive(Default, Copy, Clone)]
-struct SmbiosBiosInfo {
-    r#type: u8,
-    length: u8,
-    handle: u16,
-    vendor: u8,
-    version: u8,
-    start_addr: u16,
-    release_date: u8,
-    rom_size: u8,
-    characteristics: u64,
-    characteristics_ext1: u8,
-    characteristics_ext2: u8,
-}
-
-#[repr(C)]
-#[repr(packed)]
-#[derive(Default, Copy, Clone)]
-struct SmbiosSysInfo {
-    r#type: u8,
-    length: u8,
-    handle: u16,
-    manufacturer: u8,
-    product_name: u8,
-    version: u8,
-    serial_number: u8,
-    uuid: [u8; 16usize],
-    wake_up_type: u8,
-    sku: u8,
-    family: u8,
-}
-
-#[repr(C)]
-#[repr(packed)]
-#[derive(Default, Copy, Clone)]
-struct SmbiosOemStrings {
-    r#type: u8,
-    length: u8,
-    handle: u16,
-    count: u8,
-}
-
-#[repr(C)]
-#[repr(packed)]
-#[derive(Default, Copy, Clone)]
-struct SmbiosEndOfTable {
-    r#type: u8,
-    length: u8,
-    handle: u16,
-}
-
-// SAFETY: These data structures only contain a series of integers
 unsafe impl ByteValued for Smbios30Entrypoint {}
+
+impl Clone for Smbios30Entrypoint {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+
+#[repr(packed)]
+#[derive(Default, Copy)]
+pub struct SmbiosBiosInfo {
+    pub typ: u8,
+    pub length: u8,
+    pub handle: u16,
+    pub vendor: u8,
+    pub version: u8,
+    pub start_addr: u16,
+    pub release_date: u8,
+    pub rom_size: u8,
+    pub characteristics: u64,
+    pub characteristics_ext1: u8,
+    pub characteristics_ext2: u8,
+}
+
+impl Clone for SmbiosBiosInfo {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+
 unsafe impl ByteValued for SmbiosBiosInfo {}
+
+#[repr(packed)]
+#[derive(Default, Copy)]
+pub struct SmbiosSysInfo {
+    pub typ: u8,
+    pub length: u8,
+    pub handle: u16,
+    pub manufacturer: u8,
+    pub product_name: u8,
+    pub version: u8,
+    pub serial_number: u8,
+    pub uuid: [u8; 16usize],
+    pub wake_up_type: u8,
+    pub sku: u8,
+    pub family: u8,
+}
+
+impl Clone for SmbiosSysInfo {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+
 unsafe impl ByteValued for SmbiosSysInfo {}
-unsafe impl ByteValued for SmbiosOemStrings {}
-unsafe impl ByteValued for SmbiosEndOfTable {}
 
 fn write_and_incr<T: ByteValued>(
     mem: &GuestMemoryMmap,
@@ -176,12 +161,7 @@ fn write_string(
     Ok(curptr)
 }
 
-pub fn setup_smbios(
-    mem: &GuestMemoryMmap,
-    serial_number: Option<&str>,
-    uuid: Option<&str>,
-    oem_strings: Option<&[&str]>,
-) -> Result<u64> {
+pub fn setup_smbios(mem: &GuestMemoryMmap) -> Result<u64> {
     let physptr = GuestAddress(SMBIOS_START)
         .checked_add(mem::size_of::<Smbios30Entrypoint>() as u64)
         .ok_or(Error::NotEnoughMemory)?;
@@ -191,7 +171,7 @@ pub fn setup_smbios(
     {
         handle += 1;
         let smbios_biosinfo = SmbiosBiosInfo {
-            r#type: BIOS_INFORMATION,
+            typ: BIOS_INFORMATION,
             length: mem::size_of::<SmbiosBiosInfo>() as u8,
             handle,
             vendor: 1,  // First string written in this section
@@ -208,59 +188,29 @@ pub fn setup_smbios(
 
     {
         handle += 1;
-
-        let uuid_number = uuid
-            .map(Uuid::parse_str)
-            .transpose()
-            .map_err(Error::ParseUuid)?
-            .unwrap_or(Uuid::nil());
         let smbios_sysinfo = SmbiosSysInfo {
-            r#type: SYSTEM_INFORMATION,
+            typ: SYSTEM_INFORMATION,
             length: mem::size_of::<SmbiosSysInfo>() as u8,
             handle,
             manufacturer: 1, // First string written in this section
             product_name: 2, // Second string written in this section
-            serial_number: serial_number.map(|_| 3).unwrap_or_default(), // 3rd string
-            uuid: uuid_number.to_bytes_le(), // set uuid
             ..Default::default()
         };
         curptr = write_and_incr(mem, smbios_sysinfo, curptr)?;
         curptr = write_string(mem, "Cloud Hypervisor", curptr)?;
         curptr = write_string(mem, "cloud-hypervisor", curptr)?;
-        if let Some(serial_number) = serial_number {
-            curptr = write_string(mem, serial_number, curptr)?;
-        }
-        curptr = write_and_incr(mem, 0u8, curptr)?;
-    }
-
-    if let Some(oem_strings) = oem_strings {
-        handle += 1;
-
-        let smbios_oemstrings = SmbiosOemStrings {
-            r#type: OEM_STRINGS,
-            length: mem::size_of::<SmbiosOemStrings>() as u8,
-            handle,
-            count: oem_strings.len() as u8,
-        };
-
-        curptr = write_and_incr(mem, smbios_oemstrings, curptr)?;
-
-        for s in oem_strings {
-            curptr = write_string(mem, s, curptr)?;
-        }
-
         curptr = write_and_incr(mem, 0u8, curptr)?;
     }
 
     {
         handle += 1;
-        let smbios_end = SmbiosEndOfTable {
-            r#type: END_OF_TABLE,
-            length: mem::size_of::<SmbiosEndOfTable>() as u8,
+        let smbios_sysinfo = SmbiosSysInfo {
+            typ: END_OF_TABLE,
+            length: mem::size_of::<SmbiosSysInfo>() as u8,
             handle,
+            ..Default::default()
         };
-        curptr = write_and_incr(mem, smbios_end, curptr)?;
-        curptr = write_and_incr(mem, 0u8, curptr)?;
+        curptr = write_and_incr(mem, smbios_sysinfo, curptr)?;
         curptr = write_and_incr(mem, 0u8, curptr)?;
     }
 
@@ -282,7 +232,7 @@ pub fn setup_smbios(
             .map_err(|_| Error::WriteSmbiosEp)?;
     }
 
-    Ok(curptr.unchecked_offset_from(physptr) + std::mem::size_of::<Smbios30Entrypoint>() as u64)
+    Ok(curptr.unchecked_offset_from(physptr))
 }
 
 #[cfg(test)]
@@ -312,7 +262,7 @@ mod tests {
     fn entrypoint_checksum() {
         let mem = GuestMemoryMmap::from_ranges(&[(GuestAddress(SMBIOS_START), 4096)]).unwrap();
 
-        setup_smbios(&mem, None, None, None).unwrap();
+        setup_smbios(&mem).unwrap();
 
         let smbios_ep: Smbios30Entrypoint = mem.read_obj(GuestAddress(SMBIOS_START)).unwrap();
 

arch/src/x86_64/tdx/mod.rs

@@ -1,11 +1,10 @@
 // Copyright © 2021 Intel Corporation
 //
 // SPDX-License-Identifier: Apache-2.0
-use crate::GuestMemoryMmap;
 use std::fs::File;
 use std::io::{Read, Seek, SeekFrom};
 use thiserror::Error;
-use vm_memory::{ByteValued, Bytes, GuestAddress, GuestMemoryError};
+use vm_memory::{ByteValued, Bytes, GuestAddress, GuestMemoryError, GuestMemoryMmap};
 
 #[derive(Error, Debug)]
 pub enum TdvfError {
@@ -25,7 +24,6 @@ pub enum TdvfError {
 
 // TDVF_DESCRIPTOR
 #[repr(packed)]
-#[derive(Default)]
 pub struct TdvfDescriptor {
     signature: [u8; 4],
     length: u32,
@@ -46,19 +44,21 @@ pub struct TdvfSection {
 }
 
 #[repr(u32)]
-#[derive(Clone, Copy, Debug, Default)]
+#[derive(Clone, Copy, Debug)]
 pub enum TdvfSectionType {
     Bfv,
     Cfv,
     TdHob,
     TempMem,
-    PermMem,
-    Payload,
-    PayloadParam,
-    #[default]
     Reserved = 0xffffffff,
 }
 
+impl Default for TdvfSectionType {
+    fn default() -> Self {
+        TdvfSectionType::Reserved
+    }
+}
+
 pub fn parse_tdvf_sections(file: &mut File) -> Result<Vec<TdvfSection>, TdvfError> {
     // The 32-bit offset to the TDVF metadata is located 32 bytes from
     // the end of the file.
@@ -74,7 +74,7 @@ pub fn parse_tdvf_sections(file: &mut File) -> Result<Vec<TdvfSection>, TdvfErro
     file.seek(SeekFrom::Start(descriptor_offset))
         .map_err(TdvfError::ReadDescriptor)?;
 
-    let mut descriptor: TdvfDescriptor = Default::default();
+    let mut descriptor: TdvfDescriptor = unsafe { std::mem::zeroed() };
     // Safe as we read exactly the size of the descriptor header
     file.read_exact(unsafe {
         std::slice::from_raw_parts_mut(
@@ -115,16 +115,20 @@ pub fn parse_tdvf_sections(file: &mut File) -> Result<Vec<TdvfSection>, TdvfErro
 }
 
 #[repr(u16)]
-#[derive(Copy, Clone, Debug, Default)]
+#[derive(Copy, Clone, Debug)]
 enum HobType {
     Handoff = 0x1,
     ResourceDescriptor = 0x3,
-    GuidExtension = 0x4,
-    #[default]
     Unused = 0xfffe,
     EndOfHobList = 0xffff,
 }
 
+impl Default for HobType {
+    fn default() -> Self {
+        HobType::Unused
+    }
+}
+
 #[repr(C)]
 #[derive(Copy, Clone, Default, Debug)]
 struct HobHeader {
@@ -132,19 +136,20 @@ struct HobHeader {
     length: u16,
     reserved: u32,
 }
+unsafe impl ByteValued for HobHeader {}
 
 #[repr(C)]
 #[derive(Copy, Clone, Default, Debug)]
 struct HobHandoffInfoTable {
     header: HobHeader,
     version: u32,
-    boot_mode: u32,
     efi_memory_top: u64,
     efi_memory_bottom: u64,
     efi_free_memory_top: u64,
     efi_free_memory_bottom: u64,
     efi_end_of_hob_list: u64,
 }
+unsafe impl ByteValued for HobHandoffInfoTable {}
 
 #[repr(C)]
 #[derive(Copy, Clone, Default, Debug)]
@@ -165,44 +170,7 @@ struct HobResourceDescriptor {
     physical_start: u64,
     resource_length: u64,
 }
-
-#[repr(C)]
-#[derive(Copy, Clone, Default, Debug)]
-struct HobGuidType {
-    header: HobHeader,
-    name: EfiGuid,
-}
-
-#[repr(u32)]
-#[derive(Clone, Copy, Debug, Default)]
-pub enum PayloadImageType {
-    #[default]
-    ExecutablePayload,
-    BzImage,
-    RawVmLinux,
-}
-
-#[repr(C)]
-#[derive(Copy, Clone, Default, Debug)]
-pub struct PayloadInfo {
-    pub image_type: PayloadImageType,
-    pub entry_point: u64,
-}
-
-#[repr(C)]
-#[derive(Copy, Clone, Default, Debug)]
-struct TdPayload {
-    guid_type: HobGuidType,
-    payload_info: PayloadInfo,
-}
-
-// SAFETY: These data structures only contain a series of integers
-unsafe impl ByteValued for HobHeader {}
-unsafe impl ByteValued for HobHandoffInfoTable {}
 unsafe impl ByteValued for HobResourceDescriptor {}
-unsafe impl ByteValued for HobGuidType {}
-unsafe impl ByteValued for PayloadInfo {}
-unsafe impl ByteValued for TdPayload {}
 
 pub struct TdHob {
     start_offset: u64,
@@ -249,7 +217,6 @@ impl TdHob {
                 reserved: 0,
             },
             version: 0x9,
-            boot_mode: 0,
             efi_memory_top: 0,
             efi_memory_bottom: 0,
             efi_free_memory_top: 0,
@@ -333,93 +300,6 @@ impl TdHob {
             0x403,
         )
     }
-
-    pub fn add_acpi_table(
-        &mut self,
-        mem: &GuestMemoryMmap,
-        table_content: &[u8],
-    ) -> Result<(), TdvfError> {
-        // We already know the HobGuidType size is 8 bytes multiple, but we
-        // need the total size to be 8 bytes multiple. That is why the ACPI
-        // table size must be 8 bytes multiple as well.
-        let length = std::mem::size_of::<HobGuidType>() as u16
-            + align_hob(table_content.len() as u64) as u16;
-        let hob_guid_type = HobGuidType {
-            header: HobHeader {
-                r#type: HobType::GuidExtension,
-                length,
-                reserved: 0,
-            },
-            // ACPI_TABLE_HOB_GUID
-            // 0x6a0c5870, 0xd4ed, 0x44f4, {0xa1, 0x35, 0xdd, 0x23, 0x8b, 0x6f, 0xc, 0x8d }
-            name: EfiGuid {
-                data1: 0x6a0c_5870,
-                data2: 0xd4ed,
-                data3: 0x44f4,
-                data4: [0xa1, 0x35, 0xdd, 0x23, 0x8b, 0x6f, 0xc, 0x8d],
-            },
-        };
-        info!(
-            "Writing HOB ACPI table {:x} {:x?} {:x?}",
-            self.current_offset, hob_guid_type, table_content
-        );
-        mem.write_obj(hob_guid_type, GuestAddress(self.current_offset))
-            .map_err(TdvfError::GuestMemoryWriteHob)?;
-        let current_offset = self.current_offset + std::mem::size_of::<HobGuidType>() as u64;
-
-        // In case the table is quite large, let's make sure we can handle
-        // retrying until everything has been correctly copied.
-        let mut offset: usize = 0;
-        loop {
-            let bytes_written = mem
-                .write(
-                    &table_content[offset..],
-                    GuestAddress(current_offset + offset as u64),
-                )
-                .map_err(TdvfError::GuestMemoryWriteHob)?;
-            offset += bytes_written;
-            if offset >= table_content.len() {
-                break;
-            }
-        }
-        self.current_offset += length as u64;
-
-        Ok(())
-    }
-
-    pub fn add_payload(
-        &mut self,
-        mem: &GuestMemoryMmap,
-        payload_info: PayloadInfo,
-    ) -> Result<(), TdvfError> {
-        let payload = TdPayload {
-            guid_type: HobGuidType {
-                header: HobHeader {
-                    r#type: HobType::GuidExtension,
-                    length: std::mem::size_of::<TdPayload>() as u16,
-                    reserved: 0,
-                },
-                // HOB_PAYLOAD_INFO_GUID
-                // 0xb96fa412, 0x461f, 0x4be3, {0x8c, 0xd, 0xad, 0x80, 0x5a, 0x49, 0x7a, 0xc0
-                name: EfiGuid {
-                    data1: 0xb96f_a412,
-                    data2: 0x461f,
-                    data3: 0x4be3,
-                    data4: [0x8c, 0xd, 0xad, 0x80, 0x5a, 0x49, 0x7a, 0xc0],
-                },
-            },
-            payload_info,
-        };
-        info!(
-            "Writing HOB TD_PAYLOAD {:x} {:x?}",
-            self.current_offset, payload
-        );
-        mem.write_obj(payload, GuestAddress(self.current_offset))
-            .map_err(TdvfError::GuestMemoryWriteHob)?;
-        self.update_offset::<TdPayload>();
-
-        Ok(())
-    }
 }
 
 #[cfg(test)]
@@ -432,7 +312,7 @@ mod tests {
         let mut f = std::fs::File::open("tdvf.fd").unwrap();
         let sections = parse_tdvf_sections(&mut f).unwrap();
         for section in sections {
-            eprintln!("{section:x?}")
+            eprintln!("{:x?}", section)
         }
     }
 }

arch_gen/Cargo.lock

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

arch_gen/Cargo.toml

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

arch_gen/src/lib.rs

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

arch_gen/src/x86/mod.rs

@@ -0,0 +1,14 @@
+// Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+// SPDX-License-Identifier: Apache-2.0
+//
+// Portions Copyright 2017 The Chromium OS Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE-BSD-3-Clause file.
+
+#[allow(non_upper_case_globals)]
+#[allow(non_camel_case_types)]
+#[allow(non_snake_case)]
+#[allow(non_camel_case_types)]
+#[allow(non_upper_case_globals)]
+#[allow(clippy::unreadable_literal, clippy::redundant_static_lifetimes)]
+pub mod mpspec;

arch_gen/src/x86/mpspec.rs

@@ -0,0 +1,832 @@
+// Copyright 2017 The Chromium OS Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE-BSD-3-Clause file.
+
+/* automatically generated by rust-bindgen */
+
+pub const MPC_SIGNATURE: &'static [u8; 5usize] = b"PCMP\x00";
+pub const MP_PROCESSOR: ::std::os::raw::c_uint = 0;
+pub const MP_BUS: ::std::os::raw::c_uint = 1;
+pub const MP_IOAPIC: ::std::os::raw::c_uint = 2;
+pub const MP_INTSRC: ::std::os::raw::c_uint = 3;
+pub const MP_LINTSRC: ::std::os::raw::c_uint = 4;
+pub const MP_TRANSLATION: ::std::os::raw::c_uint = 192;
+pub const CPU_ENABLED: ::std::os::raw::c_uint = 1;
+pub const CPU_BOOTPROCESSOR: ::std::os::raw::c_uint = 2;
+pub const CPU_STEPPING_MASK: ::std::os::raw::c_uint = 15;
+pub const CPU_MODEL_MASK: ::std::os::raw::c_uint = 240;
+pub const CPU_FAMILY_MASK: ::std::os::raw::c_uint = 3840;
+pub const BUSTYPE_EISA: &'static [u8; 5usize] = b"EISA\x00";
+pub const BUSTYPE_ISA: &'static [u8; 4usize] = b"ISA\x00";
+pub const BUSTYPE_INTERN: &'static [u8; 7usize] = b"INTERN\x00";
+pub const BUSTYPE_MCA: &'static [u8; 4usize] = b"MCA\x00";
+pub const BUSTYPE_VL: &'static [u8; 3usize] = b"VL\x00";
+pub const BUSTYPE_PCI: &'static [u8; 4usize] = b"PCI\x00";
+pub const BUSTYPE_PCMCIA: &'static [u8; 7usize] = b"PCMCIA\x00";
+pub const BUSTYPE_CBUS: &'static [u8; 5usize] = b"CBUS\x00";
+pub const BUSTYPE_CBUSII: &'static [u8; 7usize] = b"CBUSII\x00";
+pub const BUSTYPE_FUTURE: &'static [u8; 7usize] = b"FUTURE\x00";
+pub const BUSTYPE_MBI: &'static [u8; 4usize] = b"MBI\x00";
+pub const BUSTYPE_MBII: &'static [u8; 5usize] = b"MBII\x00";
+pub const BUSTYPE_MPI: &'static [u8; 4usize] = b"MPI\x00";
+pub const BUSTYPE_MPSA: &'static [u8; 5usize] = b"MPSA\x00";
+pub const BUSTYPE_NUBUS: &'static [u8; 6usize] = b"NUBUS\x00";
+pub const BUSTYPE_TC: &'static [u8; 3usize] = b"TC\x00";
+pub const BUSTYPE_VME: &'static [u8; 4usize] = b"VME\x00";
+pub const BUSTYPE_XPRESS: &'static [u8; 7usize] = b"XPRESS\x00";
+pub const MPC_APIC_USABLE: ::std::os::raw::c_uint = 1;
+pub const MP_IRQDIR_DEFAULT: ::std::os::raw::c_uint = 0;
+pub const MP_IRQDIR_HIGH: ::std::os::raw::c_uint = 1;
+pub const MP_IRQDIR_LOW: ::std::os::raw::c_uint = 3;
+pub const MP_APIC_ALL: ::std::os::raw::c_uint = 255;
+pub const MPC_OEM_SIGNATURE: &'static [u8; 5usize] = b"_OEM\x00";
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpf_intel {
+    pub signature: [::std::os::raw::c_char; 4usize],
+    pub physptr: ::std::os::raw::c_uint,
+    pub length: ::std::os::raw::c_uchar,
+    pub specification: ::std::os::raw::c_uchar,
+    pub checksum: ::std::os::raw::c_uchar,
+    pub feature1: ::std::os::raw::c_uchar,
+    pub feature2: ::std::os::raw::c_uchar,
+    pub feature3: ::std::os::raw::c_uchar,
+    pub feature4: ::std::os::raw::c_uchar,
+    pub feature5: ::std::os::raw::c_uchar,
+}
+#[test]
+fn bindgen_test_layout_mpf_intel() {
+    assert_eq!(
+        ::std::mem::size_of::<mpf_intel>(),
+        16usize,
+        concat!("Size of: ", stringify!(mpf_intel))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpf_intel>(),
+        4usize,
+        concat!("Alignment of ", stringify!(mpf_intel))
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpf_intel>()).signature as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(signature)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpf_intel>()).physptr as *const _ as usize },
+        4usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(physptr)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpf_intel>()).length as *const _ as usize },
+        8usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(length)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpf_intel>()).specification as *const _ as usize },
+        9usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(specification)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpf_intel>()).checksum as *const _ as usize },
+        10usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(checksum)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpf_intel>()).feature1 as *const _ as usize },
+        11usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(feature1)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpf_intel>()).feature2 as *const _ as usize },
+        12usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(feature2)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpf_intel>()).feature3 as *const _ as usize },
+        13usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(feature3)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpf_intel>()).feature4 as *const _ as usize },
+        14usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(feature4)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpf_intel>()).feature5 as *const _ as usize },
+        15usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpf_intel),
+            "::",
+            stringify!(feature5)
+        )
+    );
+}
+impl Clone for mpf_intel {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpc_table {
+    pub signature: [::std::os::raw::c_char; 4usize],
+    pub length: ::std::os::raw::c_ushort,
+    pub spec: ::std::os::raw::c_char,
+    pub checksum: ::std::os::raw::c_char,
+    pub oem: [::std::os::raw::c_char; 8usize],
+    pub productid: [::std::os::raw::c_char; 12usize],
+    pub oemptr: ::std::os::raw::c_uint,
+    pub oemsize: ::std::os::raw::c_ushort,
+    pub oemcount: ::std::os::raw::c_ushort,
+    pub lapic: ::std::os::raw::c_uint,
+    pub reserved: ::std::os::raw::c_uint,
+}
+#[test]
+fn bindgen_test_layout_mpc_table() {
+    assert_eq!(
+        ::std::mem::size_of::<mpc_table>(),
+        44usize,
+        concat!("Size of: ", stringify!(mpc_table))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpc_table>(),
+        4usize,
+        concat!("Alignment of ", stringify!(mpc_table))
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_table>()).signature as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(signature)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_table>()).length as *const _ as usize },
+        4usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(length)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_table>()).spec as *const _ as usize },
+        6usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(spec)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_table>()).checksum as *const _ as usize },
+        7usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(checksum)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_table>()).oem as *const _ as usize },
+        8usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(oem)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_table>()).productid as *const _ as usize },
+        16usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(productid)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_table>()).oemptr as *const _ as usize },
+        28usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(oemptr)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_table>()).oemsize as *const _ as usize },
+        32usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(oemsize)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_table>()).oemcount as *const _ as usize },
+        34usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(oemcount)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_table>()).lapic as *const _ as usize },
+        36usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(lapic)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_table>()).reserved as *const _ as usize },
+        40usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_table),
+            "::",
+            stringify!(reserved)
+        )
+    );
+}
+impl Clone for mpc_table {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpc_cpu {
+    pub type_: ::std::os::raw::c_uchar,
+    pub apicid: ::std::os::raw::c_uchar,
+    pub apicver: ::std::os::raw::c_uchar,
+    pub cpuflag: ::std::os::raw::c_uchar,
+    pub cpufeature: ::std::os::raw::c_uint,
+    pub featureflag: ::std::os::raw::c_uint,
+    pub reserved: [::std::os::raw::c_uint; 2usize],
+}
+#[test]
+fn bindgen_test_layout_mpc_cpu() {
+    assert_eq!(
+        ::std::mem::size_of::<mpc_cpu>(),
+        20usize,
+        concat!("Size of: ", stringify!(mpc_cpu))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpc_cpu>(),
+        4usize,
+        concat!("Alignment of ", stringify!(mpc_cpu))
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_cpu>()).type_ as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_cpu),
+            "::",
+            stringify!(type_)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_cpu>()).apicid as *const _ as usize },
+        1usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_cpu),
+            "::",
+            stringify!(apicid)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_cpu>()).apicver as *const _ as usize },
+        2usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_cpu),
+            "::",
+            stringify!(apicver)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_cpu>()).cpuflag as *const _ as usize },
+        3usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_cpu),
+            "::",
+            stringify!(cpuflag)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_cpu>()).cpufeature as *const _ as usize },
+        4usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_cpu),
+            "::",
+            stringify!(cpufeature)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_cpu>()).featureflag as *const _ as usize },
+        8usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_cpu),
+            "::",
+            stringify!(featureflag)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_cpu>()).reserved as *const _ as usize },
+        12usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_cpu),
+            "::",
+            stringify!(reserved)
+        )
+    );
+}
+impl Clone for mpc_cpu {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpc_bus {
+    pub type_: ::std::os::raw::c_uchar,
+    pub busid: ::std::os::raw::c_uchar,
+    pub bustype: [::std::os::raw::c_uchar; 6usize],
+}
+#[test]
+fn bindgen_test_layout_mpc_bus() {
+    assert_eq!(
+        ::std::mem::size_of::<mpc_bus>(),
+        8usize,
+        concat!("Size of: ", stringify!(mpc_bus))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpc_bus>(),
+        1usize,
+        concat!("Alignment of ", stringify!(mpc_bus))
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_bus>()).type_ as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_bus),
+            "::",
+            stringify!(type_)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_bus>()).busid as *const _ as usize },
+        1usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_bus),
+            "::",
+            stringify!(busid)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_bus>()).bustype as *const _ as usize },
+        2usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_bus),
+            "::",
+            stringify!(bustype)
+        )
+    );
+}
+impl Clone for mpc_bus {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpc_ioapic {
+    pub type_: ::std::os::raw::c_uchar,
+    pub apicid: ::std::os::raw::c_uchar,
+    pub apicver: ::std::os::raw::c_uchar,
+    pub flags: ::std::os::raw::c_uchar,
+    pub apicaddr: ::std::os::raw::c_uint,
+}
+#[test]
+fn bindgen_test_layout_mpc_ioapic() {
+    assert_eq!(
+        ::std::mem::size_of::<mpc_ioapic>(),
+        8usize,
+        concat!("Size of: ", stringify!(mpc_ioapic))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpc_ioapic>(),
+        4usize,
+        concat!("Alignment of ", stringify!(mpc_ioapic))
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_ioapic>()).type_ as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_ioapic),
+            "::",
+            stringify!(type_)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_ioapic>()).apicid as *const _ as usize },
+        1usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_ioapic),
+            "::",
+            stringify!(apicid)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_ioapic>()).apicver as *const _ as usize },
+        2usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_ioapic),
+            "::",
+            stringify!(apicver)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_ioapic>()).flags as *const _ as usize },
+        3usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_ioapic),
+            "::",
+            stringify!(flags)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_ioapic>()).apicaddr as *const _ as usize },
+        4usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_ioapic),
+            "::",
+            stringify!(apicaddr)
+        )
+    );
+}
+impl Clone for mpc_ioapic {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpc_intsrc {
+    pub type_: ::std::os::raw::c_uchar,
+    pub irqtype: ::std::os::raw::c_uchar,
+    pub irqflag: ::std::os::raw::c_ushort,
+    pub srcbus: ::std::os::raw::c_uchar,
+    pub srcbusirq: ::std::os::raw::c_uchar,
+    pub dstapic: ::std::os::raw::c_uchar,
+    pub dstirq: ::std::os::raw::c_uchar,
+}
+#[test]
+fn bindgen_test_layout_mpc_intsrc() {
+    assert_eq!(
+        ::std::mem::size_of::<mpc_intsrc>(),
+        8usize,
+        concat!("Size of: ", stringify!(mpc_intsrc))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpc_intsrc>(),
+        2usize,
+        concat!("Alignment of ", stringify!(mpc_intsrc))
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_intsrc>()).type_ as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_intsrc),
+            "::",
+            stringify!(type_)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_intsrc>()).irqtype as *const _ as usize },
+        1usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_intsrc),
+            "::",
+            stringify!(irqtype)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_intsrc>()).irqflag as *const _ as usize },
+        2usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_intsrc),
+            "::",
+            stringify!(irqflag)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_intsrc>()).srcbus as *const _ as usize },
+        4usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_intsrc),
+            "::",
+            stringify!(srcbus)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_intsrc>()).srcbusirq as *const _ as usize },
+        5usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_intsrc),
+            "::",
+            stringify!(srcbusirq)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_intsrc>()).dstapic as *const _ as usize },
+        6usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_intsrc),
+            "::",
+            stringify!(dstapic)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_intsrc>()).dstirq as *const _ as usize },
+        7usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_intsrc),
+            "::",
+            stringify!(dstirq)
+        )
+    );
+}
+impl Clone for mpc_intsrc {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+pub const mp_irq_source_types_mp_INT: mp_irq_source_types = 0;
+pub const mp_irq_source_types_mp_NMI: mp_irq_source_types = 1;
+pub const mp_irq_source_types_mp_SMI: mp_irq_source_types = 2;
+pub const mp_irq_source_types_mp_ExtINT: mp_irq_source_types = 3;
+pub type mp_irq_source_types = ::std::os::raw::c_uint;
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpc_lintsrc {
+    pub type_: ::std::os::raw::c_uchar,
+    pub irqtype: ::std::os::raw::c_uchar,
+    pub irqflag: ::std::os::raw::c_ushort,
+    pub srcbusid: ::std::os::raw::c_uchar,
+    pub srcbusirq: ::std::os::raw::c_uchar,
+    pub destapic: ::std::os::raw::c_uchar,
+    pub destapiclint: ::std::os::raw::c_uchar,
+}
+#[test]
+fn bindgen_test_layout_mpc_lintsrc() {
+    assert_eq!(
+        ::std::mem::size_of::<mpc_lintsrc>(),
+        8usize,
+        concat!("Size of: ", stringify!(mpc_lintsrc))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpc_lintsrc>(),
+        2usize,
+        concat!("Alignment of ", stringify!(mpc_lintsrc))
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_lintsrc>()).type_ as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_lintsrc),
+            "::",
+            stringify!(type_)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_lintsrc>()).irqtype as *const _ as usize },
+        1usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_lintsrc),
+            "::",
+            stringify!(irqtype)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_lintsrc>()).irqflag as *const _ as usize },
+        2usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_lintsrc),
+            "::",
+            stringify!(irqflag)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_lintsrc>()).srcbusid as *const _ as usize },
+        4usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_lintsrc),
+            "::",
+            stringify!(srcbusid)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_lintsrc>()).srcbusirq as *const _ as usize },
+        5usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_lintsrc),
+            "::",
+            stringify!(srcbusirq)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_lintsrc>()).destapic as *const _ as usize },
+        6usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_lintsrc),
+            "::",
+            stringify!(destapic)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_lintsrc>()).destapiclint as *const _ as usize },
+        7usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_lintsrc),
+            "::",
+            stringify!(destapiclint)
+        )
+    );
+}
+impl Clone for mpc_lintsrc {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+#[repr(C)]
+#[derive(Debug, Default, Copy)]
+pub struct mpc_oemtable {
+    pub signature: [::std::os::raw::c_char; 4usize],
+    pub length: ::std::os::raw::c_ushort,
+    pub rev: ::std::os::raw::c_char,
+    pub checksum: ::std::os::raw::c_char,
+    pub mpc: [::std::os::raw::c_char; 8usize],
+}
+#[test]
+fn bindgen_test_layout_mpc_oemtable() {
+    assert_eq!(
+        ::std::mem::size_of::<mpc_oemtable>(),
+        16usize,
+        concat!("Size of: ", stringify!(mpc_oemtable))
+    );
+    assert_eq!(
+        ::std::mem::align_of::<mpc_oemtable>(),
+        2usize,
+        concat!("Alignment of ", stringify!(mpc_oemtable))
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_oemtable>()).signature as *const _ as usize },
+        0usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_oemtable),
+            "::",
+            stringify!(signature)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_oemtable>()).length as *const _ as usize },
+        4usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_oemtable),
+            "::",
+            stringify!(length)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_oemtable>()).rev as *const _ as usize },
+        6usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_oemtable),
+            "::",
+            stringify!(rev)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_oemtable>()).checksum as *const _ as usize },
+        7usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_oemtable),
+            "::",
+            stringify!(checksum)
+        )
+    );
+    assert_eq!(
+        unsafe { &(*std::ptr::null::<mpc_oemtable>()).mpc as *const _ as usize },
+        8usize,
+        concat!(
+            "Alignment of field: ",
+            stringify!(mpc_oemtable),
+            "::",
+            stringify!(mpc)
+        )
+    );
+}
+impl Clone for mpc_oemtable {
+    fn clone(&self) -> Self {
+        *self
+    }
+}
+pub const mp_bustype_MP_BUS_ISA: mp_bustype = 1;
+pub const mp_bustype_MP_BUS_EISA: mp_bustype = 2;
+pub const mp_bustype_MP_BUS_PCI: mp_bustype = 3;
+pub type mp_bustype = ::std::os::raw::c_uint;

block_util/Cargo.toml

@@ -2,23 +2,23 @@
 name = "block_util"
 version = "0.1.0"
 authors = ["The Cloud Hypervisor Authors"]
-edition = "2021"
+edition = "2018"
 
 [features]
 default = []
+io_uring = []
 
 [dependencies]
-io-uring = "0.5.9"
-libc = "0.2.138"
-log = "0.4.17"
+io-uring = ">=0.4.0"
+libc = "0.2.91"
+log = "0.4.14"
 qcow = { path = "../qcow" }
-thiserror = "1.0.37"
-versionize = "0.1.9"
-versionize_derive = "0.1.4"
-vhdx = { path = "../vhdx" }
-virtio-bindings = { version = "0.1.0", features = ["virtio-v5_0_0"] }
-virtio-queue = "0.7.0"
-vm-memory = { version = "0.10.0", features = ["backend-mmap", "backend-atomic", "backend-bitmap"] }
+serde = ">=1.0.27"
+serde_derive = ">=1.0.27"
+serde_json = ">=1.0.9"
+thiserror = "1.0"
+virtio-bindings = { version = "0.1", features = ["virtio-v5_0_0"]}
+vm-memory = { version = "0.5.0", features = ["backend-mmap", "backend-atomic"] }
 vm-virtio = { path = "../vm-virtio" }
-vmm-sys-util = "0.11.0"
+vmm-sys-util = ">=0.3.1"
 

block_util/src/async_io.rs

@@ -2,13 +2,8 @@
 //
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
-use libc::{ioctl, S_IFBLK, S_IFMT};
-use std::convert::TryInto;
-use std::fs::File;
-use std::os::unix::io::AsRawFd;
 use thiserror::Error;
 use vmm_sys_util::eventfd::EventFd;
-use vmm_sys_util::{ioctl_io_nr, ioctl_ioc_nr};
 
 #[derive(Error, Debug)]
 pub enum DiskFileError {
@@ -20,96 +15,11 @@ pub enum DiskFileError {
     NewAsyncIo(#[source] std::io::Error),
 }
 
-#[derive(Debug)]
-pub struct DiskTopology {
-    pub logical_block_size: u64,
-    pub physical_block_size: u64,
-    pub minimum_io_size: u64,
-    pub optimal_io_size: u64,
-}
-
-impl Default for DiskTopology {
-    fn default() -> Self {
-        Self {
-            logical_block_size: 512,
-            physical_block_size: 512,
-            minimum_io_size: 512,
-            optimal_io_size: 0,
-        }
-    }
-}
-
-ioctl_io_nr!(BLKSSZGET, 0x12, 104);
-ioctl_io_nr!(BLKPBSZGET, 0x12, 123);
-ioctl_io_nr!(BLKIOMIN, 0x12, 120);
-ioctl_io_nr!(BLKIOOPT, 0x12, 121);
-
-enum BlockSize {
-    LogicalBlock,
-    PhysicalBlock,
-    MinimumIo,
-    OptimalIo,
-}
-
-impl DiskTopology {
-    fn is_block_device(f: &mut File) -> std::io::Result<bool> {
-        let mut stat = std::mem::MaybeUninit::<libc::stat>::uninit();
-        let ret = unsafe { libc::fstat(f.as_raw_fd(), stat.as_mut_ptr()) };
-        if ret != 0 {
-            return Err(std::io::Error::last_os_error());
-        }
-
-        let is_block = unsafe { (*stat.as_ptr()).st_mode & S_IFMT == S_IFBLK };
-        Ok(is_block)
-    }
-
-    // libc::ioctl() takes different types on different architectures
-    #[allow(clippy::useless_conversion)]
-    fn query_block_size(f: &mut File, block_size_type: BlockSize) -> std::io::Result<u64> {
-        let mut block_size = 0;
-        let ret = unsafe {
-            ioctl(
-                f.as_raw_fd(),
-                match block_size_type {
-                    BlockSize::LogicalBlock => BLKSSZGET(),
-                    BlockSize::PhysicalBlock => BLKPBSZGET(),
-                    BlockSize::MinimumIo => BLKIOMIN(),
-                    BlockSize::OptimalIo => BLKIOOPT(),
-                }
-                .try_into()
-                .unwrap(),
-                &mut block_size,
-            )
-        };
-        if ret != 0 {
-            return Err(std::io::Error::last_os_error());
-        };
-
-        Ok(block_size)
-    }
-
-    pub fn probe(f: &mut File) -> std::io::Result<Self> {
-        if !Self::is_block_device(f)? {
-            return Ok(DiskTopology::default());
-        }
-
-        Ok(DiskTopology {
-            logical_block_size: Self::query_block_size(f, BlockSize::LogicalBlock)?,
-            physical_block_size: Self::query_block_size(f, BlockSize::PhysicalBlock)?,
-            minimum_io_size: Self::query_block_size(f, BlockSize::MinimumIo)?,
-            optimal_io_size: Self::query_block_size(f, BlockSize::OptimalIo)?,
-        })
-    }
-}
-
 pub type DiskFileResult<T> = std::result::Result<T, DiskFileError>;
 
-pub trait DiskFile: Send {
+pub trait DiskFile: Send + Sync {
     fn size(&mut self) -> DiskFileResult<u64>;
     fn new_async_io(&self, ring_depth: u32) -> DiskFileResult<Box<dyn AsyncIo>>;
-    fn topology(&mut self) -> DiskTopology {
-        DiskTopology::default()
-    }
 }
 
 #[derive(Error, Debug)]
@@ -127,7 +37,7 @@ pub enum AsyncIoError {
 
 pub type AsyncIoResult<T> = std::result::Result<T, AsyncIoError>;
 
-pub trait AsyncIo: Send {
+pub trait AsyncIo: Send + Sync {
     fn notifier(&self) -> &EventFd;
     fn read_vectored(
         &mut self,

block_util/src/lib.rs

@@ -10,6 +10,8 @@
 
 #[macro_use]
 extern crate log;
+#[macro_use]
+extern crate serde_derive;
 
 pub mod async_io;
 pub mod fixed_vhd_async;
@@ -18,56 +20,48 @@ pub mod qcow_sync;
 pub mod raw_async;
 pub mod raw_sync;
 pub mod vhd;
-pub mod vhdx_sync;
 
-use crate::async_io::{AsyncIo, AsyncIoError, AsyncIoResult};
+use crate::async_io::{AsyncIo, AsyncIoError, AsyncIoResult, DiskFileError, DiskFileResult};
+#[cfg(feature = "io_uring")]
 use io_uring::{opcode, IoUring, Probe};
-use std::alloc::{alloc_zeroed, dealloc, Layout};
+use serde::ser::{Serialize, SerializeStruct, Serializer};
 use std::cmp;
 use std::convert::TryInto;
 use std::fs::File;
 use std::io::{self, IoSlice, IoSliceMut, Read, Seek, SeekFrom, Write};
 use std::os::linux::fs::MetadataExt;
+#[cfg(feature = "io_uring")]
+use std::os::unix::io::AsRawFd;
 use std::path::Path;
 use std::result;
-use std::sync::Arc;
-use std::sync::MutexGuard;
-use thiserror::Error;
-use versionize::{VersionMap, Versionize, VersionizeResult};
-use versionize_derive::Versionize;
+use std::sync::{Arc, Mutex};
 use virtio_bindings::bindings::virtio_blk::*;
-use virtio_queue::DescriptorChain;
-use vm_memory::{
-    bitmap::AtomicBitmap, bitmap::Bitmap, ByteValued, Bytes, GuestAddress, GuestMemory,
-    GuestMemoryError, GuestMemoryLoadGuard,
-};
-use vm_virtio::{AccessPlatform, Translatable};
+use vm_memory::{ByteValued, Bytes, GuestAddress, GuestMemory, GuestMemoryError, GuestMemoryMmap};
+use vm_virtio::DescriptorChain;
 use vmm_sys_util::eventfd::EventFd;
 
-type GuestMemoryMmap = vm_memory::GuestMemoryMmap<AtomicBitmap>;
-
 const SECTOR_SHIFT: u8 = 9;
 pub const SECTOR_SIZE: u64 = 0x01 << SECTOR_SHIFT;
 
-#[derive(Error, Debug)]
+#[derive(Debug)]
 pub enum Error {
-    #[error("Guest gave us bad memory addresses")]
+    /// Guest gave us bad memory addresses.
     GuestMemory(GuestMemoryError),
-    #[error("Guest gave us offsets that would have overflowed a usize")]
+    /// Guest gave us offsets that would have overflowed a usize.
     CheckedOffset(GuestAddress, usize),
-    #[error("Guest gave us a write only descriptor that protocol says to read from")]
+    /// Guest gave us a write only descriptor that protocol says to read from.
     UnexpectedWriteOnlyDescriptor,
-    #[error("Guest gave us a read only descriptor that protocol says to write to")]
+    /// Guest gave us a read only descriptor that protocol says to write to.
     UnexpectedReadOnlyDescriptor,
-    #[error("Guest gave us too few descriptors in a descriptor chain")]
+    /// Guest gave us too few descriptors in a descriptor chain.
     DescriptorChainTooShort,
-    #[error("Guest gave us a descriptor that was too short to use")]
+    /// Guest gave us a descriptor that was too short to use.
     DescriptorLengthTooSmall,
-    #[error("Getting a block's metadata fails for any reason")]
+    /// Getting a block's metadata fails for any reason.
     GetFileMetadata,
-    #[error("The requested operation would cause a seek beyond disk end")]
+    /// The requested operation would cause a seek beyond disk end.
     InvalidOffset,
-    #[error("The requested operation does not support multiple descriptors")]
+    /// The requested operation does not support multiple descriptors.
     TooManyDescriptors,
 }
 
@@ -103,32 +97,19 @@ pub fn build_disk_image_id(disk_path: &Path) -> Vec<u8> {
     default_disk_image_id
 }
 
-#[derive(Error, Debug)]
+#[derive(Debug)]
 pub enum ExecuteError {
-    #[error("Bad request: {0}")]
     BadRequest(Error),
-    #[error("Falied to flush: {0}")]
     Flush(io::Error),
-    #[error("Failed to read: {0}")]
     Read(GuestMemoryError),
-    #[error("Failed to seek: {0}")]
     Seek(io::Error),
-    #[error("Failed to write: {0}")]
     Write(GuestMemoryError),
-    #[error("Unsupported request: {0}")]
     Unsupported(u32),
-    #[error("Failed to submit io uring: {0}")]
     SubmitIoUring(io::Error),
-    #[error("Failed to get guest address: {0}")]
     GetHostAddress(GuestMemoryError),
-    #[error("Failed to async read: {0}")]
     AsyncRead(AsyncIoError),
-    #[error("Failed to async write: {0}")]
     AsyncWrite(AsyncIoError),
-    #[error("failed to async flush: {0}")]
     AsyncFlush(AsyncIoError),
-    #[error("Failed allocating a temporary buffer: {0}")]
-    TemporaryBufferAllocation(io::Error),
 }
 
 impl ExecuteError {
@@ -145,12 +126,11 @@ impl ExecuteError {
             ExecuteError::AsyncRead(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::AsyncWrite(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::AsyncFlush(_) => VIRTIO_BLK_S_IOERR,
-            ExecuteError::TemporaryBufferAllocation(_) => VIRTIO_BLK_S_IOERR,
         }
     }
 }
 
-#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+#[derive(Clone, Copy, Debug, PartialEq)]
 pub enum RequestType {
     In,
     Out,
@@ -183,14 +163,6 @@ fn sector(mem: &GuestMemoryMmap, desc_addr: GuestAddress) -> result::Result<u64,
     mem.read_obj(addr).map_err(Error::GuestMemory)
 }
 
-#[derive(Debug)]
-pub struct AlignedOperation {
-    origin_ptr: u64,
-    aligned_ptr: u64,
-    size: usize,
-    layout: Layout,
-}
-
 #[derive(Debug)]
 pub struct Request {
     pub request_type: RequestType,
@@ -198,43 +170,29 @@ pub struct Request {
     pub data_descriptors: Vec<(GuestAddress, u32)>,
     pub status_addr: GuestAddress,
     pub writeback: bool,
-    pub aligned_operations: Vec<AlignedOperation>,
 }
 
 impl Request {
     pub fn parse(
-        desc_chain: &mut DescriptorChain<GuestMemoryLoadGuard<GuestMemoryMmap>>,
-        access_platform: Option<&Arc<dyn AccessPlatform>>,
+        avail_desc: &DescriptorChain,
+        mem: &GuestMemoryMmap,
     ) -> result::Result<Request, Error> {
-        let hdr_desc = desc_chain
-            .next()
-            .ok_or(Error::DescriptorChainTooShort)
-            .map_err(|e| {
-                error!("Missing head descriptor");
-                e
-            })?;
-
         // The head contains the request type which MUST be readable.
-        if hdr_desc.is_write_only() {
+        if avail_desc.is_write_only() {
             return Err(Error::UnexpectedWriteOnlyDescriptor);
         }
 
-        let hdr_desc_addr = hdr_desc
-            .addr()
-            .translate_gva(access_platform, hdr_desc.len() as usize);
-
         let mut req = Request {
-            request_type: request_type(desc_chain.memory(), hdr_desc_addr)?,
-            sector: sector(desc_chain.memory(), hdr_desc_addr)?,
+            request_type: request_type(&mem, avail_desc.addr)?,
+            sector: sector(&mem, avail_desc.addr)?,
             data_descriptors: Vec::new(),
             status_addr: GuestAddress(0),
             writeback: true,
-            aligned_operations: Vec::new(),
         };
 
         let status_desc;
-        let mut desc = desc_chain
-            .next()
+        let mut desc = avail_desc
+            .next_descriptor()
             .ok_or(Error::DescriptorChainTooShort)
             .map_err(|e| {
                 error!("Only head descriptor present: request = {:?}", req);
@@ -259,14 +217,9 @@ impl Request {
                 if !desc.is_write_only() && req.request_type == RequestType::GetDeviceId {
                     return Err(Error::UnexpectedReadOnlyDescriptor);
                 }
-
-                req.data_descriptors.push((
-                    desc.addr()
-                        .translate_gva(access_platform, desc.len() as usize),
-                    desc.len(),
-                ));
-                desc = desc_chain
-                    .next()
+                req.data_descriptors.push((desc.addr, desc.len));
+                desc = desc
+                    .next_descriptor()
                     .ok_or(Error::DescriptorChainTooShort)
                     .map_err(|e| {
                         error!("DescriptorChain corrupted: request = {:?}", req);
@@ -281,23 +234,22 @@ impl Request {
             return Err(Error::UnexpectedReadOnlyDescriptor);
         }
 
-        if status_desc.len() < 1 {
+        if status_desc.len < 1 {
             return Err(Error::DescriptorLengthTooSmall);
         }
 
-        req.status_addr = status_desc
-            .addr()
-            .translate_gva(access_platform, status_desc.len() as usize);
+        req.status_addr = status_desc.addr;
 
         Ok(req)
     }
 
+    #[allow(clippy::ptr_arg)]
     pub fn execute<T: Seek + Read + Write>(
         &self,
         disk: &mut T,
         disk_nsectors: u64,
         mem: &GuestMemoryMmap,
-        disk_id: &[u8],
+        disk_id: &Vec<u8>,
     ) -> result::Result<u32, ExecuteError> {
         disk.seek(SeekFrom::Start(self.sector << SECTOR_SHIFT))
             .map_err(ExecuteError::Seek)?;
@@ -332,7 +284,7 @@ impl Request {
                     if (*data_len as usize) < disk_id.len() {
                         return Err(ExecuteError::BadRequest(Error::InvalidOffset));
                     }
-                    mem.write_slice(disk_id, *data_addr)
+                    mem.write_slice(&disk_id.as_slice(), *data_addr)
                         .map_err(ExecuteError::Write)?;
                 }
                 RequestType::Unsupported(t) => return Err(ExecuteError::Unsupported(t)),
@@ -342,7 +294,7 @@ impl Request {
     }
 
     pub fn execute_async(
-        &mut self,
+        &self,
         mem: &GuestMemoryMmap,
         disk_nsectors: u64,
         disk_image: &mut dyn AsyncIo,
@@ -355,9 +307,6 @@ impl Request {
 
         let mut iovecs = Vec::new();
         for (data_addr, data_len) in &self.data_descriptors {
-            if *data_len == 0 {
-                continue;
-            }
             let mut top: u64 = u64::from(*data_len) / SECTOR_SIZE;
             if u64::from(*data_len) % SECTOR_SIZE != 0 {
                 top += 1;
@@ -369,52 +318,12 @@ impl Request {
                 return Err(ExecuteError::BadRequest(Error::InvalidOffset));
             }
 
-            let origin_ptr = mem
+            let buf = mem
                 .get_slice(*data_addr, *data_len as usize)
                 .map_err(ExecuteError::GetHostAddress)?
                 .as_ptr();
-
-            // Verify the buffer alignment.
-            // In case it's not properly aligned, an intermediate buffer is
-            // created with the correct alignment, and a copy from/to the
-            // origin buffer is performed, depending on the type of operation.
-            let iov_base = if (origin_ptr as u64) % SECTOR_SIZE != 0 {
-                let layout =
-                    Layout::from_size_align(*data_len as usize, SECTOR_SIZE as usize).unwrap();
-                // Safe because layout has non-zero size
-                let aligned_ptr = unsafe { alloc_zeroed(layout) };
-                if aligned_ptr.is_null() {
-                    return Err(ExecuteError::TemporaryBufferAllocation(
-                        io::Error::last_os_error(),
-                    ));
-                }
-
-                // We need to perform the copy beforehand in case we're writing
-                // data out.
-                if request_type == RequestType::Out {
-                    // Safe because destination buffer has been allocated with
-                    // the proper size.
-                    unsafe {
-                        std::ptr::copy(origin_ptr as *const u8, aligned_ptr, *data_len as usize)
-                    };
-                }
-
-                // Store both origin and aligned pointers for complete_async()
-                // to process them.
-                self.aligned_operations.push(AlignedOperation {
-                    origin_ptr: origin_ptr as u64,
-                    aligned_ptr: aligned_ptr as u64,
-                    size: *data_len as usize,
-                    layout,
-                });
-
-                aligned_ptr as *mut libc::c_void
-            } else {
-                origin_ptr as *mut libc::c_void
-            };
-
             let iovec = libc::iovec {
-                iov_base,
+                iov_base: buf as *mut libc::c_void,
                 iov_len: *data_len as libc::size_t,
             };
             iovecs.push(iovec);
@@ -423,12 +332,6 @@ impl Request {
         // Queue operations expected to be submitted.
         match request_type {
             RequestType::In => {
-                for (data_addr, data_len) in &self.data_descriptors {
-                    mem.get_slice(*data_addr, *data_len as usize)
-                        .map_err(ExecuteError::GetHostAddress)?
-                        .bitmap()
-                        .mark_dirty(0, *data_len as usize);
-                }
                 disk_image
                     .read_vectored(offset, iovecs, user_data)
                     .map_err(ExecuteError::AsyncRead)?;
@@ -462,42 +365,12 @@ impl Request {
         Ok(true)
     }
 
-    pub fn complete_async(&mut self) -> result::Result<(), Error> {
-        for aligned_operation in self.aligned_operations.drain(..) {
-            // We need to perform the copy after the data has been read inside
-            // the aligned buffer in case we're reading data in.
-            if self.request_type == RequestType::In {
-                // Safe because origin buffer has been allocated with the
-                // proper size.
-                unsafe {
-                    std::ptr::copy(
-                        aligned_operation.aligned_ptr as *const u8,
-                        aligned_operation.origin_ptr as *mut u8,
-                        aligned_operation.size,
-                    )
-                };
-            }
-
-            // Free the temporary aligned buffer.
-            // Safe because aligned_ptr was allocated by alloc_zeroed with the same
-            // layout
-            unsafe {
-                dealloc(
-                    aligned_operation.aligned_ptr as *mut u8,
-                    aligned_operation.layout,
-                )
-            };
-        }
-
-        Ok(())
-    }
-
     pub fn set_writeback(&mut self, writeback: bool) {
         self.writeback = writeback
     }
 }
 
-#[derive(Copy, Clone, Debug, Default, Versionize)]
+#[derive(Copy, Clone, Debug, Default, Deserialize)]
 #[repr(C, packed)]
 pub struct VirtioBlockConfig {
     pub capacity: u64,
@@ -520,7 +393,66 @@ pub struct VirtioBlockConfig {
     pub write_zeroes_may_unmap: u8,
     pub unused1: [u8; 3],
 }
-#[derive(Copy, Clone, Debug, Default, Versionize)]
+
+// We must explicitly implement Serialize since the structure is packed and
+// it's unsafe to borrow from a packed structure. And by default, if we derive
+// Serialize from serde, it will borrow the values from the structure.
+// That's why this implementation copies each field separately before it
+// serializes the entire structure field by field.
+impl Serialize for VirtioBlockConfig {
+    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: Serializer,
+    {
+        let capacity = self.capacity;
+        let size_max = self.size_max;
+        let seg_max = self.seg_max;
+        let geometry = self.geometry;
+        let blk_size = self.blk_size;
+        let physical_block_exp = self.physical_block_exp;
+        let alignment_offset = self.alignment_offset;
+        let min_io_size = self.min_io_size;
+        let opt_io_size = self.opt_io_size;
+        let writeback = self.writeback;
+        let unused = self.unused;
+        let num_queues = self.num_queues;
+        let max_discard_sectors = self.max_discard_sectors;
+        let max_discard_seg = self.max_discard_seg;
+        let discard_sector_alignment = self.discard_sector_alignment;
+        let max_write_zeroes_sectors = self.max_write_zeroes_sectors;
+        let max_write_zeroes_seg = self.max_write_zeroes_seg;
+        let write_zeroes_may_unmap = self.write_zeroes_may_unmap;
+        let unused1 = self.unused1;
+
+        let mut virtio_block_config = serializer.serialize_struct("VirtioBlockConfig", 60)?;
+        virtio_block_config.serialize_field("capacity", &capacity)?;
+        virtio_block_config.serialize_field("size_max", &size_max)?;
+        virtio_block_config.serialize_field("seg_max", &seg_max)?;
+        virtio_block_config.serialize_field("geometry", &geometry)?;
+        virtio_block_config.serialize_field("blk_size", &blk_size)?;
+        virtio_block_config.serialize_field("physical_block_exp", &physical_block_exp)?;
+        virtio_block_config.serialize_field("alignment_offset", &alignment_offset)?;
+        virtio_block_config.serialize_field("min_io_size", &min_io_size)?;
+        virtio_block_config.serialize_field("opt_io_size", &opt_io_size)?;
+        virtio_block_config.serialize_field("writeback", &writeback)?;
+        virtio_block_config.serialize_field("unused", &unused)?;
+        virtio_block_config.serialize_field("num_queues", &num_queues)?;
+        virtio_block_config.serialize_field("max_discard_sectors", &max_discard_sectors)?;
+        virtio_block_config.serialize_field("max_discard_seg", &max_discard_seg)?;
+        virtio_block_config
+            .serialize_field("discard_sector_alignment", &discard_sector_alignment)?;
+        virtio_block_config
+            .serialize_field("max_write_zeroes_sectors", &max_write_zeroes_sectors)?;
+        virtio_block_config.serialize_field("max_write_zeroes_seg", &max_write_zeroes_seg)?;
+        virtio_block_config.serialize_field("write_zeroes_may_unmap", &write_zeroes_may_unmap)?;
+        virtio_block_config.serialize_field("unused1", &unused1)?;
+        virtio_block_config.end()
+    }
+}
+
+unsafe impl ByteValued for VirtioBlockConfig {}
+
+#[derive(Copy, Clone, Debug, Default, Deserialize)]
 #[repr(C, packed)]
 pub struct VirtioBlockGeometry {
     pub cylinders: u16,
@@ -528,12 +460,33 @@ pub struct VirtioBlockGeometry {
     pub sectors: u8,
 }
 
-// SAFETY: these data structures only contain a series of integers
-unsafe impl ByteValued for VirtioBlockConfig {}
+// We must explicitly implement Serialize since the structure is packed and
+// it's unsafe to borrow from a packed structure. And by default, if we derive
+// Serialize from serde, it will borrow the values from the structure.
+// That's why this implementation copies each field separately before it
+// serializes the entire structure field by field.
+impl Serialize for VirtioBlockGeometry {
+    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: Serializer,
+    {
+        let cylinders = self.cylinders;
+        let heads = self.heads;
+        let sectors = self.sectors;
+
+        let mut virtio_block_geometry = serializer.serialize_struct("VirtioBlockGeometry", 4)?;
+        virtio_block_geometry.serialize_field("cylinders", &cylinders)?;
+        virtio_block_geometry.serialize_field("heads", &heads)?;
+        virtio_block_geometry.serialize_field("sectors", &sectors)?;
+        virtio_block_geometry.end()
+    }
+}
+
 unsafe impl ByteValued for VirtioBlockGeometry {}
 
 /// Check if io_uring for block device can be used on the current system, as
 /// it correctly supports the expected io_uring features.
+#[cfg(feature = "io_uring")]
 pub fn block_io_uring_is_supported() -> bool {
     let error_msg = "io_uring not supported:";
 
@@ -549,6 +502,25 @@ pub fn block_io_uring_is_supported() -> bool {
 
     let submitter = io_uring.submitter();
 
+    let event_fd = match EventFd::new(libc::EFD_NONBLOCK) {
+        Ok(fd) => fd,
+        Err(e) => {
+            info!("{} failed to create eventfd: {}", error_msg, e);
+            return false;
+        }
+    };
+
+    // Check we can register an eventfd as this is going to be needed while
+    // using io_uring with the virtio block device. This also validates that
+    // io_uring_register() syscall is supported.
+    match submitter.register_eventfd(event_fd.as_raw_fd()) {
+        Ok(_) => {}
+        Err(e) => {
+            info!("{} failed to register eventfd: {}", error_msg, e);
+            return false;
+        }
+    }
+
     let mut probe = Probe::new();
 
     // Check we can register a probe to validate supported operations.
@@ -566,124 +538,143 @@ pub fn block_io_uring_is_supported() -> bool {
         return false;
     }
 
-    // Check IORING_OP_READV is supported
-    if !probe.is_supported(opcode::Readv::CODE) {
-        info!("{} IORING_OP_READV operation not supported", error_msg);
+    // Check IORING_OP_READ is supported
+    if !probe.is_supported(opcode::Read::CODE) {
+        info!("{} IORING_OP_READ operation not supported", error_msg);
         return false;
     }
 
-    // Check IORING_OP_WRITEV is supported
-    if !probe.is_supported(opcode::Writev::CODE) {
-        info!("{} IORING_OP_WRITEV operation not supported", error_msg);
+    // Check IORING_OP_WRITE is supported
+    if !probe.is_supported(opcode::Write::CODE) {
+        info!("{} IORING_OP_WRITE operation not supported", error_msg);
         return false;
     }
 
     true
 }
 
-pub trait AsyncAdaptor<F>
-where
-    F: Read + Write + Seek,
-{
-    fn read_vectored_sync(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: Vec<libc::iovec>,
-        user_data: u64,
-        eventfd: &EventFd,
-        completion_list: &mut Vec<(u64, i32)>,
-    ) -> AsyncIoResult<()> {
-        // Convert libc::iovec into IoSliceMut
-        let mut slices = Vec::new();
-        for iovec in iovecs.iter() {
-            slices.push(IoSliceMut::new(unsafe { std::mem::transmute(*iovec) }));
-        }
+#[cfg(not(feature = "io_uring"))]
+pub fn block_io_uring_is_supported() -> bool {
+    false
+}
 
-        let result = {
-            let mut file = self.file();
+pub fn disk_size(file: &mut dyn Seek, semaphore: &mut Arc<Mutex<()>>) -> DiskFileResult<u64> {
+    // Take the semaphore to ensure other threads are not interacting with
+    // the underlying file.
+    let _lock = semaphore.lock().unwrap();
 
-            // Move the cursor to the right offset
-            file.seek(SeekFrom::Start(offset as u64))
-                .map_err(AsyncIoError::ReadVectored)?;
+    Ok(file.seek(SeekFrom::End(0)).map_err(DiskFileError::Size)? as u64)
+}
 
-            // Read vectored
-            file.read_vectored(slices.as_mut_slice())
-                .map_err(AsyncIoError::ReadVectored)?
-        };
+pub trait ReadSeekFile: Read + Seek {}
+impl<F: Read + Seek> ReadSeekFile for F {}
 
-        completion_list.push((user_data, result as i32));
+pub fn read_vectored_sync(
+    offset: libc::off_t,
+    iovecs: Vec<libc::iovec>,
+    user_data: u64,
+    file: &mut dyn ReadSeekFile,
+    eventfd: &EventFd,
+    completion_list: &mut Vec<(u64, i32)>,
+    semaphore: &mut Arc<Mutex<()>>,
+) -> AsyncIoResult<()> {
+    // Convert libc::iovec into IoSliceMut
+    let mut slices = Vec::new();
+    for iovec in iovecs.iter() {
+        slices.push(IoSliceMut::new(unsafe { std::mem::transmute(*iovec) }));
+    }
+
+    let result = {
+        // Take the semaphore to ensure other threads are not interacting
+        // with the underlying file.
+        let _lock = semaphore.lock().unwrap();
+
+        // Move the cursor to the right offset
+        file.seek(SeekFrom::Start(offset as u64))
+            .map_err(AsyncIoError::ReadVectored)?;
+
+        // Read vectored
+        file.read_vectored(slices.as_mut_slice())
+            .map_err(AsyncIoError::ReadVectored)?
+    };
+
+    completion_list.push((user_data, result as i32));
+    eventfd.write(1).unwrap();
+
+    Ok(())
+}
+
+pub trait WriteSeekFile: Write + Seek {}
+impl<F: Write + Seek> WriteSeekFile for F {}
+
+pub fn write_vectored_sync(
+    offset: libc::off_t,
+    iovecs: Vec<libc::iovec>,
+    user_data: u64,
+    file: &mut dyn WriteSeekFile,
+    eventfd: &EventFd,
+    completion_list: &mut Vec<(u64, i32)>,
+    semaphore: &mut Arc<Mutex<()>>,
+) -> AsyncIoResult<()> {
+    // Convert libc::iovec into IoSlice
+    let mut slices = Vec::new();
+    for iovec in iovecs.iter() {
+        slices.push(IoSlice::new(unsafe { std::mem::transmute(*iovec) }));
+    }
+
+    let result = {
+        // Take the semaphore to ensure other threads are not interacting
+        // with the underlying file.
+        let _lock = semaphore.lock().unwrap();
+
+        // Move the cursor to the right offset
+        file.seek(SeekFrom::Start(offset as u64))
+            .map_err(AsyncIoError::WriteVectored)?;
+
+        // Write vectored
+        file.write_vectored(slices.as_slice())
+            .map_err(AsyncIoError::WriteVectored)?
+    };
+
+    completion_list.push((user_data, result as i32));
+    eventfd.write(1).unwrap();
+
+    Ok(())
+}
+
+pub fn fsync_sync(
+    user_data: Option<u64>,
+    file: &mut dyn Write,
+    eventfd: &EventFd,
+    completion_list: &mut Vec<(u64, i32)>,
+    semaphore: &mut Arc<Mutex<()>>,
+) -> AsyncIoResult<()> {
+    let result: i32 = {
+        // Take the semaphore to ensure other threads are not interacting
+        // with the underlying file.
+        let _lock = semaphore.lock().unwrap();
+
+        // Flush
+        file.flush().map_err(AsyncIoError::Fsync)?;
+
+        0
+    };
+
+    if let Some(user_data) = user_data {
+        completion_list.push((user_data, result));
         eventfd.write(1).unwrap();
-
-        Ok(())
     }
 
-    fn write_vectored_sync(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: Vec<libc::iovec>,
-        user_data: u64,
-        eventfd: &EventFd,
-        completion_list: &mut Vec<(u64, i32)>,
-    ) -> AsyncIoResult<()> {
-        // Convert libc::iovec into IoSlice
-        let mut slices = Vec::new();
-        for iovec in iovecs.iter() {
-            slices.push(IoSlice::new(unsafe { std::mem::transmute(*iovec) }));
-        }
-
-        let result = {
-            let mut file = self.file();
-
-            // Move the cursor to the right offset
-            file.seek(SeekFrom::Start(offset as u64))
-                .map_err(AsyncIoError::WriteVectored)?;
-
-            // Write vectored
-            file.write_vectored(slices.as_slice())
-                .map_err(AsyncIoError::WriteVectored)?
-        };
-
-        completion_list.push((user_data, result as i32));
-        eventfd.write(1).unwrap();
-
-        Ok(())
-    }
-
-    fn fsync_sync(
-        &mut self,
-        user_data: Option<u64>,
-        eventfd: &EventFd,
-        completion_list: &mut Vec<(u64, i32)>,
-    ) -> AsyncIoResult<()> {
-        let result: i32 = {
-            let mut file = self.file();
-
-            // Flush
-            file.flush().map_err(AsyncIoError::Fsync)?;
-
-            0
-        };
-
-        if let Some(user_data) = user_data {
-            completion_list.push((user_data, result));
-            eventfd.write(1).unwrap();
-        }
-
-        Ok(())
-    }
-
-    fn file(&mut self) -> MutexGuard<F>;
+    Ok(())
 }
 
 pub enum ImageType {
     FixedVhd,
     Qcow2,
     Raw,
-    Vhdx,
 }
 
 const QCOW_MAGIC: u32 = 0x5146_49fb;
-const VHDX_SIGN: u64 = 0x656C_6966_7864_6876;
 
 /// Determine image type through file parsing.
 pub fn detect_image_type(f: &mut File) -> std::io::Result<ImageType> {
@@ -702,8 +693,6 @@ pub fn detect_image_type(f: &mut File) -> std::io::Result<ImageType> {
         ImageType::Qcow2
     } else if vhd::is_fixed_vhd(f)? {
         ImageType::FixedVhd
-    } else if u64::from_le_bytes(s.data[0..8].try_into().unwrap()) == VHDX_SIGN {
-        ImageType::Vhdx
     } else {
         ImageType::Raw
     };

block_util/src/qcow_sync.rs

@@ -2,61 +2,60 @@
 //
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
-use crate::async_io::{AsyncIo, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult};
-use crate::AsyncAdaptor;
-use qcow::{QcowFile, RawFile, Result as QcowResult};
+use crate::async_io::{AsyncIo, AsyncIoResult, DiskFile, DiskFileResult};
+use crate::{disk_size, fsync_sync, read_vectored_sync, write_vectored_sync};
+use qcow::{QcowFile, RawFile};
 use std::fs::File;
-use std::io::{Seek, SeekFrom};
-use std::sync::{Arc, Mutex, MutexGuard};
+use std::sync::{Arc, Mutex};
 use vmm_sys_util::eventfd::EventFd;
 
 pub struct QcowDiskSync {
-    qcow_file: Arc<Mutex<QcowFile>>,
+    qcow_file: QcowFile,
+    semaphore: Arc<Mutex<()>>,
 }
 
 impl QcowDiskSync {
-    pub fn new(file: File, direct_io: bool) -> QcowResult<Self> {
-        Ok(QcowDiskSync {
-            qcow_file: Arc::new(Mutex::new(QcowFile::from(RawFile::new(file, direct_io))?)),
-        })
+    pub fn new(file: File, direct_io: bool) -> Self {
+        QcowDiskSync {
+            qcow_file: QcowFile::from(RawFile::new(file, direct_io))
+                .expect("Failed creating QcowFile"),
+            semaphore: Arc::new(Mutex::new(())),
+        }
     }
 }
 
 impl DiskFile for QcowDiskSync {
     fn size(&mut self) -> DiskFileResult<u64> {
-        let mut file = self.qcow_file.lock().unwrap();
-
-        file.seek(SeekFrom::End(0)).map_err(DiskFileError::Size)
+        disk_size(&mut self.qcow_file, &mut self.semaphore)
     }
 
     fn new_async_io(&self, _ring_depth: u32) -> DiskFileResult<Box<dyn AsyncIo>> {
-        Ok(Box::new(QcowSync::new(self.qcow_file.clone())) as Box<dyn AsyncIo>)
+        Ok(Box::new(QcowSync::new(
+            self.qcow_file.clone(),
+            self.semaphore.clone(),
+        )) as Box<dyn AsyncIo>)
     }
 }
 
 pub struct QcowSync {
-    qcow_file: Arc<Mutex<QcowFile>>,
+    qcow_file: QcowFile,
     eventfd: EventFd,
     completion_list: Vec<(u64, i32)>,
+    semaphore: Arc<Mutex<()>>,
 }
 
 impl QcowSync {
-    pub fn new(qcow_file: Arc<Mutex<QcowFile>>) -> Self {
+    pub fn new(qcow_file: QcowFile, semaphore: Arc<Mutex<()>>) -> Self {
         QcowSync {
             qcow_file,
             eventfd: EventFd::new(libc::EFD_NONBLOCK)
                 .expect("Failed creating EventFd for QcowSync"),
             completion_list: Vec::new(),
+            semaphore,
         }
     }
 }
 
-impl AsyncAdaptor<QcowFile> for Arc<Mutex<QcowFile>> {
-    fn file(&mut self) -> MutexGuard<QcowFile> {
-        self.lock().unwrap()
-    }
-}
-
 impl AsyncIo for QcowSync {
     fn notifier(&self) -> &EventFd {
         &self.eventfd
@@ -68,12 +67,14 @@ impl AsyncIo for QcowSync {
         iovecs: Vec<libc::iovec>,
         user_data: u64,
     ) -> AsyncIoResult<()> {
-        self.qcow_file.read_vectored_sync(
+        read_vectored_sync(
             offset,
             iovecs,
             user_data,
+            &mut self.qcow_file,
             &self.eventfd,
             &mut self.completion_list,
+            &mut self.semaphore,
         )
     }
 
@@ -83,18 +84,25 @@ impl AsyncIo for QcowSync {
         iovecs: Vec<libc::iovec>,
         user_data: u64,
     ) -> AsyncIoResult<()> {
-        self.qcow_file.write_vectored_sync(
+        write_vectored_sync(
             offset,
             iovecs,
             user_data,
+            &mut self.qcow_file,
             &self.eventfd,
             &mut self.completion_list,
+            &mut self.semaphore,
         )
     }
 
     fn fsync(&mut self, user_data: Option<u64>) -> AsyncIoResult<()> {
-        self.qcow_file
-            .fsync_sync(user_data, &self.eventfd, &mut self.completion_list)
+        fsync_sync(
+            user_data,
+            &mut self.qcow_file,
+            &self.eventfd,
+            &mut self.completion_list,
+            &mut self.semaphore,
+        )
     }
 
     fn complete(&mut self) -> Vec<(u64, i32)> {

block_util/src/raw_async.rs

@@ -3,7 +3,7 @@
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
 use crate::async_io::{
-    AsyncIo, AsyncIoError, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult, DiskTopology,
+    AsyncIo, AsyncIoError, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult,
 };
 use io_uring::{opcode, squeue, types, IoUring};
 use std::fs::File;
@@ -23,9 +23,10 @@ impl RawFileDisk {
 
 impl DiskFile for RawFileDisk {
     fn size(&mut self) -> DiskFileResult<u64> {
-        self.file
+        Ok(self
+            .file
             .seek(SeekFrom::End(0))
-            .map_err(DiskFileError::Size)
+            .map_err(DiskFileError::Size)? as u64)
     }
 
     fn new_async_io(&self, ring_depth: u32) -> DiskFileResult<Box<dyn AsyncIo>> {
@@ -34,15 +35,6 @@ impl DiskFile for RawFileDisk {
                 .map_err(DiskFileError::NewAsyncIo)?,
         ) as Box<dyn AsyncIo>)
     }
-
-    fn topology(&mut self) -> DiskTopology {
-        if let Ok(topology) = DiskTopology::probe(&mut self.file) {
-            topology
-        } else {
-            warn!("Unable to get device topology. Using default topology");
-            DiskTopology::default()
-        }
-    }
 }
 
 pub struct RawFileAsync {

block_util/src/raw_sync.rs

@@ -3,7 +3,7 @@
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
 use crate::async_io::{
-    AsyncIo, AsyncIoError, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult, DiskTopology,
+    AsyncIo, AsyncIoError, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult,
 };
 use std::fs::File;
 use std::io::{Seek, SeekFrom};
@@ -22,23 +22,15 @@ impl RawFileDiskSync {
 
 impl DiskFile for RawFileDiskSync {
     fn size(&mut self) -> DiskFileResult<u64> {
-        self.file
+        Ok(self
+            .file
             .seek(SeekFrom::End(0))
-            .map_err(DiskFileError::Size)
+            .map_err(DiskFileError::Size)? as u64)
     }
 
     fn new_async_io(&self, _ring_depth: u32) -> DiskFileResult<Box<dyn AsyncIo>> {
         Ok(Box::new(RawFileSync::new(self.file.as_raw_fd())) as Box<dyn AsyncIo>)
     }
-
-    fn topology(&mut self) -> DiskTopology {
-        if let Ok(topology) = DiskTopology::probe(&mut self.file) {
-            topology
-        } else {
-            warn!("Unable to get device topology. Using default topology");
-            DiskTopology::default()
-        }
-    }
 }
 
 pub struct RawFileSync {
@@ -117,7 +109,7 @@ impl AsyncIo for RawFileSync {
         }
 
         if let Some(user_data) = user_data {
-            self.completion_list.push((user_data, result));
+            self.completion_list.push((user_data, result as i32));
             self.eventfd.write(1).unwrap();
         }
 

block_util/src/vhd.rs

@@ -175,7 +175,7 @@ mod tests {
         let mut disk_file: File = TempFile::new().unwrap().into_file();
         disk_file.set_len(0x1000_0200).unwrap();
         disk_file.seek(SeekFrom::Start(0x1000_0000)).unwrap();
-        disk_file.write_all(footer).unwrap();
+        disk_file.write_all(&footer).unwrap();
 
         testfn(disk_file); // File closed when the function exits.
     }

block_util/src/vhdx_sync.rs

@@ -1,102 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-
-use crate::async_io::{AsyncIo, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult};
-use crate::AsyncAdaptor;
-use std::fs::File;
-use std::sync::{Arc, Mutex, MutexGuard};
-use vhdx::vhdx::{Result as VhdxResult, Vhdx};
-use vmm_sys_util::eventfd::EventFd;
-
-pub struct VhdxDiskSync {
-    vhdx_file: Arc<Mutex<Vhdx>>,
-}
-
-impl VhdxDiskSync {
-    pub fn new(f: File) -> VhdxResult<Self> {
-        Ok(VhdxDiskSync {
-            vhdx_file: Arc::new(Mutex::new(Vhdx::new(f)?)),
-        })
-    }
-}
-
-impl DiskFile for VhdxDiskSync {
-    fn size(&mut self) -> DiskFileResult<u64> {
-        Ok(self.vhdx_file.lock().unwrap().virtual_disk_size())
-    }
-
-    fn new_async_io(&self, _ring_depth: u32) -> DiskFileResult<Box<dyn AsyncIo>> {
-        Ok(
-            Box::new(VhdxSync::new(self.vhdx_file.clone()).map_err(DiskFileError::NewAsyncIo)?)
-                as Box<dyn AsyncIo>,
-        )
-    }
-}
-
-pub struct VhdxSync {
-    vhdx_file: Arc<Mutex<Vhdx>>,
-    eventfd: EventFd,
-    completion_list: Vec<(u64, i32)>,
-}
-
-impl VhdxSync {
-    pub fn new(vhdx_file: Arc<Mutex<Vhdx>>) -> std::io::Result<Self> {
-        Ok(VhdxSync {
-            vhdx_file,
-            eventfd: EventFd::new(libc::EFD_NONBLOCK)?,
-            completion_list: Vec::new(),
-        })
-    }
-}
-
-impl AsyncAdaptor<Vhdx> for Arc<Mutex<Vhdx>> {
-    fn file(&mut self) -> MutexGuard<Vhdx> {
-        self.lock().unwrap()
-    }
-}
-
-impl AsyncIo for VhdxSync {
-    fn notifier(&self) -> &EventFd {
-        &self.eventfd
-    }
-
-    fn read_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: Vec<libc::iovec>,
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        self.vhdx_file.read_vectored_sync(
-            offset,
-            iovecs,
-            user_data,
-            &self.eventfd,
-            &mut self.completion_list,
-        )
-    }
-
-    fn write_vectored(
-        &mut self,
-        offset: libc::off_t,
-        iovecs: Vec<libc::iovec>,
-        user_data: u64,
-    ) -> AsyncIoResult<()> {
-        self.vhdx_file.write_vectored_sync(
-            offset,
-            iovecs,
-            user_data,
-            &self.eventfd,
-            &mut self.completion_list,
-        )
-    }
-
-    fn fsync(&mut self, user_data: Option<u64>) -> AsyncIoResult<()> {
-        self.vhdx_file
-            .fsync_sync(user_data, &self.eventfd, &mut self.completion_list)
-    }
-
-    fn complete(&mut self) -> Vec<(u64, i32)> {
-        self.completion_list.drain(..).collect()
-    }
-}

build.rs

@@ -11,7 +11,7 @@ use std::process::Command;
 fn main() {
     let mut version = "v".to_owned() + crate_version!();
 
-    if let Ok(git_out) = Command::new("git").args(["describe", "--dirty"]).output() {
+    if let Ok(git_out) = Command::new("git").args(&["describe", "--dirty"]).output() {
         if git_out.status.success() {
             if let Ok(git_out_str) = String::from_utf8(git_out.stdout) {
                 version = git_out_str;
@@ -23,5 +23,5 @@ fn main() {
     // variable BUILT_VERSION, so that it can be reused from the binary.
     // Particularly, this is used from src/main.rs to display the exact
     // version.
-    println!("cargo:rustc-env=BUILT_VERSION={version}");
+    println!("cargo:rustc-env=BUILT_VERSION={}", version);
 }

devices/Cargo.toml

@@ -2,29 +2,25 @@
 name = "devices"
 version = "0.1.0"
 authors = ["The Chromium OS Authors"]
-edition = "2021"
 
 [dependencies]
-acpi_tables = { path = "../acpi_tables" }
-anyhow = "1.0.66"
-arch = { path = "../arch" }
-bitflags = "1.3.2"
+anyhow = "1.0"
+bitflags = ">=1.2.1"
 byteorder = "1.4.3"
-hypervisor = { path = "../hypervisor" }
-libc = "0.2.138"
-log = "0.4.17"
-phf = { version = "0.11.1", features = ["macros"] }
-thiserror = "1.0.37"
-tpm = { path = "../tpm" }
-versionize = "0.1.9"
-versionize_derive = "0.1.4"
+epoll = ">=4.0.1"
+libc = "0.2.91"
+log = "0.4.14"
+serde = {version = ">=1.0.27", features = ["rc"] }
+serde_derive = ">=1.0.27"
+serde_json = ">=1.0.9"
 vm-device = { path = "../vm-device" }
-vm-memory = "0.10.0"
+acpi_tables = { path = "../acpi_tables", optional = true }
+vm-memory = "0.5.0"
 vm-migration = { path = "../vm-migration" }
-vmm-sys-util = "0.11.0"
-
-[target.'cfg(target_arch = "aarch64")'.dependencies]
-arch = { path = "../arch" }
+vmm-sys-util = ">=0.3.1"
 
 [features]
 default = []
+acpi = ["acpi_tables"]
+cmos = []
+fwdebug = []

devices/src/acpi.rs

@@ -3,7 +3,6 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
-use super::AcpiNotificationFlags;
 use acpi_tables::{aml, aml::Aml};
 use std::sync::{Arc, Barrier};
 use std::time::Instant;
@@ -11,6 +10,7 @@ use vm_device::interrupt::InterruptSourceGroup;
 use vm_device::BusDevice;
 use vm_memory::GuestAddress;
 use vmm_sys_util::eventfd::EventFd;
+use AcpiNotificationFlags;
 
 pub const GED_DEVICE_ACPI_SIZE: usize = 0x1;
 
@@ -34,12 +34,14 @@ impl AcpiShutdownDevice {
 impl BusDevice for AcpiShutdownDevice {
     // Spec has all fields as zero
     fn read(&mut self, _base: u64, _offset: u64, data: &mut [u8]) {
-        data.fill(0)
+        for i in data.iter_mut() {
+            *i = 0;
+        }
     }
 
     fn write(&mut self, _base: u64, _offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
         if data[0] == 1 {
-            info!("ACPI Reboot signalled");
+            debug!("ACPI Reboot signalled");
             if let Err(e) = self.reset_evt.write(1) {
                 error!("Error triggering ACPI reset event: {}", e);
             }
@@ -49,7 +51,8 @@ impl BusDevice for AcpiShutdownDevice {
         const SLEEP_STATUS_EN_BIT: u8 = 5;
         const SLEEP_VALUE_BIT: u8 = 2;
         if data[0] == (S5_SLEEP_VALUE << SLEEP_VALUE_BIT) | (1 << SLEEP_STATUS_EN_BIT) {
-            info!("ACPI Shutdown signalled");
+            debug!("ACPI Shutdown signalled");
+            extern crate bitflags;
             if let Err(e) = self.exit_evt.write(1) {
                 error!("Error triggering ACPI shutdown event: {}", e);
             }
@@ -60,7 +63,7 @@ impl BusDevice for AcpiShutdownDevice {
 
 /// A device for handling ACPI GED event generation
 pub struct AcpiGedDevice {
-    interrupt: Arc<dyn InterruptSourceGroup>,
+    interrupt: Arc<Box<dyn InterruptSourceGroup>>,
     notification_type: AcpiNotificationFlags,
     ged_irq: u32,
     address: GuestAddress,
@@ -68,7 +71,7 @@ pub struct AcpiGedDevice {
 
 impl AcpiGedDevice {
     pub fn new(
-        interrupt: Arc<dyn InterruptSourceGroup>,
+        interrupt: Arc<Box<dyn InterruptSourceGroup>>,
         ged_irq: u32,
         address: GuestAddress,
     ) -> AcpiGedDevice {
@@ -102,20 +105,22 @@ impl BusDevice for AcpiGedDevice {
     }
 }
 
+#[cfg(feature = "acpi")]
 impl Aml for AcpiGedDevice {
-    fn append_aml_bytes(&self, bytes: &mut Vec<u8>) {
+    fn to_aml_bytes(&self) -> Vec<u8> {
         aml::Device::new(
-            "_SB_.GEC_".into(),
+            "_SB_.GED_".into(),
             vec![
-                &aml::Name::new("_HID".into(), &aml::EisaName::new("PNP0A06")),
-                &aml::Name::new("_UID".into(), &"Generic Event Controller"),
+                &aml::Name::new("_HID".into(), &"ACPI0013"),
+                &aml::Name::new("_UID".into(), &aml::ZERO),
                 &aml::Name::new(
                     "_CRS".into(),
-                    &aml::ResourceTemplate::new(vec![&aml::AddressSpace::new_memory(
-                        aml::AddressSpaceCachable::NotCacheable,
+                    &aml::ResourceTemplate::new(vec![&aml::Interrupt::new(
                         true,
-                        self.address.0,
-                        self.address.0 + GED_DEVICE_ACPI_SIZE as u64 - 1,
+                        true,
+                        false,
+                        false,
+                        self.ged_irq,
                     )]),
                 ),
                 &aml::OpRegion::new(
@@ -131,8 +136,8 @@ impl Aml for AcpiGedDevice {
                     vec![aml::FieldEntry::Named(*b"GDAT", 8)],
                 ),
                 &aml::Method::new(
-                    "ESCN".into(),
-                    0,
+                    "_EVT".into(),
+                    1,
                     true,
                     vec![
                         &aml::Store::new(&aml::Local(0), &aml::Path::new("GDAT")),
@@ -149,7 +154,7 @@ impl Aml for AcpiGedDevice {
                         &aml::And::new(&aml::Local(1), &aml::Local(0), &4usize),
                         &aml::If::new(
                             &aml::Equal::new(&aml::Local(1), &4usize),
-                            vec![&aml::MethodCall::new("\\_SB_.PHPR.PSCN".into(), vec![])],
+                            vec![&aml::MethodCall::new("\\_SB_.PCI0.PCNT".into(), vec![])],
                         ),
                         &aml::And::new(&aml::Local(1), &aml::Local(0), &8usize),
                         &aml::If::new(
@@ -163,31 +168,7 @@ impl Aml for AcpiGedDevice {
                 ),
             ],
         )
-        .append_aml_bytes(bytes);
-        aml::Device::new(
-            "_SB_.GED_".into(),
-            vec![
-                &aml::Name::new("_HID".into(), &"ACPI0013"),
-                &aml::Name::new("_UID".into(), &aml::ZERO),
-                &aml::Name::new(
-                    "_CRS".into(),
-                    &aml::ResourceTemplate::new(vec![&aml::Interrupt::new(
-                        true,
-                        true,
-                        false,
-                        false,
-                        self.ged_irq,
-                    )]),
-                ),
-                &aml::Method::new(
-                    "_EVT".into(),
-                    1,
-                    true,
-                    vec![&aml::MethodCall::new("\\_SB_.GEC_.ESCN".into(), vec![])],
-                ),
-            ],
-        )
-        .append_aml_bytes(bytes)
+        .to_aml_bytes()
     }
 }
 
@@ -211,10 +192,6 @@ impl Default for AcpiPmTimerDevice {
 
 impl BusDevice for AcpiPmTimerDevice {
     fn read(&mut self, _base: u64, _offset: u64, data: &mut [u8]) {
-        if data.len() != std::mem::size_of::<u32>() {
-            warn!("Invalid sized read of PM timer: {}", data.len());
-            return;
-        }
         let now = Instant::now();
         let since = now.duration_since(self.start);
         let nanos = since.as_nanos();

devices/src/gic.rs

@@ -3,38 +3,28 @@
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
 use super::interrupt_controller::{Error, InterruptController};
-extern crate arch;
-use anyhow::anyhow;
-use arch::layout;
-use hypervisor::{
-    arch::aarch64::gic::{Vgic, VgicConfig},
-    CpuState,
-};
 use std::result;
-use std::sync::{Arc, Mutex};
+use std::sync::Arc;
 use vm_device::interrupt::{
     InterruptIndex, InterruptManager, InterruptSourceConfig, InterruptSourceGroup,
     LegacyIrqSourceConfig, MsiIrqGroupConfig,
 };
-use vm_memory::address::Address;
-use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
 use vmm_sys_util::eventfd::EventFd;
 
 type Result<T> = result::Result<T, Error>;
 
-// Reserve 32 IRQs for legacy devices.
-pub const IRQ_LEGACY_BASE: usize = layout::IRQ_BASE as usize;
+// Reserve 32 IRQs for legacy device.
+pub const IRQ_LEGACY_BASE: usize = 0;
 pub const IRQ_LEGACY_COUNT: usize = 32;
 
-// Gic (Generic Interupt Controller) struct provides all the functionality of a
-// GIC device. It wraps a hypervisor-emulated GIC device (Vgic) provided by the
-// `hypervisor` crate.
-// Gic struct also implements InterruptController to provide interrupt delivery
-// service.
+// This Gic struct implements InterruptController to provide interrupt delivery service.
+// The Gic source files in arch/ folder maintain the Aarch64 specific Gic device.
+// The 2 Gic instances could be merged together.
+// Leave this refactoring to future. Two options may be considered:
+//   1. Move Gic*.rs from arch/ folder here.
+//   2. Move this file and ioapic.rs to arch/, as they are architecture specific.
 pub struct Gic {
-    interrupt_source_group: Arc<dyn InterruptSourceGroup>,
-    // The hypervisor agnostic virtual GIC
-    vgic: Option<Arc<Mutex<dyn Vgic>>>,
+    interrupt_source_group: Arc<Box<dyn InterruptSourceGroup>>,
 }
 
 impl Gic {
@@ -51,40 +41,8 @@ impl Gic {
 
         Ok(Gic {
             interrupt_source_group,
-            vgic: None,
         })
     }
-
-    /// Default config implied by arch::layout
-    pub fn create_default_config(vcpu_count: u64) -> VgicConfig {
-        let redists_size = layout::GIC_V3_REDIST_SIZE * vcpu_count;
-        let redists_addr = layout::GIC_V3_DIST_START.raw_value() - redists_size;
-        VgicConfig {
-            vcpu_count,
-            dist_addr: layout::GIC_V3_DIST_START.raw_value(),
-            dist_size: layout::GIC_V3_DIST_SIZE,
-            redists_addr,
-            redists_size,
-            msi_addr: redists_addr - layout::GIC_V3_ITS_SIZE,
-            msi_size: layout::GIC_V3_ITS_SIZE,
-            nr_irqs: layout::IRQ_NUM,
-        }
-    }
-
-    pub fn create_vgic(
-        &mut self,
-        vm: &Arc<dyn hypervisor::Vm>,
-        config: VgicConfig,
-    ) -> Result<Arc<Mutex<dyn Vgic>>> {
-        let vgic = vm.create_vgic(config).map_err(Error::CreateGic)?;
-        self.vgic = Some(vgic.clone());
-        Ok(vgic.clone())
-    }
-
-    pub fn set_gicr_typers(&mut self, vcpu_states: &[CpuState]) {
-        let vgic = self.vgic.as_ref().unwrap().clone();
-        vgic.lock().unwrap().set_gicr_typers(vcpu_states);
-    }
 }
 
 impl InterruptController for Gic {
@@ -100,13 +58,12 @@ impl InterruptController for Gic {
         for i in IRQ_LEGACY_BASE..(IRQ_LEGACY_BASE + IRQ_LEGACY_COUNT) {
             let config = LegacyIrqSourceConfig {
                 irqchip: 0,
-                pin: (i - IRQ_LEGACY_BASE) as u32,
+                pin: i as u32,
             };
             self.interrupt_source_group
                 .update(
                     i as InterruptIndex,
                     InterruptSourceConfig::LegacyIrq(config),
-                    false,
                 )
                 .map_err(Error::EnableInterrupt)?;
         }
@@ -127,43 +84,3 @@ impl InterruptController for Gic {
         self.interrupt_source_group.notifier(irq as InterruptIndex)
     }
 }
-
-pub const GIC_V3_ITS_SNAPSHOT_ID: &str = "gic-v3-its";
-impl Snapshottable for Gic {
-    fn id(&self) -> String {
-        GIC_V3_ITS_SNAPSHOT_ID.to_string()
-    }
-
-    fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        let vgic = self.vgic.as_ref().unwrap().clone();
-        let state = vgic.lock().unwrap().state().unwrap();
-        Snapshot::new_from_state(&self.id(), &state)
-    }
-
-    fn restore(&mut self, snapshot: Snapshot) -> std::result::Result<(), MigratableError> {
-        let vgic = self.vgic.as_ref().unwrap().clone();
-        vgic.lock()
-            .unwrap()
-            .set_state(&snapshot.to_state(&self.id())?)
-            .map_err(|e| {
-                MigratableError::Restore(anyhow!("Could not restore GICv3ITS state {:?}", e))
-            })?;
-        Ok(())
-    }
-}
-
-impl Pausable for Gic {
-    fn pause(&mut self) -> std::result::Result<(), MigratableError> {
-        // Flush tables to guest RAM
-        let vgic = self.vgic.as_ref().unwrap().clone();
-        vgic.lock().unwrap().save_data_tables().map_err(|e| {
-            MigratableError::Pause(anyhow!(
-                "Could not save GICv3ITS GIC pending tables {:?}",
-                e
-            ))
-        })?;
-        Ok(())
-    }
-}
-impl Transportable for Gic {}
-impl Migratable for Gic {}

devices/src/interrupt_controller.rs

@@ -24,8 +24,6 @@ pub enum Error {
     UpdateInterrupt(io::Error),
     /// Failed enabling the interrupt.
     EnableInterrupt(io::Error),
-    /// Failed creating GIC device.
-    CreateGic(hypervisor::HypervisorVmError),
 }
 
 type Result<T> = result::Result<T, Error>;

devices/src/ioapic.rs

@@ -14,8 +14,6 @@ use anyhow::anyhow;
 use byteorder::{ByteOrder, LittleEndian};
 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,
@@ -23,10 +21,15 @@ use vm_device::interrupt::{
 use vm_device::BusDevice;
 use vm_memory::GuestAddress;
 use vm_migration::{
-    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
+    Migratable, MigratableError, Pausable, Snapshot, SnapshotDataSection, Snapshottable,
+    Transportable,
 };
 use vmm_sys_util::eventfd::EventFd;
 
+#[derive(Serialize, Deserialize)]
+#[serde(remote = "GuestAddress")]
+pub struct GuestAddressDef(pub u64);
+
 type Result<T> = result::Result<T, Error>;
 
 // I/O REDIRECTION TABLE REGISTER
@@ -134,25 +137,22 @@ pub struct Ioapic {
     reg_entries: [RedirectionTableEntry; NUM_IOAPIC_PINS],
     used_entries: [bool; NUM_IOAPIC_PINS],
     apic_address: GuestAddress,
-    interrupt_source_group: Arc<dyn InterruptSourceGroup>,
+    interrupt_source_group: Arc<Box<dyn InterruptSourceGroup>>,
 }
 
-#[derive(Versionize)]
+#[derive(Serialize, Deserialize)]
 pub struct IoapicState {
     id_reg: u32,
     reg_sel: u32,
     reg_entries: [RedirectionTableEntry; NUM_IOAPIC_PINS],
     used_entries: [bool; NUM_IOAPIC_PINS],
-    apic_address: u64,
+    #[serde(with = "GuestAddressDef")]
+    apic_address: GuestAddress,
 }
-impl VersionMapped for IoapicState {}
 
 impl BusDevice for Ioapic {
     fn read(&mut self, _base: u64, offset: u64, data: &mut [u8]) {
-        if data.len() != std::mem::size_of::<u32>() {
-            warn!("Invalid read size on IOAPIC: {}", data.len());
-            return;
-        }
+        assert!(data.len() == 4);
 
         debug!("IOAPIC_R @ offset 0x{:x}", offset);
 
@@ -169,10 +169,7 @@ impl BusDevice for Ioapic {
     }
 
     fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
-        if data.len() != std::mem::size_of::<u32>() {
-            warn!("Invalid write size on IOAPIC: {}", data.len());
-            return None;
-        }
+        assert!(data.len() == 4);
 
         debug!("IOAPIC_W @ offset 0x{:x}", offset);
 
@@ -232,10 +229,6 @@ impl Ioapic {
             IOAPIC_REG_ID => self.id_reg = (val >> 24) & 0xf,
             IOWIN_OFF..=REG_MAX_OFFSET => {
                 let (index, is_high_bits) = decode_irq_from_selector(self.reg_sel as u8);
-                if index > NUM_IOAPIC_PINS {
-                    warn!("IOAPIC index out of range: {}", index);
-                    return;
-                }
                 if is_high_bits {
                     self.reg_entries[index] &= 0xffff_ffff;
                     self.reg_entries[index] |= u64::from(val) << 32;
@@ -269,10 +262,6 @@ impl Ioapic {
             IOAPIC_REG_ID | IOAPIC_REG_ARBITRATION_ID => (self.id_reg & 0xf) << 24,
             IOWIN_OFF..=REG_MAX_OFFSET => {
                 let (index, is_high_bits) = decode_irq_from_selector(self.reg_sel as u8);
-                if index > NUM_IOAPIC_PINS {
-                    warn!("IOAPIC index out of range: {}", index);
-                    return 0;
-                }
                 if is_high_bits {
                     (self.reg_entries[index] >> 32) as u32
                 } else {
@@ -295,7 +284,7 @@ impl Ioapic {
             reg_sel: self.reg_sel,
             reg_entries: self.reg_entries,
             used_entries: self.used_entries,
-            apic_address: self.apic_address.0,
+            apic_address: self.apic_address,
         }
     }
 
@@ -304,7 +293,7 @@ impl Ioapic {
         self.reg_sel = state.reg_sel;
         self.reg_entries = state.reg_entries;
         self.used_entries = state.used_entries;
-        self.apic_address = GuestAddress(state.apic_address);
+        self.apic_address = state.apic_address;
         for (irq, entry) in self.used_entries.iter().enumerate() {
             if *entry {
                 self.update_entry(irq)?;
@@ -367,13 +356,19 @@ impl Ioapic {
         };
 
         self.interrupt_source_group
-            .update(
-                irq as InterruptIndex,
-                InterruptSourceConfig::MsiIrq(config),
-                interrupt_mask(entry) == 1,
-            )
+            .update(irq as InterruptIndex, InterruptSourceConfig::MsiIrq(config))
             .map_err(Error::UpdateInterrupt)?;
 
+        if interrupt_mask(entry) == 1 {
+            self.interrupt_source_group
+                .mask(irq as InterruptIndex)
+                .map_err(Error::MaskInterrupt)?;
+        } else {
+            self.interrupt_source_group
+                .unmask(irq as InterruptIndex)
+                .map_err(Error::UnmaskInterrupt)?;
+        }
+
         Ok(())
     }
 }
@@ -423,18 +418,38 @@ impl Snapshottable for Ioapic {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        Snapshot::new_from_versioned_state(&self.id, &self.state())
+        let snapshot =
+            serde_json::to_vec(&self.state()).map_err(|e| MigratableError::Snapshot(e.into()))?;
+
+        let mut ioapic_snapshot = Snapshot::new(self.id.as_str());
+        ioapic_snapshot.add_data_section(SnapshotDataSection {
+            id: format!("{}-section", self.id),
+            snapshot,
+        });
+
+        Ok(ioapic_snapshot)
     }
 
     fn restore(&mut self, snapshot: Snapshot) -> std::result::Result<(), MigratableError> {
-        self.set_state(&snapshot.to_versioned_state(&self.id)?)
-            .map_err(|e| {
-                MigratableError::Restore(anyhow!(
-                    "Could not restore state for {}: {:?}",
-                    self.id,
-                    e
-                ))
-            })
+        if let Some(ioapic_section) = snapshot.snapshot_data.get(&format!("{}-section", self.id)) {
+            let ioapic_state = match serde_json::from_slice(&ioapic_section.snapshot) {
+                Ok(state) => state,
+                Err(error) => {
+                    return Err(MigratableError::Restore(anyhow!(
+                        "Could not deserialize IOAPIC {}",
+                        error
+                    )))
+                }
+            };
+
+            return self.set_state(&ioapic_state).map_err(|e| {
+                MigratableError::Restore(anyhow!("Could not restore IOAPIC state {:?}", e))
+            });
+        }
+
+        Err(MigratableError::Restore(anyhow!(
+            "Could not find IOAPIC snapshot section"
+        )))
     }
 }
 

devices/src/legacy/cmos.rs

@@ -2,16 +2,11 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
-use libc::{clock_gettime, gmtime_r, timespec, tm, CLOCK_REALTIME};
+use libc::{clock_gettime, gmtime_r, time_t, timespec, tm, CLOCK_REALTIME};
 use std::cmp::min;
 use std::mem;
 use std::sync::{Arc, Barrier};
 use vm_device::BusDevice;
-use vmm_sys_util::eventfd::EventFd;
-
-// https://github.com/rust-lang/libc/issues/1848
-#[cfg_attr(target_env = "musl", allow(deprecated))]
-use libc::time_t;
 
 const INDEX_MASK: u8 = 0x7f;
 const INDEX_OFFSET: u64 = 0x0;
@@ -22,14 +17,13 @@ const DATA_LEN: usize = 128;
 pub struct Cmos {
     index: u8,
     data: [u8; DATA_LEN],
-    reset_evt: EventFd,
 }
 
 impl Cmos {
     /// Constructs a CMOS/RTC device with initial data.
     /// `mem_below_4g` is the size of memory in bytes below the 32-bit gap.
     /// `mem_above_4g` is the size of memory in bytes above the 32-bit gap.
-    pub fn new(mem_below_4g: u64, mem_above_4g: u64, reset_evt: EventFd) -> Cmos {
+    pub fn new(mem_below_4g: u64, mem_above_4g: u64) -> Cmos {
         let mut data = [0u8; DATA_LEN];
 
         // Extended memory from 16 MB to 4 GB in units of 64 KB
@@ -46,32 +40,20 @@ impl Cmos {
         data[0x5c] = (high_mem >> 8) as u8;
         data[0x5d] = (high_mem >> 16) as u8;
 
-        Cmos {
-            index: 0,
-            data,
-            reset_evt,
-        }
+        Cmos { index: 0, data }
     }
 }
 
 impl BusDevice for Cmos {
     fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
         if data.len() != 1 {
-            warn!("Invalid write size on CMOS device: {}", data.len());
             return None;
         }
 
         match offset {
-            INDEX_OFFSET => self.index = data[0],
-            DATA_OFFSET => {
-                if self.index == 0x8f && data[0] == 0 {
-                    info!("CMOS reset");
-                    self.reset_evt.write(1).unwrap();
-                } else {
-                    self.data[(self.index & INDEX_MASK) as usize] = data[0]
-                }
-            }
-            o => warn!("bad write offset on CMOS device: {}", o),
+            INDEX_OFFSET => self.index = data[0] & INDEX_MASK,
+            DATA_OFFSET => self.data[self.index as usize] = data[0],
+            o => panic!("bad write offset on CMOS device: {}", o),
         };
         None
     }
@@ -83,7 +65,6 @@ impl BusDevice for Cmos {
         }
 
         if data.len() != 1 {
-            warn!("Invalid read size on CMOS device: {}", data.len());
             return;
         }
 
@@ -104,8 +85,6 @@ impl BusDevice for Cmos {
                     let mut timespec: timespec = mem::zeroed();
                     clock_gettime(CLOCK_REALTIME, &mut timespec as *mut _);
 
-                    // https://github.com/rust-lang/libc/issues/1848
-                    #[cfg_attr(target_env = "musl", allow(deprecated))]
                     let now: time_t = timespec.tv_sec;
                     let mut tm: tm = mem::zeroed();
                     gmtime_r(&now, &mut tm as *mut _);
@@ -134,9 +113,6 @@ impl BusDevice for Cmos {
                     0x09 => to_bcd((year % 100) as u8),
                     // Bit 5 for 32kHz clock. Bit 7 for Update in Progress
                     0x0a => 1 << 5 | (update_in_progress as u8) << 7,
-                    // Bit 0-6 are reserved and must be 0.
-                    // Bit 7 must be 1 (CMOS has power)
-                    0x0d => 1 << 7,
                     0x32 => to_bcd(((year + 1900) / 100) as u8),
                     _ => {
                         // self.index is always guaranteed to be in range via INDEX_MASK.
@@ -144,10 +120,7 @@ impl BusDevice for Cmos {
                     }
                 }
             }
-            o => {
-                warn!("bad read offset on CMOS device: {}", o);
-                0
-            }
+            o => panic!("bad read offset on CMOS device: {}", o),
         }
     }
 }

devices/src/legacy/debug_port.rs

@@ -1,86 +0,0 @@
-// Copyright © 2022 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-//
-
-use std::fmt;
-use std::time::Instant;
-use vm_device::BusDevice;
-
-/// Debug I/O port, see:
-/// https://www.intel.com/content/www/us/en/support/articles/000005500/boards-and-kits.html
-///
-/// Since we're not a physical platform, we can freely assign code ranges for
-/// debugging specific parts of our virtual platform.
-pub enum DebugIoPortRange {
-    Firmware,
-    Bootloader,
-    Kernel,
-    Userspace,
-    Custom,
-}
-
-#[cfg(target_arch = "x86_64")]
-const DEBUG_IOPORT_PREFIX: &str = "Debug I/O port";
-
-#[cfg(target_arch = "x86_64")]
-impl DebugIoPortRange {
-    fn from_u8(value: u8) -> DebugIoPortRange {
-        match value {
-            0x00..=0x1f => DebugIoPortRange::Firmware,
-            0x20..=0x3f => DebugIoPortRange::Bootloader,
-            0x40..=0x5f => DebugIoPortRange::Kernel,
-            0x60..=0x7f => DebugIoPortRange::Userspace,
-            _ => DebugIoPortRange::Custom,
-        }
-    }
-}
-
-#[cfg(target_arch = "x86_64")]
-impl fmt::Display for DebugIoPortRange {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        match self {
-            DebugIoPortRange::Firmware => write!(f, "{DEBUG_IOPORT_PREFIX}: Firmware"),
-            DebugIoPortRange::Bootloader => write!(f, "{DEBUG_IOPORT_PREFIX}: Bootloader"),
-            DebugIoPortRange::Kernel => write!(f, "{DEBUG_IOPORT_PREFIX}: Kernel"),
-            DebugIoPortRange::Userspace => write!(f, "{DEBUG_IOPORT_PREFIX}: Userspace"),
-            DebugIoPortRange::Custom => write!(f, "{DEBUG_IOPORT_PREFIX}: Custom"),
-        }
-    }
-}
-
-pub struct DebugPort {
-    timestamp: Instant,
-}
-
-impl DebugPort {
-    pub fn new(timestamp: Instant) -> Self {
-        Self { timestamp }
-    }
-}
-
-impl BusDevice for DebugPort {
-    fn read(&mut self, _base: u64, _offset: u64, _data: &mut [u8]) {
-        error!("Invalid read to debug port")
-    }
-
-    fn write(
-        &mut self,
-        _base: u64,
-        _offset: u64,
-        data: &[u8],
-    ) -> Option<std::sync::Arc<std::sync::Barrier>> {
-        let elapsed = self.timestamp.elapsed();
-
-        let code = data[0];
-        warn!(
-            "[{} code 0x{:x}] {}.{:>06} seconds",
-            DebugIoPortRange::from_u8(code),
-            code,
-            elapsed.as_secs(),
-            elapsed.as_micros()
-        );
-
-        None
-    }
-}

devices/src/legacy/gpio_pl061.rs

@@ -8,15 +8,15 @@
 //!
 
 use crate::{read_le_u32, write_le_u32};
+use anyhow::anyhow;
 use std::result;
 use std::sync::{Arc, Barrier};
 use std::{fmt, io};
-use versionize::{VersionMap, Versionize, VersionizeResult};
-use versionize_derive::Versionize;
 use vm_device::interrupt::InterruptSourceGroup;
 use vm_device::BusDevice;
 use vm_migration::{
-    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
+    Migratable, MigratableError, Pausable, Snapshot, SnapshotDataSection, Snapshottable,
+    Transportable,
 };
 
 const OFS_DATA: u64 = 0x400; // Data Register
@@ -51,13 +51,13 @@ pub enum 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::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}.")
+                write!(f, "Could not trigger GPIO interrupt: {}.", e)
             }
             Error::GpioTriggerKeyFailure(key) => {
-                write!(f, "Invalid GPIO Input key triggerd: {key}.")
+                write!(f, "Invalid GPIO Input key triggerd: {}.", key)
             }
         }
     }
@@ -86,10 +86,10 @@ pub struct Gpio {
     // Mode Control Select Register
     afsel: u32,
     // GPIO irq_field
-    interrupt: Arc<dyn InterruptSourceGroup>,
+    interrupt: Arc<Box<dyn InterruptSourceGroup>>,
 }
 
-#[derive(Versionize)]
+#[derive(Serialize, Deserialize)]
 pub struct GpioState {
     data: u32,
     old_in_data: u32,
@@ -102,11 +102,9 @@ pub struct GpioState {
     afsel: u32,
 }
 
-impl VersionMapped for GpioState {}
-
 impl Gpio {
     /// Constructs an PL061 GPIO device.
-    pub fn new(id: String, interrupt: Arc<dyn InterruptSourceGroup>) -> Self {
+    pub fn new(id: String, interrupt: Arc<Box<dyn InterruptSourceGroup>>) -> Self {
         Self {
             id,
             data: 0,
@@ -297,7 +295,7 @@ impl BusDevice for Gpio {
 
     fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
         if data.len() <= 4 {
-            let value = read_le_u32(data);
+            let value = read_le_u32(&data);
             if let Err(e) = self.handle_write(offset, value) {
                 warn!("Failed to write to GPIO PL061 device: {}", e);
             }
@@ -319,12 +317,38 @@ impl Snapshottable for Gpio {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        Snapshot::new_from_versioned_state(&self.id, &self.state())
+        let snapshot =
+            serde_json::to_vec(&self.state()).map_err(|e| MigratableError::Snapshot(e.into()))?;
+
+        let mut gpio_snapshot = Snapshot::new(self.id.as_str());
+        gpio_snapshot.add_data_section(SnapshotDataSection {
+            id: format!("{}-section", self.id),
+            snapshot,
+        });
+
+        Ok(gpio_snapshot)
     }
 
     fn restore(&mut self, snapshot: Snapshot) -> std::result::Result<(), MigratableError> {
-        self.set_state(&snapshot.to_versioned_state(&self.id)?);
-        Ok(())
+        if let Some(gpio_section) = snapshot.snapshot_data.get(&format!("{}-section", self.id)) {
+            let gpio_state = match serde_json::from_slice(&gpio_section.snapshot) {
+                Ok(state) => state,
+                Err(error) => {
+                    return Err(MigratableError::Restore(anyhow!(
+                        "Could not deserialize GPIO {}",
+                        error
+                    )))
+                }
+            };
+
+            self.set_state(&gpio_state);
+
+            return Ok(());
+        }
+
+        Err(MigratableError::Restore(anyhow!(
+            "Could not find the GPIO snapshot section"
+        )))
     }
 }
 
@@ -356,7 +380,6 @@ mod tests {
             &self,
             _index: InterruptIndex,
             _config: InterruptSourceConfig,
-            _masked: bool,
         ) -> result::Result<(), std::io::Error> {
             Ok(())
         }
@@ -377,14 +400,14 @@ mod tests {
         let intr_evt = EventFd::new(libc::EFD_NONBLOCK).unwrap();
         let mut gpio = Gpio::new(
             String::from(GPIO_NAME),
-            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
+            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
         );
         let mut data = [0; 4];
 
         // Read and write to the GPIODIR register.
         // Set pin 0 output pin.
         write_le_u32(&mut data, 1);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIODIR, &data);
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIODIR, &mut data);
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIODIR, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 1);
@@ -392,8 +415,8 @@ mod tests {
         // Read and write to the GPIODATA register.
         write_le_u32(&mut data, 1);
         // Set pin 0 high.
-        let offset = 0x00000004_u64;
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, offset, &data);
+        let offset = 0x00000004 as u64;
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, offset, &mut data);
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, offset, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 1);
@@ -401,7 +424,7 @@ mod tests {
         // Read and write to the GPIOIS register.
         // Configure pin 0 detecting level interrupt.
         write_le_u32(&mut data, 1);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIS, &data);
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIS, &mut data);
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOIS, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 1);
@@ -409,7 +432,7 @@ mod tests {
         // Read and write to the GPIOIBE register.
         // Configure pin 1 detecting both falling and rising edges.
         write_le_u32(&mut data, 2);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIBE, &data);
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIBE, &mut data);
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOIBE, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 2);
@@ -417,7 +440,7 @@ mod tests {
         // Read and write to the GPIOIEV register.
         // Configure pin 2 detecting both falling and rising edges.
         write_le_u32(&mut data, 4);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIEV, &data);
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIEV, &mut data);
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOIEV, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 4);
@@ -426,12 +449,12 @@ mod tests {
         // Configure pin 0...2 capable of triggering their individual interrupts
         // and then the combined GPIOINTR line.
         write_le_u32(&mut data, 7);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIE, &data);
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIE, &mut data);
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOIE, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 7);
 
-        let mask = 0x00000002_u32;
+        let mask = 0x00000002 as u32;
         // emulate an rising pulse in pin 1.
         gpio.data |= !(gpio.data & mask) & mask;
         gpio.pl061_internal_update();
@@ -444,14 +467,14 @@ mod tests {
         // Read and Write to the GPIOIC register.
         // clear interrupt in pin 1.
         write_le_u32(&mut data, 2);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIC, &data);
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIC, &mut data);
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOIC, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 2);
 
         // Attempts to write beyond the writable space.
         write_le_u32(&mut data, 0);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIO_ID_LOW, &data);
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIO_ID_LOW, &mut data);
 
         let mut data = [0; 4];
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIO_ID_LOW, &mut data);

devices/src/legacy/i8042.rs

@@ -34,7 +34,7 @@ impl BusDevice for I8042Device {
 
     fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
         if data.len() == 1 && data[0] == 0xfe && offset == 3 {
-            info!("i8042 reset signalled");
+            debug!("i8042 reset signalled");
             if let Err(e) = self.reset_evt.write(1) {
                 error!("Error triggering i8042 reset event: {}", e);
             }

devices/src/legacy/mod.rs

@@ -5,10 +5,9 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE-BSD-3-Clause file.
 
+#[cfg(feature = "cmos")]
 mod cmos;
-#[cfg(target_arch = "x86_64")]
-mod debug_port;
-#[cfg(target_arch = "x86_64")]
+#[cfg(feature = "fwdebug")]
 mod fwdebug;
 #[cfg(target_arch = "aarch64")]
 mod gpio_pl061;
@@ -19,10 +18,9 @@ mod serial;
 #[cfg(target_arch = "aarch64")]
 mod uart_pl011;
 
+#[cfg(feature = "cmos")]
 pub use self::cmos::Cmos;
-#[cfg(target_arch = "x86_64")]
-pub use self::debug_port::DebugPort;
-#[cfg(target_arch = "x86_64")]
+#[cfg(feature = "fwdebug")]
 pub use self::fwdebug::FwDebugDevice;
 pub use self::i8042::I8042Device;
 pub use self::serial::Serial;

devices/src/legacy/rtc_pl031.rs

@@ -48,8 +48,8 @@ pub enum 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}"),
+            Error::BadWriteOffset(offset) => write!(f, "Bad Write Offset: {}", offset),
+            Error::InterruptFailure(e) => write!(f, "Failed to trigger interrupt: {}", e),
         }
     }
 }
@@ -224,12 +224,12 @@ pub struct Rtc {
     load: u32,
     imsc: u32,
     ris: u32,
-    interrupt: Arc<dyn InterruptSourceGroup>,
+    interrupt: Arc<Box<dyn InterruptSourceGroup>>,
 }
 
 impl Rtc {
     /// Constructs an AMBA PL031 RTC device.
-    pub fn new(interrupt: Arc<dyn InterruptSourceGroup>) -> Self {
+    pub fn new(interrupt: Arc<Box<dyn InterruptSourceGroup>>) -> Self {
         Self {
             // This is used only for duration measuring purposes.
             previous_now: Instant::now(),
@@ -291,13 +291,14 @@ impl Rtc {
 
 impl BusDevice for Rtc {
     fn read(&mut self, _base: u64, offset: u64, data: &mut [u8]) {
+        let v;
         let mut read_ok = true;
 
-        let v = if (AMBA_ID_LOW..AMBA_ID_HIGH).contains(&offset) {
+        if (AMBA_ID_LOW..AMBA_ID_HIGH).contains(&offset) {
             let index = ((offset - AMBA_ID_LOW) >> 2) as usize;
-            u32::from(PL031_ID[index])
+            v = u32::from(PL031_ID[index]);
         } else {
-            match offset {
+            v = match offset {
                 RTCDR => self.get_time(),
                 RTCMR => {
                     // Even though we are not implementing RTC alarm we return the last value
@@ -312,8 +313,8 @@ impl BusDevice for Rtc {
                     read_ok = false;
                     0
                 }
-            }
-        };
+            };
+        }
         if read_ok && data.len() <= 4 {
             write_le_u32(data, v);
         } else {
@@ -327,7 +328,7 @@ impl BusDevice for Rtc {
 
     fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
         if data.len() <= 4 {
-            let v = read_le_u32(data);
+            let v = read_le_u32(&data);
             if let Err(e) = self.handle_write(offset, v) {
                 warn!("Failed to write to RTC PL031 device: {}", e);
             }
@@ -430,7 +431,6 @@ mod tests {
             &self,
             _index: InterruptIndex,
             _config: InterruptSourceConfig,
-            _masked: bool,
         ) -> result::Result<(), std::io::Error> {
             Ok(())
         }
@@ -450,12 +450,14 @@ mod tests {
     fn test_rtc_read_write_and_event() {
         let intr_evt = EventFd::new(libc::EFD_NONBLOCK).unwrap();
 
-        let mut rtc = Rtc::new(Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())));
+        let mut rtc = Rtc::new(Arc::new(Box::new(TestInterrupt::new(
+            intr_evt.try_clone().unwrap(),
+        ))));
         let mut data = [0; 4];
 
         // Read and write to the MR register.
         write_le_u32(&mut data, 123);
-        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCMR, &data);
+        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCMR, &mut data);
         rtc.read(LEGACY_RTC_MAPPED_IO_START, RTCMR, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 123);
@@ -464,7 +466,7 @@ mod tests {
         let v = get_time(ClockType::Real);
         write_le_u32(&mut data, (v / NANOS_PER_SECOND) as u32);
         let previous_now_before = rtc.previous_now;
-        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCLR, &data);
+        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCLR, &mut data);
 
         assert!(rtc.previous_now > previous_now_before);
 
@@ -476,7 +478,7 @@ mod tests {
         // Test with non zero value.
         let non_zero = 1;
         write_le_u32(&mut data, non_zero);
-        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCIMSC, &data);
+        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCIMSC, &mut data);
         // The interrupt line should be on.
         assert!(rtc.interrupt.notifier(0).unwrap().read().unwrap() == 1);
         rtc.read(LEGACY_RTC_MAPPED_IO_START, RTCIMSC, &mut data);
@@ -485,14 +487,14 @@ mod tests {
 
         // Now test with 0.
         write_le_u32(&mut data, 0);
-        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCIMSC, &data);
+        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCIMSC, &mut data);
         rtc.read(LEGACY_RTC_MAPPED_IO_START, RTCIMSC, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(0, v);
 
         // Read and write to the ICR register.
         write_le_u32(&mut data, 1);
-        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCICR, &data);
+        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCICR, &mut data);
         // The interrupt line should be on.
         assert!(rtc.interrupt.notifier(0).unwrap().read().unwrap() > 1);
         let v_before = read_le_u32(&data);
@@ -504,7 +506,7 @@ mod tests {
 
         // Attempts to turn off the RTC should not go through.
         write_le_u32(&mut data, 0);
-        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCCR, &data);
+        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCCR, &mut data);
         rtc.read(LEGACY_RTC_MAPPED_IO_START, RTCCR, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 1);
@@ -512,7 +514,7 @@ mod tests {
         // Attempts to write beyond the writable space. Using here the space used to read
         // the CID and PID from.
         write_le_u32(&mut data, 0);
-        rtc.write(LEGACY_RTC_MAPPED_IO_START, AMBA_ID_LOW, &data);
+        rtc.write(LEGACY_RTC_MAPPED_IO_START, AMBA_ID_LOW, &mut data);
         // However, reading from the AMBA_ID_LOW should succeed upon read.
 
         let mut data = [0; 4];

devices/src/legacy/serial.rs

@@ -5,15 +5,15 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE-BSD-3-Clause file.
 
+use anyhow::anyhow;
 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,
+    Migratable, MigratableError, Pausable, Snapshot, SnapshotDataSection, Snapshottable,
+    Transportable,
 };
 use vmm_sys_util::errno::Result;
 
@@ -63,7 +63,7 @@ pub struct Serial {
     id: String,
     interrupt_enable: u8,
     interrupt_identification: u8,
-    interrupt: Arc<dyn InterruptSourceGroup>,
+    interrupt: Arc<Box<dyn InterruptSourceGroup>>,
     line_control: u8,
     line_status: u8,
     modem_control: u8,
@@ -74,7 +74,7 @@ pub struct Serial {
     out: Option<Box<dyn io::Write + Send>>,
 }
 
-#[derive(Versionize)]
+#[derive(Serialize, Deserialize)]
 pub struct SerialState {
     interrupt_enable: u8,
     interrupt_identification: u8,
@@ -84,14 +84,13 @@ pub struct SerialState {
     modem_status: u8,
     scratch: u8,
     baud_divisor: u16,
-    in_buffer: Vec<u8>,
+    in_buffer: VecDeque<u8>,
 }
-impl VersionMapped for SerialState {}
 
 impl Serial {
     pub fn new(
         id: String,
-        interrupt: Arc<dyn InterruptSourceGroup>,
+        interrupt: Arc<Box<dyn InterruptSourceGroup>>,
         out: Option<Box<dyn io::Write + Send>>,
     ) -> Serial {
         Serial {
@@ -113,21 +112,17 @@ impl Serial {
     /// Constructs a Serial port ready for output.
     pub fn new_out(
         id: String,
-        interrupt: Arc<dyn InterruptSourceGroup>,
+        interrupt: Arc<Box<dyn InterruptSourceGroup>>,
         out: Box<dyn io::Write + Send>,
     ) -> Serial {
         Self::new(id, interrupt, Some(out))
     }
 
     /// Constructs a Serial port with no connected output.
-    pub fn new_sink(id: String, interrupt: Arc<dyn InterruptSourceGroup>) -> Serial {
+    pub fn new_sink(id: String, interrupt: Arc<Box<dyn InterruptSourceGroup>>) -> Serial {
         Self::new(id, interrupt, None)
     }
 
-    pub fn set_out(&mut self, out: Box<dyn io::Write + Send>) {
-        self.out = Some(out);
-    }
-
     /// Queues raw bytes for the guest to read and signals the interrupt if the line status would
     /// change.
     pub fn queue_input_bytes(&mut self, c: &[u8]) -> Result<()> {
@@ -138,13 +133,6 @@ impl Serial {
         Ok(())
     }
 
-    pub fn flush_output(&mut self) -> result::Result<(), io::Error> {
-        if let Some(out) = self.out.as_mut() {
-            out.flush()?;
-        }
-        Ok(())
-    }
-
     fn is_dlab_set(&self) -> bool {
         (self.line_control & LCR_DLAB_BIT) != 0
     }
@@ -199,7 +187,7 @@ impl Serial {
     }
 
     fn handle_write(&mut self, offset: u8, v: u8) -> Result<()> {
-        match offset {
+        match offset as u8 {
             DLAB_LOW if self.is_dlab_set() => {
                 self.baud_divisor = (self.baud_divisor & 0xff00) | u16::from(v)
             }
@@ -239,7 +227,7 @@ impl Serial {
             modem_status: self.modem_status,
             scratch: self.scratch,
             baud_divisor: self.baud_divisor,
-            in_buffer: self.in_buffer.clone().into(),
+            in_buffer: self.in_buffer.clone(),
         }
     }
 
@@ -252,7 +240,7 @@ impl Serial {
         self.modem_status = state.modem_status;
         self.scratch = state.scratch;
         self.baud_divisor = state.baud_divisor;
-        self.in_buffer = state.in_buffer.clone().into();
+        self.in_buffer = state.in_buffer.clone();
     }
 }
 
@@ -304,12 +292,38 @@ impl Snapshottable for Serial {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        Snapshot::new_from_versioned_state(&self.id, &self.state())
+        let snapshot =
+            serde_json::to_vec(&self.state()).map_err(|e| MigratableError::Snapshot(e.into()))?;
+
+        let mut serial_snapshot = Snapshot::new(self.id.as_str());
+        serial_snapshot.add_data_section(SnapshotDataSection {
+            id: format!("{}-section", self.id),
+            snapshot,
+        });
+
+        Ok(serial_snapshot)
     }
 
     fn restore(&mut self, snapshot: Snapshot) -> std::result::Result<(), MigratableError> {
-        self.set_state(&snapshot.to_versioned_state(&self.id)?);
-        Ok(())
+        if let Some(serial_section) = snapshot.snapshot_data.get(&format!("{}-section", self.id)) {
+            let serial_state = match serde_json::from_slice(&serial_section.snapshot) {
+                Ok(state) => state,
+                Err(error) => {
+                    return Err(MigratableError::Restore(anyhow!(
+                        "Could not deserialize SERIAL {}",
+                        error
+                    )))
+                }
+            };
+
+            self.set_state(&serial_state);
+
+            return Ok(());
+        }
+
+        Err(MigratableError::Restore(anyhow!(
+            "Could not find the serial snapshot section"
+        )))
     }
 }
 
@@ -339,7 +353,6 @@ mod tests {
             &self,
             _index: InterruptIndex,
             _config: InterruptSourceConfig,
-            _masked: bool,
         ) -> result::Result<(), std::io::Error> {
             Ok(())
         }
@@ -382,7 +395,7 @@ mod tests {
         let serial_out = SharedBuffer::new();
         let mut serial = Serial::new_out(
             String::from(SERIAL_NAME),
-            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
+            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
             Box::new(serial_out.clone()),
         );
 
@@ -402,7 +415,7 @@ mod tests {
         let serial_out = SharedBuffer::new();
         let mut serial = Serial::new_out(
             String::from(SERIAL_NAME),
-            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
+            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
             Box::new(serial_out),
         );
 
@@ -439,7 +452,7 @@ mod tests {
         let intr_evt = EventFd::new(0).unwrap();
         let mut serial = Serial::new_sink(
             String::from(SERIAL_NAME),
-            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
+            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
         );
 
         // write 1 to the interrupt event fd, so that read doesn't block in case the event fd
@@ -461,7 +474,7 @@ mod tests {
         let intr_evt = EventFd::new(0).unwrap();
         let mut serial = Serial::new_sink(
             String::from(SERIAL_NAME),
-            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
+            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
         );
 
         serial.write(0, LCR as u64, &[LCR_DLAB_BIT]);
@@ -482,7 +495,7 @@ mod tests {
         let intr_evt = EventFd::new(0).unwrap();
         let mut serial = Serial::new_sink(
             String::from(SERIAL_NAME),
-            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
+            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
         );
 
         serial.write(0, MCR as u64, &[MCR_LOOP_BIT]);
@@ -508,7 +521,7 @@ mod tests {
         let intr_evt = EventFd::new(0).unwrap();
         let mut serial = Serial::new_sink(
             String::from(SERIAL_NAME),
-            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
+            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
         );
 
         serial.write(0, SCR as u64, &[0x12]);

devices/src/legacy/uart_pl011.rs

@@ -7,17 +7,16 @@
 //!
 
 use crate::{read_le_u32, write_le_u32};
+use anyhow::anyhow;
 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 vm_device::interrupt::InterruptSourceGroup;
 use vm_device::BusDevice;
 use vm_migration::{
-    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
+    Migratable, MigratableError, Pausable, Snapshot, SnapshotDataSection, Snapshottable,
+    Transportable,
 };
 
 /* Registers */
@@ -35,7 +34,6 @@ const UARTRIS: u64 = 15;
 const UARTMIS: u64 = 16;
 const UARTICR: u64 = 17;
 const UARTDMACR: u64 = 18;
-const UARTDEBUG: u64 = 0x3c0;
 
 const PL011_INT_TX: u32 = 0x20;
 const PL011_INT_RX: u32 = 0x10;
@@ -60,11 +58,11 @@ pub enum 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::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}"),
+            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),
         }
     }
 }
@@ -79,7 +77,6 @@ pub struct Pl011 {
     rsr: u32,
     cr: u32,
     dmacr: u32,
-    debug: u32,
     int_enabled: u32,
     int_level: u32,
     read_fifo: VecDeque<u8>,
@@ -89,22 +86,20 @@ pub struct Pl011 {
     ifl: u32,
     read_count: u32,
     read_trigger: u32,
-    irq: Arc<dyn InterruptSourceGroup>,
+    irq: Arc<Box<dyn InterruptSourceGroup>>,
     out: Option<Box<dyn io::Write + Send>>,
-    timestamp: std::time::Instant,
 }
 
-#[derive(Versionize)]
+#[derive(Serialize, Deserialize)]
 pub struct Pl011State {
     flags: u32,
     lcr: u32,
     rsr: u32,
     cr: u32,
     dmacr: u32,
-    debug: u32,
     int_enabled: u32,
     int_level: u32,
-    read_fifo: Vec<u8>,
+    read_fifo: VecDeque<u8>,
     ilpr: u32,
     ibrd: u32,
     fbrd: u32,
@@ -113,15 +108,12 @@ pub struct Pl011State {
     read_trigger: u32,
 }
 
-impl VersionMapped for Pl011State {}
-
 impl Pl011 {
     /// Constructs an AMBA PL011 UART device.
     pub fn new(
         id: String,
-        irq: Arc<dyn InterruptSourceGroup>,
+        irq: Arc<Box<dyn InterruptSourceGroup>>,
         out: Option<Box<dyn io::Write + Send>>,
-        timestamp: Instant,
     ) -> Self {
         Self {
             id,
@@ -130,7 +122,6 @@ impl Pl011 {
             rsr: 0u32,
             cr: 0x300u32,
             dmacr: 0u32,
-            debug: 0u32,
             int_enabled: 0u32,
             int_level: 0u32,
             read_fifo: VecDeque::new(),
@@ -142,14 +133,9 @@ impl Pl011 {
             read_trigger: 1u32,
             irq,
             out,
-            timestamp,
         }
     }
 
-    pub fn set_out(&mut self, out: Box<dyn io::Write + Send>) {
-        self.out = Some(out);
-    }
-
     fn state(&self) -> Pl011State {
         Pl011State {
             flags: self.flags,
@@ -157,10 +143,9 @@ impl Pl011 {
             rsr: self.rsr,
             cr: self.cr,
             dmacr: self.dmacr,
-            debug: self.debug,
             int_enabled: self.int_enabled,
             int_level: self.int_level,
-            read_fifo: self.read_fifo.clone().into(),
+            read_fifo: self.read_fifo.clone(),
             ilpr: self.ilpr,
             ibrd: self.ibrd,
             fbrd: self.fbrd,
@@ -176,10 +161,9 @@ impl Pl011 {
         self.rsr = state.rsr;
         self.cr = state.cr;
         self.dmacr = state.dmacr;
-        self.debug = state.debug;
         self.int_enabled = state.int_enabled;
         self.int_level = state.int_level;
-        self.read_fifo = state.read_fifo.clone().into();
+        self.read_fifo = state.read_fifo.clone();
         self.ilpr = state.ilpr;
         self.ibrd = state.ibrd;
         self.fbrd = state.fbrd;
@@ -206,13 +190,6 @@ impl Pl011 {
         Ok(())
     }
 
-    pub fn flush_output(&mut self) -> result::Result<(), io::Error> {
-        if let Some(out) = self.out.as_mut() {
-            out.flush()?;
-        }
-        Ok(())
-    }
-
     fn pl011_get_baudrate(&self) -> u32 {
         if self.fbrd == 0 {
             return 0;
@@ -290,50 +267,13 @@ impl Pl011 {
                     return Err(Error::DmaNotImplemented);
                 }
             }
-            UARTDEBUG => {
-                self.debug = val;
-                self.handle_debug();
-            }
             off => {
-                debug!("PL011: Bad write offset, offset: {}", off);
                 return Err(Error::BadWriteOffset(off));
             }
         }
         Ok(())
     }
 
-    fn handle_debug(&self) {
-        let elapsed = self.timestamp.elapsed();
-
-        match self.debug {
-            0x00..=0x1f => warn!(
-                "[Debug I/O port: Firmware code: 0x{:x}] {}.{:>06} seconds",
-                self.debug,
-                elapsed.as_secs(),
-                elapsed.as_micros()
-            ),
-            0x20..=0x3f => warn!(
-                "[Debug I/O port: Bootloader code: 0x{:x}] {}.{:>06} seconds",
-                self.debug,
-                elapsed.as_secs(),
-                elapsed.as_micros()
-            ),
-            0x40..=0x5f => warn!(
-                "[Debug I/O port: Kernel code: 0x{:x}] {}.{:>06} seconds",
-                self.debug,
-                elapsed.as_secs(),
-                elapsed.as_micros()
-            ),
-            0x60..=0x7f => warn!(
-                "[Debug I/O port: Userspace code: 0x{:x}] {}.{:>06} seconds",
-                self.debug,
-                elapsed.as_secs(),
-                elapsed.as_micros()
-            ),
-            _ => {}
-        }
-    }
-
     fn trigger_interrupt(&mut self) -> result::Result<(), io::Error> {
         self.irq.trigger(0)
     }
@@ -341,15 +281,19 @@ impl Pl011 {
 
 impl BusDevice for Pl011 {
     fn read(&mut self, _base: u64, offset: u64, data: &mut [u8]) {
+        let v;
         let mut read_ok = true;
-        let v = if (AMBA_ID_LOW..AMBA_ID_HIGH).contains(&(offset >> 2)) {
+        if (AMBA_ID_LOW..AMBA_ID_HIGH).contains(&(offset >> 2)) {
             let index = ((offset - 0xfe0) >> 2) as usize;
-            u32::from(PL011_ID[index])
+            v = u32::from(PL011_ID[index]);
         } else {
-            match offset >> 2 {
+            v = match offset >> 2 {
                 UARTDR => {
+                    let c: u32;
+                    let r: u32;
+
                     self.flags &= !PL011_FLAG_RXFF;
-                    let c: u32 = self.read_fifo.pop_front().unwrap_or_default().into();
+                    c = self.read_fifo.pop_front().unwrap_or_default().into();
                     if self.read_count > 0 {
                         self.read_count -= 1;
                     }
@@ -360,7 +304,8 @@ impl BusDevice for Pl011 {
                         self.int_level &= !PL011_INT_RX;
                     }
                     self.rsr = c >> 8;
-                    c
+                    r = c;
+                    r
                 }
                 UARTRSR_UARTECR => self.rsr,
                 UARTFR => self.flags,
@@ -372,15 +317,14 @@ impl BusDevice for Pl011 {
                 UARTIFLS => self.ifl,
                 UARTIMSC => self.int_enabled,
                 UARTRIS => self.int_level,
-                UARTMIS => self.int_level & self.int_enabled,
+                UARTMIS => (self.int_level & self.int_enabled),
                 UARTDMACR => self.dmacr,
-                UARTDEBUG => self.debug,
                 _ => {
                     read_ok = false;
                     0
                 }
             }
-        };
+        }
 
         if read_ok && data.len() <= 4 {
             write_le_u32(data, v);
@@ -395,7 +339,7 @@ impl BusDevice for Pl011 {
 
     fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
         if data.len() <= 4 {
-            let v = read_le_u32(data);
+            let v = read_le_u32(&data);
             if let Err(e) = self.handle_write(offset, v) {
                 warn!("Failed to write to PL011 device: {}", e);
             }
@@ -417,12 +361,38 @@ impl Snapshottable for Pl011 {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        Snapshot::new_from_versioned_state(&self.id, &self.state())
+        let snapshot =
+            serde_json::to_vec(&self.state()).map_err(|e| MigratableError::Snapshot(e.into()))?;
+
+        let mut pl011_snapshot = Snapshot::new(self.id.as_str());
+        pl011_snapshot.add_data_section(SnapshotDataSection {
+            id: format!("{}-section", self.id),
+            snapshot,
+        });
+
+        Ok(pl011_snapshot)
     }
 
     fn restore(&mut self, snapshot: Snapshot) -> std::result::Result<(), MigratableError> {
-        self.set_state(&snapshot.to_versioned_state(&self.id)?);
-        Ok(())
+        if let Some(pl011_section) = snapshot.snapshot_data.get(&format!("{}-section", self.id)) {
+            let pl011_state = match serde_json::from_slice(&pl011_section.snapshot) {
+                Ok(state) => state,
+                Err(error) => {
+                    return Err(MigratableError::Restore(anyhow!(
+                        "Could not deserialize PL011 {}",
+                        error
+                    )))
+                }
+            };
+
+            self.set_state(&pl011_state);
+
+            return Ok(());
+        }
+
+        Err(MigratableError::Restore(anyhow!(
+            "Could not find the PL011 snapshot section"
+        )))
     }
 }
 
@@ -452,7 +422,6 @@ mod tests {
             &self,
             _index: InterruptIndex,
             _config: InterruptSourceConfig,
-            _masked: bool,
         ) -> result::Result<(), std::io::Error> {
             Ok(())
         }
@@ -495,9 +464,8 @@ mod tests {
         let pl011_out = SharedBuffer::new();
         let mut pl011 = Pl011::new(
             String::from(SERIAL_NAME),
-            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
+            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
             Some(Box::new(pl011_out.clone())),
-            Instant::now(),
         );
 
         pl011.write(0, UARTDR as u64, &[b'x', b'y']);
@@ -516,9 +484,8 @@ mod tests {
         let pl011_out = SharedBuffer::new();
         let mut pl011 = Pl011::new(
             String::from(SERIAL_NAME),
-            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
+            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
             Some(Box::new(pl011_out)),
-            Instant::now(),
         );
 
         // write 1 to the interrupt event fd, so that read doesn't block in case the event fd

devices/src/lib.rs

@@ -6,12 +6,26 @@
 // found in the LICENSE-BSD-3-Clause file.
 
 //! Emulates virtual and hardware devices.
-
+extern crate anyhow;
 #[macro_use]
 extern crate bitflags;
+extern crate byteorder;
+extern crate epoll;
+extern crate libc;
 #[macro_use]
 extern crate log;
+#[cfg(feature = "acpi")]
+extern crate acpi_tables;
+extern crate serde;
+extern crate vm_device;
+extern crate vm_memory;
+extern crate vm_migration;
+extern crate vmm_sys_util;
+#[macro_use]
+extern crate serde_derive;
+extern crate serde_json;
 
+#[cfg(feature = "acpi")]
 pub mod acpi;
 #[cfg(target_arch = "aarch64")]
 pub mod gic;
@@ -19,8 +33,8 @@ pub mod interrupt_controller;
 #[cfg(target_arch = "x86_64")]
 pub mod ioapic;
 pub mod legacy;
-pub mod tpm;
 
+#[cfg(feature = "acpi")]
 pub use self::acpi::{AcpiGedDevice, AcpiPmTimerDevice, AcpiShutdownDevice};
 
 bitflags! {

devices/src/tpm.rs

@@ -1,467 +0,0 @@
-// Copyright © 2022, Microsoft Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-//
-
-use anyhow::anyhow;
-#[cfg(target_arch = "aarch64")]
-use arch::aarch64::layout::{TPM_SIZE, TPM_START};
-#[cfg(target_arch = "x86_64")]
-use arch::x86_64::layout::{TPM_SIZE, TPM_START};
-use phf::phf_map;
-use std::cmp;
-use std::sync::{Arc, Barrier};
-use thiserror::Error;
-use tpm::emulator::{BackendCmd, Emulator};
-use tpm::TPM_CRB_BUFFER_MAX;
-use tpm::TPM_SUCCESS;
-use vm_device::BusDevice;
-
-#[derive(Error, Debug)]
-pub enum Error {
-    #[error("Emulator doesn't implement min required capabilities: {0}")]
-    CheckCaps(#[source] anyhow::Error),
-    #[error("Failed to initialize tpm: {0}")]
-    Init(#[source] anyhow::Error),
-    #[error("Failed to deliver tpm Command: {0}")]
-    DeliverRequest(#[source] anyhow::Error),
-}
-type Result<T> = anyhow::Result<T, Error>;
-
-/* crb 32-bit registers */
-const CRB_LOC_STATE: u32 = 0x0;
-//Register Fields
-// Field => (start, length)
-// start: lowest bit in the bit field numbered from 0
-// length: length of the bit field
-const CRB_LOC_STATE_FIELDS: phf::Map<&str, [u32; 2]> = phf_map! {
-    "tpmEstablished" => [0, 1],
-    "locAssigned" => [1,1],
-    "activeLocality"=> [2, 3],
-    "reserved" => [5, 2],
-    "tpmRegValidSts" => [7, 1]
-};
-const CRB_LOC_CTRL: u32 = 0x08;
-const CRB_LOC_CTRL_REQUEST_ACCESS: u32 = 1 << 0;
-const CRB_LOC_CTRL_RELINQUISH: u32 = 1 << 1;
-const CRB_LOC_CTRL_RESET_ESTABLISHMENT_BIT: u32 = 1 << 3;
-const CRB_LOC_STS: u32 = 0x0C;
-const CRB_LOC_STS_FIELDS: phf::Map<&str, [u32; 2]> = phf_map! {
-    "Granted" => [0, 1],
-    "beenSeized" => [1,1]
-};
-const CRB_INTF_ID: u32 = 0x30;
-const CRB_INTF_ID_FIELDS: phf::Map<&str, [u32; 2]> = phf_map! {
-    "InterfaceType" => [0, 4],
-    "InterfaceVersion" => [4, 4],
-    "CapLocality" =>  [8, 1],
-    "CapCRBIdleBypass" => [9, 1],
-    "Reserved1" => [10, 1],
-    "CapDataXferSizeSupport" => [11, 2],
-    "CapFIFO" =>  [13, 1],
-    "CapCRB" => [14, 1],
-    "CapIFRes" => [15, 2],
-    "InterfaceSelector" => [17, 2],
-    "IntfSelLock" =>  [19, 1],
-    "Reserved2" => [20, 4],
-    "RID" => [24, 8]
-};
-const CRB_INTF_ID2: u32 = 0x34;
-const CRB_INTF_ID2_FIELDS: phf::Map<&str, [u32; 2]> = phf_map! {
-    "VID" => [0, 16],
-    "DID" => [16, 16]
-};
-const CRB_CTRL_REQ: u32 = 0x40;
-const CRB_CTRL_REQ_CMD_READY: u32 = 1 << 0;
-const CRB_CTRL_REQ_GO_IDLE: u32 = 1 << 1;
-const CRB_CTRL_STS: u32 = 0x44;
-const CRB_CTRL_STS_FIELDS: phf::Map<&str, [u32; 2]> = phf_map! {
-    "tpmSts" => [0, 1],
-    "tpmIdle" => [1, 1]
-};
-const CRB_CTRL_CANCEL: u32 = 0x48;
-const CRB_CANCEL_INVOKE: u32 = 1 << 0;
-const CRB_CTRL_START: u32 = 0x4C;
-const CRB_START_INVOKE: u32 = 1 << 0;
-const CRB_CTRL_CMD_LADDR: u32 = 0x5C;
-const CRB_CTRL_CMD_HADDR: u32 = 0x60;
-const CRB_CTRL_RSP_SIZE: u32 = 0x64;
-const CRB_CTRL_RSP_ADDR: u32 = 0x68;
-const CRB_DATA_BUFFER: u32 = 0x80;
-
-const TPM_CRB_NO_LOCALITY: u32 = 0xff;
-
-const TPM_CRB_ADDR_BASE: u32 = TPM_START.0 as u32;
-const TPM_CRB_ADDR_SIZE: usize = TPM_SIZE as usize;
-
-const TPM_CRB_R_MAX: u32 = CRB_DATA_BUFFER;
-
-// CRB Protocol details
-const CRB_INTF_TYPE_CRB_ACTIVE: u32 = 0b1;
-const CRB_INTF_VERSION_CRB: u32 = 0b1;
-const CRB_INTF_CAP_LOCALITY_0_ONLY: u32 = 0b0;
-const CRB_INTF_CAP_IDLE_FAST: u32 = 0b0;
-const CRB_INTF_CAP_XFER_SIZE_64: u32 = 0b11;
-const CRB_INTF_CAP_FIFO_NOT_SUPPORTED: u32 = 0b0;
-const CRB_INTF_CAP_CRB_SUPPORTED: u32 = 0b1;
-const CRB_INTF_IF_SELECTOR_CRB: u32 = 0b1;
-const PCI_VENDOR_ID_IBM: u32 = 0x1014;
-const CRB_CTRL_CMD_SIZE_REG: u32 = 0x58;
-const CRB_CTRL_CMD_SIZE: usize = TPM_CRB_ADDR_SIZE - CRB_DATA_BUFFER as usize;
-
-fn get_fields_map(reg: u32) -> phf::Map<&'static str, [u32; 2]> {
-    match reg {
-        CRB_LOC_STATE => CRB_LOC_STATE_FIELDS,
-        CRB_LOC_STS => CRB_LOC_STS_FIELDS,
-        CRB_INTF_ID => CRB_INTF_ID_FIELDS,
-        CRB_INTF_ID2 => CRB_INTF_ID2_FIELDS,
-        CRB_CTRL_STS => CRB_CTRL_STS_FIELDS,
-        _ => {
-            panic!("Fields in '{reg:?}' register were accessed which are Invalid");
-        }
-    }
-}
-
-/// Set a particular field in a Register
-fn set_reg_field(regs: &mut [u32; TPM_CRB_R_MAX as usize], reg: u32, field: &str, value: u32) {
-    let reg_fields = get_fields_map(reg);
-    if reg_fields.contains_key(field) {
-        let start = reg_fields.get(field).unwrap()[0];
-        let len = reg_fields.get(field).unwrap()[1];
-        let mask = (!(0_u32) >> (32 - len)) << start;
-        regs[reg as usize] = (regs[reg as usize] & !mask) | ((value << start) & mask);
-    } else {
-        error!(
-            "Failed to tpm Register. {:?} is not a valid field in Reg {:#X}",
-            field, reg
-        )
-    }
-}
-
-/// Get the value of a particular field in a Register
-fn get_reg_field(regs: &[u32; TPM_CRB_R_MAX as usize], reg: u32, field: &str) -> u32 {
-    let reg_fields = get_fields_map(reg);
-    if reg_fields.contains_key(field) {
-        let start = reg_fields.get(field).unwrap()[0];
-        let len = reg_fields.get(field).unwrap()[1];
-        let mask = (!(0_u32) >> (32 - len)) << start;
-        (regs[reg as usize] & mask) >> start
-    } else {
-        // TODO: Sensible return value if fields do not exist
-        0x0
-    }
-}
-
-fn locality_from_addr(addr: u32) -> u8 {
-    (addr >> 12) as u8
-}
-
-pub struct Tpm {
-    emulator: Emulator,
-    cmd: Option<BackendCmd>,
-    regs: [u32; TPM_CRB_R_MAX as usize],
-    backend_buff_size: usize,
-    data_buff: [u8; TPM_CRB_BUFFER_MAX],
-    data_buff_len: usize,
-}
-
-impl Tpm {
-    pub fn new(path: String) -> Result<Self> {
-        let emulator = Emulator::new(path)
-            .map_err(|e| Error::Init(anyhow!("Failed while initializing tpm Emulator: {:?}", e)))?;
-        let mut tpm = Tpm {
-            emulator,
-            cmd: None,
-            regs: [0; TPM_CRB_R_MAX as usize],
-            backend_buff_size: TPM_CRB_BUFFER_MAX,
-            data_buff: [0; TPM_CRB_BUFFER_MAX],
-            data_buff_len: 0,
-        };
-        tpm.reset()?;
-        Ok(tpm)
-    }
-
-    fn get_active_locality(&mut self) -> u32 {
-        if get_reg_field(&self.regs, CRB_LOC_STATE, "locAssigned") == 0 {
-            return TPM_CRB_NO_LOCALITY;
-        }
-        get_reg_field(&self.regs, CRB_LOC_STATE, "activeLocality")
-    }
-
-    fn request_completed(&mut self, result: isize) {
-        self.regs[CRB_CTRL_START as usize] = !CRB_START_INVOKE;
-        if result != 0 {
-            set_reg_field(&mut self.regs, CRB_CTRL_STS, "tpmSts", 1);
-        }
-    }
-
-    fn reset(&mut self) -> Result<()> {
-        let cur_buff_size = self.emulator.get_buffer_size().unwrap();
-        self.regs = [0; TPM_CRB_R_MAX as usize];
-        set_reg_field(&mut self.regs, CRB_LOC_STATE, "tpmRegValidSts", 1);
-        set_reg_field(&mut self.regs, CRB_CTRL_STS, "tpmIdle", 1);
-        set_reg_field(
-            &mut self.regs,
-            CRB_INTF_ID,
-            "InterfaceType",
-            CRB_INTF_TYPE_CRB_ACTIVE,
-        );
-        set_reg_field(
-            &mut self.regs,
-            CRB_INTF_ID,
-            "InterfaceVersion",
-            CRB_INTF_VERSION_CRB,
-        );
-        set_reg_field(
-            &mut self.regs,
-            CRB_INTF_ID,
-            "CapLocality",
-            CRB_INTF_CAP_LOCALITY_0_ONLY,
-        );
-        set_reg_field(
-            &mut self.regs,
-            CRB_INTF_ID,
-            "CapCRBIdleBypass",
-            CRB_INTF_CAP_IDLE_FAST,
-        );
-        set_reg_field(
-            &mut self.regs,
-            CRB_INTF_ID,
-            "CapDataXferSizeSupport",
-            CRB_INTF_CAP_XFER_SIZE_64,
-        );
-        set_reg_field(
-            &mut self.regs,
-            CRB_INTF_ID,
-            "CapFIFO",
-            CRB_INTF_CAP_FIFO_NOT_SUPPORTED,
-        );
-        set_reg_field(
-            &mut self.regs,
-            CRB_INTF_ID,
-            "CapCRB",
-            CRB_INTF_CAP_CRB_SUPPORTED,
-        );
-        set_reg_field(
-            &mut self.regs,
-            CRB_INTF_ID,
-            "InterfaceSelector",
-            CRB_INTF_IF_SELECTOR_CRB,
-        );
-        set_reg_field(&mut self.regs, CRB_INTF_ID, "RID", 0b0000);
-        set_reg_field(&mut self.regs, CRB_INTF_ID2, "VID", PCI_VENDOR_ID_IBM);
-
-        self.regs[CRB_CTRL_CMD_SIZE_REG as usize] = CRB_CTRL_CMD_SIZE as u32;
-        self.regs[CRB_CTRL_CMD_LADDR as usize] = TPM_CRB_ADDR_BASE + CRB_DATA_BUFFER;
-        self.regs[CRB_CTRL_RSP_SIZE as usize] = CRB_CTRL_CMD_SIZE as u32;
-        self.regs[CRB_CTRL_RSP_ADDR as usize] = TPM_CRB_ADDR_BASE + CRB_DATA_BUFFER;
-
-        self.backend_buff_size = cmp::min(cur_buff_size, TPM_CRB_BUFFER_MAX);
-
-        if let Err(e) = self.emulator.startup_tpm(self.backend_buff_size) {
-            return Err(Error::Init(anyhow!(
-                "Failed while running Startup TPM. Error: {:?}",
-                e
-            )));
-        }
-        Ok(())
-    }
-}
-
-//impl BusDevice for TPM
-impl BusDevice for Tpm {
-    fn read(&mut self, _base: u64, offset: u64, data: &mut [u8]) {
-        let mut offset: u32 = offset as u32;
-        let read_len: usize = data.len();
-
-        if offset >= CRB_DATA_BUFFER
-            && (offset + read_len as u32) < (CRB_DATA_BUFFER + self.data_buff.len() as u32)
-        {
-            // Read from Data Buffer
-            let start: usize = (offset as usize) - (CRB_DATA_BUFFER as usize);
-            let end: usize = start + read_len;
-            data[..].clone_from_slice(&self.data_buff[start..end]);
-        } else {
-            offset &= 0xff;
-            let mut val = self.regs[offset as usize];
-
-            if offset == CRB_LOC_STATE && !self.emulator.get_established_flag() {
-                val |= 0x1;
-            }
-
-            if data.len() <= 4 {
-                data.clone_from_slice(val.to_ne_bytes()[0..read_len].as_ref());
-            } else {
-                error!(
-                    "Invalid tpm read: offset {:#X}, data length {:?}",
-                    offset,
-                    data.len()
-                );
-            }
-        }
-        debug!(
-            "MMIO Read: offset {:#X} len {:?} val = {:02X?}  ",
-            offset,
-            data.len(),
-            data
-        );
-    }
-
-    fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
-        debug!(
-            "MMIO Write: offset {:#X} len {:?} input data {:02X?}",
-            offset,
-            data.len(),
-            data
-        );
-        let mut offset: u32 = offset as u32;
-        if offset < CRB_DATA_BUFFER {
-            offset &= 0xff;
-        }
-        let locality = locality_from_addr(offset) as u32;
-        let write_len = data.len();
-
-        if offset >= CRB_DATA_BUFFER
-            && (offset + write_len as u32) < (CRB_DATA_BUFFER + self.data_buff.len() as u32)
-        {
-            let start: usize = (offset as usize) - (CRB_DATA_BUFFER as usize);
-            if start == 0 {
-                // If filling data_buff at index 0, reset length to 0
-                self.data_buff_len = 0;
-                self.data_buff.fill(0);
-            }
-            let end: usize = start + data.len();
-            self.data_buff[start..end].clone_from_slice(data);
-            self.data_buff_len += data.len();
-        } else {
-            // Ctrl Commands that take more than 4 bytes as input are not yet supported
-            // CTRL_RSP_ADDR usually gets 8 byte write request. Last 4 bytes are zeros.
-            if write_len > 4 && offset != CRB_CTRL_RSP_ADDR {
-                error!(
-                    "Invalid tpm write: offset {:#X}, data length {}",
-                    offset,
-                    data.len()
-                );
-                return None;
-            }
-
-            let mut input: [u8; 4] = [0; 4];
-            input.copy_from_slice(&data[0..4]);
-            let v = u32::from_le_bytes(input);
-
-            match offset {
-                CRB_CTRL_CMD_SIZE_REG => {
-                    self.regs[CRB_CTRL_CMD_SIZE_REG as usize] = v;
-                }
-                CRB_CTRL_CMD_LADDR => {
-                    self.regs[CRB_CTRL_CMD_LADDR as usize] = v;
-                }
-                CRB_CTRL_CMD_HADDR => {
-                    self.regs[CRB_CTRL_CMD_HADDR as usize] = v;
-                }
-                CRB_CTRL_RSP_SIZE => {
-                    self.regs[CRB_CTRL_RSP_SIZE as usize] = v;
-                }
-                CRB_CTRL_RSP_ADDR => {
-                    self.regs[CRB_CTRL_RSP_ADDR as usize] = v;
-                }
-                CRB_CTRL_REQ => match v {
-                    CRB_CTRL_REQ_CMD_READY => {
-                        set_reg_field(&mut self.regs, CRB_CTRL_STS, "tpmIdle", 0);
-                    }
-                    CRB_CTRL_REQ_GO_IDLE => {
-                        set_reg_field(&mut self.regs, CRB_CTRL_STS, "tpmIdle", 1);
-                    }
-                    _ => {
-                        error!("Invalid value passed to CRTL_REQ register");
-                        return None;
-                    }
-                },
-                CRB_CTRL_CANCEL => {
-                    if v == CRB_CANCEL_INVOKE
-                        && (self.regs[CRB_CTRL_START as usize] & CRB_START_INVOKE != 0)
-                    {
-                        if let Err(e) = self.emulator.cancel_cmd() {
-                            error!("Failed to run cancel command. Error: {:?}", e);
-                        }
-                    }
-                }
-                CRB_CTRL_START => {
-                    if v == CRB_START_INVOKE
-                        && ((self.regs[CRB_CTRL_START as usize] & CRB_START_INVOKE) == 0)
-                        && self.get_active_locality() == locality
-                    {
-                        self.regs[CRB_CTRL_START as usize] |= CRB_START_INVOKE;
-
-                        self.cmd = Some(BackendCmd {
-                            locality: locality as u8,
-                            input: self.data_buff[0..self.data_buff_len].to_vec(),
-                            input_len: cmp::min(self.data_buff_len, TPM_CRB_BUFFER_MAX),
-                            output: self.data_buff.to_vec(),
-                            output_len: TPM_CRB_BUFFER_MAX,
-                            selftest_done: false,
-                        });
-
-                        let mut cmd = self.cmd.as_ref().unwrap().clone();
-                        let output = self.emulator.deliver_request(&mut cmd).map_err(|e| {
-                            Error::DeliverRequest(anyhow!(
-                                "Failed to deliver tpm request. Error :{:?}",
-                                e
-                            ))
-                        });
-                        //TODO: drop the copy here
-                        self.data_buff.fill(0);
-                        self.data_buff.clone_from_slice(output.unwrap().as_slice());
-
-                        self.request_completed(TPM_SUCCESS as isize);
-                    }
-                }
-                CRB_LOC_CTRL => {
-                    warn!(
-                        "CRB_LOC_CTRL locality to write = {:?} val = {:?}",
-                        locality, v
-                    );
-                    match v {
-                        CRB_LOC_CTRL_RESET_ESTABLISHMENT_BIT => {}
-                        CRB_LOC_CTRL_RELINQUISH => {
-                            set_reg_field(&mut self.regs, CRB_LOC_STATE, "locAssigned", 0);
-                            set_reg_field(&mut self.regs, CRB_LOC_STS, "Granted", 0);
-                        }
-                        CRB_LOC_CTRL_REQUEST_ACCESS => {
-                            set_reg_field(&mut self.regs, CRB_LOC_STS, "Granted", 1);
-                            set_reg_field(&mut self.regs, CRB_LOC_STS, "beenSeized", 0);
-                            set_reg_field(&mut self.regs, CRB_LOC_STATE, "locAssigned", 1);
-                        }
-                        _ => {
-                            error!("Invalid value to write in CRB_LOC_CTRL {:#X} ", v);
-                        }
-                    }
-                }
-                _ => {
-                    error!(
-                        "Invalid tpm write: offset {:#X}, data length {:?}",
-                        offset,
-                        data.len()
-                    );
-                }
-            }
-        }
-        None
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_set_get_reg_field() {
-        let mut regs: [u32; TPM_CRB_R_MAX as usize] = [0; TPM_CRB_R_MAX as usize];
-        set_reg_field(&mut regs, CRB_INTF_ID, "RID", 0xAC);
-        assert_eq!(
-            get_reg_field(&regs, CRB_INTF_ID, "RID"),
-            0xAC,
-            concat!("Test: ", stringify!(set_get_reg_field))
-        );
-    }
-}

docs/COPYING.docs

@@ -1,399 +0,0 @@
-The documentation in this directory is covered by the following license:
-
-Attribution 4.0 International
-
-=======================================================================
-
-Creative Commons Corporation ("Creative Commons") is not a law firm and
-does not provide legal services or legal advice. Distribution of
-Creative Commons public licenses does not create a lawyer-client or
-other relationship. Creative Commons makes its licenses and related
-information available on an "as-is" basis. Creative Commons gives no
-warranties regarding its licenses, any material licensed under their
-terms and conditions, or any related information. Creative Commons
-disclaims all liability for damages resulting from their use to the
-fullest extent possible.
-
-Using Creative Commons Public Licenses
-
-Creative Commons public licenses provide a standard set of terms and
-conditions that creators and other rights holders may use to share
-original works of authorship and other material subject to copyright
-and certain other rights specified in the public license below. The
-following considerations are for informational purposes only, are not
-exhaustive, and do not form part of our licenses.
-
-     Considerations for licensors: Our public licenses are
-     intended for use by those authorized to give the public
-     permission to use material in ways otherwise restricted by
-     copyright and certain other rights. Our licenses are
-     irrevocable. Licensors should read and understand the terms
-     and conditions of the license they choose before applying it.
-     Licensors should also secure all rights necessary before
-     applying our licenses so that the public can reuse the
-     material as expected. Licensors should clearly mark any
-     material not subject to the license. This includes other CC-
-     licensed material, or material used under an exception or
-     limitation to copyright. More considerations for licensors:
-    wiki.creativecommons.org/Considerations_for_licensors
-
-     Considerations for the public: By using one of our public
-     licenses, a licensor grants the public permission to use the
-     licensed material under specified terms and conditions. If
-     the licensor's permission is not necessary for any reason--for
-     example, because of any applicable exception or limitation to
-     copyright--then that use is not regulated by the license. Our
-     licenses grant only permissions under copyright and certain
-     other rights that a licensor has authority to grant. Use of
-     the licensed material may still be restricted for other
-     reasons, including because others have copyright or other
-     rights in the material. A licensor may make special requests,
-     such as asking that all changes be marked or described.
-     Although not required by our licenses, you are encouraged to
-     respect those requests where reasonable. More considerations
-     for the public:
-    wiki.creativecommons.org/Considerations_for_licensees
-
-=======================================================================
-
-Creative Commons Attribution 4.0 International Public License
-
-By exercising the Licensed Rights (defined below), You accept and agree
-to be bound by the terms and conditions of this Creative Commons
-Attribution 4.0 International Public License ("Public License"). To the
-extent this Public License may be interpreted as a contract, You are
-granted the Licensed Rights in consideration of Your acceptance of
-these terms and conditions, and the Licensor grants You such rights in
-consideration of benefits the Licensor receives from making the
-Licensed Material available under these terms and conditions.
-
-
-Section 1 -- Definitions.
-
-  a. Adapted Material means material subject to Copyright and Similar
-     Rights that is derived from or based upon the Licensed Material
-     and in which the Licensed Material is translated, altered,
-     arranged, transformed, or otherwise modified in a manner requiring
-     permission under the Copyright and Similar Rights held by the
-     Licensor. For purposes of this Public License, where the Licensed
-     Material is a musical work, performance, or sound recording,
-     Adapted Material is always produced where the Licensed Material is
-     synched in timed relation with a moving image.
-
-  b. Adapter's License means the license You apply to Your Copyright
-     and Similar Rights in Your contributions to Adapted Material in
-     accordance with the terms and conditions of this Public License.
-
-  c. Copyright and Similar Rights means copyright and/or similar rights
-     closely related to copyright including, without limitation,
-     performance, broadcast, sound recording, and Sui Generis Database
-     Rights, without regard to how the rights are labeled or
-     categorized. For purposes of this Public License, the rights
-     specified in Section 2(b)(1)-(2) are not Copyright and Similar
-     Rights.
-
-  d. Effective Technological Measures means those measures that, in the
-     absence of proper authority, may not be circumvented under laws
-     fulfilling obligations under Article 11 of the WIPO Copyright
-     Treaty adopted on December 20, 1996, and/or similar international
-     agreements.
-
-  e. Exceptions and Limitations means fair use, fair dealing, and/or
-     any other exception or limitation to Copyright and Similar Rights
-     that applies to Your use of the Licensed Material.
-
-  f. Licensed Material means the artistic or literary work, database,
-     or other material to which the Licensor applied this Public
-     License.
-
-  g. Licensed Rights means the rights granted to You subject to the
-     terms and conditions of this Public License, which are limited to
-     all Copyright and Similar Rights that apply to Your use of the
-     Licensed Material and that the Licensor has authority to license.
-
-  h. Licensor means the individual(s) or entity(ies) granting rights
-     under this Public License.
-
-  i. Share means to provide material to the public by any means or
-     process that requires permission under the Licensed Rights, such
-     as reproduction, public display, public performance, distribution,
-     dissemination, communication, or importation, and to make material
-     available to the public including in ways that members of the
-     public may access the material from a place and at a time
-     individually chosen by them.
-
-  j. Sui Generis Database Rights means rights other than copyright
-     resulting from Directive 96/9/EC of the European Parliament and of
-     the Council of 11 March 1996 on the legal protection of databases,
-     as amended and/or succeeded, as well as other essentially
-     equivalent rights anywhere in the world.
-
-  k. You means the individual or entity exercising the Licensed Rights
-     under this Public License. Your has a corresponding meaning.
-
-
-Section 2 -- Scope.
-
-  a. License grant.
-
-       1. Subject to the terms and conditions of this Public License,
-          the Licensor hereby grants You a worldwide, royalty-free,
-          non-sublicensable, non-exclusive, irrevocable license to
-          exercise the Licensed Rights in the Licensed Material to:
-
-            a. reproduce and Share the Licensed Material, in whole or
-               in part; and
-
-            b. produce, reproduce, and Share Adapted Material.
-
-       2. Exceptions and Limitations. For the avoidance of doubt, where
-          Exceptions and Limitations apply to Your use, this Public
-          License does not apply, and You do not need to comply with
-          its terms and conditions.
-
-       3. Term. The term of this Public License is specified in Section
-          6(a).
-
-       4. Media and formats; technical modifications allowed. The
-          Licensor authorizes You to exercise the Licensed Rights in
-          all media and formats whether now known or hereafter created,
-          and to make technical modifications necessary to do so. The
-          Licensor waives and/or agrees not to assert any right or
-          authority to forbid You from making technical modifications
-          necessary to exercise the Licensed Rights, including
-          technical modifications necessary to circumvent Effective
-          Technological Measures. For purposes of this Public License,
-          simply making modifications authorized by this Section 2(a)
-          (4) never produces Adapted Material.
-
-       5. Downstream recipients.
-
-            a. Offer from the Licensor -- Licensed Material. Every
-               recipient of the Licensed Material automatically
-               receives an offer from the Licensor to exercise the
-               Licensed Rights under the terms and conditions of this
-               Public License.
-
-            b. No downstream restrictions. You may not offer or impose
-               any additional or different terms or conditions on, or
-               apply any Effective Technological Measures to, the
-               Licensed Material if doing so restricts exercise of the
-               Licensed Rights by any recipient of the Licensed
-               Material.
-
-       6. No endorsement. Nothing in this Public License constitutes or
-          may be construed as permission to assert or imply that You
-          are, or that Your use of the Licensed Material is, connected
-          with, or sponsored, endorsed, or granted official status by,
-          the Licensor or others designated to receive attribution as
-          provided in Section 3(a)(1)(A)(i).
-
-  b. Other rights.
-
-       1. Moral rights, such as the right of integrity, are not
-          licensed under this Public License, nor are publicity,
-          privacy, and/or other similar personality rights; however, to
-          the extent possible, the Licensor waives and/or agrees not to
-          assert any such rights held by the Licensor to the limited
-          extent necessary to allow You to exercise the Licensed
-          Rights, but not otherwise.
-
-       2. Patent and trademark rights are not licensed under this
-          Public License.
-
-       3. To the extent possible, the Licensor waives any right to
-          collect royalties from You for the exercise of the Licensed
-          Rights, whether directly or through a collecting society
-          under any voluntary or waivable statutory or compulsory
-          licensing scheme. In all other cases the Licensor expressly
-          reserves any right to collect such royalties.
-
-
-Section 3 -- License Conditions.
-
-Your exercise of the Licensed Rights is expressly made subject to the
-following conditions.
-
-  a. Attribution.
-
-       1. If You Share the Licensed Material (including in modified
-          form), You must:
-
-            a. retain the following if it is supplied by the Licensor
-               with the Licensed Material:
-
-                 i. identification of the creator(s) of the Licensed
-                    Material and any others designated to receive
-                    attribution, in any reasonable manner requested by
-                    the Licensor (including by pseudonym if
-                    designated);
-
-                ii. a copyright notice;
-
-               iii. a notice that refers to this Public License;
-
-                iv. a notice that refers to the disclaimer of
-                    warranties;
-
-                 v. a URI or hyperlink to the Licensed Material to the
-                    extent reasonably practicable;
-
-            b. indicate if You modified the Licensed Material and
-               retain an indication of any previous modifications; and
-
-            c. indicate the Licensed Material is licensed under this
-               Public License, and include the text of, or the URI or
-               hyperlink to, this Public License.
-
-       2. You may satisfy the conditions in Section 3(a)(1) in any
-          reasonable manner based on the medium, means, and context in
-          which You Share the Licensed Material. For example, it may be
-          reasonable to satisfy the conditions by providing a URI or
-          hyperlink to a resource that includes the required
-          information.
-
-       3. If requested by the Licensor, You must remove any of the
-          information required by Section 3(a)(1)(A) to the extent
-          reasonably practicable.
-
-       4. If You Share Adapted Material You produce, the Adapter's
-          License You apply must not prevent recipients of the Adapted
-          Material from complying with this Public License.
-
-
-Section 4 -- Sui Generis Database Rights.
-
-Where the Licensed Rights include Sui Generis Database Rights that
-apply to Your use of the Licensed Material:
-
-  a. for the avoidance of doubt, Section 2(a)(1) grants You the right
-     to extract, reuse, reproduce, and Share all or a substantial
-     portion of the contents of the database;
-
-  b. if You include all or a substantial portion of the database
-     contents in a database in which You have Sui Generis Database
-     Rights, then the database in which You have Sui Generis Database
-     Rights (but not its individual contents) is Adapted Material; and
-
-  c. You must comply with the conditions in Section 3(a) if You Share
-     all or a substantial portion of the contents of the database.
-
-For the avoidance of doubt, this Section 4 supplements and does not
-replace Your obligations under this Public License where the Licensed
-Rights include other Copyright and Similar Rights.
-
-
-Section 5 -- Disclaimer of Warranties and Limitation of Liability.
-
-  a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE
-     EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS
-     AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF
-     ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS,
-     IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION,
-     WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR
-     PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS,
-     ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT
-     KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT
-     ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU.
-
-  b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE
-     TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION,
-     NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT,
-     INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES,
-     COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR
-     USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN
-     ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR
-     DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR
-     IN PART, THIS LIMITATION MAY NOT APPLY TO YOU.
-
-  c. The disclaimer of warranties and limitation of liability provided
-     above shall be interpreted in a manner that, to the extent
-     possible, most closely approximates an absolute disclaimer and
-     waiver of all liability.
-
-
-Section 6 -- Term and Termination.
-
-  a. This Public License applies for the term of the Copyright and
-     Similar Rights licensed here. However, if You fail to comply with
-     this Public License, then Your rights under this Public License
-     terminate automatically.
-
-  b. Where Your right to use the Licensed Material has terminated under
-     Section 6(a), it reinstates:
-
-       1. automatically as of the date the violation is cured, provided
-          it is cured within 30 days of Your discovery of the
-          violation; or
-
-       2. upon express reinstatement by the Licensor.
-
-     For the avoidance of doubt, this Section 6(b) does not affect any
-     right the Licensor may have to seek remedies for Your violations
-     of this Public License.
-
-  c. For the avoidance of doubt, the Licensor may also offer the
-     Licensed Material under separate terms or conditions or stop
-     distributing the Licensed Material at any time; however, doing so
-     will not terminate this Public License.
-
-  d. Sections 1, 5, 6, 7, and 8 survive termination of this Public
-     License.
-
-
-Section 7 -- Other Terms and Conditions.
-
-  a. The Licensor shall not be bound by any additional or different
-     terms or conditions communicated by You unless expressly agreed.
-
-  b. Any arrangements, understandings, or agreements regarding the
-     Licensed Material not stated herein are separate from and
-     independent of the terms and conditions of this Public License.
-
-
-Section 8 -- Interpretation.
-
-  a. For the avoidance of doubt, this Public License does not, and
-     shall not be interpreted to, reduce, limit, restrict, or impose
-     conditions on any use of the Licensed Material that could lawfully
-     be made without permission under this Public License.
-
-  b. To the extent possible, if any provision of this Public License is
-     deemed unenforceable, it shall be automatically reformed to the
-     minimum extent necessary to make it enforceable. If the provision
-     cannot be reformed, it shall be severed from this Public License
-     without affecting the enforceability of the remaining terms and
-     conditions.
-
-  c. No term or condition of this Public License will be waived and no
-     failure to comply consented to unless expressly agreed to by the
-     Licensor.
-
-  d. Nothing in this Public License constitutes or may be interpreted
-     as a limitation upon, or waiver of, any privileges and immunities
-     that apply to the Licensor or You, including from the legal
-     processes of any jurisdiction or authority.
-
-
-=======================================================================
-
-Creative Commons is not a party to its public
-licenses. Notwithstanding, Creative Commons may elect to apply one of
-its public licenses to material it publishes and in those instances
-will be considered the “Licensor.” The text of the Creative Commons
-public licenses is dedicated to the public domain under the CC0 Public
-Domain Dedication. Except for the limited purpose of indicating that
-material is shared under a Creative Commons public license or as
-otherwise permitted by the Creative Commons policies published at
-creativecommons.org/policies, Creative Commons does not authorize the
-use of the trademark "Creative Commons" or any other trademark or logo
-of Creative Commons without its prior written consent including,
-without limitation, in connection with any unauthorized modifications
-to any of its public licenses or any other arrangements,
-understandings, or agreements concerning use of licensed material. For
-the avoidance of doubt, this paragraph does not form part of the
-public licenses.
-
-Creative Commons may be contacted at creativecommons.org.
-
-

docs/api.md

@@ -1,21 +1,21 @@
 - [Cloud Hypervisor API](#cloud-hypervisor-api)
-  - [External API](#external-api)
-    - [REST API](#rest-api)
-    - [Location and availability](#location-and-availability)
-    - [Endpoints](#endpoints)
-      - [Virtual Machine Manager (VMM) Actions](#virtual-machine-manager-vmm-actions)
-      - [Virtual Machine (VM) Actions](#virtual-machine-vm-actions)
-    - [REST API Examples](#rest-api-examples)
-      - [Create a Virtual Machine](#create-a-virtual-machine)
-      - [Boot a Virtual Machine](#boot-a-virtual-machine)
-      - [Dump a Virtual Machine Information](#dump-a-virtual-machine-information)
-      - [Reboot a Virtual Machine](#reboot-a-virtual-machine)
-      - [Shut a Virtual Machine Down](#shut-a-virtual-machine-down)
-    - [Command Line Interface](#command-line-interface)
-    - [REST API and CLI Architectural Relationship](#rest-api-and-cli-architectural-relationship)
-  - [Internal API](#internal-api)
-    - [Goals and Design](#goals-and-design)
-  - [End to End Example](#end-to-end-example)
+  * [External API](#external-api)
+    + [REST API](#rest-api)
+      - [Location and availability](#location-and-availability)
+      - [Endpoints](#endpoints)
+		* [Virtual Machine Manager (VMM) Actions](#virtual-machine-manager-vmm-actions)
+		* [Virtual Machine (VM) Actions](#virtual-machine-vm-actions)
+      - [REST API Examples](#rest-api-examples)
+        * [Create a Virtual Machine](#create-a-virtual-machine)
+	    * [Boot a Virtual Machine](#boot-a-virtual-machine)
+        * [Dump a Virtual Machine Information](#dump-a-virtual-machine-information)
+        * [Reboot a Virtual Machine](#reboot-a-virtual-machine)
+        * [Shut a Virtual Machine Down](#shut-a-virtual-machine-down)
+    + [Command Line Interface](#command-line-interface)
+    + [REST API and CLI Architectural Relationship](#rest-api-and-cli-architectural-relationship)
+  * [Internal API](#internal-api)
+    + [Goals and Design](#goals-and-design)
+  * [End to End Example](#end-to-end-example)
 
 # Cloud Hypervisor API
 
@@ -71,40 +71,34 @@ The Cloud Hypervisor API exposes the following actions through its endpoints:
 
 #### Virtual Machine Manager (VMM) Actions
 
-| Action                              | Endpoint        | Request Body | Response Body              | Prerequisites      |
-| ----------------------------------- | --------------- | ------------ | -------------------------- | ------------------ |
-| Check for the REST API availability | `/vmm.ping`     | N/A          | `/schemas/VmmPingResponse` | N/A                |
-| Shut the VMM down                   | `/vmm.shutdown` | N/A          | N/A                        | The VMM is running |
+Action                              | Endpoint        | Request Body | Response Body              | Prerequisites
+------------------------------------|-----------------|--------------|----------------------------|---------------------------
+Check for the REST API availability | `/vmm.ping`     | N/A          | `/schemas/VmmPingResponse` | N/A
+Shut the VMM down                   | `/vmm.shutdown` | N/A          | N/A                        | The VMM is running
 
 #### Virtual Machine (VM) Actions
 
-| Action                             | Endpoint              | Request Body                | Response Body            | Prerequisites                    |
-| ---------------------------------- | --------------------- | --------------------------- | ------------------------ | -------------------------------- |
-| Create the VM                      | `/vm.create`          | `/schemas/VmConfig`         | N/A                      | The VM is not created yet        |
-| Delete the VM                      | `/vm.delete`          | N/A                         | N/A                      | N/A                              |
-| Boot the VM                        | `/vm.boot`            | N/A                         | N/A                      | The VM is created but not booted |
-| Shut the VM down                   | `/vm.shutdown`        | N/A                         | N/A                      | The VM is booted                 |
-| Reboot the VM                      | `/vm.reboot`          | N/A                         | N/A                      | The VM is booted                 |
-| Trigger power button of the VM     | `/vm.power-button`    | N/A                         | N/A                      | The VM is booted                 |
-| Pause the VM                       | `/vm.pause`           | N/A                         | N/A                      | The VM is booted                 |
-| Resume the VM                      | `/vm.resume`          | N/A                         | N/A                      | The VM is paused                 |
-| Task a snapshot of the VM          | `/vm.snapshot`        | `/schemas/VmSnapshotConfig` | N/A                      | The VM is paused                 |
-| Perform a coredump of the VM       | `/vm.coredump`        | `/schemas/VmCoredumpData`   | N/A                      | The VM is paused                 |
-| Restore the VM from a snapshot     | `/vm.restore`         | `/schemas/RestoreConfig`    | N/A                      | The VM is created but not booted |
-| Add/remove CPUs to/from the VM     | `/vm.resize`          | `/schemas/VmResize`         | N/A                      | The VM is booted                 |
-| Add/remove memory from the VM      | `/vm.resize`          | `/schemas/VmResize`         | N/A                      | The VM is booted                 |
-| Add/remove memory from a zone      | `/vm.resize-zone`     | `/schemas/VmResizeZone`     | N/A                      | The VM is booted                 |
-| Dump the VM information            | `/vm.info`            | N/A                         | `/schemas/VmInfo`        | The VM is created                |
-| Add VFIO PCI device to the VM      | `/vm.add-device`      | `/schemas/VmAddDevice`      | `/schemas/PciDeviceInfo` | The VM is booted                 |
-| Add disk device to the VM          | `/vm.add-disk`        | `/schemas/DiskConfig`       | `/schemas/PciDeviceInfo` | The VM is booted                 |
-| Add fs device to the VM            | `/vm.add-fs`          | `/schemas/FsConfig`         | `/schemas/PciDeviceInfo` | The VM is booted                 |
-| Add pmem device to the VM          | `/vm.add-pmem`        | `/schemas/PmemConfig`       | `/schemas/PciDeviceInfo` | The VM is booted                 |
-| Add network device to the VM       | `/vm.add-net`         | `/schemas/NetConfig`        | `/schemas/PciDeviceInfo` | The VM is booted                 |
-| Add userspace PCI device to the VM | `/vm.add-user-device` | `/schemas/VmAddUserDevice`  | `/schemas/PciDeviceInfo` | The VM is booted                 |
-| Add vdpa device to the VM          | `/vm.add-vdpa`        | `/schemas/VdpaConfig`       | `/schemas/PciDeviceInfo` | The VM is booted                 |
-| 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                 |
+Action                             | Endpoint            | Request Body              | Response Body            | Prerequisites
+-----------------------------------|---------------------|---------------------------|--------------------------|---------------------------
+Create the VM                      | `/vm.create`        | `/schemas/VmConfig`       | N/A                      | The VM is not created yet
+Delete the VM                      | `/vm.delete`        | N/A                       | N/A                      | N/A
+Boot the VM                        | `/vm.boot`          | N/A                       | N/A                      | The VM is created but not booted
+Shut the VM down                   | `/vm.shutdown`      | N/A                       | N/A                      | The VM is booted
+Reboot the VM                      | `/vm.reboot`        | N/A                       | N/A                      | The VM is booted
+Pause the VM                       | `/vm.pause`         | N/A                       | N/A                      | The VM is booted
+Resume the VM                      | `/vm.resume`        | N/A                       | N/A                      | The VM is paused
+Add/remove CPUs to/from the VM     | `/vm.resize`        | `/schemas/VmResize`       | N/A                      | The VM is booted
+Add/remove memory from the VM      | `/vm.resize`        | `/schemas/VmResize`       | N/A                      | The VM is booted
+Add/remove memory from a zone      | `/vm.resize-zone`   | `/schemas/VmResizeZone`   | N/A                      | The VM is booted
+Dump the VM information            | `/vm.info`          | N/A                       | `/schemas/VmInfo`        | The VM is created
+Add VFIO PCI device to the VM      | `/vm.add-device`    | `/schemas/VmAddDevice`    | `/schemas/PciDeviceInfo` | The VM is booted
+Add disk device to the VM          | `/vm.add-disk`      | `/schemas/DiskConfig`     | `/schemas/PciDeviceInfo` | The VM is booted
+Add fs device to the VM            | `/vm.add-fs`        | `/schemas/FsConfig`       | `/schemas/PciDeviceInfo` | The VM is booted
+Add pmem device to the VM          | `/vm.add-pmem`      | `/schemas/PmemConfig`     | `/schemas/PciDeviceInfo` | The VM is booted
+Add network device to the VM       | `/vm.add-net`       | `/schemas/NetConfig`      | `/schemas/PciDeviceInfo` | The VM is booted
+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
 
 ### REST API Examples
 
@@ -143,7 +137,8 @@ curl --unix-socket /tmp/cloud-hypervisor.sock -i \
      -H 'Content-Type: application/json'         \
      -d '{
          "cpus":{"boot_vcpus": 4, "max_vcpus": 4},
-         "payload":{"kernel":"/opt/clh/kernel/vmlinux-virtio-fs-virtio-iommu", "cmdline":"console=ttyS0 console=hvc0 root=/dev/vda1 rw"},
+         "kernel":{"path":"/opt/clh/kernel/vmlinux-virtio-fs-virtio-iommu"},
+         "cmdline":{"args":"console=ttyS0 console=hvc0 root=/dev/vda1 rw"},
          "disks":[{"path":"/opt/clh/images/focal-server-cloudimg-amd64.raw"}],
          "rng":{"src":"/dev/urandom"},
          "net":[{"ip":"192.168.10.10", "mask":"255.255.255.0", "mac":"12:34:56:78:90:01"}]
@@ -310,7 +305,8 @@ APIs work together, let's look at a complete VM creation flow, from the
 		-H 'Content-Type: application/json'         \
 		-d '{
 			"cpus":{"boot_vcpus": 4, "max_vcpus": 4},
-			"payload":{"kernel":"/opt/clh/kernel/vmlinux-virtio-fs-virtio-iommu", "cmdline":"console=ttyS0 console=hvc0 root=/dev/vda1 rw"},
+			"kernel":{"path":"/opt/clh/kernel/vmlinux-virtio-fs-virtio-iommu"},
+			"cmdline":{"args":"console=ttyS0 console=hvc0 root=/dev/vda1 rw"},
 			"disks":[{"path":"/opt/clh/images/focal-server-cloudimg-amd64.raw"}],
 			"rng":{"src":"/dev/urandom"},
 			"net":[{"ip":"192.168.10.10", "mask":"255.255.255.0", "mac":"12:34:56:78:90:01"}]

docs/arm64.md

@@ -1,152 +1,58 @@
-# How to build and test Cloud Hypervisor on AArch64
+# How to build and run Cloud-hypervisor on AArch64
 
-This document introduces how to build and test Cloud Hypervisor on AArch64.
-Currently, Cloud Hypervisor supports 2 methods of booting on AArch64: UEFI
-booting and direct-kernel booting. The document covers both methods.
-
-All the steps are based on Ubuntu. We use the Ubuntu cloud image for guest VM
-disk.
-
-## Hardware requirements
-
-- AArch64 servers (recommended) or development boards equipped with the GICv3
-interrupt controller.
-
-- On development boards that have constrained RAM resources, if the creation of
-a VM consumes a large portion of the free memory on the host, it may be required
-to enable swap. For example, this was required on a board with 3 GB of RAM
-booting a 2 GB VM at a point in time when 2.8 GB were free. Without enabling
-swap the `cloud-hypervisor` process was terminated by the OOM killer. In this
-situation memory was allocated for the virtual machine using memfd while the
-page cache was filled, leading to a situation where the kernel could not even
-drop caches. Making a small section of swap available (observably, 1 to 15 MB),
-this situation can be resolved and the resulting memory footprint of
-`cloud-hypervisor` is as expected.
-
-## Getting started
-
-We create a folder to build and run Cloud Hypervisor at `$HOME/cloud-hypervisor`
-
-```shell
-$ export CLOUDH=$HOME/cloud-hypervisor
-$ mkdir $CLOUDH
-```
+Cloud-hypervisor is partially enabled on AArch64 architecture.
+Although all features are not ready yet, you can begin to test Cloud-hypervisor on a AArch64 host by following this guide.
 
 ## Prerequisites
 
-You need to install some prerequisite packages to build and test Cloud Hypervisor.
+On AArch64 machines, Cloud-hypervisor depends on an external library `libfdt-dev` for generating Flattened Device Tree (FDT).
 
-### Tools
+The long-term plan is to replace `libfdt-dev` with some pure-Rust component to get rid of such dependency.
 
 ```bash
-# Install rust tool chain
-$ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
-# Install the tools used for building guest kernel, EDK2 and converting guest disk
-$ sudo apt-get update
-$ sudo apt-get install git build-essential m4 bison flex uuid-dev qemu-utils
+sudo apt-get update
+sudo apt-get install libfdt-dev
 ```
 
-### Building Cloud Hypervisor
+## Build
+
+Using PCI devices requires GICv3-ITS for MSI messaging. GICv3-ITS is very common in modern servers.
 
 ```bash
-$ pushd $CLOUDH
-$ git clone https://github.com/cloud-hypervisor/cloud-hypervisor.git
-$ cd cloud-hypervisor
-$ cargo build
-$ popd
+cargo build --no-default-features --features kvm
 ```
 
-### Disk image
+## Image
 
-Download the Ubuntu cloud image and convert the image type.
+Download kernel binary and rootfs image from AWS.
 
 ```bash
-$ pushd $CLOUDH
-$ wget https://cloud-images.ubuntu.com/focal/current/focal-server-cloudimg-arm64.img
-$ qemu-img convert -p -f qcow2 -O raw focal-server-cloudimg-arm64.img focal-server-cloudimg-arm64.raw
-$ popd
+wget https://s3.amazonaws.com/spec.ccfc.min/img/aarch64/ubuntu_with_ssh/fsfiles/xenial.rootfs.ext4 -O rootfs.ext4
+wget https://s3.amazonaws.com/spec.ccfc.min/img/aarch64/ubuntu_with_ssh/kernel/vmlinux.bin -O kernel.bin
 ```
 
-## UEFI booting
+## Containerized build
 
-This part introduces how to build EDK2 firmware and boot Cloud Hypervisor with it.
+If you want to build and test Cloud Hypervisor without having to install all the required dependencies, you can also turn to the development script: dev_cli.sh.
 
-### Building EDK2
+To build the development container:
 
 ```bash
-$ pushd $CLOUDH
-
-# Clone source code repos
-$ git clone --depth 1 https://github.com/tianocore/edk2.git -b master
-$ cd edk2
-$ git submodule update --init
-$ cd ..
-$ git clone --depth 1 https://github.com/tianocore/edk2-platforms.git -b master
-$ git clone --depth 1 https://github.com/acpica/acpica.git -b master
-
-# Build tools
-$ export PACKAGES_PATH="$PWD/edk2:$PWD/edk2-platforms"
-$ export IASL_PREFIX="$PWD/acpica/generate/unix/bin/"
-$ make -C acpica
-$ cd edk2/
-$ . edksetup.sh
-$ cd ..
-$ make -C edk2/BaseTools
-
-# Build EDK2
-$ build -a AARCH64 -t GCC5 -p ArmVirtPkg/ArmVirtCloudHv.dsc -b RELEASE
-
-$ popd
+./scripts/dev_cli.sh build-container
 ```
 
-If the build goes well, the EDK2 binary is available at
-`edk2/Build/ArmVirtCloudHv-AARCH64/RELEASE_GCC5/FV/CLOUDHV_EFI.fd`.
-
-### Booting the guest VM
+To build Cloud-hypervisor in the container:
 
 ```bash
-$ pushd $CLOUDH
-$ sudo RUST_BACKTRACE=1 $CLOUDH/cloud-hypervisor/target/debug/cloud-hypervisor \
-           --api-socket /tmp/cloud-hypervisor.sock \
-           --kernel $CLOUDH/edk2/Build/ArmVirtCloudHv-AARCH64/RELEASE_GCC5/FV/CLOUDHV_EFI.fd \
-           --disk path=$CLOUDH/focal-server-cloudimg-arm64.raw \
-           --cpus boot=4 \
-           --memory size=4096M \
-           --net tap=,mac=12:34:56:78:90:01,ip=192.168.1.1,mask=255.255.255.0 \
-           --serial tty \
-           --console off
-$ popd
+./scripts/dev_cli.sh build
 ```
 
-## Direct-kernel booting
+## Run
 
-Alternativelly, you can build your own kernel for guest VM. This way, UEFI is
-not involved and ACPI cannot be enabled.
-
-### Building kernel
+Assuming you have built Cloud-hypervisor with the development container, a VM can be started with command:
 
 ```bash
-$ pushd $CLOUDH
-$ git clone --depth 1 "https://github.com/cloud-hypervisor/linux.git" -b ch-5.12
-$ cd linux
-$ cp $CLOUDH/cloud-hypervisor/resources/linux-config-aarch64 .config
-$ make -j `nproc`
-$ popd
+sudo build/cargo_target/aarch64-unknown-linux-gnu/debug/cloud-hypervisor --kernel kernel.bin --disk path=rootfs.ext4 --cmdline "keep_bootcon console=hvc0 reboot=k panic=1 root=/dev/vda rw" --cpus boot=4 --memory size=512M --serial file=serial.log --log-file log.log -vvv
 ```
 
-### Booting the guest VM
-
-```bash
-$ pushd $CLOUDH
-$ sudo $CLOUDH/cloud-hypervisor/target/debug/cloud-hypervisor \
-           --api-socket /tmp/cloud-hypervisor.sock \
-           --kernel $CLOUDH/linux/arch/arm64/boot/Image \
-           --disk path=focal-server-cloudimg-arm64.raw \
-           --cmdline "keep_bootcon console=ttyAMA0 reboot=k panic=1 root=/dev/vda1 rw" \
-           --cpus boot=4 \
-           --memory size=4096M \
-           --net tap=,mac=12:34:56:78:90:01,ip=192.168.1.1,mask=255.255.255.0 \
-           --serial tty \
-           --console off
-$ popd
-```
+If the build was done out of the container, replace the binary path with `target/debug/cloud-hypervisor`.

docs/balloon.md

@@ -1,76 +0,0 @@
-# Balloon
-
-Cloud Hypervisor implements a balloon device based on the VIRTIO specification.
-Its main purpose is to provide the host a way to reclaim memory by controlling
-the amount of memory visible to the guest. But it also provides some interesting
-features related to guest memory management.
-
-## Parameters
-
-`BalloonConfig` (known as `--balloon` from the CLI perspective) contains the
-list of parameters available for the balloon device.
-
-```rust
-struct BalloonConfig {
-    pub size: u64,
-    pub deflate_on_oom: bool,
-    pub free_page_reporting: bool,
-}
-```
-
-```
---balloon <balloon>	Balloon parameters "size=<balloon_size>,deflate_on_oom=on|off,free_page_reporting=on|off"
-```
-
-### `size`
-
-Size of the balloon device. It is subtracted from the VM's total size. For
-instance, if creating a VM with 4GiB of RAM, along with a balloon of 1GiB, the
-guest will be able to use 3GiB of accessible memory. The guest sees all the RAM
-and unless it is balloon enlightened is entitled to all of it.
-
-This parameter is mandatory.
-
-Value is an unsigned integer of 64 bits corresponding to the balloon size in
-bytes.
-
-_Example_
-
-```
---balloon size=1G
-```
-
-### `deflate_on_oom`
-
-Allow the guest to deflate the balloon if running Out Of Memory (OOM). Assuming
-the balloon size is greater than 0, this means the guest is allowed to reduce
-the balloon size all the way down to 0 if this can help recover from the OOM
-event.
-
-This parameter is optional.
-
-Value is a boolean set to `off` by default.
-
-_Example_
-
-```
---ballloon size=2G,deflate_on_oom=on
-```
-
-### `free_page_reporting`
-
-Allow the guest to report lists of free pages. This feature doesn't require the
-balloon to be of any specific size as it doesn't impact the balloon size. The
-guest can let the VMM know about pages that are free after they have been used.
-Based on this information, the VMM can advise the host that it doesn't need
-these pages anymore.
-
-This parameter is optional.
-
-Value is a boolean set to `off` by default.
-
-_Example_
-
-```
---ballloon size=0,free_page_reporting=on
-```

docs/building.md

@@ -1,82 +0,0 @@
-- [Building Cloud Hypervisor](#building-cloud-hypervisor)
-  - [Preparation](#preparation)
-  - [Install prerequisites](#install-prerequisites)
-  - [Clone and build](#clone-and-build)
-    - [Containerized builds and tests](#containerized-builds-and-tests)
-
-# Building Cloud Hypervisor
-
-We recommend users use the pre-built binaries that are mentioned in the README.md file in the root of the repository. Building from source is only necessary if you wish to make modifications.
-
-## Preparation
-
-We create a folder to build and run `cloud-hypervisor` at `$HOME/cloud-hypervisor`
-
-```shell
-$ export CLOUDH=$HOME/cloud-hypervisor
-$ mkdir $CLOUDH
-```
-
-## Install prerequisites
-
-You need to install some prerequisite packages in order to build and test Cloud
-Hypervisor. Here, all the steps are based on Ubuntu, for other Linux
-distributions please replace the package manager and package name.
-
-```shell
-# Install build-essential, git, and qemu-utils
-$ sudo apt install git build-essential qemu-utils
-# Install rust tool chain
-$ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
-# If you want to build statically linked binary please add musl target
-$ rustup target add x86_64-unknown-linux-musl
-```
-
-## Clone and build
-
-First you need to clone and build the Cloud Hypervisor repository:
-
-```shell
-$ pushd $CLOUDH
-$ git clone https://github.com/cloud-hypervisor/cloud-hypervisor.git
-$ cd cloud-hypervisor
-$ cargo build --release
-
-# We need to give the cloud-hypervisor binary the NET_ADMIN capabilities for it to set TAP interfaces up on the host.
-$ sudo setcap cap_net_admin+ep ./target/release/cloud-hypervisor
-
-# If you want to build statically linked binary
-$ cargo build --release --target=x86_64-unknown-linux-musl --all
-$ popd
-```
-
-This will build a `cloud-hypervisor` binary under
-`$CLOUDH/cloud-hypervisor/target/release/cloud-hypervisor`.
-
-### Containerized builds and tests
-
-If you want to build and test Cloud Hypervisor without having to install all the
-required dependencies (The rust toolchain, cargo tools, etc), you can also use
-Cloud Hypervisor's development script: `dev_cli.sh`. Please note that upon its
-first invocation, this script will pull a fairly large container image.
-
-For example, to build the Cloud Hypervisor release binary:
-
-```shell
-$ pushd $CLOUDH
-$ cd cloud-hypervisor
-$ ./scripts/dev_cli.sh build --release
-```
-
-With `dev_cli.sh`, one can also run the Cloud Hypervisor CI locally. This can be
-very convenient for debugging CI errors without having to fully rely on the
-Cloud Hypervisor CI infrastructure.
-
-For example, to run the Cloud Hypervisor unit tests:
-
-```shell
-$ ./scripts/dev_cli.sh tests --unit
-```
-
-Run the `./scripts/dev_cli.sh --help` command to view all the supported
-development script commands and their related options.

docs/cpu.md

@@ -1,211 +0,0 @@
-# CPU
-
-Cloud Hypervisor has many options when it comes to the creation of virtual
-CPUs. This document aims to explain what Cloud Hypervisor is capable of and
-how it can be used to meet the needs of very different use cases.
-
-## Options
-
-`CpusConfig` or what is known as `--cpus` from the CLI perspective is the way
-to set vCPUs options for Cloud Hypervisor.
-
-```rust
-struct CpusConfig {
-    boot_vcpus: u8,
-    max_vcpus: u8,
-    topology: Option<CpuTopology>,
-    kvm_hyperv: bool,
-    max_phys_bits: u8,
-    affinity: Option<Vec<CpuAffinity>>,
-    features: CpuFeatures,
-}
-```
-
-```
---cpus boot=<boot_vcpus>,max=<max_vcpus>,topology=<threads_per_core>:<cores_per_die>:<dies_per_package>:<packages>,kvm_hyperv=on|off,max_phys_bits=<maximum_number_of_physical_bits>,affinity=<list_of_vcpus_with_their_associated_cpuset>,features=<list_of_features_to_enable>
-```
-
-### `boot`
-
-Number of vCPUs present at boot time.
-
-This option allows to define a specific number of vCPUs to be present at the
-time the VM is started. This option is mandatory when using the `--cpus`
-parameter. If `--cpus` is not specified, this option takes the default value
-of `1`, starting the VM with a single vCPU.
-
-Value is an unsigned integer of 8 bits.
-
-_Example_
-
-```
---cpus boot=2
-```
-
-### `max`
-
-Maximum number of vCPUs.
-
-This option defines the maximum number of vCPUs that can be assigned to the VM.
-In particular, this option is used when looking for CPU hotplug as it lets the
-provide an indication about how many vCPUs might be needed later during the
-runtime of the VM.
-For instance, if booting the VM with 2 vCPUs and a maximum of 6 vCPUs, it means
-up to 4 vCPUs can be added later at runtime by resizing the VM.
-
-The value must be greater than or equal to the number of boot vCPUs.
-The value is an unsigned integer of 8 bits.
-
-By default this option takes the value of `boot`, meaning vCPU hotplug is not
-expected and can't be performed.
-
-_Example_
-
-```
---cpus max=3
-```
-
-### `topology`
-
-Topology of the guest platform.
-
-This option gives the user a way to describe the exact topology that should be
-exposed to the guest. It can be useful to describe to the guest the same
-topology found on the host as it allows for proper usage of the resources and
-is a way to achieve better performances.
-
-The topology is described through the following structure:
-
-```rust
-struct CpuTopology {
-    threads_per_core: u8,
-    cores_per_die: u8,
-    dies_per_package: u8,
-    packages: u8,
-}
-```
-
-or the following syntax through the CLI:
-
-```
-topology=<threads_per_core>:<cores_per_die>:<dies_per_package>:<packages>
-```
-
-By default the topology will be `1:1:1:1`.
-
-_Example_
-
-```
---cpus boot=2,topology=1:1:2:1
-```
-
-### `kvm_hyperv`
-
-Enable KVM Hyper-V emulation.
-
-When turned on, this option relies on KVM to emulate the synthetic interrupt
-controller (SynIC) along with synthetic timers expected by a Windows guest.
-A Windows guest usually runs on top of Microsoft Hyper-V, therefore expects
-these synthetic devices to be present. That's why KVM provides a way to emulate
-them and avoids failures running a Windows guest with Cloud Hypervisor.
-
-By default this option is turned off.
-
-_Example_
-
-```
---cpus kvm_hyperv=on
-```
-
-### `max_phys_bits`
-
-Maximum size for guest's addressable space.
-
-This option defines the maximum number of physical bits for all vCPUs, which
-sets a limit for the size of the guest's addressable space. This is mainly
-useful for debug purpose.
-
-The value is an unsigned integer of 8 bits.
-
-_Example_
-
-```
---cpus max_phys_bits=40
-```
-
-### `affinity`
-
-Affinity of each vCPU.
-
-This option gives the user a way to provide the host CPU set associated with
-each vCPU. It is useful for achieving CPU pinning, ensuring multiple VMs won't
-affect the performance of each other. It might also be used in the context of
-NUMA as it is way of making sure the VM can run on a specific host NUMA node.
-In general, this option is used to increase the performances of a VM depending
-on the host platform and the type of workload running in the guest.
-
-The affinity is described through the following structure:
-
-```rust
-struct CpuAffinity {
-    vcpu: u8,
-    host_cpus: Vec<u8>,
-}
-```
-
-or the following syntax through the CLI:
-
-```
-affinity=[<vcpu_id1>@[<host_cpu_id1>, <host_cpu_id2>], <vcpu_id2>@[<host_cpu_id3>, <host_cpu_id4>]]
-```
-
-The outer brackets define the list of vCPUs. And for each vCPU, the inner
-brackets attached to `@` define the list of host CPUs the vCPU is allowed to
-run onto.
-
-Multiple values can be provided to define each list. Each value is an unsigned
-integer of 8 bits.
-
-For instance, if one needs to run vCPU 0 on host CPUs from 0 to 4, the syntax
-using `-` will help define a contiguous range with `affinity=0@[0-4]`. The
-same example could also be described with `affinity=0@[0,1,2,3,4]`.
-
-A combination of both `-` and `,` separators is useful when one might need to
-describe a list containing host CPUs from 0 to 99 and the host CPU 255, as it
-could simply be described with `affinity=0@[0-99,255]`.
-
-As soon as one tries to describe a list of values, `[` and `]` must be used to
-demarcate the list.
-
-By default each vCPU runs on the entire host CPU set.
-
-_Example_
-
-```
---cpus boot=3,affinity=[0@[2,3],1@[0,1]]
-```
-
-In this example, assuming the host has 4 CPUs, vCPU 0 will run exclusively on
-host CPUs 2 and 3, while vCPU 1 will run exclusively on host CPUs 0 and 1.
-Because nothing is defined for vCPU 2, it can run on any of the 4 host CPUs.
-
-### `features`
-
-Set of CPU features to enable.
-
-This option allows the user to enable a set of CPU features that are disabled
-by default otherwise.
-
-The currently available feature set is: `amx`.
-
-The `amx` feature will enable the x86 extension adding hardware units for
-matrix operations (int and float dot products). The goal of the extension is to
-provide performance enhancements for these common operations.
-
-_Example_
-
-```
---cpus features=amx
-```
-
-In this example the amx CPU feature will be enabled for the VMM.

docs/custom-image.md

@@ -59,16 +59,6 @@ mkdir -p /mnt
 sudo mount -o loop,offset=$((227328 * 512)) focal-server-cloudimg-amd64.raw /mnt
 ```
 
-### Set up DNS
-
-The next step describes changing the root directory to the rootfs contained by 
-the cloud image. For DNS to work in the root directory, you will need to first bind-mount 
-the host `/etc/resolv.conf` onto the mounted linux partition of the cloud image.
-
-```bash
-sudo mount -o bind /etc/resolv.conf /mnt/etc/resolv.conf
-```
-
 ### Change root directory
 
 Changing the root directory will allow us to install new packages to the rootfs
@@ -82,13 +72,13 @@ mount -t devpts devpts /dev/pts
 
 ### Install needed packages
 
-In the context Cloud Hypervisor's integration tests, we need several utilities.
+In the context Cloud-Hypervisor's integration tests, we need several utilities.
 Here is the way to install them for a Ubuntu image. This step is specific to
 Ubuntu distributions.
 
 ```bash
 apt update
-apt install fio iperf iperf3 socat stress
+apt install fio iperf iperf3 socat
 ```
 
 ### Remove counterproductive packages
@@ -118,7 +108,6 @@ umount /dev/pts
 umount /proc
 history -c
 exit
-umount /mnt/etc/resolv.conf
 umount /mnt
 ```
 

docs/device_model.md

@@ -6,22 +6,22 @@ This document describes the device model supported by `cloud-hypervisor`.
 
 | Device | Build configurable | Enabled by default | Runtime configurable |
 | :----: | :----: | :----: | :----: |
-| Serial port | :x: | :x: | :heavy_check_mark: |
-| RTC/CMOS | :heavy_check_mark: | :heavy_check_mark: | :x: |
-| I/O APIC | :x: | :x: | :heavy_check_mark: |
-| i8042 shutdown/reboot | :x: | :x: | :x: |
-| ACPI shutdown/reboot | :x: | :heavy_check_mark: | :x: |
-| virtio-blk | :x: | :x: | :heavy_check_mark: |
-| virtio-console | :x: | :x: | :heavy_check_mark: |
-| virtio-iommu | :x: | :x: | :heavy_check_mark: |
-| virtio-net | :x: | :x: | :heavy_check_mark: |
-| virtio-pmem | :x: | :x: | :heavy_check_mark: |
-| virtio-rng | :x: | :x: | :heavy_check_mark: |
-| virtio-vsock | :x: | :x: | :heavy_check_mark: |
-| vhost-user-blk | :x: | :x: | :heavy_check_mark: |
-| vhost-user-fs | :x: | :x: | :heavy_check_mark: |
-| vhost-user-net | :x: | :x: | :heavy_check_mark: |
-| VFIO | :heavy_check_mark: | :x: | :heavy_check_mark: |
+| Serial port | :negative_squared_cross_mark: | :negative_squared_cross_mark: | :heavy_check_mark: |
+| RTC/CMOS | :heavy_check_mark: | :heavy_check_mark: | :negative_squared_cross_mark: |
+| I/O APIC | :negative_squared_cross_mark: | :negative_squared_cross_mark: | :heavy_check_mark: |
+| i8042 shutdown/reboot | :negative_squared_cross_mark: | :negative_squared_cross_mark: | :negative_squared_cross_mark: |
+| ACPI shutdown/reboot | :negative_squared_cross_mark: | :heavy_check_mark: | :negative_squared_cross_mark: |
+| virtio-blk | :negative_squared_cross_mark: | :negative_squared_cross_mark: | :heavy_check_mark: |
+| virtio-console | :negative_squared_cross_mark: | :negative_squared_cross_mark: | :heavy_check_mark: |
+| virtio-iommu | :negative_squared_cross_mark: | :negative_squared_cross_mark: | :heavy_check_mark: |
+| virtio-net | :negative_squared_cross_mark: | :negative_squared_cross_mark: | :heavy_check_mark: |
+| virtio-pmem | :negative_squared_cross_mark: | :negative_squared_cross_mark: | :heavy_check_mark: |
+| virtio-rng | :negative_squared_cross_mark: | :negative_squared_cross_mark: | :heavy_check_mark: |
+| virtio-vsock | :negative_squared_cross_mark: | :negative_squared_cross_mark: | :heavy_check_mark: |
+| vhost-user-blk | :negative_squared_cross_mark: | :negative_squared_cross_mark: | :heavy_check_mark: |
+| vhost-user-fs | :negative_squared_cross_mark: | :negative_squared_cross_mark: | :heavy_check_mark: |
+| vhost-user-net | :negative_squared_cross_mark: | :negative_squared_cross_mark: | :heavy_check_mark: |
+| VFIO | :heavy_check_mark: | :negative_squared_cross_mark: | :heavy_check_mark: |
 
 ## Legacy devices
 
@@ -89,9 +89,7 @@ feature is enabled by default.
 ## Virtio devices
 
 For all virtio devices listed below, only `virtio-pci` transport layer is
-supported. Cloud Hypervisor supports multiple PCI segments, and users can
-append `,pci_segment=<PCI_segment_number>` to the device flag in the Cloud
-Hypervisor command line to assign devices to a specific PCI segment.
+supported.
 
 ### virtio-block
 
@@ -115,8 +113,9 @@ selecting `--serial tty --console off` from the command line.
 ### virtio-iommu
 
 As we want to improve our nested guests support, we added support for exposing
-a [paravirtualized IOMMU](iommu.md) device through virtio. This allows for a
-safer nested virtio and directly assigned devices support.
+a [paravirtualized IOMMU](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/iommu.md)
+device through virtio. This allows for a safer nested virtio and directly
+assigned devices support.
 
 This device is always built-in, and it is enabled based on the presence of the
 parameter `iommu=on` in any of the virtio or VFIO devices. If at least one of
@@ -185,8 +184,8 @@ This device is always built-in, and it is enabled when `vhost_user=true` and
 shared file system, allowing for an efficient and reliable way of sharing
 a filesystem between the host and the cloud-hypervisor guest.
 
-See our [filesystem sharing](fs.md) documentation for more details on how to
-use virtio-fs with cloud-hypervisor.
+See our [filesystem sharing](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/fs.md)
+documentation for more details on how to use virtio-fs with cloud-hypervisor.
 
 This device is always built-in, and it is enabled based on the presence of the
 flag `--fs`.
@@ -207,8 +206,9 @@ VFIO (Virtual Function I/O) is a kernel framework that exposes direct device
 access to userspace. `cloud-hypervisor` uses VFIO to directly assign host
 physical devices into its guest.
 
-See our [VFIO documentation](vfio.md) for more details on how to directly
-assign host devices to `cloud-hypervisor` guests.
+See our [VFIO documentation](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/vfio.md)
+for more details on how to directly assign host devices to `cloud-hypervisor`
+guests.
 
 Because VFIO implies `vfio-pci` in the `cloud-hypervisor` context, the VFIO
 support is built-in when the `pci` feature is selected. And because the `pci`

docs/fs.md

@@ -1,27 +1,23 @@
 # How to use virtio-fs
 
-In the context of virtualization, it is always convenient to be able to share a
-directory from the host with the guest.
+In the context of virtualization, it is always convenient to be able to share a directory from the host with the guest.
 
-__virtio-fs__, also known as __vhost-user-fs__ is a virtual device defined by
-the VIRTIO specification which allows any VMM to perform filesystem sharing.
+__virtio-fs__, also known as __vhost-user-fs__ is a virtual device defined by the VIRTIO specification which allows any VMM to perform filesystem sharing.
 
 ## Pre-requisites
 
 ### The daemon
 
-This virtual device relies on the _vhost-user_ protocol, which assumes the
-backend (device emulation) is handled by a dedicated process running on the
-host. This daemon is called __virtiofsd__ and needs to be present on the host.
+This virtual device relies on the _vhost-user_ protocol, which assumes the backend (device emulation) is handled by a dedicated process running on the host. This daemon is called __virtiofsd__ and needs to be present on the host.
 
 _Build virtiofsd_
 ```bash
-git clone https://gitlab.com/virtio-fs/virtiofsd
-pushd virtiofsd
-cargo build --release
-sudo setcap cap_sys_admin+epi target/release/virtiofsd
+git clone --depth 1 "https://github.com/sboeuf/qemu.git" -b "virtio-fs" $VIRTIOFSD_DIR
+cd $VIRTIOFSD_DIR
+./configure --prefix=$PWD --target-list=x86_64-softmmu
+make virtiofsd -j `nproc`
+sudo setcap cap_sys_admin+epi "virtiofsd"
 ```
-
 _Create shared directory_
 ```bash
 mkdir /tmp/shared_dir
@@ -29,70 +25,64 @@ mkdir /tmp/shared_dir
 _Run virtiofsd_
 ```bash
 ./virtiofsd \
-    --log-level debug \
+    -d \
     --socket-path=/tmp/virtiofs \
-    --shared-dir=/tmp/shared_dir \
-    --cache=never \
-    --thread-pool-size=$N
+    -o source=/tmp/shared_dir \
+    -o cache=none
 ```
 
-The `cache=never` option is the default when using `virtiofsd` with
-Cloud Hypervisor. This prevents from using the host page cache, reducing the
-overall footprint on host memory. This increases the maximum density of virtual
-machines that can be launched on a single host.
+The `cache=none` option should be the default when using `virtiofsd` with the __cloud-hypervisor__ VMM. This prevents from using the guest page cache, which reduces the memory footprint of the guest. When running multiple virtual machines on the same host, this will let the host deal with page cache, which will increase the density of virtual machines which can be launched.
 
-The `cache=always` option will allow the host page cache to be used, which can
-result in better performance for the guest's workload at the cost of increasing
-the footprint on host memory.
+The `cache=always` option will allow for the guest page cache to be used, which will increase the memory footprint of the guest. This option should be used only for specific use cases where a single VM is going to be running on a host.
 
-The `thread-pool-size` option controls how many IO threads are spawned. For
-very fast storage like NVMe spawning enough worker threads is critical to
-getting an acceptable performance compared to native.
+### The kernel
 
-### Kernel support
+In order to leverage __virtio-fs__ support from within the guest, and because the code has not been merged in upstream Linux kernel yet, it is required to build a custom kernel embedding the patches.
 
-Modern Linux kernels (at least v5.10) have support for virtio-fs. Use of older
-kernels, with additional patches, are not supported.
+The following branch `virtio-fs-virtio-iommu` on the repository https://github.com/cloud-hypervisor/linux.git includes all the needed patches to support __virtio-fs__.
+
+Make sure to build a kernel out of this branch that can be then used to boot the VM.
 
 ## How to share directories with cloud-hypervisor
 
 ### Start the VM
+Once the daemon is running, the option `--fs` from __cloud-hypervisor__ needs to be used.
 
-Once the daemon is running, the option `--fs` from Cloud Hypervisor needs
-to be used.
+Direct kernel boot option is preferred since we need to provide the custom kernel including the __virtio-fs__ patches. We could boot from `hypervisor-fw` if we had previously edited the image to replace the kernel binary.
 
-Both direct kernel boot and EFI firmware can be used to boot a VM with
-virtio-fs, given that the cloud image contains a recent enough kernel.
+Because _vhost-user_ expects a dedicated process (__virtiofsd__ in this case) to be able to access the guest RAM to communicate through the _virtqueues_ with the driver running in the guest, `--memory` option needs to be slightly modified. It needs to specify a backing file for the memory so that an external process can access it.
 
-Correct functioning of `--fs` requires `--memory shared=on` to facilitate
-interprocess memory sharing.
-
-Assuming you have `focal-server-cloudimg-amd64.raw` and `vmlinux` on your
-system, here is the Cloud Hypervisor command you need to run:
+Assuming you have `focal-server-cloudimg-amd64.raw` and `custom-vmlinux.bin` on your system, here is the __cloud-hypervisor__ command you need to run:
 ```bash
 ./cloud-hypervisor \
-    --cpus boot=1 \
-    --memory size=1G,shared=on \
+    --cpus 4 \
+    --memory "size=512M,shared=on" \
     --disk path=focal-server-cloudimg-amd64.raw \
-    --kernel vmlinux \
-    --cmdline "console=hvc0 root=/dev/vda1 rw" \
+    --kernel custom-vmlinux.bin \
+    --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw" \
     --fs tag=myfs,socket=/tmp/virtiofs,num_queues=1,queue_size=512
 ```
 
-### Mount the shared directory
-
-The last step is to mount the shared directory inside the guest, using the
-`virtiofs` filesystem type.
+By default, DAX is enabled with a cache window of 8GiB. You can specify a custom size (let's say 4GiB for this example) for the cache by explicitly setting DAX and the cache size:
 
 ```bash
-mkdir mount_dir
-mount -t virtiofs myfs mount_dir/
+--fs tag=virtiofs,socket=/tmp/virtiofs,num_queues=1,queue_size=512,dax=on,cache_size=4G
+
 ```
 
-The `tag` needs to be consistent with what has been provided through the
-Cloud Hypervisor command line, which happens to be `myfs` in this example.
+In case you don't want to use a shared window of cache to pass the shared files content, this means you will have to explicitly disable DAX with `dax=off`. Note that in this case, the `cache_size` parameter will be ignored.
 
-## DAX feature
+```bash
+--fs tag=virtiofs,socket=/tmp/virtiofs,num_queues=1,queue_size=512,dax=off
 
-Given the DAX feature is not stable yet from a daemon standpoint, it is not
-available in Cloud Hypervisor.
+```
+
+### Mount the shared directory
+The last step is to mount the shared directory inside the guest, using the `virtiofs` filesystem type.
+```bash
+mkdir mount_dir
+mount -t virtiofs -o dax myfs mount_dir/
+```
+The `tag` needs to be consistent with what has been provided through the __cloud-hypervisor__ command line, which happens to be `myfs` in this example.
+
+The `-o dax` option must be removed in case the shared cache region is not enabled from the VMM.

docs/fuzzing.md

@@ -20,10 +20,10 @@ cargo install cargo-fuzz
 
 ## Running the fuzzers
 
-e.g. To run the `block` fuzzer using all available CPUs:
+e.g. To run the `qcow` fuzzer using all available CPUs:
 
 ```
-cargo fuzz run block -j `nproc`
+cargo fuzz run qcow -j `nproc`
 ```
 
 ## Adding a new fuzzer
@@ -32,4 +32,4 @@ cargo fuzz run block -j `nproc`
 cargo fuzz add <new_fuzzer>
 ```
 
-Inspiration for fuzzers can be found in [crosvm](https://chromium.googlesource.com/chromiumos/platform/crosvm/+/refs/heads/master/fuzz/)
+Inspiration for fuzzers can be found in [crosvm](https://chromium.googlesource.com/chromiumos/platform/crosvm/+/refs/heads/master/fuzz/)

docs/gdb.md

@@ -1,47 +0,0 @@
-# GDB Support
-
-This feature allows remote guest debugging using GDB. Note that this feature is only supported on x86_64/KVM.
-
-To enable debugging with GDB, build with the `guest_debug` feature enabled:
-
-```bash
-cargo build --features guest_debug
-```
-
-To use the `--gdb` option, specify the Unix Domain Socket with `--path` that Cloud Hypervisor will use to communicate with the host's GDB:
-
-```bash
-./cloud-hypervisor \
-    --kernel hypervisor-fw \
-    --disk path=bionic-server-cloudimg-amd64.raw \
-    --cpus boot=1 \
-    --memory size=1024M \
-    --net "tap=,mac=,ip=,mask=" \
-    --console off \
-    --serial tty \
-    --gdb path=/tmp/ch-gdb-sock
-```
-
-Cloud Hypervisor will listen for GDB on the host side before starting the guest.
-On the host side, connect to the GDB remote server as follows:
-
-```bash
-gdb -q
-(gdb) target remote /tmp/ch-gdb-sock
-Remote debugging using /tmp/ch-gdb-sock
-warning: No executable has been specified, and target does not support
-determining executable automatically. Try using the "file" command.
-0x000000000011217e in ?? ()
-```
-
-You can set up to four hardware breakpoints using the x86 debug register:
-
-```bash
-(gdb) hb *0x1121b7
-Hardware assisted breakpoint 1 at 0x1121b7
-(gdb) c
-Continuing.
-
-Breakpoint 1, 0x00000000001121b7 in ?? ()
-(gdb)
-```

docs/hotplug.md

@@ -1,6 +1,6 @@
 # Cloud Hypervisor Hot Plug
 
-Currently Cloud Hypervisor supports hot plugging of CPUs devices (x86 only), PCI devices and memory resizing.
+Currently Cloud Hypervisor only support hot plugging of CPU devices.
 
 ## Kernel support
 
@@ -9,7 +9,7 @@ or by using this kernel patch (available in 5.5-rc1 and later): https://git.kern
 
 ## CPU Hot Plug
 
-Extra vCPUs can be added and removed from a running `cloud-hypervisor` instance. This is controlled by two mechanisms:
+Extra vCPUs can be added and removed from a running Cloud Hypervisor instance. This is controlled by two mechanisms:
 
 1. Specifying a number of maximum potential vCPUs that is greater than the number of default (boot) vCPUs.
 2. Making a HTTP API request to the VMM to ask for the additional vCPUs to be added.
@@ -31,7 +31,7 @@ $ ./cloud-hypervisor/target/release/cloud-hypervisor \
 $ popd
 ```
 
-Notice the addition of `--api-socket=/tmp/ch-socket` and a `max` parameter on `--cpus boot=4,max=8`.
+Notice the addition of `--api-socket=/tmp/ch-socket` and a `max` parameter on `--cpus boot=4.max=8`.
 
 To ask the VMM to add additional vCPUs then use the resize API:
 
@@ -65,7 +65,7 @@ As per adding CPUs to the guest, after a reboot the VM will be running with the
 
 ### ACPI method
 
-Extra memory can be added from a running `cloud-hypervisor` instance. This is controlled by two mechanisms:
+Extra memory can be added from a running Cloud Hypervisor instance. This is controlled by two mechanisms:
 
 1. Allocating some of the guest physical address space for hotplug memory.
 2. Making a HTTP API request to the VMM to ask for a new amount of RAM to be assigned to the VM. In the case of expanding the memory for the VM the new memory will be hotplugged into the running VM, if reducing the size of the memory then change will take effect after the next reboot.
@@ -157,9 +157,7 @@ The same API can also be used to reduce the desired RAM for a VM. It is importan
 
 ## PCI Device Hot Plug
 
-Extra PCI devices can be added and removed from a running `cloud-hypervisor` instance. This is controlled by making a HTTP API request to the VMM to ask for the additional device to be added, or for the existing device to be removed.
-
-Note: On AArch64 platform, PCI device hotplug can only be achieved using ACPI. Please refer to the [documentation](arm64.md#uefi-booting) for more information.
+Extra PCI devices can be added and removed from a running Cloud Hypervisor instance. This is controlled by making a HTTP API request to the VMM to ask for the additional device to be added, or for the existing device to be removed.
 
 To use PCI device hotplug start the VM with the HTTP server.
 

docs/intel_sgx.md

@@ -1,7 +1,7 @@
 # Intel SGX
 
 Intel® Software Guard Extensions (Intel® SGX) is an Intel technology designed
-to increase the security of application code and data. Cloud Hypervisor supports
+to increase the security of application code and data. Cloud-Hypervisor supports
 SGX virtualization through KVM. Because SGX is built on hardware features that
 cannot be emulated in software, virtualizing SGX requires support in KVM and in
 the host kernel. The required Linux and KVM changes can be found in the
@@ -17,12 +17,12 @@ For more information about SGX, please refer to the [SGX Homepage](https://softw
 For more information about SGX SDK and how to test SGX, please refer to the
 following [instructions](https://github.com/intel/linux-sgx).
 
-## Cloud Hypervisor support
+## Cloud-Hypervisor support
 
-Assuming the host exposes `/dev/sgx_vepc`, we can pass SGX enclaves through
+Assuming the host exposes `/dev/sgx_virt_epc`, we can pass SGX enclaves through
 the guest.
 
-In order to use SGX enclaves within a Cloud Hypervisor VM, we must define one
+In order to use SGX enclaves within a Cloud-Hypervisor VM, we must define one
 or several Enclave Page Cache (EPC) sections. Here is an example of a VM being
 created with 2 EPC sections, the first one being 64MiB with pre-allocated
 memory, the second one being 32MiB with no pre-allocated memory.
@@ -32,9 +32,9 @@ memory, the second one being 32MiB with no pre-allocated memory.
     --cpus boot=1 \
     --memory size=1G \
     --disk path=focal-server-cloudimg-amd64.raw \
-    --kernel vmlinux \
+    --kernel bzImage \
     --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw" \
-    --sgx-epc id=epc0,size=64M,prefault=on id=epc1,size=32M,prefault=off
+    --sgx-epc size=64M,prefault=on size=32M,prefault=off
 ```
 
 Once booted, and assuming your guest kernel contains the patches from the
@@ -43,7 +43,7 @@ have been correctly created under `/dev/sgx`:
 
 ```bash
 ls /dev/sgx*
-/dev/sgx_enclave  /dev/sgx_provision  /dev/sgx_vepc
+/dev/sgx_enclave  /dev/sgx_provision  /dev/sgx_virt_epc
 ```
 
 From this point, it is possible to run any SGX application from the guest, as
@@ -51,5 +51,5 @@ it will access `/dev/sgx_enclave` device to create dedicated SGX enclaves.
 
 Note: There is only one contiguous SGX EPC region, which contains all SGX EPC
 sections. This region is exposed through ACPI and marked as reserved through
-the e820 table. It is treated as yet another device, which means it should
+the e820 table. It is treated yet as another device, which means it should
 appear at the end of the guest address space.

docs/intel_tdx.md

@@ -1,123 +0,0 @@
-# Intel TDX
-
-Intel® Trust Domain Extensions (Intel® TDX) is an Intel technology designed to
-isolate virtual machines from the VMM, hypervisor and any other software on the
-host platform.
-
-For more information about TDX technical aspects, design and specification
-please refer to the
-[TDX Homepage](https://www.intel.com/content/www/us/en/developer/articles/technical/intel-trust-domain-extensions.html).
-
-The required Linux changes for the host side can be found in the
-[KVM TDX tree](https://github.com/intel/tdx/tree/kvm) while the changes for
-the guest side can be found in the [Guest TDX tree](https://github.com/intel/tdx/tree/guest).
-
-The TDVF firmware can be found in the
-[EDK2 staging project](https://github.com/tianocore/edk2-staging/tree/TDVF).
-
-The TDShim firmware can be found in the
-[Confidential Containers project](https://github.com/confidential-containers/td-shim).
-
-## Cloud Hypervisor support
-
-First, you must be running on a machine with TDX enabled in hardware, and
-with the host OS compiled from the [KVM TDX tree](https://github.com/intel/tdx/tree/kvm).
-
-Cloud Hypervisor can run TDX VM (Trust Domain) by loading a TD firmware,
-which will then load the guest kernel from the image. The image must be custom
-as it must include a kernel built from the [Guest TDX tree](https://github.com/intel/tdx/tree/guest).
-
-### TDVF
-
-The firmware can be built as follows:
-
-```bash
-git clone https://github.com/tianocore/edk2-staging.git
-cd edk2-staging
-git checkout origin/TDVF
-git submodule update --init --recursive
-make -C BaseTools
-source ./edksetup.sh
-build -p OvmfPkg/OvmfCh.dsc -a X64 -t GCC5 -b RELEASE
-```
-
-If debug logs are needed, here is the alternative command:
-
-```bash
-build -p OvmfPkg/OvmfCh.dsc -a X64 -t GCC5 -D DEBUG_ON_SERIAL_PORT=TRUE
-```
-
-On the Cloud Hypervisor side, all you need is to build the project with the
-`tdx` feature enabled:
-
-```bash
-cargo build --features tdx
-```
-
-And run a TDX VM by providing the firmware previously built, along with the
-guest image containing the TDX enlightened kernel. The latest image
-`td-guest-rhel8.5.raw` contains `console=hvc0` on the kernel boot parameters,
-meaning it will be printing guest kernel logs to the `virtio-console` device.
-
-```bash
-./cloud-hypervisor \
-    --platform tdx=on
-    --firmware edk2-staging/Build/OvmfCh/RELEASE_GCC5/FV/OVMF.fd \
-    --cpus boot=1 \
-    --memory size=1G \
-    --disk path=tdx_guest_img
-```
-
-And here is the alternative command when looking for debug logs from the
-firmware:
-
-```bash
-./cloud-hypervisor \
-    --platform tdx=on
-    --firmware edk2-staging/Build/OvmfCh/DEBUG_GCC5/FV/OVMF.fd \
-    --cpus boot=1 \
-    --memory size=1G \
-    --disk path=tdx_guest_img \
-    --serial file=/tmp/ch_serial \
-    --console tty
-```
-
-### TDShim
-
-This is a lightweight version of the TDVF, written in Rust and designed for
-direct kernel boot, which is useful for containers use cases.
-
-You can find the instructions for building the firmware directly from the
-project [documentation](https://github.com/confidential-containers/td-shim/tree/staging#how-to-build).
-
-And run a TDX VM by providing the firmware previously built, along with a guest
-kernel built from the [Guest TDX tree](https://github.com/intel/tdx/tree/guest).
-The appropriate kernel boot options must be provided through the `--cmdline`
-option as well.
-
-```bash
-./cloud-hypervisor \
-    --platform tdx=on
-    --firmware tdshim \
-    --kernel bzImage \
-    --cmdline "root=/dev/vda3 console=hvc0 rw"
-    --cpus boot=1 \
-    --memory size=1G \
-    --disk path=tdx_guest_img
-```
-
-### Guest kernel limitations
-
-#### Serial ports disabled
-
-The latest guest kernel that can be found in the latest image
-`td-guest-rhel8.5.raw` disabled the support for serial ports. This means adding
-`console=ttyS0` will have no effect and will not print any log from the guest.
-
-#### PCI hotplug through ACPI
-
-Unless you run the guest kernel with the parameter `tdx_disable_filter`, ACPI
-devices responsible for handling PCI hotplug (PCI hotplug controller, PCI
-Express Bus and Generic Event Device) will not be allowed, therefore the
-corresponding drivers will not be loaded and the PCI hotplug feature will not
-be supported.

docs/io_throttling.md

@@ -1,16 +1,13 @@
 # I/O Throttling
 
-Cloud Hypervisor now supports I/O throttling on virtio-block and virtio-net
+Cloud Hypervisor now supports I/O throttling on virtio-block
 devices. This support is based on the [`rate-limiter` module](https://github.com/firecracker-microvm/firecracker/tree/master/src/rate_limiter)
 from Firecracker. This document explains the user interface of this
 feature, and highlights some internal implementations that can help users
 better understand the expected behavior of I/O throttling in practice.
 
 Cloud Hypervisor allows to limit both the I/O bandwidth (e.g. bytes/s)
-and I/O operations (ops/s) independently. For virtio-net devices, while
-sharing the same "rate limit" from user inputs (on both bandwidth and
-operations), the RX and TX queues are throttled independently.
-To limit the I/O bandwidth, Cloud Hypervisor
+and I/O operations (ops/s) independently. To limit the I/O bandwidth, it
 provides three user options, i.e., `bw_size` (bytes), `bw_one_time_burst`
 (bytes), and `bw_refill_time` (ms). Both `bw_size` and `bw_refill_time`
 are required, while `bw_one_time_burst` is optional.
@@ -24,16 +21,16 @@ bucket is unbounded in speed which allows for bursts bound in size by
 the amount of tokens available. Once the token bucket is empty,
 consumption speed is bound by the "refill-rate". Similarly, Cloud
 Hypervisor provides another three options for limiting I/O operations,
-i.e., `ops_size` (I/O operations), `ops_one_time_burst` (I/O operations),
-and `ops_refill_time` (ms).
+i.e., `ops_size` (I/O operations), `bw_one_time_burst` (I/O operations),
+and `bw_refill_time` (ms).
 
 One caveat in the I/O throttling is that every-time the bucket gets
 empty, it will stop I/O operations for a fixed amount of time
 (`cool_down_time`). The `cool_down_time` now is fixed at `100 ms`, it
 can have big implications to the actual rate limit (which can be a lot
 different the expected "refill-rate" derived from user inputs). For
-example, to have a 1000 IOPS limit on a virtio-blk device, users should
-be able to provide either of the following two options:
+example, to have a 1000 IOPS limit, users should be able to provide
+either of the following two options:
 `ops_size=1000,ops_refill_time=1000` or
 `ops_size=10,ops_refill_time=10`. However, the actual IOPS limits are
 likely to be ~1000 IOPS and ~100 IOPS respectively. The reason is the

docs/iommu.md

@@ -89,7 +89,7 @@ virtual IOMMU:
     --cpus boot=1 \
     --memory size=512M \
     --disk path=focal-server-cloudimg-amd64.raw,iommu=on \
-    --kernel custom-vmlinux \
+    --kernel custom-bzImage \
     --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw" \
 ```
 
@@ -121,29 +121,6 @@ lspci
 00:04.0 Unassigned class [ffff]: Red Hat, Inc. Virtio RNG
 ```
 
-### Work with FDT on AArch64
-
-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
-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
-devices will be added into a IOMMU group.
-
-As a result, the directory content of `/sys/kernel/iommu_groups` would be:
-
-```bash
-ls /sys/kernel/iommu_groups/0/devices/
-0000:00:02.0
-ls /sys/kernel/iommu_groups/1/devices/
-0000:00:03.0
-ls /sys/kernel/iommu_groups/2/devices/
-0000:00:04.0
-```
-
 ## Faster mappings
 
 By default, the guest memory is mapped with 4k pages and no huge pages, which
@@ -189,7 +166,7 @@ be consumed.
     --cpus boot=1 \
     --memory size=8G,hugepages=on \
     --disk path=focal-server-cloudimg-amd64.raw \
-    --kernel custom-vmlinux \
+    --kernel custom-bzImage \
     --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw hugepagesz=2M hugepages=2048" \
     --net tap=,mac=,iommu=on
 ```
@@ -206,7 +183,7 @@ passing through is `0000:00:01.0`.
     --cpus boot=1 \
     --memory size=8G,hugepages=on \
     --disk path=focal-server-cloudimg-amd64.raw \
-    --kernel custom-vmlinux \
+    --kernel custom-bzImage \
     --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw kvm-intel.nested=1 vfio_iommu_type1.allow_unsafe_interrupts rw hugepagesz=2M hugepages=2048" \
     --device path=/sys/bus/pci/devices/0000:00:01.0,iommu=on
 ```
@@ -217,7 +194,6 @@ guest, and bind it to VFIO (it should appear as `0000:00:04.0`).
 ```bash
 echo 0000:00:04.0 > /sys/bus/pci/devices/0000\:00\:04.0/driver/unbind
 echo 8086 1502 > /sys/bus/pci/drivers/vfio-pci/new_id
-echo 0000:00:04.0 > /sys/bus/pci/drivers/vfio-pci/bind
 ```
 
 Last thing is to start the L2 guest with the huge pages memory backend.
@@ -227,42 +203,7 @@ Last thing is to start the L2 guest with the huge pages memory backend.
     --cpus boot=1 \
     --memory size=4G,hugepages=on \
     --disk path=focal-server-cloudimg-amd64.raw \
-    --kernel custom-vmlinux \
+    --kernel custom-bzImage \
     --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw" \
     --device path=/sys/bus/pci/devices/0000:00:04.0
 ```
-
-### Dedicated IOMMU PCI segments
-
-To facilitate hotplug of devices that require being behind an IOMMU it is
-possible to mark entire PCI segments as behind the IOMMU.
-
-This is accomplished through `--platform
-num_pci_segments=<number_of_segments>,iommu_segments=<range of segments>` or
-via the equivalents in `PlatformConfig` for the API.
-
-e.g.
-
-```bash
-./cloud-hypervisor \
-    --api-socket=/tmp/api \
-    --cpus boot=1 \
-    --memory size=4G,hugepages=on \
-    --disk path=focal-server-cloudimg-amd64.raw \
-    --kernel custom-vmlinux \
-    --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw" \
-    --platform num_pci_segments=2,iommu_segments=1
-```
-
-This adds a second PCI segment to the platform behind the IOMMU. A VFIO device
-requiring the IOMMU then may be hotplugged:
-
-e.g.
-
-```bash
-./ch-remote --api-socket=/tmp/api add-device path=/sys/bus/pci/devices/0000:00:04.0,iommu=on,pci_segment=1
-```
-
-Devices that cannot be placed behind an IOMMU (e.g. lacking an `iommu=` option)
-cannot be placed on the IOMMU segments.
-

docs/live_migration.md

@@ -1,139 +0,0 @@
-# Live Migration
-
-This document gives two examples of how to use the live migration
-support in Cloud Hypervisor:
-
-1. local migration - migrating between two VMs running on the same
-   machine;
-1. nested-vm migration - migrating between two nested VMs whose host VMs
-   are running on the same machine.
-
-## Local Migration (Suitable for Live Upgrade of VMM)
-Launch the source VM (on the host machine):
-```bash
-$ target/release/cloud-hypervisor
-    --kernel ~/workloads/vmlinux \
-    --disk path=~/workloads/focal.raw \
-    --cpus boot=1 --memory size=1G,shared=on \
-    --cmdline "root=/dev/vda1 console=ttyS0"  \
-    --serial tty --console off --api-socket=/tmp/api1
-```
-
-Launch the destination VM from the same directory (on the host machine):
-```bash
-$ target/release/cloud-hypervisor --api-socket=/tmp/api2
-```
-
-Get ready for receiving migration for the destination VM (on the host machine):
-```bash
-$ target/release/ch-remote --api-socket=/tmp/api2 receive-migration unix:/tmp/sock
-```
-
-Start to send migration for the source VM (on the host machine):
-```bash
-$ target/release/ch-remote --api-socket=/tmp/api1 send-migration --local unix:/tmp/sock
-```
-
-When the above commands completed, the source VM should be successfully
-migrated to the destination VM. Now the destination VM is running while
-the source VM is terminated gracefully.
-
-## Nested-VM Migration
-
-Launch VM 1 (on the host machine) with an extra virtio-blk device for
-exposing a guest image for the nested source VM:
-> Note: the example below also attached an additional virtio-blk device
-> with a dummy image for testing purpose (which is optional).
-```bash
-$ head -c 1M < /dev/urandom > tmp.img # create a dummy image for testing
-$ sudo /target/release/cloud-hypervisor \
-        --serial tty --console off \
-        --cpus boot=1 --memory size=512M \
-        --kernel vmlinux \
-        --cmdline "root=/dev/vda1 console=ttyS0"  \
-        --disk path=focal-1.raw path=focal-nested.raw path=tmp.img\
-        --net ip=192.168.101.1
-```
-
-Launch VM 2 (on the host machine) with an extra virtio-blk device for
-exposing the same guest image for the nested destination VM:
-```bash
-$ sudo /target/release/cloud-hypervisor \
-        --serial tty --console off \
-        --cpus boot=1 --memory size=512M \
-        --kernel vmlinux \
-        --cmdline "root=/dev/vda1 console=ttyS0"  \
-        --disk path=focal-2.raw path=focal-nested.raw path=tmp.img\
-        --net ip=192.168.102.1
-```
-
-Launch the nested source VM (inside the guest OS of the VM 1) :
-```bash
-vm-1:~$ sudo ./cloud-hypervisor \
-        --serial tty --console off \
-        --memory size=128M \
-        --kernel vmlinux \
-        --cmdline "console=ttyS0 root=/dev/vda1" \
-        --disk path=/dev/vdb path=/dev/vdc \
-        --api-socket=/tmp/api1 \
-        --net ip=192.168.100.1
-vm-1:~$ # setup the guest network if needed
-vm-1:~$ sudo ip addr add 192.168.101.2/24 dev ens4
-vm-1:~$ sudo ip link set up dev ens4
-vm-1:~$ sudo ip r add default via 192.168.101.1
-```
-Optional: Run the guest workload below (on the guest OS of the nested source VM),
-which performs intensive virtio-blk operations. Now the console of the nested
-source VM should repeatedly print `"equal"`, and our goal is migrating
-this VM and the running workload without interruption.
-```bash
-#/bin/bash
-
-# On the guest OS of the nested source VM
-
-input="/dev/vdb"
-result=$(md5sum $input)
-tmp=$(md5sum $input)
-
-while  [[ "$result" == "$tmp" ]]
-do
-    echo "equal"
-    tmp=$(md5sum $input)
-done
-
-echo "not equal"
-echo "result = $result"
-echo "tmp = $tmp"
-```
-
-Launch the nested destination VM (inside the guest OS of the VM 2):
-```bash
-vm-2:~$ sudo ./cloud-hypervisor --api-socket=/tmp/api2
-vm-2:~$ # setup the guest network with the following commands if needed
-vm-2:~$ sudo ip addr add 192.168.102.2/24 dev ens4
-vm-2:~$ sudo ip link set up dev ens4
-vm-2:~$ sudo ip r add default via 192.168.102.1
-vm-2:~$ ping 192.168.101.2 # This should succeed
-```
-> Note: If the above ping failed, please check the iptables rule on the
-> host machine, e.g. whether the policy for the `FORWARD` chain is set
-> to `DROP` (which is the default setting configured by Docker).
-
-Get ready for receiving migration for the nested destination VM (inside
-the guest OS of the VM 2):
-```bash
-vm-2:~$ sudo ./ch-remote --api-socket=/tmp/api2 receive-migration unix:/tmp/sock2
-vm-2:~$ sudo socat TCP-LISTEN:6000,reuseaddr UNIX-CLIENT:/tmp/sock2
-```
-
-Start to send migration for the nested source VM (inside the guest OS of
-the VM 1):
-```bash
-vm-1:~$ sudo socat UNIX-LISTEN:/tmp/sock1,reuseaddr TCP:192.168.102.2:6000
-vm-1:~$ sudo ./ch-remote --api-socket=/tmp/api1 send-migration unix:/tmp/sock1
-```
-
-When the above commands completed, the source VM should be successfully
-migrated to the destination VM without interrupting our testing guest
-workload. Now the destination VM is running the testing guest workload
-while the source VM is terminated gracefully.

docs/macvtap-bridge.md

@@ -1,6 +1,6 @@
 # Using MACVTAP to Bridge onto Host Network
 
-Cloud Hypervisor supports using a MACVTAP device which is derived from a MACVLAN. Full details of configuring MACVLAN or MACVTAP is out of scope of this document. However the example below indicates how to bridge the guest directly onto the network the host is on. Due to the lack of hairpin mode it not usually possible to reach the guest directly from the host.
+Cloud Hypervisor supports using a MACVTAP device which is derived from a MACVLAN. Full details of configuring MACVLAN or MACVTAP is out of scope of this document. However the example below indicates how to bridge the guest directly onto the the network the host is on. Due to the lack of hairpin mode it not usually possible to reach the guest directly from the host.
 
 ```bash
 # The MAC address must be attached to the macvtap and be used inside the guest

docs/memory.md

@@ -1,32 +1,30 @@
 # Memory
 
-Cloud Hypervisor has many ways to expose memory to the guest VM. This document
-aims to explain what Cloud Hypervisor is capable of and how it can be used to
+Cloud-Hypervisor has many ways to expose memory to the guest VM. This document
+aims to explain what Cloud-Hypervisor is capable of and how it can be used to
 meet the needs of very different use cases.
 
 ## Basic Parameters
 
 `MemoryConfig` or what is known as `--memory` from the CLI perspective is the
-easiest way to get started with Cloud Hypervisor.
+easiest way to get started with Cloud-Hypervisor.
 
 ```rust
 struct MemoryConfig {
     size: u64,
     mergeable: bool,
-    hotplug_method: HotplugMethod,
-    hotplug_size: Option<u64>,
-    hotplugged_size: Option<u64>,
     shared: bool,
     hugepages: bool,
     hugepage_size: Option<u64>,
-    prefault: bool,
-    thp: bool
+    hotplug_method: HotplugMethod,
+    hotplug_size: Option<u64>,
+    hotplugged_size: Option<u64>,
     zones: Option<Vec<MemoryZoneConfig>>,
 }
 ```
 
 ```
---memory <memory>	Memory parameters "size=<guest_memory_size>,mergeable=on|off,shared=on|off,hugepages=on|off,hugepage_size=<hugepage_size>,hotplug_method=acpi|virtio-mem,hotplug_size=<hotpluggable_memory_size>,hotplugged_size=<hotplugged_memory_size>,prefault=on|off,thp=on|off" [default: size=512M,thp=on]
+--memory <memory>	Memory parameters "size=<guest_memory_size>,mergeable=on|off,shared=on|off,hugepages=on|off,hotplug_method=acpi|virtio-mem,hotplug_size=<hotpluggable_memory_size>,hotplugged_size=<hotplugged_memory_size>"
 ```
 
 ### `size`
@@ -61,6 +59,44 @@ _Example_
 --memory size=1G,mergeable=on
 ```
 
+### `shared`
+
+Specifies if the memory must be `mmap(2)` with `MAP_SHARED` flag.
+
+By sharing a memory mapping, one can share the guest RAM with other processes
+running on the host. One can use this option when running vhost-user devices
+as part of the VM device model, as they will be driven by standalone daemons
+needing access to the guest RAM content.
+
+By default this option is turned off, which results in performing `mmap(2)`
+with `MAP_PRIVATE` flag.
+
+_Example_
+
+```
+--memory size=1G,shared=on
+```
+
+### `hugepages` and `hugepage_size`
+
+Specifies if the memory must be created and `mmap(2)` with `MAP_HUGETLB` and size
+flags. This performs a memory mapping relying on the specified huge page size. If no huge page size is supplied the system's default huge page size is used.
+
+By using hugepages, one can improve the overall performance of the VM, assuming
+the guest will allocate hugepages as well. Another interesting use case is VFIO
+as it speeds up the VM's boot time since the amount of IOMMU mappings are
+reduced.
+
+The user is responsible for ensuring there are sufficient huge pages of the specified size for the VMM to use. Failure to do so may result in strange VMM behaviour.
+
+By default this option is turned off.
+
+_Example_
+
+```
+--memory size=1G,hugepages=on,hugepage_size=2M
+```
+
 ### `hotplug_method`
 
 Selects the way of adding and/or removing memory to/from a booted VM.
@@ -106,97 +142,6 @@ _Example_
 --memory size=1G,hotplug_method=virtio-mem,hotplug_size=1G,hotplugged_size=512M
 ```
 
-### `shared`
-
-Specifies if the memory must be `mmap(2)` with `MAP_SHARED` flag.
-
-By sharing a memory mapping, one can share the guest RAM with other processes
-running on the host. One can use this option when running vhost-user devices
-as part of the VM device model, as they will be driven by standalone daemons
-needing access to the guest RAM content.
-
-By default this option is turned off, which results in performing `mmap(2)`
-with `MAP_PRIVATE` flag.
-
-If `hugepages=on` then the value of this field is ignored as huge pages always
-requires `MAP_SHARED`.
-
-_Example_
-
-```
---memory size=1G,shared=on
-```
-
-### `hugepages` and `hugepage_size`
-
-Specifies if the memory must be created and `mmap(2)` with `MAP_HUGETLB` and size
-flags. This performs a memory mapping relying on the specified huge page size.
-If no huge page size is supplied the system's default huge page size is used.
-
-By using hugepages, one can improve the overall performance of the VM, assuming
-the guest will allocate hugepages as well. Another interesting use case is VFIO
-as it speeds up the VM's boot time since the amount of IOMMU mappings are
-reduced.
-
-The user is responsible for ensuring there are sufficient huge pages of the
-specified size for the VMM to use. Failure to do so may result in strange VMM
-behaviour, e.g. error with `ReadKernelImage` is common. If there is a strange
-error with `hugepages` enabled, just disable it or check whether there are enough
-huge pages.
-
-If `hugepages=on` then the value of `shared` is ignored as huge pages always
-requires `MAP_SHARED`.
-
-By default this option is turned off.
-
-_Example_
-
-```
---memory size=1G,hugepages=on,hugepage_size=2M
-```
-
-### `prefault`
-
-Specifies if the memory must be `mmap(2)` with `MAP_POPULATE` flag.
-
-By triggering prefault, one can allocate all required physical memory and create
-its page tables while calling `mmap`. With physical memory allocated, the number
-of page faults will decrease during running, and performance will also improve.
-
-Note that boot of VM will be slower with `prefault` enabled because of allocating
-physical memory and creating page tables in advance, and physical memory of the
-specified size will be consumed quickly.
-
-This option only takes effect at boot of VM. There is also a `prefault` option in
-restore and its choice will overwrite `prefault` in memory.
-
-By default this option is turned off.
-
-_Example_
-
-```
---memory size=1G,prefault=on
-```
-
-### `thp`
-
-Specifies if private anonymous memory for the guest (i.e. `shared=off` and no
-backing file) should be labelled `MADV_HUGEPAGE` with `madvise(2)` indicating
-to the kernel that this memory may be backed with huge pages transparently.
-
-The use of transparent huge pages can improve the performance of the guest as
-there will fewer virtualisation related page faults. Unlike using
-`hugepages=on` a specific number of huge pages do not need to be allocated by
-the kernel.
-
-By default this option is turned on.
-
-_Example_
-
-```
---memory size=1G,thp=on
-```
-
 ## Advanced Parameters
 
 `MemoryZoneConfig` or what is known as `--memory-zone` from the CLI perspective
@@ -210,16 +155,14 @@ struct MemoryZoneConfig {
     file: Option<PathBuf>,
     shared: bool,
     hugepages: bool,
-    hugepage_size: Option<u64>,
     host_numa_node: Option<u32>,
     hotplug_size: Option<u64>,
     hotplugged_size: Option<u64>,
-    prefault: bool,
 }
 ```
 
 ```
---memory-zone <memory-zone>	User defined memory zone parameters "size=<guest_memory_region_size>,file=<backing_file>,shared=on|off,hugepages=on|off,hugepage_size=<hugepage_size>,host_numa_node=<node_id>,id=<zone_identifier>,hotplug_size=<hotpluggable_memory_size>,hotplugged_size=<hotplugged_memory_size>,prefault=on|off"
+--memory-zone <memory-zone>	User defined memory zone parameters "size=<guest_memory_region_size>,file=<backing_file>,shared=on|off,hugepages=on|off,host_numa_node=<node_id>,id=<zone_identifier>,hotplug_size=<hotpluggable_memory_size>,hotplugged_size=<hotplugged_memory_size>"
 ```
 
 This parameter expects one or more occurences, allowing for a list of memory
@@ -297,9 +240,6 @@ other processes running on the host. One can use this option when running
 vhost-user devices as part of the VM device model, as they will be driven
 by standalone daemons needing access to the guest RAM content.
 
-If `hugepages=on` then the value of this field is ignored as huge pages always
-requires `MAP_SHARED`.
-
 By default this option is turned off, which result in performing `mmap(2)`
 with `MAP_PRIVATE` flag.
 
@@ -310,33 +250,24 @@ _Example_
 --memory-zone id=mem0,size=1G,shared=on
 ```
 
-### `hugepages` and `hugepage_size`
+### `hugepages`
 
-Specifies if the memory must be created and `mmap(2)` with `MAP_HUGETLB` and size
-flags. This performs a memory mapping relying on the specified huge page size.
-If no huge page size is supplied the system's default huge page size is used.
+Specifies if the memory zone must be `mmap(2)` with `MAP_HUGETLB` and
+`MAP_HUGE_2MB` flags. This performs a memory zone mapping relying on 2MiB
+pages instead of the default 4kiB pages.
 
 By using hugepages, one can improve the overall performance of the VM, assuming
 the guest will allocate hugepages as well. Another interesting use case is VFIO
 as it speeds up the VM's boot time since the amount of IOMMU mappings are
 reduced.
 
-The user is responsible for ensuring there are sufficient huge pages of the
-specified size for the VMM to use. Failure to do so may result in strange VMM
-behaviour, e.g. error with `ReadKernelImage` is common. If there is a strange
-error with `hugepages` enabled, just disable it or check whether there are enough
-huge pages.
-
-If `hugepages=on` then the value of `shared` is ignored as huge pages always
-requires `MAP_SHARED`.
-
 By default this option is turned off.
 
 _Example_
 
 ```
 --memory size=0
---memory-zone id=mem0,size=1G,hugepages=on,hugepage_size=2M
+--memory-zone id=mem0,size=1G,hugepages=on
 ```
 
 ### `host_numa_node`
@@ -403,30 +334,6 @@ _Example_
 --memory-zone id=mem0,size=1G,hotplug_size=1G,hotplugged_size=512M
 ```
 
-### `prefault`
-
-Specifies if the memory must be `mmap(2)` with `MAP_POPULATE` flag.
-
-By triggering prefault, one can allocate all required physical memory and create
-its page tables while calling `mmap`. With physical memory allocated, the number
-of page faults will decrease during running, and performance will also improve.
-
-Note that boot of VM will be slower with `prefault` enabled because of allocating
-physical memory and creating page tables in advance, and physical memory of the
-specified size will be consumed quickly.
-
-This option only takes effect at boot of VM. There is also a `prefault` option in
-restore and its choice will overwrite `prefault` in memory.
-
-By default this option is turned off.
-
-_Example_
-
-```
---memory size=0
---memory-zone id=mem0,size=1G,prefault=on
-```
-
 ## NUMA settings
 
 `NumaConfig` or what is known as `--numa` from the CLI perspective has been
@@ -436,16 +343,15 @@ it allows for specifying the distance between each NUMA node.
 
 ```rust
 struct NumaConfig {
-    guest_numa_id: u32,
+    id: u32,
     cpus: Option<Vec<u8>>,
     distances: Option<Vec<NumaDistance>>,
     memory_zones: Option<Vec<String>>,
-    sgx_epc_sections: Option<Vec<String>>,
 }
 ```
 
 ```
---numa <numa>	Settings related to a given NUMA node "guest_numa_id=<node_id>,cpus=<cpus_id>,distances=<list_of_distances_to_destination_nodes>,memory_zones=<list_of_memory_zones>,sgx_epc_sections=<list_of_sgx_epc_sections>"
+--numa <numa>	Settings related to a given NUMA node "id=<node_id>,cpus=<cpus_id>,distances=<list_of_distances_to_destination_nodes>,memory_zones=<list_of_memory_zones>"
 ```
 
 ### `guest_numa_id`
@@ -478,20 +384,18 @@ integer of 8 bits.
 
 For instance, if one needs to attach all CPUs from 0 to 4 to a specific node,
 the syntax using `-` will help define a contiguous range with `cpus=0-4`. The
-same example could also be described with `cpus=[0,1,2,3,4]`.
+same example could also be described with `cpus=0:1:2:3:4`.
 
-A combination of both `-` and `,` separators is useful when one might need to
+A combination of both `-` and `:` separators is useful when one might need to
 describe a list containing all CPUs from 0 to 99 and the CPU 255, as it could
-simply be described with `cpus=[0-99,255]`.
-
-As soon as one tries to describe a list of values, `[` and `]` must be used to
-demarcate the list.
+simply be described with `cpus=0-99:255`.
 
 _Example_
 
 ```
 --cpus boot=8
---numa guest_numa_id=0,cpus=[1-3,7] guest_numa_id=1,cpus=[0,4-6]
+--numa guest_numa_id=0,cpus=1-3:7
+--numa guest_numa_id=1,cpus=0:4-6
 ```
 
 ### `distances`
@@ -508,10 +412,7 @@ node. The second value is an unsigned integer of 8 bits as it represents the
 distance between the current NUMA node and the destination NUMA node. The two
 values are separated by `@` (`value1@value2`), meaning the destination NUMA
 node `value1` is located at a distance of `value2`. Each tuple is separated
-from the others with `,` separator.
-
-As soon as one tries to describe a list of values, `[` and `]` must be used to
-demarcate the list.
+from the others with `:` separator.
 
 For instance, if one wants to define 3 NUMA nodes, with each node located at
 different distances, it can be described with the following example.
@@ -519,7 +420,9 @@ different distances, it can be described with the following example.
 _Example_
 
 ```
---numa guest_numa_id=0,distances=[1@15,2@25] guest_numa_id=1,distances=[0@15,2@20] guest_numa_id=2,distances=[0@25,1@20]
+--numa guest_numa_id=0,distances=1@15:2@25
+--numa guest_numa_id=1,distances=0@15:2@20
+--numa guest_numa_id=2,distances=0@25:1@20
 ```
 
 ### `memory_zones`
@@ -536,46 +439,15 @@ workload run more efficiently.
 
 Multiple values can be provided to define the list. Each value is a string
 referring to an existing memory zone identifier. Values are separated from
-each other with the `,` separator.
-
-As soon as one tries to describe a list of values, `[` and `]` must be used to
-demarcate the list.
-
-Note that a memory zone must belong to a single NUMA node. The following
-configuration is incorrect, therefore not allowed:
-`--numa guest_numa_id=0,memory_zones=mem0 guest_numa_id=1,memory_zones=mem0`
+each other with the `:` separator.
 
 _Example_
 
 ```
 --memory size=0
---memory-zone id=mem0,size=1G id=mem1,size=1G id=mem2,size=1G
---numa guest_numa_id=0,memory_zones=[mem0,mem2] guest_numa_id=1,memory_zones=mem1
+--memory-zone id=mem0,size=1G
+--memory-zone id=mem1,size=1G
+--memory-zone id=mem2,size=1G
+--numa guest_numa_id=0,memory_zones=mem0:mem2
+--numa guest_numa_id=1,memory_zones=mem1
 ```
-
-### `sgx_epc_sections`
-
-List of SGX EPC sections attached to the guest NUMA node identified by the
-`guest_numa_id` option. This allows for describing a list of SGX EPC sections
-which must be seen by the guest as belonging to the NUMA node `guest_numa_id`.
-
-Multiple values can be provided to define the list. Each value is a string
-referring to an existing SGX EPC section identifier. Values are separated from
-each other with the `,` separator.
-
-As soon as one tries to describe a list of values, `[` and `]` must be used to
-demarcate the list.
-
-_Example_
-
-```
---sgx-epc id=epc0,size=32M id=epc1,size=64M id=epc2,size=32M
---numa guest_numa_id=0,sgx_epc_sections=epc1 guest_numa_id=1,sgx_epc_sections=[epc0,epc2]
-```
-
-### PCI bus
-
-Cloud Hypervisor supports only one PCI bus, which is why it has been tied to
-the NUMA node 0 by default. It is the user responsibility to organize the NUMA
-nodes correctly so that vCPUs and guest RAM which should be located on the same
-NUMA node as the PCI bus end up on the NUMA node 0.

docs/networking.md

@@ -0,0 +1,206 @@
+# How to use networking
+
+cloud-hypervisor can emulate one or more virtual network interfaces, represented at the hypervisor host by [tap devices](https://www.kernel.org/doc/Documentation/networking/tuntap.txt). This guide briefly describes, in a manual and distribution neutral way, how to setup and use networking with cloud-hypervisor.
+
+## Multiple queue support for net devices ##
+
+While multiple vcpus defined for guest, to gain the benefit of vcpu scalable to improve performance, it suggests to define multiple queue pairs for net devices, one Tx/Rx queue pair per one vcpu, that means the number of queue pairs at least is equal to the vcpu count. In that case, after virtnet driver set cpu affinity for virtqueues in guest kernel, vcpus could handle interrupt from different virtqueue pairs in parallel.
+
+It will gain better performance for guest that has multiple queues defined for net devices while it has multiple net sessions running in userspace.
+
+To enable multiple queue support in cloud-hypervisor, multiple queue pairs will be defined, while multiple tap fds will be opened for the same tap device, it will also have multiple threads started, each thread will monitor and handle the events from each virtqueue pairs and the associated tap fd.
+
+Note:
+
+- Currently, it does not support to use ethtool to change the combined queue numbers in guest.
+- Multiple queue is enabled for vhost-user-net backend in cloud-hypervisor, however, multiple thread is not added to handle mq, thus, the performance for vhost-user-net backend is not supposed to be improved. The multiple thread will be added for backend later.
+- Performance test for vhost-user-net will be covered once vhost-user-net backend has multiple thread supported.
+- Performance test for virtio-net is done by comparing 2 queue pairs with 1 queue pairs, that to run 2 iperf3 sessions in the same test environments, throughput is improved about 37%.
+
+## Start cloud-hypervisor with net devices
+
+Use one `--net` command-line argument from cloud-hypervisor to specify the emulation of one or more virtual NIC's. The example below instructs cloud-hypervisor to emulate for instance 2 virtual NIC's:
+
+```bash
+./cloud-hypervisor \
+    --cpus 4 \
+    --memory "size=512M" \
+    --disk path=focal-server-cloudimg-amd64.raw \
+    --kernel my-vmlinux.bin \
+    --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw" \
+    --net tap=ich0,mac=a4:a1:c2:00:00:01,ip=192.168.4.2,mask=255.255.255.0,num_queues=2,queue_size=256 \
+          tap=ich1,mac=a4:a1:c2:00:00:02,ip=10.0.1.2,mask=255.255.255.0,num_queues=2,queue_size=256
+```
+
+The `--net` argument takes 1 or more space-separated strings of key value pairs containing the following 4 keys or fields:
+
+| Name       | Purpose                    | Optional  |
+| -----------|----------------------------| ----------|
+| tap        | tap device name            | Yes       |
+| mac        | vNIC mac address           | Yes       |
+| ip         | tap IP IP address          | yes       |
+| mask       | tap IP netmask             | Yes       |
+| num_queues | the number of queues       | yes       |
+| queue_size | the size of each queue     | Yes       |
+
+num_queues is the total number of tx and rx queues, the default value is 2, and it could be increased by multiples of 2. Additionally, num_queues is suggested to be as 2 times of vcpu count. The default value for queue_size is 256.
+
+If the tap device is pre-created on host before guest boot up. To use multiple queue support for net device in guest, the tap device should be opened like this from host.
+
+```bash
+[root@localhost ~]# ip tuntap add name ich0 mode tap multi_queue
+```
+
+And the `--net` device should specify support for multiple queues. `num_queues` must be a multiple of 2 starting at least from 4 since multiple queues really means multiple queue pairs. We need at least 2 pairs for this configuration to be correct:
+
+```bash
+--net tap=ich0,mac=a4:a1:c2:00:00:01,ip=192.168.4.2,mask=255.255.255.0,num_queues=4,queue_size=256
+```
+
+## Configure the tap devices
+
+After starting cloud-hypervisor as shown above, 2 tap devices with state down will become available at the host:
+
+```bash
+root@host:~# ip link show ich0
+78: ich0: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000
+    link/ether 72:54:12:ff:ce:6f brd ff:ff:ff:ff:ff:ff
+root@host:~# ip link show ich1
+79: ich1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000
+    link/ether 06:7a:fc:1b:9a:67 brd ff:ff:ff:ff:ff:ff
+```
+
+Set the tap devices to up state:
+
+```bash
+root@host:~# ip link set up ich0
+root@host:~# ip link set up ich1
+
+root@host:~# ip link show ich0
+78: ich0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UNKNOWN mode DEFAULT group default qlen 1000
+    link/ether 72:54:12:ff:ce:6f brd ff:ff:ff:ff:ff:ff
+root@host:~# ip link show ich1
+79: ich1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UNKNOWN mode DEFAULT group default qlen 1000
+    link/ether 06:7a:fc:1b:9a:67 brd ff:ff:ff:ff:ff:ff
+```
+
+## Connect tap devices
+
+Different networking models can be used to provide external connectivity. In this example we will
+use 2 linux bridges emulating 2 different networks. The integration bridge (ich-int) in this example will also be used
+for external connectivity.
+
+Create the bridges and connect the cloud-hypervisor tap devices to the bridges:
+
+```bash
+root@host:~# brctl addbr ich-int
+root@host:~# brctl addbr ich-dpl
+root@host:~# ip link set up ich-int
+root@host:~# ip link set up ich-dpl
+root@host:~# brctl addif ich-int ich0
+root@host:~# brctl addif ich-dpl ich1
+root@host:~# brctl show
+bridge name     bridge id               STP enabled     interfaces
+ich-dpl         8000.067afc1b9a67       no              ich1
+ich-int         8000.725412ffce6f       no              ich0
+```
+This completes the layer 2 wiring: The cloud-hypervisor is now connected to the hypervisor host via the 2 linux bridges.
+
+## IP (Layer 3) provisioning
+
+### Hypervisor host
+
+On the hypervisor host add the network gateway IP address of each network to the 2 linux bridges:
+
+```bash
+root@host:~# ip addr add 192.168.4.1/24 dev ich-int
+root@host:~# ip addr add 10.0.1.1/24 dev ich-dpl
+```
+The routing table of the hypervisor host should now also have corresponding routing entries:
+
+```bash
+root@host:~# route -n
+Kernel IP routing table
+Destination     Gateway         Genmask         Flags Metric Ref    Use Iface
+0.0.0.0         192.168.178.1   0.0.0.0         UG    600    0        0 wlan1
+10.0.1.0        0.0.0.0         255.255.255.0   U     0      0        0 ich-dpl
+192.168.4.0     0.0.0.0         255.255.255.0   U     0      0        0 ich-int
+192.168.178.0   0.0.0.0         255.255.255.0   U     600    0        0 wlan1
+```
+### Virtual Machine
+
+Within the virtual machine set the vNIC's to up state and provision the corresponding IP addresses on the 2 vNIC's. The steps outlined below use the ip command as an example. Alternative distribution specific procedures can also apply.   
+
+```bash
+root@guest:~# ip link set up enp0s2
+root@guest:~# ip link set up enp0s3
+root@guest:~# ip addr add 192.168.4.2/24 dev enp0s2
+root@guest:~# ip addr add 10.0.1.2/24 dev enp0s3
+```
+
+IP connectivity between the virtual machine and the hypervisor-host can be verified by sending
+ICMP requests to the hypervisor-host for the gateway IP address from within the virtual machine:
+
+```bash
+root@guest:~# ping 192.168.4.1
+PING 192.168.4.1 (192.168.4.1) 56(84) bytes of data.
+64 bytes from 192.168.4.1: icmp_seq=1 ttl=64 time=0.456 ms
+64 bytes from 192.168.4.1: icmp_seq=2 ttl=64 time=0.226 ms
+root@guest:~# ping 10.0.1.1
+PING 10.0.1.1 (10.0.1.1) 56(84) bytes of data.
+64 bytes from 10.0.1.1: icmp_seq=1 ttl=64 time=0.449 ms
+64 bytes from 10.0.1.1: icmp_seq=2 ttl=64 time=0.393 ms
+```
+
+The connection can now be used for instance to log into the virtual machine with
+ssh under the precondition that the machine has an ssh daemon provisioned:
+
+```bash
+root@host:~# ssh root@192.168.4.2
+The authenticity of host '192.168.4.2 (192.168.4.2)' can't be established.
+ECDSA key fingerprint is SHA256:qNAUmTtDMW9pNuZARkpLQhfw+Yc1tqUDBrQp7aZGSjw.
+Are you sure you want to continue connecting (yes/no)? yes
+Warning: Permanently added '192.168.4.2' (ECDSA) to the list of known hosts.
+root@192.168.4.2's password:
+Linux cloud-hypervisor 5.2.0 #2 SMP Thu Jul 11 08:08:16 CEST 2019 x86_64
+
+Debian GNU/Linux comes with ABSOLUTELY NO WARRANTY, to the extent
+permitted by applicable law.                                                         
+
+
+Last login: Fri Jul 12 13:27:56 2019 from 192.168.4.1
+root@guest:~#
+```
+
+## Internet connectivity
+
+To enable internet connectivity a default gw and a nameserver has to be set within
+the virtual machine:
+
+```bash
+root@guest:~# ip route add default via 192.168.4.1
+root@guest:~# cat /etc/resolv.conf
+options timeout:2
+domain vallis.nl
+search vallis.nl
+nameserver 192.168.178.1
+```
+
+make sure that the default gateway of the hypervisor host (in this example host 192.168.178.1 which is an adsl router) has an entry in the routing table for the 192.168.4.0/24 network otherwise IP connectivity will not work.
+
+```bash
+root@guest:~# nslookup  ftp.nl.debian.org       
+Server:         192.168.178.1
+Address:        192.168.178.1#53
+
+Non-authoritative answer:
+cdn-fastly.deb.debian.org       canonical name = prod.debian.map.fastly.net.
+Name:   prod.debian.map.fastly.net
+Address: 151.101.36.204
+
+root@guest:~# apt-get update
+Ign:1 http://cdn-fastly.deb.debian.org/debian stretch InRelease
+Get:2 http://cdn-fastly.deb.debian.org/debian stretch Release [118 kB]
+Get:3 http://cdn-fastly.deb.debian.org/debian stretch Release.gpg [2434 B]
+Fetched 120 kB in 1s (110 kB/s)
+```

docs/performance_metrics.md

@@ -1,29 +0,0 @@
-# Performance Metrics
-
-Cloud Hypervisor provides a [performance metrics](https://github.com/cloud-hypervisor/cloud-hypervisor/tree/main/performance-metrics)
-binary for users to generate metrics data from their own
-environment. This document describes how to generate metrics data
-quickly by using Cloud Hypervisor's development script,
-e.g. `dev_cli.sh`. The only prerequisite is [Docker installation](https://docs.docker.com/engine/install/).
-Please note that upon its first invocation, this script will pull a
-fairly large container image.
-
-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:
-
-```
-$ ./scripts/dev_cli.sh tests --metrics -- -- --report-file /tmp/metrics.json
-```
-
-To get a list of available performance tests:
-
-```
-$ ./scripts/dev_cli.sh tests --metrics -- -- --list-tests
-```
-
-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
-```

docs/profiling.md

@@ -1,6 +1,6 @@
 # Profiling
 
-`perf` can be used to profile the `cloud-hypervisor` binary but it is necessary to make some modifications to the build in order to produce a binary that gives useful results.
+`perf` can be used to profile the `cloud-hypervisor` binary but it is necessary to make some modifications to the the build in order to produce a binary that gives useful results.
 
 ## Building a suitable binary
 
@@ -43,22 +43,3 @@ $ perf report -g
 ```
 
 If profiling with a network device attached either the TAP device must be already created and configured or the profiling must be done as root so that the TAP device can be created.
-
-## Userspace only profiling with LBR
-
-The use of LBR (Last Branch Record; available since Haswell) offers lower
-overhead if only userspace profiling is required. This lower overhead can allow
-a higher frequency of sampling. This also removes the requirement to compile
-with custom `RUSTFLAGS` however debug symbols should still be included:
-
-e.g.
-
-```
-$ perf record --call-graph lbr --all-user --user-callchains -g target/release/cloud-hypervisor \
-        --kernel ~/src/linux/vmlinux \
-        --pmem file=~/workloads/focal.raw \
-        --cpus boot=1 --memory size=1G \
-        --cmdline "root=/dev/pmem0p1 console=ttyS0" \
-        --serial tty --console off \
-        --api-socket=/tmp/api1
-```

docs/releases.md

@@ -1,103 +0,0 @@
-# Release Documentation
-
-## Abstract
-
-This document provides guidance to users, downstream maintainers and
-any other consumers of the Cloud Hypervisor project, this document
-describes the release process, release cadence, stability expectations and
-related topics.
-
-## Basic Terms
-
-### Stability
-
-For Cloud Hypervisor the following areas are subject to stability guarantees:
-
-- [REST API](api.md#rest-api)
-- [Command line options](api.md#command-line-interface)
-- [Device Model](device_model.md)
-- Device tree, device list, ACPI, Hyper-V enlightenments and any other
-  features exposed to guest
-- KVM compatibility
-- Rust edition compatibility
-
-This list is incomplete but this document serves as a best effort guide to stability
-across releases.
-
-### Experimental features
-
-Experimental features are under active development and no guarantees are made about their stability.
-
-List of experimental features:
-
-- TDX
-- vfio-user
-- vDPA
-
-### Security
-
-Security fixes should be included in a new point release.
-
-For security issues an advisory will be published via the GitHub security advisory process along with the release. Watching the project on GitHub will notify you of those issues.
-
-## Releases
-
-### Versioning
-
-The versioning scheme uses `MAJOR.POINT` pattern:
-
-- `MAJOR` can introduce incompatible changes along with support for new features. Changes to the [API](api.md#rest-api),
-  [CLI options](api.md#command-line-interface) and [device model](device_model.md)
-  require a notice at least 2 releases in advance for the actual change to take
-  place.
-- `POINT` contains bug fixes and/or security fixes.
-
-### Major Release Cadence
-
-Cloud Hypervisor is under active development. A new major release is issued approximately
-every 6 weeks. Point releases are issued on demand, when important bug fixes are in
-the queue. A major release would receive bug fixes for the next two cycles (~12 weeks)
-and then be considered EOL.
-
-```
-+ - Active release support
-E - EOL
-
-        2021                2022                2023 
-         |    |    |    |    |    |    |    |    | 
-18.0     |    |    |  ++++++++E
-19.0     |    |    |    |++++++++E
-20.0     |    |    |    |   ++++++++E
-21.0     |    |    |    |    | ++++++++E
-22.0     |    |    |    |    |    +++++++++E
-23.0     |    |    |    |    |    |  +++++++++E
-
-```
-
-### Major Release Stability Considerations
-
-Snapshot/restore support is not compatible across `MAJOR` versions.
-Live migration support is not compatible across `MAJOR` versions.
-
-### LTS Release Cadence
-
-A regular release is promoted to LTS every 12 months. An LTS release is supported for 18 months. This gives a 6 months window for users to move to the new LTS.
-
-```
-+ - Active release support
-E - EOL
-
-        2022                2023               2024                 2025                2026
-         |    |    |    |    |    |    |    |    |    |    |    |    |    |    |    |    |
-23.0     |    |+++++++++++++++++++++++++++++E
-43.0     |    |    |    |    |    |+++++++++++++++++++++++++++++E
-63.0     |    |    |    |    |    |    |    |    |    |+++++++++++++++++++++++++++++E
-
-```
-
-### LTS Stablity 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.
-The focus lays on critical and security bug fixes which are pulled at the
-maintainer's discretion.

docs/seccomp.md

@@ -64,5 +64,5 @@ it will log every system call issued by the process. It is important to use
 `-f` option in order to trace each and every thread belonging to the process.
 
 ```
-strace --decode-pids=comm -f ./cloud-hypervisor ...
+strace -f ./cloud-hypervisor ...
 ```

docs/snapshot_restore.md

@@ -8,16 +8,19 @@ snapshot and creates the exact same virtual machine, restoring the previously
 saved states. The new virtual machine is restored in a paused state, as it was
 before the snapshot was performed.
 
-## Snapshot a Cloud Hypervisor VM
+This feature is important for the project as it establishes the first step
+towards the support for live migration.
 
-First thing, we must run a Cloud Hypervisor VM:
+## Snapshot a Cloud-Hypervisor VM
+
+First thing, we must run a Cloud-Hypervisor VM:
 
 ```bash
 ./cloud-hypervisor \
     --api-socket /tmp/cloud-hypervisor.sock \
     --cpus boot=4 \
     --memory size=4G \
-    --kernel vmlinux \
+    --kernel bzImage \
     --cmdline "root=/dev/vda1 console=hvc0 rw" \
     --disk path=focal-server-cloudimg-amd64.raw
 ```
@@ -43,24 +46,26 @@ ll /home/foo/snapshot/
 total 4194536
 drwxrwxr-x  2 foo bar       4096 Jul 22 11:50 ./
 drwxr-xr-x 47 foo bar       4096 Jul 22 11:47 ../
--rw-------  1 foo bar       1084 Jul 22 11:19 config.json
--rw-------  1 foo bar 4294967296 Jul 22 11:19 memory-ranges
--rw-------  1 foo bar     217853 Jul 22 11:19 state.json
+-rw-------  1 foo bar 3221225472 Jul 22 11:19 memory-region-0
+-rw-------  1 foo bar 1073741824 Jul 22 11:19 memory-region-1
+-rw-------  1 foo bar     217853 Jul 22 11:19 vm.json
 ```
 
-`config.json` contains the virtual machine configuration. It is used to create
-a similar virtual machine with the correct amount of CPUs, RAM, and other
-expected devices. It is stored in a human readable format so that it could be
-modified between the snapshot and restore phases to achieve some very special
-use cases. But for most cases, manually modifying the configuration should not
-be needed.
+In this particular example, we can observe that 2 memory region files were
+created. That is explained by the size of the guest RAM, which is 4GiB in this
+case. Because it exceeds 3GiB (which is where we can find a ~1GiB memory hole),
+Cloud-Hypervisor needs 2 distinct memory regions to be created. Each memory
+region's content is stored through a dedicated file, which explains why we end
+up with 2 different files, the first one containing the guest RAM range 0-3GiB
+and the second one containing the guest RAM range 3-4GiB.
 
-`memory-ranges` stores the content of the guest RAM.
+`vm.json` gathers all information related to the virtual machine configuration
+and state. The configuration bits are used to create a similar virtual machine
+with the correct amount of CPUs, RAM, and other expected devices. The state
+bits are used to restore each component in the state it was left before the
+snapshot occurred.
 
-`state.json` contains the virtual machine state. It is used to restore each
-component in the state it was left before the snapshot occurred.
-
-## Restore a Cloud Hypervisor VM
+## 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 
@@ -95,4 +100,13 @@ snapshot earlier.
 
 ## Limitations
 
-VFIO devices and Intel SGX are out of scope.
+The support of snapshot/restore feature is still experimental, meaning one
+might still find some bugs associated with it.
+
+Additionally, some devices and features don't support to be snapshot and
+restored yet:
+- `vhost-user` devices
+- `virtio-mem`
+- Intel SGX
+
+VFIO devices are out of scope.

docs/tpm.md

@@ -1,122 +0,0 @@
-# TPM
-Tpm in Cloud-Hypervisor is emulated using `swtpm` as the backend. [swtpm](https://github.com/stefanberger/swtpm) is the link to swtpm project.
-
-Current implementation only supports TPM `2.0` version. At the moment only
-`CRB Interface` is implemented. This interface is described in
-[TCG PC Client Platform TPM Profile Specification for TPM 2.0, Revision 01.05 v4](https://trustedcomputinggroup.org/wp-content/uploads/PC-Client-Specific-Platform-TPM-Profile-for-TPM-2p0-v1p05p_r14_pub.pdf).
-
-
-## Usage
-`--tpm`, an optional argument, can be passed to enable tpm device.
-This argument takes an UNIX domain Socket as a `socket` value.
-
-_Example_
-
-An Example invocation with `--tpm` argument:
-
-```
- ./cloud-hypervisor/target/release/cloud-hypervisor \
-	--kernel ./hypervisor-fw \
-	--disk path=focal-server-cloudimg-amd64.raw \
-	--cpus boot=4 \
-	--memory size=1024M \
-	--net "tap=,mac=,ip=,mask=" \
-	--tpm socket="/var/run/swtpm.socket"
-```
-
-## swtpm
-Before invoking cloud-hypervisor with `--tpm` argument, a `swtpm`
-process should be started to listen at the input socket. Below is an
-example invocation of swtpm process.
-
-```
-swtpm socket --tpmstate dir=/var/run/swtpm \
-	--ctrl type=unixio,path="/var/run/swtpm.socket" \
-	--flags startup-clear \
-	--tpm2
-```
-
-## Guest
-After starting a guest with the above commands, ensure below listed modules are
-loaded in the guest:
-
-```
-# lsmod | grep tpm
-tpm_crb                20480  0
-tpm                    81920  1 tpm_crb
-```
-
-Below is the IO Memory map configured in the guest:
-
-```
-# cat /proc/iomem  | grep MSFT
-fed40000-fed40fff : MSFT0101:00
-  fed40000-fed40fff : MSFT0101:00
-```
-Below are the devices created in the guest:
-
-```
-# ls /dev/tpm*
-/dev/tpm0  /dev/tpmrm0
-```
-
-
-## Testing
-
-Inside the guest install `tpm2-tools` package. This package provides some
-commands to run against TPM that supports 2.0 version.
-
-_Examples_
-```
-// Run Self Test
-# tpm2_selftest -f
-# echo $?
-0
-
-
-# echo "hello" > input.txt
-// this command generates hash of the input file using all the algos supported by TPM
-
-# tpm2_pcrevent input.txt
-sha1: f572d396fae9206628714fb2ce00f72e94f2258f
-sha256: 5891b5b522d5df086d0ff0b110fbd9d21bb4fc7163af34d08286a2e846f6be03
-sha384: 1d0f284efe3edea4b9ca3bd514fa134b17eae361ccc7a1eefeff801b9bd6604e01f21f6bf249ef030599f0c
-218f2ba8c
-sha512: e7c22b994c59d9cf2b48e549b1e24666636045930d3da7c1acb299d1c3b7f931f94aae41edda2c2b207a36e
-10f8bcb8d45223e54878f5b316e7ce3b6bc019629
-
-// verify one of the hashes
-# sha256sum input.txt
-5891b5b522d5df086d0ff0b110fbd9d21bb4fc7163af34d08286a2e846f6be03  input.txt
-```
-
-### Bundled Functional Test
-
-Build time dependencies for `tpm2-tss` are captured in [INSTALL](https://github.com/tpm2-software/tpm2-tss/blob/master/INSTALL.md).
-
-```
-# git clone https://github.com/tpm2-software/tpm2-tss.git
-# cd tpm2-tss
-# ./configure --enable-integration --with-devicetests="mandatory,optional" --with-device=/dev/tpm0
-# sudo make check-device
-.
-.
-.
-.
-============================================================================
-Testsuite summary for tpm2-tss 3.2.0-74-ge03617d9
-============================================================================
-# TOTAL: 154
-# PASS:  88
-# SKIP:  7
-# XFAIL: 0
-# FAIL:  59
-# XPASS: 0
-# ERROR: 0
-============================================================================
-See ./test-suite.log
-Please report to https://github.com/tpm2-software/tpm2-tss/issues
-============================================================================
-```
-The same set of failures are noticed while running these tests on `Qemu` with
-its TPM implementation.