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: 3
-  allow:
-  - dependency-type: direct
-  - dependency-type: indirect
-- package-ecosystem: cargo
-  directory: "/fuzz"
-  schedule:
-    interval: daily
-  open-pull-requests-limit: 3
-  allow:
-  - dependency-type: direct
-  - dependency-type: indirect

.github/workflows/build.yaml

@@ -31,26 +31,14 @@ jobs:
 
       - name: Debug Check (default features)
         run: |
-          git rev-list origin/main..$GITHUB_SHA | xargs -t -I % sh -c 'git checkout %; cargo check --all --target=${{ matrix.target }}'
+          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 (default + tdx)
-        run: cargo rustc --bin cloud-hypervisor --features "tdx" -- -D warnings
-
       - name: Build (acpi,kvm)
         run: cargo rustc --bin cloud-hypervisor --no-default-features --features "acpi,kvm"  -- -D warnings
 
       - name: Build (kvm)
         run: cargo rustc --bin cloud-hypervisor --no-default-features --features "kvm"  -- -D warnings
-
-      - name: Build (acpi,mshv)
-        run: cargo rustc --bin cloud-hypervisor --no-default-features --features "acpi,mshv"  -- -D warnings
-
-      - name: Build (mshv)
-        run: cargo rustc --bin cloud-hypervisor --no-default-features --features "mshv"  -- -D warnings
         
       - name: Release Build (default features)
         run: cargo build --all --release --target=${{ matrix.target }}
-
-      - name: Check build did not modify any files
-        run: test -z "$(git status --porcelain)"

.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:
@@ -21,14 +19,12 @@ 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: Build and push
-        if: ${{ github.event_name == 'push' }}
         uses: docker/build-push-action@v2
         with:
           file: ./resources/Dockerfile
@@ -36,13 +32,5 @@ jobs:
           push: true
           tags: cloudhypervisor/dev:latest
 
-      - 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: 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

@@ -6,19 +6,12 @@ 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:
           - aarch64-unknown-linux-gnu
-        experimental: [false]
-        include:
-          - rust: beta
-            target: aarch64-unknown-linux-gnu
-            experimental: true
     steps:
       - name: Code checkout
         uses: actions/checkout@v2
@@ -29,33 +22,13 @@ jobs:
             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 }} --all --no-default-features --features "kvm" -- -D warnings
-
-      - name: Clippy (kvm,acpi)
-        uses: actions-rs/cargo@v1
-        with:
-          use-cross: true
-          command: clippy
-          args: --target=${{ matrix.target }} --all --no-default-features --features "kvm,acpi" -- -D warnings
-
-      - name: Clippy (all features,kvm)
-        uses: actions-rs/cargo@v1
-        with:
-          use-cross: true
-          command: clippy
-          args: --target=${{ matrix.target }} --all --no-default-features --features "common,kvm" -- -D warnings
-
-      - name: Clippy (default)
-        uses: actions-rs/cargo@v1
-        with:
-          use-cross: true
-          command: clippy
-          args: --target=${{ matrix.target }} --all -- -D warnings
+          args: --target=${{ matrix.target }} --no-default-features --features "kvm" -- -D warnings

.github/workflows/quality.yaml

@@ -6,19 +6,12 @@ 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
-        experimental: [false]
-        include:
-          - rust: beta
-            target: x86_64-unknown-linux-gnu
-            experimental: true
     steps:
       - name: Code checkout
         uses: actions/checkout@v2
@@ -55,7 +48,4 @@ jobs:
         run: cargo clippy --all --all-targets --no-default-features --tests --features "mshv" -- -D warnings
 
       - name: Clippy (integration tests)
-        run: cargo clippy --all --all-targets --tests -- -D warnings
-
-      - name: Check build did not modify any files
-        run: test -z "$(git status --porcelain)"
+        run: cargo clippy --all --all-targets --tests --features "integration_tests" -- -D warnings

.github/workflows/release.yaml

@@ -9,8 +9,6 @@ jobs:
     steps:
       - name: Code checkout
         uses: actions/checkout@v2
-      - name: Create release directory
-        run: rsync -rv --exclude=.git . ../cloud-hypervisor-${{ github.event.ref }}
       - name: Install Rust toolchain (x86_64-unknown-linux-gnu)
         uses: actions-rs/toolchain@v1
         with:
@@ -27,25 +25,6 @@ jobs:
         run: cargo build --all --release --target=x86_64-unknown-linux-musl
       - name: Strip cloud-hypervisor binaries
         run: strip target/*/release/cloud-hypervisor
-      - name: Install Rust toolchain (aarch64-unknown-linux-musl)
-        uses: actions-rs/toolchain@v1
-        with:
-            toolchain: stable
-            target: aarch64-unknown-linux-musl
-            override: true
-      - name: Static Build (AArch64)
-        uses: actions-rs/cargo@v1
-        with:
-            use-cross: true
-            command: build
-            args: --all --release --target=aarch64-unknown-linux-musl
-      - name: Vendor
-        working-directory: ../cloud-hypervisor-${{ github.event.ref }}
-        run: |
-          mkdir ../vendor-cargo-home
-          export CARGO_HOME=$(realpath ../vendor-cargo-home)
-          mkdir .cargo
-          cargo vendor > .cargo/config.toml
       - name: Create Release
         id: create_release
         uses: actions/create-release@v1
@@ -56,19 +35,6 @@ jobs:
           release_name: ${{ github.ref }}
           draft: true
           prerelease: true
-      - name: Create vendored source archive
-        working-directory: ../
-        run:  tar cJf cloud-hypervisor-${{ github.event.ref }}.tar.xz cloud-hypervisor-${{ github.event.ref }}
-      - name: Upload cloud-hypervisor vendored source archive
-        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
       - name: Upload cloud-hypervisor
         id: upload-release-cloud-hypervisor
         uses: actions/upload-release-asset@v1
@@ -99,33 +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
-        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: Upload static AArch64 cloud-hypervisor
-        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
-        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

.gitignore

@@ -1,5 +1,4 @@
 /build
-/.cargo
 /target
 **/*.rs.bk
 **/Cargo.lock

CONTRIBUTING.md

@@ -1,13 +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. Contributions
-can be made under either license or both. 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.
+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
 
@@ -62,7 +55,7 @@ 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.
+   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

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cloud-hypervisor"
-version = "21.1.0"
+version = "0.14.1"
 authors = ["The Cloud Hypervisor Authors"]
 edition = "2018"
 default-run = "cloud-hypervisor"
@@ -13,56 +13,60 @@ homepage = "https://github.com/cloud-hypervisor/cloud-hypervisor"
 lto = true
 
 [dependencies]
-anyhow = "1.0.52"
+anyhow = "1.0.39"
 api_client = { path = "api_client" }
-clap = { version = "3.0.10", features = ["wrap_help","cargo"] }
+clap = { version = "2.33.3", features = ["wrap_help"] }
 epoll = "4.3.1"
 event_monitor = { path = "event_monitor" }
 hypervisor = { path = "hypervisor" }
-libc = "0.2.112"
+libc = "0.2.91"
 log = { version = "0.4.14", features = ["std"] }
 option_parser = { path = "option_parser" }
-seccompiler = "0.2.0"
-serde_json = "1.0.75"
-signal-hook = "0.3.13"
-thiserror = "1.0.30"
+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 = "0.9.0"
-vm-memory = "0.7.0"
+vmm-sys-util = "0.8.0"
+vm-memory = "0.5.0"
 
 [build-dependencies]
-clap = { version = "3.0.10", features = ["wrap_help"] }
+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-v0.5.0", features = ["with-serde", "fam-wrappers"] }
-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" }
-serde_json = "1.0.75"
+serde_json = "1.0.64"
 test_infra = { path = "test_infra" }
 wait-timeout = "0.2.0"
 
 [features]
-default = ["common", "kvm"]
+default = ["acpi", "cmos", "io_uring", "kvm"]
 # Common features for all hypervisors
-common = ["acpi", "cmos", "fwdebug"]
+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"]
 
+# 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",
@@ -72,14 +76,10 @@ members = [
     "option_parser",
     "pci",
     "qcow",
-    "rate_limiter",
-    "vfio_user",
-    "vhdx",
     "vhost_user_backend",
     "vhost_user_block",
     "vhost_user_net",
     "virtio-devices",
-    "virtio-queue",
     "vmm",
     "vm-allocator",
     "vm-device",

Jenkinsfile

@@ -2,7 +2,7 @@ pipeline{
 	agent none
 	stages {
 		stage ('Early checks') {
-			agent { node { label 'built-in' } }
+			agent { node { label 'master' } }
 			stages {
 				stage ('Check for RFC/WIP builds') {
 					when {
@@ -14,7 +14,7 @@ pipeline{
 					}
 				}
 				stage ('Cancel older builds') {
-					when { not { branch 'main' } }
+					when { not { branch 'master' } }
 					steps {
 						cancelPreviousBuilds()
 					}
@@ -22,19 +22,15 @@ pipeline{
 			}
 		}
 		stage ('Build') {
-            parallel {
+            		parallel {
 				stage ('Worker build') {
-					agent { node { label 'hirsute' } }
-					environment {
-        					AZURE_CONNECTION_STRING = credentials('46b4e7d6-315f-4cc1-8333-b58780863b9b')
-					}
+					agent { node { label 'groovy' } }
 					stages {
 						stage ('Checkout') {
 							steps {
 								checkout scm
 							}
 						}
-
 						stage ('Run OpenAPI tests') {
 							steps {
 								sh "scripts/run_openapi_tests.sh"
@@ -50,7 +46,6 @@ pipeline{
 								timeout(time: 1, unit: 'HOURS')
 							}
 							steps {
-								sh "sudo modprobe openvswitch"
 								sh "scripts/dev_cli.sh tests --integration"
 							}
 						}
@@ -74,7 +69,6 @@ pipeline{
 								timeout(time: 1, unit: 'HOURS')
 							}
 							steps {
-								sh "sudo modprobe openvswitch"
 								sh "scripts/dev_cli.sh tests --integration"
 							}
 						}
@@ -87,17 +81,13 @@ pipeline{
 					}
 				}
 				stage ('Worker build (musl)') {
-					agent { node { label 'hirsute' } }
-					environment {
-        					AZURE_CONNECTION_STRING = credentials('46b4e7d6-315f-4cc1-8333-b58780863b9b')
-					}
+					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"
@@ -108,7 +98,6 @@ pipeline{
 								timeout(time: 1, unit: 'HOURS')
 							}
 							steps {
-								sh "sudo modprobe openvswitch"
 								sh "scripts/dev_cli.sh tests --integration --libc musl"
 							}
 						}
@@ -116,10 +105,7 @@ pipeline{
 				}
 				stage ('Worker build SGX') {
 					agent { node { label 'bionic-sgx' } }
-					when {
-						beforeAgent true
-						branch 'main'
-					}
+					when { branch 'master' }
 					stages {
 						stage ('Checkout') {
 							steps {
@@ -152,10 +138,7 @@ pipeline{
 				}
 				stage ('Worker build VFIO') {
 					agent { node { label 'bionic-vfio' } }
-					when {
-						beforeAgent true
-						branch 'main'
-					}
+					when { branch 'master' }
 					stages {
 						stage ('Checkout') {
 							steps {
@@ -187,25 +170,26 @@ pipeline{
 					}
 				}
 				stage ('Worker build - Windows guest') {
-					agent { node { label 'hirsute' } }
-					environment {
-        					AZURE_CONNECTION_STRING = credentials('46b4e7d6-315f-4cc1-8333-b58780863b9b')
-					}
+					agent { node { label 'groovy-win' } }
 					stages {
 						stage ('Checkout') {
 							steps {
 								checkout scm
 							}
 						}
-						stage ('Install azure-cli') {
-							steps {
-								installAzureCli()
-							}
-						}
 						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 "$AZURE_CONNECTION_STRING"'
+								azureDownload(storageCredentialId: 'ch-image-store',
+											  containerName: 'private-images',
+											  includeFilesPattern: 'OVMF-4b47d0c6c8.fd',
+											  downloadType: 'container',
+											  downloadDirLoc: "${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') {
@@ -226,49 +210,21 @@ pipeline{
 						}
 					}
 				}
-				stage ('Worker build - Live Migration') {
-					agent { node { label 'hirsute-small' } }
-					stages {
-						stage ('Checkout') {
-							steps {
-								checkout scm
-							}
-						}
-						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 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"
-							}
-						}
-					}
-				}
 			}
 		}
 	}
 	post {
 		regression {
 			script {
-				if (env.BRANCH_NAME == 'main') {
-					slackSend (color: '#ff0000', message: '"main" branch build is now failing')
+				if (env.BRANCH_NAME == 'master') {
+					slackSend (color: '#ff0000', message: '"master" branch build is now failing')
 				}
 			}
 		}
 		fixed {
 			script {
-				if (env.BRANCH_NAME == 'main') {
-					slackSend (color: '#00ff00', message: '"main" branch build is now fixed')
+				if (env.BRANCH_NAME == 'master') {
+					slackSend (color: '#00ff00', message: '"master" branch build is now fixed')
 				}
 			}
 		}
@@ -289,11 +245,3 @@ def cancelPreviousBuilds() {
 			}
 		}
 }
-
-def installAzureCli() {
-	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=amd64] https://packages.microsoft.com/repos/azure-cli/ hirsute main\" | sudo tee /etc/apt/sources.list.d/azure-cli.list"
-	sh "sudo apt update"
-	sh "sudo apt install -y azure-cli"
-}

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

@@ -1,11 +1,11 @@
+[![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)
-  - [Preparation](#preparation)
-  - [Install prerequisites](#install-prerequisites)
   - [Clone and build](#clone-and-build)
     - [Containerized builds and tests](#containerized-builds-and-tests)
   - [Run](#run)
@@ -23,12 +23,10 @@
 - [5. Community](#5-community)
   - [Contribute](#contribute)
   - [Join us](#join-us)
-  - [Security issues](#security-issues)
 
 # 1. What is Cloud Hypervisor?
 
-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) and the MSHV hypervisors .
-
+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.
 
@@ -38,7 +36,7 @@ Cloud Hypervisor is implemented in [Rust](https://www.rust-lang.org/) and is bas
 
 ### High Level
 
-- Runs on KVM or MSHV
+- KVM based
 - Minimal emulation
 - Low latency
 - Low memory footprint
@@ -55,16 +53,10 @@ Cloud Hypervisor supports the `x86-64` and `AArch64` architectures. There are so
 
 ### 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
 
-Below 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
-[Arm64 documentation](docs/arm64.md).
-
-## Preparation
-
 We create a folder to build and run `cloud-hypervisor` at `$HOME/cloud-hypervisor`
 
 ```shell
@@ -156,7 +148,7 @@ We need to get the latest `rust-hypervisor-firmware` release and also a working
 $ 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/0.3.2/hypervisor-fw
+$ wget https://github.com/cloud-hypervisor/rust-hypervisor-firmware/releases/download/0.3.0/hypervisor-fw
 $ popd
 ```
 
@@ -168,7 +160,8 @@ $ ./cloud-hypervisor/target/release/cloud-hypervisor \
 	--disk path=focal-server-cloudimg-amd64.raw \
 	--cpus boot=4 \
 	--memory size=1024M \
-	--net "tap=,mac=,ip=,mask="
+	--net "tap=,mac=,ip=,mask=" \
+	--rng
 $ popd
 ```
 
@@ -178,7 +171,7 @@ Multiple arguments can be given to the `--disk` parameter.
 
 #### Building your kernel
 
-Cloud Hypervisor also supports direct kernel boot into a `vmlinux` ELF kernel. In order to support 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.
+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:
 
@@ -186,12 +179,12 @@ To build the kernel:
 
 # Clone the Cloud Hypervisor Linux branch
 $ pushd $CLOUDH
-$ git clone --depth 1 https://github.com/cloud-hypervisor/linux.git -b ch-5.15.12 linux-cloud-hypervisor
+$ 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
 $ cp $CLOUDH/cloud-hypervisor/resources/linux-config-x86_64 .config
-$ KCFLAGS="-Wa,-mx86-used-note=no" make bzImage -j `nproc`
+$ make bzImage -j `nproc`
 $ popd
 ```
 
@@ -211,7 +204,7 @@ $ popd
 #### Booting the guest VM
 
 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 1024 MBytes of memory:
+If we want to have 4 vCPUs and 512 MBytes of memory:
 
 ```shell
 $ pushd $CLOUDH
@@ -222,7 +215,8 @@ $ ./cloud-hypervisor/target/release/cloud-hypervisor \
 	--cmdline "console=hvc0 root=/dev/vda1 rw" \
 	--cpus boot=4 \
 	--memory size=1024M \
-	--net "tap=,mac=,ip=,mask="
+	--net "tap=,mac=,ip=,mask=" \
+	--rng
 ```
 
 The above example use the `virtio-console` device as the guest console, and this
@@ -241,45 +235,29 @@ $ ./cloud-hypervisor/target/release/cloud-hypervisor \
 	--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 releases notice. Where possible warnings
-  will be given about the use of deprecated functionality and the deprecations
-  will be documented in the release notes.
-* Point releases will be made between individual releases where there are
-  substantial bug fixes or security issues that need to be fixed.
-
-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, SGX.
-
-
-As of 2021-04-29, the following cloud images are supported:
+As of 2020-07-02, the following cloud images are supported:
 
 - [Ubuntu Bionic](https://cloud-images.ubuntu.com/bionic/current/) (cloudimg)
 - [Ubuntu Focal](https://cloud-images.ubuntu.com/focal/current/) (cloudimg)
-- [Ubuntu Groovy](https://cloud-images.ubuntu.com/groovy/current/) (cloudimg)
-- [Ubuntu Hirsute](https://cloud-images.ubuntu.com/hirsute/current/) (cloudimg)
 
 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
+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).
 
 ## TODO
 
@@ -339,7 +317,3 @@ etc, are all equal and welcome means of contribution. See the [CONTRIBUTING](CON
 
 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/).
-
-## Security issues
-
-Please use the GitHub security advisories feature for reporting issues: https://github.com/cloud-hypervisor/cloud-hypervisor/security/advisories/new

acpi_tables/Cargo.toml

@@ -5,4 +5,5 @@ authors = ["The Cloud Hypervisor Authors"]
 edition = "2018"
 
 [dependencies]
-vm-memory = "0.7.0"
+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.to_vec());
+            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

@@ -22,15 +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 {
@@ -75,7 +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

@@ -3,6 +3,3 @@ name = "api_client"
 version = "0.1.0"
 authors = ["The Cloud Hypervisor Authors"]
 edition = "2018"
-
-[dependencies]
-vmm-sys-util = "0.9.0"

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),
@@ -23,7 +20,6 @@ impl fmt::Display for Error {
         use Error::*;
         match self {
             Socket(e) => write!(f, "Error writing to or reading from HTTP socket: {}", e),
-            SocketSendFds(e) => write!(f, "Error writing to or reading from HTTP socket: {}", e),
             StatusCodeParsing(e) => write!(f, "Error parsing HTTP status code: {}", e),
             MissingProtocol => write!(f, "HTTP output is missing protocol statement"),
             ContentLengthParsing(e) => write!(f, "Error parsing HTTP Content-Length field: {}", e),
@@ -80,8 +76,11 @@ 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()])
+    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> {
@@ -137,23 +136,21 @@ fn parse_http_response(socket: &mut dyn Read) -> Result<Option<String>, Error> {
     }
 }
 
-pub fn simple_api_command_with_fds<T: Read + Write + ScmSocket>(
+pub fn simple_api_command<T: Read + Write>(
     socket: &mut T,
     method: &str,
     c: &str,
     request_body: Option<&str>,
-    request_fds: Vec<RawFd>,
 ) -> Result<(), Error> {
     socket
-        .send_with_fds(
-            &[format!(
+        .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
@@ -176,12 +173,3 @@ pub fn simple_api_command_with_fds<T: Read + Write + ScmSocket>(
     }
     Ok(())
 }
-
-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

@@ -2,7 +2,6 @@
 name = "arch"
 version = "0.1.0"
 authors = ["The Chromium OS Authors"]
-edition = "2018"
 
 [features]
 default = []
@@ -11,21 +10,17 @@ tdx = []
 
 [dependencies]
 acpi_tables = { path = "../acpi_tables", optional = true }
-anyhow = "1.0.52"
+anyhow = "1.0"
+arch_gen = { path = "../arch_gen" }
 byteorder = "1.4.3"
 hypervisor = { path = "../hypervisor" }
-libc = "0.2.112"
-linux-loader = { version = "0.4.0", features = ["elf", "bzimage", "pe"] }
+libc = "0.2.91"
+linux-loader = { version = "0.3.0", features = ["elf", "bzimage", "pe"] }
 log = "0.4.14"
-serde = { version = "1.0.133", features = ["rc"] }
-serde_derive = "1.0.133"
-thiserror = "1.0.30"
-versionize = "0.1.6"
-versionize_derive = "0.1.4"
-vm-memory = { version = "0.7.0", features = ["backend-mmap", "backend-bitmap"] }
+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 = "0.9.0", features = ["with-serde"] }
 
-[target.'cfg(target_arch = "aarch64")'.dependencies]
-fdt_parser = { version = "0.1.3", package = 'fdt'}
-vm-fdt = { git = "https://github.com/rust-vmm/vm-fdt", branch = "main" }

arch/src/aarch64/gic/dist_regs.rs

@@ -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),
@@ -152,7 +152,7 @@ pub fn set_dist_regs(gic: &Arc<dyn hypervisor::Device>, state: &[u32]) -> Result
 
     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];
@@ -169,7 +169,7 @@ pub fn get_dist_regs(gic: &Arc<dyn hypervisor::Device>) -> Result<Vec<u32>> {
 
     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

@@ -1,30 +1,22 @@
-// Copyright 2021 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
-//
-// This file implements the GicV3 device.
 
 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::{
-        construct_gicr_typers, get_redist_regs, set_redist_regs,
-    };
+    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 hypervisor::CpuState;
     use std::any::Any;
     use std::convert::TryInto;
     use std::sync::Arc;
     use std::{boxed::Box, result};
-    use versionize::{VersionMap, Versionize, VersionizeResult};
-    use versionize_derive::Versionize;
     use vm_migration::{
-        Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable,
-        VersionMapped,
+        Migratable, MigratableError, Pausable, Snapshot, SnapshotDataSection, Snapshottable,
+        Transportable,
     };
 
     /// Errors thrown while saving/restoring the GICv3.
@@ -53,7 +45,7 @@ pub mod kvm {
     type Result<T> = result::Result<T, Error>;
 
     pub struct KvmGicV3 {
-        /// The hypervisor agnostic device for the GicV3
+        /// The hypervisor agnostic device
         device: Arc<dyn hypervisor::Device>,
 
         /// Vector holding values of GICR_TYPER for each vCPU
@@ -66,7 +58,7 @@ pub mod kvm {
         vcpu_count: u64,
     }
 
-    #[derive(Versionize)]
+    #[derive(Serialize, Deserialize)]
     pub struct Gicv3State {
         dist: Vec<u32>,
         rdist: Vec<u32>,
@@ -75,20 +67,24 @@ pub mod kvm {
         gicd_ctlr: u32,
     }
 
-    impl VersionMapped for Gicv3State {}
-
     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::GIC_V3_DIST_START
+            layout::MAPPED_IO_START - KvmGicV3::KVM_VGIC_V3_DIST_SIZE
         }
 
         /// Get the size of the GIC distributor.
         pub fn get_dist_size() -> u64 {
-            layout::GIC_V3_DIST_SIZE
+            KvmGicV3::KVM_VGIC_V3_DIST_SIZE
         }
 
         /// Get the address of the GIC redistributors.
@@ -98,22 +94,25 @@ pub mod kvm {
 
         /// Get the size of the GIC redistributors.
         pub fn get_redists_size(vcpu_count: u64) -> u64 {
-            vcpu_count * layout::GIC_V3_REDIST_SIZE
+            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)?;
+                read_ctlr(&self.device()).map_err(Error::SaveDistributorCtrlRegisters)?;
 
             let dist_state =
-                get_dist_regs(self.device()).map_err(Error::SaveDistributorRegisters)?;
+                get_dist_regs(&self.device()).map_err(Error::SaveDistributorRegisters)?;
 
-            let rdist_state = get_redist_regs(self.device(), gicr_typers)
+            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)?;
+                get_icc_regs(&self.device(), &gicr_typers).map_err(Error::SaveIccRegisters)?;
 
             Ok(Gicv3State {
                 dist: dist_state,
@@ -125,16 +124,16 @@ pub mod kvm {
 
         /// Restore the state of GIC.
         fn set_state(&mut self, gicr_typers: &[u64], state: &Gicv3State) -> Result<()> {
-            write_ctlr(self.device(), state.gicd_ctlr)
+            write_ctlr(&self.device(), state.gicd_ctlr)
                 .map_err(Error::RestoreDistributorCtrlRegisters)?;
 
-            set_dist_regs(self.device(), &state.dist)
+            set_dist_regs(&self.device(), &state.dist)
                 .map_err(Error::RestoreDistributorRegisters)?;
 
-            set_redist_regs(self.device(), gicr_typers, &state.rdist)
+            set_redist_regs(&self.device(), gicr_typers, &state.rdist)
                 .map_err(Error::RestoreRedistributorRegisters)?;
 
-            set_icc_regs(self.device(), gicr_typers, &state.icc)
+            set_icc_regs(&self.device(), &gicr_typers, &state.icc)
                 .map_err(Error::RestoreIccRegisters)?;
 
             Ok(())
@@ -162,10 +161,7 @@ pub mod kvm {
             self.vcpu_count
         }
 
-        fn set_its_device(&mut self, _its_device: Option<Arc<dyn hypervisor::Device>>) {}
-
-        fn set_gicr_typers(&mut self, vcpu_states: &[CpuState]) {
-            let gicr_typers = construct_gicr_typers(vcpu_states);
+        fn set_gicr_typers(&mut self, gicr_typers: Vec<u64>) {
             self.gicr_typers = gicr_typers;
         }
 
@@ -198,7 +194,7 @@ pub mod kvm {
 
         fn init_device_attributes(
             _vm: &Arc<dyn hypervisor::Vm>,
-            gic_device: &mut dyn GicDevice,
+            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.
@@ -234,28 +230,46 @@ pub mod kvm {
 
         fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
             let gicr_typers = self.gicr_typers.clone();
-            Snapshot::new_from_versioned_state(&self.id(), &self.state(&gicr_typers).unwrap())
+            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> {
-            let gicr_typers = self.gicr_typers.clone();
-            self.set_state(&gicr_typers, &snapshot.to_versioned_state(&self.id())?)
-                .map_err(|e| {
+            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 {
-        fn pause(&mut self) -> std::result::Result<(), MigratableError> {
-            // Flush redistributors pending tables to guest RAM.
-            save_pending_tables(self.device()).map_err(|e| {
-                MigratableError::Pause(anyhow!("Could not save GICv3 GIC pending tables {:?}", e))
-            })?;
-
-            Ok(())
-        }
-    }
+    impl Pausable for KvmGicV3 {}
     impl Transportable for KvmGicV3 {}
     impl Migratable for KvmGicV3 {}
 }

arch/src/aarch64/gic/gicv3_its.rs

@@ -1,153 +1,21 @@
-// Copyright 2021 Arm Limited (or its affiliates). All rights reserved.
+// Copyright 2020 ARM Limited
 // SPDX-License-Identifier: Apache-2.0
-//
-// This file implements the GicV3 device with ITS (Virtual Interrupt Translation Service).
 
 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::redist_regs::{
-        construct_gicr_typers, get_redist_regs, set_redist_regs,
-    };
-
-    use crate::aarch64::gic::gicv3::kvm::KvmGicV3;
-    use crate::aarch64::gic::kvm::{save_pending_tables, KvmGicDevice};
-    use crate::aarch64::gic::GicDevice;
-    use crate::layout;
-    use anyhow::anyhow;
-    use hypervisor::kvm::kvm_bindings;
-    use hypervisor::CpuState;
     use std::any::Any;
     use std::convert::TryInto;
     use std::sync::Arc;
     use std::{boxed::Box, result};
-    use versionize::{VersionMap, Versionize, VersionizeResult};
-    use versionize_derive::Versionize;
-    use vm_migration::{
-        Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable,
-        VersionMapped,
-    };
-
-    const GITS_CTLR: u32 = 0x0000;
-    const GITS_IIDR: u32 = 0x0004;
-    const GITS_CBASER: u32 = 0x0080;
-    const GITS_CWRITER: u32 = 0x0088;
-    const GITS_CREADR: u32 = 0x0090;
-    const GITS_BASER: u32 = 0x0100;
-
-    /// Errors thrown while saving/restoring the GICv3ITS.
-    #[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),
-        /// Error in saving GICv3ITS IIDR register.
-        SaveITSIIDR(crate::aarch64::gic::Error),
-        /// Error in restoring GICv3ITS IIDR register.
-        RestoreITSIIDR(crate::aarch64::gic::Error),
-        /// Error in saving GICv3ITS CBASER register.
-        SaveITSCBASER(crate::aarch64::gic::Error),
-        /// Error in restoring GICv3ITS CBASER register.
-        RestoreITSCBASER(crate::aarch64::gic::Error),
-        /// Error in saving GICv3ITS CREADR register.
-        SaveITSCREADR(crate::aarch64::gic::Error),
-        /// Error in restoring GICv3ITS CREADR register.
-        RestoreITSCREADR(crate::aarch64::gic::Error),
-        /// Error in saving GICv3ITS CWRITER register.
-        SaveITSCWRITER(crate::aarch64::gic::Error),
-        /// Error in restoring GICv3ITS CWRITER register.
-        RestoreITSCWRITER(crate::aarch64::gic::Error),
-        /// Error in saving GICv3ITS BASER register.
-        SaveITSBASER(crate::aarch64::gic::Error),
-        /// Error in restoring GICv3ITS BASER register.
-        RestoreITSBASER(crate::aarch64::gic::Error),
-        /// Error in saving GICv3ITS CTLR register.
-        SaveITSCTLR(crate::aarch64::gic::Error),
-        /// Error in restoring GICv3ITS CTLR register.
-        RestoreITSCTLR(crate::aarch64::gic::Error),
-        /// Error in saving GICv3ITS restore tables.
-        SaveITSTables(crate::aarch64::gic::Error),
-        /// Error in restoring GICv3ITS restore tables.
-        RestoreITSTables(crate::aarch64::gic::Error),
-    }
-
     type Result<T> = result::Result<T, Error>;
-
-    /// Access an ITS device attribute.
-    ///
-    /// This is a helper function to get/set the ITS device attribute depending
-    /// the bool parameter `set` provided.
-    pub fn gicv3_its_attr_access(
-        its_device: &Arc<dyn hypervisor::Device>,
-        group: u32,
-        attr: u32,
-        val: &u64,
-        set: bool,
-    ) -> crate::aarch64::gic::Result<()> {
-        let mut gicv3_its_attr = kvm_bindings::kvm_device_attr {
-            group,
-            attr: attr as u64,
-            addr: val as *const u64 as u64,
-            flags: 0,
-        };
-        if set {
-            its_device
-                .set_device_attr(&gicv3_its_attr)
-                .map_err(crate::aarch64::gic::Error::SetDeviceAttribute)?;
-        } else {
-            its_device
-                .get_device_attr(&mut gicv3_its_attr)
-                .map_err(crate::aarch64::gic::Error::GetDeviceAttribute)?;
-        }
-        Ok(())
-    }
-
-    /// Function that saves/restores ITS tables into guest RAM.
-    ///
-    /// The tables get flushed to guest RAM whenever the VM gets stopped.
-    pub fn gicv3_its_tables_access(
-        its_device: &Arc<dyn hypervisor::Device>,
-        save: bool,
-    ) -> crate::aarch64::gic::Result<()> {
-        let attr = if save {
-            u64::from(kvm_bindings::KVM_DEV_ARM_ITS_SAVE_TABLES)
-        } else {
-            u64::from(kvm_bindings::KVM_DEV_ARM_ITS_RESTORE_TABLES)
-        };
-
-        let init_gic_attr = kvm_bindings::kvm_device_attr {
-            group: kvm_bindings::KVM_DEV_ARM_VGIC_GRP_CTRL,
-            attr,
-            addr: 0,
-            flags: 0,
-        };
-        its_device
-            .set_device_attr(&init_gic_attr)
-            .map_err(crate::aarch64::gic::Error::SetDeviceAttribute)
-    }
+    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 for the GicV3
+        /// The hypervisor agnostic device
         device: Arc<dyn hypervisor::Device>,
 
-        /// The hypervisor agnostic device for the Its device
-        its_device: Option<Arc<dyn hypervisor::Device>>,
-
         /// Vector holding values of GICR_TYPER for each vCPU
         gicr_typers: Vec<u64>,
 
@@ -161,199 +29,16 @@ pub mod kvm {
         vcpu_count: u64,
     }
 
-    #[derive(Versionize)]
-    pub struct Gicv3ItsState {
-        dist: Vec<u32>,
-        rdist: Vec<u32>,
-        icc: Vec<u32>,
-        // special register that enables interrupts and affinity routing
-        gicd_ctlr: u32,
-        its_ctlr: u64,
-        its_iidr: u64,
-        its_cbaser: u64,
-        its_cwriter: u64,
-        its_creadr: u64,
-        its_baser: [u64; 8],
-    }
-
-    impl VersionMapped for Gicv3ItsState {}
-
     impl KvmGicV3Its {
+        const KVM_VGIC_V3_ITS_SIZE: u64 = (2 * KvmGicV3::SZ_64K);
+
         fn get_msi_size() -> u64 {
-            layout::GIC_V3_ITS_SIZE
+            KvmGicV3Its::KVM_VGIC_V3_ITS_SIZE
         }
 
         fn get_msi_addr(vcpu_count: u64) -> u64 {
             KvmGicV3::get_redists_addr(vcpu_count) - KvmGicV3Its::get_msi_size()
         }
-
-        /// Save the state of GICv3ITS.
-        fn state(&self, gicr_typers: &[u64]) -> Result<Gicv3ItsState> {
-            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)?;
-
-            let its_baser_state: [u64; 8] = [0; 8];
-            for i in 0..8 {
-                gicv3_its_attr_access(
-                    self.its_device().unwrap(),
-                    kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
-                    GITS_BASER + i * 8,
-                    &its_baser_state[i as usize],
-                    false,
-                )
-                .map_err(Error::SaveITSBASER)?;
-            }
-
-            let its_ctlr_state: u64 = 0;
-            gicv3_its_attr_access(
-                self.its_device().unwrap(),
-                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
-                GITS_CTLR,
-                &its_ctlr_state,
-                false,
-            )
-            .map_err(Error::SaveITSCTLR)?;
-
-            let its_cbaser_state: u64 = 0;
-            gicv3_its_attr_access(
-                self.its_device().unwrap(),
-                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
-                GITS_CBASER,
-                &its_cbaser_state,
-                false,
-            )
-            .map_err(Error::SaveITSCBASER)?;
-
-            let its_creadr_state: u64 = 0;
-            gicv3_its_attr_access(
-                self.its_device().unwrap(),
-                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
-                GITS_CREADR,
-                &its_creadr_state,
-                false,
-            )
-            .map_err(Error::SaveITSCREADR)?;
-
-            let its_cwriter_state: u64 = 0;
-            gicv3_its_attr_access(
-                self.its_device().unwrap(),
-                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
-                GITS_CWRITER,
-                &its_cwriter_state,
-                false,
-            )
-            .map_err(Error::SaveITSCWRITER)?;
-
-            let its_iidr_state: u64 = 0;
-            gicv3_its_attr_access(
-                self.its_device().unwrap(),
-                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
-                GITS_IIDR,
-                &its_iidr_state,
-                false,
-            )
-            .map_err(Error::SaveITSIIDR)?;
-
-            Ok(Gicv3ItsState {
-                dist: dist_state,
-                rdist: rdist_state,
-                icc: icc_state,
-                gicd_ctlr,
-                its_ctlr: its_ctlr_state,
-                its_iidr: its_iidr_state,
-                its_cbaser: its_cbaser_state,
-                its_cwriter: its_cwriter_state,
-                its_creadr: its_creadr_state,
-                its_baser: its_baser_state,
-            })
-        }
-
-        /// Restore the state of GICv3ITS.
-        fn set_state(&mut self, gicr_typers: &[u64], state: &Gicv3ItsState) -> 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)?;
-
-            //Restore GICv3ITS registers
-            gicv3_its_attr_access(
-                self.its_device().unwrap(),
-                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
-                GITS_IIDR,
-                &state.its_iidr,
-                true,
-            )
-            .map_err(Error::RestoreITSIIDR)?;
-
-            gicv3_its_attr_access(
-                self.its_device().unwrap(),
-                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
-                GITS_CBASER,
-                &state.its_cbaser,
-                true,
-            )
-            .map_err(Error::RestoreITSCBASER)?;
-
-            gicv3_its_attr_access(
-                self.its_device().unwrap(),
-                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
-                GITS_CREADR,
-                &state.its_creadr,
-                true,
-            )
-            .map_err(Error::RestoreITSCREADR)?;
-
-            gicv3_its_attr_access(
-                self.its_device().unwrap(),
-                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
-                GITS_CWRITER,
-                &state.its_cwriter,
-                true,
-            )
-            .map_err(Error::RestoreITSCWRITER)?;
-
-            for i in 0..8 {
-                gicv3_its_attr_access(
-                    self.its_device().unwrap(),
-                    kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
-                    GITS_BASER + i * 8,
-                    &state.its_baser[i as usize],
-                    true,
-                )
-                .map_err(Error::RestoreITSBASER)?;
-            }
-
-            // Restore ITS tables
-            gicv3_its_tables_access(self.its_device().unwrap(), false)
-                .map_err(Error::RestoreITSTables)?;
-
-            gicv3_its_attr_access(
-                self.its_device().unwrap(),
-                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
-                GITS_CTLR,
-                &state.its_ctlr,
-                true,
-            )
-            .map_err(Error::RestoreITSCTLR)?;
-
-            Ok(())
-        }
     }
 
     impl GicDevice for KvmGicV3Its {
@@ -361,10 +46,6 @@ pub mod kvm {
             &self.device
         }
 
-        fn its_device(&self) -> Option<&Arc<dyn hypervisor::Device>> {
-            self.its_device.as_ref()
-        }
-
         fn fdt_compatibility(&self) -> &str {
             "arm,gic-v3"
         }
@@ -393,12 +74,7 @@ pub mod kvm {
             self.vcpu_count
         }
 
-        fn set_its_device(&mut self, its_device: Option<Arc<dyn hypervisor::Device>>) {
-            self.its_device = its_device;
-        }
-
-        fn set_gicr_typers(&mut self, vcpu_states: &[CpuState]) {
-            let gicr_typers = construct_gicr_typers(vcpu_states);
+        fn set_gicr_typers(&mut self, gicr_typers: Vec<u64>) {
             self.gicr_typers = gicr_typers;
         }
 
@@ -418,7 +94,6 @@ pub mod kvm {
         ) -> Box<dyn GicDevice> {
             Box::new(KvmGicV3Its {
                 device,
-                its_device: None,
                 gicr_typers: vec![0; vcpu_count.try_into().unwrap()],
                 gic_properties: [
                     KvmGicV3::get_dist_addr(),
@@ -436,8 +111,8 @@ pub mod kvm {
 
         fn init_device_attributes(
             vm: &Arc<dyn hypervisor::Vm>,
-            gic_device: &mut dyn GicDevice,
-        ) -> crate::aarch64::gic::Result<()> {
+            gic_device: &dyn GicDevice,
+        ) -> Result<()> {
             KvmGicV3::init_device_attributes(vm, gic_device)?;
 
             let mut its_device = kvm_bindings::kvm_create_device {
@@ -448,7 +123,7 @@ pub mod kvm {
 
             let its_fd = vm
                 .create_device(&mut its_device)
-                .map_err(crate::aarch64::gic::Error::CreateGic)?;
+                .map_err(Error::CreateGic)?;
 
             Self::set_device_attribute(
                 &its_fd,
@@ -466,49 +141,7 @@ pub mod kvm {
                 0,
             )?;
 
-            gic_device.set_its_device(Some(its_fd));
-
             Ok(())
         }
     }
-
-    pub const GIC_V3_ITS_SNAPSHOT_ID: &str = "gic-v3-its";
-    impl Snapshottable for KvmGicV3Its {
-        fn id(&self) -> String {
-            GIC_V3_ITS_SNAPSHOT_ID.to_string()
-        }
-
-        fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-            let gicr_typers = self.gicr_typers.clone();
-            Snapshot::new_from_versioned_state(&self.id(), &self.state(&gicr_typers).unwrap())
-        }
-
-        fn restore(&mut self, snapshot: Snapshot) -> std::result::Result<(), MigratableError> {
-            let gicr_typers = self.gicr_typers.clone();
-            self.set_state(&gicr_typers, &snapshot.to_versioned_state(&self.id())?)
-                .map_err(|e| {
-                    MigratableError::Restore(anyhow!("Could not restore GICv3ITS state {:?}", e))
-                })
-        }
-    }
-
-    impl Pausable for KvmGicV3Its {
-        fn pause(&mut self) -> std::result::Result<(), MigratableError> {
-            // Flush redistributors pending tables to guest RAM.
-            save_pending_tables(self.device()).map_err(|e| {
-                MigratableError::Pause(anyhow!(
-                    "Could not save GICv3ITS GIC pending tables {:?}",
-                    e
-                ))
-            })?;
-            // Flush ITS tables to guest RAM.
-            gicv3_its_tables_access(self.its_device().unwrap(), true).map_err(|e| {
-                MigratableError::Pause(anyhow!("Could not save GICv3ITS ITS tables {:?}", e))
-            })?;
-
-            Ok(())
-        }
-    }
-    impl Transportable for KvmGicV3Its {}
-    impl Migratable for KvmGicV3Its {}
 }

arch/src/aarch64/gic/icc_regs.rs

@@ -59,7 +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,
@@ -91,7 +91,8 @@ fn icc_attr_access(
         flags: 0,
     };
     if set {
-        gic.set_device_attr(&gic_icc_attr)
+        #[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)

arch/src/aarch64/gic/mod.rs

@@ -1,4 +1,3 @@
-// Copyright 2021 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
 
@@ -11,7 +10,6 @@ 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 hypervisor::CpuState;
 use std::any::Any;
 use std::result;
 use std::sync::Arc;
@@ -32,11 +30,6 @@ pub trait GicDevice: Send {
     /// Returns the hypervisor agnostic Device of the GIC device
     fn device(&self) -> &Arc<dyn hypervisor::Device>;
 
-    /// Returns the hypervisor agnostic Device of the ITS device
-    fn its_device(&self) -> Option<&Arc<dyn hypervisor::Device>> {
-        None
-    }
-
     /// Returns the fdt compatibility property of the device
     fn fdt_compatibility(&self) -> &str;
 
@@ -64,10 +57,8 @@ pub trait GicDevice: Send {
         &[]
     }
 
-    fn set_its_device(&mut self, its_device: Option<Arc<dyn hypervisor::Device>>);
-
     /// Get the values of GICR_TYPER for each vCPU.
-    fn set_gicr_typers(&mut self, vcpu_states: &[CpuState]);
+    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;
@@ -96,7 +87,7 @@ pub mod kvm {
         /// Setup the device-specific attributes
         fn init_device_attributes(
             vm: &Arc<dyn hypervisor::Vm>,
-            gic_device: &mut dyn GicDevice,
+            gic_device: &dyn GicDevice,
         ) -> Result<()>;
 
         /// Initialize a GIC device
@@ -120,10 +111,10 @@ pub mod kvm {
             flags: u32,
         ) -> Result<()> {
             let attr = kvm_bindings::kvm_device_attr {
-                flags,
                 group,
                 attr,
                 addr,
+                flags,
             };
             device
                 .set_device_attr(&attr)
@@ -141,10 +132,10 @@ pub mod kvm {
             flags: u32,
         ) -> Result<()> {
             let mut attr = kvm_bindings::kvm_device_attr {
-                flags,
                 group,
                 attr,
                 addr,
+                flags,
             };
             device
                 .get_device_attr(&mut attr)
@@ -158,7 +149,7 @@ pub mod kvm {
             /* 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_NUM;
+            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(),
@@ -187,9 +178,9 @@ pub mod kvm {
         fn new(vm: &Arc<dyn hypervisor::Vm>, vcpu_count: u64) -> Result<Box<dyn GicDevice>> {
             let vgic_fd = Self::init_device(vm)?;
 
-            let mut device = Self::create_device(vgic_fd, vcpu_count);
+            let device = Self::create_device(vgic_fd, vcpu_count);
 
-            Self::init_device_attributes(vm, &mut *device)?;
+            Self::init_device_attributes(vm, &*device)?;
 
             Self::finalize_device(&*device)?;
 

arch/src/aarch64/gic/redist_regs.rs

@@ -3,7 +3,6 @@
 
 use super::{Error, Result};
 use hypervisor::kvm::kvm_bindings::{kvm_device_attr, KVM_DEV_ARM_VGIC_GRP_REDIST_REGS};
-use hypervisor::CpuState;
 use std::sync::Arc;
 
 // Relevant redistributor registers that we want to save/restore.
@@ -61,16 +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),
@@ -96,7 +95,8 @@ fn redist_attr_access(
         flags: 0,
     };
     if set {
-        gic.set_device_attr(&gic_dist_attr)
+        #[allow(clippy::unnecessary_mut_passed)]
+        gic.set_device_attr(&mut gic_dist_attr)
             .map_err(Error::SetDeviceAttribute)?;
     } else {
         gic.get_device_attr(&mut gic_dist_attr)
@@ -109,7 +109,7 @@ fn access_redists_aux(
     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<()> {
@@ -141,14 +141,14 @@ pub fn get_redist_regs(gic: &Arc<dyn hypervisor::Device>, gicr_typer: &[u64]) ->
     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)
 }
 
@@ -177,34 +177,3 @@ pub fn set_redist_regs(
         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 last = {
-            if index == vcpu_states.len() - 1 {
-                1
-            } else {
-                0
-            }
-        };
-        //calculate affinity
-        let mut cpu_affid = state.mpidr & 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

@@ -19,14 +19,15 @@
 // memory)   |                                                               |
 //           |                            DRAM                               |
 //           |                                                               |
+// 2GB       +---------------------------------------------------------------+
 //           |                                                               |
+//           |                           Reserved                            |
 //           |                                                               |
-// 1GB       +---------------------------------------------------------------+
+// 1G+256M   +---------------------------------------------------------------+
 //           |                                                               |
 //           |                        PCI MMCONFIG space                     |
 //           |                                                               |
-// 768 M     +---------------------------------------------------------------+
-//           |                                                               |
+// 1GB       +---------------------------------------------------------------+
 //           |                                                               |
 //           |                           PCI MMIO space                      |
 //           |                                                               |
@@ -35,10 +36,8 @@
 //           |                        Legacy devices space                   |
 //           |                                                               |
 // 144 M     +---------------------------------------------------------------|
-//           |                    Reserved (now GIC is here)                 |
-// 64  M     +---------------------------------------------------------------+
 //           |                                                               |
-//           |                          UEFI space                           |
+//           |                    Reserved (now GIC is here)                 |
 //           |                                                               |
 // 0GB       +---------------------------------------------------------------+
 //
@@ -46,76 +45,43 @@
 
 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: u64 = 0x0;
-pub const MEM_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.
 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: u64 = MAPPED_IO_START - GIC_V3_DIST_SIZE;
-/// Below 0x08ff_0000 is reserved for GICv3 Redistributor.
-/// The size defined here is for each vcpu.
-/// The total size is 'number_of_vcpu * GIC_V3_REDIST_SIZE'
-pub const GIC_V3_REDIST_SIZE: u64 = 0x02_0000;
-/// Below Redistributor area is GICv3 ITS
-pub const GIC_V3_ITS_SIZE: u64 = 0x02_0000;
-
-/// Space 0x0900_0000 ~ 0x0905_0000 is reserved for legacy devices.
+/// 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 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;
+/// Legacy space will be allocated at once whiling setting up legacy devices.
+pub const LEGACY_DEVICES_MAPPED_IO_SIZE: u64 = 0x0700_0000;
 
-/// 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 on 64 bit ARM.
-pub const RAM_64BIT_START: u64 = 0x4000_0000;
+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: u64 = RAM_64BIT_START;
 pub const FDT_MAX_SIZE: usize = 0x20_0000;
 
-/// Put ACPI table above dtb
-pub const ACPI_START: u64 = RAM_64BIT_START + FDT_MAX_SIZE as u64;
-pub const ACPI_MAX_SIZE: usize = 0x20_0000;
-pub const RSDP_POINTER: GuestAddress = GuestAddress(ACPI_START);
-
-/// Kernel start after FDT and ACPI
-pub const KERNEL_START: u64 = ACPI_START + ACPI_MAX_SIZE as u64;
-
-/// Pci high memory base
-pub const PCI_HIGH_BASE: u64 = 0x2_0000_0000_u64;
-
 // As per virt/kvm/arm/vgic/vgic-kvm-device.c we need
 // the number of interrupts our GIC will support to be:
 // * bigger than 32
 // * less than 1023 and
 // * a multiple of 32.
 // We are setting up our interrupt controller to support a maximum of 256 interrupts.
-/// First usable interrupt on aarch64
-pub const IRQ_BASE: u32 = 32;
+/// 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

@@ -10,27 +10,25 @@ pub mod gic;
 pub mod layout;
 /// 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 gic::GicDevice;
-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;
-use vm_memory::{Address, GuestAddress, GuestMemory, GuestUsize};
+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(gic::Error),
@@ -64,10 +62,16 @@ pub fn configure_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 {
-        regs::setup_regs(fd, id, kernel_entry_point.entry_addr.raw_value())
-            .map_err(Error::RegsConfiguration)?;
+        regs::setup_regs(
+            fd,
+            id,
+            kernel_entry_point.entry_addr.raw_value(),
+            &vm_memory.memory(),
+        )
+        .map_err(Error::RegsConfiguration)?;
     }
 
     let mpidr = fd.read_mpidr().map_err(Error::VcpuRegMpidr)?;
@@ -75,89 +79,64 @@ pub fn configure_vcpu(
 }
 
 pub fn arch_memory_regions(size: GuestUsize) -> Vec<(GuestAddress, usize, RegionType)> {
-    // Normally UEFI should be loaded to a flash area at the beginning of memory.
-    // But now flash memory type is not supported.
-    // As a workaround, we take 4 MiB memory from the main RAM for UEFI.
-    // As a result, the RAM that the guest can see is less than what has been
-    // assigned in command line, when ACPI and UEFI is enabled.
-    let ram_deduction = if cfg!(feature = "acpi") {
-        layout::UEFI_SIZE
-    } else {
-        0
-    };
-
     vec![
-        // 0 ~ 4 MiB: Reserved for UEFI space
-        #[cfg(feature = "acpi")]
-        (GuestAddress(0), layout::UEFI_SIZE as usize, RegionType::Ram),
-        #[cfg(not(feature = "acpi"))]
+        // 0 ~ 256 MiB: Reserved
         (
             GuestAddress(0),
-            layout::UEFI_SIZE as usize,
+            layout::MEM_32BIT_DEVICES_START.0 as usize,
             RegionType::Reserved,
         ),
-        // 4 MiB ~ 256 MiB: Gic and legacy devices
-        (
-            GuestAddress(layout::UEFI_SIZE),
-            (layout::MEM_32BIT_DEVICES_START.0 - layout::UEFI_SIZE) 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,
         ),
-        // 1 GiB ~ : Ram
         (
             GuestAddress(layout::RAM_64BIT_START),
-            (size - ram_deduction) as usize,
+            size as usize,
             RegionType::Ram,
         ),
     ]
 }
 
 /// 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: &dyn GicDevice,
-    numa_nodes: &NumaNodes,
-) -> 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,
+        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.
@@ -166,9 +145,8 @@ 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) {
@@ -183,31 +161,41 @@ pub fn initramfs_load_addr(
 
 /// Returns the memory address where the kernel could be loaded.
 pub fn get_kernel_start() -> u64 {
-    layout::KERNEL_START
-}
-
-///Return guest memory address where the uefi should be loaded.
-pub fn get_uefi_start() -> u64 {
-    layout::UEFI_START
+    layout::RAM_64BIT_START
 }
 
 // Auxiliary function to get the address where the device tree blob is loaded.
-fn get_fdt_addr() -> u64 {
-    layout::FDT_START
+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 {
-    // 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
-    }
+    // 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)]
@@ -217,9 +205,38 @@ mod tests {
     #[test]
     fn test_arch_memory_regions_dram() {
         let regions = arch_memory_regions((1usize << 32) as u64); //4GB
-        assert_eq!(5, regions.len());
-        assert_eq!(GuestAddress(layout::RAM_64BIT_START), regions[4].0);
-        assert_eq!(1usize << 32, regions[4].1);
-        assert_eq!(RegionType::Ram, regions[4].2);
+        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);
+    }
+
+    #[test]
+    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

@@ -12,6 +12,7 @@ use hypervisor::kvm::kvm_bindings::{
 use hypervisor::{arm64_core_reg_id, offset__of};
 use std::sync::Arc;
 use std::{mem, result};
+use vm_memory::GuestMemoryMmap;
 
 /// Errors thrown while setting aarch64 registers.
 #[derive(Debug)]
@@ -42,7 +43,12 @@ const PSTATE_FAULT_BITS_64: u64 = PSR_MODE_EL1h | PSR_A_BIT | PSR_F_BIT | PSR_I_
 /// * `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) -> Result<()> {
+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.
@@ -67,7 +73,7 @@ pub fn setup_regs(vcpu: &Arc<dyn hypervisor::Vcpu>, cpu_id: u8, boot_ip: u64) ->
         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() as u64,
+            get_fdt_addr(mem) as u64,
         )
         .map_err(Error::SetCoreRegister)?;
     }

arch/src/aarch64/uefi.rs

@@ -1,43 +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
-        .seek(SeekFrom::Start(0))
-        .map_err(|_| Error::SeekUefiStart)?;
-    guest_mem
-        .read_exact_from(guest_addr, uefi_image, uefi_size)
-        .map_err(|_| Error::ReadUefiImage)
-}

arch/src/lib.rs

@@ -6,24 +6,29 @@
 
 //! 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 std::collections::BTreeMap;
 use std::fmt;
 use std::result;
-use std::sync::Arc;
-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)]
@@ -58,7 +63,7 @@ pub enum Error {
 pub type Result<T> = result::Result<T, Error>;
 
 /// Type for memory region types.
-#[derive(Clone, Copy, PartialEq, Debug, Serialize, Deserialize, Versionize)]
+#[derive(PartialEq, Debug)]
 pub enum RegionType {
     /// RAM type
     Ram,
@@ -76,8 +81,6 @@ pub enum RegionType {
     Reserved,
 }
 
-impl VersionMapped for RegionType {}
-
 /// Module for aarch64 related functionality.
 #[cfg(target_arch = "aarch64")]
 pub mod aarch64;
@@ -85,8 +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, get_kernel_start, get_uefi_start, 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")]
@@ -94,9 +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)`.
@@ -107,19 +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
@@ -161,16 +151,6 @@ pub struct MmioDeviceInfo {
     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 {

arch/src/x86_64/interrupts.rs

@@ -12,6 +12,12 @@ 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.
@@ -95,4 +101,22 @@ mod tests {
         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

@@ -79,9 +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 ==
 
@@ -93,16 +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;
 
 // IOAPIC
 pub const IOAPIC_START: GuestAddress = GuestAddress(0xfec0_0000);
@@ -111,6 +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/mod.rs

@@ -9,47 +9,39 @@
 use std::sync::Arc;
 pub mod interrupts;
 pub mod layout;
-mod mpspec;
 mod mptable;
 pub mod regs;
-use crate::GuestMemoryMmap;
 use crate::InitramfsConfig;
 use crate::RegionType;
-use hypervisor::{CpuId, CpuIdEntry, HypervisorError, CPUID_FLAG_VALID_INDEX};
-use linux_loader::loader::bootparam::boot_params;
+use hypervisor::{CpuId, CpuIdEntry, CPUID_FLAG_VALID_INDEX};
+use linux_loader::loader::bootparam::{boot_params, setup_header};
 use linux_loader::loader::elf::start_info::{
     hvm_memmap_table_entry, hvm_modlist_entry, hvm_start_info,
 };
-use std::collections::BTreeMap;
 use std::mem;
 use vm_memory::{
     Address, ByteValued, Bytes, GuestAddress, GuestAddressSpace, GuestMemory, GuestMemoryAtomic,
-    GuestMemoryRegion, GuestUsize,
+    GuestMemoryMmap, GuestMemoryRegion, GuestUsize,
 };
 mod smbios;
 use std::arch::x86_64;
 #[cfg(feature = "tdx")]
 pub mod tdx;
 
-// CPUID feature bits
-const TSC_DEADLINE_TIMER_ECX_BIT: u8 = 24; // tsc deadline timer ecx bit.
-const HYPERVISOR_ECX_BIT: u8 = 31; // Hypervisor ecx bit.
-const MTRR_EDX_BIT: u8 = 12; // Hypervisor ecx bit.
+#[derive(Debug, Copy, Clone)]
+pub enum BootProtocol {
+    LinuxBoot,
+    PvhBoot,
+}
 
-// KVM feature bits
-const KVM_FEATURE_ASYNC_PF_INT_BIT: u8 = 14;
-#[cfg(feature = "tdx")]
-const KVM_FEATURE_CLOCKSOURCE_BIT: u8 = 0;
-#[cfg(feature = "tdx")]
-const KVM_FEATURE_CLOCKSOURCE2_BIT: u8 = 3;
-#[cfg(feature = "tdx")]
-const KVM_FEATURE_CLOCKSOURCE_STABLE_BIT: u8 = 24;
-#[cfg(feature = "tdx")]
-const KVM_FEATURE_ASYNC_PF_BIT: u8 = 4;
-#[cfg(feature = "tdx")]
-const KVM_FEATURE_ASYNC_PF_VMEXIT_BIT: u8 = 10;
-#[cfg(feature = "tdx")]
-const KVM_FEATURE_STEAL_TIME_BIT: u8 = 5;
+impl ::std::fmt::Display for BootProtocol {
+    fn fmt(&self, f: &mut ::std::fmt::Formatter) -> ::std::fmt::Result {
+        match self {
+            BootProtocol::LinuxBoot => write!(f, "Linux 64-bit boot protocol"),
+            BootProtocol::PvhBoot => write!(f, "PVH boot protocol"),
+        }
+    }
+}
 
 #[derive(Debug, Copy, Clone)]
 /// Specifies the entry point address where the guest must start
@@ -57,7 +49,11 @@ const KVM_FEATURE_STEAL_TIME_BIT: u8 = 5;
 /// is to be used to configure the guest initial state.
 pub struct EntryPoint {
     /// Address in guest memory where the guest must start execution
-    pub entry_addr: Option<GuestAddress>,
+    pub entry_addr: GuestAddress,
+    /// Specifies which boot protocol to use
+    pub protocol: BootProtocol,
+    /// This field is used for bzImage to fill zero page
+    pub setup_header: Option<setup_header>,
 }
 
 const E820_RAM: u32 = 1;
@@ -85,7 +81,7 @@ impl SgxEpcSection {
 pub struct SgxEpcRegion {
     start: GuestAddress,
     size: GuestUsize,
-    epc_sections: BTreeMap<String, SgxEpcSection>,
+    epc_sections: Vec<SgxEpcSection>,
 }
 
 impl SgxEpcRegion {
@@ -93,7 +89,7 @@ impl SgxEpcRegion {
         SgxEpcRegion {
             start,
             size,
-            epc_sections: BTreeMap::new(),
+            epc_sections: Vec::new(),
         }
     }
     pub fn start(&self) -> GuestAddress {
@@ -102,11 +98,11 @@ impl SgxEpcRegion {
     pub fn size(&self) -> GuestUsize {
         self.size
     }
-    pub fn epc_sections(&self) -> &BTreeMap<String, SgxEpcSection> {
+    pub fn epc_sections(&self) -> &Vec<SgxEpcSection> {
         &self.epc_sections
     }
-    pub fn insert(&mut self, id: String, epc_section: SgxEpcSection) {
-        self.epc_sections.insert(id, epc_section);
+    pub fn push(&mut self, epc_section: SgxEpcSection) {
+        self.epc_sections.push(epc_section);
     }
 }
 
@@ -118,15 +114,17 @@ impl SgxEpcRegion {
 #[derive(Copy, Clone, Default)]
 struct StartInfoWrapper(hvm_start_info);
 
+// It is safe to initialize StartInfoWrapper which is a wrapper over `hvm_start_info` (a series of ints).
+unsafe impl ByteValued for StartInfoWrapper {}
+
 #[derive(Copy, Clone, Default)]
 struct MemmapTableEntryWrapper(hvm_memmap_table_entry);
 
+unsafe impl ByteValued for MemmapTableEntryWrapper {}
+
 #[derive(Copy, Clone, Default)]
 struct ModlistEntryWrapper(hvm_modlist_entry);
 
-// SAFETY: These data structures only contain a series of integers
-unsafe impl ByteValued for StartInfoWrapper {}
-unsafe impl ByteValued for MemmapTableEntryWrapper {}
 unsafe impl ByteValued for ModlistEntryWrapper {}
 
 // This is a workaround to the Rust enforcement specifying that any implementation of a foreign
@@ -137,11 +135,14 @@ unsafe impl ByteValued for ModlistEntryWrapper {}
 #[derive(Copy, Clone, Default)]
 struct BootParamsWrapper(boot_params);
 
-// SAFETY: BootParamsWrap is a wrapper over `boot_params` (a series of ints).
+// It is safe to initialize BootParamsWrap which is a wrapper over `boot_params` (a series of ints).
 unsafe impl ByteValued for BootParamsWrapper {}
 
 #[derive(Debug)]
 pub enum Error {
+    /// Invalid e820 setup params.
+    E820Configuration,
+
     /// Error writing MP table to memory.
     MpTableSetup(mptable::Error),
 
@@ -174,18 +175,6 @@ pub enum Error {
 
     /// Missing SGX_LC CPU feature
     MissingSgxLaunchControlFeature,
-
-    /// Error getting supported CPUID through the hypervisor (kvm/mshv) API
-    CpuidGetSupported(HypervisorError),
-
-    /// Error populating CPUID with KVM HyperV emulation details
-    CpuidKvmHyperV(vmm_sys_util::fam::Error),
-
-    /// Error populating CPUID with CPU identification
-    CpuidIdentification(vmm_sys_util::fam::Error),
-
-    /// Error checking CPUID compatibility
-    CpuidCheckCompatibility,
 }
 
 impl From<Error> for super::Error {
@@ -195,7 +184,7 @@ impl From<Error> for super::Error {
 }
 
 #[allow(dead_code, clippy::upper_case_acronyms)]
-#[derive(Copy, Clone, Debug)]
+#[derive(Copy, Clone)]
 pub enum CpuidReg {
     EAX,
     EBX,
@@ -315,12 +304,21 @@ impl CpuidPatch {
 
         for entry in entries.iter() {
             if entry.function == function && entry.index == index {
-                let reg_val = match reg {
-                    CpuidReg::EAX => entry.eax,
-                    CpuidReg::EBX => entry.ebx,
-                    CpuidReg::ECX => entry.ecx,
-                    CpuidReg::EDX => entry.edx,
-                };
+                let reg_val: u32;
+                match reg {
+                    CpuidReg::EAX => {
+                        reg_val = entry.eax;
+                    }
+                    CpuidReg::EBX => {
+                        reg_val = entry.ebx;
+                    }
+                    CpuidReg::ECX => {
+                        reg_val = entry.ecx;
+                    }
+                    CpuidReg::EDX => {
+                        reg_val = entry.edx;
+                    }
+                }
 
                 return (reg_val & mask) == mask;
             }
@@ -330,381 +328,6 @@ impl CpuidPatch {
     }
 }
 
-#[derive(Debug)]
-enum CpuidCompatibleCheck {
-    BitwiseSubset, // bitwise subset
-    Equal,         // equal in value
-    NumNotGreater, // smaller or equal as a number
-}
-
-pub struct CpuidFeatureEntry {
-    function: u32,
-    index: u32,
-    feature_reg: CpuidReg,
-    compatible_check: CpuidCompatibleCheck,
-}
-
-impl CpuidFeatureEntry {
-    fn checked_feature_entry_list() -> Vec<CpuidFeatureEntry> {
-        vec![
-            // The following list includes all hardware features bits from
-            // the CPUID Wiki Page: https://en.wikipedia.org/wiki/CPUID
-            // Leaf 0x1, ECX/EDX, feature bits
-            CpuidFeatureEntry {
-                function: 1,
-                index: 0,
-                feature_reg: CpuidReg::ECX,
-                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
-            },
-            CpuidFeatureEntry {
-                function: 1,
-                index: 0,
-                feature_reg: CpuidReg::EDX,
-                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
-            },
-            // Leaf 0x7, EAX/EBX/ECX/EDX, extended features
-            CpuidFeatureEntry {
-                function: 7,
-                index: 0,
-                feature_reg: CpuidReg::EAX,
-                compatible_check: CpuidCompatibleCheck::NumNotGreater,
-            },
-            CpuidFeatureEntry {
-                function: 7,
-                index: 0,
-                feature_reg: CpuidReg::EBX,
-                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
-            },
-            CpuidFeatureEntry {
-                function: 7,
-                index: 0,
-                feature_reg: CpuidReg::ECX,
-                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
-            },
-            CpuidFeatureEntry {
-                function: 7,
-                index: 0,
-                feature_reg: CpuidReg::EDX,
-                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
-            },
-            // Leaf 0x7 subleaf 0x1, EAX, extended features
-            CpuidFeatureEntry {
-                function: 7,
-                index: 1,
-                feature_reg: CpuidReg::EAX,
-                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
-            },
-            // Leaf 0x8000_0001, ECX/EDX, CPUID features bits
-            CpuidFeatureEntry {
-                function: 0x8000_0001,
-                index: 0,
-                feature_reg: CpuidReg::ECX,
-                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
-            },
-            CpuidFeatureEntry {
-                function: 0x8000_0001,
-                index: 0,
-                feature_reg: CpuidReg::EDX,
-                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
-            },
-            // KVM CPUID bits: https://www.kernel.org/doc/html/latest/virt/kvm/cpuid.html
-            // Leaf 0x4000_0000, EAX/EBX/ECX/EDX, KVM CPUID SIGNATURE
-            CpuidFeatureEntry {
-                function: 0x4000_0000,
-                index: 0,
-                feature_reg: CpuidReg::EAX,
-                compatible_check: CpuidCompatibleCheck::NumNotGreater,
-            },
-            CpuidFeatureEntry {
-                function: 0x4000_0000,
-                index: 0,
-                feature_reg: CpuidReg::EBX,
-                compatible_check: CpuidCompatibleCheck::Equal,
-            },
-            CpuidFeatureEntry {
-                function: 0x4000_0000,
-                index: 0,
-                feature_reg: CpuidReg::ECX,
-                compatible_check: CpuidCompatibleCheck::Equal,
-            },
-            CpuidFeatureEntry {
-                function: 0x4000_0000,
-                index: 0,
-                feature_reg: CpuidReg::EDX,
-                compatible_check: CpuidCompatibleCheck::Equal,
-            },
-            // Leaf 0x4000_0001, EAX/EBX/ECX/EDX, KVM CPUID features
-            CpuidFeatureEntry {
-                function: 0x4000_0001,
-                index: 0,
-                feature_reg: CpuidReg::EAX,
-                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
-            },
-            CpuidFeatureEntry {
-                function: 0x4000_0001,
-                index: 0,
-                feature_reg: CpuidReg::EBX,
-                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
-            },
-            CpuidFeatureEntry {
-                function: 0x4000_0001,
-                index: 0,
-                feature_reg: CpuidReg::ECX,
-                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
-            },
-            CpuidFeatureEntry {
-                function: 0x4000_0001,
-                index: 0,
-                feature_reg: CpuidReg::EDX,
-                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
-            },
-        ]
-    }
-
-    fn get_features_from_cpuid(
-        cpuid: &CpuId,
-        feature_entry_list: &[CpuidFeatureEntry],
-    ) -> Vec<u32> {
-        let mut features = vec![0; feature_entry_list.len()];
-        for (i, feature_entry) in feature_entry_list.iter().enumerate() {
-            for cpuid_entry in cpuid.as_slice().iter() {
-                if cpuid_entry.function == feature_entry.function
-                    && cpuid_entry.index == feature_entry.index
-                {
-                    match feature_entry.feature_reg {
-                        CpuidReg::EAX => {
-                            features[i] = cpuid_entry.eax;
-                        }
-                        CpuidReg::EBX => {
-                            features[i] = cpuid_entry.ebx;
-                        }
-                        CpuidReg::ECX => {
-                            features[i] = cpuid_entry.ecx;
-                        }
-                        CpuidReg::EDX => {
-                            features[i] = cpuid_entry.edx;
-                        }
-                    }
-
-                    break;
-                }
-            }
-        }
-
-        features
-    }
-
-    // The function returns `Error` (a.k.a. "incompatible"), when the CPUID features from `src_vm_cpuid`
-    // is not a subset of those of the `dest_vm_cpuid`.
-    pub fn check_cpuid_compatibility(
-        src_vm_cpuid: &CpuId,
-        dest_vm_cpuid: &CpuId,
-    ) -> Result<(), Error> {
-        let feature_entry_list = &Self::checked_feature_entry_list();
-        let src_vm_features = Self::get_features_from_cpuid(src_vm_cpuid, feature_entry_list);
-        let dest_vm_features = Self::get_features_from_cpuid(dest_vm_cpuid, feature_entry_list);
-
-        // Loop on feature bit and check if the 'source vm' feature is a subset
-        // of those of the 'destination vm' feature
-        let mut compatible = true;
-        for (i, (src_vm_feature, dest_vm_feature)) in src_vm_features
-            .iter()
-            .zip(dest_vm_features.iter())
-            .enumerate()
-        {
-            let entry = &feature_entry_list[i];
-            let entry_compatible = match entry.compatible_check {
-                CpuidCompatibleCheck::BitwiseSubset => {
-                    let different_feature_bits = src_vm_feature ^ dest_vm_feature;
-                    let src_vm_feature_bits_only = different_feature_bits & src_vm_feature;
-                    src_vm_feature_bits_only == 0
-                }
-                CpuidCompatibleCheck::Equal => src_vm_feature == dest_vm_feature,
-                CpuidCompatibleCheck::NumNotGreater => src_vm_feature <= dest_vm_feature,
-            };
-            if !entry_compatible {
-                error!(
-                    "Detected incompatible CPUID entry: leaf={:#02x} (subleaf={:#02x}), register='{:?}', \
-                    compatilbe_check='{:?}', source VM feature='{:#04x}', destination VM feature'{:#04x}'.",
-                    entry.function, entry.index, entry.feature_reg,
-                    entry.compatible_check, src_vm_feature, dest_vm_feature
-                    );
-
-                compatible = false;
-            }
-        }
-
-        if compatible {
-            info!("No CPU incompatibility detected.");
-            Ok(())
-        } else {
-            Err(Error::CpuidCheckCompatibility)
-        }
-    }
-}
-
-pub fn generate_common_cpuid(
-    hypervisor: Arc<dyn hypervisor::Hypervisor>,
-    topology: Option<(u8, u8, u8)>,
-    sgx_epc_sections: Option<Vec<SgxEpcSection>>,
-    phys_bits: u8,
-    kvm_hyperv: bool,
-    #[cfg(feature = "tdx")] tdx_enabled: bool,
-) -> super::Result<CpuId> {
-    let cpuid_patches = vec![
-        // Patch tsc deadline timer bit
-        CpuidPatch {
-            function: 1,
-            index: 0,
-            flags_bit: None,
-            eax_bit: None,
-            ebx_bit: None,
-            ecx_bit: Some(TSC_DEADLINE_TIMER_ECX_BIT),
-            edx_bit: None,
-        },
-        // Patch hypervisor bit
-        CpuidPatch {
-            function: 1,
-            index: 0,
-            flags_bit: None,
-            eax_bit: None,
-            ebx_bit: None,
-            ecx_bit: Some(HYPERVISOR_ECX_BIT),
-            edx_bit: None,
-        },
-        // Enable MTRR feature
-        CpuidPatch {
-            function: 1,
-            index: 0,
-            flags_bit: None,
-            eax_bit: None,
-            ebx_bit: None,
-            ecx_bit: None,
-            edx_bit: Some(MTRR_EDX_BIT),
-        },
-    ];
-
-    // Supported CPUID
-    let mut cpuid = hypervisor.get_cpuid().map_err(Error::CpuidGetSupported)?;
-
-    CpuidPatch::patch_cpuid(&mut cpuid, cpuid_patches);
-
-    if let Some(t) = topology {
-        update_cpuid_topology(&mut cpuid, t.0, t.1, t.2);
-    }
-
-    if let Some(sgx_epc_sections) = sgx_epc_sections {
-        update_cpuid_sgx(&mut cpuid, sgx_epc_sections)?;
-    }
-
-    // Update some existing CPUID
-    for entry in cpuid.as_mut_slice().iter_mut() {
-        match entry.function {
-            // Set CPU physical bits
-            0x8000_0008 => {
-                entry.eax = (entry.eax & 0xffff_ff00) | (phys_bits as u32 & 0xff);
-            }
-            // Disable KVM_FEATURE_ASYNC_PF_INT
-            // This is required until we find out why the asynchronous page
-            // fault is generating unexpected behavior when using interrupt
-            // mechanism.
-            // TODO: Re-enable KVM_FEATURE_ASYNC_PF_INT (#2277)
-            0x4000_0001 => {
-                entry.eax &= !(1 << KVM_FEATURE_ASYNC_PF_INT_BIT);
-
-                // These features are not supported by TDX
-                #[cfg(feature = "tdx")]
-                if tdx_enabled {
-                    entry.eax &= !(1 << KVM_FEATURE_CLOCKSOURCE_BIT
-                        | 1 << KVM_FEATURE_CLOCKSOURCE2_BIT
-                        | 1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT
-                        | 1 << KVM_FEATURE_ASYNC_PF_BIT
-                        | 1 << KVM_FEATURE_ASYNC_PF_VMEXIT_BIT
-                        | 1 << KVM_FEATURE_STEAL_TIME_BIT)
-                }
-            }
-            _ => {}
-        }
-    }
-
-    // Copy CPU identification string
-    for i in 0x8000_0002..=0x8000_0004 {
-        cpuid.retain(|c| c.function != i);
-        let leaf = unsafe { std::arch::x86_64::__cpuid(i) };
-        cpuid
-            .push(CpuIdEntry {
-                function: i,
-                eax: leaf.eax,
-                ebx: leaf.ebx,
-                ecx: leaf.ecx,
-                edx: leaf.edx,
-                ..Default::default()
-            })
-            .map_err(Error::CpuidIdentification)?;
-    }
-
-    if kvm_hyperv {
-        // Remove conflicting entries
-        cpuid.retain(|c| c.function != 0x4000_0000);
-        cpuid.retain(|c| c.function != 0x4000_0001);
-        // See "Hypervisor Top Level Functional Specification" for details
-        // Compliance with "Hv#1" requires leaves up to 0x4000_000a
-        cpuid
-            .push(CpuIdEntry {
-                function: 0x40000000,
-                eax: 0x4000000a, // Maximum cpuid leaf
-                ebx: 0x756e694c, // "Linu"
-                ecx: 0x564b2078, // "x KV"
-                edx: 0x7648204d, // "M Hv"
-                ..Default::default()
-            })
-            .map_err(Error::CpuidKvmHyperV)?;
-        cpuid
-            .push(CpuIdEntry {
-                function: 0x40000001,
-                eax: 0x31237648, // "Hv#1"
-                ..Default::default()
-            })
-            .map_err(Error::CpuidKvmHyperV)?;
-        cpuid
-            .push(CpuIdEntry {
-                function: 0x40000002,
-                eax: 0x3839,  // "Build number"
-                ebx: 0xa0000, // "Version"
-                ..Default::default()
-            })
-            .map_err(Error::CpuidKvmHyperV)?;
-        cpuid
-            .push(CpuIdEntry {
-                function: 0x4000_0003,
-                eax: 1 << 1 // AccessPartitionReferenceCounter
-                   | 1 << 2 // AccessSynicRegs
-                   | 1 << 3 // AccessSyntheticTimerRegs
-                   | 1 << 9, // AccessPartitionReferenceTsc
-                edx: 1 << 3, // CPU dynamic partitioning
-                ..Default::default()
-            })
-            .map_err(Error::CpuidKvmHyperV)?;
-        cpuid
-            .push(CpuIdEntry {
-                function: 0x4000_0004,
-                eax: 1 << 5, // Recommend relaxed timing
-                ..Default::default()
-            })
-            .map_err(Error::CpuidKvmHyperV)?;
-        for i in 0x4000_0005..=0x4000_000a {
-            cpuid
-                .push(CpuIdEntry {
-                    function: i,
-                    ..Default::default()
-                })
-                .map_err(Error::CpuidKvmHyperV)?;
-        }
-    }
-
-    Ok(cpuid)
-}
-
 pub fn configure_vcpu(
     fd: &Arc<dyn hypervisor::Vcpu>,
     id: u8,
@@ -713,7 +336,7 @@ pub fn configure_vcpu(
     cpuid: CpuId,
     kvm_hyperv: bool,
 ) -> super::Result<()> {
-    // Per vCPU CPUID changes; common are handled via generate_common_cpuid()
+    // Per vCPU CPUID changes; common are handled via CpuManager::generate_common_cpuid()
     let mut cpuid = cpuid;
     CpuidPatch::set_cpuid_reg(&mut cpuid, 0xb, None, CpuidReg::EDX, u32::from(id));
     CpuidPatch::set_cpuid_reg(&mut cpuid, 0x1f, None, CpuidReg::EDX, u32::from(id));
@@ -727,12 +350,18 @@ pub fn configure_vcpu(
 
     regs::setup_msrs(fd).map_err(Error::MsrsConfiguration)?;
     if let Some(kernel_entry_point) = kernel_entry_point {
-        if let Some(entry_addr) = kernel_entry_point.entry_addr {
-            // Safe to unwrap because this method is called after the VM is configured
-            regs::setup_regs(fd, entry_addr.raw_value()).map_err(Error::RegsConfiguration)?;
-            regs::setup_fpu(fd).map_err(Error::FpuConfiguration)?;
-            regs::setup_sregs(&vm_memory.memory(), fd).map_err(Error::SregsConfiguration)?;
-        }
+        // Safe to unwrap because this method is called after the VM is configured
+        regs::setup_regs(
+            fd,
+            kernel_entry_point.entry_addr.raw_value(),
+            layout::BOOT_STACK_POINTER.raw_value(),
+            layout::ZERO_PAGE_START.raw_value(),
+            kernel_entry_point.protocol,
+        )
+        .map_err(Error::RegsConfiguration)?;
+        regs::setup_fpu(fd).map_err(Error::FpuConfiguration)?;
+        regs::setup_sregs(&vm_memory.memory(), fd, kernel_entry_point.protocol)
+            .map_err(Error::SregsConfiguration)?;
     }
     interrupts::set_lint(fd).map_err(|e| Error::LocalIntConfiguration(e.into()))?;
     Ok(())
@@ -797,9 +426,12 @@ pub fn arch_memory_regions(size: GuestUsize) -> Vec<(GuestAddress, usize, Region
 pub fn configure_system(
     guest_mem: &GuestMemoryMmap,
     cmdline_addr: GuestAddress,
+    cmdline_size: usize,
     initramfs: &Option<InitramfsConfig>,
     _num_cpus: u8,
+    setup_hdr: Option<setup_header>,
     rsdp_addr: Option<GuestAddress>,
+    boot_prot: BootProtocol,
     sgx_epc_region: Option<SgxEpcRegion>,
 ) -> super::Result<()> {
     let size = smbios::setup_smbios(guest_mem).map_err(Error::SmbiosSetup)?;
@@ -816,13 +448,31 @@ pub fn configure_system(
         }
     }
 
-    configure_pvh(
-        guest_mem,
-        cmdline_addr,
-        initramfs,
-        rsdp_addr,
-        sgx_epc_region,
-    )
+    match boot_prot {
+        BootProtocol::PvhBoot => {
+            configure_pvh(
+                guest_mem,
+                cmdline_addr,
+                initramfs,
+                rsdp_addr,
+                sgx_epc_region,
+            )?;
+        }
+        BootProtocol::LinuxBoot => {
+            error!("Using deprecated LinuxBoot protocol: Please configure your kernel with CONFIG_PVH=y and supply the `vmlinux` file to `--kernel`");
+            configure_64bit_boot(
+                guest_mem,
+                cmdline_addr,
+                cmdline_size,
+                initramfs,
+                setup_hdr,
+                rsdp_addr,
+                sgx_epc_region,
+            )?;
+        }
+    }
+
+    Ok(())
 }
 
 fn configure_pvh(
@@ -965,6 +615,121 @@ fn add_memmap_entry(memmap: &mut Vec<hvm_memmap_table_entry>, addr: u64, size: u
     });
 }
 
+fn configure_64bit_boot(
+    guest_mem: &GuestMemoryMmap,
+    cmdline_addr: GuestAddress,
+    cmdline_size: usize,
+    initramfs: &Option<InitramfsConfig>,
+    setup_hdr: Option<setup_header>,
+    rsdp_addr: Option<GuestAddress>,
+    sgx_epc_region: Option<SgxEpcRegion>,
+) -> super::Result<()> {
+    const KERNEL_BOOT_FLAG_MAGIC: u16 = 0xaa55;
+    const KERNEL_HDR_MAGIC: u32 = 0x53726448;
+    const KERNEL_LOADER_OTHER: u8 = 0xff;
+    const KERNEL_MIN_ALIGNMENT_BYTES: u32 = 0x1000000; // Must be non-zero.
+
+    let mut params: BootParamsWrapper = BootParamsWrapper(boot_params::default());
+
+    if let Some(hdr) = setup_hdr {
+        // We should use the header if the loader provides one (e.g. from a bzImage).
+        params.0.hdr = hdr;
+    } else {
+        params.0.hdr.boot_flag = KERNEL_BOOT_FLAG_MAGIC;
+        params.0.hdr.header = KERNEL_HDR_MAGIC;
+        params.0.hdr.kernel_alignment = KERNEL_MIN_ALIGNMENT_BYTES;
+    };
+
+    // Common bootparams settings
+    if params.0.hdr.type_of_loader == 0 {
+        params.0.hdr.type_of_loader = KERNEL_LOADER_OTHER;
+    }
+    params.0.hdr.cmd_line_ptr = cmdline_addr.raw_value() as u32;
+    params.0.hdr.cmdline_size = cmdline_size as u32;
+
+    if let Some(initramfs_config) = initramfs {
+        params.0.hdr.ramdisk_image = initramfs_config.address.raw_value() as u32;
+        params.0.hdr.ramdisk_size = initramfs_config.size as u32;
+    }
+
+    add_e820_entry(&mut params.0, 0, layout::EBDA_START.raw_value(), E820_RAM)?;
+
+    let mem_end = guest_mem.last_addr();
+    if mem_end < layout::MEM_32BIT_RESERVED_START {
+        add_e820_entry(
+            &mut params.0,
+            layout::HIGH_RAM_START.raw_value(),
+            mem_end.unchecked_offset_from(layout::HIGH_RAM_START) + 1,
+            E820_RAM,
+        )?;
+    } else {
+        add_e820_entry(
+            &mut params.0,
+            layout::HIGH_RAM_START.raw_value(),
+            layout::MEM_32BIT_RESERVED_START.unchecked_offset_from(layout::HIGH_RAM_START),
+            E820_RAM,
+        )?;
+        if mem_end > layout::RAM_64BIT_START {
+            add_e820_entry(
+                &mut params.0,
+                layout::RAM_64BIT_START.raw_value(),
+                mem_end.unchecked_offset_from(layout::RAM_64BIT_START) + 1,
+                E820_RAM,
+            )?;
+        }
+    }
+
+    add_e820_entry(
+        &mut params.0,
+        layout::PCI_MMCONFIG_START.0,
+        layout::PCI_MMCONFIG_SIZE,
+        E820_RESERVED,
+    )?;
+
+    if let Some(sgx_epc_region) = sgx_epc_region {
+        add_e820_entry(
+            &mut params.0,
+            sgx_epc_region.start().raw_value(),
+            sgx_epc_region.size() as u64,
+            E820_RESERVED,
+        )?;
+    }
+
+    if let Some(rsdp_addr) = rsdp_addr {
+        params.0.acpi_rsdp_addr = rsdp_addr.0;
+    }
+
+    let zero_page_addr = layout::ZERO_PAGE_START;
+    guest_mem
+        .checked_offset(zero_page_addr, mem::size_of::<boot_params>())
+        .ok_or(super::Error::ZeroPagePastRamEnd)?;
+    guest_mem
+        .write_obj(params, zero_page_addr)
+        .map_err(super::Error::ZeroPageSetup)?;
+
+    Ok(())
+}
+
+/// Add an e820 region to the e820 map.
+/// Returns Ok(()) if successful, or an error if there is no space left in the map.
+fn add_e820_entry(
+    params: &mut boot_params,
+    addr: u64,
+    size: u64,
+    mem_type: u32,
+) -> Result<(), Error> {
+    if params.e820_entries >= params.e820_table.len() as u8 {
+        return Err(Error::E820Configuration);
+    }
+
+    params.e820_table[params.e820_entries as usize].addr = addr;
+    params.e820_table[params.e820_entries as usize].size = size;
+    params.e820_table[params.e820_entries as usize].type_ = mem_type;
+    params.e820_entries += 1;
+
+    Ok(())
+}
+
 /// Returns the memory address where the initramfs could be loaded.
 pub fn initramfs_load_addr(
     guest_mem: &GuestMemoryMmap,
@@ -1011,7 +776,7 @@ pub fn get_host_cpu_phys_bits() -> u8 {
     }
 }
 
-fn update_cpuid_topology(
+pub fn update_cpuid_topology(
     cpuid: &mut CpuId,
     threads_per_core: u8,
     cores_per_die: u8,
@@ -1076,7 +841,7 @@ fn update_cpuid_topology(
 
 // The goal is to update the CPUID sub-leaves to reflect the number of EPC
 // sections exposed to the guest.
-fn update_cpuid_sgx(cpuid: &mut CpuId, epc_sections: Vec<SgxEpcSection>) -> Result<(), Error> {
+pub fn update_cpuid_sgx(cpuid: &mut CpuId, epc_sections: Vec<SgxEpcSection>) -> Result<(), Error> {
     // Something's wrong if there's no EPC section.
     if epc_sections.is_empty() {
         return Err(Error::NoSgxEpcSection);
@@ -1123,6 +888,7 @@ fn update_cpuid_sgx(cpuid: &mut CpuId, epc_sections: Vec<SgxEpcSection>) -> Resu
 #[cfg(test)]
 mod tests {
     use super::*;
+    use linux_loader::loader::bootparam::boot_e820_entry;
 
     #[test]
     fn regions_lt_4gb() {
@@ -1147,9 +913,12 @@ mod tests {
         let config_err = configure_system(
             &gm,
             GuestAddress(0),
+            0,
             &None,
             1,
+            None,
             Some(layout::RSDP_POINTER),
+            BootProtocol::LinuxBoot,
             None,
         );
         assert!(config_err.is_err());
@@ -1163,8 +932,31 @@ mod tests {
             .map(|r| (r.0, r.1))
             .collect();
         let gm = GuestMemoryMmap::from_ranges(&ram_regions).unwrap();
+        configure_system(
+            &gm,
+            GuestAddress(0),
+            0,
+            &None,
+            no_vcpus,
+            None,
+            None,
+            BootProtocol::LinuxBoot,
+            None,
+        )
+        .unwrap();
 
-        configure_system(&gm, GuestAddress(0), &None, no_vcpus, None, None).unwrap();
+        configure_system(
+            &gm,
+            GuestAddress(0),
+            0,
+            &None,
+            no_vcpus,
+            None,
+            None,
+            BootProtocol::PvhBoot,
+            None,
+        )
+        .unwrap();
 
         // Now assigning some memory that is equal to the start of the 32bit memory hole.
         let mem_size = 3328 << 20;
@@ -1175,9 +967,31 @@ mod tests {
             .map(|r| (r.0, r.1))
             .collect();
         let gm = GuestMemoryMmap::from_ranges(&ram_regions).unwrap();
-        configure_system(&gm, GuestAddress(0), &None, no_vcpus, None, None).unwrap();
+        configure_system(
+            &gm,
+            GuestAddress(0),
+            0,
+            &None,
+            no_vcpus,
+            None,
+            None,
+            BootProtocol::LinuxBoot,
+            None,
+        )
+        .unwrap();
 
-        configure_system(&gm, GuestAddress(0), &None, no_vcpus, None, None).unwrap();
+        configure_system(
+            &gm,
+            GuestAddress(0),
+            0,
+            &None,
+            no_vcpus,
+            None,
+            None,
+            BootProtocol::PvhBoot,
+            None,
+        )
+        .unwrap();
 
         // Now assigning some memory that falls after the 32bit memory hole.
         let mem_size = 3330 << 20;
@@ -1188,9 +1002,71 @@ mod tests {
             .map(|r| (r.0, r.1))
             .collect();
         let gm = GuestMemoryMmap::from_ranges(&ram_regions).unwrap();
-        configure_system(&gm, GuestAddress(0), &None, no_vcpus, None, None).unwrap();
+        configure_system(
+            &gm,
+            GuestAddress(0),
+            0,
+            &None,
+            no_vcpus,
+            None,
+            None,
+            BootProtocol::LinuxBoot,
+            None,
+        )
+        .unwrap();
 
-        configure_system(&gm, GuestAddress(0), &None, no_vcpus, None, None).unwrap();
+        configure_system(
+            &gm,
+            GuestAddress(0),
+            0,
+            &None,
+            no_vcpus,
+            None,
+            None,
+            BootProtocol::PvhBoot,
+            None,
+        )
+        .unwrap();
+    }
+
+    #[test]
+    fn test_add_e820_entry() {
+        let e820_table = [(boot_e820_entry {
+            addr: 0x1,
+            size: 4,
+            type_: 1,
+        }); 128];
+
+        let expected_params = boot_params {
+            e820_table,
+            e820_entries: 1,
+            ..Default::default()
+        };
+
+        let mut params: boot_params = Default::default();
+        add_e820_entry(
+            &mut params,
+            e820_table[0].addr,
+            e820_table[0].size,
+            e820_table[0].type_,
+        )
+        .unwrap();
+        assert_eq!(
+            format!("{:?}", params.e820_table[0]),
+            format!("{:?}", expected_params.e820_table[0])
+        );
+        assert_eq!(params.e820_entries, expected_params.e820_entries);
+
+        // Exercise the scenario where the field storing the length of the e820 entry table is
+        // is bigger than the allocated memory.
+        params.e820_entries = params.e820_table.len() as u8 + 1;
+        assert!(add_e820_entry(
+            &mut params,
+            e820_table[0].addr,
+            e820_table[0].size,
+            e820_table[0].type_
+        )
+        .is_err());
     }
 
     #[test]

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 {

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 std::sync::Arc;
+use std::{mem, result};
+
+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 std::sync::Arc;
-use std::{mem, result};
-use vm_memory::{Address, Bytes, GuestMemory, GuestMemoryError};
+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 {
@@ -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 as usize] = {
-        // 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

@@ -6,14 +6,13 @@
 //
 // 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 vm_memory::ByteValued;
-use vm_memory::{Address, Bytes, GuestAddress};
+use vm_memory::{Address, Bytes, GuestAddress, GuestMemoryMmap};
 
 #[allow(unused_variables)]
 #[derive(Debug)]
@@ -82,6 +81,7 @@ pub struct Smbios30Entrypoint {
     pub max_size: u32,
     pub physptr: u64,
 }
+unsafe impl ByteValued for Smbios30Entrypoint {}
 
 impl Clone for Smbios30Entrypoint {
     fn clone(&self) -> Self {
@@ -111,6 +111,8 @@ impl Clone for SmbiosBiosInfo {
     }
 }
 
+unsafe impl ByteValued for SmbiosBiosInfo {}
+
 #[repr(packed)]
 #[derive(Default, Copy)]
 pub struct SmbiosSysInfo {
@@ -133,9 +135,6 @@ impl Clone for SmbiosSysInfo {
     }
 }
 
-// SAFETY: These data structures only contain a series of integers
-unsafe impl ByteValued for Smbios30Entrypoint {}
-unsafe impl ByteValued for SmbiosBiosInfo {}
 unsafe impl ByteValued for SmbiosSysInfo {}
 
 fn write_and_incr<T: ByteValued>(

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,
@@ -61,57 +59,6 @@ impl Default for TdvfSectionType {
     }
 }
 
-#[repr(C)]
-#[derive(Clone, Copy, Default, Debug)]
-pub struct TdVmmDataRegion {
-    pub start_address: u64,
-    pub length: u64,
-    pub region_type: TdVmmDataRegionType,
-}
-
-#[repr(u16)]
-#[derive(Clone, Copy, Debug)]
-pub enum TdVmmDataRegionType {
-    Signature = 0x0000,
-    InterfaceVersion = 0x0001,
-    SystemUuid = 0x0002,
-    RamSize = 0x0003,
-    GraphicsEnabled = 0x0004,
-    SmpCpuCount = 0x0005,
-    MachineId = 0x0006,
-    KernelAddress = 0x0007,
-    KernelSize = 0x0008,
-    KernelCommandLine = 0x0009,
-    InitrdAddress = 0x000a,
-    InitrdSize = 0x000b,
-    BootDevice = 0x000c,
-    NumaData = 0x000d,
-    BootMenu = 0x000e,
-    MaximumCpuCount = 0x000f,
-    KernelEntry = 0x0010,
-    KernelData = 0x0011,
-    InitrdData = 0x0012,
-    CommandLineAddress = 0x0013,
-    CommandLineSize = 0x0014,
-    CommandLineData = 0x0015,
-    KernelSetupAddress = 0x0016,
-    KernelSetupSize = 0x0017,
-    KernelSetupData = 0x0018,
-    FileDir = 0x0019,
-    AcpiTables = 0x8000,
-    SmbiosTables = 0x8001,
-    Irq0Override = 0x8002,
-    E820Table = 0x8003,
-    HpetData = 0x8004,
-    Reserved = 0xffff,
-}
-
-impl Default for TdVmmDataRegionType {
-    fn default() -> Self {
-        TdVmmDataRegionType::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.
@@ -127,7 +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(
@@ -172,7 +119,6 @@ pub fn parse_tdvf_sections(file: &mut File) -> Result<Vec<TdvfSection>, TdvfErro
 enum HobType {
     Handoff = 0x1,
     ResourceDescriptor = 0x3,
-    GuidExtension = 0x4,
     Unused = 0xfffe,
     EndOfHobList = 0xffff,
 }
@@ -190,19 +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)]
@@ -223,28 +170,7 @@ struct HobResourceDescriptor {
     physical_start: u64,
     resource_length: u64,
 }
-
-#[repr(C)]
-#[derive(Copy, Clone, Default, Debug)]
-struct HobGuidType {
-    header: HobHeader,
-    name: EfiGuid,
-}
-
-#[repr(C)]
-#[derive(Copy, Clone, Default, Debug)]
-struct TdVmmData {
-    guid_type: HobGuidType,
-    region: TdVmmDataRegion,
-}
-
-// SAFETY: These data structures only contain a series of integers
-unsafe impl ByteValued for TdVmmDataRegion {}
-unsafe impl ByteValued for HobHeader {}
-unsafe impl ByteValued for HobHandoffInfoTable {}
 unsafe impl ByteValued for HobResourceDescriptor {}
-unsafe impl ByteValued for HobGuidType {}
-unsafe impl ByteValued for TdVmmData {}
 
 pub struct TdHob {
     start_offset: u64,
@@ -291,7 +217,6 @@ impl TdHob {
                 reserved: 0,
             },
             version: 0x9,
-            boot_mode: 0,
             efi_memory_top: 0,
             efi_memory_bottom: 0,
             efi_free_memory_top: 0,
@@ -351,10 +276,10 @@ impl TdHob {
             },
             /* TODO:
              * QEMU currently fills it in like this:
-             * EFI_RESOURCE_ATTRIBUTE_PRESENT | EFI_RESOURCE_ATTRIBUTE_INITIALIZED | EFI_RESOURCE_ATTRIBUTE_ENCRYPTED | EFI_RESOURCE_ATTRIBUTE_TESTED
+             * EFI_RESOURCE_ATTRIBUTE_PRESENT | EFI_RESOURCE_ATTRIBUTE_INITIALIZED | EFI_RESOURCE_ATTRIBUTE_TESTED
              * which differs from the spec (due to TDVF implementation issue?)
              */
-            0x04000007,
+            0x7,
         )
     }
 
@@ -375,38 +300,6 @@ impl TdHob {
             0x403,
         )
     }
-
-    pub fn add_td_vmm_data(
-        &mut self,
-        mem: &GuestMemoryMmap,
-        region: TdVmmDataRegion,
-    ) -> Result<(), TdvfError> {
-        let td_vmm_data = TdVmmData {
-            guid_type: HobGuidType {
-                header: HobHeader {
-                    r#type: HobType::GuidExtension,
-                    length: std::mem::size_of::<TdVmmData>() as u16,
-                    reserved: 0,
-                },
-                // TD_VMM_DATA_GUID CF2643E4-C0D3-46FF-0000-72EE623DDE38
-                name: EfiGuid {
-                    data1: 0xcf26_43e4,
-                    data2: 0xc0d3,
-                    data3: 0x46ff,
-                    data4: [0x00, 0x00, 0x72, 0xee, 0x62, 0x3d, 0xde, 0x38],
-                },
-            },
-            region,
-        };
-        info!(
-            "Writing HOB TD_VMM_DATA {:x} {:x?}",
-            self.current_offset, td_vmm_data
-        );
-        mem.write_obj(td_vmm_data, GuestAddress(self.current_offset))
-            .map_err(TdvfError::GuestMemoryWriteHob)?;
-        self.update_offset::<TdVmmData>();
-        Ok(())
-    }
 }
 
 #[cfg(test)]

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

@@ -6,19 +6,19 @@ edition = "2018"
 
 [features]
 default = []
+io_uring = []
 
 [dependencies]
-io-uring = "0.5.2"
-libc = "0.2.112"
+io-uring = ">=0.4.0"
+libc = "0.2.91"
 log = "0.4.14"
 qcow = { path = "../qcow" }
-thiserror = "1.0.30"
-versionize = "0.1.6"
-versionize_derive = "0.1.4"
-vhdx = { path = "../vhdx" }
-virtio-bindings = { version = "0.1.0", features = ["virtio-v5_0_0"] }
-virtio-queue = { path = "../virtio-queue" }
-vm-memory = { version = "0.7.0", 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 = "0.9.0"
+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_expr, 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 + 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)]

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;
@@ -18,31 +20,26 @@ 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::MutexGuard;
-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_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;
 
@@ -113,8 +110,6 @@ pub enum ExecuteError {
     AsyncRead(AsyncIoError),
     AsyncWrite(AsyncIoError),
     AsyncFlush(AsyncIoError),
-    /// Failed allocating a temporary buffer.
-    TemporaryBufferAllocation(io::Error),
 }
 
 impl ExecuteError {
@@ -131,7 +126,6 @@ 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,
         }
     }
 }
@@ -169,14 +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,
@@ -184,38 +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>>,
+        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 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);
@@ -240,9 +217,9 @@ impl Request {
                 if !desc.is_write_only() && req.request_type == RequestType::GetDeviceId {
                     return Err(Error::UnexpectedReadOnlyDescriptor);
                 }
-                req.data_descriptors.push((desc.addr(), 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);
@@ -257,21 +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();
+        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)?;
@@ -306,7 +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)),
@@ -316,7 +294,7 @@ impl Request {
     }
 
     pub fn execute_async(
-        &mut self,
+        &self,
         mem: &GuestMemoryMmap,
         disk_nsectors: u64,
         disk_image: &mut dyn AsyncIo,
@@ -329,9 +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;
@@ -343,52 +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);
@@ -397,12 +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)?;
@@ -436,42 +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,
@@ -494,7 +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,
@@ -502,12 +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:";
 
@@ -523,6 +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.
@@ -555,109 +553,128 @@ pub fn block_io_uring_is_supported() -> bool {
     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> {
@@ -676,8 +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();
-
-        Ok(file.seek(SeekFrom::End(0)).map_err(DiskFileError::Size)? as u64)
+        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;
@@ -35,15 +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};
@@ -31,15 +31,6 @@ impl DiskFile for RawFileDiskSync {
     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 {

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()
-    }
-}

devices/Cargo.toml

@@ -2,23 +2,22 @@
 name = "devices"
 version = "0.1.0"
 authors = ["The Chromium OS Authors"]
-edition = "2018"
 
 [dependencies]
-acpi_tables = { path = "../acpi_tables", optional = true }
-anyhow = "1.0.52"
-arch = { path = "../arch" }
-bitflags = "1.3.2"
+anyhow = "1.0"
+bitflags = ">=1.2.1"
 byteorder = "1.4.3"
-epoll = "4.3.1"
-libc = "0.2.112"
+epoll = ">=4.0.1"
+libc = "0.2.91"
 log = "0.4.14"
-versionize = "0.1.6"
-versionize_derive = "0.1.4"
+serde = {version = ">=1.0.27", features = ["rc"] }
+serde_derive = ">=1.0.27"
+serde_json = ">=1.0.9"
 vm-device = { path = "../vm-device" }
-vm-memory = "0.7.0"
+acpi_tables = { path = "../acpi_tables", optional = true }
+vm-memory = "0.5.0"
 vm-migration = { path = "../vm-migration" }
-vmm-sys-util = "0.9.0"
+vmm-sys-util = ">=0.3.1"
 
 [features]
 default = []

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 {
@@ -104,7 +107,7 @@ 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_.GED_".into(),
             vec![
@@ -151,7 +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(
@@ -165,7 +168,7 @@ impl Aml for AcpiGedDevice {
                 ),
             ],
         )
-        .append_aml_bytes(bytes)
+        .to_aml_bytes()
     }
 }
 
@@ -189,10 +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

@@ -3,10 +3,8 @@
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
 use super::interrupt_controller::{Error, InterruptController};
-extern crate arch;
-use arch::aarch64::gic::GicDevice;
 use std::result;
-use std::sync::{Arc, Mutex};
+use std::sync::Arc;
 use vm_device::interrupt::{
     InterruptIndex, InterruptManager, InterruptSourceConfig, InterruptSourceGroup,
     LegacyIrqSourceConfig, MsiIrqGroupConfig,
@@ -16,7 +14,7 @@ use vmm_sys_util::eventfd::EventFd;
 type Result<T> = result::Result<T, Error>;
 
 // Reserve 32 IRQs for legacy device.
-pub const IRQ_LEGACY_BASE: usize = arch::layout::IRQ_BASE as usize;
+pub const IRQ_LEGACY_BASE: usize = 0;
 pub const IRQ_LEGACY_COUNT: usize = 32;
 
 // This Gic struct implements InterruptController to provide interrupt delivery service.
@@ -26,8 +24,7 @@ pub const IRQ_LEGACY_COUNT: usize = 32;
 //   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>,
-    gic_device: Option<Arc<Mutex<Box<dyn GicDevice>>>>,
+    interrupt_source_group: Arc<Box<dyn InterruptSourceGroup>>,
 }
 
 impl Gic {
@@ -44,17 +41,8 @@ impl Gic {
 
         Ok(Gic {
             interrupt_source_group,
-            gic_device: None,
         })
     }
-
-    pub fn set_gic_device(&mut self, gic_device: Arc<Mutex<Box<dyn GicDevice>>>) {
-        self.gic_device = Some(gic_device);
-    }
-
-    pub fn get_gic_device(&self) -> Option<&Arc<Mutex<Box<dyn GicDevice>>>> {
-        self.gic_device.as_ref()
-    }
 }
 
 impl InterruptController for Gic {
@@ -70,7 +58,7 @@ 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(

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)?;
@@ -429,18 +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 +2,12 @@
 // 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;
 
-// 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;
 const DATA_OFFSET: u64 = 0x1;
@@ -51,14 +47,13 @@ impl Cmos {
 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] & INDEX_MASK,
             DATA_OFFSET => self.data[self.index as usize] = data[0],
-            o => warn!("bad write offset on CMOS device: {}", o),
+            o => panic!("bad write offset on CMOS device: {}", o),
         };
         None
     }
@@ -70,7 +65,6 @@ impl BusDevice for Cmos {
         }
 
         if data.len() != 1 {
-            warn!("Invalid read size on CMOS device: {}", data.len());
             return;
         }
 
@@ -91,8 +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 _);
@@ -121,9 +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.
@@ -131,10 +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/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
@@ -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"
+        )))
     }
 }
 
@@ -376,14 +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);
@@ -391,8 +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);
@@ -400,7 +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);
@@ -408,7 +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);
@@ -416,7 +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);
@@ -425,12 +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();
@@ -443,14 +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/rtc_pl031.rs

@@ -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);
             }
@@ -449,12 +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);
@@ -463,7 +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);
 
@@ -475,7 +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);
@@ -484,14 +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);
@@ -503,7 +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);
@@ -511,7 +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
     }
@@ -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"
+        )))
     }
 }
 
@@ -381,7 +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()),
         );
 
@@ -401,7 +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),
         );
 
@@ -438,7 +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
@@ -460,7 +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]);
@@ -481,7 +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]);
@@ -507,7 +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

@@ -7,16 +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::{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 */
@@ -86,11 +86,11 @@ 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>>,
 }
 
-#[derive(Versionize)]
+#[derive(Serialize, Deserialize)]
 pub struct Pl011State {
     flags: u32,
     lcr: u32,
@@ -99,7 +99,7 @@ pub struct Pl011State {
     dmacr: u32,
     int_enabled: u32,
     int_level: u32,
-    read_fifo: Vec<u8>,
+    read_fifo: VecDeque<u8>,
     ilpr: u32,
     ibrd: u32,
     fbrd: u32,
@@ -108,13 +108,11 @@ 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>>,
     ) -> Self {
         Self {
@@ -138,10 +136,6 @@ impl Pl011 {
         }
     }
 
-    pub fn set_out(&mut self, out: Box<dyn io::Write + Send>) {
-        self.out = Some(out);
-    }
-
     fn state(&self) -> Pl011State {
         Pl011State {
             flags: self.flags,
@@ -151,7 +145,7 @@ impl Pl011 {
             dmacr: self.dmacr,
             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,
@@ -169,7 +163,7 @@ impl Pl011 {
         self.dmacr = state.dmacr;
         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;
@@ -196,13 +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;
@@ -294,15 +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;
                     }
@@ -313,7 +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,
@@ -332,7 +324,7 @@ impl BusDevice for Pl011 {
                     0
                 }
             }
-        };
+        }
 
         if read_ok && data.len() <= 4 {
             write_le_u32(data, v);
@@ -347,7 +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);
             }
@@ -369,12 +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"
+        )))
     }
 }
 
@@ -446,7 +464,7 @@ 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())),
         );
 
@@ -466,7 +484,7 @@ 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)),
         );
 

devices/src/lib.rs

@@ -6,11 +6,24 @@
 // 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;

docs/api.md

@@ -78,29 +78,27 @@ Shut the VMM down                   | `/vmm.shutdown` | N/A          | N/A
 
 #### 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
-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 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
 

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/cpu.md

@@ -1,189 +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>>,
-}
-```
-
-```
---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>
-```
-
-### `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.

docs/custom-image.md

@@ -72,13 +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

docs/device_model.md

@@ -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

@@ -12,7 +12,7 @@ This virtual device relies on the _vhost-user_ protocol, which assumes the backe
 
 _Build virtiofsd_
 ```bash
-git clone --depth 1 "https://gitlab.com/virtio-fs/qemu.git" -b "qemu5.0-virtiofs-dax" $VIRTIOFSD_DIR
+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`
@@ -35,42 +35,45 @@ The `cache=none` option should be the default when using `virtiofsd` with the __
 
 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.
 
-### Kernel support
+### The kernel
 
-Modern Linux kernels starting (at least v5.10) have support for virtio-fs. Use
-of older kernels, with additional patches, are not supported.
+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.
+
+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.
 
-Direct kernel boot is the preferred option, but we can boot from an EFI cloud image if it contains a recent enough kernel.
+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.
 
-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 must specify `shared=on` to share the memory pages so that an external process can access them.
+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.
 
-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
 ```
 
 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
---fs tag=myfs,socket=/tmp/virtiofs,num_queues=1,queue_size=512,dax=on,cache_size=4G
+--fs tag=virtiofs,socket=/tmp/virtiofs,num_queues=1,queue_size=512,dax=on,cache_size=4G
 
 ```
 
 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.
 
 ```bash
---fs tag=myfs,socket=/tmp/virtiofs,num_queues=1,queue_size=512,dax=off
+--fs tag=virtiofs,socket=/tmp/virtiofs,num_queues=1,queue_size=512,dax=off
 
 ```
 

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/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

@@ -1,75 +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).
-
-## 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 the TDVF 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).
-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. Assuming the guest kernel
-command line contains `console=hvc0` (printing to the `virtio-console` device),
-run Cloud Hypervisor as follows:
-
-```bash
-./cloud-hypervisor \
-    --tdx 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 (assuming the
-guest kernel command line contains `console=ttyS0`):
-
-```bash
-./cloud-hypervisor \
-    --tdx firmware=edk2-staging/Build/OvmfCh/DEBUG_GCC5/FV/OVMF.fd \
-    --cpus boot=1 \
-    --memory size=1G \
-    --disk path=tdx_guest_img \
-    --serial tty \
-    --console off
-```

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.
@@ -32,8 +29,8 @@ 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.
@@ -227,7 +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
 ```

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

@@ -1,31 +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,
+    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" [default: size=512M]
+--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`
@@ -60,6 +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.
@@ -105,72 +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.
-
-_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.
-
-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
-```
-
 ## Advanced Parameters
 
 `MemoryZoneConfig` or what is known as `--memory-zone` from the CLI perspective
@@ -184,16 +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
@@ -281,30 +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.
-
 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`
@@ -371,30 +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
@@ -404,16 +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`
@@ -446,20 +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`
@@ -476,10 +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.
@@ -487,7 +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`
@@ -504,46 +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

@@ -2,7 +2,7 @@
 
 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
+## 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.
 
@@ -23,7 +23,7 @@ Use one `--net` command-line argument from cloud-hypervisor to specify the emula
 
 ```bash
 ./cloud-hypervisor \
-    --cpus boot=4 \
+    --cpus 4 \
     --memory "size=512M" \
     --disk path=focal-server-cloudimg-amd64.raw \
     --kernel my-vmlinux.bin \
@@ -34,14 +34,14 @@ Use one `--net` command-line argument from cloud-hypervisor to specify the emula
 
 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      |
+| 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.
 
@@ -104,7 +104,6 @@ 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
@@ -117,7 +116,6 @@ On the hypervisor host add the network gateway IP address of each network to the
 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
@@ -129,10 +127,9 @@ Destination     Gateway         Genmask         Flags Metric Ref    Use Iface
 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.
+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
@@ -168,7 +165,7 @@ 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.
+permitted by applicable law.                                                         
 
 
 Last login: Fri Jul 12 13:27:56 2019 from 192.168.4.1
@@ -192,7 +189,7 @@ 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
+root@guest:~# nslookup  ftp.nl.debian.org       
 Server:         192.168.178.1
 Address:        192.168.178.1#53
 

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
 

docs/snapshot_restore.md

@@ -11,16 +11,16 @@ before the snapshot was performed.
 This feature is important for the project as it establishes the first step
 towards the support for live migration.
 
-## Snapshot a Cloud Hypervisor VM
+## Snapshot a Cloud-Hypervisor VM
 
-First thing, we must run 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
 ```
@@ -54,7 +54,7 @@ drwxr-xr-x 47 foo bar       4096 Jul 22 11:47 ../
 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
+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.
@@ -65,7 +65,7 @@ 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.
 
-## 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 

docs/uefi.md

@@ -17,7 +17,7 @@ cd edk2
 . edksetup.sh
 git submodule update --init
 
-echo "ACTIVE_PLATFORM=OvmfPkg/CloudHv/CloudHvX64.dsc" >> Conf/target.txt
+echo "ACTIVE_PLATFORM=OvmfPkg/OvmfCh.dsc" >> Conf/target.txt
 echo "TARGET_ARCH=X64" >> Conf/target.txt
 echo "TOOL_CHAIN_TAG=GCC5" >> Conf/target.txt
 
@@ -25,16 +25,48 @@ make -C ./BaseTools
 build
 ```
 
-After the successful build, the resulting firmware binaries are available under `Build/CloudHvX64/DEBUG_GCC5/FV` underneath the edk2 checkout.
+After the successful build, the resulting firmware binaries are available under `Build/OvmfCh/DEBUG_GCC5/FV` underneath the edk2 checkout.
 
 ## Using OVMF Binaries
 
 Any UEFI capable image can be booted using the Cloud Hypervisor specific firmware. Windows guests under Cloud Hypervisor only support UEFI boot, therefore OVMF is mandatory there.
 
-To make Cloud Hypervisor use UEFI boot, pass the `CLOUDHV.fd` file path as an argument to the `--kernel` option. The firmware file will be opened in read only mode.
+To make Cloud Hypervisor use UEFI boot, pass the `OVMF.fd` file path as an argument to the `--kernel` option. The firmware file will be opened in read only mode.
 
 The same firmware can be used with Cloud Hypervisor or with QEMU. This is particularly useful if using QEMU for the preparation phase.
 
+## Building UEFI Firmware with Compatibility Support Module (CSM)
+
+CSM is a module that allows to boot legacy operating systems using the OVMF firmware. OVMF can embed a CSM build of SeaBIOS. To build the SeaBIOS with CSM support, add `CONFIG_CSM=y` to `.config` before the build. The outcome `out/Csm16.bin` is to be moved into `OvmfPkg/Csm/Csm16/Csm16.bin` before OVMF is built. Then, the OVMF build will have to be passed the `-D CSM_ENABLE` option in order to generate a legacy aware UEFI firmware. At the current stage, all the necessary patches are included in the Cloud Hypervisor specific [SeaBIOS branch](https://github.com/cloud-hypervisor/seabios/tree/ch). Taking into account the previous instructions, the modified command sequence to compile an OVMF binary with CSM support is the following one:
+
+```shell
+sudo apt-get update
+sudo apt-get install uuid-dev nasm iasl build-essential python3-distutils git
+
+git checkout https://github.com/cloud-hypervisor/seabios -b ch
+cd seabios
+make menuconfig
+# Enable `CONFIG_CSM` and `CONFIG_QEMU_HARDWARE`
+make CONFIG_CSM=y CONFIG_QEMU_HARDWARE=y
+cd ..
+
+git clone https://github.com/cloud-hypervisor/edk2 -b ch
+cd edk2
+. edksetup.sh
+git submodule update --init
+cp ../seabios/out/Csm16.bin OvmfPkg/Csm/Csm16/
+
+echo "ACTIVE_PLATFORM=OvmfPkg/OvmfCh.dsc" >> Conf/target.txt
+echo "TARGET_ARCH=X64" >> Conf/target.txt
+echo "TOOL_CHAIN_TAG=GCC5" >> Conf/target.txt
+
+make -C ./BaseTools
+build
+
+```
+
+Please note, that the CSM support has currently only been tested with Linux guests. There are no plans to provide legacy support for other OSes (e.g. Windows).
+
 # Links
 
 - [OVMF wiki](https://github.com/tianocore/tianocore.github.io/wiki/OVMF) 

docs/vfio-user.md

@@ -1,79 +0,0 @@
-# Cloud Hypervisor VFIO-user HOWTO
-
-VFIO-user is an *experimental* protocol for allowing devices to be implemented in another process and communicate over a socket; ie.e VFIO-user is to VFIO as virtio is to vhost-user.
-
-The protocol is documented here: https://github.com/nutanix/libvfio-user/blob/master/docs/vfio-user.rst
-
-The Cloud Hypervisor support for such devices is *experimental*. Not all Cloud Hypervisor functionality is supported in particular: virtio-mem and iommu are not supported.
-
-## Usage
-
-The `--user-device socket=<path>` parameter is used to create a vfio-user device when creating the VM specifying the socket to connect to. The device can also be hotplugged with `ch-remote add-user-device socket=<path>`.
-
-## Example (GPIO device)
-
-There is a simple GPIO device included in the libvfio-user repository: https://github.com/nutanix/libvfio-user#gpio
-
-Run the example from the libvfio-user repository:
-
-```sh
-rm /tmp/vfio-user.sock
-./build/dbg/samples/gpio-pci-idio-16 -v /tmp/vfio-user.sock &
-```
-
-Start Cloud Hypervisor:
-
-```sh
-target/debug/cloud-hypervisor \
-    --memory size=1G,shared=on \
-    --disk path=~/images/focal-server-cloudimg-amd64.raw \
-    --kernel ~/src/linux/vmlinux \
-    --cmdline "root=/dev/vda1 console=hvc0" \
-    --user-device socket=/tmp/vfio-user.sock 
-```
-
-Inside the VM you can test the device with:
-
-```sh
-cat /sys/class/gpio/gpiochip480/base > /sys/class/gpio/export
-for ((i=0;i<12;i++)); do cat /sys/class/gpio/OUT0/value; done
-```
-
-## Example (NVMe device)
-
-Use SPDK: https://github.com/spdk/spdk
-
-Compile with `./configure --with-vfio-user`
-
-Create an NVMe controller listening on a vfio-user socket with a simple AIO block device in spdk.
-More details of configuring SPDK bdev can be viewed in [SPDK bdev](https://spdk.io/doc/bdev.html).
-More details of setting SPDK NVMe-oF target can be viewed in [SDPK NVMe-oF tgt](https://spdk.io/doc/nvmf.html).
-
-```sh
-sudo scripts/setup.sh
-rm ~/images/test-disk.raw
-truncate ~/images/test-disk.raw -s 128M
-mkfs.ext4  ~/images/test-disk.raw
-sudo killall ./build/bin/nvmf_tgt
-sudo ./build/bin/nvmf_tgt -i 0 -e 0xFFFF -m 0x1 &
-sleep 2
-sudo ./scripts/rpc.py nvmf_create_transport -t VFIOUSER
-sudo rm -rf /tmp/nvme-vfio-user
-sudo mkdir -p /tmp/nvme-vfio-user
-sudo ./scripts/rpc.py bdev_aio_create ~/images/test-disk.raw test 512
-sudo ./scripts/rpc.py nvmf_create_subsystem nqn.2019-07.io.spdk:cnode -a -s test
-sudo ./scripts/rpc.py nvmf_subsystem_add_ns nqn.2019-07.io.spdk:cnode test
-sudo ./scripts/rpc.py nvmf_subsystem_add_listener nqn.2019-07.io.spdk:cnode -t VFIOUSER -a /tmp/nvme-vfio-user -s 0
-sudo chown $USER.$USER -R /tmp/nvme-vfio-user
-```
-
-Start Cloud Hypervisor:
-
-```sh
-target/debug/cloud-hypervisor \
-    --memory size=1G,shared=on \
-    --disk path=~/images/focal-server-cloudimg-amd64.raw \
-    --kernel ~/src/linux/vmlinux \
-    --cmdline "root=/dev/vda1 console=hvc0" \
-    --user-device socket=/tmp/nvme-vfio-user/cntrl 
-```

docs/vfio.md

@@ -11,7 +11,7 @@ by the VFIO kernel drivers. However, by default, a host device will be bound to
 its native driver, which is not the VFIO one.
 
 As a consequence, a device must be unbound from its native driver before passing
-it to `cloud-hypervisor` for assigning it to a guest.
+it to `cloud-hypervisor` for assigning it to a guess.
 
 ### Example
 
@@ -36,22 +36,14 @@ Now that we have identified the device, we must unbind it from its native driver
 First we add VFIO support to the host:
 
 ```
-# modprobe -r vfio_pci
-# modprobe -r vfio_iommu_type1
-# modprobe vfio_iommu_type1 allow_unsafe_interrupts
-# modprobe vfio_pci
-```
-
-In case the VFIO drivers are built-in, enable unsafe interrupts with:
-
-```
-# echo 1 > /sys/module/vfio_iommu_type1/parameters/allow_unsafe_interrupts
+$ sudo modprobe vfio_pci
+$ sudo modprobe vfio_iommu_type1 allow_unsafe_interrupts
 ```
 
 Then we unbind it from its native driver:
 
 ```
-# echo 0000:01:00.0 > /sys/bus/pci/devices/0000\:01\:00.0/driver/unbind
+$ echo 0000:01:00.0 > /sys/bus/pci/devices/0000\:01\:00.0/driver/unbind
 ```
 
 And finally we bind it to the VFIO driver. To do that we first need to get the
@@ -61,14 +53,7 @@ device's VID (Vendor ID) and PID (Product ID):
 $ lspci -n -s 01:00.0
 01:00.0 ff00: 10ec:525a (rev 01)
 
-# echo 10ec 525a > /sys/bus/pci/drivers/vfio-pci/new_id
-```
-
-If you have more than one device with the same `vendorID`/`deviceID`, starting
-with the second device, the binding is performed as follows:
-
-```
-# echo 0000:02:00.0 > /sys/bus/pci/drivers/vfio-pci/bind
+$ echo 10ec 525a > /sys/bus/pci/drivers/vfio-pci/new_id
 ```
 
 Now the device is managed by the VFIO framework.
@@ -93,33 +78,3 @@ takes the device's sysfs path as an argument. In our example it is
 The guest kernel will then detect the card reader on its PCI bus and provided
 that support for this device is enabled, it will probe and enable it for the
 guest to use.
-
-In case you want to pass multiple devices, here is the correct syntax:
-
-```
---device path=/sys/bus/pci/devices/0000:01:00.0/ path=/sys/bus/pci/devices/0000:02:00.0/
-```
-
-### Multiple devices in the same IOMMU group
-
-There are cases where multiple devices can be found under the same IOMMU group.
-This happens often with graphics card embedding an audio controller.
-
-```
-$ lspci
-[...]
-01:00.0 VGA compatible controller: NVIDIA Corporation GK208B [GeForce GT 710] (rev a1)
-01:00.1 Audio device: NVIDIA Corporation GK208 HDMI/DP Audio Controller (rev a1)
-[...]
-```
-
-This is usually exposed as follows through `sysfs`:
-
-```
-$ ls /sys/kernel/iommu_groups/22/devices/
-0000:01:00.0  0000:01:00.1
-```
-
-This means these two devices are under the same IOMMU group 22. In such case,
-it is important to bind both devices to VFIO and pass them both through the
-VM, otherwise this could cause some functional and security issues.

docs/vhost-user-blk-testing.md

@@ -35,56 +35,38 @@ Here are some good references for detailing them.
 
 ## Test environment
 
-The below test environment is based on Ubuntu release (20.04.1 LTS), as for other system, please check related documents.
-This test runs with multiple queue (MQ) support enabled, using 4 queues defined for both SPDK and the virtual machine.
-Here are the detailed instructions.
+The below test environment is based on ubuntu release(16.04.1 LTS), as for other system, please check related document.
+The test runs with multiple queue (MQ) support enabled, using 4 queues defined for both SPDK and the virtual machine.
+Here are the details on how the test can be run.
 
-### The hugepages settings on the host
-Allocate enough persistent huge pages (e.g. 2GiB) on the host:
-
-```bash
-# Assume the default hugepage size is 2MiB
-echo 1024 | sudo tee /proc/sys/vm/nr_hugepages
-# Confirm the value of "Hugepagesize" and "HugePages_Total"
-cat /proc/meminfo | grep -i huge
-```
+### The hugepages settings in host linux
+Add "default_hugepagesz=1G hugepagesz=1G hugepages=2" into host linux cmdline.
+As for how to change Ubuntu linux cmdline in grub file, please ref below link:
+https://www.ostechnix.com/configure-grub-2-boot-loader-settings-ubuntu-16-04/
+reboot Ubuntu
+sudo mount -t hugetlbfs -o pagesize=1G none /dev/hugepages
 
 ### Download the SPDK code
-```bash
 git clone https://github.com/spdk/spdk
 cd spdk
 git submodule update --init
-```
 
 ### Create the build dep
-
-```bash
 ./scripts/pkgdep.sh
-```
 
-### Build SPDK
-```bash
+### Build spdk
 ./configure
 make
-```
 
-### Set the SPDK environment
-
-Run SPDK vhost target with 2 CPU cores, i.e., core 0 and 1.
-```bash
+### Set the SPDk environment
 sudo HUGEMEM=2048 scripts/setup.sh
-sudo ./build/bin/vhost -S /var/tmp -s 1024 -m 0x3 &
-```
+sudo ./app/vhost/vhost -S /var/tmp -s 1024 -m 0x3 &
 
 ### Create 512M block device
-
-Create a 512M (first parameter) block device with 512 bytes (second parameter) block size.
-```bash
 sudo scripts/rpc.py bdev_malloc_create 512 512 -b Malloc0
 sudo scripts/rpc.py vhost_create_blk_controller --cpumask 0x1 vhost.1 Malloc0
-```
 
-### Launch the VM
+_Launch the VM_
 
 VMs run in client mode. They connect to the socket created by the `dpdkvhostuser` in the SPDK backend.
 ```bash
@@ -107,9 +89,9 @@ login in guest
 # Use lsblk command to find out vhost-user-blk device
 lsblk
 NAME    MAJ:MIN RM  SIZE RO TYPE MOUNTPOINT
-vda     252:0    0  2.2G  0 disk
+vda     252:0    0  2.2G  0 disk 
 ├─vda1  252:1    0  2.1G  0 part /
-├─vda14 252:14   0    4M  0 part
+├─vda14 252:14   0    4M  0 part 
 └─vda15 252:15   0  106M  0 part /boot/efi
 vdb    253:16   0  512M  0 disk
 

docs/vhost-user-net-testing.md

@@ -1,30 +1,27 @@
 # How to test Vhost-user net with OpenVSwitch/DPDK
 
-The purpose of this document is to illustrate how to test vhost-user-net
-in cloud-hypervisor with OVS/DPDK as the backend. This document was
-tested with Open vSwitch v2.13.1, DPDK v19.11.3, and Cloud Hypervisor
-v15.0 on Ubuntu 20.04.1 (host kernel v5.4.0).
+The purpose of this document is to illustrate how to test vhost-user-net in cloud-hypervisor with OVS/DPDK as the backend.
 
 ## Framework
 
 It's a simple test to validate the communication between two virtual machine, connecting them to vhost-user ports respectively provided by `OVS/DPDK`.
 ```
-             +----+----------+          +-------------+-----------+-------------+          +----------+----+
-             |    |          |          |             |           |             |          |          |    |
-             |    |vhost-user|----------| vhost-user  |   ovs     | vhost-user  |----------|vhost-user|    |
-             |    |net device|          | port 1      |           | port 2      |          |net device|    |
-             |    |          |          |             |           |             |          |          |    |
-             |    +----------+          +-------------+-----------+-------------+          +----------+    |
-             |               |          |                                       |          |               |
-             |vm1            |          |                  dpdk                 |          |           vm2 |
-             |               |          |                                       |          |               |
-          +--+---------------------------------------------------------------------------------------------+--+
-          |  |                                       hugepages                                             |  |
-          |  +---------------------------------------------------------------------------------------------+  |
-          |                                                                                                   |
-          |                                              host                                                 |
-          |                                                                                                   |
-          +---------------------------------------------------------------------------------------------------+
+             +----+----------+          +-------------+-----------+-------------+          +----------+----+  
+             |    |          |          |             |           |             |          |          |    | 
+             |    |vhost-user|----------| vhost-user  |   ovs     | vhost-user  |----------|vhost-user|    |           
+             |    |net device|          | port 1      |           | port 2      |          |net device|    |           
+             |    |          |          |             |           |             |          |          |    |           
+             |    +----------+          +-------------+-----------+-------------+          +----------+    |           
+             |               |          |                                       |          |               |           
+             |vm1            |          |                  dpdk                 |          |           vm2 |           
+             |               |          |                                       |          |               |           
+          +--+---------------------------------------------------------------------------------------------+--+        
+          |  |                                       hugepages                                             |  |        
+          |  +---------------------------------------------------------------------------------------------+  |        
+          |                                                                                                   |        
+          |                                              host                                                 |        
+          |                                                                                                   |  
+          +---------------------------------------------------------------------------------------------------+        
 ```
 ## Prerequisites
 
@@ -33,54 +30,44 @@ Prior to running the test, the following steps need to be performed.
 - Install DPDK
 - Install OVS
 
-Here is a good reference for setting up OVS with DPDK from scratch:
-https://docs.openvswitch.org/en/latest/intro/install/dpdk/.
+Here are some good references for detailing them.
+- Red Hat
+	* https://wiki.qemu.org/Documentation/vhost-user-ovs-dpdk
+- Ubuntu server
+	* https://help.ubuntu.com/lts/serverguide/DPDK.html
+	* https://software.intel.com/en-us/articles/set-up-open-vswitch-with-dpdk-on-ubuntu-server
 
-On Ubuntu systems (18.04 or newer), the OpenVswitch-DPDK package can be
-easily installed with:
-```bash
-sudo apt-get update
-sudo apt-get install openvswitch-switch-dpdk
-sudo update-alternatives --set ovs-vswitchd /usr/lib/openvswitch-switch-dpdk/ovs-vswitchd-dpdk
-```
 ## Test
-The test runs with multiple queue (MQ) support enabled, using 2 pairs of
-TX/RX queues defined for both OVS and the virtual machine. Here are the
-detailed instructions.
+The test runs with multiple queue (MQ) support enabled, using 2 pairs of TX/RX queues defined for both OVS and the virtual machine. Here are the details on how the test can be run.
 
 _Setup OVS_
 
-Here is an example how to configure a basic OpenVswitch using DPDK:
+`ovs_test.sh` is created to setup and start OVS. OVS will provide the `dpdkvhostuser` backend running in server mode.
 ```bash
-# load the ovs kernel module
+mkdir -p /var/run/openvswitch
 modprobe openvswitch
-sudo service openvswitch-switch start
-ovs-vsctl init
-ovs-vsctl set Open_vSwitch . other_config:dpdk-init=true
-# run on core 0-3 only
-ovs-vsctl set Open_vSwitch . other_config:dpdk-lcore-mask=0xf
-# allocate 2G huge pages (to NUMA 0 only)
-ovs-vsctl set Open_vSwitch . other_config:dpdk-socket-mem=1024
-# run PMD (Pull Mode Driver) threads on core 0-3 only
-ovs-vsctl set Open_vSwitch . other_config:pmd-cpu-mask=0xf
-sudo service openvswitch-switch restart
-# double check the configurations
-ovs-vsctl list Open_vSwitch
-```
-
-Here is an example how to create a bridge and add two DPDK ports to it
-(for later use via Cloud Hypervisor):
-```bash
-# create a bridge
+killall ovsdb-server ovs-vswitchd
+rm -f /var/run/openvswitch/vhost-user*
+rm -f /etc/openvswitch/conf.db
+export DB_SOCK=/var/run/openvswitch/db.sock
+ovsdb-tool create /etc/openvswitch/conf.db /usr/share/openvswitch/vswitch.ovsschema
+ovsdb-server --remote=punix:$DB_SOCK --remote=db:Open_vSwitch,Open_vSwitch,manager_options --pidfile --detach
+ovs-vsctl --no-wait init
+ovs-vsctl --no-wait set Open_vSwitch . other_config:dpdk-lcore-mask=0xf
+ovs-vsctl --no-wait set Open_vSwitch . other_config:dpdk-socket-mem=1024
+ovs-vsctl --no-wait set Open_vSwitch . other_config:dpdk-init=true
+ovs-vsctl --no-wait set Open_vSwitch . other_config:pmd-cpu-mask=0xf
+ovs-vswitchd unix:$DB_SOCK --pidfile --detach --log-file=/var/log/openvswitch/ovs-vswitchd.log
 ovs-vsctl add-br ovsbr0 -- set bridge ovsbr0 datapath_type=netdev
-# create two DPDK ports and add them to the bridge
 ovs-vsctl add-port ovsbr0 vhost-user1 -- set Interface vhost-user1 type=dpdkvhostuser
-ovs-vsctl add-port ovsbr0 vhost-user2 -- set Interface vhost-user2
-type=dpdkvhostuser
-# set the number of rx queues
+ovs-vsctl add-port ovsbr0 vhost-user2 -- set Interface vhost-user2 type=dpdkvhostuser
 ovs-vsctl set Interface vhost-user1 options:n_rxq=2
 ovs-vsctl set Interface vhost-user2 options:n_rxq=2
 ```
+_Run ovs_test.sh_
+```bash
+./ovs_test.sh
+```
 
 _Launch the VMs_
 
@@ -102,21 +89,19 @@ VMs run in client mode. They connect to the socket created by the `dpdkvhostuser
         --kernel vmlinux \
         --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw" \
         --disk path=focal-server-cloudimg-amd64.raw   \
-        --net mac=52:54:20:11:C5:02,vhost_user=true,socket=/var/run/openvswitch/vhost-user2,num_queues=4
+        --net "mac=52:54:20:11:C5:02,vhost_user=true,socket=/var/run/openvswitch/vhost-user2,num_queues=4"
 ```
 
 _Setup VM1_
 ```bash
 # From inside the guest
-sudo ip addr add 172.100.0.1/24 dev ens2
-sudo ip link set up dev ens2
+sudo ip addr add 172.100.0.1/24 dev enp0s3
 ```
 
 _Setup VM2_
 ```bash
 # From inside the guest
-sudo ip addr add 172.100.0.2/24 dev ens2
-sudo ip link set up dev ens2
+sudo ip addr add 172.100.0.2/24 dev enp0s3
 ```
 
 _Ping VM1 from VM2_
@@ -144,3 +129,4 @@ _Run VM2 as client_
 # From inside the guest
 iperf3 -c 172.100.0.1 -t 30 -p 4444 &
 ```
+

docs/windows.md

@@ -30,15 +30,15 @@ This step currently requires QEMU to install Windows onto the guest. QEMU is onl
 Preparing several command parts as these will be used in the follow up sections as well.
 
 ```shell
-IMG_FILE=windows-disk.raw
+IMG_FILE=windows-disk.qcow
 WIN_ISO_FILE=en_windows_server_version_2004_updated_may_2020_x64_dvd_1e7f1cfa.iso
 VIRTIO_ISO_FILE=virtio-win-0.1.185.iso
 OVMF_DIR=./FV
 ```
 
-Create an empty image file, `raw` is supported.
+Create an empty image file, `qcow` or `raw` is supported.
 ```shell
-qemu-img create -f raw $IMG_FILE 30G
+qemu-img create -f qcow2 $IMG_FILE 30G
 ```
 
 Begin the Windows installation process under QEMU
@@ -67,7 +67,7 @@ The basic command to boot a Windows image. The configuration section should be c
 
 ```shell
 cloud-hypervisor \
-	--kernel ./$OVMF_DIR/CLOUDHV.fd \
+	--kernel ./$OVMF_DIR/OVMF.fd \
 	--disk path=./$IMG_FILE \
 	--cpus boot=1,kvm_hyperv=on \
 	--memory size=4G \
@@ -184,16 +184,6 @@ Set-Service -Name sshd -StartupType ‘Automatic’
 
 This allows for SSH login from a remote machine, for example through the `administrator` user: `ssh administrator@192.168.249.2`. For a more detailed OpenSSH guide, please follow the MSDN article from the [links](#links) section.
 
-## Hotplug capability
-
-CPU hotplug is supported. The VM operating system needs to support hotplug and be appropriately licensed. SKU limitations like constraints on the number of cores are to be taken into consideration. Note, that Windows doesn't support CPU hot-remove. When `ch-remote` is invoked to reduce the number of CPUs, the result will be visible after the OS reboot within the same hypervisor instance.
-
-RAM hotplug is supported. Note, that while the `pnpmem.sys` driver in use supports RAM hot-remove, the RAM being unplugged has to be not in use and have no reserved pages. In most cases it means, hot-remove won't work. Same as with the CPU hot-remove, when `ch-remote` is invoked to reduce the RAM size, the result will be visible after the OS reboot.
-
-Network device hotplug and hot-remove are supported.
-
-Disk hotplug and hot-remove are supported. After the device has been hotplugged, it will need to be onlined from within the guest. Among other tools, powershell applets `Get-Disk` and `Set-Disk` can be used for the disk configuration and activation.
-
 ## Debugging
 
 The Windows guest debugging process relies heavily on QEMU and [socat](http://www.dest-unreach.org/socat/). The procedure requires two Windows VMs:
@@ -221,7 +211,7 @@ qemu-system-x86_64 \
 	-m 4G \
 	-cdrom ./$WIN_ISO_FILE \
 	-drive file=./$VIRTIO_ISO_FILE,index=0,media=cdrom
-	-drive if=none,id=root,file=./windbg-disk.raw \
+	-drive if=none,id=root,file=./windbg-disk.qcow \
 	-device virtio-blk-pci,drive=root,disable-legacy=on \
 	-device virtio-net-pci,netdev=mynet0,disable-legacy=on \
 	-netdev user,id=mynet0,net=192.168.178.0/24,host=192.168.178.1,dhcpstart=192.168.178.64,hostname=windbg-host \
@@ -280,7 +270,7 @@ qemu-system-x86_64 \
 	-cpu host \
 	-smp 1 \
 	-m 4G \
-	-drive if=none,id=root,file=./windbg-disk.raw \
+	-drive if=none,id=root,file=./windbg-disk.qcow \
 	-device virtio-blk-pci,drive=root,disable-legacy=on \
 	-serial tcp::4445,server,nowait \
 	-device virtio-net-pci,netdev=mynet0,disable-legacy=on \

event_monitor/Cargo.toml

@@ -5,7 +5,7 @@ authors = ["The Cloud Hypervisor Authors"]
 edition = "2018"
 
 [dependencies]
-libc = "0.2.112"
-serde = { version = "1.0.133", features = ["rc"] }
-serde_derive = "1.0.133"
-serde_json = "1.0.75"
+libc = "0.2.91"
+serde = {version = ">=1.0.27", features = ["rc"] }
+serde_derive = ">=1.0.27"
+serde_json = ">=1.0.9"

fuzz/Cargo.lock

@@ -10,29 +10,35 @@ dependencies = [
 ]
 
 [[package]]
-name = "anyhow"
-version = "1.0.52"
+name = "ansi_term"
+version = "0.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "84450d0b4a8bd1ba4144ce8ce718fbc5d071358b1e5384bace6536b3d1f2d5b3"
+checksum = "ee49baf6cb617b853aa8d93bf420db2383fab46d314482ca2803b40d5fde979b"
+dependencies = [
+ "winapi",
+]
+
+[[package]]
+name = "anyhow"
+version = "1.0.39"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "81cddc5f91628367664cc7c69714ff08deee8a3efc54623011c772544d7b2767"
 
 [[package]]
 name = "api_client"
 version = "0.1.0"
-dependencies = [
- "vmm-sys-util",
-]
 
 [[package]]
 name = "arbitrary"
-version = "1.0.3"
+version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "510c76ecefdceada737ea728f4f9a84bd2e1ef29f1ba555e560940fe279954de"
+checksum = "698b65a961a9d730fb45b6b0327e20207810c9f61ee421b082b27ba003f49e2b"
 
 [[package]]
 name = "arc-swap"
-version = "1.5.0"
+version = "1.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c5d78ce20460b82d3fa150275ed9d55e21064fc7951177baacf86a145c4a4b1f"
+checksum = "d4d7d63395147b81a9e570bcc6243aaf71c017bd666d4909cfef0085bdda8d73"
 
 [[package]]
 name = "arch"
@@ -40,23 +46,24 @@ version = "0.1.0"
 dependencies = [
  "acpi_tables",
  "anyhow",
+ "arch_gen",
  "byteorder",
- "fdt",
  "hypervisor",
  "libc",
  "linux-loader",
  "log",
  "serde",
  "serde_derive",
+ "serde_json",
  "thiserror",
- "versionize",
- "versionize_derive",
- "vm-fdt",
  "vm-memory",
  "vm-migration",
- "vmm-sys-util",
 ]
 
+[[package]]
+name = "arch_gen"
+version = "0.1.0"
+
 [[package]]
 name = "atty"
 version = "0.2.14"
@@ -68,26 +75,11 @@ dependencies = [
  "winapi",
 ]
 
-[[package]]
-name = "autocfg"
-version = "1.0.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cdb031dd78e28731d87d56cc8ffef4a8f36ca26c38fe2de700543e627f8a464a"
-
-[[package]]
-name = "bincode"
-version = "1.3.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b1f45e9417d87227c7a56d22e471c6206462cba514c7590c09aff4cf6d1ddcad"
-dependencies = [
- "serde",
-]
-
 [[package]]
 name = "bitflags"
-version = "1.3.2"
+version = "1.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
+checksum = "cf1de2fe8c75bc145a2f577add951f8134889b4795d47466a54a5c846d691693"
 
 [[package]]
 name = "block_util"
@@ -97,12 +89,11 @@ dependencies = [
  "libc",
  "log",
  "qcow",
+ "serde",
+ "serde_derive",
+ "serde_json",
  "thiserror",
- "versionize",
- "versionize_derive",
- "vhdx",
  "virtio-bindings",
- "virtio-queue",
  "vm-memory",
  "vm-virtio",
  "vmm-sys-util",
@@ -116,9 +107,9 @@ checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610"
 
 [[package]]
 name = "cc"
-version = "1.0.72"
+version = "1.0.67"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "22a9137b95ea06864e018375b72adfb7db6e6f68cfc8df5a04d00288050485ee"
+checksum = "e3c69b077ad434294d3ce9f1f6143a2a4b89a8a2d54ef813d85003a4fd1137fd"
 
 [[package]]
 name = "cfg-if"
@@ -128,24 +119,23 @@ checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
 [[package]]
 name = "clap"
-version = "3.0.10"
+version = "2.33.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7a30c3bf9ff12dfe5dae53f0a96e0febcd18420d1c0e7fad77796d9d5c4b5375"
+checksum = "37e58ac78573c40708d45522f0d80fa2f01cc4f9b4e2bf749807255454312002"
 dependencies = [
+ "ansi_term",
  "atty",
  "bitflags",
- "indexmap",
- "lazy_static",
- "os_str_bytes",
  "strsim",
- "termcolor",
- "terminal_size",
+ "term_size",
  "textwrap",
+ "unicode-width",
+ "vec_map",
 ]
 
 [[package]]
 name = "cloud-hypervisor"
-version = "20.0.0"
+version = "0.13.0"
 dependencies = [
  "anyhow",
  "api_client",
@@ -156,7 +146,7 @@ dependencies = [
  "libc",
  "log",
  "option_parser",
- "seccompiler",
+ "seccomp",
  "serde_json",
  "signal-hook",
  "thiserror",
@@ -174,44 +164,27 @@ dependencies = [
  "libc",
  "libfuzzer-sys",
  "qcow",
- "seccompiler",
- "vhdx",
+ "seccomp",
  "virtio-devices",
- "virtio-queue",
  "vm-memory",
  "vm-virtio",
  "vmm-sys-util",
 ]
 
-[[package]]
-name = "crc32c"
-version = "0.6.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ee6b9c9389584bcba988bd0836086789b7f87ad91892d6a83d5291dbb24524b5"
-dependencies = [
- "rustc_version",
-]
-
-[[package]]
-name = "crc64"
-version = "1.0.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "55626594feae15d266d52440b26ff77de0e22230cf0c113abe619084c1ddc910"
-
 [[package]]
 name = "devices"
 version = "0.1.0"
 dependencies = [
  "acpi_tables",
  "anyhow",
- "arch",
  "bitflags",
  "byteorder",
  "epoll",
  "libc",
  "log",
- "versionize",
- "versionize_derive",
+ "serde",
+ "serde_derive",
+ "serde_json",
  "vm-device",
  "vm-memory",
  "vm-migration",
@@ -238,34 +211,11 @@ dependencies = [
  "serde_json",
 ]
 
-[[package]]
-name = "fdt"
-version = "0.1.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b643857cf70949306b81d7e92cb9d47add673868edac9863c4a49c42feaf3f1e"
-
-[[package]]
-name = "getrandom"
-version = "0.2.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "418d37c8b1d42553c93648be529cb70f920d3baf8ef469b74b9638df426e0b4c"
-dependencies = [
- "cfg-if",
- "libc",
- "wasi",
-]
-
-[[package]]
-name = "hashbrown"
-version = "0.11.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ab5ef0d4909ef3724cc8cce6ccc8572c5c817592e9285f5464f8e86f8bd3726e"
-
 [[package]]
 name = "hermit-abi"
-version = "0.1.20"
+version = "0.1.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c7a30908dbce072eca83216eab939d2290080e00ca71611b96a09e5cdce5f3fa"
+checksum = "322f4de77956e22ed0e5032c359a0f1273f1f7f0d79bfa3b8ffbc730d7fbcc5c"
 dependencies = [
  "libc",
 ]
@@ -291,29 +241,19 @@ dependencies = [
 
 [[package]]
 name = "iced-x86"
-version = "1.15.0"
+version = "1.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "46e977036f7f5139d580c7f19ad62df9cb8ebd8410bb569e73585226be80a86f"
+checksum = "4261b15a556aa9b83b976b7aa4613f5a3b80351683af14c5d8d7e62c00869d5a"
 dependencies = [
  "lazy_static",
  "static_assertions",
 ]
 
-[[package]]
-name = "indexmap"
-version = "1.8.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "282a6247722caba404c065016bbfa522806e51714c34f5dfc3e4a3a46fcb4223"
-dependencies = [
- "autocfg",
- "hashbrown",
-]
-
 [[package]]
 name = "io-uring"
-version = "0.5.2"
+version = "0.5.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8d75829ed9377bab6c90039fe47b9d84caceb4b5063266142e21bcce6550cda8"
+checksum = "fb82832e05cc4ca298f198a8db108837b4f7b7b1248e3cba8e48f151aece80cf"
 dependencies = [
  "bitflags",
  "libc",
@@ -321,14 +261,14 @@ dependencies = [
 
 [[package]]
 name = "itoa"
-version = "1.0.1"
+version = "0.4.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1aab8fc367588b89dcee83ab0fd66b72b50b72fa1904d7095045ace2b0c81c35"
+checksum = "dd25036021b0de88a0aff6b850051563c6516d0bf53f8638938edbb9de732736"
 
 [[package]]
 name = "kvm-bindings"
-version = "0.5.0"
-source = "git+https://github.com/cloud-hypervisor/kvm-bindings?branch=ch-v0.5.0#9c497710ba9968d8efe15dbae03991b16cf82e23"
+version = "0.4.0"
+source = "git+https://github.com/cloud-hypervisor/kvm-bindings?branch=ch-v0.4.0#1a68725639283e622f4bb64584885b30bfe8be44"
 dependencies = [
  "serde",
  "serde_derive",
@@ -337,8 +277,9 @@ dependencies = [
 
 [[package]]
 name = "kvm-ioctls"
-version = "0.11.0"
-source = "git+https://github.com/rust-vmm/kvm-ioctls?branch=main#d22ef1f51852dfb055da38004e1a4fed81246f81"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "74058b16912c6723db02d4ca3ec919b73cd41512ccd3b6202cf91ae8d6c9dce5"
 dependencies = [
  "kvm-bindings",
  "libc",
@@ -353,26 +294,25 @@ checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
 
 [[package]]
 name = "libc"
-version = "0.2.112"
+version = "0.2.91"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1b03d17f364a3a042d5e5d46b053bbbf82c92c9430c592dd4c064dc6ee997125"
+checksum = "8916b1f6ca17130ec6568feccee27c156ad12037880833a3b842a823236502e7"
 
 [[package]]
 name = "libfuzzer-sys"
-version = "0.4.2"
+version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "36a9a84a6e8b55dfefb04235e55edb2b9a2a18488fcae777a6bdaa6f06f1deb3"
+checksum = "86c975d637bc2a2f99440932b731491fc34c7f785d239e38af3addd3c2fd0e46"
 dependencies = [
  "arbitrary",
  "cc",
- "once_cell",
 ]
 
 [[package]]
 name = "linux-loader"
-version = "0.4.0"
+version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8a5e77493808403a6bd56a301a64ea6b9342e36ea845044bf0dfdf56fe52fa08"
+checksum = "c819cc8275b0f2c1ed9feec455ca288b45d82932384a6a5f7a86812ee3427459"
 dependencies = [
  "vm-memory",
 ]
@@ -386,19 +326,12 @@ dependencies = [
  "cfg-if",
 ]
 
-[[package]]
-name = "memchr"
-version = "2.4.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "308cc39be01b73d0d18f82a0e7b2a3df85245f84af96fdddc5d202d27e47b86a"
-
 [[package]]
 name = "micro_http"
 version = "0.1.0"
-source = "git+https://github.com/firecracker-microvm/micro-http?branch=main#9517a300370a158a7af0996b7eebf040d171e1a4"
+source = "git+https://github.com/firecracker-microvm/micro-http?branch=master#59ab64440a95f7b16253fef67b5201c2ec4adaf7"
 dependencies = [
- "libc",
- "vmm-sys-util",
+ "epoll",
 ]
 
 [[package]]
@@ -413,40 +346,20 @@ name = "net_util"
 version = "0.1.0"
 dependencies = [
  "epoll",
- "getrandom",
  "libc",
  "log",
  "net_gen",
- "rate_limiter",
  "serde",
- "versionize",
- "versionize_derive",
  "virtio-bindings",
- "virtio-queue",
  "vm-memory",
  "vm-virtio",
  "vmm-sys-util",
 ]
 
-[[package]]
-name = "once_cell"
-version = "1.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "da32515d9f6e6e489d7bc9d84c71b060db7247dc035bbe44eac88cf87486d8d5"
-
 [[package]]
 name = "option_parser"
 version = "0.1.0"
 
-[[package]]
-name = "os_str_bytes"
-version = "6.0.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8e22443d1643a904602595ba1cd8f7d896afe56d26712531c5ff73a15b2fbf64"
-dependencies = [
- "memchr",
-]
-
 [[package]]
 name = "pci"
 version = "0.1.0"
@@ -456,12 +369,11 @@ dependencies = [
  "hypervisor",
  "libc",
  "log",
- "thiserror",
- "versionize",
- "versionize_derive",
+ "serde",
+ "serde_derive",
+ "serde_json",
  "vfio-bindings",
  "vfio-ioctls",
- "vfio_user",
  "vm-allocator",
  "vm-device",
  "vm-memory",
@@ -471,9 +383,9 @@ dependencies = [
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.36"
+version = "1.0.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c7342d5883fbccae1cc37a2353b09c87c9b0f3afd73f5fb9bba687a1f733b029"
+checksum = "1e0704ee1a7e00d7bb417d0770ea303c1bccbabf0ef1667dae92b5967f5f8a71"
 dependencies = [
  "unicode-xid",
 ]
@@ -491,22 +403,13 @@ dependencies = [
 
 [[package]]
 name = "quote"
-version = "1.0.14"
+version = "1.0.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "47aa80447ce4daf1717500037052af176af5d38cc3e571d9ec1c7353fc10c87d"
+checksum = "c3d0b9745dc2debf507c8422de05d7226cc1f0644216dfdfead988f9b1ab32a7"
 dependencies = [
  "proc-macro2",
 ]
 
-[[package]]
-name = "rate_limiter"
-version = "0.1.0"
-dependencies = [
- "libc",
- "log",
- "vmm-sys-util",
-]
-
 [[package]]
 name = "remain"
 version = "0.2.2"
@@ -518,47 +421,31 @@ dependencies = [
  "syn",
 ]
 
-[[package]]
-name = "rustc_version"
-version = "0.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bfa0f585226d2e68097d4f95d113b15b83a82e819ab25717ec0590d9584ef366"
-dependencies = [
- "semver",
-]
-
 [[package]]
 name = "ryu"
-version = "1.0.9"
+version = "1.0.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "73b4b750c782965c211b42f022f59af1fbceabdd026623714f104152f1ec149f"
+checksum = "71d301d4193d031abdd79ff7e3dd721168a9572ef3fe51a1517aba235bd8f86e"
 
 [[package]]
-name = "seccompiler"
-version = "0.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e01d1292a1131b22ccea49f30bd106f1238b5ddeec1a98d39268dcc31d540e68"
+name = "seccomp"
+version = "0.1.0"
+source = "git+https://github.com/firecracker-microvm/firecracker?tag=v0.22.0#cc5387637c132e500b4857b80b5a239d8d732b77"
 dependencies = [
  "libc",
 ]
 
-[[package]]
-name = "semver"
-version = "1.0.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "568a8e6258aa33c13358f81fd834adb854c6f7c9468520910a9b1e8fac068012"
-
 [[package]]
 name = "serde"
-version = "1.0.133"
+version = "1.0.125"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "97565067517b60e2d1ea8b268e59ce036de907ac523ad83a0475da04e818989a"
+checksum = "558dc50e1a5a5fa7112ca2ce4effcb321b0300c0d4ccf0776a9f60cd89031171"
 
 [[package]]
 name = "serde_derive"
-version = "1.0.133"
+version = "1.0.125"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ed201699328568d8d08208fdd080e3ff594e6c422e438b6705905da01005d537"
+checksum = "b093b7a2bb58203b5da3056c05b4ec1fed827dcfdb37347a8841695263b3d06d"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -567,9 +454,9 @@ dependencies = [
 
 [[package]]
 name = "serde_json"
-version = "1.0.75"
+version = "1.0.64"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c059c05b48c5c0067d4b4b2b4f0732dd65feb52daf7e0ea09cd87e7dadc1af79"
+checksum = "799e97dc9fdae36a5c8b8f2cae9ce2ee9fdce2058c57a93e6099d919fd982f79"
 dependencies = [
  "itoa",
  "ryu",
@@ -578,9 +465,9 @@ dependencies = [
 
 [[package]]
 name = "signal-hook"
-version = "0.3.13"
+version = "0.3.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "647c97df271007dcea485bb74ffdb57f2e683f1306c854f468a0c244badabf2d"
+checksum = "6aa894ef3fade0ee7243422f4fbbd6c2b48e6de767e621d37ef65f2310f53cea"
 dependencies = [
  "libc",
  "signal-hook-registry",
@@ -588,9 +475,9 @@ dependencies = [
 
 [[package]]
 name = "signal-hook-registry"
-version = "1.4.0"
+version = "1.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e51e73328dc4ac0c7ccbda3a494dfa03df1de2f46018127f60c693f2648455b0"
+checksum = "16f1d0fef1604ba8f7a073c7e701f213e056707210e9020af4528e0101ce11a6"
 dependencies = [
  "libc",
 ]
@@ -603,15 +490,15 @@ checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f"
 
 [[package]]
 name = "strsim"
-version = "0.10.0"
+version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623"
+checksum = "8ea5119cdb4c55b55d432abb513a0429384878c15dde60cc77b1c99de1a95a6a"
 
 [[package]]
 name = "syn"
-version = "1.0.85"
+version = "1.0.64"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a684ac3dcd8913827e18cd09a68384ee66c1de24157e3c556c9ab16d85695fb7"
+checksum = "3fd9d1e9976102a03c542daa2eff1b43f9d72306342f3f8b3ed5fb8908195d6f"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -619,19 +506,10 @@ dependencies = [
 ]
 
 [[package]]
-name = "termcolor"
-version = "1.1.2"
+name = "term_size"
+version = "0.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2dfed899f0eb03f32ee8c6a0aabdb8a7949659e3466561fc0adf54e26d88c5f4"
-dependencies = [
- "winapi-util",
-]
-
-[[package]]
-name = "terminal_size"
-version = "0.1.17"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "633c1a546cee861a1a6d0dc69ebeca693bf4296661ba7852b9d21d159e0506df"
+checksum = "1e4129646ca0ed8f45d09b929036bafad5377103edd06e50bf574b353d2b08d9"
 dependencies = [
  "libc",
  "winapi",
@@ -639,80 +517,57 @@ dependencies = [
 
 [[package]]
 name = "textwrap"
-version = "0.14.2"
+version = "0.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0066c8d12af8b5acd21e00547c3797fde4e8677254a7ee429176ccebbe93dd80"
+checksum = "d326610f408c7a4eb6f51c37c330e496b08506c9457c9d34287ecc38809fb060"
 dependencies = [
- "terminal_size",
+ "term_size",
+ "unicode-width",
 ]
 
 [[package]]
 name = "thiserror"
-version = "1.0.30"
+version = "1.0.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "854babe52e4df1653706b98fcfc05843010039b406875930a70e4d9644e5c417"
+checksum = "e0f4a65597094d4483ddaed134f409b2cb7c1beccf25201a9f73c719254fa98e"
 dependencies = [
  "thiserror-impl",
 ]
 
 [[package]]
 name = "thiserror-impl"
-version = "1.0.30"
+version = "1.0.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aa32fd3f627f367fe16f893e2597ae3c05020f8bba2666a4e6ea73d377e5714b"
+checksum = "7765189610d8241a44529806d6fd1f2e0a08734313a35d5b3a556f92b381f3c0"
 dependencies = [
  "proc-macro2",
  "quote",
  "syn",
 ]
 
+[[package]]
+name = "unicode-width"
+version = "0.1.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9337591893a19b88d8d87f2cec1e73fad5cdfd10e5a6f349f498ad6ea2ffb1e3"
+
 [[package]]
 name = "unicode-xid"
-version = "0.2.2"
+version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8ccb82d61f80a663efe1f787a51b16b5a51e3314d6ac365b08639f52387b33f3"
+checksum = "f7fe0bb3479651439c9112f72b6c505038574c9fbb575ed1bf3b797fa39dd564"
 
 [[package]]
-name = "uuid"
+name = "vec_map"
 version = "0.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bc5cf98d8186244414c848017f0e2676b3fcb46807f6668a97dfe67359a3c4b7"
-dependencies = [
- "getrandom",
-]
-
-[[package]]
-name = "versionize"
-version = "0.1.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7429cf68de8f091b667d27323ed323afd39584a56d533995b12ddd748e5e6ca9"
-dependencies = [
- "bincode",
- "crc64",
- "proc-macro2",
- "quote",
- "serde",
- "serde_derive",
- "syn",
- "versionize_derive",
- "vmm-sys-util",
-]
-
-[[package]]
-name = "versionize_derive"
-version = "0.1.4"
-source = "git+https://github.com/cloud-hypervisor/versionize_derive?branch=ch#ae35ef7a3ddabd3371ab8ac0193a383aff6e4b1b"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn",
-]
+checksum = "f1bddf1187be692e79c5ffeab891132dfb0f236ed36a43c7ed39f1165ee20191"
 
 [[package]]
 name = "vfio-bindings"
-version = "0.3.1"
+version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "43449b404c488f70507dca193debd4bea361fe8089869b947adc19720e464bce"
+checksum = "4a21f546f2bda37f5a8cfb138c87f95b8e34d2d78d6a7a92ba3785f4e08604a7"
 dependencies = [
  "vmm-sys-util",
 ]
@@ -720,7 +575,7 @@ dependencies = [
 [[package]]
 name = "vfio-ioctls"
 version = "0.1.0"
-source = "git+https://github.com/rust-vmm/vfio-ioctls?branch=main#8f7f2210ebe71660938b05b2ed7eec9253478bc5"
+source = "git+https://github.com/rust-vmm/vfio-ioctls?branch=master#a87b13bdec026e8144b91f30f35451a966d8c1ca"
 dependencies = [
  "byteorder",
  "kvm-bindings",
@@ -731,45 +586,13 @@ dependencies = [
  "vmm-sys-util",
 ]
 
-[[package]]
-name = "vfio_user"
-version = "0.1.0"
-dependencies = [
- "anyhow",
- "libc",
- "log",
- "serde",
- "serde_derive",
- "serde_json",
- "thiserror",
- "vfio-bindings",
- "vm-memory",
- "vmm-sys-util",
-]
-
-[[package]]
-name = "vhdx"
-version = "0.1.0"
-dependencies = [
- "byteorder",
- "crc32c",
- "libc",
- "log",
- "remain",
- "thiserror",
- "uuid",
- "vmm-sys-util",
-]
-
 [[package]]
 name = "vhost"
-version = "0.3.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3b56bf8f178fc500fe14505fca8b00dec76fc38f2304f461c8d9d7547982311d"
+version = "0.1.0"
+source = "git+https://github.com/rust-vmm/vhost?branch=master#ee3e8722706c984b3dfe12d3a130e92101b78e8f"
 dependencies = [
  "bitflags",
  "libc",
- "vm-memory",
  "vmm-sys-util",
 ]
 
@@ -795,16 +618,12 @@ dependencies = [
  "net_gen",
  "net_util",
  "pci",
- "rate_limiter",
- "seccompiler",
+ "seccomp",
  "serde",
  "serde_derive",
  "serde_json",
- "versionize",
- "versionize_derive",
  "vhost",
  "virtio-bindings",
- "virtio-queue",
  "vm-allocator",
  "vm-device",
  "vm-memory",
@@ -813,15 +632,6 @@ dependencies = [
  "vmm-sys-util",
 ]
 
-[[package]]
-name = "virtio-queue"
-version = "0.1.0"
-dependencies = [
- "log",
- "vm-memory",
- "vmm-sys-util",
-]
-
 [[package]]
 name = "vm-allocator"
 version = "0.1.0"
@@ -845,16 +655,11 @@ dependencies = [
  "vmm-sys-util",
 ]
 
-[[package]]
-name = "vm-fdt"
-version = "0.1.0"
-source = "git+https://github.com/rust-vmm/vm-fdt?branch=main#720e48e435b791ec6cbe8d2b229448b71dcb1ab9"
-
 [[package]]
 name = "vm-memory"
-version = "0.7.0"
+version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "339d4349c126fdcd87e034631d7274370cf19eb0e87b33166bcd956589fc72c5"
+checksum = "625f401b1b8b3ac3d43f53903cd138cfe840bd985f8581e553027b31d2bb8ae8"
 dependencies = [
  "arc-swap",
  "libc",
@@ -870,8 +675,6 @@ dependencies = [
  "serde_derive",
  "serde_json",
  "thiserror",
- "versionize",
- "versionize_derive",
  "vm-memory",
 ]
 
@@ -880,8 +683,10 @@ name = "vm-virtio"
 version = "0.1.0"
 dependencies = [
  "log",
+ "serde",
+ "serde_derive",
+ "serde_json",
  "virtio-bindings",
- "virtio-queue",
  "vm-memory",
 ]
 
@@ -909,20 +714,14 @@ dependencies = [
  "option_parser",
  "pci",
  "qcow",
- "seccompiler",
+ "seccomp",
  "serde",
  "serde_derive",
  "serde_json",
  "signal-hook",
  "thiserror",
- "uuid",
- "versionize",
- "versionize_derive",
  "vfio-ioctls",
- "vfio_user",
- "vhdx",
  "virtio-devices",
- "virtio-queue",
  "vm-allocator",
  "vm-device",
  "vm-memory",
@@ -933,9 +732,9 @@ dependencies = [
 
 [[package]]
 name = "vmm-sys-util"
-version = "0.9.0"
+version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "733537bded03aaa93543f785ae997727b30d1d9f4a03b7861d23290474242e11"
+checksum = "01cf11afbc4ebc0d5c7a7748a77d19e2042677fc15faa2f4ccccb27c18a60605"
 dependencies = [
  "bitflags",
  "libc",
@@ -943,12 +742,6 @@ dependencies = [
  "serde_derive",
 ]
 
-[[package]]
-name = "wasi"
-version = "0.10.2+wasi-snapshot-preview1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fd6fbd9a79829dd1ad0cc20627bf1ed606756a7f77edff7b66b7064f9cb327c6"
-
 [[package]]
 name = "winapi"
 version = "0.3.9"
@@ -965,15 +758,6 @@ version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
 
-[[package]]
-name = "winapi-util"
-version = "0.1.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "70ec6ce85bb158151cae5e5c87f95a8e97d2c0c4b001223f33a334e3ce5de178"
-dependencies = [
- "winapi",
-]
-
 [[package]]
 name = "winapi-x86_64-pc-windows-gnu"
 version = "0.4.0"

fuzz/Cargo.toml

@@ -10,25 +10,21 @@ cargo-fuzz = true
 
 [dependencies]
 block_util = { path = "../block_util" }
-libc = "0.2.112"
-libfuzzer-sys = "0.4.2"
+libc = "0.2.90"
+libfuzzer-sys = "0.4"
 qcow = { path = "../qcow" }
-seccompiler = "0.2.0"
-vhdx = { path = "../vhdx" }
+seccomp = { git = "https://github.com/firecracker-microvm/firecracker", tag = "v0.22.0" }
 virtio-devices = { path = "../virtio-devices" }
-virtio-queue = { path = "../virtio-queue" }
-vmm-sys-util = "0.9.0"
+vmm-sys-util = "0.8.0"
 vm-virtio = { path = "../vm-virtio" }
-vm-memory = "0.7.0"
+vm-memory = "0.5.0"
+
+[patch.crates-io]
+kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.4.0", features = ["with-serde", "fam-wrappers"] }
 
 [dependencies.cloud-hypervisor]
 path = ".."
 
-[patch.crates-io]
-kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.5.0", features = ["with-serde", "fam-wrappers"] }
-kvm-ioctls = { git = "https://github.com/rust-vmm/kvm-ioctls", branch = "main" }
-versionize_derive = { git = "https://github.com/cloud-hypervisor/versionize_derive", branch = "ch" }
-
 # Prevent this from interfering with workspaces
 [workspace]
 members = ["."]
@@ -44,9 +40,3 @@ name = "block"
 path = "fuzz_targets/block.rs"
 test = false
 doc = false
-
-[[bin]]
-name = "vhdx"
-path = "fuzz_targets/vhdx.rs"
-test = false
-doc = false

fuzz/fuzz_targets/block.rs

@@ -4,9 +4,9 @@
 
 #![no_main]
 
-use block_util::{async_io::DiskFile, raw_sync::RawFileDiskSync};
+use block_util::{async_io::DiskFile, qcow_sync::QcowDiskSync};
 use libfuzzer_sys::fuzz_target;
-use seccompiler::SeccompAction;
+use seccomp::SeccompAction;
 use std::ffi;
 use std::fs::File;
 use std::io::{self, Cursor, Read, Seek, SeekFrom};
@@ -15,11 +15,9 @@ use std::os::unix::io::{AsRawFd, FromRawFd, RawFd};
 use std::path::PathBuf;
 use std::sync::Arc;
 use virtio_devices::{Block, VirtioDevice, VirtioInterrupt, VirtioInterruptType};
-use virtio_queue::{Queue, QueueState};
-use vm_memory::{bitmap::AtomicBitmap, Bytes, GuestAddress, GuestMemoryAtomic};
-use vmm_sys_util::eventfd::{EventFd, EFD_NONBLOCK};
-
-type GuestMemoryMmap = vm_memory::GuestMemoryMmap<AtomicBitmap>;
+use vm_memory::{Bytes, GuestAddress, GuestMemoryAtomic, GuestMemoryMmap};
+use vm_virtio::Queue;
+use vmm_sys_util::eventfd::EventFd;
 
 const MEM_SIZE: u64 = 256 * 1024 * 1024;
 const DESC_SIZE: u64 = 16; // Bytes in one virtio descriptor.
@@ -75,14 +73,10 @@ fuzz_target!(|bytes| {
         return;
     }
 
-    let guest_memory = GuestMemoryAtomic::new(mem);
-
-    let mut q = Queue::<
-        GuestMemoryAtomic<GuestMemoryMmap>,
-        QueueState,
-    >::new(guest_memory.clone(), QUEUE_SIZE);
-    q.state.ready = true;
-    q.state.size = QUEUE_SIZE / 2;
+    let mut q = Queue::new(QUEUE_SIZE);
+    q.ready = true;
+    q.size = QUEUE_SIZE / 2;
+    q.max_size = QUEUE_SIZE;
 
     let queue_evts: Vec<EventFd> = vec![EventFd::new(0).unwrap()];
     let queue_fd = queue_evts[0].as_raw_fd();
@@ -90,7 +84,7 @@ fuzz_target!(|bytes| {
 
     let shm = memfd_create(&ffi::CString::new("fuzz").unwrap(), 0).unwrap();
     let disk_file: File = unsafe { File::from_raw_fd(shm) };
-    let qcow_disk = Box::new(RawFileDiskSync::new(disk_file)) as Box<dyn DiskFile>;
+    let qcow_disk = Box::new(QcowDiskSync::new(disk_file, false)) as Box<dyn DiskFile>;
 
     let mut block = Block::new(
         "tmp".to_owned(),
@@ -102,13 +96,12 @@ fuzz_target!(|bytes| {
         256,
         SeccompAction::Allow,
         None,
-        EventFd::new(EFD_NONBLOCK).unwrap(),
     )
     .unwrap();
 
     block
         .activate(
-            guest_memory,
+            GuestMemoryAtomic::new(mem),
             Arc::new(NoopVirtioInterrupt {}),
             vec![q],
             queue_evts,
@@ -140,7 +133,7 @@ impl VirtioInterrupt for NoopVirtioInterrupt {
     fn trigger(
         &self,
         _int_type: &VirtioInterruptType,
-        _queue: Option<&Queue<GuestMemoryAtomic<GuestMemoryMmap>>>,
+        _queue: Option<&Queue>,
     ) -> std::result::Result<(), std::io::Error> {
         Ok(())
     }

fuzz/fuzz_targets/vhdx.rs

@@ -1,53 +0,0 @@
-// Copyright © 2021 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-
-#![no_main]
-use libfuzzer_sys::fuzz_target;
-use std::ffi;
-use std::fs::File;
-use std::io::{self, Read, Seek, SeekFrom, Write};
-use std::os::unix::io::{FromRawFd, RawFd};
-use vhdx::vhdx::Vhdx;
-
-// Populate the corpus directory with a test file:
-// truncate -s 16M /tmp/source
-// qemu-img convert -O vhdx /tmp/source fuzz/corpus/vhdx/test.vhdx
-// Run with:
-// cargo fuzz run vhdx -j 32 -- -max_len=16777216
-fuzz_target!(|bytes| {
-    let shm = memfd_create(&ffi::CString::new("fuzz").unwrap(), 0).unwrap();
-    let mut disk_file: File = unsafe { File::from_raw_fd(shm) };
-    disk_file.write_all(&bytes[..]).unwrap();
-    disk_file.seek(SeekFrom::Start(0)).unwrap();
-
-    if let Ok(mut vhdx) = Vhdx::new(disk_file) {
-        if vhdx.seek(SeekFrom::Start(0)).is_ok() {
-            let mut offset = 0;
-            while offset < bytes.len() {
-                let mut data = vec![0; 8192];
-                vhdx.read_exact(&mut data).ok();
-                offset += data.len();
-            }
-        }
-
-        if vhdx.seek(SeekFrom::Start(0)).is_ok() {
-            let mut offset = 0;
-            while offset < bytes.len() {
-                let data = vec![0; 8192];
-                vhdx.write_all(&data).ok();
-                offset += data.len();
-            }
-        }
-    }
-});
-
-fn memfd_create(name: &ffi::CStr, flags: u32) -> Result<RawFd, io::Error> {
-    let res = unsafe { libc::syscall(libc::SYS_memfd_create, name.as_ptr(), flags) };
-
-    if res < 0 {
-        Err(io::Error::last_os_error())
-    } else {
-        Ok(res as RawFd)
-    }
-}

hypervisor/Cargo.toml

@@ -11,25 +11,25 @@ mshv = ["mshv-ioctls", "mshv-bindings"]
 tdx = []
 
 [dependencies]
-anyhow = "1.0.52"
-epoll = "4.3.1"
-thiserror = "1.0.30"
-libc = "0.2.112"
+anyhow = "1.0"
+epoll = ">=4.0.1"
+thiserror = "1.0"
+libc = "0.2.91"
 log = "0.4.14"
-kvm-ioctls = { version = "0.11.0", optional = true }
-kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.5.0", features = ["with-serde", "fam-wrappers"], optional  = true }
-mshv-bindings = {git = "https://github.com/rust-vmm/mshv", branch = "main", features = ["with-serde", "fam-wrappers"], optional  = true }
-mshv-ioctls = { git = "https://github.com/rust-vmm/mshv", branch = "main", optional  = true}
-serde = { version = "1.0.133", features = ["rc"] }
-serde_derive = "1.0.133"
-serde_json = "1.0.75"
-vm-memory = { version = "0.7.0", features = ["backend-mmap", "backend-atomic"] }
-vmm-sys-util = { version = "0.9.0", features = ["with-serde"] }
+kvm-ioctls = {  version = "0.8.0", optional = true }
+kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.4.0", features = ["with-serde", "fam-wrappers"], optional  = true }
+mshv-bindings = {git = "https://github.com/cloud-hypervisor/mshv", branch = "master", features = ["with-serde", "fam-wrappers"], optional  = true }
+mshv-ioctls = { git = "https://github.com/cloud-hypervisor/mshv", branch = "master", optional  = true}
+serde = {version = ">=1.0.27", features = ["rc"] }
+serde_derive = ">=1.0.27"
+serde_json = ">=1.0.9"
+vm-memory = { version = "0.5.0", features = ["backend-mmap", "backend-atomic"] }
+vmm-sys-util = { version = ">=0.5.0", features = ["with-serde"] }
 
 [target.'cfg(target_arch = "x86_64")'.dependencies.iced-x86]
-version = "1.15.0"
+version = "1.11"
 default-features = false
 features = ["std", "decoder", "op_code_info", "instr_info", "fast_fmt"]
 
 [dev-dependencies]
-env_logger = "0.9.0"
+env_logger = "0.8.3"

hypervisor/src/arch/emulator/mod.rs

@@ -4,6 +4,8 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
+extern crate thiserror;
+
 use core::fmt::Debug;
 use std::fmt::{self, Display};
 use thiserror::Error;
@@ -18,18 +20,7 @@ pub struct Exception<T: Debug> {
 
 impl<T: Debug> Display for Exception<T> {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        write!(
-            f,
-            "Exception {:?} at IP {:#x}{}{}",
-            self.vector,
-            self.ip,
-            self.error
-                .map(|e| format!(": error {:x}", e))
-                .unwrap_or_else(|| "".to_owned()),
-            self.payload
-                .map(|payload| format!(": payload {:x}", payload))
-                .unwrap_or_else(|| "".to_owned())
-        )
+        write!(f, "Exception {:?} at IP {:#x}", self.vector, self.ip)
     }
 }
 

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

@@ -10,6 +10,8 @@
 // CMP-Compare Two Operands
 //
 
+extern crate iced_x86;
+
 use crate::arch::emulator::{EmulationError, PlatformEmulator};
 use crate::arch::x86::emulator::instructions::*;
 use crate::arch::x86::regs::*;

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

@@ -4,6 +4,8 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
+extern crate iced_x86;
+
 use crate::arch::emulator::{EmulationError, PlatformEmulator, PlatformError};
 use crate::arch::x86::emulator::CpuStateManager;
 use crate::arch::x86::Exception;
@@ -12,7 +14,6 @@ use iced_x86::*;
 pub mod cmp;
 pub mod mov;
 pub mod movs;
-pub mod or;
 
 fn get_op<T: CpuStateManager>(
     insn: &Instruction,