Merge pull request #6817 from fidencio/3.1.1-branch-bump

# Kata Containers 3.1.1

.github/cargo-deny-composite-action/cargo-deny-generator.sh

@@ -0,0 +1,40 @@
+#!/bin/bash
+#
+# Copyright (c) 2022 Red Hat
+#
+# SPDX-License-Identifier: Apache-2.0
+#
+
+script_dir=$(dirname "$(readlink -f "$0")")
+parent_dir=$(realpath "${script_dir}/../..")
+cidir="${parent_dir}/ci"
+source "${cidir}/lib.sh"
+
+cargo_deny_file="${script_dir}/action.yaml"
+
+cat cargo-deny-skeleton.yaml.in > "${cargo_deny_file}"
+
+changed_files_status=$(run_get_pr_changed_file_details)
+changed_files_status=$(echo "$changed_files_status" | grep "Cargo\.toml$" || true)
+changed_files=$(echo "$changed_files_status" | awk '{print $NF}' || true)
+
+if [ -z "$changed_files" ]; then
+  cat >> "${cargo_deny_file}" << EOF
+    - run: echo "No Cargo.toml files to check"
+      shell: bash
+EOF
+fi
+
+for path in $changed_files
+do
+    cat >> "${cargo_deny_file}" << EOF
+
+    - name: ${path}
+      continue-on-error: true
+      shell: bash
+      run: |
+        pushd $(dirname ${path})
+        cargo deny check
+        popd
+EOF
+done

.github/cargo-deny-composite-action/cargo-deny-skeleton.yaml.in

@@ -0,0 +1,30 @@
+#
+# Copyright (c) 2022 Red Hat
+#
+# SPDX-License-Identifier: Apache-2.0
+#
+
+name: 'Cargo Crates Check'
+description: 'Checks every Cargo.toml file using cargo-deny'
+
+env:
+  CARGO_TERM_COLOR: always
+
+runs:
+  using: "composite"
+  steps:
+    - name: Install Rust
+      uses: actions-rs/toolchain@v1
+      with:
+        profile: minimal
+        toolchain: nightly 
+        override: true
+
+    - name: Cache
+      uses: Swatinem/rust-cache@v2
+
+    - name: Install Cargo deny
+      shell: bash
+      run: |
+        which cargo
+        cargo install --locked cargo-deny || true

.github/workflows/add-backport-label.yaml

@@ -0,0 +1,100 @@
+name: Add backport label
+
+on:
+  pull_request:
+    types:
+      - opened
+      - synchronize
+      - reopened
+      - edited
+      - labeled
+      - unlabeled
+
+jobs:
+  check-issues:
+    if: ${{ github.event.label.name != 'auto-backport' }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code to allow hub to communicate with the project
+        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
+        uses: actions/checkout@v3
+
+      - name: Install hub extension script
+        run: |
+          pushd $(mktemp -d) &>/dev/null
+          git clone --single-branch --depth 1 "https://github.com/kata-containers/.github" && cd .github/scripts
+          sudo install hub-util.sh /usr/local/bin
+          popd &>/dev/null
+
+      - name: Determine whether to add label 
+        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          CONTAINS_AUTO_BACKPORT: ${{ contains(github.event.pull_request.labels.*.name, 'auto-backport') }}
+        id: add_label
+        run: |
+          pr=${{ github.event.pull_request.number }}
+          linked_issue_urls=$(hub-util.sh \
+            list-issues-for-pr "$pr" |\
+            grep -v "^\#"  |\
+            cut -d';' -f3 || true)
+          [ -z "$linked_issue_urls" ] && {
+            echo "::error::No linked issues for PR $pr"
+            exit 1
+          }
+          has_bug=false
+          for issue_url in $(echo "$linked_issue_urls")
+          do
+            issue=$(echo "$issue_url"| awk -F\/ '{print $NF}' || true)
+            [ -z "$issue" ] && {
+              echo "::error::Cannot determine issue number from $issue_url for PR $pr"
+              exit 1
+            }
+            labels=$(hub-util.sh list-labels-for-issue "$issue")
+            
+            label_names=$(echo $labels | jq -r '.[].name' || true)
+            if [[ "$label_names" =~ "bug" ]]; then
+              has_bug=true
+              break
+            fi
+          done
+
+          has_backport_needed_label=${{ contains(github.event.pull_request.labels.*.name, 'needs-backport') }}
+          has_no_backport_needed_label=${{ contains(github.event.pull_request.labels.*.name, 'no-backport-needed') }}
+
+          echo "::set-output name=add_backport_label::false"
+          if [ $has_backport_needed_label  = true ] || [ $has_bug  = true ]; then
+            if [[ $has_no_backport_needed_label = false ]]; then
+              echo "::set-output name=add_backport_label::true"
+            fi
+          fi
+
+          # Do not spam comment, only if auto-backport label is going to be newly added.
+          echo "::set-output name=auto_backport_added::$CONTAINS_AUTO_BACKPORT"
+
+      - name: Add comment
+        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') && steps.add_label.outputs.add_backport_label == 'true' && steps.add_label.outputs.auto_backport_added == 'false' }}
+        uses: actions/github-script@v6
+        with:
+          script: |
+            github.rest.issues.createComment({
+              issue_number: context.issue.number,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: 'This issue has been marked for auto-backporting. Add label(s) backport-to-BRANCHNAME to backport to them'
+            })
+
+      # Allow label to be removed by adding no-backport-needed label
+      - name: Remove auto-backport label
+        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') && steps.add_label.outputs.add_backport_label == 'false' }}
+        uses: andymckay/labeler@e6c4322d0397f3240f0e7e30a33b5c5df2d39e90
+        with:
+          remove-labels: "auto-backport"
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Add auto-backport label
+        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') && steps.add_label.outputs.add_backport_label == 'true' }}
+        uses: andymckay/labeler@e6c4322d0397f3240f0e7e30a33b5c5df2d39e90
+        with:
+          add-labels: "auto-backport"
+          repo-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/auto-backport.yaml

@@ -0,0 +1,29 @@
+on:
+  pull_request_target:
+    types: ["labeled", "closed"]
+
+jobs:
+  backport:
+    name: Backport PR
+    runs-on: ubuntu-latest
+    if: |
+      github.event.pull_request.merged == true
+      && contains(github.event.pull_request.labels.*.name, 'auto-backport')
+      && (
+        (github.event.action == 'labeled' && github.event.label.name == 'auto-backport')
+        || (github.event.action == 'closed')
+      )
+    steps:
+      - name: Backport Action
+        uses: sqren/backport-github-action@v8.9.2
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          auto_backport_label_prefix: backport-to-
+
+      - name: Info log
+        if: ${{ success() }}
+        run: cat /home/runner/.backport/backport.info.log
+        
+      - name: Debug log
+        if: ${{ failure() }}
+        run: cat /home/runner/.backport/backport.debug.log

.github/workflows/cargo-deny-runner.yaml

@@ -0,0 +1,26 @@
+name: Cargo Crates Check Runner
+on:
+  pull_request:
+    types:
+      - opened
+      - edited
+      - reopened
+      - synchronize
+    paths-ignore: [ '**.md', '**.png', '**.jpg', '**.jpeg', '**.svg', '/docs/**' ]
+jobs:
+  cargo-deny-runner:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout Code
+        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
+        uses: actions/checkout@v3
+      - name: Generate Action
+        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
+        run: bash cargo-deny-generator.sh
+        working-directory: ./.github/cargo-deny-composite-action/
+        env:
+          GOPATH: ${{ runner.workspace }}/kata-containers
+      - name: Run Action
+        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
+        uses: ./.github/cargo-deny-composite-action

.github/workflows/darwin-tests.yaml

@@ -5,20 +5,16 @@ on:
       - edited
       - reopened
       - synchronize
-
+    paths-ignore: [ '**.md', '**.png', '**.jpg', '**.jpeg', '**.svg', '/docs/**' ]
 name: Darwin tests
 jobs:
   test:
-    strategy:
-      matrix:
-        go-version: [1.16.x, 1.17.x]
-        os: [macos-latest]
-    runs-on: ${{ matrix.os }}
+    runs-on: macos-latest
     steps:
     - name: Install Go
       uses: actions/setup-go@v2
       with:
-        go-version: ${{ matrix.go-version }}
+        go-version: 1.19.3
     - name: Checkout code
       uses: actions/checkout@v2
     - name: Build utils

.github/workflows/docs-url-alive-check.yaml

@@ -5,11 +5,7 @@ on:
 name: Docs URL Alive Check
 jobs:
   test:
-    strategy:
-      matrix:
-        go-version: [1.17.x]
-        os: [ubuntu-20.04]
-    runs-on: ${{ matrix.os }}
+    runs-on: ubuntu-20.04
     # don't run this action on forks
     if: github.repository_owner == 'kata-containers'
     env:
@@ -18,7 +14,7 @@ jobs:
     - name: Install Go
       uses: actions/setup-go@v2
       with:
-        go-version: ${{ matrix.go-version }}
+        go-version: 1.19.3
       env:
         GOPATH: ${{ runner.workspace }}/kata-containers
     - name: Set env

.github/workflows/kata-deploy-push.yaml

@@ -18,6 +18,7 @@ jobs:
       matrix:
         asset:
           - kernel
+          - kernel-dragonball-experimental
           - shim-v2
           - qemu
           - cloud-hypervisor
@@ -25,14 +26,9 @@ jobs:
           - rootfs-image
           - rootfs-initrd
           - virtiofsd
+          - nydus
     steps:
       - uses: actions/checkout@v2
-      - name: Install docker
-        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-        run: |
-          curl -fsSL https://test.docker.com -o test-docker.sh
-          sh test-docker.sh
-
       - name: Build ${{ matrix.asset }}
         if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
         run: |

.github/workflows/kata-deploy-test.yaml

@@ -1,5 +1,10 @@
 on:
   workflow_dispatch: # this is used to trigger the workflow on non-main branches
+    inputs:
+      pr:
+        description: 'PR number from the selected branch to test'
+        type: string
+        required: true
   issue_comment:
     types: [created, edited]
 
@@ -13,19 +18,20 @@ jobs:
       && github.event_name == 'issue_comment'
       && github.event.action == 'created'
       && startsWith(github.event.comment.body, '/test_kata_deploy')
+      || github.event_name == 'workflow_dispatch'
     steps:
-      - name: Check membership
+      - name: Check membership on comment or dispatch
         uses: kata-containers/is-organization-member@1.0.1
         id: is_organization_member
         with:
           organization: kata-containers
-          username: ${{ github.event.comment.user.login }}
+          username: ${{ github.event.comment.user.login || github.event.sender.login }}
           token: ${{ secrets.GITHUB_TOKEN }}
       - name: Fail if not member
         run: |
           result=${{ steps.is_organization_member.outputs.result }}
           if [ $result == false ]; then
-              user=${{ github.event.comment.user.login }}
+              user=${{ github.event.comment.user.login || github.event.sender.login }}
               echo Either ${user} is not part of the kata-containers organization
               echo or ${user} has its Organization Visibility set to Private at
               echo https://github.com/orgs/kata-containers/people?query=${user}
@@ -44,6 +50,8 @@ jobs:
           - cloud-hypervisor
           - firecracker
           - kernel
+          - kernel-dragonball-experimental
+          - nydus
           - qemu
           - rootfs-image
           - rootfs-initrd
@@ -53,18 +61,17 @@ jobs:
       - name: get-PR-ref
         id: get-PR-ref
         run: |
-            ref=$(cat $GITHUB_EVENT_PATH | jq -r '.issue.pull_request.url' | sed  's#^.*\/pulls#refs\/pull#' | sed 's#$#\/merge#')
-            echo "reference for PR: " ${ref}
+            if [ ${{ github.event_name }} == 'issue_comment' ]; then
+                ref=$(cat $GITHUB_EVENT_PATH | jq -r '.issue.pull_request.url' | sed  's#^.*\/pulls#refs\/pull#' | sed 's#$#\/merge#')
+            else # workflow_dispatch
+                ref="refs/pull/${{ github.event.inputs.pr }}/merge"
+            fi
+            echo "reference for PR: " ${ref} "event:" ${{ github.event_name }}
             echo "##[set-output name=pr-ref;]${ref}"
       - uses: actions/checkout@v2
         with:
           ref: ${{ steps.get-PR-ref.outputs.pr-ref }}
 
-      - name: Install docker
-        run: |
-          curl -fsSL https://test.docker.com -o test-docker.sh
-          sh test-docker.sh
-
       - name: Build ${{ matrix.asset }}
         run: |
           make "${KATA_ASSET}-tarball"
@@ -89,8 +96,12 @@ jobs:
       - name: get-PR-ref
         id: get-PR-ref
         run: |
-            ref=$(cat $GITHUB_EVENT_PATH | jq -r '.issue.pull_request.url' | sed  's#^.*\/pulls#refs\/pull#' | sed 's#$#\/merge#')
-            echo "reference for PR: " ${ref}
+            if [ ${{ github.event_name }} == 'issue_comment' ]; then
+                ref=$(cat $GITHUB_EVENT_PATH | jq -r '.issue.pull_request.url' | sed  's#^.*\/pulls#refs\/pull#' | sed 's#$#\/merge#')
+            else # workflow_dispatch
+                ref="refs/pull/${{ github.event.inputs.pr }}/merge"
+            fi
+            echo "reference for PR: " ${ref} "event:" ${{ github.event_name }}
             echo "##[set-output name=pr-ref;]${ref}"
       - uses: actions/checkout@v2
         with:
@@ -116,8 +127,12 @@ jobs:
       - name: get-PR-ref
         id: get-PR-ref
         run: |
-            ref=$(cat $GITHUB_EVENT_PATH | jq -r '.issue.pull_request.url' | sed  's#^.*\/pulls#refs\/pull#' | sed 's#$#\/merge#')
-            echo "reference for PR: " ${ref}
+            if [ ${{ github.event_name }} == 'issue_comment' ]; then
+                ref=$(cat $GITHUB_EVENT_PATH | jq -r '.issue.pull_request.url' | sed  's#^.*\/pulls#refs\/pull#' | sed 's#$#\/merge#')
+            else # workflow_dispatch
+                ref="refs/pull/${{ github.event.inputs.pr }}/merge"
+            fi
+            echo "reference for PR: " ${ref} "event:" ${{ github.event_name }}
             echo "##[set-output name=pr-ref;]${ref}"
       - uses: actions/checkout@v2
         with:

.github/workflows/release.yaml

@@ -13,6 +13,8 @@ jobs:
           - cloud-hypervisor
           - firecracker
           - kernel
+          - kernel-dragonball-experimental
+          - nydus
           - qemu
           - rootfs-image
           - rootfs-initrd
@@ -20,11 +22,6 @@ jobs:
           - virtiofsd
     steps:
       - uses: actions/checkout@v2
-      - name: Install docker
-        run: |
-          curl -fsSL https://test.docker.com -o test-docker.sh
-          sh test-docker.sh
-
       - name: Build ${{ matrix.asset }}
         run: |
           ./tools/packaging/kata-deploy/local-build/kata-deploy-copy-yq-installer.sh

.github/workflows/snap-release.yaml

@@ -4,6 +4,9 @@ on:
     tags:
       - '[0-9]+.[0-9]+.[0-9]+*'
 
+env:
+  SNAPCRAFT_STORE_CREDENTIALS: ${{ secrets.snapcraft_token }}
+
 jobs:
   release-snap:
     runs-on: ubuntu-20.04
@@ -14,9 +17,16 @@ jobs:
           fetch-depth: 0
 
       - name: Install Snapcraft
-        uses: samuelmeuli/action-snapcraft@v1
-        with:
-          snapcraft_token: ${{ secrets.snapcraft_token }}
+        run: |
+          # Required to avoid snapcraft install failure
+          sudo chown root:root /
+
+          # "--classic" is needed for the GitHub action runner
+          # environment.
+          sudo snap install snapcraft --classic
+
+          # Allow other parts to access snap binaries
+          echo /snap/bin >> "$GITHUB_PATH"
 
       - name: Build snap
         run: |

.github/workflows/snap.yaml

@@ -6,6 +6,7 @@ on:
       - synchronize
       - reopened
       - edited
+    paths-ignore: [ '**.md', '**.png', '**.jpg', '**.jpeg', '**.svg', '/docs/**' ]
 
 jobs:
   test:
@@ -19,7 +20,16 @@ jobs:
 
       - name: Install Snapcraft
         if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-        uses: samuelmeuli/action-snapcraft@v1
+        run: |
+          # Required to avoid snapcraft install failure
+          sudo chown root:root /
+
+          # "--classic" is needed for the GitHub action runner
+          # environment.
+          sudo snap install snapcraft --classic
+
+          # Allow other parts to access snap binaries
+          echo /snap/bin >> "$GITHUB_PATH"
 
       - name: Build snap
         if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}

.github/workflows/static-checks-dragonball.yaml

@@ -0,0 +1,33 @@
+on:
+  pull_request:
+    types:
+      - opened
+      - edited
+      - reopened
+      - synchronize
+    paths-ignore: [ '**.md', '**.png', '**.jpg', '**.jpeg', '**.svg', '/docs/**' ]
+
+name: Static checks dragonball
+jobs:
+  test-dragonball:
+    runs-on: self-hosted
+    env:
+      RUST_BACKTRACE: "1"
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set env
+        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
+        run: |
+          echo "GOPATH=${{ github.workspace }}" >> $GITHUB_ENV
+      - name: Install Rust
+        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
+        run: |
+          ./ci/install_rust.sh
+          PATH=$PATH:"$HOME/.cargo/bin"
+      - name: Run Unit Test
+        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
+        run: |
+          cd src/dragonball
+          cargo version
+          rustc --version
+          sudo -E env PATH=$PATH LIBC=gnu SUPPORT_VIRTUALIZATION=true make test

.github/workflows/static-checks.yaml

@@ -8,12 +8,16 @@ on:
 
 name: Static checks
 jobs:
-  test:
+  static-checks:
+    runs-on: ubuntu-20.04
     strategy:
       matrix:
-        go-version: [1.16.x, 1.17.x]
-        os: [ubuntu-20.04]
-    runs-on: ${{ matrix.os }}
+        cmd:
+          - "make vendor"
+          - "make static-checks"
+          - "make check"
+          - "make test"
+          - "sudo -E PATH=\"$PATH\" make test"
     env:
       TRAVIS: "true"
       TRAVIS_BRANCH: ${{ github.base_ref }}
@@ -22,13 +26,33 @@ jobs:
       RUST_BACKTRACE: "1"
       target_branch: ${{ github.base_ref }}
     steps:
-    - name: Install Go
-      if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-      uses: actions/setup-go@v2
+    - name: Checkout code
+      uses: actions/checkout@v3
       with:
-        go-version: ${{ matrix.go-version }}
+        fetch-depth: 0
+        path: ./src/github.com/${{ github.repository }}
+    - name: Install Go
+      uses: actions/setup-go@v3
+      with:
+        go-version: 1.19.3
       env:
         GOPATH: ${{ runner.workspace }}/kata-containers
+    - name: Check kernel config version
+      run: |
+        cd "${{ github.workspace }}/src/github.com/${{ github.repository }}"
+        kernel_dir="tools/packaging/kernel/"
+        kernel_version_file="${kernel_dir}kata_config_version"
+        modified_files=$(git diff --name-only origin/main..HEAD)
+        result=$(git whatchanged origin/main..HEAD "${kernel_dir}" >>"/dev/null")
+        if git whatchanged origin/main..HEAD "${kernel_dir}" >>"/dev/null"; then
+          echo "Kernel directory has changed, checking if $kernel_version_file has been updated"
+          if echo "$modified_files" | grep -v "README.md" | grep "${kernel_dir}" >>"/dev/null"; then
+            echo "$modified_files" | grep "$kernel_version_file" >>/dev/null || ( echo "Please bump version in $kernel_version_file" && exit 1)
+          else
+            echo "Readme file changed, no need for kernel config version update."
+          fi
+          echo "Check passed"
+        fi
     - name: Setup GOPATH
       if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
       run: |
@@ -41,12 +65,6 @@ jobs:
       run: |
         echo "GOPATH=${{ github.workspace }}" >> $GITHUB_ENV
         echo "${{ github.workspace }}/bin" >> $GITHUB_PATH
-    - name: Checkout code
-      if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-      uses: actions/checkout@v2
-      with:
-        fetch-depth: 0
-        path: ./src/github.com/${{ github.repository }}
     - name: Setup travis references
       if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
       run: |
@@ -66,6 +84,7 @@ jobs:
         rustup target add x86_64-unknown-linux-musl
         rustup component add rustfmt clippy
     - name: Setup seccomp
+      if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
       run: |
         libseccomp_install_dir=$(mktemp -d -t libseccomp.XXXXXXXXXX)
         gperf_install_dir=$(mktemp -d -t gperf.XXXXXXXXXX)
@@ -73,24 +92,7 @@ jobs:
         echo "Set environment variables for the libseccomp crate to link the libseccomp library statically"
         echo "LIBSECCOMP_LINK_TYPE=static" >> $GITHUB_ENV
         echo "LIBSECCOMP_LIB_PATH=${libseccomp_install_dir}/lib" >> $GITHUB_ENV
-    # Check whether the vendored code is up-to-date & working as the first thing
-    - name: Check vendored code
+    - name: Run check
       if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
       run: |
-        cd ${GOPATH}/src/github.com/${{ github.repository }} && make vendor
-    - name: Static Checks
-      if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-      run: |
-        cd ${GOPATH}/src/github.com/${{ github.repository }} && make static-checks
-    - name: Run Compiler Checks
-      if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-      run: |
-        cd ${GOPATH}/src/github.com/${{ github.repository }} && make check
-    - name: Run Unit Tests
-      if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-      run: |
-        cd ${GOPATH}/src/github.com/${{ github.repository }} && make test
-    - name: Run Unit Tests As Root User
-      if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-      run: |
-        cd ${GOPATH}/src/github.com/${{ github.repository }} && sudo -E PATH="$PATH" make test
+        cd ${GOPATH}/src/github.com/${{ github.repository }} && ${{ matrix.cmd }}

.gitignore

@@ -4,6 +4,8 @@
 **/*.rej
 **/target
 **/.vscode
+**/.idea
+**/.fleet
 pkg/logging/Cargo.lock
 src/agent/src/version.rs
 src/agent/kata-agent.service
@@ -11,4 +13,3 @@ src/agent/protocols/src/*.rs
 !src/agent/protocols/src/lib.rs
 build
 src/tools/log-parser/kata-log-parser
-

Makefile

@@ -8,6 +8,7 @@ COMPONENTS =
 
 COMPONENTS += libs
 COMPONENTS += agent
+COMPONENTS += dragonball
 COMPONENTS += runtime
 COMPONENTS += runtime-rs
 
@@ -15,11 +16,12 @@ COMPONENTS += runtime-rs
 TOOLS =
 
 TOOLS += agent-ctl
-TOOLS += trace-forwarder
-TOOLS += runk
+TOOLS += kata-ctl
 TOOLS += log-parser
+TOOLS += runk
+TOOLS += trace-forwarder
 
-STANDARD_TARGETS = build check clean install test vendor
+STANDARD_TARGETS = build check clean install static-checks-build test vendor
 
 default: all
 
@@ -35,7 +37,7 @@ generate-protocols:
 	make -C src/agent generate-protocols
 
 # Some static checks rely on generated source files of components.
-static-checks: build
+static-checks: static-checks-build
 	bash ci/static-checks.sh
 
 docs-url-alive-check:
@@ -43,10 +45,8 @@ docs-url-alive-check:
 
 .PHONY: \
 	all \
-	binary-tarball \
+	kata-tarball \
+	install-tarball \
 	default \
-	install-binary-tarball \
 	static-checks \
 	docs-url-alive-check
-
-

README.md

@@ -117,11 +117,10 @@ The table below lists the core parts of the project:
 | Component | Type | Description |
 |-|-|-|
 | [runtime](src/runtime) | core | Main component run by a container manager and providing a containerd shimv2 runtime implementation. |
+| [runtime-rs](src/runtime-rs) | core | The Rust version runtime. |
 | [agent](src/agent) | core | Management process running inside the virtual machine / POD that sets up the container environment. |
-| [libraries](src/libs) | core | Library crates shared by multiple Kata Container components or published to [`crates.io`](https://crates.io/index.html) |
 | [`dragonball`](src/dragonball) | core | An optional built-in VMM brings out-of-the-box Kata Containers experience with optimizations on container workloads |
 | [documentation](docs) | documentation | Documentation common to all components (such as design and install documentation). |
-| [libraries](src/libs) | core | Library crates shared by multiple Kata Container components or published to [`crates.io`](https://crates.io/index.html) |
 | [tests](https://github.com/kata-containers/tests) | tests | Excludes unit tests which live with the main code. |
 
 ### Additional components
@@ -134,6 +133,7 @@ The table below lists the remaining parts of the project:
 | [kernel](https://www.kernel.org) | kernel | Linux kernel used by the hypervisor to boot the guest image. Patches are stored [here](tools/packaging/kernel). |
 | [osbuilder](tools/osbuilder) | infrastructure | Tool to create "mini O/S" rootfs and initrd images and kernel for the hypervisor. |
 | [`agent-ctl`](src/tools/agent-ctl) | utility | Tool that provides low-level access for testing the agent. |
+| [`kata-ctl`](src/tools/kata-ctl) | utility | Tool that provides advanced commands and debug facilities. |
 | [`trace-forwarder`](src/tools/trace-forwarder) | utility | Agent tracing helper. |
 | [`runk`](src/tools/runk) | utility | Standard OCI container runtime based on the agent. |
 | [`ci`](https://github.com/kata-containers/ci) | CI | Continuous Integration configuration files and scripts. |

VERSION

@@ -1 +1 @@
-3.0.0-alpha0
+3.1.1

ci/install_libseccomp.sh

@@ -23,25 +23,27 @@ arch=${ARCH:-$(uname -m)}
 workdir="$(mktemp -d --tmpdir build-libseccomp.XXXXX)"
 
 # Variables for libseccomp
-# Currently, specify the libseccomp version directly without using `versions.yaml`
-# because the current Snap workflow is incomplete.
-# After solving the issue, replace this code by using the `versions.yaml`.
-# libseccomp_version=$(get_version "externals.libseccomp.version")
-# libseccomp_url=$(get_version "externals.libseccomp.url")
-libseccomp_version="2.5.1"
-libseccomp_url="https://github.com/seccomp/libseccomp"
+libseccomp_version="${LIBSECCOMP_VERSION:-""}"
+if [ -z "${libseccomp_version}" ]; then
+    libseccomp_version=$(get_version "externals.libseccomp.version")
+fi
+libseccomp_url="${LIBSECCOMP_URL:-""}"
+if [ -z "${libseccomp_url}" ]; then
+    libseccomp_url=$(get_version "externals.libseccomp.url")
+fi
 libseccomp_tarball="libseccomp-${libseccomp_version}.tar.gz"
 libseccomp_tarball_url="${libseccomp_url}/releases/download/v${libseccomp_version}/${libseccomp_tarball}"
 cflags="-O2"
 
 # Variables for gperf
-# Currently, specify the gperf version directly without using `versions.yaml`
-# because the current Snap workflow is incomplete.
-# After solving the issue, replace this code by using the `versions.yaml`.
-# gperf_version=$(get_version "externals.gperf.version")
-# gperf_url=$(get_version "externals.gperf.url")
-gperf_version="3.1"
-gperf_url="https://ftp.gnu.org/gnu/gperf"
+gperf_version="${GPERF_VERSION:-""}"
+if [ -z "${gperf_version}" ]; then
+    gperf_version=$(get_version "externals.gperf.version")
+fi
+gperf_url="${GPERF_URL:-""}"
+if [ -z "${gperf_url}" ]; then
+    gperf_url=$(get_version "externals.gperf.url")
+fi
 gperf_tarball="gperf-${gperf_version}.tar.gz"
 gperf_tarball_url="${gperf_url}/${gperf_tarball}"
 

ci/install_yq.sh

@@ -43,6 +43,16 @@ function install_yq() {
 	"aarch64")
 		goarch=arm64
 		;;
+	"arm64")
+		# If we're on an apple silicon machine, just assign amd64. 
+		# The version of yq we use doesn't have a darwin arm build, 
+		# but Rosetta can come to the rescue here.
+		if [ $goos == "Darwin" ]; then 
+			goarch=amd64
+		else 
+			goarch=arm64
+		fi
+		;;
 	"ppc64le")
 		goarch=ppc64le
 		;;
@@ -64,7 +74,7 @@ function install_yq() {
 	fi
 
 	## NOTE: ${var,,} => gives lowercase value of var
-	local yq_url="https://${yq_pkg}/releases/download/${yq_version}/yq_${goos,,}_${goarch}"
+	local yq_url="https://${yq_pkg}/releases/download/${yq_version}/yq_${goos}_${goarch}"
 	curl -o "${yq_path}" -LSsf "${yq_url}"
 	[ $? -ne 0 ] && die "Download ${yq_url} failed"
 	chmod +x "${yq_path}"

ci/lib.sh

@@ -54,3 +54,13 @@ run_docs_url_alive_check()
 	git fetch -a
 	bash "$tests_repo_dir/.ci/static-checks.sh" --docs --all "github.com/kata-containers/kata-containers"
 }
+
+run_get_pr_changed_file_details()
+{
+	clone_tests_repo
+	# Make sure we have the targeting branch
+	git remote set-branches --add origin "${branch}"
+	git fetch -a
+	source "$tests_repo_dir/.ci/lib.sh"
+	get_pr_changed_file_details
+}

deny.toml

@@ -0,0 +1,33 @@
+targets = [
+    { triple = "x86_64-apple-darwin" },
+    { triple = "x86_64-unknown-linux-gnu" },
+    { triple = "x86_64-unknown-linux-musl" },
+]
+
+[advisories]
+vulnerability = "deny"
+unsound = "deny"
+unmaintained = "deny"
+ignore = ["RUSTSEC-2020-0071"]
+
+[bans]
+multiple-versions = "allow"
+deny = [
+    { name = "cmake" },
+    { name = "openssl-sys" },
+]
+
+[licenses]
+unlicensed = "deny"
+allow-osi-fsf-free = "neither"
+copyleft = "allow"
+# We want really high confidence when inferring licenses from text
+confidence-threshold = 0.93
+allow = ["0BSD", "Apache-2.0", "BSD-2-Clause", "BSD-3-Clause", "CC0-1.0", "ISC", "MIT", "MPL-2.0"]
+private = { ignore = true}
+
+exceptions = []
+
+[sources]
+unknown-registry = "allow"
+unknown-git = "allow"

docs/Developer-Guide.md

@@ -33,51 +33,41 @@ You need to install the following to build Kata Containers components:
 - `make`.
 - `gcc` (required for building the shim and runtime).
 
-# Build and install the Kata Containers runtime
+# Build and install Kata Containers
+## Build and install the Kata Containers runtime
 
-```
-$ go get -d -u github.com/kata-containers/kata-containers
-$ cd $GOPATH/src/github.com/kata-containers/kata-containers/src/runtime
-$ make && sudo -E PATH=$PATH make install
+```bash
+$ git clone https://github.com/kata-containers/kata-containers.git
+$ pushd kata-containers/src/runtime
+$ make && sudo -E "PATH=$PATH" make install
+$ sudo mkdir -p /etc/kata-containers/
+$ sudo install -o root -g root -m 0640 /usr/share/defaults/kata-containers/configuration.toml /etc/kata-containers
+$ popd
 ```
 
 The build will create the following:
 
 - runtime binary: `/usr/local/bin/kata-runtime` and `/usr/local/bin/containerd-shim-kata-v2`
-- configuration file: `/usr/share/defaults/kata-containers/configuration.toml`
-
-# Check hardware requirements
-
-You can check if your system is capable of creating a Kata Container by running the following:
-
-```
-$ sudo kata-runtime check
-```
-
-If your system is *not* able to run Kata Containers, the previous command will error out and explain why.
+- configuration file: `/usr/share/defaults/kata-containers/configuration.toml` and `/etc/kata-containers/configuration.toml`
 
 ## Configure to use initrd or rootfs image
 
 Kata containers can run with either an initrd image or a rootfs image.
 
-If you want to test with `initrd`, make sure you have `initrd = /usr/share/kata-containers/kata-containers-initrd.img`
-in your configuration file, commenting out the `image` line:
+If you want to test with `initrd`, make sure you have uncommented `initrd = /usr/share/kata-containers/kata-containers-initrd.img`
+in your configuration file, commenting out the `image` line in
+`/etc/kata-containers/configuration.toml`. For example:
 
-`/usr/share/defaults/kata-containers/configuration.toml` and comment out the `image` line with the following. For example:
-
-```
-$ sudo mkdir -p /etc/kata-containers/
-$ sudo install -o root -g root -m 0640 /usr/share/defaults/kata-containers/configuration.toml /etc/kata-containers
+```bash
 $ sudo sed -i 's/^\(image =.*\)/# \1/g' /etc/kata-containers/configuration.toml
+$ sudo sed -i 's/^# \(initrd =.*\)/\1/g' /etc/kata-containers/configuration.toml
 ```
 You can create the initrd image as shown in the [create an initrd image](#create-an-initrd-image---optional) section.
 
-If you want to test with a rootfs `image`, make sure you have `image = /usr/share/kata-containers/kata-containers.img`
+If you want to test with a rootfs `image`, make sure you have uncommented `image = /usr/share/kata-containers/kata-containers.img`
 in your configuration file, commenting out the `initrd` line. For example:
 
-```
-$ sudo mkdir -p /etc/kata-containers/
-$ sudo install -o root -g root -m 0640 /usr/share/defaults/kata-containers/configuration.toml /etc/kata-containers
+```bash
 $ sudo sed -i 's/^\(initrd =.*\)/# \1/g' /etc/kata-containers/configuration.toml
 ```
 The rootfs image is created as shown in the [create a rootfs image](#create-a-rootfs-image) section.
@@ -90,19 +80,38 @@ rootfs `image`(100MB+).
 
 Enable seccomp as follows:
 
-```
+```bash
 $ sudo sed -i '/^disable_guest_seccomp/ s/true/false/' /etc/kata-containers/configuration.toml
 ```
 
 This will pass container seccomp profiles to the kata agent.
 
+## Enable SELinux on the guest
+
+> **Note:**
+>
+> - To enable SELinux on the guest, SELinux MUST be also enabled on the host.
+> - You MUST create and build a rootfs image for SELinux in advance.
+>   See [Create a rootfs image](#create-a-rootfs-image) and [Build a rootfs image](#build-a-rootfs-image).
+> - SELinux on the guest is supported in only a rootfs image currently, so
+>   you cannot enable SELinux with the agent init (`AGENT_INIT=yes`) yet.
+
+Enable guest SELinux in Enforcing mode as follows:
+
+```
+$ sudo sed -i '/^disable_guest_selinux/ s/true/false/g' /etc/kata-containers/configuration.toml
+```
+
+The runtime automatically will set `selinux=1` to the kernel parameters and `xattr` option to
+`virtiofsd` when `disable_guest_selinux` is set to `false`.
+
+If you want to enable SELinux in Permissive mode, add `enforcing=0` to the kernel parameters.
+
 ## Enable full debug
 
 Enable full debug as follows:
 
-```
-$ sudo mkdir -p /etc/kata-containers/
-$ sudo install -o root -g root -m 0640 /usr/share/defaults/kata-containers/configuration.toml /etc/kata-containers
+```bash
 $ sudo sed -i -e 's/^# *\(enable_debug\).*=.*$/\1 = true/g' /etc/kata-containers/configuration.toml
 $ sudo sed -i -e 's/^kernel_params = "\(.*\)"/kernel_params = "\1 agent.log=debug initcall_debug"/g' /etc/kata-containers/configuration.toml
 ```
@@ -175,7 +184,7 @@ and offers possible workarounds and fixes.
 it stores. When messages are suppressed, it is noted in the logs. This can be checked
 for by looking for those notifications, such as:
 
-```sh
+```bash
 $ sudo journalctl --since today | fgrep Suppressed
 Jun 29 14:51:17 mymachine systemd-journald[346]: Suppressed 4150 messages from /system.slice/docker.service
 ```
@@ -200,7 +209,7 @@ RateLimitBurst=0
 
 Restart `systemd-journald` for the changes to take effect:
 
-```sh
+```bash
 $ sudo systemctl restart systemd-journald
 ```
 
@@ -214,39 +223,52 @@ $ sudo systemctl restart systemd-journald
 
 The agent is built with a statically linked `musl.` The default `libc` used is `musl`, but on `ppc64le` and `s390x`, `gnu` should be used. To configure this:
 
-```
-$ export ARCH=$(uname -m)
+```bash
+$ export ARCH="$(uname -m)"
 $ if [ "$ARCH" = "ppc64le" -o "$ARCH" = "s390x" ]; then export LIBC=gnu; else export LIBC=musl; fi
-$ [ ${ARCH} == "ppc64le" ] && export ARCH=powerpc64le
-$ rustup target add ${ARCH}-unknown-linux-${LIBC}
+$ [ "${ARCH}" == "ppc64le" ] && export ARCH=powerpc64le
+$ rustup target add "${ARCH}-unknown-linux-${LIBC}"
 ```
 
 To build the agent:
 
-```
-$ go get -d -u github.com/kata-containers/kata-containers
-$ cd $GOPATH/src/github.com/kata-containers/kata-containers/src/agent && make
-```
-
 The agent is built with seccomp capability by default.
 If you want to build the agent without the seccomp capability, you need to run `make` with `SECCOMP=no` as follows.
 
+```bash
+$ make -C kata-containers/src/agent SECCOMP=no
 ```
-$ make -C $GOPATH/src/github.com/kata-containers/kata-containers/src/agent SECCOMP=no
+
+For building the agent with seccomp support using `musl`, set the environment
+variables for the [`libseccomp` crate](https://github.com/libseccomp-rs/libseccomp-rs).
+
+```bash
+$ export LIBSECCOMP_LINK_TYPE=static
+$ export LIBSECCOMP_LIB_PATH="the path of the directory containing libseccomp.a"
+$ make -C kata-containers/src/agent
 ```
 
+If the compilation fails when the agent tries to link the `libseccomp` library statically
+against `musl`, you will need to build `libseccomp` manually with `-U_FORTIFY_SOURCE`.
+You can use [our script](https://github.com/kata-containers/kata-containers/blob/main/ci/install_libseccomp.sh)
+to install `libseccomp` for the agent.
+
+```bash
+$ mkdir -p ${seccomp_install_path} ${gperf_install_path}
+$ kata-containers/ci/install_libseccomp.sh ${seccomp_install_path} ${gperf_install_path}
+$ export LIBSECCOMP_LIB_PATH="${seccomp_install_path}/lib"
+```
+
+On `ppc64le` and `s390x`, `glibc` is used. You will need to install the `libseccomp` library
+provided by your distribution.
+
+> e.g. `libseccomp-dev` for Ubuntu, or `libseccomp-devel` for CentOS
+
 > **Note:**
 >
 > - If you enable seccomp in the main configuration file but build the agent without seccomp capability,
 >   the runtime exits conservatively with an error message.
 
-## Get the osbuilder
-
-```
-$ go get -d -u github.com/kata-containers/kata-containers
-$ cd $GOPATH/src/github.com/kata-containers/kata-containers/tools/osbuilder
-```
-
 ## Create a rootfs image
 ### Create a local rootfs
 
@@ -254,24 +276,32 @@ As a prerequisite, you need to install Docker. Otherwise, you will not be
 able to run the `rootfs.sh` script with `USE_DOCKER=true` as expected in
 the following example.
 
-```
-$ export ROOTFS_DIR=${GOPATH}/src/github.com/kata-containers/kata-containers/tools/osbuilder/rootfs-builder/rootfs
-$ sudo rm -rf ${ROOTFS_DIR}
-$ cd $GOPATH/src/github.com/kata-containers/kata-containers/tools/osbuilder/rootfs-builder
-$ script -fec 'sudo -E GOPATH=$GOPATH USE_DOCKER=true ./rootfs.sh ${distro}'
+```bash
+$ export distro="ubuntu" # example
+$ export ROOTFS_DIR="$(realpath kata-containers/tools/osbuilder/rootfs-builder/rootfs)"
+$ sudo rm -rf "${ROOTFS_DIR}"
+$ pushd kata-containers/tools/osbuilder/rootfs-builder
+$ script -fec 'sudo -E USE_DOCKER=true ./rootfs.sh "${distro}"'
+$ popd
 ```
 
 You MUST choose a distribution (e.g., `ubuntu`) for `${distro}`.
 You can get a supported distributions list in the Kata Containers by running the following.
 
-```
-$ ./rootfs.sh -l
+```bash
+$ ./kata-containers/tools/osbuilder/rootfs-builder/rootfs.sh -l
 ```
 
 If you want to build the agent without seccomp capability, you need to run the `rootfs.sh` script with `SECCOMP=no` as follows.
 
+```bash
+$ script -fec 'sudo -E AGENT_INIT=yes USE_DOCKER=true SECCOMP=no ./rootfs.sh "${distro}"'
 ```
-$ script -fec 'sudo -E GOPATH=$GOPATH AGENT_INIT=yes USE_DOCKER=true SECCOMP=no ./rootfs.sh ${distro}'
+
+If you want to enable SELinux on the guest, you MUST choose `centos` and run the `rootfs.sh` script with `SELINUX=yes` as follows.
+
+```
+$ script -fec 'sudo -E GOPATH=$GOPATH USE_DOCKER=true SELINUX=yes ./rootfs.sh centos'
 ```
 
 > **Note:**
@@ -287,18 +317,32 @@ $ script -fec 'sudo -E GOPATH=$GOPATH AGENT_INIT=yes USE_DOCKER=true SECCOMP=no
 >
 > - You should only do this step if you are testing with the latest version of the agent.
 
-```
-$ sudo install -o root -g root -m 0550 -t ${ROOTFS_DIR}/usr/bin ../../../src/agent/target/x86_64-unknown-linux-musl/release/kata-agent
-$ sudo install -o root -g root -m 0440 ../../../src/agent/kata-agent.service ${ROOTFS_DIR}/usr/lib/systemd/system/
-$ sudo install -o root -g root -m 0440 ../../../src/agent/kata-containers.target ${ROOTFS_DIR}/usr/lib/systemd/system/
+```bash
+$ sudo install -o root -g root -m 0550 -t "${ROOTFS_DIR}/usr/bin" "${ROOTFS_DIR}/../../../../src/agent/target/x86_64-unknown-linux-musl/release/kata-agent"
+$ sudo install -o root -g root -m 0440 "${ROOTFS_DIR}/../../../../src/agent/kata-agent.service" "${ROOTFS_DIR}/usr/lib/systemd/system/"
+$ sudo install -o root -g root -m 0440 "${ROOTFS_DIR}/../../../../src/agent/kata-containers.target" "${ROOTFS_DIR}/usr/lib/systemd/system/"
 ```
 
 ### Build a rootfs image
 
+```bash
+$ pushd  kata-containers/tools/osbuilder/image-builder
+$ script -fec 'sudo -E USE_DOCKER=true ./image_builder.sh "${ROOTFS_DIR}"'
+$ popd
 ```
-$ cd $GOPATH/src/github.com/kata-containers/kata-containers/tools/osbuilder/image-builder
-$ script -fec 'sudo -E USE_DOCKER=true ./image_builder.sh ${ROOTFS_DIR}'
+
+If you want to enable SELinux on the guest, you MUST run the `image_builder.sh` script with `SELINUX=yes`
+to label the guest image as follows.
+To label the image on the host, you need to make sure that SELinux is enabled (`selinuxfs` is mounted) on the host
+and the rootfs MUST be created by running the `rootfs.sh` with `SELINUX=yes`.
+
 ```
+$ script -fec 'sudo -E USE_DOCKER=true SELINUX=yes ./image_builder.sh ${ROOTFS_DIR}'
+```
+
+Currently, the `image_builder.sh` uses `chcon` as an interim solution in order to apply `container_runtime_exec_t`
+to the `kata-agent`. Hence, if you run `restorecon` to the guest image after running the `image_builder.sh`,
+the `kata-agent` needs to be labeled `container_runtime_exec_t` again by yourself.
 
 > **Notes:**
 >
@@ -309,25 +353,31 @@ $ script -fec 'sudo -E USE_DOCKER=true ./image_builder.sh ${ROOTFS_DIR}'
 >   variable in the previous command and ensure the `qemu-img` command is
 >   available on your system.
 >   - If `qemu-img` is not installed, you will likely see errors such as `ERROR: File /dev/loop19p1 is not a block device` and `losetup: /tmp/tmp.bHz11oY851: Warning: file is smaller than 512 bytes; the loop device may be useless or invisible for system tools`. These can be mitigated by installing the `qemu-img` command (available in the `qemu-img` package on Fedora or the `qemu-utils` package on Debian).
+> - If `loop` module is not probed, you will likely see errors such as `losetup: cannot find an unused loop device`. Execute `modprobe loop` could resolve it.
 
 
 ### Install the rootfs image
 
-```
-$ commit=$(git log --format=%h -1 HEAD)
-$ date=$(date +%Y-%m-%d-%T.%N%z)
+```bash
+$ pushd kata-containers/tools/osbuilder/image-builder
+$ commit="$(git log --format=%h -1 HEAD)"
+$ date="$(date +%Y-%m-%d-%T.%N%z)"
 $ image="kata-containers-${date}-${commit}"
 $ sudo install -o root -g root -m 0640 -D kata-containers.img "/usr/share/kata-containers/${image}"
 $ (cd /usr/share/kata-containers && sudo ln -sf "$image" kata-containers.img)
+$ popd
 ```
 
 ## Create an initrd image - OPTIONAL
 ### Create a local rootfs for initrd image
-```
-$ export ROOTFS_DIR="${GOPATH}/src/github.com/kata-containers/kata-containers/tools/osbuilder/rootfs-builder/rootfs"
-$ sudo rm -rf ${ROOTFS_DIR}
-$ cd $GOPATH/src/github.com/kata-containers/kata-containers/tools/osbuilder/rootfs-builder
-$ script -fec 'sudo -E GOPATH=$GOPATH AGENT_INIT=yes USE_DOCKER=true ./rootfs.sh ${distro}'
+
+```bash
+$ export distro="ubuntu" # example
+$ export ROOTFS_DIR="$(realpath kata-containers/tools/osbuilder/rootfs-builder/rootfs)"
+$ sudo rm -rf "${ROOTFS_DIR}"
+$ pushd kata-containers/tools/osbuilder/rootfs-builder/
+$ script -fec 'sudo -E AGENT_INIT=yes USE_DOCKER=true ./rootfs.sh "${distro}"'
+$ popd
 ```
 `AGENT_INIT` controls if the guest image uses the Kata agent as the guest `init` process. When you create an initrd image,
 always set `AGENT_INIT` to `yes`.
@@ -335,14 +385,14 @@ always set `AGENT_INIT` to `yes`.
 You MUST choose a distribution (e.g., `ubuntu`) for `${distro}`.
 You can get a supported distributions list in the Kata Containers by running the following.
 
-```
-$ ./rootfs.sh -l
+```bash
+$ ./kata-containers/tools/osbuilder/rootfs-builder/rootfs.sh -l
 ```
 
 If you want to build the agent without seccomp capability, you need to run the `rootfs.sh` script with `SECCOMP=no` as follows.
 
-```
-$ script -fec 'sudo -E GOPATH=$GOPATH AGENT_INIT=yes USE_DOCKER=true SECCOMP=no ./rootfs.sh ${distro}'
+```bash
+$ script -fec 'sudo -E AGENT_INIT=yes USE_DOCKER=true SECCOMP=no ./rootfs.sh "${distro}"'
 ```
 
 > **Note:**
@@ -351,28 +401,31 @@ $ script -fec 'sudo -E GOPATH=$GOPATH AGENT_INIT=yes USE_DOCKER=true SECCOMP=no
 
 Optionally, add your custom agent binary to the rootfs with the following commands. The default `$LIBC` used
 is `musl`, but on ppc64le and s390x, `gnu` should be used. Also, Rust refers to ppc64le as `powerpc64le`:
-```
-$ export ARCH=$(uname -m)
-$ [ ${ARCH} == "ppc64le" ] || [ ${ARCH} == "s390x" ] && export LIBC=gnu || export LIBC=musl
-$ [ ${ARCH} == "ppc64le" ] && export ARCH=powerpc64le
-$ sudo install -o root -g root -m 0550 -T ../../../src/agent/target/${ARCH}-unknown-linux-${LIBC}/release/kata-agent ${ROOTFS_DIR}/sbin/init
+```bash
+$ export ARCH="$(uname -m)"
+$ [ "${ARCH}" == "ppc64le" ] || [ "${ARCH}" == "s390x" ] && export LIBC=gnu || export LIBC=musl
+$ [ "${ARCH}" == "ppc64le" ] && export ARCH=powerpc64le
+$ sudo install -o root -g root -m 0550 -T "${ROOTFS_DIR}/../../../../src/agent/target/${ARCH}-unknown-linux-${LIBC}/release/kata-agent" "${ROOTFS_DIR}/sbin/init"
 ```
 
 ### Build an initrd image
 
-```
-$ cd $GOPATH/src/github.com/kata-containers/kata-containers/tools/osbuilder/initrd-builder
-$ script -fec 'sudo -E AGENT_INIT=yes USE_DOCKER=true ./initrd_builder.sh ${ROOTFS_DIR}'
+```bash
+$ pushd kata-containers/tools/osbuilder/initrd-builder
+$ script -fec 'sudo -E AGENT_INIT=yes USE_DOCKER=true ./initrd_builder.sh "${ROOTFS_DIR}"'
+$ popd
 ```
 
 ### Install the initrd image
 
-```
-$ commit=$(git log --format=%h -1 HEAD)
-$ date=$(date +%Y-%m-%d-%T.%N%z)
+```bash
+$ pushd kata-containers/tools/osbuilder/initrd-builder
+$ commit="$(git log --format=%h -1 HEAD)"
+$ date="$(date +%Y-%m-%d-%T.%N%z)"
 $ image="kata-containers-initrd-${date}-${commit}"
 $ sudo install -o root -g root -m 0640 -D kata-containers-initrd.img "/usr/share/kata-containers/${image}"
 $ (cd /usr/share/kata-containers && sudo ln -sf "$image" kata-containers-initrd.img)
+$ popd
 ```
 
 # Install guest kernel images
@@ -391,44 +444,44 @@ Kata Containers makes use of upstream QEMU branch. The exact version
 and repository utilized can be found by looking at the [versions file](../versions.yaml).
 
 Find the correct version of QEMU from the versions file:
-```
-$ source ${GOPATH}/src/github.com/kata-containers/kata-containers/tools/packaging/scripts/lib.sh
-$ qemu_version=$(get_from_kata_deps "assets.hypervisor.qemu.version")
-$ echo ${qemu_version}
+```bash
+$ source kata-containers/tools/packaging/scripts/lib.sh
+$ qemu_version="$(get_from_kata_deps "assets.hypervisor.qemu.version")"
+$ echo "${qemu_version}"
 ```
 Get source from the matching branch of QEMU:
-```
-$ go get -d github.com/qemu/qemu
-$ cd ${GOPATH}/src/github.com/qemu/qemu
-$ git checkout ${qemu_version}
-$ your_qemu_directory=${GOPATH}/src/github.com/qemu/qemu
+```bash
+$ git clone -b "${qemu_version}" https://github.com/qemu/qemu.git
+$ your_qemu_directory="$(realpath qemu)"
 ```
 
 There are scripts to manage the build and packaging of QEMU. For the examples below, set your
 environment as:
-```
-$ go get -d github.com/kata-containers/kata-containers
-$ packaging_dir="${GOPATH}/src/github.com/kata-containers/kata-containers/tools/packaging"
+```bash
+$ packaging_dir="$(realpath kata-containers/tools/packaging)"
 ```
 
 Kata often utilizes patches for not-yet-upstream and/or backported fixes for components,
 including QEMU. These can be found in the [packaging/QEMU directory](../tools/packaging/qemu/patches),
 and it's *recommended* that you apply them. For example, suppose that you are going to build QEMU
 version 5.2.0, do:
-```
-$ cd $your_qemu_directory
-$ $packaging_dir/scripts/apply_patches.sh $packaging_dir/qemu/patches/5.2.x/
+```bash
+$ "$packaging_dir/scripts/apply_patches.sh" "$packaging_dir/qemu/patches/5.2.x/"
 ```
 
 To build utilizing the same options as Kata, you should make use of the `configure-hypervisor.sh` script. For example:
-```
-$ cd $your_qemu_directory
-$ $packaging_dir/scripts/configure-hypervisor.sh kata-qemu > kata.cfg
+```bash
+$ pushd "$your_qemu_directory"
+$ "$packaging_dir/scripts/configure-hypervisor.sh" kata-qemu > kata.cfg
 $ eval ./configure "$(cat kata.cfg)"
 $ make -j $(nproc --ignore=1)
+# Optional
 $ sudo -E make install
+$ popd
 ```
 
+If you do not want to install the respective QEMU version, the configuration file can be modified to point to the correct binary. In `/etc/kata-containers/configuration.toml`, change `path = "/path/to/qemu/build/qemu-system-x86_64"` to point to the correct QEMU binary.
+
 See the [static-build script for QEMU](../tools/packaging/static-build/qemu/build-static-qemu.sh) for a reference on how to get, setup, configure and build QEMU for Kata.
 
 ### Build a custom QEMU for aarch64/arm64 - REQUIRED
@@ -439,11 +492,33 @@ See the [static-build script for QEMU](../tools/packaging/static-build/qemu/buil
 >   under upstream review for supporting NVDIMM on aarch64.
 >
 You could build the custom `qemu-system-aarch64` as required with the following command:
+```bash
+$ git clone https://github.com/kata-containers/tests.git
+$ script -fec 'sudo -E tests/.ci/install_qemu.sh'
 ```
-$ go get -d github.com/kata-containers/tests
-$ script -fec 'sudo -E ${GOPATH}/src/github.com/kata-containers/tests/.ci/install_qemu.sh'
+
+## Build `virtiofsd`
+
+When using the file system type virtio-fs (default), `virtiofsd` is required
+
+```bash
+$ pushd kata-containers/tools/packaging/static-build/virtiofsd
+$ ./build.sh
+$ popd
 ```
 
+Modify `/etc/kata-containers/configuration.toml` and update value `virtio_fs_daemon = "/path/to/kata-containers/tools/packaging/static-build/virtiofsd/virtiofsd/virtiofsd"` to point to the binary.
+
+# Check hardware requirements
+
+You can check if your system is capable of creating a Kata Container by running the following:
+
+```bash
+$ sudo kata-runtime check
+```
+
+If your system is *not* able to run Kata Containers, the previous command will error out and explain why.
+
 # Run Kata Containers with Containerd
 Refer to the [How to use Kata Containers and Containerd](how-to/containerd-kata.md) how-to guide.
 
@@ -474,7 +549,7 @@ See [Set up a debug console](#set-up-a-debug-console).
 
 ## Checking Docker default runtime
 
-```
+```bash
 $ sudo docker info 2>/dev/null | grep -i "default runtime" | cut -d: -f2- | grep -q runc  && echo "SUCCESS" || echo "ERROR: Incorrect default Docker runtime"
 ```
 ## Set up a debug console
@@ -491,7 +566,7 @@ contain either `/bin/sh` or `/bin/bash`.
 
 Enable debug_console_enabled in the `configuration.toml` configuration file:
 
-```
+```toml
 [agent.kata]
 debug_console_enabled = true
 ```
@@ -502,7 +577,7 @@ This will pass `agent.debug_console agent.debug_console_vport=1026` to agent as
 
 For Kata Containers `2.0.x` releases, the `kata-runtime exec` command depends on the`kata-monitor` running, in order to get the sandbox's `vsock` address to connect to. Thus, first start the `kata-monitor` process.
 
-```
+```bash
 $ sudo kata-monitor
 ```
 
@@ -522,7 +597,7 @@ bash-4.2# exit
 exit
 ```
 
-`kata-runtime exec` has a command-line option `runtime-namespace`, which is used to specify under which [runtime namespace](https://github.com/containerd/containerd/blob/master/docs/namespaces.md) the particular pod was created. By default, it is set to `k8s.io` and works for containerd when configured
+`kata-runtime exec` has a command-line option `runtime-namespace`, which is used to specify under which [runtime namespace](https://github.com/containerd/containerd/blob/main/docs/namespaces.md) the particular pod was created. By default, it is set to `k8s.io` and works for containerd when configured
  with Kubernetes. For CRI-O, the namespace should set to `default` explicitly. This should not be confused with [Kubernetes namespaces](https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/).
 For other CRI-runtimes and configurations, you may need to set the namespace utilizing the `runtime-namespace` option.
 
@@ -564,10 +639,10 @@ an additional `coreutils` package.
 
 For example using CentOS:
 
-```
-$ cd $GOPATH/src/github.com/kata-containers/kata-containers/tools/osbuilder/rootfs-builder
-$ export ROOTFS_DIR=${GOPATH}/src/github.com/kata-containers/kata-containers/tools/osbuilder/rootfs-builder/rootfs
-$ script -fec 'sudo -E GOPATH=$GOPATH USE_DOCKER=true EXTRA_PKGS="bash coreutils" ./rootfs.sh centos'
+```bash
+$ pushd kata-containers/tools/osbuilder/rootfs-builder
+$ export ROOTFS_DIR="$(realpath ./rootfs)"
+$ script -fec 'sudo -E USE_DOCKER=true EXTRA_PKGS="bash coreutils" ./rootfs.sh centos'
 ```
 
 #### Build the debug image
@@ -582,9 +657,10 @@ Install the image:
 >**Note**: When using an initrd image, replace the below rootfs image name `kata-containers.img` 
 >with the initrd image name `kata-containers-initrd.img`.
 
-```
+```bash
 $ name="kata-containers-centos-with-debug-console.img"
 $ sudo install -o root -g root -m 0640 kata-containers.img "/usr/share/kata-containers/${name}"
+$ popd
 ```
 
 Next, modify the `image=` values in the `[hypervisor.qemu]` section of the
@@ -593,7 +669,7 @@ to specify the full path to the image name specified in the previous code
 section. Alternatively, recreate the symbolic link so it points to
 the new debug image:
 
-```
+```bash
 $ (cd /usr/share/kata-containers && sudo ln -sf "$name" kata-containers.img)
 ```
 
@@ -604,7 +680,7 @@ to avoid all subsequently created containers from using the debug image.
 
 Create a container as normal. For example using `crictl`:
 
-```
+```bash
 $ sudo crictl run -r kata container.yaml pod.yaml
 ```
 
@@ -617,7 +693,7 @@ those for firecracker / cloud-hypervisor.
 
 Add `agent.debug_console` to the guest kernel command line to allow the agent process to start a debug console. 
 
-```
+```bash
 $ sudo sed -i -e 's/^kernel_params = "\(.*\)"/kernel_params = "\1 agent.debug_console"/g' "${kata_configuration_file}"
 ```
 
@@ -638,7 +714,7 @@ between the host and the guest. The kernel command line option `agent.debug_cons
 
 Add the parameter `agent.debug_console_vport=1026` to the kernel command line
 as shown below:
-```
+```bash
 sudo sed -i -e 's/^kernel_params = "\(.*\)"/kernel_params = "\1 agent.debug_console_vport=1026"/g' "${kata_configuration_file}"
 ```
 
@@ -651,7 +727,7 @@ Next, connect to the debug console. The VSOCKS paths vary slightly between each
 VMM solution.
 
 In case of cloud-hypervisor, connect to the `vsock` as shown:
-```
+```bash
 $ sudo su -c 'cd /var/run/vc/vm/${sandbox_id}/root/ && socat stdin unix-connect:clh.sock'
 CONNECT 1026
 ```
@@ -659,7 +735,7 @@ CONNECT 1026
 **Note**: You need to type `CONNECT 1026` and press `RETURN` key after entering the `socat` command.
 
 For firecracker, connect to the `hvsock` as shown:
-```
+```bash
 $ sudo su -c 'cd /var/run/vc/firecracker/${sandbox_id}/root/ && socat stdin unix-connect:kata.hvsock'
 CONNECT 1026
 ```
@@ -668,7 +744,7 @@ CONNECT 1026
 
 
 For QEMU, connect to the `vsock` as shown:
-```
+```bash
 $ sudo su -c 'cd /var/run/vc/vm/${sandbox_id} && socat "stdin,raw,echo=0,escape=0x11" "unix-connect:console.sock"'
 ```
 
@@ -681,7 +757,7 @@ If the image is created using
 [osbuilder](../tools/osbuilder), the following YAML
 file exists and contains details of the image and how it was created:
 
-```
+```bash
 $ cat /var/lib/osbuilder/osbuilder.yaml
 ```
 

docs/Unit-Test-Advice.md

@@ -341,7 +341,7 @@ The main repository has the most comprehensive set of skip abilities. See:
 
 One method is to use the `nix` crate along with some custom macros:
 
-```
+```rust
 #[cfg(test)]
 mod tests {
     #[allow(unused_macros)]

docs/design/README.md

@@ -7,7 +7,9 @@ Kata Containers design documents:
 - [Design requirements for Kata Containers](kata-design-requirements.md)
 - [VSocks](VSocks.md)
 - [VCPU handling](vcpu-handling.md)
+- [VCPU threads pinning](vcpu-threads-pinning.md)
 - [Host cgroups](host-cgroups.md)
+- [Agent systemd cgroup](agent-systemd-cgroup.md)
 - [`Inotify` support](inotify.md)
 - [Metrics(Kata 2.0)](kata-2-0-metrics.md)
 - [Design for Kata Containers `Lazyload` ability with `nydus`](kata-nydus-design.md)

docs/design/agent-systemd-cgroup.md

@@ -0,0 +1,84 @@
+# Systemd Cgroup for Agent
+
+As we know, we can interact with cgroups in two ways, **`cgroupfs`** and **`systemd`**. The former is achieved by reading and writing cgroup `tmpfs` files under `/sys/fs/cgroup` while the latter is done by configuring a transient unit by requesting systemd. Kata agent uses **`cgroupfs`** by default, unless you pass the parameter `--systemd-cgroup`.
+
+## usage
+
+For systemd, kata agent configures cgroups according to the following `linux.cgroupsPath` format standard provided by `runc` (`[slice]:[prefix]:[name]`). If you don't provide a valid `linux.cgroupsPath`, kata agent will treat it as `"system.slice:kata_agent:<container-id>"`. 
+
+> Here slice is a systemd slice under which the container is placed. If empty, it defaults to system.slice, except when cgroup v2 is used and rootless container is created, in which case it defaults to user.slice.
+>
+> Note that slice can contain dashes to denote a sub-slice (e.g. user-1000.slice is a correct notation, meaning a `subslice` of user.slice), but it must not contain slashes (e.g. user.slice/user-1000.slice is invalid).
+>
+> A slice of `-` represents a root slice.
+>
+> Next, prefix and name are used to compose the unit name, which is `<prefix>-<name>.scope`, unless name has `.slice` suffix, in which case prefix is ignored and the name is used as is.
+
+## supported properties
+
+The kata agent will translate the parameters in the `linux.resources` of `config.json` into systemd unit properties, and send it to systemd for configuration. Since systemd supports limited properties, only the following parameters in `linux.resources` will be applied. We will simply treat hybrid mode as legacy mode by the way.
+
+- CPU
+
+  - v1
+
+  | runtime spec resource | systemd property name |
+  | --------------------- | --------------------- |
+  | `cpu.shares`          | `CPUShares`           |
+
+  - v2
+
+  | runtime spec resource      | systemd property name      |
+  | -------------------------- | -------------------------- |
+  | `cpu.shares`               | `CPUShares`                |
+  | `cpu.period`               | `CPUQuotaPeriodUSec`(v242) |
+  | `cpu.period` & `cpu.quota` | `CPUQuotaPerSecUSec`       |
+
+- MEMORY
+
+  - v1
+
+  | runtime spec resource | systemd property name |
+  | --------------------- | --------------------- |
+  | `memory.limit`        | `MemoryLimit`         |
+
+  - v2
+
+  | runtime spec resource          | systemd property name |
+  | ------------------------------ | --------------------- |
+  | `memory.low`                   | `MemoryLow`           |
+  | `memory.max`                   | `MemoryMax`           |
+  | `memory.swap` & `memory.limit` | `MemorySwapMax`       |
+
+- PIDS
+
+  | runtime spec resource | systemd property name |
+  | --------------------- | --------------------- |
+  | `pids.limit `         | `TasksMax`            |
+
+- CPUSET
+
+  | runtime spec resource | systemd property name      |
+  | --------------------- | -------------------------- |
+  | `cpuset.cpus`         | `AllowedCPUs`(v244)        |
+  | `cpuset.mems`         | `AllowedMemoryNodes`(v244) |
+
+## Systemd Interface
+
+`session.rs` and `system.rs` in `src/agent/rustjail/src/cgroups/systemd/interface` are automatically generated by `zbus-xmlgen`, which is is an accompanying tool provided by `zbus` to generate Rust code from `D-Bus XML interface descriptions`. The specific commands to generate these two files are as follows: 
+
+```shell
+// system.rs
+zbus-xmlgen --system org.freedesktop.systemd1 /org/freedesktop/systemd1
+// session.rs
+zbus-xmlgen --session org.freedesktop.systemd1 /org/freedesktop/systemd1
+```
+
+The current implementation of `cgroups/systemd` uses `system.rs` while `session.rs` could be used to build rootless containers in the future.
+
+## references
+
+- [runc - systemd cgroup driver](https://github.com/opencontainers/runc/blob/main/docs/systemd.md)
+
+- [systemd.resource-control  — Resource control unit settings](https://www.freedesktop.org/software/systemd/man/systemd.resource-control.html)
+

docs/design/architecture_3.0/README.md

@@ -64,8 +64,8 @@ The kata-runtime is controlled by TOKIO_RUNTIME_WORKER_THREADS to run the OS thr
   ├─ TTRPC listener thread(M * tokio task)
   ├─ TTRPC client handler thread(7 * M * tokio task)
   ├─ container stdin io thread(M * tokio task)
-  ├─ container stdin io thread(M * tokio task)
-  └─ container stdin io thread(M * tokio task)
+  ├─ container stdout io thread(M * tokio task)
+  └─ container stderr io thread(M * tokio task)
 ```
 ### Extensible Framework
 The Kata 3.x runtime is designed with the extension of service, runtime, and hypervisor, combined with configuration to meet the needs of different scenarios. At present, the service provides a register mechanism to support multiple services. Services could interact with runtime through messages. In addition, the runtime handler handles messages from services. To meet the needs of a binary that supports multiple runtimes and hypervisors, the startup must obtain the runtime handler type and hypervisor type through configuration.
@@ -81,31 +81,31 @@ In our case, there will be a variety of resources, and every resource has severa
 - Stage 2 (September): support common features
 - Stage 3: support full features
 
-| **Class**                  | **Sub-Class**       | **Development Stage** |
-| -------------------------- | ------------------- | --------------------- |
-| Service                    | task service        | Stage 1               |
-|                            | extend service      | Stage 3               |
-|                            | image service       | Stage 3               |
-| Runtime handler            | `Virt-Container`    | Stage 1               |
-|                            | `Wasm-Container`    | Stage 3               |
-|                            | `Linux-Container`   | Stage 3               |
-| Endpoint                   | VETH Endpoint       | Stage 1               |
-|                            | Physical Endpoint   | Stage 2               |
-|                            | Tap Endpoint        | Stage 2               |
-|                            | `Tuntap` Endpoint   | Stage 2               |
-|                            | `IPVlan` Endpoint   | Stage 3               |
-|                            | `MacVlan` Endpoint  | Stage 3               |
-|                            | MACVTAP Endpoint    | Stage 3               |
-|                            | `VhostUserEndpoint` | Stage 3               |
-| Network Interworking Model | Tc filter           | Stage 1               |
-|                            | `MacVtap`           | Stage 3               |
-| Storage                    | Virtio-fs           | Stage 1               |
-|                            | `nydus`             | Stage 2               |
-| Hypervisor                 | `Dragonball`        | Stage 1               |
-|                            | QEMU                | Stage 2               |
-|                            | ACRN                | Stage 3               |
-|                            | Cloud Hypervisor    | Stage 3               |
-|                            | Firecracker         | Stage 3               |
+| **Class**                  | **Sub-Class**       | **Development Stage** | **Status** |
+| -------------------------- | ------------------- | --------------------- |------------|
+| Service                    | task service        | Stage 1               |  ✅        |
+|                            | extend service      | Stage 3               |  🚫        |
+|                            | image service       | Stage 3               |  🚫        |
+| Runtime handler            | `Virt-Container`    | Stage 1               |  ✅        |
+| Endpoint                   | VETH Endpoint       | Stage 1               |  ✅        |
+|                            | Physical Endpoint   | Stage 2               |  ✅        |
+|                            | Tap Endpoint        | Stage 2               |  ✅        |
+|                            | `Tuntap` Endpoint   | Stage 2               |  ✅        |
+|                            | `IPVlan` Endpoint   | Stage 2               |  ✅        |
+|                            | `MacVlan` Endpoint  | Stage 2               |  ✅        |
+|                            | MACVTAP Endpoint    | Stage 3               |  🚫        |
+|                            | `VhostUserEndpoint` | Stage 3               |  🚫        |
+| Network Interworking Model | Tc filter           | Stage 1               |  ✅        |
+|                            | `MacVtap`           | Stage 3               |  🚧        |
+| Storage                    | Virtio-fs           | Stage 1               |  ✅        |
+|                            | `nydus`             | Stage 2               |  🚧        |
+|                            | `device mapper`     | Stage 2               |  🚫        |
+| `Cgroup V2`                |                     | Stage 2               |  🚧        |
+| Hypervisor                 | `Dragonball`        | Stage 1               |  🚧        |
+|                            | QEMU                | Stage 2               |  🚫        |
+|                            | ACRN                | Stage 3               |  🚫        |
+|                            | Cloud Hypervisor    | Stage 3               |  🚫        |
+|                            | Firecracker         | Stage 3               |  🚫        |
 
 ## FAQ
 

docs/design/direct-blk-device-assignment.md

@@ -81,7 +81,7 @@ Notes: given that the `mountInfo` is persisted to the disk by the Kata runtime,
 Instead of the CSI node driver writing the mount info into a `csiPlugin.json` file under the volume root, 
 as described in the original proposal, here we propose that the CSI node driver passes the mount information to 
 the Kata Containers runtime through a new `kata-runtime` commandline command. The `kata-runtime` then writes the mount 
-information to a `mount-info.json` file in a predefined location (`/run/kata-containers/shared/direct-volumes/[volume_path]/`).
+information to a `mountInfo.json` file in a predefined location (`/run/kata-containers/shared/direct-volumes/[volume_path]/`).
 
 When the Kata Containers runtime starts a container, it verifies whether a volume mount is a direct-assigned volume by checking 
 whether there is a `mountInfo` file under the computed Kata `direct-volumes` directory. If it is, the runtime parses the `mountInfo` file, 

docs/design/vcpu-threads-pinning.md

@@ -0,0 +1,37 @@
+# Design Doc for Kata Containers' VCPUs Pinning Feature
+
+## Background
+By now, vCPU threads of Kata Containers are scheduled randomly to CPUs. And each pod would request a specific set of CPUs which we call it CPU set (just the CPU set meaning in Linux cgroups).    
+
+If the number of vCPU threads are equal to that of CPUs claimed in CPU set, we can then pin each vCPU thread to one specified CPU, to reduce the cost of random scheduling. 
+
+## Detailed Design
+
+### Passing Config Parameters
+Two ways are provided to use this vCPU thread pinning feature: through `QEMU` configuration file and through annotations. Finally the pinning parameter is passed to `HypervisorConfig`.
+
+### Related Linux Thread Scheduling API
+
+| API Info          | Value                                                     |
+|-------------------|-----------------------------------------------------------|
+| Package           | `golang.org/x/sys/unix`                                     |
+| Method            | `unix.SchedSetaffinity(thread_id, &unixCPUSet)`             |
+| Official Doc Page | https://pkg.go.dev/golang.org/x/sys/unix#SchedSetaffinity |
+
+### When is VCPUs Pinning Checked?
+
+As shown in Section 1, when `num(vCPU threads) == num(CPUs in CPU set)`, we shall pin each vCPU thread to a specified CPU. And when this condition is broken, we should restore to the original random scheduling pattern.  
+So when may `num(CPUs in CPU set)` change? There are 5 possible scenes:
+
+| Possible scenes                   | Related Code                               |
+|-----------------------------------|--------------------------------------------|
+| when creating a container         | File Sandbox.go, in method `CreateContainer`  |
+| when starting a container         | File Sandbox.go, in method `StartContainer`   |
+| when deleting a container         | File Sandbox.go, in method `DeleteContainer`  |
+| when updating a container         | File Sandbox.go, in method `UpdateContainer`  |
+| when creating multiple containers | File Sandbox.go, in method `createContainers` |
+
+### Core Pinning Logics
+
+We can split the whole process into the following steps. Related methods are `checkVCPUsPinning` and `resetVCPUsPinning`, in file Sandbox.go.
+![](arch-images/vcpus-pinning-process.png) 

docs/design/virtualization.md

@@ -110,7 +110,7 @@ Devices and features used:
 - VFIO
 - hotplug
 - seccomp filters
-- [HTTP OpenAPI](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/vmm/src/api/openapi/cloud-hypervisor.yaml)
+- [HTTP OpenAPI](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/main/vmm/src/api/openapi/cloud-hypervisor.yaml)
 
 ### Summary
 

docs/how-to/README.md

@@ -42,4 +42,6 @@
 - [How to setup swap devices in guest kernel](how-to-setup-swap-devices-in-guest-kernel.md)
 - [How to run rootless vmm](how-to-run-rootless-vmm.md)
 - [How to run Docker with Kata Containers](how-to-run-docker-with-kata.md)
-- [How to run Kata Containers with `nydus`](how-to-use-virtio-fs-nydus-with-kata.md)
+- [How to run Kata Containers with `nydus`](how-to-use-virtio-fs-nydus-with-kata.md)
+- [How to run Kata Containers with AMD SEV-SNP](how-to-run-kata-containers-with-SNP-VMs.md)
+- [How to use EROFS to build rootfs in Kata Containers](how-to-use-erofs-build-rootfs.md)

docs/how-to/containerd-kata.md

@@ -77,8 +77,8 @@ $ command -v containerd
 You can manually install CNI plugins as follows:
 
 ```bash
-$ go get github.com/containernetworking/plugins
-$ pushd $GOPATH/src/github.com/containernetworking/plugins
+$ git clone https://github.com/containernetworking/plugins.git
+$ pushd plugins
 $ ./build_linux.sh
 $ sudo mkdir /opt/cni
 $ sudo cp -r bin /opt/cni/
@@ -93,8 +93,8 @@ $ popd
 You can install the `cri-tools` from source code:
 
 ```bash
-$ go get github.com/kubernetes-sigs/cri-tools
-$ pushd $GOPATH/src/github.com/kubernetes-sigs/cri-tools
+$ git clone https://github.com/kubernetes-sigs/cri-tools.git
+$ pushd cri-tools
 $ make
 $ sudo -E make install
 $ popd
@@ -257,6 +257,48 @@ This launches a BusyBox container named `hello`, and it will be removed by `--rm
 The `--cni` flag enables CNI networking for the container. Without this flag, a container with just a
 loopback interface is created.
 
+### Launch containers using `ctr` command line with rootfs bundle
+
+#### Get rootfs
+Use the script to create rootfs
+```bash
+ctr i pull quay.io/prometheus/busybox:latest
+ctr i export rootfs.tar quay.io/prometheus/busybox:latest
+
+rootfs_tar=rootfs.tar
+bundle_dir="./bundle"
+mkdir -p "${bundle_dir}"
+
+# extract busybox rootfs
+rootfs_dir="${bundle_dir}/rootfs"
+mkdir -p "${rootfs_dir}"
+layers_dir="$(mktemp -d)"
+tar -C "${layers_dir}" -pxf "${rootfs_tar}"
+for ((i=0;i<$(cat ${layers_dir}/manifest.json | jq -r ".[].Layers | length");i++)); do
+  tar -C ${rootfs_dir} -xf ${layers_dir}/$(cat ${layers_dir}/manifest.json | jq -r ".[].Layers[${i}]")
+done
+```
+#### Get `config.json`
+Use runc spec to generate `config.json`
+```bash
+cd ./bundle/rootfs
+runc spec
+mv config.json ../
+```
+Change the root `path` in `config.json` to the absolute path of rootfs
+
+```JSON
+"root":{
+    "path":"/root/test/bundle/rootfs",
+    "readonly": false
+},
+```
+
+#### Run container
+```bash
+sudo ctr run -d --runtime io.containerd.run.kata.v2 --config bundle/config.json hello
+sudo ctr t exec --exec-id ${ID} -t hello sh
+```
 ### Launch Pods with `crictl` command line
 
 With the `crictl` command line of `cri-tools`, you can specify runtime class with `-r` or `--runtime` flag.

docs/how-to/how-to-hotplug-memory-arm64.md

@@ -15,6 +15,18 @@ $ sudo .ci/aarch64/install_rom_aarch64.sh
 $ popd
 ```
 
+## Config KATA QEMU
+
+After executing the above script, two files will be generated under the directory `/usr/share/kata-containers/` by default, namely `kata-flash0.img` and `kata-flash1.img`. Next we need to change the configuration file of `kata qemu`, which is in `/opt/kata/share/defaults/kata-containers/configuration-qemu.toml` by default, specify in the configuration file to use the UEFI ROM installed above. The above is an example of `kata deploy` installation. For package management installation, please use `kata-runtime env` to find the location of the configuration file. Please refer to the following configuration.
+
+```
+[hypervisor.qemu]
+
+# -pflash can add image file to VM. The arguments of it should be in format
+# of ["/path/to/flash0.img", "/path/to/flash1.img"]
+pflashes = ["/usr/share/kata-containers/kata-flash0.img", "/usr/share/kata-containers/kata-flash1.img"]
+```
+
 ## Run for test
 
 Let's test if the memory hotplug is ready for Kata after install the UEFI ROM. Make sure containerd is ready to run Kata before test.

docs/how-to/how-to-run-kata-containers-with-SNP-VMs.md

@@ -0,0 +1,159 @@
+# Kata Containers with AMD SEV-SNP VMs
+
+## Disclaimer
+
+This guide is designed for developers and is - same as the Developer Guide - not intended for production systems or end users. It is advisable to only follow this guide on non-critical development systems.
+
+## Prerequisites
+
+To run  Kata Containers in SNP-VMs, the following software stack is used.
+
+![Kubernetes integration with shimv2](./images/SNP-stack.svg)
+
+The host BIOS and kernel must be capable of supporting AMD SEV-SNP and configured accordingly. For Kata Containers, the host kernel with branch [`sev-snp-iommu-avic_5.19-rc6_v3`](https://github.com/AMDESE/linux/tree/sev-snp-iommu-avic_5.19-rc6_v3) and commit [`3a88547`](https://github.com/AMDESE/linux/commit/3a885471cf89156ea555341f3b737ad2a8d9d3d0) is known to work in conjunction with SEV Firmware version 1.51.3 (0xh\_1.33.03) available on AMD's [SEV developer website](https://developer.amd.com/sev/). See [AMD's guide](https://github.com/AMDESE/AMDSEV/tree/sev-snp-devel) to configure the host accordingly. Verify that you are able to run SEV-SNP encrypted VMs first. The guest components required for Kata Containers are built as described below.
+
+**Tip**: It is easiest to first have Kata Containers running on your system and then modify it to run containers in SNP-VMs. Follow the [Developer guide](../Developer-Guide.md#warning) and then follow the below steps. Nonetheless, you can just follow this guide from the start.
+
+## How to build
+
+Follow all of the below steps to install Kata Containers with SNP-support from scratch. These steps mostly follow the developer guide with modifications to support SNP
+
+__Steps from the Developer Guide:__
+- Get all the [required components](../Developer-Guide.md#requirements-to-build-individual-components) for building the kata-runtime
+- [Build the and install kata-runtime](../Developer-Guide.md#build-and-install-the-kata-containers-runtime)
+- [Build a custom agent](../Developer-Guide.md#build-a-custom-kata-agent---optional)
+- [Create an initrd image](../Developer-Guide.md#create-an-initrd-image---optional) by first building a rootfs, then building the initrd based on the rootfs, use a custom agent and install. `ubuntu` works as the distribution of choice.
+- Get the [required components](../../tools/packaging/kernel/README.md#requirements) to build a custom kernel
+
+__SNP-specific steps:__
+- Build the SNP-specific kernel as shown below (see this [guide](../../tools/packaging/kernel/README.md#build-kata-containers-kernel) for more information)
+```bash
+$ pushd kata-containers/tools/packaging/kernel/
+$ ./build-kernel.sh -a x86_64 -x snp setup
+$ ./build-kernel.sh -a x86_64 -x snp build
+$ sudo -E PATH="${PATH}" ./build-kernel.sh -x snp install
+$ popd
+```
+- Build a current OVMF capable of SEV-SNP:
+```bash
+$ pushd kata-containers/tools/packaging/static-build/ovmf
+$ ./build.sh
+$ tar -xvf edk2-x86_64.tar.gz
+$ popd
+```
+- Build a custom QEMU
+```bash
+$ source kata-containers/tools/packaging/scripts/lib.sh
+$ qemu_url="$(get_from_kata_deps "assets.hypervisor.qemu.snp.url")"
+$ qemu_branch="$(get_from_kata_deps "assets.hypervisor.qemu.snp.branch")"
+$ qemu_commit="$(get_from_kata_deps "assets.hypervisor.qemu.snp.commit")"
+$ git clone -b "${qemu_branch}" "${qemu_url}"
+$ pushd qemu
+$ git checkout "${qemu_commit}"
+$ ./configure --enable-virtfs --target-list=x86_64-softmmu --enable-debug
+$ make -j "$(nproc)"
+$ popd
+```
+
+### Kata Containers Configuration for SNP
+
+The configuration file located at `/etc/kata-containers/configuration.toml` must be adapted as follows to support SNP-VMs:
+- Use the SNP-specific kernel for the guest VM (change path)
+```toml
+kernel = "/usr/share/kata-containers/vmlinuz-snp.container"
+```
+- Enable the use of an initrd (uncomment)
+```toml
+initrd = "/usr/share/kata-containers/kata-containers-initrd.img"
+```
+- Disable the use of a rootfs (comment out)
+```toml
+# image = "/usr/share/kata-containers/kata-containers.img"
+```
+- Use the custom QEMU capable of SNP (change path)
+```toml
+path = "/path/to/qemu/build/qemu-system-x86_64"
+```
+- Use `virtio-9p` device since `virtio-fs` is unsupported due to bugs / shortcomings in QEMU version [`snp-v3`](https://github.com/AMDESE/qemu/tree/snp-v3) for SEV and SEV-SNP (change value)
+```toml
+shared_fs = "virtio-9p"
+```
+- Disable `virtiofsd` since it is no longer required (comment out)
+```toml
+# virtio_fs_daemon = "/usr/libexec/virtiofsd"
+```
+- Disable NVDIMM (uncomment)
+```toml
+disable_image_nvdimm = true
+```
+- Disable shared memory (uncomment)
+```toml
+file_mem_backend = ""
+```
+- Enable confidential guests (uncomment)
+```toml
+confidential_guest = true
+```
+- Enable SNP-VMs (uncomment)
+```toml
+sev_snp_guest = true
+```
+  - Configure an OVMF (add path)
+```toml
+firmware = "/path/to/kata-containers/tools/packaging/static-build/ovmf/opt/kata/share/ovmf/OVMF.fd"
+```
+
+## Test Kata Containers with Containerd
+
+With Kata Containers configured to support SNP-VMs, we use containerd to test and deploy containers in these VMs.
+
+### Install Containerd
+If not already present, follow [this guide](./containerd-kata.md#install) to install containerd and its related components including `CNI` and the `cri-tools` (skip Kata Containers since we already installed it)
+
+### Containerd Configuration
+
+Follow [this guide](./containerd-kata.md#configuration) to configure containerd to use Kata Containers
+
+## Run Kata Containers in SNP-VMs
+
+Run the below commands to start a container. See [this guide](./containerd-kata.md#run) for more information
+```bash
+$ sudo ctr image pull docker.io/library/busybox:latest
+$ sudo ctr run --cni --runtime io.containerd.run.kata.v2 -t --rm docker.io/library/busybox:latest hello sh
+```
+
+### Check for active SNP:
+
+Inside the running container, run the following commands to check if SNP is active. It should look something like this:
+```
+/ # dmesg | grep -i sev
+[    0.299242] Memory Encryption Features active: AMD SEV SEV-ES SEV-SNP
+[    0.472286] SEV: Using SNP CPUID table, 31 entries present.
+[    0.514574] SEV: SNP guest platform device initialized.
+[    0.885425] sev-guest sev-guest: Initialized SEV guest driver (using vmpck_id 0)
+```
+
+### Obtain an SNP Attestation Report
+
+To obtain an attestation report inside the container, the `/dev/sev-guest` must first be configured. As of now, the VM does not perform this step, however it can be performed inside the container, either in the terminal or in code.
+
+Example for shell:
+```
+/ # SNP_MAJOR=$(cat /sys/devices/virtual/misc/sev-guest/dev | awk -F: '{print $1}')
+/ # SNP_MINOR=$(cat /sys/devices/virtual/misc/sev-guest/dev | awk -F: '{print $2}')
+/ # mknod -m 600 /dev/sev-guest c "${SNP_MAJOR}" "${SNP_MINOR}"
+```
+
+## Known Issues
+
+- Support for cgroups v2 is still [work in progress](https://github.com/kata-containers/kata-containers/issues/927). If issues occur due to cgroups v2 becoming the default in newer systems, one possible solution is to downgrade cgroups to v1:
+```bash
+sudo sed -i 's/^\(GRUB_CMDLINE_LINUX=".*\)"/\1 systemd.unified_cgroup_hierarchy=0"/' /etc/default/grub
+sudo update-grub
+sudo reboot
+```
+- If both SEV and SEV-SNP are supported by the host, Kata Containers uses SEV-SNP by default. You can verify what features are enabled by checking `/sys/module/kvm_amd/parameters/sev` and `sev_snp`. This means that Kata Containers can not run both SEV-SNP-VMs and SEV-VMs at the same time. If SEV is to be used by Kata Containers instead, reload the `kvm_amd` kernel module without SNP-support, this will disable SNP-support for the entire platform.
+```bash
+sudo rmmod kvm_amd && sudo modprobe kvm_amd sev_snp=0
+```
+

docs/how-to/how-to-set-sandbox-config-kata.md

@@ -57,6 +57,7 @@ There are several kinds of Kata configurations and they are listed below.
 | `io.katacontainers.config.hypervisor.enable_iothreads` | `boolean`| enable IO to be processed in a separate thread. Supported currently for virtio-`scsi` driver |
 | `io.katacontainers.config.hypervisor.enable_mem_prealloc` | `boolean` | the memory space used for `nvdimm` device by the hypervisor |
 | `io.katacontainers.config.hypervisor.enable_vhost_user_store` | `boolean` | enable vhost-user storage device (QEMU) |
+| `io.katacontainers.config.hypervisor.vhost_user_reconnect_timeout_sec` | `string`| the timeout for reconnecting vhost user socket (QEMU) 
 | `io.katacontainers.config.hypervisor.enable_virtio_mem` | `boolean` | enable virtio-mem (QEMU) |
 | `io.katacontainers.config.hypervisor.entropy_source` (R) | string| the path to a host source of entropy (`/dev/random`, `/dev/urandom` or real hardware RNG device) |
 | `io.katacontainers.config.hypervisor.file_mem_backend` (R) | string | file based memory backend root directory |
@@ -87,7 +88,7 @@ There are several kinds of Kata configurations and they are listed below.
 | `io.katacontainers.config.hypervisor.use_vsock` | `boolean` | specify use of `vsock` for agent communication |
 | `io.katacontainers.config.hypervisor.vhost_user_store_path` (R) | `string` | specify the directory path where vhost-user devices related folders, sockets and device nodes should be (QEMU) |
 | `io.katacontainers.config.hypervisor.virtio_fs_cache_size` | uint32 | virtio-fs DAX cache size in `MiB` |
-| `io.katacontainers.config.hypervisor.virtio_fs_cache` | string | the cache mode for virtio-fs, valid values are `always`, `auto` and `none` |
+| `io.katacontainers.config.hypervisor.virtio_fs_cache` | string | the cache mode for virtio-fs, valid values are `always`, `auto` and `never` |
 | `io.katacontainers.config.hypervisor.virtio_fs_daemon` | string | virtio-fs `vhost-user` daemon path |
 | `io.katacontainers.config.hypervisor.virtio_fs_extra_args` | string | extra options passed to `virtiofs` daemon |
 | `io.katacontainers.config.hypervisor.enable_guest_swap` | `boolean` | enable swap in the guest |

docs/how-to/how-to-setup-swap-devices-in-guest-kernel.md

@@ -17,9 +17,9 @@ Enable setup swap device in guest kernel as follows:
 $ sudo sed -i -e 's/^#enable_guest_swap.*$/enable_guest_swap = true/g' /etc/kata-containers/configuration.toml
 ```
 
-## Run a Kata Container utilizing swap device
+## Run a Kata Containers utilizing swap device
 
-Use following command to start a Kata Container with swappiness 60 and 1GB swap device (swap_in_bytes - memory_limit_in_bytes).
+Use following command to start a Kata Containers with swappiness 60 and 1GB swap device (swap_in_bytes - memory_limit_in_bytes).
 ```
 $ pod_yaml=pod.yaml
 $ container_yaml=container.yaml
@@ -43,12 +43,12 @@ command:
 - top
 EOF
 $ sudo crictl pull $image
-$ podid=$(sudo crictl runp $pod_yaml)
+$ podid=$(sudo crictl runp --runtime kata $pod_yaml)
 $ cid=$(sudo crictl create $podid $container_yaml $pod_yaml)
 $ sudo crictl start $cid
 ```
 
-Kata Container setups swap device for this container only when `io.katacontainers.container.resource.swappiness` is set.
+Kata Containers setups swap device for this container only when `io.katacontainers.container.resource.swappiness` is set.
 
 The following table shows the swap size how to decide if `io.katacontainers.container.resource.swappiness` is set.
 |`io.katacontainers.container.resource.swap_in_bytes`|`memory_limit_in_bytes`|swap size|

docs/how-to/how-to-use-erofs-build-rootfs.md

@@ -0,0 +1,90 @@
+# Configure Kata Containers to use EROFS build rootfs
+
+## Introduction
+For kata containers, rootfs is used in the read-only way. EROFS can noticeably decrease metadata overhead.
+
+`mkfs.erofs` can generate compressed and uncompressed EROFS images.
+
+For uncompressed images, no files are compressed. However, it is optional to inline the data blocks at the end of the file with the metadata.
+
+For compressed images, each file will be compressed using the lz4 or lz4hc algorithm, and it will be confirmed whether it can save space. Use No compression of the file if compression does not save space.
+
+## Performance comparison
+|                 | EROFS | EXT4 | XFS |
+|-----------------|-------| --- | --- |
+| Image Size [MB] | 106(uncompressed) | 256 | 126 |
+
+
+## Guidance
+### Install the `erofs-utils`
+#### `apt/dnf` install
+On newer `Ubuntu/Debian` systems, it can be installed directly using the `apt` command, and on `Fedora` it can be installed directly using the `dnf` command.
+
+```shell
+# Debian/Ubuntu
+$ apt install erofs-utils
+# Fedora
+$ dnf install erofs-utils
+```
+
+#### Source install
+[https://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs-utils.git](https://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs-utils.git)
+
+##### Compile dependencies
+If you need to enable the `Lz4` compression feature, `Lz4 1.8.0+` is required, and `Lz4 1.9.3+` is strongly recommended.
+
+##### Compilation process
+For some old lz4 versions (lz4-1.8.0~1.8.3), if lz4-static is not installed, the lz4hc algorithm will not be supported. lz4-static can be installed with apt install lz4-static.x86_64. However, these versions have some bugs in compression, and it is not recommended to use these versions directly.
+If you use `lz4 1.9.0+`, you can directly use the following command to compile.
+
+```shell
+$ ./autogen.sh
+$ ./configure
+$ make
+```
+
+The compiled `mkfs.erofs` program will be saved in the `mkfs` directory. Afterwards, the generated tools can be installed to a system directory using make install (requires root privileges).
+
+### Create a local rootfs
+```shell
+$ export distro="ubuntu"
+$ export FS_TYPE="erofs"
+$ export ROOTFS_DIR="realpath kata-containers/tools/osbuilder/rootfs-builder/rootfs"
+$ sudo rm -rf "${ROOTFS_DIR}"
+$ pushd kata-containers/tools/osbuilder/rootfs-builder
+$ script -fec 'sudo -E SECCOMP=no ./rootfs.sh "${distro}"'
+$ popd
+```
+
+### Add a custom agent to the image - OPTIONAL
+> Note:
+> - You should only do this step if you are testing with the latest version of the agent.
+```shell
+$ sudo install -o root -g root -m 0550 -t "${ROOTFS_DIR}/usr/bin" "${ROOTFS_DIR}/../../../../src/agent/target/x86_64-unknown-linux-musl/release/kata-agent"
+$ sudo install -o root -g root -m 0440 "${ROOTFS_DIR}/../../../../src/agent/kata-agent.service" "${ROOTFS_DIR}/usr/lib/systemd/system/"
+$ sudo install -o root -g root -m 0440 "${ROOTFS_DIR}/../../../../src/agent/kata-containers.target" "${ROOTFS_DIR}/usr/lib/systemd/system/"
+```
+
+### Build a root image
+```shell
+$ pushd  kata-containers/tools/osbuilder/image-builder
+$ script -fec 'sudo -E ./image_builder.sh "${ROOTFS_DIR}"'
+$ popd
+```
+
+### Install the rootfs image
+```shell
+$ pushd kata-containers/tools/osbuilder/image-builder
+$ commit="$(git log --format=%h -1 HEAD)"
+$ date="$(date +%Y-%m-%d-%T.%N%z)"
+$ rootfs="erofs"
+$ image="kata-containers-${rootfs}-${date}-${commit}"
+$ sudo install -o root -g root -m 0640 -D kata-containers.img "/usr/share/kata-containers/${image}"
+$ (cd /usr/share/kata-containers && sudo ln -sf "$image" kata-containers.img)
+$ popd
+```
+
+### Use `EROFS` in the runtime
+```shell
+$ sudo sed -i -e 's/^# *\(rootfs_type\).*=.*$/\1 = erofs/g' /etc/kata-containers/configuration.toml
+```

docs/how-to/how-to-use-kata-containers-with-firecracker.md

@@ -104,7 +104,7 @@ sudo dmsetup create "${POOL_NAME}" \
 
 cat << EOF
 #
-# Add this to your config.toml configuration file and restart `containerd` daemon
+# Add this to your config.toml configuration file and restart containerd daemon
 #
 [plugins]
   [plugins.devmapper]
@@ -212,7 +212,7 @@ Next, we need to configure containerd. Add a file in your path (e.g. `/usr/local
 
 ```
 #!/bin/bash
-KATA_CONF_FILE=/etc/containers/configuration-fc.toml /usr/local/bin/containerd-shim-kata-v2 $@
+KATA_CONF_FILE=/etc/kata-containers/configuration-fc.toml /usr/local/bin/containerd-shim-kata-v2 $@
 ```
 > **Note:** You may need to edit the paths of the configuration file and the `containerd-shim-kata-v2` to correspond to your setup.
 

docs/install/kata-containers-3.0-rust-runtime-installation-guide.md

@@ -24,7 +24,7 @@ architectures:
 
 | Installation method                                  | Description                                                                                  | Automatic updates | Use case                                                                                      | Availability
 |------------------------------------------------------|----------------------------------------------------------------------------------------------|-------------------|-----------------------------------------------------------------------------------------------|----------- |
-| [Using kata-deploy](#kata-deploy-installation)       | The preferred way to deploy the Kata Containers distributed binaries on a Kubernetes cluster | **No!**           | Best way to give it a try on kata-containers on an already up and running Kubernetes cluster. | No |
+| [Using kata-deploy](#kata-deploy-installation)       | The preferred way to deploy the Kata Containers distributed binaries on a Kubernetes cluster | **No!**           | Best way to give it a try on kata-containers on an already up and running Kubernetes cluster. | Yes |
 | [Using official distro packages](#official-packages) | Kata packages provided by Linux distributions official repositories                          | yes               | Recommended for most users. | No |                                                                   
 | [Using snap](#snap-installation)                     | Easy to install                                                                              | yes               | Good alternative to official distro packages.                                                 | No |
 | [Automatic](#automatic-installation)                 | Run a single command to install a full system                                                | **No!**           | For those wanting the latest release quickly.                                                 | No |
@@ -32,7 +32,8 @@ architectures:
 | [Build from source](#build-from-source-installation) | Build the software components manually                                                       | **No!**           | Power users and developers only.  | Yes |              
 
 ### Kata Deploy Installation
-`ToDo`
+
+Follow the [`kata-deploy`](../../tools/packaging/kata-deploy/README.md).
 ### Official packages
 `ToDo`
 ### Snap Installation
@@ -48,14 +49,14 @@ architectures:
 
 * Download `Rustup` and install  `Rust`
     > **Notes:**
-    > Rust version 1.58 is needed
+    > Rust version 1.62.0 is needed
 
     Example for `x86_64`
     ```
     $ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
     $ source $HOME/.cargo/env
-    $ rustup install 1.58
-    $ rustup default 1.58-x86_64-unknown-linux-gnu
+    $ rustup install 1.62.0
+    $ rustup default 1.62.0-x86_64-unknown-linux-gnu
     ```
 
 * Musl support for fully static binary
@@ -83,7 +84,7 @@ $ git clone https://github.com/kata-containers/kata-containers.git
 $ cd kata-containers/src/runtime-rs
 $ make && sudo make install
 ```
-After running the command above, the default config file `configuration.toml` will be installed under `/usr/share/defaults/kata-containers/`,  the binary file `containerd-shim-kata-v2` will be installed under `/user/local/bin` .
+After running the command above, the default config file `configuration.toml` will be installed under `/usr/share/defaults/kata-containers/`,  the binary file `containerd-shim-kata-v2` will be installed under `/usr/local/bin/` .
 
 ### Build Kata Containers Kernel
 Follow the [Kernel installation guide](/tools/packaging/kernel/README.md).

docs/install/minikube-installation-guide.md

@@ -55,11 +55,11 @@ Here are the features to set up a CRI-O based Minikube, and why you need them:
 
 | what | why |
 | ---- | --- |
-| `--bootstrapper=kubeadm` | As recommended for [minikube CRI-o](https://kubernetes.io/docs/setup/minikube/#cri-o) |
+| `--bootstrapper=kubeadm` | As recommended for [minikube CRI-O](https://minikube.sigs.k8s.io/docs/handbook/config/#runtime-configuration) |
 | `--container-runtime=cri-o` | Using CRI-O for Kata |
-| `--enable-default-cni` | As recommended for [minikube CRI-o](https://kubernetes.io/docs/setup/minikube/#cri-o) |
+| `--enable-default-cni` | As recommended for [minikube CRI-O](https://minikube.sigs.k8s.io/docs/handbook/config/#runtime-configuration) |
 | `--memory 6144` | Allocate sufficient memory, as Kata Containers default to 1 or 2Gb |
-| `--network-plugin=cni` | As recommended for [minikube CRI-o](https://kubernetes.io/docs/setup/minikube/#cri-o) |
+| `--network-plugin=cni` | As recommended for [minikube CRI-O](https://minikube.sigs.k8s.io/docs/handbook/config/#runtime-configuration) |
 | `--vm-driver kvm2` | The host VM driver |
 
 To use containerd, modify the `--container-runtime` argument:
@@ -71,12 +71,6 @@ To use containerd, modify the `--container-runtime` argument:
 > **Notes:**
 > - Adjust the `--memory 6144` line to suit your environment and requirements. Kata Containers default to
 > requesting 2048MB per container. We recommended you supply more than that to the Minikube node.
-> - Prior to Minikube/Kubernetes v1.14, the beta `RuntimeClass` feature also needed enabling with
-> the following.
->
-> | what | why |
-> | ---- | --- |
-> | `--feature-gates=RuntimeClass=true` | Kata needs to use the `RuntimeClass` Kubernetes feature |
 
 The full command is therefore:
 
@@ -138,17 +132,9 @@ $ kubectl -n kube-system exec ${podname} -- ps -ef | fgrep infinity
 
 ## Enabling Kata Containers
 
-> **Note:** Only Minikube/Kubernetes versions <= 1.13 require this step. Since version
-> v1.14, the `RuntimeClass` is enabled by default. Performing this step on Kubernetes > v1.14 is
-> however benign.
-
 Now you have installed the Kata Containers components in the Minikube node. Next, you need to configure
 Kubernetes `RuntimeClass` to know when to use Kata Containers to run a pod.
 
-```sh
-$ kubectl apply -f https://raw.githubusercontent.com/kubernetes/node-api/master/manifests/runtimeclass_crd.yaml > runtimeclass_crd.yaml
-```
-
 ### Register the runtime
 
 Now register the `kata qemu` runtime with that class. This should result in no errors:

docs/use-cases/NVIDIA-GPU-passthrough-and-Kata.md

@@ -545,6 +545,12 @@ Create the hook execution file for Kata:
 /usr/bin/nvidia-container-toolkit -debug $@
 ```
 
+Make sure the hook shell is executable:
+
+```sh
+chmod +x $ROOTFS_DIR/usr/share/oci/hooks/prestart/nvidia-container-toolkit.sh
+```
+
 As the last step one can do some cleanup of files or package caches. Build the
 rootfs and configure it for use with Kata according to the development guide.
 

docs/use-cases/using-Intel-QAT-and-kata.md

@@ -49,7 +49,7 @@ the latest driver.
 $ export QAT_DRIVER_VER=qat1.7.l.4.14.0-00031.tar.gz
 $ export QAT_DRIVER_URL=https://downloadmirror.intel.com/30178/eng/${QAT_DRIVER_VER}
 $ export QAT_CONF_LOCATION=~/QAT_conf
-$ export QAT_DOCKERFILE=https://raw.githubusercontent.com/intel/intel-device-plugins-for-kubernetes/master/demo/openssl-qat-engine/Dockerfile
+$ export QAT_DOCKERFILE=https://raw.githubusercontent.com/intel/intel-device-plugins-for-kubernetes/main/demo/openssl-qat-engine/Dockerfile
 $ export QAT_SRC=~/src/QAT
 $ export GOPATH=~/src/go
 $ export KATA_KERNEL_LOCATION=~/kata

docs/use-cases/using-Intel-SGX-and-kata.md

@@ -61,6 +61,9 @@ spec:
           name: eosgx-demo-job-1
           image: oeciteam/oe-helloworld:latest
           imagePullPolicy: IfNotPresent
+          volumeMounts:
+          - mountPath: /dev
+            name: dev-mount
           securityContext:
             readOnlyRootFilesystem: true
             capabilities:

docs/use-cases/using-SPDK-vhostuser-and-kata.md

@@ -197,11 +197,6 @@ vhost_user_store_path = "<Path of the base directory for vhost-user device>"
 > under `[hypervisor.qemu]` section.
 
 
-For the subdirectories of `vhost_user_store_path`: `block` is used for block
-device; `block/sockets` is where we expect UNIX domain sockets for vhost-user
-block devices to live; `block/devices` is where simulated block device nodes
-for vhost-user block devices are created.
-
 For the subdirectories of `vhost_user_store_path`:
 -  `block` is used for block device;
 -  `block/sockets` is where we expect UNIX domain sockets for vhost-user

snap/snapcraft.yaml

@@ -82,8 +82,39 @@ parts:
       fi
       rustup component add rustfmt
 
+  docker:
+    after: [metadata]
+    plugin: nil
+    prime:
+      - -*
+    build-packages:
+      - ca-certificates
+      - containerd
+      - curl
+      - gnupg
+      - lsb-release
+      - runc
+    override-build: |
+      source "${SNAPCRAFT_PROJECT_DIR}/snap/local/snap-common.sh"
+
+      curl -fsSL https://download.docker.com/linux/ubuntu/gpg |\
+          sudo gpg --batch --yes --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg
+      distro_codename=$(lsb_release -cs)
+      echo "deb [arch=${dpkg_arch} signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/ubuntu ${distro_codename} stable" |\
+          sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
+      sudo apt-get -y update
+      sudo apt-get -y install docker-ce docker-ce-cli containerd.io
+
+      echo "Unmasking docker service"
+      sudo -E systemctl unmask docker.service || true
+      sudo -E systemctl unmask docker.socket || true
+      echo "Adding $USER into docker group"
+      sudo -E gpasswd -a $USER docker
+      echo "Starting docker"
+      sudo -E systemctl start docker || true
+
   image:
-    after: [godeps, qemu, kernel]
+    after: [godeps, docker, qemu, kernel]
     plugin: nil
     build-packages:
       - docker.io
@@ -107,14 +138,6 @@ parts:
       # Copy yq binary. It's used in the container
       cp -a "${yq}" "${GOPATH}/bin/"
 
-      echo "Unmasking docker service"
-      sudo -E systemctl unmask docker.service || true
-      sudo -E systemctl unmask docker.socket || true
-      echo "Adding $USER into docker group"
-      sudo -E gpasswd -a $USER docker
-      echo "Starting docker"
-      sudo -E systemctl start docker || true
-
       cd "${kata_dir}/tools/osbuilder"
 
       # build image
@@ -206,7 +229,7 @@ parts:
 
       # Install raw kernel
       vmlinux_path="vmlinux"
-      [ "${arch}" = "s390x" ] && vmlinux_path="arch/s390/boot/compressed/vmlinux"
+      [ "${arch}" = "s390x" ] && vmlinux_path="arch/s390/boot/vmlinux"
       vmlinux_name="vmlinux-${kernel_suffix}"
       cp "${vmlinux_path}" "${kata_kernel_dir}/${vmlinux_name}"
       ln -sf "${vmlinux_name}" "${kata_kernel_dir}/vmlinux.container"
@@ -301,54 +324,31 @@ parts:
 
   virtiofsd:
     plugin: nil
-    after: [godeps, rustdeps]
+    after: [godeps, rustdeps, docker]
     override-build: |
       source "${SNAPCRAFT_PROJECT_DIR}/snap/local/snap-common.sh"
 
-      # Currently, powerpc makes use of the QEMU's C implementation.
-      # The other platforms make use of the new rust virtiofsd.
-      #
-      # See "tools/packaging/scripts/configure-hypervisor.sh".
-      if [ "${arch}" == "ppc64le" ]
-      then
-          echo "INFO: Building QEMU's C version of virtiofsd"
-          # Handled by the 'qemu' part, so nothing more to do here.
-          exit 0
-      else
-          echo "INFO: Building rust version of virtiofsd"
-      fi
+      echo "INFO: Building rust version of virtiofsd"
 
-      cd "${kata_dir}"
+      cd "${SNAPCRAFT_PROJECT_DIR}"
+      # Clean-up build dir in case it already exists
+      sudo -E NO_TTY=true make virtiofsd-tarball
 
-      export PATH=${PATH}:${HOME}/.cargo/bin
-      # Download the rust implementation of virtiofsd
-      tools/packaging/static-build/virtiofsd/build-static-virtiofsd.sh
       sudo install \
         --owner='root' \
         --group='root' \
         --mode=0755 \
         -D \
         --target-directory="${SNAPCRAFT_PART_INSTALL}/usr/libexec/" \
-        virtiofsd/virtiofsd
+        build/virtiofsd/builddir/virtiofsd/virtiofsd
 
   cloud-hypervisor:
     plugin: nil
-    after: [godeps]
+    after: [godeps, docker]
     override-build: |
       source "${SNAPCRAFT_PROJECT_DIR}/snap/local/snap-common.sh"
 
       if [ "${arch}" == "aarch64" ] || [ "${arch}" == "x86_64" ]; then
-          sudo apt-get -y update
-          sudo apt-get -y install ca-certificates curl gnupg lsb-release
-          curl -fsSL https://download.docker.com/linux/ubuntu/gpg |\
-              sudo gpg --batch --yes --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg
-          distro_codename=$(lsb_release -cs)
-          echo "deb [arch=${dpkg_arch} signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/ubuntu ${distro_codename} stable" |\
-              sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
-          sudo apt-get -y update
-          sudo apt-get -y install docker-ce docker-ce-cli containerd.io
-          sudo systemctl start docker.socket
-
           cd "${SNAPCRAFT_PROJECT_DIR}"
           sudo -E NO_TTY=true make cloud-hypervisor-tarball
 

src/agent/Cargo.toml

@@ -3,6 +3,7 @@ name = "kata-agent"
 version = "0.1.0"
 authors = ["The Kata Containers community <kata-dev@lists.katacontainers.io>"]
 edition = "2018"
+license = "Apache-2.0"
 
 [dependencies]
 oci = { path = "../libs/oci" }
@@ -12,16 +13,16 @@ lazy_static = "1.3.0"
 ttrpc = { version = "0.6.0", features = ["async"], default-features = false }
 protobuf = "2.27.0"
 libc = "0.2.58"
-nix = "0.24.1"
+nix = "0.24.2"
 capctl = "0.2.0"
 serde_json = "1.0.39"
 scan_fmt = "0.2.3"
 scopeguard = "1.0.0"
 thiserror = "1.0.26"
-regex = "1.5.5"
+regex = "1.5.6"
 serial_test = "0.5.1"
 kata-sys-util = { path = "../libs/kata-sys-util" }
-sysinfo = "0.23.0"
+kata-types = { path = "../libs/kata-types" }
 
 # Async helpers
 async-trait = "0.1.42"
@@ -33,7 +34,7 @@ tokio = { version = "1.14.0", features = ["full"] }
 tokio-vsock = "0.3.1"
 
 netlink-sys = { version = "0.7.0", features = ["tokio_socket",]}
-rtnetlink = "0.11.0"
+rtnetlink = "0.8.0"
 netlink-packet-utils = "0.4.1"
 ipnetwork = "0.17.0"
 
@@ -50,7 +51,7 @@ log = "0.4.11"
 prometheus = { version = "0.13.0", features = ["process"] }
 procfs = "0.12.0"
 anyhow = "1.0.32"
-cgroups = { package = "cgroups-rs", version = "0.2.8" }
+cgroups = { package = "cgroups-rs", version = "0.3.2" }
 
 # Tracing
 tracing = "0.1.26"
@@ -66,6 +67,8 @@ clap = { version = "3.0.1", features = ["derive"] }
 
 [dev-dependencies]
 tempfile = "3.1.0"
+test-utils = { path = "../libs/test-utils" }
+which = "4.3.0"
 
 [workspace]
 members = [

src/agent/Makefile

@@ -107,6 +107,8 @@ endef
 ##TARGET default: build code
 default: $(TARGET) show-header
 
+static-checks-build: $(GENERATED_CODE)
+
 $(TARGET): $(GENERATED_CODE) $(TARGET_PATH)
 
 $(TARGET_PATH): show-summary

src/agent/rustjail/Cargo.toml

@@ -3,6 +3,7 @@ name = "rustjail"
 version = "0.1.0"
 authors = ["The Kata Containers community <kata-dev@lists.katacontainers.io>"]
 edition = "2018"
+license = "Apache-2.0"
 
 [dependencies]
 serde = "1.0.91"
@@ -10,8 +11,9 @@ serde_json = "1.0.39"
 serde_derive = "1.0.91"
 oci = { path = "../../libs/oci" }
 protocols = { path ="../../libs/protocols" }
+kata-sys-util = { path = "../../libs/kata-sys-util" }
 caps = "0.5.0"
-nix = "0.23.0"
+nix = "0.24.2"
 scopeguard = "1.0.0"
 capctl = "0.2.0"
 lazy_static = "1.3.0"
@@ -20,10 +22,10 @@ protobuf = "2.27.0"
 slog = "2.5.2"
 slog-scope = "4.1.2"
 scan_fmt = "0.2.6"
-regex = "1.5.5"
+regex = "1.5.6"
 path-absolutize = "1.2.0"
 anyhow = "1.0.32"
-cgroups = { package = "cgroups-rs", version = "0.2.8" }
+cgroups = { package = "cgroups-rs", version = "0.3.2" }
 rlimit = "0.5.3"
 cfg-if = "0.1.0"
 
@@ -31,11 +33,15 @@ tokio = { version = "1.2.0", features = ["sync", "io-util", "process", "time", "
 futures = "0.3.17"
 async-trait = "0.1.31"
 inotify = "0.9.2"
-libseccomp = { version = "0.1.3", optional = true }
+libseccomp = { version = "0.3.0", optional = true }
+zbus = "2.3.0"
+bit-vec= "0.6.3"
+xattr = "0.2.3"
 
 [dev-dependencies]
 serial_test = "0.5.0"
 tempfile = "3.1.0"
+test-utils = { path = "../../libs/test-utils" }
 
 [features]
 seccomp = ["libseccomp"]

src/agent/rustjail/src/cgroups/fs/mod.rs

@@ -32,6 +32,7 @@ use protocols::agent::{
     BlkioStats, BlkioStatsEntry, CgroupStats, CpuStats, CpuUsage, HugetlbStats, MemoryData,
     MemoryStats, PidsStats, ThrottlingData,
 };
+use std::any::Any;
 use std::collections::HashMap;
 use std::fs;
 use std::path::Path;
@@ -75,7 +76,7 @@ macro_rules! set_resource {
 
 impl CgroupManager for Manager {
     fn apply(&self, pid: pid_t) -> Result<()> {
-        self.cgroup.add_task(CgroupPid::from(pid as u64))?;
+        self.cgroup.add_task_by_tgid(CgroupPid::from(pid as u64))?;
         Ok(())
     }
 
@@ -174,7 +175,7 @@ impl CgroupManager for Manager {
                 freezer_controller.freeze()?;
             }
             _ => {
-                return Err(anyhow!(nix::Error::EINVAL));
+                return Err(anyhow!("Invalid FreezerState"));
             }
         }
 
@@ -193,6 +194,83 @@ impl CgroupManager for Manager {
 
         Ok(result)
     }
+
+    fn update_cpuset_path(&self, guest_cpuset: &str, container_cpuset: &str) -> Result<()> {
+        if guest_cpuset.is_empty() {
+            return Ok(());
+        }
+        info!(sl!(), "update_cpuset_path to: {}", guest_cpuset);
+
+        let h = cgroups::hierarchies::auto();
+        let root_cg = h.root_control_group();
+
+        let root_cpuset_controller: &CpuSetController = root_cg.controller_of().unwrap();
+        let path = root_cpuset_controller.path();
+        let root_path = Path::new(path);
+        info!(sl!(), "root cpuset path: {:?}", &path);
+
+        let container_cpuset_controller: &CpuSetController = self.cgroup.controller_of().unwrap();
+        let path = container_cpuset_controller.path();
+        let container_path = Path::new(path);
+        info!(sl!(), "container cpuset path: {:?}", &path);
+
+        let mut paths = vec![];
+        for ancestor in container_path.ancestors() {
+            if ancestor == root_path {
+                break;
+            }
+            paths.push(ancestor);
+        }
+        info!(sl!(), "parent paths to update cpuset: {:?}", &paths);
+
+        let mut i = paths.len();
+        loop {
+            if i == 0 {
+                break;
+            }
+            i -= 1;
+
+            // remove cgroup root from path
+            let r_path = &paths[i]
+                .to_str()
+                .unwrap()
+                .trim_start_matches(root_path.to_str().unwrap());
+            info!(sl!(), "updating cpuset for parent path {:?}", &r_path);
+            let cg = new_cgroup(cgroups::hierarchies::auto(), r_path)?;
+            let cpuset_controller: &CpuSetController = cg.controller_of().unwrap();
+            cpuset_controller.set_cpus(guest_cpuset)?;
+        }
+
+        if !container_cpuset.is_empty() {
+            info!(
+                sl!(),
+                "updating cpuset for container path: {:?} cpuset: {}",
+                &container_path,
+                container_cpuset
+            );
+            container_cpuset_controller.set_cpus(container_cpuset)?;
+        }
+
+        Ok(())
+    }
+
+    fn get_cgroup_path(&self, cg: &str) -> Result<String> {
+        if cgroups::hierarchies::is_cgroup2_unified_mode() {
+            let cg_path = format!("/sys/fs/cgroup/{}", self.cpath);
+            return Ok(cg_path);
+        }
+
+        // for cgroup v1
+        Ok(self.paths.get(cg).map(|s| s.to_string()).unwrap())
+    }
+
+    fn as_any(&self) -> Result<&dyn Any> {
+        Ok(self)
+    }
+
+    fn name(&self) -> &str {
+        "cgroupfs"
+    }
 }
 
 fn set_network_resources(
@@ -252,19 +330,28 @@ fn set_devices_resources(
 }
 
 fn set_hugepages_resources(
-    _cg: &cgroups::Cgroup,
+    cg: &cgroups::Cgroup,
     hugepage_limits: &[LinuxHugepageLimit],
     res: &mut cgroups::Resources,
 ) {
     info!(sl!(), "cgroup manager set hugepage");
     let mut limits = vec![];
+    let hugetlb_controller = cg.controller_of::<HugeTlbController>();
 
     for l in hugepage_limits.iter() {
-        let hr = HugePageResource {
-            size: l.page_size.clone(),
-            limit: l.limit,
-        };
-        limits.push(hr);
+        if hugetlb_controller.is_some() && hugetlb_controller.unwrap().size_supported(&l.page_size)
+        {
+            let hr = HugePageResource {
+                size: l.page_size.clone(),
+                limit: l.limit,
+            };
+            limits.push(hr);
+        } else {
+            warn!(
+                sl!(),
+                "{} page size support cannot be verified, dropping requested limit", l.page_size
+            );
+        }
     }
     res.hugepages.limits = limits;
 }
@@ -608,17 +695,6 @@ fn get_cpuacct_stats(cg: &cgroups::Cgroup) -> SingularPtrField<CpuUsage> {
         });
     }
 
-    if cg.v2() {
-        return SingularPtrField::some(CpuUsage {
-            total_usage: 0,
-            percpu_usage: vec![],
-            usage_in_kernelmode: 0,
-            usage_in_usermode: 0,
-            unknown_fields: UnknownFields::default(),
-            cached_size: CachedSize::default(),
-        });
-    }
-
     // try to get from cpu controller
     let cpu_controller: &CpuController = get_controller_or_return_singular_none!(cg);
     let stat = cpu_controller.cpu().stat;
@@ -649,7 +725,7 @@ fn get_memory_stats(cg: &cgroups::Cgroup) -> SingularPtrField<MemoryStats> {
     let value = memory.use_hierarchy;
     let use_hierarchy = value == 1;
 
-    // gte memory datas
+    // get memory data
     let usage = SingularPtrField::some(MemoryData {
         usage: memory.usage_in_bytes,
         max_usage: memory.max_usage_in_bytes,
@@ -940,9 +1016,9 @@ pub fn get_mounts(paths: &HashMap<String, String>) -> Result<HashMap<String, Str
     Ok(m)
 }
 
-fn new_cgroup(h: Box<dyn cgroups::Hierarchy>, path: &str) -> Cgroup {
+fn new_cgroup(h: Box<dyn cgroups::Hierarchy>, path: &str) -> Result<Cgroup> {
     let valid_path = path.trim_start_matches('/').to_string();
-    cgroups::Cgroup::new(h, valid_path.as_str())
+    cgroups::Cgroup::new(h, valid_path.as_str()).map_err(anyhow::Error::from)
 }
 
 impl Manager {
@@ -964,83 +1040,16 @@ impl Manager {
             m.insert(key.to_string(), p);
         }
 
+        let cg = new_cgroup(cgroups::hierarchies::auto(), cpath)?;
+
         Ok(Self {
             paths: m,
             mounts,
             // rels: paths,
             cpath: cpath.to_string(),
-            cgroup: new_cgroup(cgroups::hierarchies::auto(), cpath),
+            cgroup: cg,
         })
     }
-
-    pub fn update_cpuset_path(&self, guest_cpuset: &str, container_cpuset: &str) -> Result<()> {
-        if guest_cpuset.is_empty() {
-            return Ok(());
-        }
-        info!(sl!(), "update_cpuset_path to: {}", guest_cpuset);
-
-        let h = cgroups::hierarchies::auto();
-        let root_cg = h.root_control_group();
-
-        let root_cpuset_controller: &CpuSetController = root_cg.controller_of().unwrap();
-        let path = root_cpuset_controller.path();
-        let root_path = Path::new(path);
-        info!(sl!(), "root cpuset path: {:?}", &path);
-
-        let container_cpuset_controller: &CpuSetController = self.cgroup.controller_of().unwrap();
-        let path = container_cpuset_controller.path();
-        let container_path = Path::new(path);
-        info!(sl!(), "container cpuset path: {:?}", &path);
-
-        let mut paths = vec![];
-        for ancestor in container_path.ancestors() {
-            if ancestor == root_path {
-                break;
-            }
-            paths.push(ancestor);
-        }
-        info!(sl!(), "parent paths to update cpuset: {:?}", &paths);
-
-        let mut i = paths.len();
-        loop {
-            if i == 0 {
-                break;
-            }
-            i -= 1;
-
-            // remove cgroup root from path
-            let r_path = &paths[i]
-                .to_str()
-                .unwrap()
-                .trim_start_matches(root_path.to_str().unwrap());
-            info!(sl!(), "updating cpuset for parent path {:?}", &r_path);
-            let cg = new_cgroup(cgroups::hierarchies::auto(), r_path);
-            let cpuset_controller: &CpuSetController = cg.controller_of().unwrap();
-            cpuset_controller.set_cpus(guest_cpuset)?;
-        }
-
-        if !container_cpuset.is_empty() {
-            info!(
-                sl!(),
-                "updating cpuset for container path: {:?} cpuset: {}",
-                &container_path,
-                container_cpuset
-            );
-            container_cpuset_controller.set_cpus(container_cpuset)?;
-        }
-
-        Ok(())
-    }
-
-    pub fn get_cg_path(&self, cg: &str) -> Option<String> {
-        if cgroups::hierarchies::is_cgroup2_unified_mode() {
-            let cg_path = format!("/sys/fs/cgroup/{}", self.cpath);
-            return Some(cg_path);
-        }
-
-        // for cgroup v1
-        self.paths.get(cg).map(|s| s.to_string())
-    }
 }
 
 // get the guest's online cpus.

src/agent/rustjail/src/cgroups/mock.rs

@@ -11,6 +11,7 @@ use anyhow::Result;
 use cgroups::freezer::FreezerState;
 use libc::{self, pid_t};
 use oci::LinuxResources;
+use std::any::Any;
 use std::collections::HashMap;
 use std::string::String;
 
@@ -53,6 +54,22 @@ impl CgroupManager for Manager {
     fn get_pids(&self) -> Result<Vec<pid_t>> {
         Ok(Vec::new())
     }
+
+    fn update_cpuset_path(&self, _: &str, _: &str) -> Result<()> {
+        Ok(())
+    }
+
+    fn get_cgroup_path(&self, _: &str) -> Result<String> {
+        Ok("".to_string())
+    }
+
+    fn as_any(&self) -> Result<&dyn Any> {
+        Ok(self)
+    }
+
+    fn name(&self) -> &str {
+        "mock"
+    }
 }
 
 impl Manager {
@@ -63,12 +80,4 @@ impl Manager {
             cpath: cpath.to_string(),
         })
     }
-
-    pub fn update_cpuset_path(&self, _: &str, _: &str) -> Result<()> {
-        Ok(())
-    }
-
-    pub fn get_cg_path(&self, _: &str) -> Option<String> {
-        Some("".to_string())
-    }
 }

src/agent/rustjail/src/cgroups/mod.rs

@@ -4,8 +4,10 @@
 //
 
 use anyhow::{anyhow, Result};
+use core::fmt::Debug;
 use oci::LinuxResources;
 use protocols::agent::CgroupStats;
+use std::any::Any;
 
 use cgroups::freezer::FreezerState;
 
@@ -38,4 +40,24 @@ pub trait Manager {
     fn set(&self, _container: &LinuxResources, _update: bool) -> Result<()> {
         Err(anyhow!("not supported!"))
     }
+
+    fn update_cpuset_path(&self, _: &str, _: &str) -> Result<()> {
+        Err(anyhow!("not supported!"))
+    }
+
+    fn get_cgroup_path(&self, _: &str) -> Result<String> {
+        Err(anyhow!("not supported!"))
+    }
+
+    fn as_any(&self) -> Result<&dyn Any> {
+        Err(anyhow!("not supported!"))
+    }
+
+    fn name(&self) -> &str;
+}
+
+impl Debug for dyn Manager + Send + Sync {
+    fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
+        write!(f, "{}", self.name())
+    }
 }

src/agent/rustjail/src/cgroups/systemd.rs

@@ -1,10 +0,0 @@
-// Copyright (c) 2019 Ant Financial
-//
-// SPDX-License-Identifier: Apache-2.0
-//
-
-use crate::cgroups::Manager as CgroupManager;
-
-pub struct Manager {}
-
-impl CgroupManager for Manager {}

src/agent/rustjail/src/cgroups/systemd/cgroups_path.rs

@@ -0,0 +1,95 @@
+// Copyright 2021-2022 Kata Contributors
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+use anyhow::{anyhow, Result};
+
+use super::common::{DEFAULT_SLICE, SCOPE_SUFFIX, SLICE_SUFFIX};
+use std::string::String;
+
+#[derive(Serialize, Deserialize, Debug, Clone)]
+pub struct CgroupsPath {
+    pub slice: String,
+    pub prefix: String,
+    pub name: String,
+}
+
+impl CgroupsPath {
+    pub fn new(cgroups_path_str: &str) -> Result<Self> {
+        let path_vec: Vec<&str> = cgroups_path_str.split(':').collect();
+        if path_vec.len() != 3 {
+            return Err(anyhow!("invalid cpath: {:?}", cgroups_path_str));
+        }
+
+        Ok(CgroupsPath {
+            slice: if path_vec[0].is_empty() {
+                DEFAULT_SLICE.to_string()
+            } else {
+                path_vec[0].to_owned()
+            },
+            prefix: path_vec[1].to_owned(),
+            name: path_vec[2].to_owned(),
+        })
+    }
+
+    // ref: https://github.com/opencontainers/runc/blob/main/docs/systemd.md
+    // return: (parent_slice, unit_name)
+    pub fn parse(&self) -> Result<(String, String)> {
+        Ok((
+            parse_parent(self.slice.to_owned())?,
+            get_unit_name(self.prefix.to_owned(), self.name.to_owned()),
+        ))
+    }
+}
+
+fn parse_parent(slice: String) -> Result<String> {
+    if !slice.ends_with(SLICE_SUFFIX) || slice.contains('/') {
+        return Err(anyhow!("invalid slice name: {}", slice));
+    } else if slice == "-.slice" {
+        return Ok(String::new());
+    }
+
+    let mut slice_path = String::new();
+    let mut prefix = String::new();
+    for subslice in slice.trim_end_matches(SLICE_SUFFIX).split('-') {
+        if subslice.is_empty() {
+            return Err(anyhow!("invalid slice name: {}", slice));
+        }
+        slice_path = format!("{}/{}{}{}", slice_path, prefix, subslice, SLICE_SUFFIX);
+        prefix = format!("{}{}-", prefix, subslice);
+    }
+    slice_path.remove(0);
+    Ok(slice_path)
+}
+
+fn get_unit_name(prefix: String, name: String) -> String {
+    if name.ends_with(SLICE_SUFFIX) {
+        name
+    } else if prefix.is_empty() {
+        format!("{}{}", name, SCOPE_SUFFIX)
+    } else {
+        format!("{}-{}{}", prefix, name, SCOPE_SUFFIX)
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::CgroupsPath;
+
+    #[test]
+    fn test_cgroup_path_parse() {
+        let slice = "system.slice";
+        let prefix = "kata_agent";
+        let name = "123";
+        let cgroups_path =
+            CgroupsPath::new(format!("{}:{}:{}", slice, prefix, name).as_str()).unwrap();
+        assert_eq!(slice, cgroups_path.slice.as_str());
+        assert_eq!(prefix, cgroups_path.prefix.as_str());
+        assert_eq!(name, cgroups_path.name.as_str());
+
+        let (parent_slice, unit_name) = cgroups_path.parse().unwrap();
+        assert_eq!(format!("{}", slice), parent_slice);
+        assert_eq!(format!("{}-{}.scope", prefix, name), unit_name);
+    }
+}

src/agent/rustjail/src/cgroups/systemd/common.rs

@@ -0,0 +1,17 @@
+// Copyright 2021-2022 Kata Contributors
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+pub const DEFAULT_SLICE: &str = "system.slice";
+pub const SLICE_SUFFIX: &str = ".slice";
+pub const SCOPE_SUFFIX: &str = ".scope";
+pub const UNIT_MODE: &str = "replace";
+
+pub type Properties<'a> = Vec<(&'a str, zbus::zvariant::Value<'a>)>;
+
+#[derive(Serialize, Deserialize, Debug, Clone)]
+pub enum CgroupHierarchy {
+    Legacy,
+    Unified,
+}

src/agent/rustjail/src/cgroups/systemd/dbus_client.rs

@@ -0,0 +1,129 @@
+// Copyright 2021-2022 Kata Contributors
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+use std::vec;
+
+use super::common::CgroupHierarchy;
+use super::common::{Properties, SLICE_SUFFIX, UNIT_MODE};
+use super::interface::system::ManagerProxyBlocking as SystemManager;
+use anyhow::{Context, Result};
+use zbus::zvariant::Value;
+
+pub trait SystemdInterface {
+    fn start_unit(
+        &self,
+        pid: i32,
+        parent: &str,
+        unit_name: &str,
+        cg_hierarchy: &CgroupHierarchy,
+    ) -> Result<()>;
+
+    fn set_properties(&self, unit_name: &str, properties: &Properties) -> Result<()>;
+
+    fn stop_unit(&self, unit_name: &str) -> Result<()>;
+
+    fn get_version(&self) -> Result<String>;
+
+    fn unit_exists(&self, unit_name: &str) -> Result<bool>;
+
+    fn add_process(&self, pid: i32, unit_name: &str) -> Result<()>;
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone)]
+pub struct DBusClient {}
+
+impl DBusClient {
+    fn build_proxy(&self) -> Result<SystemManager<'static>> {
+        let connection =
+            zbus::blocking::Connection::system().context("Establishing a D-Bus connection")?;
+        let proxy = SystemManager::new(&connection).context("Building a D-Bus proxy manager")?;
+        Ok(proxy)
+    }
+}
+
+impl SystemdInterface for DBusClient {
+    fn start_unit(
+        &self,
+        pid: i32,
+        parent: &str,
+        unit_name: &str,
+        cg_hierarchy: &CgroupHierarchy,
+    ) -> Result<()> {
+        let proxy = self.build_proxy()?;
+
+        // enable CPUAccounting & MemoryAccounting & (Block)IOAccounting by default
+        let mut properties: Properties = vec![
+            ("CPUAccounting", Value::Bool(true)),
+            ("DefaultDependencies", Value::Bool(false)),
+            ("MemoryAccounting", Value::Bool(true)),
+            ("TasksAccounting", Value::Bool(true)),
+            ("Description", Value::Str("kata-agent container".into())),
+            ("PIDs", Value::Array(vec![pid as u32].into())),
+        ];
+
+        match *cg_hierarchy {
+            CgroupHierarchy::Legacy => properties.push(("IOAccounting", Value::Bool(true))),
+            CgroupHierarchy::Unified => properties.push(("BlockIOAccounting", Value::Bool(true))),
+        }
+
+        if unit_name.ends_with(SLICE_SUFFIX) {
+            properties.push(("Wants", Value::Str(parent.into())));
+        } else {
+            properties.push(("Slice", Value::Str(parent.into())));
+            properties.push(("Delegate", Value::Bool(true)));
+        }
+
+        proxy
+            .start_transient_unit(unit_name, UNIT_MODE, &properties, &[])
+            .with_context(|| format!("failed to start transient unit {}", unit_name))?;
+        Ok(())
+    }
+
+    fn set_properties(&self, unit_name: &str, properties: &Properties) -> Result<()> {
+        let proxy = self.build_proxy()?;
+
+        proxy
+            .set_unit_properties(unit_name, true, properties)
+            .with_context(|| format!("failed to set unit properties {}", unit_name))?;
+
+        Ok(())
+    }
+
+    fn stop_unit(&self, unit_name: &str) -> Result<()> {
+        let proxy = self.build_proxy()?;
+
+        proxy
+            .stop_unit(unit_name, UNIT_MODE)
+            .with_context(|| format!("failed to stop unit {}", unit_name))?;
+        Ok(())
+    }
+
+    fn get_version(&self) -> Result<String> {
+        let proxy = self.build_proxy()?;
+
+        let systemd_version = proxy
+            .version()
+            .with_context(|| "failed to get systemd version".to_string())?;
+        Ok(systemd_version)
+    }
+
+    fn unit_exists(&self, unit_name: &str) -> Result<bool> {
+        let proxy = self
+            .build_proxy()
+            .with_context(|| format!("Checking if systemd unit {} exists", unit_name))?;
+
+        Ok(proxy.get_unit(unit_name).is_ok())
+    }
+
+    fn add_process(&self, pid: i32, unit_name: &str) -> Result<()> {
+        let proxy = self.build_proxy()?;
+
+        proxy
+            .attach_processes_to_unit(unit_name, "/", &[pid as u32])
+            .with_context(|| format!("failed to add process {}", unit_name))?;
+
+        Ok(())
+    }
+}

src/agent/rustjail/src/cgroups/systemd/interface/mod.rs

@@ -0,0 +1,7 @@
+// Copyright 2021-2022 Kata Contributors
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+pub(crate) mod session;
+pub(crate) mod system;

src/agent/rustjail/src/cgroups/systemd/manager.rs

@@ -0,0 +1,133 @@
+// Copyright 2021-2022 Kata Contributors
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+use crate::cgroups::Manager as CgroupManager;
+use crate::protocols::agent::CgroupStats;
+use anyhow::Result;
+use cgroups::freezer::FreezerState;
+use libc::{self, pid_t};
+use oci::LinuxResources;
+use std::any::Any;
+use std::collections::HashMap;
+use std::convert::TryInto;
+use std::string::String;
+use std::vec;
+
+use super::super::fs::Manager as FsManager;
+
+use super::cgroups_path::CgroupsPath;
+use super::common::{CgroupHierarchy, Properties};
+use super::dbus_client::{DBusClient, SystemdInterface};
+use super::subsystem::transformer::Transformer;
+use super::subsystem::{cpu::Cpu, cpuset::CpuSet, memory::Memory, pids::Pids};
+
+#[derive(Serialize, Deserialize, Debug, Clone)]
+pub struct Manager {
+    pub paths: HashMap<String, String>,
+    pub mounts: HashMap<String, String>,
+    pub cgroups_path: CgroupsPath,
+    pub cpath: String,
+    pub unit_name: String,
+    // dbus client for set properties
+    dbus_client: DBusClient,
+    // fs manager for get properties
+    fs_manager: FsManager,
+    // cgroup version for different dbus properties
+    cg_hierarchy: CgroupHierarchy,
+}
+
+impl CgroupManager for Manager {
+    fn apply(&self, pid: pid_t) -> Result<()> {
+        let unit_name = self.unit_name.as_str();
+        if self.dbus_client.unit_exists(unit_name)? {
+            self.dbus_client.add_process(pid, self.unit_name.as_str())?;
+        } else {
+            self.dbus_client.start_unit(
+                (pid as u32).try_into().unwrap(),
+                self.cgroups_path.slice.as_str(),
+                self.unit_name.as_str(),
+                &self.cg_hierarchy,
+            )?;
+        }
+
+        Ok(())
+    }
+
+    fn set(&self, r: &LinuxResources, _: bool) -> Result<()> {
+        let mut properties: Properties = vec![];
+
+        let systemd_version = self.dbus_client.get_version()?;
+        let systemd_version_str = systemd_version.as_str();
+
+        Cpu::apply(r, &mut properties, &self.cg_hierarchy, systemd_version_str)?;
+        Memory::apply(r, &mut properties, &self.cg_hierarchy, systemd_version_str)?;
+        Pids::apply(r, &mut properties, &self.cg_hierarchy, systemd_version_str)?;
+        CpuSet::apply(r, &mut properties, &self.cg_hierarchy, systemd_version_str)?;
+
+        self.dbus_client
+            .set_properties(self.unit_name.as_str(), &properties)?;
+
+        Ok(())
+    }
+
+    fn get_stats(&self) -> Result<CgroupStats> {
+        self.fs_manager.get_stats()
+    }
+
+    fn freeze(&self, state: FreezerState) -> Result<()> {
+        self.fs_manager.freeze(state)
+    }
+
+    fn destroy(&mut self) -> Result<()> {
+        self.dbus_client.stop_unit(self.unit_name.as_str())?;
+        self.fs_manager.destroy()
+    }
+
+    fn get_pids(&self) -> Result<Vec<pid_t>> {
+        self.fs_manager.get_pids()
+    }
+
+    fn update_cpuset_path(&self, guest_cpuset: &str, container_cpuset: &str) -> Result<()> {
+        self.fs_manager
+            .update_cpuset_path(guest_cpuset, container_cpuset)
+    }
+
+    fn get_cgroup_path(&self, cg: &str) -> Result<String> {
+        self.fs_manager.get_cgroup_path(cg)
+    }
+
+    fn as_any(&self) -> Result<&dyn Any> {
+        Ok(self)
+    }
+
+    fn name(&self) -> &str {
+        "systemd"
+    }
+}
+
+impl Manager {
+    pub fn new(cgroups_path_str: &str) -> Result<Self> {
+        let cgroups_path = CgroupsPath::new(cgroups_path_str)?;
+        let (parent_slice, unit_name) = cgroups_path.parse()?;
+        let cpath = parent_slice + "/" + &unit_name;
+
+        let fs_manager = FsManager::new(cpath.as_str())?;
+
+        Ok(Manager {
+            paths: fs_manager.paths.clone(),
+            mounts: fs_manager.mounts.clone(),
+            cgroups_path,
+            cpath,
+            unit_name,
+            dbus_client: DBusClient {},
+            fs_manager,
+            cg_hierarchy: if cgroups::hierarchies::is_cgroup2_unified_mode() {
+                CgroupHierarchy::Unified
+            } else {
+                CgroupHierarchy::Legacy
+            },
+        })
+    }
+}

src/agent/rustjail/src/cgroups/systemd/mod.rs

@@ -0,0 +1,12 @@
+// Copyright 2021-2022 Kata Contributors
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+pub mod manager;
+
+mod cgroups_path;
+mod common;
+mod dbus_client;
+mod interface;
+mod subsystem;

src/agent/rustjail/src/cgroups/systemd/subsystem/cpu.rs

@@ -0,0 +1,139 @@
+// Copyright 2021-2022 Kata Contributors
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+use super::super::common::{CgroupHierarchy, Properties};
+use super::transformer::Transformer;
+
+use anyhow::Result;
+use oci::{LinuxCpu, LinuxResources};
+use zbus::zvariant::Value;
+
+const BASIC_SYSTEMD_VERSION: &str = "242";
+const DEFAULT_CPUQUOTAPERIOD: u64 = 100 * 1000;
+const SEC2MICROSEC: u64 = 1000 * 1000;
+const BASIC_INTERVAL: u64 = 10 * 1000;
+
+pub struct Cpu {}
+
+impl Transformer for Cpu {
+    fn apply(
+        r: &LinuxResources,
+        properties: &mut Properties,
+        cgroup_hierarchy: &CgroupHierarchy,
+        systemd_version: &str,
+    ) -> Result<()> {
+        if let Some(cpu_resources) = &r.cpu {
+            match cgroup_hierarchy {
+                CgroupHierarchy::Legacy => {
+                    Self::legacy_apply(cpu_resources, properties, systemd_version)?
+                }
+                CgroupHierarchy::Unified => {
+                    Self::unified_apply(cpu_resources, properties, systemd_version)?
+                }
+            }
+        }
+
+        Ok(())
+    }
+}
+
+impl Cpu {
+    // v1:
+    // cpu.shares <-> CPUShares
+    // cpu.period <-> CPUQuotaPeriodUSec
+    // cpu.period & cpu.quota <-> CPUQuotaPerSecUSec
+    fn legacy_apply(
+        cpu_resources: &LinuxCpu,
+        properties: &mut Properties,
+        systemd_version: &str,
+    ) -> Result<()> {
+        if let Some(shares) = cpu_resources.shares {
+            properties.push(("CPUShares", Value::U64(shares)));
+        }
+
+        if let Some(period) = cpu_resources.period {
+            if period != 0 && systemd_version >= BASIC_SYSTEMD_VERSION {
+                properties.push(("CPUQuotaPeriodUSec", Value::U64(period)));
+            }
+        }
+
+        if let Some(quota) = cpu_resources.quota {
+            let period = cpu_resources.period.unwrap_or(DEFAULT_CPUQUOTAPERIOD);
+            if period != 0 {
+                let cpu_quota_per_sec_usec = resolve_cpuquota(quota, period);
+                properties.push(("CPUQuotaPerSecUSec", Value::U64(cpu_quota_per_sec_usec)));
+            }
+        }
+
+        Ok(())
+    }
+
+    // v2:
+    // cpu.shares <-> CPUWeight
+    // cpu.period <-> CPUQuotaPeriodUSec
+    // cpu.period & cpu.quota <-> CPUQuotaPerSecUSec
+    fn unified_apply(
+        cpu_resources: &LinuxCpu,
+        properties: &mut Properties,
+        systemd_version: &str,
+    ) -> Result<()> {
+        if let Some(shares) = cpu_resources.shares {
+            let weight = shares_to_weight(shares);
+            properties.push(("CPUWeight", Value::U64(weight)));
+        }
+
+        if let Some(period) = cpu_resources.period {
+            if period != 0 && systemd_version >= BASIC_SYSTEMD_VERSION {
+                properties.push(("CPUQuotaPeriodUSec", Value::U64(period)));
+            }
+        }
+
+        if let Some(quota) = cpu_resources.quota {
+            let period = cpu_resources.period.unwrap_or(DEFAULT_CPUQUOTAPERIOD);
+            if period != 0 {
+                let cpu_quota_per_sec_usec = resolve_cpuquota(quota, period);
+                properties.push(("CPUQuotaPerSecUSec", Value::U64(cpu_quota_per_sec_usec)));
+            }
+        }
+
+        Ok(())
+    }
+}
+
+// ref: https://github.com/containers/crun/blob/main/crun.1.md#cgroup-v2
+// [2-262144] to [1-10000]
+fn shares_to_weight(shares: u64) -> u64 {
+    if shares == 0 {
+        return 100;
+    }
+
+    1 + ((shares - 2) * 9999) / 262142
+}
+
+fn resolve_cpuquota(quota: i64, period: u64) -> u64 {
+    let mut cpu_quota_per_sec_usec = u64::MAX;
+    if quota > 0 {
+        cpu_quota_per_sec_usec = (quota as u64) * SEC2MICROSEC / period;
+        if cpu_quota_per_sec_usec % BASIC_INTERVAL != 0 {
+            cpu_quota_per_sec_usec =
+                ((cpu_quota_per_sec_usec / BASIC_INTERVAL) + 1) * BASIC_INTERVAL;
+        }
+    }
+    cpu_quota_per_sec_usec
+}
+
+#[cfg(test)]
+mod tests {
+    use crate::cgroups::systemd::subsystem::cpu::resolve_cpuquota;
+
+    #[test]
+    fn test_unified_cpuquota() {
+        let quota: i64 = 1000000;
+        let period: u64 = 500000;
+        let cpu_quota_per_sec_usec = resolve_cpuquota(quota, period);
+
+        assert_eq!(2000000, cpu_quota_per_sec_usec);
+    }
+}

src/agent/rustjail/src/cgroups/systemd/subsystem/cpuset.rs

@@ -0,0 +1,124 @@
+// Copyright 2021-2022 Kata Contributors
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+use super::super::common::{CgroupHierarchy, Properties};
+
+use super::transformer::Transformer;
+
+use anyhow::{bail, Result};
+use bit_vec::BitVec;
+use oci::{LinuxCpu, LinuxResources};
+use std::convert::{TryFrom, TryInto};
+use zbus::zvariant::Value;
+
+const BASIC_SYSTEMD_VERSION: &str = "244";
+
+pub struct CpuSet {}
+
+impl Transformer for CpuSet {
+    fn apply(
+        r: &LinuxResources,
+        properties: &mut Properties,
+        _: &CgroupHierarchy,
+        systemd_version: &str,
+    ) -> Result<()> {
+        if let Some(cpuset_resources) = &r.cpu {
+            Self::apply(cpuset_resources, properties, systemd_version)?;
+        }
+
+        Ok(())
+    }
+}
+
+// v1 & v2:
+// cpuset.cpus <-> AllowedCPUs (v244)
+// cpuset.mems <-> AllowedMemoryNodes (v244)
+impl CpuSet {
+    fn apply(
+        cpuset_resources: &LinuxCpu,
+        properties: &mut Properties,
+        systemd_version: &str,
+    ) -> Result<()> {
+        if systemd_version < BASIC_SYSTEMD_VERSION {
+            return Ok(());
+        }
+
+        let cpus = cpuset_resources.cpus.as_str();
+        if !cpus.is_empty() {
+            let cpus_vec: BitMask = cpus.try_into()?;
+            properties.push(("AllowedCPUs", Value::Array(cpus_vec.0.into())));
+        }
+
+        let mems = cpuset_resources.mems.as_str();
+        if !mems.is_empty() {
+            let mems_vec: BitMask = mems.try_into()?;
+            properties.push(("AllowedMemoryNodes", Value::Array(mems_vec.0.into())));
+        }
+
+        Ok(())
+    }
+}
+
+struct BitMask(Vec<u8>);
+
+impl TryFrom<&str> for BitMask {
+    type Error = anyhow::Error;
+
+    fn try_from(bitmask_str: &str) -> Result<Self, Self::Error> {
+        let mut bitmask_vec = BitVec::from_elem(8, false);
+        let bitmask_str_vec: Vec<&str> = bitmask_str.split(',').collect();
+        for bitmask in bitmask_str_vec.iter() {
+            let range: Vec<&str> = bitmask.split('-').collect();
+            match range.len() {
+                1 => {
+                    let idx: usize = range[0].parse()?;
+                    while idx >= bitmask_vec.len() {
+                        bitmask_vec.grow(8, false);
+                    }
+                    bitmask_vec.set(adjust_index(idx), true);
+                }
+                2 => {
+                    let left_index = range[0].parse()?;
+                    let right_index = range[1].parse()?;
+                    while right_index >= bitmask_vec.len() {
+                        bitmask_vec.grow(8, false);
+                    }
+                    for idx in left_index..=right_index {
+                        bitmask_vec.set(adjust_index(idx), true);
+                    }
+                }
+                _ => bail!("invalid bitmask str {}", bitmask_str),
+            }
+        }
+        let mut result_vec = bitmask_vec.to_bytes();
+        result_vec.reverse();
+
+        Ok(BitMask(result_vec))
+    }
+}
+
+#[inline(always)]
+fn adjust_index(idx: usize) -> usize {
+    idx / 8 * 8 + 7 - idx % 8
+}
+
+#[cfg(test)]
+mod tests {
+    use std::convert::TryInto;
+
+    use crate::cgroups::systemd::subsystem::cpuset::BitMask;
+
+    #[test]
+    fn test_bitmask_conversion() {
+        let cpus_vec: BitMask = "2-4".try_into().unwrap();
+        assert_eq!(vec![0b11100 as u8], cpus_vec.0);
+
+        let cpus_vec: BitMask = "1,7".try_into().unwrap();
+        assert_eq!(vec![0b10000010 as u8], cpus_vec.0);
+
+        let cpus_vec: BitMask = "0,2-3,7".try_into().unwrap();
+        assert_eq!(vec![0b10001101 as u8], cpus_vec.0);
+    }
+}

src/agent/rustjail/src/cgroups/systemd/subsystem/memory.rs

@@ -0,0 +1,117 @@
+// Copyright 2021-2022 Kata Contributors
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+use super::super::common::{CgroupHierarchy, Properties};
+
+use super::transformer::Transformer;
+
+use anyhow::{bail, Result};
+use oci::{LinuxMemory, LinuxResources};
+use zbus::zvariant::Value;
+
+pub struct Memory {}
+
+impl Transformer for Memory {
+    fn apply(
+        r: &LinuxResources,
+        properties: &mut Properties,
+        cgroup_hierarchy: &CgroupHierarchy,
+        _: &str,
+    ) -> Result<()> {
+        if let Some(memory_resources) = &r.memory {
+            match cgroup_hierarchy {
+                CgroupHierarchy::Legacy => Self::legacy_apply(memory_resources, properties)?,
+                CgroupHierarchy::Unified => Self::unified_apply(memory_resources, properties)?,
+            }
+        }
+
+        Ok(())
+    }
+}
+
+impl Memory {
+    // v1:
+    // memory.limit <-> MemoryLimit
+    fn legacy_apply(memory_resources: &LinuxMemory, properties: &mut Properties) -> Result<()> {
+        if let Some(limit) = memory_resources.limit {
+            let limit = match limit {
+                1..=i64::MAX => limit as u64,
+                0 => u64::MAX,
+                _ => bail!("invalid memory.limit"),
+            };
+            properties.push(("MemoryLimit", Value::U64(limit)));
+        }
+
+        Ok(())
+    }
+
+    // v2:
+    // memory.low <-> MemoryLow
+    // memory.max <-> MemoryMax
+    // memory.swap & memory.limit <-> MemorySwapMax
+    fn unified_apply(memory_resources: &LinuxMemory, properties: &mut Properties) -> Result<()> {
+        if let Some(limit) = memory_resources.limit {
+            let limit = match limit {
+                1..=i64::MAX => limit as u64,
+                0 => u64::MAX,
+                _ => bail!("invalid memory.limit: {}", limit),
+            };
+            properties.push(("MemoryMax", Value::U64(limit)));
+        }
+
+        if let Some(reservation) = memory_resources.reservation {
+            let reservation = match reservation {
+                1..=i64::MAX => reservation as u64,
+                0 => u64::MAX,
+                _ => bail!("invalid memory.reservation: {}", reservation),
+            };
+            properties.push(("MemoryLow", Value::U64(reservation)));
+        }
+
+        let swap = match memory_resources.swap {
+            Some(0) => u64::MAX,
+            Some(1..=i64::MAX) => match memory_resources.limit {
+                Some(1..=i64::MAX) => {
+                    (memory_resources.limit.unwrap() - memory_resources.swap.unwrap()) as u64
+                }
+                _ => bail!("invalid memory.limit when memory.swap specified"),
+            },
+            None => u64::MAX,
+            _ => bail!("invalid memory.swap"),
+        };
+
+        properties.push(("MemorySwapMax", Value::U64(swap)));
+
+        Ok(())
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::Memory;
+    use super::Properties;
+    use super::Value;
+
+    #[test]
+    fn test_unified_memory() {
+        let memory_resources = oci::LinuxMemory {
+            limit: Some(736870912),
+            reservation: Some(536870912),
+            swap: Some(536870912),
+            kernel: Some(0),
+            kernel_tcp: Some(0),
+            swappiness: Some(0),
+            disable_oom_killer: Some(false),
+        };
+        let mut properties: Properties = vec![];
+
+        assert_eq!(
+            true,
+            Memory::unified_apply(&memory_resources, &mut properties).is_ok()
+        );
+
+        assert_eq!(Value::U64(200000000), properties[2].1);
+    }
+}

src/agent/rustjail/src/cgroups/systemd/subsystem/mod.rs

@@ -0,0 +1,10 @@
+// Copyright 2021-2022 Kata Contributors
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+pub mod cpu;
+pub mod cpuset;
+pub mod memory;
+pub mod pids;
+pub mod transformer;

src/agent/rustjail/src/cgroups/systemd/subsystem/pids.rs

@@ -0,0 +1,60 @@
+// Copyright 2021-2022 Kata Contributors
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+use super::super::common::{CgroupHierarchy, Properties};
+
+use super::transformer::Transformer;
+
+use anyhow::Result;
+use oci::{LinuxPids, LinuxResources};
+use zbus::zvariant::Value;
+
+pub struct Pids {}
+
+impl Transformer for Pids {
+    fn apply(
+        r: &LinuxResources,
+        properties: &mut Properties,
+        _: &CgroupHierarchy,
+        _: &str,
+    ) -> Result<()> {
+        if let Some(pids_resources) = &r.pids {
+            Self::apply(pids_resources, properties)?;
+        }
+
+        Ok(())
+    }
+}
+
+// pids.limit <-> TasksMax
+impl Pids {
+    fn apply(pids_resources: &LinuxPids, properties: &mut Properties) -> Result<()> {
+        let limit = if pids_resources.limit > 0 {
+            pids_resources.limit as u64
+        } else {
+            u64::MAX
+        };
+
+        properties.push(("TasksMax", Value::U64(limit)));
+        Ok(())
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::Pids;
+    use super::Properties;
+    use super::Value;
+
+    #[test]
+    fn test_subsystem_workflow() {
+        let pids_resources = oci::LinuxPids { limit: 0 };
+        let mut properties: Properties = vec![];
+
+        assert_eq!(true, Pids::apply(&pids_resources, &mut properties).is_ok());
+
+        assert_eq!(Value::U64(u64::MAX), properties[0].1);
+    }
+}

src/agent/rustjail/src/cgroups/systemd/subsystem/transformer.rs

@@ -0,0 +1,17 @@
+// Copyright 2021-2022 Kata Contributors
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+use super::super::common::{CgroupHierarchy, Properties};
+use anyhow::Result;
+use oci::LinuxResources;
+
+pub trait Transformer {
+    fn apply(
+        r: &LinuxResources,
+        properties: &mut Properties,
+        cgroup_hierarchy: &CgroupHierarchy,
+        systemd_version: &str,
+    ) -> Result<()>;
+}

src/agent/rustjail/src/console.rs

@@ -6,8 +6,9 @@
 use anyhow::{anyhow, Result};
 use nix::errno::Errno;
 use nix::pty;
-use nix::sys::{socket, uio};
+use nix::sys::socket;
 use nix::unistd::{self, dup2};
+use std::io::IoSlice;
 use std::os::unix::io::{AsRawFd, RawFd};
 use std::path::Path;
 
@@ -23,10 +24,7 @@ pub fn setup_console_socket(csocket_path: &str) -> Result<Option<RawFd>> {
         None,
     )?;
 
-    match socket::connect(
-        socket_fd,
-        &socket::SockAddr::Unix(socket::UnixAddr::new(Path::new(csocket_path))?),
-    ) {
+    match socket::connect(socket_fd, &socket::UnixAddr::new(Path::new(csocket_path))?) {
         Ok(()) => Ok(Some(socket_fd)),
         Err(errno) => Err(anyhow!("failed to open console fd: {}", errno)),
     }
@@ -36,11 +34,11 @@ pub fn setup_master_console(socket_fd: RawFd) -> Result<()> {
     let pseudo = pty::openpty(None, None)?;
 
     let pty_name: &[u8] = b"/dev/ptmx";
-    let iov = [uio::IoVec::from_slice(pty_name)];
+    let iov = [IoSlice::new(pty_name)];
     let fds = [pseudo.master];
     let cmsg = socket::ControlMessage::ScmRights(&fds);
 
-    socket::sendmsg(socket_fd, &iov, &[cmsg], socket::MsgFlags::empty(), None)?;
+    socket::sendmsg::<()>(socket_fd, &iov, &[cmsg], socket::MsgFlags::empty(), None)?;
 
     unistd::setsid()?;
     let ret = unsafe { libc::ioctl(pseudo.slave, libc::TIOCSCTTY) };

src/agent/rustjail/src/container.rs

@@ -6,7 +6,7 @@
 use anyhow::{anyhow, Context, Result};
 use libc::pid_t;
 use oci::{ContainerState, LinuxDevice, LinuxIdMapping};
-use oci::{Hook, Linux, LinuxNamespace, LinuxResources, Spec};
+use oci::{Linux, LinuxNamespace, LinuxResources, Spec};
 use std::clone::Clone;
 use std::ffi::CString;
 use std::fmt::Display;
@@ -22,6 +22,7 @@ use crate::capabilities;
 use crate::cgroups::fs::Manager as FsManager;
 #[cfg(test)]
 use crate::cgroups::mock::Manager as FsManager;
+use crate::cgroups::systemd::manager::Manager as SystemdManager;
 use crate::cgroups::Manager;
 #[cfg(feature = "standard-oci-runtime")]
 use crate::console;
@@ -29,6 +30,7 @@ use crate::log_child;
 use crate::process::Process;
 #[cfg(feature = "seccomp")]
 use crate::seccomp;
+use crate::selinux;
 use crate::specconv::CreateOpts;
 use crate::{mount, validator};
 
@@ -49,6 +51,7 @@ use std::os::unix::io::AsRawFd;
 use protobuf::SingularPtrField;
 
 use oci::State as OCIState;
+use regex::Regex;
 use std::collections::HashMap;
 use std::os::unix::io::FromRawFd;
 use std::str::FromStr;
@@ -64,6 +67,9 @@ use rlimit::{setrlimit, Resource, Rlim};
 use tokio::io::AsyncBufReadExt;
 use tokio::sync::Mutex;
 
+use kata_sys_util::hooks::HookStates;
+use kata_sys_util::validate::valid_env;
+
 pub const EXEC_FIFO_FILENAME: &str = "exec.fifo";
 
 const INIT: &str = "INIT";
@@ -106,6 +112,10 @@ impl Default for ContainerStatus {
     }
 }
 
+// We might want to change this to thiserror in the future
+const MissingLinux: &str = "no linux config";
+const InvalidNamespace: &str = "invalid namespace type";
+
 pub type Config = CreateOpts;
 type NamespaceType = String;
 
@@ -196,6 +206,8 @@ lazy_static! {
             },
         ]
     };
+
+    pub static ref SYSTEMD_CGROUP_PATH_FORMAT:Regex = Regex::new(r"^[\w\-.]*:[\w\-.]*:[\w\-.]*$").unwrap();
 }
 
 #[derive(Serialize, Deserialize, Debug)]
@@ -234,7 +246,7 @@ pub struct LinuxContainer {
     pub id: String,
     pub root: String,
     pub config: Config,
-    pub cgroup_manager: Option<FsManager>,
+    pub cgroup_manager: Box<dyn Manager + Send + Sync>,
     pub init_process_pid: pid_t,
     pub init_process_start_time: u64,
     pub uid_map_path: String,
@@ -283,16 +295,11 @@ impl Container for LinuxContainer {
             ));
         }
 
-        if self.cgroup_manager.is_some() {
-            self.cgroup_manager
-                .as_ref()
-                .unwrap()
-                .freeze(FreezerState::Frozen)?;
+        self.cgroup_manager.as_ref().freeze(FreezerState::Frozen)?;
 
-            self.status.transition(ContainerState::Paused);
-            return Ok(());
-        }
-        Err(anyhow!("failed to get container's cgroup manager"))
+        self.status.transition(ContainerState::Paused);
+
+        Ok(())
     }
 
     fn resume(&mut self) -> Result<()> {
@@ -301,16 +308,11 @@ impl Container for LinuxContainer {
             return Err(anyhow!("container status is: {:?}, not paused", status));
         }
 
-        if self.cgroup_manager.is_some() {
-            self.cgroup_manager
-                .as_ref()
-                .unwrap()
-                .freeze(FreezerState::Thawed)?;
+        self.cgroup_manager.as_ref().freeze(FreezerState::Thawed)?;
 
-            self.status.transition(ContainerState::Running);
-            return Ok(());
-        }
-        Err(anyhow!("failed to get container's cgroup manager"))
+        self.status.transition(ContainerState::Running);
+
+        Ok(())
     }
 }
 
@@ -385,7 +387,9 @@ fn do_init_child(cwfd: RawFd) -> Result<()> {
     let buf = read_sync(crfd)?;
     let cm_str = std::str::from_utf8(&buf)?;
 
-    let cm: FsManager = serde_json::from_str(cm_str)?;
+    // deserialize cm_str into FsManager and SystemdManager separately
+    let fs_cm: Result<FsManager, serde_json::Error> = serde_json::from_str(cm_str);
+    let systemd_cm: Result<SystemdManager, serde_json::Error> = serde_json::from_str(cm_str);
 
     #[cfg(feature = "standard-oci-runtime")]
     let csocket_fd = console::setup_console_socket(&std::env::var(CONSOLE_SOCKET_FD)?)?;
@@ -397,7 +401,7 @@ fn do_init_child(cwfd: RawFd) -> Result<()> {
     };
 
     if spec.linux.is_none() {
-        return Err(anyhow!("no linux config"));
+        return Err(anyhow!(MissingLinux));
     }
     let linux = spec.linux.as_ref().unwrap();
 
@@ -411,7 +415,7 @@ fn do_init_child(cwfd: RawFd) -> Result<()> {
     for ns in &nses {
         let s = NAMESPACES.get(&ns.r#type.as_str());
         if s.is_none() {
-            return Err(anyhow!("invalid ns type"));
+            return Err(anyhow!(InvalidNamespace));
         }
         let s = s.unwrap();
 
@@ -526,6 +530,8 @@ fn do_init_child(cwfd: RawFd) -> Result<()> {
         }
     }
 
+    let selinux_enabled = selinux::is_enabled()?;
+
     sched::unshare(to_new & !CloneFlags::CLONE_NEWUSER)?;
 
     if userns {
@@ -543,7 +549,18 @@ fn do_init_child(cwfd: RawFd) -> Result<()> {
 
     if to_new.contains(CloneFlags::CLONE_NEWNS) {
         // setup rootfs
-        mount::init_rootfs(cfd_log, &spec, &cm.paths, &cm.mounts, bind_device)?;
+        if let Ok(systemd_cm) = systemd_cm {
+            mount::init_rootfs(
+                cfd_log,
+                &spec,
+                &systemd_cm.paths,
+                &systemd_cm.mounts,
+                bind_device,
+            )?;
+        } else {
+            let fs_cm = fs_cm.unwrap();
+            mount::init_rootfs(cfd_log, &spec, &fs_cm.paths, &fs_cm.mounts, bind_device)?;
+        }
     }
 
     if init {
@@ -616,6 +633,18 @@ fn do_init_child(cwfd: RawFd) -> Result<()> {
         capctl::prctl::set_no_new_privs().map_err(|_| anyhow!("cannot set no new privileges"))?;
     }
 
+    // Set SELinux label
+    if !oci_process.selinux_label.is_empty() {
+        if !selinux_enabled {
+            return Err(anyhow!(
+                "SELinux label for the process is provided but SELinux is not enabled on the running kernel"
+            ));
+        }
+
+        log_child!(cfd_log, "Set SELinux label to the container process");
+        selinux::set_exec_label(&oci_process.selinux_label)?;
+    }
+
     // Log unknown seccomp system calls in advance before the log file descriptor closes.
     #[cfg(feature = "seccomp")]
     if let Some(ref scmp) = linux.seccomp {
@@ -825,22 +854,17 @@ impl BaseContainer for LinuxContainer {
     }
 
     fn stats(&self) -> Result<StatsContainerResponse> {
-        let mut r = StatsContainerResponse::default();
-
-        if self.cgroup_manager.is_some() {
-            r.cgroup_stats =
-                SingularPtrField::some(self.cgroup_manager.as_ref().unwrap().get_stats()?);
-        }
-
         // what about network interface stats?
 
-        Ok(r)
+        Ok(StatsContainerResponse {
+            cgroup_stats: SingularPtrField::some(self.cgroup_manager.as_ref().get_stats()?),
+            ..Default::default()
+        })
     }
 
     fn set(&mut self, r: LinuxResources) -> Result<()> {
-        if self.cgroup_manager.is_some() {
-            self.cgroup_manager.as_ref().unwrap().set(&r, true)?;
-        }
+        self.cgroup_manager.as_ref().set(&r, true)?;
+
         self.config
             .spec
             .as_mut()
@@ -1013,7 +1037,8 @@ impl BaseContainer for LinuxContainer {
             &logger,
             spec,
             &p,
-            self.cgroup_manager.as_ref().unwrap(),
+            self.cgroup_manager.as_ref(),
+            self.config.use_systemd_cgroup,
             &st,
             &mut pipe_w,
             &mut pipe_r,
@@ -1076,12 +1101,14 @@ impl BaseContainer for LinuxContainer {
             }
         }
 
-        if spec.hooks.is_some() {
-            info!(self.logger, "poststop");
-            let hooks = spec.hooks.as_ref().unwrap();
-            for h in hooks.poststop.iter() {
-                execute_hook(&self.logger, h, &st).await?;
-            }
+        // guest Poststop hook
+        // * should be executed after the container is deleted but before the delete operation returns
+        // * the executable file is in agent namespace
+        // * should also be executed in agent namespace.
+        if let Some(hooks) = spec.hooks.as_ref() {
+            info!(self.logger, "guest Poststop hook");
+            let mut hook_states = HookStates::new();
+            hook_states.execute_hooks(&hooks.poststop, Some(st))?;
         }
 
         self.status.transition(ContainerState::Stopped);
@@ -1091,19 +1118,19 @@ impl BaseContainer for LinuxContainer {
         )?;
         fs::remove_dir_all(&self.root)?;
 
-        if let Some(cgm) = self.cgroup_manager.as_mut() {
-            // Kill all of the processes created in this container to prevent
-            // the leak of some daemon process when this container shared pidns
-            // with the sandbox.
-            let pids = cgm.get_pids().context("get cgroup pids")?;
-            for i in pids {
-                if let Err(e) = signal::kill(Pid::from_raw(i), Signal::SIGKILL) {
-                    warn!(self.logger, "kill the process {} error: {:?}", i, e);
-                }
+        let cgm = self.cgroup_manager.as_mut();
+        // Kill all of the processes created in this container to prevent
+        // the leak of some daemon process when this container shared pidns
+        // with the sandbox.
+        let pids = cgm.get_pids().context("get cgroup pids")?;
+        for i in pids {
+            if let Err(e) = signal::kill(Pid::from_raw(i), Signal::SIGKILL) {
+                warn!(self.logger, "kill the process {} error: {:?}", i, e);
             }
-
-            cgm.destroy().context("destroy cgroups")?;
         }
+
+        cgm.destroy().context("destroy cgroups")?;
+
         Ok(())
     }
 
@@ -1127,16 +1154,14 @@ impl BaseContainer for LinuxContainer {
             .ok_or_else(|| anyhow!("OCI spec was not found"))?;
         let st = self.oci_state()?;
 
-        // run poststart hook
-        if spec.hooks.is_some() {
-            info!(self.logger, "poststart hook");
-            let hooks = spec
-                .hooks
-                .as_ref()
-                .ok_or_else(|| anyhow!("OCI hooks were not found"))?;
-            for h in hooks.poststart.iter() {
-                execute_hook(&self.logger, h, &st).await?;
-            }
+        // guest Poststart hook
+        // * should be executed after the container is started but before the delete operation returns
+        // * the executable file is in agent namespace
+        // * should also be executed in agent namespace.
+        if let Some(hooks) = spec.hooks.as_ref() {
+            info!(self.logger, "guest Poststart hook");
+            let mut hook_states = HookStates::new();
+            hook_states.execute_hooks(&hooks.poststart, Some(st))?;
         }
 
         unistd::close(fd)?;
@@ -1275,11 +1300,13 @@ pub fn setup_child_logger(fd: RawFd, child_logger: Logger) -> tokio::task::JoinH
     })
 }
 
+#[allow(clippy::too_many_arguments)]
 async fn join_namespaces(
     logger: &Logger,
     spec: &Spec,
     p: &Process,
-    cm: &FsManager,
+    cm: &(dyn Manager + Send + Sync),
+    use_systemd_cgroup: bool,
     st: &OCIState,
     pipe_w: &mut PipeStream,
     pipe_r: &mut PipeStream,
@@ -1306,7 +1333,11 @@ async fn join_namespaces(
     info!(logger, "wait child received oci process");
     read_async(pipe_r).await?;
 
-    let cm_str = serde_json::to_string(cm)?;
+    let cm_str = if use_systemd_cgroup {
+        serde_json::to_string(cm.as_any()?.downcast_ref::<SystemdManager>().unwrap())
+    } else {
+        serde_json::to_string(cm.as_any()?.downcast_ref::<FsManager>().unwrap())
+    }?;
     write_async(pipe_w, SYNC_DATA, cm_str.as_str()).await?;
 
     // wait child setup user namespace
@@ -1329,13 +1360,16 @@ async fn join_namespaces(
     }
 
     // apply cgroups
-    if p.init && res.is_some() {
-        info!(logger, "apply cgroups!");
-        cm.set(res.unwrap(), false)?;
+    // For FsManger, it's no matter about the order of apply and set.
+    // For SystemdManger, apply must be precede set because we can only create a systemd unit with specific processes(pids).
+    if res.is_some() {
+        info!(logger, "apply processes to cgroups!");
+        cm.apply(p.pid)?;
     }
 
-    if res.is_some() {
-        cm.apply(p.pid)?;
+    if p.init && res.is_some() {
+        info!(logger, "set properties to cgroups!");
+        cm.set(res.unwrap(), false)?;
     }
 
     info!(logger, "notify child to continue");
@@ -1348,13 +1382,14 @@ async fn join_namespaces(
 
         info!(logger, "get ready to run prestart hook!");
 
-        // run prestart hook
-        if spec.hooks.is_some() {
-            info!(logger, "prestart hook");
-            let hooks = spec.hooks.as_ref().unwrap();
-            for h in hooks.prestart.iter() {
-                execute_hook(&logger, h, st).await?;
-            }
+        // guest Prestart hook
+        // * should be executed during the start operation, and before the container command is executed
+        // * the executable file is in agent namespace
+        // * should also be executed in agent namespace.
+        if let Some(hooks) = spec.hooks.as_ref() {
+            info!(logger, "guest Prestart hook");
+            let mut hook_states = HookStates::new();
+            hook_states.execute_hooks(&hooks.prestart, Some(st.clone()))?;
         }
 
         // notify child run prestart hooks completed
@@ -1437,33 +1472,44 @@ impl LinuxContainer {
             Some(unistd::getuid()),
             Some(unistd::getgid()),
         )
-        .context(format!("cannot change onwer of container {} root", id))?;
-
-        if config.spec.is_none() {
-            return Err(anyhow!(nix::Error::EINVAL));
-        }
+        .context(format!("Cannot change owner of container {} root", id))?;
 
         let spec = config.spec.as_ref().unwrap();
-
-        if spec.linux.is_none() {
-            return Err(anyhow!(nix::Error::EINVAL));
-        }
-
         let linux = spec.linux.as_ref().unwrap();
-
-        let cpath = if linux.cgroups_path.is_empty() {
+        let cpath = if config.use_systemd_cgroup {
+            if linux.cgroups_path.len() == 2 {
+                format!("system.slice:kata_agent:{}", id.as_str())
+            } else {
+                linux.cgroups_path.clone()
+            }
+        } else if linux.cgroups_path.is_empty() {
             format!("/{}", id.as_str())
         } else {
-            linux.cgroups_path.clone()
+            // if we have a systemd cgroup path we need to convert it to a fs cgroup path
+            linux.cgroups_path.replace(':', "/")
         };
 
-        let cgroup_manager = FsManager::new(cpath.as_str())?;
+        let cgroup_manager: Box<dyn Manager + Send + Sync> = if config.use_systemd_cgroup {
+            Box::new(SystemdManager::new(cpath.as_str()).map_err(|e| {
+                anyhow!(format!(
+                    "fail to create cgroup manager with path {}: {:}",
+                    cpath, e
+                ))
+            })?)
+        } else {
+            Box::new(FsManager::new(cpath.as_str()).map_err(|e| {
+                anyhow!(format!(
+                    "fail to create cgroup manager with path {}: {:}",
+                    cpath, e
+                ))
+            })?)
+        };
         info!(logger, "new cgroup_manager {:?}", &cgroup_manager);
 
         Ok(LinuxContainer {
             id: id.clone(),
             root,
-            cgroup_manager: Some(cgroup_manager),
+            cgroup_manager,
             status: ContainerStatus::new(),
             uid_map_path: String::from(""),
             gid_map_path: "".to_string(),
@@ -1515,154 +1561,16 @@ fn set_sysctls(sysctls: &HashMap<String, String>) -> Result<()> {
     Ok(())
 }
 
-use std::process::Stdio;
-use std::time::Duration;
-use tokio::io::{AsyncReadExt, AsyncWriteExt};
-
-pub async fn execute_hook(logger: &Logger, h: &Hook, st: &OCIState) -> Result<()> {
-    let logger = logger.new(o!("action" => "execute-hook"));
-
-    let binary = PathBuf::from(h.path.as_str());
-    let path = binary.canonicalize()?;
-    if !path.exists() {
-        return Err(anyhow!(nix::Error::EINVAL));
-    }
-
-    let mut args = h.args.clone();
-    // the hook.args[0] is the hook binary name which shouldn't be included
-    // in the Command.args
-    if args.len() > 1 {
-        args.remove(0);
-    }
-
-    // all invalid envs will be omitted, only valid envs will be passed to hook.
-    let env: HashMap<&str, &str> = h.env.iter().filter_map(|e| valid_env(e)).collect();
-
-    // Avoid the exit signal to be reaped by the global reaper.
-    let _wait_locker = WAIT_PID_LOCKER.lock().await;
-    let mut child = tokio::process::Command::new(path)
-        .args(args.iter())
-        .envs(env.iter())
-        .kill_on_drop(true)
-        .stdin(Stdio::piped())
-        .stdout(Stdio::piped())
-        .stderr(Stdio::piped())
-        .spawn()?;
-
-    // default timeout 10s
-    let mut timeout: u64 = 10;
-
-    // if timeout is set if hook, then use the specified value
-    if let Some(t) = h.timeout {
-        if t > 0 {
-            timeout = t as u64;
-        }
-    }
-
-    let state = serde_json::to_string(st)?;
-    let path = h.path.clone();
-
-    let join_handle = tokio::spawn(async move {
-        if let Some(mut stdin) = child.stdin.take() {
-            match stdin.write_all(state.as_bytes()).await {
-                Ok(_) => {}
-                Err(e) => {
-                    info!(logger, "write to child stdin failed: {:?}", e);
-                }
-            }
-        }
-
-        // read something from stdout and stderr for debug
-        if let Some(stdout) = child.stdout.as_mut() {
-            let mut out = String::new();
-            match stdout.read_to_string(&mut out).await {
-                Ok(_) => {
-                    info!(logger, "child stdout: {}", out.as_str());
-                }
-                Err(e) => {
-                    info!(logger, "read from child stdout failed: {:?}", e);
-                }
-            }
-        }
-
-        let mut err = String::new();
-        if let Some(stderr) = child.stderr.as_mut() {
-            match stderr.read_to_string(&mut err).await {
-                Ok(_) => {
-                    info!(logger, "child stderr: {}", err.as_str());
-                }
-                Err(e) => {
-                    info!(logger, "read from child stderr failed: {:?}", e);
-                }
-            }
-        }
-
-        match child.wait().await {
-            Ok(exit) => {
-                let code = exit
-                    .code()
-                    .ok_or_else(|| anyhow!("hook exit status has no status code"))?;
-
-                if code != 0 {
-                    error!(
-                        logger,
-                        "hook {} exit status is {}, error message is {}", &path, code, err
-                    );
-                    return Err(anyhow!(nix::Error::UnknownErrno));
-                }
-
-                debug!(logger, "hook {} exit status is 0", &path);
-                Ok(())
-            }
-            Err(e) => Err(anyhow!(
-                "wait child error: {} {}",
-                e,
-                e.raw_os_error().unwrap()
-            )),
-        }
-    });
-
-    match tokio::time::timeout(Duration::new(timeout, 0), join_handle).await {
-        Ok(r) => r.unwrap(),
-        Err(_) => Err(anyhow!(nix::Error::ETIMEDOUT)),
-    }
-}
-
-// valid environment variables according to https://doc.rust-lang.org/std/env/fn.set_var.html#panics
-fn valid_env(e: &str) -> Option<(&str, &str)> {
-    // wherther key or value will contain NULL char.
-    if e.as_bytes().contains(&b'\0') {
-        return None;
-    }
-
-    let v: Vec<&str> = e.splitn(2, '=').collect();
-
-    // key can't hold an `equal` sign, but value can
-    if v.len() != 2 {
-        return None;
-    }
-
-    let (key, value) = (v[0].trim(), v[1].trim());
-
-    // key can't be empty
-    if key.is_empty() {
-        return None;
-    }
-
-    Some((key, value))
-}
-
 #[cfg(test)]
 mod tests {
     use super::*;
     use crate::process::Process;
-    use crate::skip_if_not_root;
     use nix::unistd::Uid;
     use std::fs;
     use std::os::unix::fs::MetadataExt;
     use std::os::unix::io::AsRawFd;
     use tempfile::tempdir;
-    use tokio::process::Command;
+    use test_utils::skip_if_not_root;
 
     macro_rules! sl {
         () => {
@@ -1670,113 +1578,6 @@ mod tests {
         };
     }
 
-    async fn which(cmd: &str) -> String {
-        let output: std::process::Output = Command::new("which")
-            .arg(cmd)
-            .output()
-            .await
-            .expect("which command failed to run");
-
-        match String::from_utf8(output.stdout) {
-            Ok(v) => v.trim_end_matches('\n').to_string(),
-            Err(e) => panic!("Invalid UTF-8 sequence: {}", e),
-        }
-    }
-
-    #[tokio::test]
-    async fn test_execute_hook() {
-        let temp_file = "/tmp/test_execute_hook";
-
-        let touch = which("touch").await;
-
-        defer!(fs::remove_file(temp_file).unwrap(););
-        let invalid_str = vec![97, b'\0', 98];
-        let invalid_string = std::str::from_utf8(&invalid_str).unwrap();
-        let invalid_env = format!("{}=value", invalid_string);
-
-        execute_hook(
-            &slog_scope::logger(),
-            &Hook {
-                path: touch,
-                args: vec!["touch".to_string(), temp_file.to_string()],
-                env: vec![invalid_env],
-                timeout: Some(10),
-            },
-            &OCIState {
-                version: "1.2.3".to_string(),
-                id: "321".to_string(),
-                status: ContainerState::Running,
-                pid: 2,
-                bundle: "".to_string(),
-                annotations: Default::default(),
-            },
-        )
-        .await
-        .unwrap();
-
-        assert_eq!(Path::new(&temp_file).exists(), true);
-    }
-
-    #[tokio::test]
-    async fn test_execute_hook_with_error() {
-        let ls = which("ls").await;
-
-        let res = execute_hook(
-            &slog_scope::logger(),
-            &Hook {
-                path: ls,
-                args: vec!["ls".to_string(), "/tmp/not-exist".to_string()],
-                env: vec![],
-                timeout: None,
-            },
-            &OCIState {
-                version: "1.2.3".to_string(),
-                id: "321".to_string(),
-                status: ContainerState::Running,
-                pid: 2,
-                bundle: "".to_string(),
-                annotations: Default::default(),
-            },
-        )
-        .await;
-
-        let expected_err = nix::Error::UnknownErrno;
-        assert_eq!(
-            res.unwrap_err().downcast::<nix::Error>().unwrap(),
-            expected_err
-        );
-    }
-
-    #[tokio::test]
-    async fn test_execute_hook_with_timeout() {
-        let sleep = which("sleep").await;
-
-        let res = execute_hook(
-            &slog_scope::logger(),
-            &Hook {
-                path: sleep,
-                args: vec!["sleep".to_string(), "2".to_string()],
-                env: vec![],
-                timeout: Some(1),
-            },
-            &OCIState {
-                version: "1.2.3".to_string(),
-                id: "321".to_string(),
-                status: ContainerState::Running,
-                pid: 2,
-                bundle: "".to_string(),
-                annotations: Default::default(),
-            },
-        )
-        .await;
-
-        let expected_err = nix::Error::ETIMEDOUT;
-        assert_eq!(
-            res.unwrap_err().downcast::<nix::Error>().unwrap(),
-            expected_err
-        );
-    }
-
     #[test]
     fn test_status_transtition() {
         let mut status = ContainerStatus::new();
@@ -1929,20 +1730,12 @@ mod tests {
         assert!(format!("{:?}", ret).contains("failed to pause container"))
     }
 
-    #[test]
-    fn test_linuxcontainer_pause_cgroupmgr_is_none() {
-        let ret = new_linux_container_and_then(|mut c: LinuxContainer| {
-            c.cgroup_manager = None;
-            c.pause().map_err(|e| anyhow!(e))
-        });
-
-        assert!(ret.is_err(), "Expecting error, Got {:?}", ret);
-    }
-
     #[test]
     fn test_linuxcontainer_pause() {
         let ret = new_linux_container_and_then(|mut c: LinuxContainer| {
-            c.cgroup_manager = FsManager::new("").ok();
+            c.cgroup_manager = Box::new(FsManager::new("").map_err(|e| {
+                anyhow!(format!("fail to create cgroup manager with path: {:}", e))
+            })?);
             c.pause().map_err(|e| anyhow!(e))
         });
 
@@ -1961,21 +1754,12 @@ mod tests {
         assert!(format!("{:?}", ret).contains("not paused"))
     }
 
-    #[test]
-    fn test_linuxcontainer_resume_cgroupmgr_is_none() {
-        let ret = new_linux_container_and_then(|mut c: LinuxContainer| {
-            c.status.transition(ContainerState::Paused);
-            c.cgroup_manager = None;
-            c.resume().map_err(|e| anyhow!(e))
-        });
-
-        assert!(ret.is_err(), "Expecting error, Got {:?}", ret);
-    }
-
     #[test]
     fn test_linuxcontainer_resume() {
         let ret = new_linux_container_and_then(|mut c: LinuxContainer| {
-            c.cgroup_manager = FsManager::new("").ok();
+            c.cgroup_manager = Box::new(FsManager::new("").map_err(|e| {
+                anyhow!(format!("fail to create cgroup manager with path: {:}", e))
+            })?);
             // Change status to paused, this way we can resume it
             c.status.transition(ContainerState::Paused);
             c.resume().map_err(|e| anyhow!(e))
@@ -2108,49 +1892,4 @@ mod tests {
         let ret = do_init_child(std::io::stdin().as_raw_fd());
         assert!(ret.is_err(), "Expecting Err, Got {:?}", ret);
     }
-
-    #[test]
-    fn test_valid_env() {
-        let env = valid_env("a=b=c");
-        assert_eq!(Some(("a", "b=c")), env);
-
-        let env = valid_env("a=b");
-        assert_eq!(Some(("a", "b")), env);
-        let env = valid_env("a =b");
-        assert_eq!(Some(("a", "b")), env);
-
-        let env = valid_env(" a =b");
-        assert_eq!(Some(("a", "b")), env);
-
-        let env = valid_env("a= b");
-        assert_eq!(Some(("a", "b")), env);
-
-        let env = valid_env("a=b ");
-        assert_eq!(Some(("a", "b")), env);
-        let env = valid_env("a=b c ");
-        assert_eq!(Some(("a", "b c")), env);
-
-        let env = valid_env("=b");
-        assert_eq!(None, env);
-
-        let env = valid_env("a=");
-        assert_eq!(Some(("a", "")), env);
-
-        let env = valid_env("a==");
-        assert_eq!(Some(("a", "=")), env);
-
-        let env = valid_env("a");
-        assert_eq!(None, env);
-
-        let invalid_str = vec![97, b'\0', 98];
-        let invalid_string = std::str::from_utf8(&invalid_str).unwrap();
-
-        let invalid_env = format!("{}=value", invalid_string);
-        let env = valid_env(&invalid_env);
-        assert_eq!(None, env);
-
-        let invalid_env = format!("key={}", invalid_string);
-        let env = valid_env(&invalid_env);
-        assert_eq!(None, env);
-    }
 }

src/agent/rustjail/src/lib.rs

@@ -38,6 +38,7 @@ pub mod pipestream;
 pub mod process;
 #[cfg(feature = "seccomp")]
 pub mod seccomp;
+pub mod selinux;
 pub mod specconv;
 pub mod sync;
 pub mod sync_with_async;
@@ -514,15 +515,6 @@ pub fn grpc_to_oci(grpc: &grpc::Spec) -> oci::Spec {
 #[cfg(test)]
 mod tests {
     use super::*;
-    #[macro_export]
-    macro_rules! skip_if_not_root {
-        () => {
-            if !nix::unistd::Uid::effective().is_root() {
-                println!("INFO: skipping {} which needs root", module_path!());
-                return;
-            }
-        };
-    }
 
     // Parameters:
     //

src/agent/rustjail/src/mount.rs

@@ -25,6 +25,7 @@ use std::fs::File;
 use std::io::{BufRead, BufReader};
 
 use crate::container::DEFAULT_DEVICES;
+use crate::selinux;
 use crate::sync::write_count;
 use std::string::ToString;
 
@@ -181,6 +182,8 @@ pub fn init_rootfs(
         None => flags |= MsFlags::MS_SLAVE,
     }
 
+    let label = &linux.mount_label;
+
     let root = spec
         .root
         .as_ref()
@@ -244,7 +247,7 @@ pub fn init_rootfs(
                 }
             }
 
-            mount_from(cfd_log, m, rootfs, flags, &data, "")?;
+            mount_from(cfd_log, m, rootfs, flags, &data, label)?;
             // bind mount won't change mount options, we need remount to make mount options
             // effective.
             // first check that we have non-default options required before attempting a
@@ -524,7 +527,6 @@ pub fn pivot_rootfs<P: ?Sized + NixPath + std::fmt::Debug>(path: &P) -> Result<(
 
 fn rootfs_parent_mount_private(path: &str) -> Result<()> {
     let mount_infos = parse_mount_table(MOUNTINFO_PATH)?;
-
     let mut max_len = 0;
     let mut mount_point = String::from("");
     let mut options = String::from("");
@@ -767,9 +769,9 @@ fn mount_from(
     rootfs: &str,
     flags: MsFlags,
     data: &str,
-    _label: &str,
+    label: &str,
 ) -> Result<()> {
-    let d = String::from(data);
+    let mut d = String::from(data);
     let dest = secure_join(rootfs, &m.destination);
 
     let src = if m.r#type.as_str() == "bind" {
@@ -780,7 +782,7 @@ fn mount_from(
             Path::new(&dest).parent().unwrap()
         };
 
-        fs::create_dir_all(&dir).map_err(|e| {
+        fs::create_dir_all(dir).map_err(|e| {
             log_child!(
                 cfd_log,
                 "create dir {}: {}",
@@ -822,6 +824,37 @@ fn mount_from(
         e
     })?;
 
+    // Set the SELinux context for the mounts
+    let mut use_xattr = false;
+    if !label.is_empty() {
+        if selinux::is_enabled()? {
+            let device = Path::new(&m.source)
+                .file_name()
+                .ok_or_else(|| anyhow!("invalid device source path: {}", &m.source))?
+                .to_str()
+                .ok_or_else(|| anyhow!("failed to convert device source path: {}", &m.source))?;
+
+            match device {
+                // SELinux does not support labeling of /proc or /sys
+                "proc" | "sysfs" => (),
+                // SELinux does not support mount labeling against /dev/mqueue,
+                // so we use setxattr instead
+                "mqueue" => {
+                    use_xattr = true;
+                }
+                _ => {
+                    log_child!(cfd_log, "add SELinux mount label to {}", dest.as_str());
+                    selinux::add_mount_label(&mut d, label);
+                }
+            }
+        } else {
+            log_child!(
+                cfd_log,
+                "SELinux label for the mount is provided but SELinux is not enabled on the running kernel"
+            );
+        }
+    }
+
     mount(
         Some(src.as_str()),
         dest.as_str(),
@@ -834,6 +867,10 @@ fn mount_from(
         e
     })?;
 
+    if !label.is_empty() && selinux::is_enabled()? && use_xattr {
+        xattr::set(dest.as_str(), "security.selinux", label.as_bytes())?;
+    }
+
     if flags.contains(MsFlags::MS_BIND)
         && flags.intersects(
             !(MsFlags::MS_REC
@@ -1020,9 +1057,7 @@ pub fn finish_rootfs(cfd_log: RawFd, spec: &Spec, process: &Process) -> Result<(
 }
 
 fn mask_path(path: &str) -> Result<()> {
-    if !path.starts_with('/') || path.contains("..") {
-        return Err(anyhow!(nix::Error::EINVAL));
-    }
+    check_paths(path)?;
 
     match mount(
         Some("/dev/null"),
@@ -1040,9 +1075,7 @@ fn mask_path(path: &str) -> Result<()> {
 }
 
 fn readonly_path(path: &str) -> Result<()> {
-    if !path.starts_with('/') || path.contains("..") {
-        return Err(anyhow!(nix::Error::EINVAL));
-    }
+    check_paths(path)?;
 
     if let Err(e) = mount(
         Some(&path[1..]),
@@ -1068,11 +1101,20 @@ fn readonly_path(path: &str) -> Result<()> {
     Ok(())
 }
 
+fn check_paths(path: &str) -> Result<()> {
+    if !path.starts_with('/') || path.contains("..") {
+        return Err(anyhow!(
+            "Cannot mount {} (path does not start with '/' or contains '..').",
+            path
+        ));
+    }
+    Ok(())
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
     use crate::assert_result;
-    use crate::skip_if_not_root;
     use std::fs::create_dir;
     use std::fs::create_dir_all;
     use std::fs::remove_dir_all;
@@ -1080,6 +1122,7 @@ mod tests {
     use std::os::unix::fs;
     use std::os::unix::io::AsRawFd;
     use tempfile::tempdir;
+    use test_utils::skip_if_not_root;
 
     #[test]
     #[serial(chdir)]
@@ -1420,6 +1463,55 @@ mod tests {
         }
     }
 
+    #[test]
+    fn test_check_paths() {
+        #[derive(Debug)]
+        struct TestData<'a> {
+            name: &'a str,
+            path: &'a str,
+            result: Result<()>,
+        }
+
+        let tests = &[
+            TestData {
+                name: "valid path",
+                path: "/foo/bar",
+                result: Ok(()),
+            },
+            TestData {
+                name: "does not starts with /",
+                path: "foo/bar",
+                result: Err(anyhow!(
+                    "Cannot mount foo/bar (path does not start with '/' or contains '..')."
+                )),
+            },
+            TestData {
+                name: "contains ..",
+                path: "../foo/bar",
+                result: Err(anyhow!(
+                    "Cannot mount ../foo/bar (path does not start with '/' or contains '..')."
+                )),
+            },
+        ];
+
+        for (i, d) in tests.iter().enumerate() {
+            let msg = format!("test[{}]: {:?}", i, d.name);
+
+            let result = check_paths(d.path);
+
+            let msg = format!("{}: result: {:?}", msg, result);
+
+            if d.result.is_ok() {
+                assert!(result.is_ok());
+                continue;
+            }
+
+            let expected_error = format!("{}", d.result.as_ref().unwrap_err());
+            let actual_error = format!("{}", result.unwrap_err());
+            assert!(actual_error == expected_error, "{}", msg);
+        }
+    }
+
     #[test]
     fn test_check_proc_mount() {
         let mount = oci::Mount {

src/agent/rustjail/src/seccomp.rs

@@ -26,12 +26,15 @@ fn get_rule_conditions(args: &[LinuxSeccompArg]) -> Result<Vec<ScmpArgCompare>>
             return Err(anyhow!("seccomp opreator is required"));
         }
 
-        let cond = ScmpArgCompare::new(
-            arg.index,
-            ScmpCompareOp::from_str(&arg.op)?,
-            arg.value,
-            Some(arg.value_two),
-        );
+        let mut op = ScmpCompareOp::from_str(&arg.op)?;
+        let mut value = arg.value;
+        // For SCMP_CMP_MASKED_EQ, arg.value is the mask and arg.value_two is the value
+        if op == ScmpCompareOp::MaskedEqual(u64::default()) {
+            op = ScmpCompareOp::MaskedEqual(arg.value);
+            value = arg.value_two;
+        }
+
+        let cond = ScmpArgCompare::new(arg.index, op, value);
 
         conditions.push(cond);
     }
@@ -44,7 +47,7 @@ pub fn get_unknown_syscalls(scmp: &LinuxSeccomp) -> Option<Vec<String>> {
 
     for syscall in &scmp.syscalls {
         for name in &syscall.names {
-            if get_syscall_from_name(name, None).is_err() {
+            if ScmpSyscall::from_name(name).is_err() {
                 unknown_syscalls.push(name.to_string());
             }
         }
@@ -60,7 +63,7 @@ pub fn get_unknown_syscalls(scmp: &LinuxSeccomp) -> Option<Vec<String>> {
 // init_seccomp creates a seccomp filter and loads it for the current process
 // including all the child processes.
 pub fn init_seccomp(scmp: &LinuxSeccomp) -> Result<()> {
-    let def_action = ScmpAction::from_str(scmp.default_action.as_str(), Some(libc::EPERM as u32))?;
+    let def_action = ScmpAction::from_str(scmp.default_action.as_str(), Some(libc::EPERM))?;
 
     // Create a new filter context
     let mut filter = ScmpFilterContext::new_filter(def_action)?;
@@ -72,7 +75,7 @@ pub fn init_seccomp(scmp: &LinuxSeccomp) -> Result<()> {
     }
 
     // Unset no new privileges bit
-    filter.set_no_new_privs_bit(false)?;
+    filter.set_ctl_nnp(false)?;
 
     // Add a rule for each system call
     for syscall in &scmp.syscalls {
@@ -80,13 +83,13 @@ pub fn init_seccomp(scmp: &LinuxSeccomp) -> Result<()> {
             return Err(anyhow!("syscall name is required"));
         }
 
-        let action = ScmpAction::from_str(&syscall.action, Some(syscall.errno_ret))?;
+        let action = ScmpAction::from_str(&syscall.action, Some(syscall.errno_ret as i32))?;
         if action == def_action {
             continue;
         }
 
         for name in &syscall.names {
-            let syscall_num = match get_syscall_from_name(name, None) {
+            let syscall_num = match ScmpSyscall::from_name(name) {
                 Ok(num) => num,
                 Err(_) => {
                     // If we cannot resolve the given system call, we assume it is not supported
@@ -96,10 +99,10 @@ pub fn init_seccomp(scmp: &LinuxSeccomp) -> Result<()> {
             };
 
             if syscall.args.is_empty() {
-                filter.add_rule(action, syscall_num, None)?;
+                filter.add_rule(action, syscall_num)?;
             } else {
                 let conditions = get_rule_conditions(&syscall.args)?;
-                filter.add_rule(action, syscall_num, Some(&conditions))?;
+                filter.add_rule_conditional(action, syscall_num, &conditions)?;
             }
         }
     }
@@ -119,10 +122,10 @@ pub fn init_seccomp(scmp: &LinuxSeccomp) -> Result<()> {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::skip_if_not_root;
     use libc::{dup3, process_vm_readv, EPERM, O_CLOEXEC};
     use std::io::Error;
     use std::ptr::null;
+    use test_utils::skip_if_not_root;
 
     macro_rules! syscall_assert {
         ($e1: expr, $e2: expr) => {

src/agent/rustjail/src/selinux.rs

@@ -0,0 +1,80 @@
+// Copyright 2022 Sony Group Corporation
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+use anyhow::{Context, Result};
+use nix::unistd::gettid;
+use std::fs::{self, OpenOptions};
+use std::io::prelude::*;
+use std::path::Path;
+
+pub fn is_enabled() -> Result<bool> {
+    let buf = fs::read_to_string("/proc/mounts")?;
+    let enabled = buf.contains("selinuxfs");
+
+    Ok(enabled)
+}
+
+pub fn add_mount_label(data: &mut String, label: &str) {
+    if data.is_empty() {
+        let context = format!("context=\"{}\"", label);
+        data.push_str(&context);
+    } else {
+        let context = format!(",context=\"{}\"", label);
+        data.push_str(&context);
+    }
+}
+
+pub fn set_exec_label(label: &str) -> Result<()> {
+    let mut attr_path = Path::new("/proc/thread-self/attr/exec").to_path_buf();
+    if !attr_path.exists() {
+        // Fall back to the old convention
+        attr_path = Path::new("/proc/self/task")
+            .join(gettid().to_string())
+            .join("attr/exec")
+    }
+
+    let mut file = OpenOptions::new()
+        .write(true)
+        .truncate(true)
+        .open(attr_path)?;
+    file.write_all(label.as_bytes())
+        .with_context(|| "failed to apply SELinux label")?;
+
+    Ok(())
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    const TEST_LABEL: &str = "system_u:system_r:unconfined_t:s0";
+
+    #[test]
+    fn test_is_enabled() {
+        let ret = is_enabled();
+        assert!(ret.is_ok(), "Expecting Ok, Got {:?}", ret);
+    }
+
+    #[test]
+    fn test_add_mount_label() {
+        let mut data = String::new();
+        add_mount_label(&mut data, TEST_LABEL);
+        assert_eq!(data, format!("context=\"{}\"", TEST_LABEL));
+
+        let mut data = String::from("defaults");
+        add_mount_label(&mut data, TEST_LABEL);
+        assert_eq!(data, format!("defaults,context=\"{}\"", TEST_LABEL));
+    }
+
+    #[test]
+    fn test_set_exec_label() {
+        let ret = set_exec_label(TEST_LABEL);
+        if is_enabled().unwrap() {
+            assert!(ret.is_ok(), "Expecting Ok, Got {:?}", ret);
+        } else {
+            assert!(ret.is_err(), "Expecting error, Got {:?}", ret);
+        }
+    }
+}

src/agent/rustjail/src/validator.rs

@@ -4,17 +4,16 @@
 //
 
 use crate::container::Config;
-use anyhow::{anyhow, Context, Error, Result};
+use anyhow::{anyhow, Context, Result};
 use oci::{Linux, LinuxIdMapping, LinuxNamespace, Spec};
+use regex::Regex;
 use std::collections::HashMap;
 use std::path::{Component, PathBuf};
 
-fn einval() -> Error {
-    anyhow!(nix::Error::EINVAL)
-}
-
 fn get_linux(oci: &Spec) -> Result<&Linux> {
-    oci.linux.as_ref().ok_or_else(einval)
+    oci.linux
+        .as_ref()
+        .ok_or_else(|| anyhow!("Unable to get Linux section from Spec"))
 }
 
 fn contain_namespace(nses: &[LinuxNamespace], key: &str) -> bool {
@@ -31,7 +30,10 @@ fn rootfs(root: &str) -> Result<()> {
     let path = PathBuf::from(root);
     // not absolute path or not exists
     if !path.exists() || !path.is_absolute() {
-        return Err(einval());
+        return Err(anyhow!(
+            "Path from {:?} does not exist or is not absolute",
+            root
+        ));
     }
 
     // symbolic link? ..?
@@ -49,7 +51,7 @@ fn rootfs(root: &str) -> Result<()> {
         if let Some(v) = c.as_os_str().to_str() {
             stack.push(v.to_string());
         } else {
-            return Err(einval());
+            return Err(anyhow!("Invalid path component (unable to convert to str)"));
         }
     }
 
@@ -58,10 +60,13 @@ fn rootfs(root: &str) -> Result<()> {
         cleaned.push(e);
     }
 
-    let canon = path.canonicalize().context("canonicalize")?;
+    let canon = path.canonicalize().context("failed to canonicalize path")?;
     if cleaned != canon {
         // There is symbolic in path
-        return Err(einval());
+        return Err(anyhow!(
+            "There may be illegal symbols in the path name. Cleaned ({:?}) and canonicalized ({:?}) paths do not match",
+            cleaned,
+            canon));
     }
 
     Ok(())
@@ -74,7 +79,7 @@ fn hostname(oci: &Spec) -> Result<()> {
 
     let linux = get_linux(oci)?;
     if !contain_namespace(&linux.namespaces, "uts") {
-        return Err(einval());
+        return Err(anyhow!("Linux namespace does not contain uts"));
     }
 
     Ok(())
@@ -82,17 +87,32 @@ fn hostname(oci: &Spec) -> Result<()> {
 
 fn security(oci: &Spec) -> Result<()> {
     let linux = get_linux(oci)?;
+    let label_pattern = r".*_u:.*_r:.*_t:s[0-9]|1[0-5].*";
+    let label_regex = Regex::new(label_pattern)?;
+
+    if let Some(ref process) = oci.process {
+        if !process.selinux_label.is_empty() && !label_regex.is_match(&process.selinux_label) {
+            return Err(anyhow!(
+                "SELinux label for the process is invalid format: {}",
+                &process.selinux_label
+            ));
+        }
+    }
+    if !linux.mount_label.is_empty() && !label_regex.is_match(&linux.mount_label) {
+        return Err(anyhow!(
+            "SELinux label for the mount is invalid format: {}",
+            &linux.mount_label
+        ));
+    }
 
     if linux.masked_paths.is_empty() && linux.readonly_paths.is_empty() {
         return Ok(());
     }
 
     if !contain_namespace(&linux.namespaces, "mount") {
-        return Err(einval());
+        return Err(anyhow!("Linux namespace does not contain mount"));
     }
 
-    // don't care about selinux at present
-
     Ok(())
 }
 
@@ -103,7 +123,7 @@ fn idmapping(maps: &[LinuxIdMapping]) -> Result<()> {
         }
     }
 
-    Err(einval())
+    Err(anyhow!("No idmap has size > 0"))
 }
 
 fn usernamespace(oci: &Spec) -> Result<()> {
@@ -121,7 +141,7 @@ fn usernamespace(oci: &Spec) -> Result<()> {
     } else {
         // no user namespace but idmap
         if !linux.uid_mappings.is_empty() || !linux.gid_mappings.is_empty() {
-            return Err(einval());
+            return Err(anyhow!("No user namespace, but uid or gid mapping exists"));
         }
     }
 
@@ -163,7 +183,7 @@ fn sysctl(oci: &Spec) -> Result<()> {
             if contain_namespace(&linux.namespaces, "ipc") {
                 continue;
             } else {
-                return Err(einval());
+                return Err(anyhow!("Linux namespace does not contain ipc"));
             }
         }
 
@@ -178,11 +198,11 @@ fn sysctl(oci: &Spec) -> Result<()> {
             }
 
             if key == "kernel.hostname" {
-                return Err(einval());
+                return Err(anyhow!("Kernel hostname specfied in Spec"));
             }
         }
 
-        return Err(einval());
+        return Err(anyhow!("Sysctl config contains invalid settings"));
     }
     Ok(())
 }
@@ -191,12 +211,13 @@ fn rootless_euid_mapping(oci: &Spec) -> Result<()> {
     let linux = get_linux(oci)?;
 
     if !contain_namespace(&linux.namespaces, "user") {
-        return Err(einval());
+        return Err(anyhow!("Linux namespace is missing user"));
     }
 
     if linux.uid_mappings.is_empty() || linux.gid_mappings.is_empty() {
-        // rootless containers requires at least one UID/GID mapping
-        return Err(einval());
+        return Err(anyhow!(
+            "Rootless containers require at least one UID/GID mapping"
+        ));
     }
 
     Ok(())
@@ -220,7 +241,7 @@ fn rootless_euid_mount(oci: &Spec) -> Result<()> {
                 let fields: Vec<&str> = opt.split('=').collect();
 
                 if fields.len() != 2 {
-                    return Err(einval());
+                    return Err(anyhow!("Options has invalid field: {:?}", fields));
                 }
 
                 let id = fields[1]
@@ -229,11 +250,11 @@ fn rootless_euid_mount(oci: &Spec) -> Result<()> {
                     .context(format!("parse field {}", &fields[1]))?;
 
                 if opt.starts_with("uid=") && !has_idmapping(&linux.uid_mappings, id) {
-                    return Err(einval());
+                    return Err(anyhow!("uid of {} does not have a valid mapping", id));
                 }
 
                 if opt.starts_with("gid=") && !has_idmapping(&linux.gid_mappings, id) {
-                    return Err(einval());
+                    return Err(anyhow!("gid of {} does not have a valid mapping", id));
                 }
             }
         }
@@ -249,15 +270,18 @@ fn rootless_euid(oci: &Spec) -> Result<()> {
 
 pub fn validate(conf: &Config) -> Result<()> {
     lazy_static::initialize(&SYSCTLS);
-    let oci = conf.spec.as_ref().ok_or_else(einval)?;
+    let oci = conf
+        .spec
+        .as_ref()
+        .ok_or_else(|| anyhow!("Invalid config spec"))?;
 
     if oci.linux.is_none() {
-        return Err(einval());
+        return Err(anyhow!("oci Linux is none"));
     }
 
     let root = match oci.root.as_ref() {
         Some(v) => v.path.as_str(),
-        None => return Err(einval()),
+        None => return Err(anyhow!("oci root is none")),
     };
 
     rootfs(root).context("rootfs")?;
@@ -277,7 +301,7 @@ pub fn validate(conf: &Config) -> Result<()> {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use oci::Mount;
+    use oci::{Mount, Process};
 
     #[test]
     fn test_namespace() {
@@ -380,6 +404,29 @@ mod tests {
         ];
         spec.linux = Some(linux);
         security(&spec).unwrap();
+
+        // SELinux
+        let valid_label = "system_u:system_r:container_t:s0:c123,c456";
+        let mut process = Process::default();
+        process.selinux_label = valid_label.to_string();
+        spec.process = Some(process);
+        security(&spec).unwrap();
+
+        let mut linux = Linux::default();
+        linux.mount_label = valid_label.to_string();
+        spec.linux = Some(linux);
+        security(&spec).unwrap();
+
+        let invalid_label = "system_u:system_r:container_t";
+        let mut process = Process::default();
+        process.selinux_label = invalid_label.to_string();
+        spec.process = Some(process);
+        security(&spec).unwrap_err();
+
+        let mut linux = Linux::default();
+        linux.mount_label = invalid_label.to_string();
+        spec.linux = Some(linux);
+        security(&spec).unwrap_err();
     }
 
     #[test]

src/agent/src/config.rs

@@ -12,6 +12,8 @@ use std::str::FromStr;
 use std::time;
 use tracing::instrument;
 
+use kata_types::config::default::DEFAULT_AGENT_VSOCK_PORT;
+
 const DEBUG_CONSOLE_FLAG: &str = "agent.debug_console";
 const DEV_MODE_FLAG: &str = "agent.devmode";
 const TRACE_MODE_OPTION: &str = "agent.trace";
@@ -28,7 +30,6 @@ const DEFAULT_LOG_LEVEL: slog::Level = slog::Level::Info;
 const DEFAULT_HOTPLUG_TIMEOUT: time::Duration = time::Duration::from_secs(3);
 const DEFAULT_CONTAINER_PIPE_SIZE: i32 = 0;
 const VSOCK_ADDR: &str = "vsock://-1";
-const VSOCK_PORT: u16 = 1024;
 
 // Environment variables used for development and testing
 const SERVER_ADDR_ENV_VAR: &str = "KATA_AGENT_SERVER_ADDR";
@@ -147,7 +148,7 @@ impl Default for AgentConfig {
             debug_console_vport: 0,
             log_vport: 0,
             container_pipe_size: DEFAULT_CONTAINER_PIPE_SIZE,
-            server_addr: format!("{}:{}", VSOCK_ADDR, VSOCK_PORT),
+            server_addr: format!("{}:{}", VSOCK_ADDR, DEFAULT_AGENT_VSOCK_PORT),
             unified_cgroup_hierarchy: false,
             tracing: false,
             endpoints: Default::default(),
@@ -432,7 +433,7 @@ fn get_container_pipe_size(param: &str) -> Result<i32> {
 
 #[cfg(test)]
 mod tests {
-    use crate::assert_result;
+    use test_utils::assert_result;
 
     use super::*;
     use anyhow::anyhow;

src/agent/src/device.rs

@@ -414,7 +414,7 @@ fn scan_scsi_bus(scsi_addr: &str) -> Result<()> {
 
     // Scan scsi host passing in the channel, SCSI id and LUN.
     // Channel is always 0 because we have only one SCSI controller.
-    let scan_data = format!("0 {} {}", tokens[0], tokens[1]);
+    let scan_data = &format!("0 {} {}", tokens[0], tokens[1]);
 
     for entry in fs::read_dir(SYSFS_SCSI_HOST_PATH)? {
         let host = entry?.file_name();
@@ -428,7 +428,7 @@ fn scan_scsi_bus(scsi_addr: &str) -> Result<()> {
 
         let scan_path = PathBuf::from(&format!("{}/{}/{}", SYSFS_SCSI_HOST_PATH, host_str, "scan"));
 
-        fs::write(scan_path, &scan_data)?;
+        fs::write(scan_path, scan_data)?;
     }
 
     Ok(())
@@ -1531,7 +1531,7 @@ mod tests {
         pci_driver_override(syspci, dev0, "drv_b").unwrap();
         assert_eq!(fs::read_to_string(&dev0override).unwrap(), "drv_b");
         assert_eq!(fs::read_to_string(&probepath).unwrap(), dev0.to_string());
-        assert_eq!(fs::read_to_string(&drvaunbind).unwrap(), dev0.to_string());
+        assert_eq!(fs::read_to_string(drvaunbind).unwrap(), dev0.to_string());
     }
 
     #[test]
@@ -1543,7 +1543,7 @@ mod tests {
         let dev0 = pci::Address::new(0, 0, pci::SlotFn::new(0, 0).unwrap());
         let dev0path = syspci.join("devices").join(dev0.to_string());
 
-        fs::create_dir_all(&dev0path).unwrap();
+        fs::create_dir_all(dev0path).unwrap();
 
         // Test dev0
         assert!(pci_iommu_group(&syspci, dev0).unwrap().is_none());
@@ -1554,7 +1554,7 @@ mod tests {
         let dev1group = dev1path.join("iommu_group");
 
         fs::create_dir_all(&dev1path).unwrap();
-        std::os::unix::fs::symlink("../../../kernel/iommu_groups/12", &dev1group).unwrap();
+        std::os::unix::fs::symlink("../../../kernel/iommu_groups/12", dev1group).unwrap();
 
         // Test dev1
         assert_eq!(
@@ -1567,7 +1567,7 @@ mod tests {
         let dev2path = syspci.join("devices").join(dev2.to_string());
         let dev2group = dev2path.join("iommu_group");
 
-        fs::create_dir_all(&dev2group).unwrap();
+        fs::create_dir_all(dev2group).unwrap();
 
         // Test dev2
         assert!(pci_iommu_group(&syspci, dev2).is_err());

src/agent/src/main.rs

@@ -49,8 +49,6 @@ mod pci;
 pub mod random;
 mod sandbox;
 mod signal;
-#[cfg(test)]
-mod test_utils;
 mod uevent;
 mod util;
 mod version;
@@ -341,7 +339,7 @@ async fn start_sandbox(
     sandbox.lock().await.sender = Some(tx);
 
     // vsock:///dev/vsock, port
-    let mut server = rpc::start(sandbox.clone(), config.server_addr.as_str())?;
+    let mut server = rpc::start(sandbox.clone(), config.server_addr.as_str(), init_mode)?;
     server.start().await?;
 
     rx.await?;
@@ -401,7 +399,8 @@ use std::os::unix::io::{FromRawFd, RawFd};
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::test_utils::test_utils::TestUserType;
+    use test_utils::TestUserType;
+    use test_utils::{assert_result, skip_if_not_root, skip_if_root};
 
     #[tokio::test]
     async fn test_create_logger_task() {
@@ -437,9 +436,8 @@ mod tests {
             let msg = format!("test[{}]: {:?}", i, d);
             let (rfd, wfd) = unistd::pipe2(OFlag::O_CLOEXEC).unwrap();
             defer!({
-                // rfd is closed by the use of PipeStream in the crate_logger_task function,
-                // but we will attempt to close in case of a failure
-                let _ = unistd::close(rfd);
+                // XXX: Never try to close rfd, because it will be closed by PipeStream in
+                // create_logger_task() and it's not safe to close the same fd twice time.
                 unistd::close(wfd).unwrap();
             });
 

src/agent/src/metrics.rs

@@ -5,10 +5,11 @@
 
 extern crate procfs;
 
-use prometheus::{Encoder, Gauge, GaugeVec, IntCounter, TextEncoder};
+use prometheus::{Encoder, Gauge, GaugeVec, IntCounter, Opts, Registry, TextEncoder};
 
-use anyhow::Result;
+use anyhow::{anyhow, Result};
 use slog::warn;
+use std::sync::Mutex;
 use tracing::instrument;
 
 const NAMESPACE_KATA_AGENT: &str = "kata_agent";
@@ -23,55 +24,70 @@ macro_rules! sl {
 
 lazy_static! {
 
-    static ref     AGENT_SCRAPE_COUNT: IntCounter =
-    prometheus::register_int_counter!(format!("{}_{}",NAMESPACE_KATA_AGENT,"scrape_count"), "Metrics scrape count").unwrap();
+    static ref REGISTERED: Mutex<bool> = Mutex::new(false);
 
-    static ref     AGENT_THREADS: Gauge =
-    prometheus::register_gauge!(format!("{}_{}",NAMESPACE_KATA_AGENT,"threads"), "Agent process threads").unwrap();
+    // custom registry
+    static ref REGISTRY: Registry = Registry::new();
 
-    static ref     AGENT_TOTAL_TIME: Gauge =
-    prometheus::register_gauge!(format!("{}_{}",NAMESPACE_KATA_AGENT,"total_time"), "Agent process total time").unwrap();
+    static ref AGENT_SCRAPE_COUNT: IntCounter =
+    IntCounter::new(format!("{}_{}",NAMESPACE_KATA_AGENT,"scrape_count"), "Metrics scrape count").unwrap();
 
-    static ref     AGENT_TOTAL_VM: Gauge =
-    prometheus::register_gauge!(format!("{}_{}",NAMESPACE_KATA_AGENT,"total_vm"), "Agent process total VM size").unwrap();
+    // agent metrics
+    static ref AGENT_THREADS: Gauge =
+    Gauge::new(format!("{}_{}",NAMESPACE_KATA_AGENT,"threads"), "Agent process threads").unwrap();
 
-    static ref     AGENT_TOTAL_RSS: Gauge =
-    prometheus::register_gauge!(format!("{}_{}",NAMESPACE_KATA_AGENT,"total_rss"), "Agent process total RSS size").unwrap();
+    static ref AGENT_TOTAL_TIME: Gauge =
+    Gauge::new(format!("{}_{}",NAMESPACE_KATA_AGENT,"total_time"), "Agent process total time").unwrap();
 
-    static ref     AGENT_PROC_STATUS: GaugeVec =
-    prometheus::register_gauge_vec!(format!("{}_{}",NAMESPACE_KATA_AGENT,"proc_status"), "Agent process status.", &["item"]).unwrap();
+    static ref AGENT_TOTAL_VM: Gauge =
+    Gauge::new(format!("{}_{}",NAMESPACE_KATA_AGENT,"total_vm"), "Agent process total VM size").unwrap() ;
 
-    static ref     AGENT_IO_STAT: GaugeVec =
-    prometheus::register_gauge_vec!(format!("{}_{}",NAMESPACE_KATA_AGENT,"io_stat"), "Agent process IO statistics.", &["item"]).unwrap();
+    static ref AGENT_TOTAL_RSS: Gauge =
+    Gauge::new(format!("{}_{}",NAMESPACE_KATA_AGENT,"total_rss"), "Agent process total RSS size").unwrap();
 
-    static ref     AGENT_PROC_STAT: GaugeVec =
-    prometheus::register_gauge_vec!(format!("{}_{}",NAMESPACE_KATA_AGENT,"proc_stat"), "Agent process statistics.", &["item"]).unwrap();
+    static ref AGENT_PROC_STATUS: GaugeVec =
+    GaugeVec::new(Opts::new(format!("{}_{}",NAMESPACE_KATA_AGENT,"proc_status"), "Agent process status."), &["item"]).unwrap();
+
+    static ref AGENT_IO_STAT: GaugeVec =
+    GaugeVec::new(Opts::new(format!("{}_{}",NAMESPACE_KATA_AGENT,"io_stat"), "Agent process IO statistics."), &["item"]).unwrap();
+
+    static ref AGENT_PROC_STAT: GaugeVec =
+    GaugeVec::new(Opts::new(format!("{}_{}",NAMESPACE_KATA_AGENT,"proc_stat"), "Agent process statistics."), &["item"]).unwrap();
 
     // guest os metrics
-    static ref     GUEST_LOAD: GaugeVec =
-    prometheus::register_gauge_vec!(format!("{}_{}",NAMESPACE_KATA_GUEST,"load") , "Guest system load.", &["item"]).unwrap();
+    static ref GUEST_LOAD: GaugeVec =
+    GaugeVec::new(Opts::new(format!("{}_{}",NAMESPACE_KATA_GUEST,"load"), "Guest system load."), &["item"]).unwrap();
 
-    static ref     GUEST_TASKS: GaugeVec =
-    prometheus::register_gauge_vec!(format!("{}_{}",NAMESPACE_KATA_GUEST,"tasks") , "Guest system load.", &["item"]).unwrap();
+    static ref GUEST_TASKS: GaugeVec =
+    GaugeVec::new(Opts::new(format!("{}_{}",NAMESPACE_KATA_GUEST,"tasks"), "Guest system load."), &["item"]).unwrap();
 
-    static ref     GUEST_CPU_TIME: GaugeVec =
-    prometheus::register_gauge_vec!(format!("{}_{}",NAMESPACE_KATA_GUEST,"cpu_time") , "Guest CPU statistics.", &["cpu","item"]).unwrap();
+    static ref GUEST_CPU_TIME: GaugeVec =
+    GaugeVec::new(Opts::new(format!("{}_{}",NAMESPACE_KATA_GUEST,"cpu_time"), "Guest CPU statistics."), &["cpu","item"]).unwrap();
 
-    static ref     GUEST_VM_STAT: GaugeVec =
-    prometheus::register_gauge_vec!(format!("{}_{}",NAMESPACE_KATA_GUEST,"vm_stat") , "Guest virtual memory statistics.", &["item"]).unwrap();
+    static ref GUEST_VM_STAT: GaugeVec =
+    GaugeVec::new(Opts::new(format!("{}_{}",NAMESPACE_KATA_GUEST,"vm_stat"), "Guest virtual memory statistics."), &["item"]).unwrap();
 
-    static ref     GUEST_NETDEV_STAT: GaugeVec =
-    prometheus::register_gauge_vec!(format!("{}_{}",NAMESPACE_KATA_GUEST,"netdev_stat") , "Guest net devices statistics.", &["interface","item"]).unwrap();
+    static ref GUEST_NETDEV_STAT: GaugeVec =
+    GaugeVec::new(Opts::new(format!("{}_{}",NAMESPACE_KATA_GUEST,"netdev_stat"), "Guest net devices statistics."), &["interface","item"]).unwrap();
 
-    static ref     GUEST_DISKSTAT: GaugeVec =
-    prometheus::register_gauge_vec!(format!("{}_{}",NAMESPACE_KATA_GUEST,"diskstat") , "Disks statistics in system.", &["disk","item"]).unwrap();
+    static ref GUEST_DISKSTAT: GaugeVec =
+    GaugeVec::new(Opts::new(format!("{}_{}",NAMESPACE_KATA_GUEST,"diskstat"), "Disks statistics in system."), &["disk","item"]).unwrap();
 
-    static ref     GUEST_MEMINFO: GaugeVec =
-    prometheus::register_gauge_vec!(format!("{}_{}",NAMESPACE_KATA_GUEST,"meminfo") , "Statistics about memory usage in the system.", &["item"]).unwrap();
+    static ref GUEST_MEMINFO: GaugeVec =
+    GaugeVec::new(Opts::new(format!("{}_{}",NAMESPACE_KATA_GUEST,"meminfo"), "Statistics about memory usage in the system."), &["item"]).unwrap();
 }
 
 #[instrument]
 pub fn get_metrics(_: &protocols::agent::GetMetricsRequest) -> Result<String> {
+    let mut registered = REGISTERED
+        .lock()
+        .map_err(|e| anyhow!("failed to check agent metrics register status {:?}", e))?;
+
+    if !(*registered) {
+        register_metrics()?;
+        *registered = true;
+    }
+
     AGENT_SCRAPE_COUNT.inc();
 
     // update agent process metrics
@@ -81,7 +97,7 @@ pub fn get_metrics(_: &protocols::agent::GetMetricsRequest) -> Result<String> {
     update_guest_metrics();
 
     // gather all metrics and return as a String
-    let metric_families = prometheus::gather();
+    let metric_families = REGISTRY.gather();
 
     let mut buffer = Vec::new();
     let encoder = TextEncoder::new();
@@ -90,6 +106,31 @@ pub fn get_metrics(_: &protocols::agent::GetMetricsRequest) -> Result<String> {
     Ok(String::from_utf8(buffer)?)
 }
 
+#[instrument]
+fn register_metrics() -> Result<()> {
+    REGISTRY.register(Box::new(AGENT_SCRAPE_COUNT.clone()))?;
+
+    // agent metrics
+    REGISTRY.register(Box::new(AGENT_THREADS.clone()))?;
+    REGISTRY.register(Box::new(AGENT_TOTAL_TIME.clone()))?;
+    REGISTRY.register(Box::new(AGENT_TOTAL_VM.clone()))?;
+    REGISTRY.register(Box::new(AGENT_TOTAL_RSS.clone()))?;
+    REGISTRY.register(Box::new(AGENT_PROC_STATUS.clone()))?;
+    REGISTRY.register(Box::new(AGENT_IO_STAT.clone()))?;
+    REGISTRY.register(Box::new(AGENT_PROC_STAT.clone()))?;
+
+    // guest metrics
+    REGISTRY.register(Box::new(GUEST_LOAD.clone()))?;
+    REGISTRY.register(Box::new(GUEST_TASKS.clone()))?;
+    REGISTRY.register(Box::new(GUEST_CPU_TIME.clone()))?;
+    REGISTRY.register(Box::new(GUEST_VM_STAT.clone()))?;
+    REGISTRY.register(Box::new(GUEST_NETDEV_STAT.clone()))?;
+    REGISTRY.register(Box::new(GUEST_DISKSTAT.clone()))?;
+    REGISTRY.register(Box::new(GUEST_MEMINFO.clone()))?;
+
+    Ok(())
+}
+
 #[instrument]
 fn update_agent_metrics() -> Result<()> {
     let me = procfs::process::Process::myself();

src/agent/src/mount.rs

@@ -169,11 +169,12 @@ pub fn baremount(
 
     info!(
         logger,
-        "mount source={:?}, dest={:?}, fs_type={:?}, options={:?}",
+        "baremount source={:?}, dest={:?}, fs_type={:?}, options={:?}, flags={:?}",
         source,
         destination,
         fs_type,
-        options
+        options,
+        flags
     );
 
     nix::mount::mount(
@@ -647,7 +648,7 @@ pub fn recursive_ownership_change(
 ) -> Result<()> {
     let mut mask = if read_only { RO_MASK } else { RW_MASK };
     if path.is_dir() {
-        for entry in fs::read_dir(&path)? {
+        for entry in fs::read_dir(path)? {
             recursive_ownership_change(entry?.path().as_path(), uid, gid, read_only)?;
         }
         mask |= EXEC_MASK;
@@ -778,8 +779,20 @@ pub async fn add_storages(
             }
         };
 
-        // Todo need to rollback the mounted storage if err met.
-        let mount_point = res?;
+        let mount_point = match res {
+            Err(e) => {
+                error!(
+                    logger,
+                    "add_storages failed, storage: {:?}, error: {:?} ", storage, e
+                );
+                let mut sb = sandbox.lock().await;
+                sb.unset_sandbox_storage(&storage.mount_point)
+                    .map_err(|e| warn!(logger, "fail to unset sandbox storage {:?}", e))
+                    .ok();
+                return Err(e);
+            }
+            Ok(m) => m,
+        };
 
         if !mount_point.is_empty() {
             mount_list.push(mount_point);
@@ -840,7 +853,8 @@ pub fn get_mount_fs_type_from_file(mount_file: &str, mount_point: &str) -> Resul
         return Err(anyhow!("Invalid mount point {}", mount_point));
     }
 
-    let content = fs::read_to_string(mount_file)?;
+    let content = fs::read_to_string(mount_file)
+        .map_err(|e| anyhow!("read mount file {}: {}", mount_file, e))?;
 
     let re = Regex::new(format!("device .+ mounted on {} with fstype (.+)", mount_point).as_str())?;
 
@@ -880,7 +894,7 @@ pub fn get_cgroup_mounts(
         }]);
     }
 
-    let file = File::open(&cg_path)?;
+    let file = File::open(cg_path)?;
     let reader = BufReader::new(file);
 
     let mut has_device_cgroup = false;
@@ -1016,8 +1030,6 @@ fn parse_options(option_list: Vec<String>) -> HashMap<String, String> {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::test_utils::test_utils::TestUserType;
-    use crate::{skip_if_not_root, skip_loop_by_user, skip_loop_if_not_root, skip_loop_if_root};
     use protobuf::RepeatedField;
     use protocols::agent::FSGroup;
     use std::fs::File;
@@ -1025,6 +1037,10 @@ mod tests {
     use std::io::Write;
     use std::path::PathBuf;
     use tempfile::tempdir;
+    use test_utils::TestUserType;
+    use test_utils::{
+        skip_if_not_root, skip_loop_by_user, skip_loop_if_not_root, skip_loop_if_root,
+    };
 
     #[test]
     fn test_mount() {
@@ -1761,7 +1777,7 @@ mod tests {
             let tempdir = tempdir().unwrap();
 
             let src = if d.mask_src {
-                tempdir.path().join(&d.src)
+                tempdir.path().join(d.src)
             } else {
                 Path::new(d.src).to_path_buf()
             };

src/agent/src/namespace.rs

@@ -78,6 +78,7 @@ impl Namespace {
     // setup creates persistent namespace without switching to it.
     // Note, pid namespaces cannot be persisted.
     #[instrument]
+    #[allow(clippy::question_mark)]
     pub async fn setup(mut self) -> Result<Self> {
         fs::create_dir_all(&self.persistent_ns_dir)?;
 
@@ -88,7 +89,7 @@ impl Namespace {
         }
         let logger = self.logger.clone();
 
-        let new_ns_path = ns_path.join(&ns_type.get());
+        let new_ns_path = ns_path.join(ns_type.get());
 
         File::create(new_ns_path.as_path())?;
 
@@ -102,7 +103,7 @@ impl Namespace {
                 let source = Path::new(&origin_ns_path);
                 let destination = new_ns_path.as_path();
 
-                File::open(&source)?;
+                File::open(source)?;
 
                 // Create a new netns on the current thread.
                 let cf = ns_type.get_flags();
@@ -187,9 +188,10 @@ impl fmt::Debug for NamespaceType {
 #[cfg(test)]
 mod tests {
     use super::{Namespace, NamespaceType};
-    use crate::{mount::remove_mounts, skip_if_not_root};
+    use crate::mount::remove_mounts;
     use nix::sched::CloneFlags;
     use tempfile::Builder;
+    use test_utils::skip_if_not_root;
 
     #[tokio::test]
     async fn test_setup_persistent_ns() {

src/agent/src/netlink.rs

@@ -4,7 +4,7 @@
 //
 
 use anyhow::{anyhow, Context, Result};
-use futures::{future, TryStreamExt};
+use futures::{future, StreamExt, TryStreamExt};
 use ipnetwork::{IpNetwork, Ipv4Network, Ipv6Network};
 use nix::errno::Errno;
 use protobuf::RepeatedField;
@@ -164,7 +164,7 @@ impl Handle {
         let request = self.handle.link().get();
 
         let filtered = match filter {
-            LinkFilter::Name(name) => request.match_name(name.to_owned()),
+            LinkFilter::Name(name) => request.set_name_filter(name.to_owned()),
             LinkFilter::Index(index) => request.match_index(index),
             _ => request, // Post filters
         };
@@ -516,24 +516,72 @@ impl Handle {
     }
 
     /// Adds an ARP neighbor.
+    /// TODO: `rtnetlink` has no neighbours API, remove this after https://github.com/little-dude/netlink/pull/135
     async fn add_arp_neighbor(&mut self, neigh: &ARPNeighbor) -> Result<()> {
         let ip_address = neigh
             .toIPAddress
             .as_ref()
             .map(|to| to.address.as_str()) // Extract address field
             .and_then(|addr| if addr.is_empty() { None } else { Some(addr) }) // Make sure it's not empty
-            .ok_or_else(|| anyhow!(nix::Error::EINVAL))?;
+            .ok_or_else(|| anyhow!("Unable to determine ip address of ARP neighbor"))?;
 
         let ip = IpAddr::from_str(ip_address)
             .map_err(|e| anyhow!("Failed to parse IP {}: {:?}", ip_address, e))?;
 
+        // Import rtnetlink objects that make sense only for this function
+        use packet::constants::{
+            NDA_UNSPEC, NLM_F_ACK, NLM_F_CREATE, NLM_F_REPLACE, NLM_F_REQUEST,
+        };
+        use packet::neighbour::{NeighbourHeader, NeighbourMessage};
+        use packet::nlas::neighbour::Nla;
+        use packet::{NetlinkMessage, NetlinkPayload, RtnlMessage};
+        use rtnetlink::Error;
+
+        const IFA_F_PERMANENT: u16 = 0x80; // See https://github.com/little-dude/netlink/blob/0185b2952505e271805902bf175fee6ea86c42b8/netlink-packet-route/src/rtnl/constants.rs#L770
+
         let link = self.find_link(LinkFilter::Name(&neigh.device)).await?;
 
-        self.handle
-            .neighbours()
-            .add(link.index(), ip)
-            .execute()
-            .await?;
+        let message = NeighbourMessage {
+            header: NeighbourHeader {
+                family: match ip {
+                    IpAddr::V4(_) => packet::AF_INET,
+                    IpAddr::V6(_) => packet::AF_INET6,
+                } as u8,
+                ifindex: link.index(),
+                state: if neigh.state != 0 {
+                    neigh.state as u16
+                } else {
+                    IFA_F_PERMANENT
+                },
+                flags: neigh.flags as u8,
+                ntype: NDA_UNSPEC as u8,
+            },
+            nlas: {
+                let mut nlas = vec![Nla::Destination(match ip {
+                    IpAddr::V4(v4) => v4.octets().to_vec(),
+                    IpAddr::V6(v6) => v6.octets().to_vec(),
+                })];
+
+                if !neigh.lladdr.is_empty() {
+                    nlas.push(Nla::LinkLocalAddress(
+                        parse_mac_address(&neigh.lladdr)?.to_vec(),
+                    ));
+                }
+
+                nlas
+            },
+        };
+
+        // Send request and ACK
+        let mut req = NetlinkMessage::from(RtnlMessage::NewNeighbour(message));
+        req.header.flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_CREATE | NLM_F_REPLACE;
+
+        let mut response = self.handle.request(req)?;
+        while let Some(message) = response.next().await {
+            if let NetlinkPayload::Error(err) = message.payload {
+                return Err(anyhow!(Error::NetlinkError(err)));
+            }
+        }
 
         Ok(())
     }
@@ -566,7 +614,12 @@ fn parse_mac_address(addr: &str) -> Result<[u8; 6]> {
 
     // Parse single Mac address block
     let mut parse_next = || -> Result<u8> {
-        let v = u8::from_str_radix(split.next().ok_or_else(|| anyhow!(nix::Error::EINVAL))?, 16)?;
+        let v = u8::from_str_radix(
+            split
+                .next()
+                .ok_or_else(|| anyhow!("Invalid MAC address {}", addr))?,
+            16,
+        )?;
         Ok(v)
     };
 
@@ -724,10 +777,10 @@ impl Address {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::skip_if_not_root;
     use rtnetlink::packet;
     use std::iter;
     use std::process::Command;
+    use test_utils::skip_if_not_root;
 
     #[tokio::test]
     async fn find_link_by_name() {
@@ -893,18 +946,18 @@ mod tests {
     fn clean_env_for_test_add_one_arp_neighbor(dummy_name: &str, ip: &str) {
         // ip link delete dummy
         Command::new("ip")
-            .args(&["link", "delete", dummy_name])
+            .args(["link", "delete", dummy_name])
             .output()
             .expect("prepare: failed to delete dummy");
 
         // ip neigh del dev dummy ip
         Command::new("ip")
-            .args(&["neigh", "del", dummy_name, ip])
+            .args(["neigh", "del", dummy_name, ip])
             .output()
             .expect("prepare: failed to delete neigh");
     }
 
-    fn prepare_env_for_test_add_one_arp_neighbor(dummy_name: &str, ip: &str, mac: &str) {
+    fn prepare_env_for_test_add_one_arp_neighbor(dummy_name: &str, ip: &str) {
         clean_env_for_test_add_one_arp_neighbor(dummy_name, ip);
         // modprobe dummy
         Command::new("modprobe")
@@ -914,25 +967,19 @@ mod tests {
 
         // ip link add dummy type dummy
         Command::new("ip")
-            .args(&["link", "add", dummy_name, "type", "dummy"])
-            .output()
-            .expect("failed to add dummy interface");
-
-        // ip link set dummy address 6a:92:3a:59:70:aa
-        Command::new("ip")
-            .args(&["link", "set", dummy_name, "address", mac])
+            .args(["link", "add", dummy_name, "type", "dummy"])
             .output()
             .expect("failed to add dummy interface");
 
         // ip addr add 192.168.0.2/16 dev dummy
         Command::new("ip")
-            .args(&["addr", "add", "192.168.0.2/16", "dev", dummy_name])
+            .args(["addr", "add", "192.168.0.2/16", "dev", dummy_name])
             .output()
             .expect("failed to add ip for dummy");
 
         // ip link set dummy up;
         Command::new("ip")
-            .args(&["link", "set", dummy_name, "up"])
+            .args(["link", "set", dummy_name, "up"])
             .output()
             .expect("failed to up dummy");
     }
@@ -945,7 +992,7 @@ mod tests {
         let to_ip = "169.254.1.1";
         let dummy_name = "dummy_for_arp";
 
-        prepare_env_for_test_add_one_arp_neighbor(dummy_name, to_ip, mac);
+        prepare_env_for_test_add_one_arp_neighbor(dummy_name, to_ip);
 
         let mut ip_address = IPAddress::new();
         ip_address.set_address(to_ip.to_string());
@@ -964,7 +1011,7 @@ mod tests {
 
         // ip neigh show dev dummy ip
         let stdout = Command::new("ip")
-            .args(&["neigh", "show", "dev", dummy_name, to_ip])
+            .args(["neigh", "show", "dev", dummy_name, to_ip])
             .output()
             .expect("failed to show neigh")
             .stdout;

src/agent/src/network.rs

@@ -64,7 +64,7 @@ fn do_setup_guest_dns(logger: Logger, dns_list: Vec<String>, src: &str, dst: &st
         .map(|x| x.trim())
         .collect::<Vec<&str>>()
         .join("\n");
-    fs::write(src, &content)?;
+    fs::write(src, content)?;
 
     // bind mount to /etc/resolv.conf
     mount::mount(Some(src), dst, Some("bind"), MsFlags::MS_BIND, None::<&str>)
@@ -76,11 +76,11 @@ fn do_setup_guest_dns(logger: Logger, dns_list: Vec<String>, src: &str, dst: &st
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::skip_if_not_root;
     use nix::mount;
     use std::fs::File;
     use std::io::Write;
     use tempfile::tempdir;
+    use test_utils::skip_if_not_root;
 
     #[test]
     fn test_setup_guest_dns() {

src/agent/src/random.rs

@@ -53,9 +53,9 @@ pub fn reseed_rng(data: &[u8]) -> Result<()> {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::skip_if_not_root;
     use std::fs::File;
     use std::io::prelude::*;
+    use test_utils::skip_if_not_root;
 
     #[test]
     fn test_reseed_rng() {

src/agent/src/rpc.rs

@@ -36,7 +36,7 @@ use protocols::health::{
 use protocols::types::Interface;
 use protocols::{agent_ttrpc_async as agent_ttrpc, health_ttrpc_async as health_ttrpc};
 use rustjail::cgroups::notifier;
-use rustjail::container::{BaseContainer, Container, LinuxContainer};
+use rustjail::container::{BaseContainer, Container, LinuxContainer, SYSTEMD_CGROUP_PATH_FORMAT};
 use rustjail::process::Process;
 use rustjail::specconv::CreateOpts;
 
@@ -44,7 +44,6 @@ use nix::errno::Errno;
 use nix::mount::MsFlags;
 use nix::sys::{stat, statfs};
 use nix::unistd::{self, Pid};
-use rustjail::cgroups::Manager;
 use rustjail::process::ProcessOperations;
 
 use crate::device::{
@@ -84,9 +83,15 @@ use std::path::PathBuf;
 const CONTAINER_BASE: &str = "/run/kata-containers";
 const MODPROBE_PATH: &str = "/sbin/modprobe";
 
+/// the iptables seriers binaries could appear either in /sbin
+/// or /usr/sbin, we need to check both of them
+const USR_IPTABLES_SAVE: &str = "/usr/sbin/iptables-save";
 const IPTABLES_SAVE: &str = "/sbin/iptables-save";
+const USR_IPTABLES_RESTORE: &str = "/usr/sbin/iptables-store";
 const IPTABLES_RESTORE: &str = "/sbin/iptables-restore";
+const USR_IP6TABLES_SAVE: &str = "/usr/sbin/ip6tables-save";
 const IP6TABLES_SAVE: &str = "/sbin/ip6tables-save";
+const USR_IP6TABLES_RESTORE: &str = "/usr/sbin/ip6tables-save";
 const IP6TABLES_RESTORE: &str = "/sbin/ip6tables-restore";
 
 const ERR_CANNOT_GET_WRITER: &str = "Cannot get writer";
@@ -132,6 +137,7 @@ macro_rules! is_allowed {
 #[derive(Clone, Debug)]
 pub struct AgentService {
     sandbox: Arc<Mutex<Sandbox>>,
+    init_mode: bool,
 }
 
 impl AgentService {
@@ -205,9 +211,20 @@ impl AgentService {
         // restore the cwd for kata-agent process.
         defer!(unistd::chdir(&olddir).unwrap());
 
+        // determine which cgroup driver to take and then assign to use_systemd_cgroup
+        // systemd: "[slice]:[prefix]:[name]"
+        // fs: "/path_a/path_b"
+        // If agent is init we can't use systemd cgroup mode, no matter what the host tells us
+        let cgroups_path = oci.linux.as_ref().map_or("", |linux| &linux.cgroups_path);
+        let use_systemd_cgroup = if self.init_mode {
+            false
+        } else {
+            SYSTEMD_CGROUP_PATH_FORMAT.is_match(cgroups_path)
+        };
+
         let opts = CreateOpts {
             cgroup_name: "".to_string(),
-            use_systemd_cgroup: false,
+            use_systemd_cgroup,
             no_pivot_root: s.no_pivot_root,
             no_new_keyring: false,
             spec: Some(oci.clone()),
@@ -226,7 +243,20 @@ impl AgentService {
             info!(sl!(), "no process configurations!");
             return Err(anyhow!(nix::Error::EINVAL));
         };
-        ctr.start(p).await?;
+
+        // if starting container failed, we will do some rollback work
+        // to ensure no resources are leaked.
+        if let Err(err) = ctr.start(p).await {
+            error!(sl!(), "failed to start container: {:?}", err);
+            if let Err(e) = ctr.destroy().await {
+                error!(sl!(), "failed to destroy container: {:?}", e);
+            }
+            if let Err(e) = remove_container_resources(&mut s, &cid) {
+                error!(sl!(), "failed to remove container resources: {:?}", e);
+            }
+            return Err(err);
+        }
+
         s.update_shared_pidns(&ctr)?;
         s.add_container(ctr);
         info!(sl!(), "created container!");
@@ -253,14 +283,13 @@ impl AgentService {
         }
 
         // start oom event loop
-        if let Some(ref ctr) = ctr.cgroup_manager {
-            let cg_path = ctr.get_cg_path("memory");
 
-            if let Some(cg_path) = cg_path {
-                let rx = notifier::notify_oom(cid.as_str(), cg_path.to_string()).await?;
+        let cg_path = ctr.cgroup_manager.as_ref().get_cgroup_path("memory");
 
-                s.run_oom_event_monitor(rx, cid.clone()).await;
-            }
+        if let Ok(cg_path) = cg_path {
+            let rx = notifier::notify_oom(cid.as_str(), cg_path.to_string()).await?;
+
+            s.run_oom_event_monitor(rx, cid.clone()).await;
         }
 
         Ok(())
@@ -272,27 +301,6 @@ impl AgentService {
         req: protocols::agent::RemoveContainerRequest,
     ) -> Result<()> {
         let cid = req.container_id.clone();
-        let mut cmounts: Vec<String> = vec![];
-
-        let mut remove_container_resources = |sandbox: &mut Sandbox| -> Result<()> {
-            // Find the sandbox storage used by this container
-            let mounts = sandbox.container_mounts.get(&cid);
-            if let Some(mounts) = mounts {
-                for m in mounts.iter() {
-                    if sandbox.storages.get(m).is_some() {
-                        cmounts.push(m.to_string());
-                    }
-                }
-            }
-
-            for m in cmounts.iter() {
-                sandbox.unset_and_remove_sandbox_storage(m)?;
-            }
-
-            sandbox.container_mounts.remove(cid.as_str());
-            sandbox.containers.remove(cid.as_str());
-            Ok(())
-        };
 
         if req.timeout == 0 {
             let s = Arc::clone(&self.sandbox);
@@ -306,7 +314,7 @@ impl AgentService {
                 .destroy()
                 .await?;
 
-            remove_container_resources(&mut sandbox)?;
+            remove_container_resources(&mut sandbox, &cid)?;
 
             return Ok(());
         }
@@ -338,8 +346,7 @@ impl AgentService {
 
         let s = self.sandbox.clone();
         let mut sandbox = s.lock().await;
-
-        remove_container_resources(&mut sandbox)?;
+        remove_container_resources(&mut sandbox, &cid)?;
 
         Ok(())
     }
@@ -357,7 +364,7 @@ impl AgentService {
         let mut process = req
             .process
             .into_option()
-            .ok_or_else(|| anyhow!(nix::Error::EINVAL))?;
+            .ok_or_else(|| anyhow!("Unable to parse process from ExecProcessRequest"))?;
 
         // Apply any necessary corrections for PCI addresses
         update_env_pci(&mut process.Env, &sandbox.pcimap)?;
@@ -386,6 +393,7 @@ impl AgentService {
             "signal process";
             "container-id" => cid.clone(),
             "exec-id" => eid.clone(),
+            "signal" => req.signal,
         );
 
         let mut sig: libc::c_int = req.signal as libc::c_int;
@@ -399,8 +407,22 @@ impl AgentService {
             if p.init && sig == libc::SIGTERM && !is_signal_handled(&proc_status_file, sig as u32) {
                 sig = libc::SIGKILL;
             }
-            p.signal(sig)?;
-        }
+
+            match p.signal(sig) {
+                Err(Errno::ESRCH) => {
+                    info!(
+                        sl!(),
+                        "signal encounter ESRCH, continue";
+                        "container-id" => cid.clone(),
+                        "exec-id" => eid.clone(),
+                        "pid" => p.pid,
+                        "signal" => sig,
+                    );
+                }
+                Err(err) => return Err(anyhow!(err)),
+                Ok(()) => (),
+            }
+        };
 
         if eid.is_empty() {
             // eid is empty, signal all the remaining processes in the container cgroup
@@ -454,11 +476,7 @@ impl AgentService {
         let ctr = sandbox
             .get_container(cid)
             .ok_or_else(|| anyhow!("Invalid container id {}", cid))?;
-        let cm = ctr
-            .cgroup_manager
-            .as_ref()
-            .ok_or_else(|| anyhow!("cgroup manager not exist"))?;
-        cm.freeze(state)?;
+        ctr.cgroup_manager.as_ref().freeze(state)?;
         Ok(())
     }
 
@@ -468,11 +486,7 @@ impl AgentService {
         let ctr = sandbox
             .get_container(cid)
             .ok_or_else(|| anyhow!("Invalid container id {}", cid))?;
-        let cm = ctr
-            .cgroup_manager
-            .as_ref()
-            .ok_or_else(|| anyhow!("cgroup manager not exist"))?;
-        let pids = cm.get_pids()?;
+        let pids = ctr.cgroup_manager.as_ref().get_pids()?;
         Ok(pids)
     }
 
@@ -606,7 +620,7 @@ impl AgentService {
         };
 
         if reader.is_none() {
-            return Err(anyhow!(nix::Error::EINVAL));
+            return Err(anyhow!("Unable to determine stream reader, is None"));
         }
 
         let reader = reader.ok_or_else(|| anyhow!("cannot get stream reader"))?;
@@ -993,8 +1007,18 @@ impl agent_ttrpc::AgentService for AgentService {
 
         info!(sl!(), "get_ip_tables: request received");
 
+        // the binary could exists in either /usr/sbin or /sbin
+        // here check both of the places and return the one exists
+        // if none exists, return the /sbin one, and the rpc will
+        // returns an internal error
         let cmd = if req.is_ipv6 {
-            IP6TABLES_SAVE
+            if Path::new(USR_IP6TABLES_SAVE).exists() {
+                USR_IP6TABLES_SAVE
+            } else {
+                IP6TABLES_SAVE
+            }
+        } else if Path::new(USR_IPTABLES_SAVE).exists() {
+            USR_IPTABLES_SAVE
         } else {
             IPTABLES_SAVE
         }
@@ -1022,8 +1046,18 @@ impl agent_ttrpc::AgentService for AgentService {
 
         info!(sl!(), "set_ip_tables request received");
 
+        // the binary could exists in both /usr/sbin and /sbin
+        // here check both of the places and return the one exists
+        // if none exists, return the /sbin one, and the rpc will
+        // returns an internal error
         let cmd = if req.is_ipv6 {
-            IP6TABLES_RESTORE
+            if Path::new(USR_IP6TABLES_RESTORE).exists() {
+                USR_IP6TABLES_RESTORE
+            } else {
+                IP6TABLES_RESTORE
+            }
+        } else if Path::new(USR_IPTABLES_RESTORE).exists() {
+            USR_IPTABLES_RESTORE
         } else {
             IPTABLES_RESTORE
         }
@@ -1651,9 +1685,11 @@ async fn read_stream(reader: Arc<Mutex<ReadHalf<PipeStream>>>, l: usize) -> Resu
     Ok(content)
 }
 
-pub fn start(s: Arc<Mutex<Sandbox>>, server_address: &str) -> Result<TtrpcServer> {
-    let agent_service =
-        Box::new(AgentService { sandbox: s }) as Box<dyn agent_ttrpc::AgentService + Send + Sync>;
+pub fn start(s: Arc<Mutex<Sandbox>>, server_address: &str, init_mode: bool) -> Result<TtrpcServer> {
+    let agent_service = Box::new(AgentService {
+        sandbox: s,
+        init_mode,
+    }) as Box<dyn agent_ttrpc::AgentService + Send + Sync>;
 
     let agent_worker = Arc::new(agent_service);
 
@@ -1728,6 +1764,35 @@ fn update_container_namespaces(
     Ok(())
 }
 
+fn remove_container_resources(sandbox: &mut Sandbox, cid: &str) -> Result<()> {
+    let mut cmounts: Vec<String> = vec![];
+
+    // Find the sandbox storage used by this container
+    let mounts = sandbox.container_mounts.get(cid);
+    if let Some(mounts) = mounts {
+        for m in mounts.iter() {
+            if sandbox.storages.get(m).is_some() {
+                cmounts.push(m.to_string());
+            }
+        }
+    }
+
+    for m in cmounts.iter() {
+        if let Err(err) = sandbox.unset_and_remove_sandbox_storage(m) {
+            error!(
+                sl!(),
+                "failed to unset_and_remove_sandbox_storage for container {}, error: {:?}",
+                cid,
+                err
+            );
+        }
+    }
+
+    sandbox.container_mounts.remove(cid);
+    sandbox.containers.remove(cid);
+    Ok(())
+}
+
 fn append_guest_hooks(s: &Sandbox, oci: &mut Spec) -> Result<()> {
     if let Some(ref guest_hooks) = s.hooks {
         let mut hooks = oci.hooks.take().unwrap_or_default();
@@ -1819,7 +1884,11 @@ fn do_copy_file(req: &CopyFileRequest) -> Result<()> {
     let path = PathBuf::from(req.path.as_str());
 
     if !path.starts_with(CONTAINER_BASE) {
-        return Err(anyhow!(nix::Error::EINVAL));
+        return Err(anyhow!(
+            "Path {:?} does not start with {}",
+            path,
+            CONTAINER_BASE
+        ));
     }
 
     let parent = path.parent();
@@ -1987,15 +2056,18 @@ fn load_kernel_module(module: &protocols::agent::KernelModule) -> Result<()> {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::{
-        assert_result, namespace::Namespace, protocols::agent_ttrpc_async::AgentService as _,
-        skip_if_not_root,
-    };
+    use crate::{namespace::Namespace, protocols::agent_ttrpc_async::AgentService as _};
     use nix::mount;
     use nix::sched::{unshare, CloneFlags};
     use oci::{Hook, Hooks, Linux, LinuxNamespace};
     use tempfile::{tempdir, TempDir};
+    use test_utils::{assert_result, skip_if_not_root};
     use ttrpc::{r#async::TtrpcContext, MessageHeader};
+    use which::which;
+
+    fn check_command(cmd: &str) -> bool {
+        which(cmd).is_ok()
+    }
 
     fn mk_ttrpc_context() -> TtrpcContext {
         TtrpcContext {
@@ -2060,6 +2132,7 @@ mod tests {
         let result = load_kernel_module(&m);
         assert!(result.is_err(), "load module should failed");
 
+        skip_if_not_root!();
         // case 3: normal module.
         // normally this module should eixsts...
         m.name = "bridge".to_string();
@@ -2092,6 +2165,7 @@ mod tests {
 
         let agent_service = Box::new(AgentService {
             sandbox: Arc::new(Mutex::new(sandbox)),
+            init_mode: true,
         });
 
         let req = protocols::agent::UpdateInterfaceRequest::default();
@@ -2109,6 +2183,7 @@ mod tests {
 
         let agent_service = Box::new(AgentService {
             sandbox: Arc::new(Mutex::new(sandbox)),
+            init_mode: true,
         });
 
         let req = protocols::agent::UpdateRoutesRequest::default();
@@ -2126,6 +2201,7 @@ mod tests {
 
         let agent_service = Box::new(AgentService {
             sandbox: Arc::new(Mutex::new(sandbox)),
+            init_mode: true,
         });
 
         let req = protocols::agent::AddARPNeighborsRequest::default();
@@ -2259,6 +2335,7 @@ mod tests {
 
             let agent_service = Box::new(AgentService {
                 sandbox: Arc::new(Mutex::new(sandbox)),
+                init_mode: true,
             });
 
             let result = agent_service
@@ -2714,10 +2791,32 @@ OtherField:other
     async fn test_ip_tables() {
         skip_if_not_root!();
 
+        let iptables_cmd_list = [
+            USR_IPTABLES_SAVE,
+            USR_IP6TABLES_SAVE,
+            USR_IPTABLES_RESTORE,
+            USR_IP6TABLES_RESTORE,
+            IPTABLES_SAVE,
+            IP6TABLES_SAVE,
+            IPTABLES_RESTORE,
+            IP6TABLES_RESTORE,
+        ];
+
+        for cmd in iptables_cmd_list {
+            if !check_command(cmd) {
+                warn!(
+                    sl!(),
+                    "one or more commands for ip tables test are missing, skip it"
+                );
+                return;
+            }
+        }
+
         let logger = slog::Logger::root(slog::Discard, o!());
         let sandbox = Sandbox::new(&logger).unwrap();
         let agent_service = Box::new(AgentService {
             sandbox: Arc::new(Mutex::new(sandbox)),
+            init_mode: true,
         });
 
         let ctx = mk_ttrpc_context();
@@ -2823,7 +2922,7 @@ COMMIT
             .unwrap();
         assert!(!result.data.is_empty(), "we should have non-zero output:");
         assert!(
-            std::str::from_utf8(&*result.data).unwrap().contains(
+            std::str::from_utf8(&result.data).unwrap().contains(
                 "PREROUTING -d 192.168.103.153/32 -j DNAT --to-destination 192.168.188.153"
             ),
             "We should see the resulting rule"
@@ -2861,7 +2960,7 @@ COMMIT
             .unwrap();
         assert!(!result.data.is_empty(), "we should have non-zero output:");
         assert!(
-            std::str::from_utf8(&*result.data)
+            std::str::from_utf8(&result.data)
                 .unwrap()
                 .contains("INPUT -s 2001:db8:100::1/128 -i sit+ -p tcp -m tcp --sport 512:65535"),
             "We should see the resulting rule"

src/agent/src/sandbox.rs

@@ -296,7 +296,6 @@ impl Sandbox {
             info!(self.logger, "updating {}", ctr.id.as_str());
             ctr.cgroup_manager
                 .as_ref()
-                .unwrap()
                 .update_cpuset_path(guest_cpuset.as_str(), container_cpust)?;
         }
 
@@ -327,7 +326,7 @@ impl Sandbox {
             // Reject non-file, symlinks and non-executable files
             if !entry.file_type()?.is_file()
                 || entry.file_type()?.is_symlink()
-                || entry.metadata()?.permissions().mode() & 0o777 & 0o111 == 0
+                || entry.metadata()?.permissions().mode() & 0o111 == 0
             {
                 continue;
             }
@@ -471,7 +470,7 @@ fn online_memory(logger: &Logger) -> Result<()> {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::{mount::baremount, skip_if_not_root};
+    use crate::mount::baremount;
     use anyhow::{anyhow, Error};
     use nix::mount::MsFlags;
     use oci::{Linux, Root, Spec};
@@ -484,6 +483,7 @@ mod tests {
     use std::os::unix::fs::PermissionsExt;
     use std::path::Path;
     use tempfile::{tempdir, Builder, TempDir};
+    use test_utils::skip_if_not_root;
 
     fn bind_mount(src: &str, dst: &str, logger: &Logger) -> Result<(), Error> {
         let src_path = Path::new(src);
@@ -1072,7 +1072,7 @@ mod tests {
                 fs::create_dir(&subdir_path).unwrap();
                 for file in j.files {
                     let subfile_path = format!("{}/{}", subdir_path, file.name);
-                    let mut subfile = File::create(&subfile_path).unwrap();
+                    let mut subfile = File::create(subfile_path).unwrap();
                     subfile.write_all(file.content.as_bytes()).unwrap();
                 }
             }

src/agent/src/test_utils.rs

@@ -1,99 +0,0 @@
-// Copyright (c) 2019 Intel Corporation
-//
-// SPDX-License-Identifier: Apache-2.0
-//
-#![allow(clippy::module_inception)]
-
-#[cfg(test)]
-pub mod test_utils {
-    #[derive(Debug, PartialEq)]
-    pub enum TestUserType {
-        RootOnly,
-        NonRootOnly,
-        Any,
-    }
-
-    #[macro_export]
-    macro_rules! skip_if_root {
-        () => {
-            if nix::unistd::Uid::effective().is_root() {
-                println!("INFO: skipping {} which needs non-root", module_path!());
-                return;
-            }
-        };
-    }
-
-    #[macro_export]
-    macro_rules! skip_if_not_root {
-        () => {
-            if !nix::unistd::Uid::effective().is_root() {
-                println!("INFO: skipping {} which needs root", module_path!());
-                return;
-            }
-        };
-    }
-
-    #[macro_export]
-    macro_rules! skip_loop_if_root {
-        ($msg:expr) => {
-            if nix::unistd::Uid::effective().is_root() {
-                println!(
-                    "INFO: skipping loop {} in {} which needs non-root",
-                    $msg,
-                    module_path!()
-                );
-                continue;
-            }
-        };
-    }
-
-    #[macro_export]
-    macro_rules! skip_loop_if_not_root {
-        ($msg:expr) => {
-            if !nix::unistd::Uid::effective().is_root() {
-                println!(
-                    "INFO: skipping loop {} in {} which needs root",
-                    $msg,
-                    module_path!()
-                );
-                continue;
-            }
-        };
-    }
-
-    // Parameters:
-    //
-    // 1: expected Result
-    // 2: actual Result
-    // 3: string used to identify the test on error
-    #[macro_export]
-    macro_rules! assert_result {
-        ($expected_result:expr, $actual_result:expr, $msg:expr) => {
-            if $expected_result.is_ok() {
-                let expected_value = $expected_result.as_ref().unwrap();
-                let actual_value = $actual_result.unwrap();
-                assert!(*expected_value == actual_value, "{}", $msg);
-            } else {
-                assert!($actual_result.is_err(), "{}", $msg);
-
-                let expected_error = $expected_result.as_ref().unwrap_err();
-                let expected_error_msg = format!("{:?}", expected_error);
-
-                let actual_error_msg = format!("{:?}", $actual_result.unwrap_err());
-
-                assert!(expected_error_msg == actual_error_msg, "{}", $msg);
-            }
-        };
-    }
-
-    #[macro_export]
-    macro_rules! skip_loop_by_user {
-        ($msg:expr, $user:expr) => {
-            if $user == TestUserType::RootOnly {
-                skip_loop_if_not_root!($msg);
-            } else if $user == TestUserType::NonRootOnly {
-                skip_loop_if_root!($msg);
-            }
-        };
-    }
-}

src/agent/src/watcher.rs

@@ -11,7 +11,7 @@ use std::path::{Path, PathBuf};
 use std::sync::Arc;
 use std::time::SystemTime;
 
-use anyhow::{ensure, Context, Result};
+use anyhow::{anyhow, ensure, Context, Result};
 use async_recursion::async_recursion;
 use nix::mount::{umount, MsFlags};
 use nix::unistd::{Gid, Uid};
@@ -34,9 +34,13 @@ const MAX_SIZE_PER_WATCHABLE_MOUNT: u64 = 1024 * 1024;
 /// How often to check for modified files.
 const WATCH_INTERVAL_SECS: u64 = 2;
 
-/// Destination path for tmpfs
+/// Destination path for tmpfs, which used by the golang runtime
 const WATCH_MOUNT_POINT_PATH: &str = "/run/kata-containers/shared/containers/watchable/";
 
+/// Destination path for tmpfs for runtime-rs passthrough file sharing
+const WATCH_MOUNT_POINT_PATH_PASSTHROUGH: &str =
+    "/run/kata-containers/shared/containers/passthrough/watchable/";
+
 /// Represents a single watched storage entry which may have multiple files to watch.
 #[derive(Default, Debug, Clone)]
 struct Storage {
@@ -120,7 +124,7 @@ impl Storage {
 
         // if we are creating a directory: just create it, nothing more to do
         if metadata.file_type().is_dir() {
-            let dest_file_path = self.make_target_path(&source_file_path)?;
+            let dest_file_path = self.make_target_path(source_file_path)?;
 
             fs::create_dir_all(&dest_file_path)
                 .await
@@ -148,7 +152,7 @@ impl Storage {
             // Assume target mount is a file path
             self.target_mount_point.clone()
         } else {
-            let dest_file_path = self.make_target_path(&source_file_path)?;
+            let dest_file_path = self.make_target_path(source_file_path)?;
 
             if let Some(path) = dest_file_path.parent() {
                 debug!(logger, "Creating destination directory: {}", path.display());
@@ -451,7 +455,7 @@ impl BindWatcher {
     ) -> Result<()> {
         if self.watch_thread.is_none() {
             // Virtio-fs shared path is RO by default, so we back the target-mounts by tmpfs.
-            self.mount(logger).await?;
+            self.mount(logger).await.context("mount watch directory")?;
 
             // Spawn background thread to monitor changes
             self.watch_thread = Some(Self::spawn_watcher(
@@ -500,16 +504,28 @@ impl BindWatcher {
     }
 
     async fn mount(&self, logger: &Logger) -> Result<()> {
-        fs::create_dir_all(WATCH_MOUNT_POINT_PATH).await?;
+        // the watchable directory is created on the host side.
+        // here we can only check if it exist.
+        // first we will check the default WATCH_MOUNT_POINT_PATH,
+        // and then check WATCH_MOUNT_POINT_PATH_PASSTHROUGH
+        // in turn which are introduced by runtime-rs file sharing.
+        let watchable_dir = if Path::new(WATCH_MOUNT_POINT_PATH).is_dir() {
+            WATCH_MOUNT_POINT_PATH
+        } else if Path::new(WATCH_MOUNT_POINT_PATH_PASSTHROUGH).is_dir() {
+            WATCH_MOUNT_POINT_PATH_PASSTHROUGH
+        } else {
+            return Err(anyhow!("watchable mount source not found"));
+        };
 
         baremount(
             Path::new("tmpfs"),
-            Path::new(WATCH_MOUNT_POINT_PATH),
+            Path::new(watchable_dir),
             "tmpfs",
             MsFlags::empty(),
             "",
             logger,
-        )?;
+        )
+        .context("baremount watchable mount path")?;
 
         Ok(())
     }
@@ -520,7 +536,12 @@ impl BindWatcher {
             handle.abort();
         }
 
-        let _ = umount(WATCH_MOUNT_POINT_PATH);
+        // try umount watchable mount path in turn
+        if Path::new(WATCH_MOUNT_POINT_PATH).is_dir() {
+            let _ = umount(WATCH_MOUNT_POINT_PATH);
+        } else if Path::new(WATCH_MOUNT_POINT_PATH_PASSTHROUGH).is_dir() {
+            let _ = umount(WATCH_MOUNT_POINT_PATH_PASSTHROUGH);
+        }
     }
 }
 
@@ -528,10 +549,11 @@ impl BindWatcher {
 mod tests {
     use super::*;
     use crate::mount::is_mounted;
-    use crate::skip_if_not_root;
     use nix::unistd::{Gid, Uid};
+    use scopeguard::defer;
     use std::fs;
     use std::thread;
+    use test_utils::skip_if_not_root;
 
     async fn create_test_storage(dir: &Path, id: &str) -> Result<(protos::Storage, PathBuf)> {
         let src_path = dir.join(format!("src{}", id));
@@ -756,7 +778,7 @@ mod tests {
             22
         );
         assert_eq!(
-            fs::read_to_string(&entries.0[0].target_mount_point.as_path().join("1.txt")).unwrap(),
+            fs::read_to_string(entries.0[0].target_mount_point.as_path().join("1.txt")).unwrap(),
             "updated"
         );
 
@@ -801,7 +823,7 @@ mod tests {
             2
         );
         assert_eq!(
-            fs::read_to_string(&entries.0[1].target_mount_point.as_path().join("foo.txt")).unwrap(),
+            fs::read_to_string(entries.0[1].target_mount_point.as_path().join("foo.txt")).unwrap(),
             "updated"
         );
 
@@ -978,7 +1000,7 @@ mod tests {
 
         // create a path we'll remove later
         fs::create_dir_all(source_dir.path().join("tmp")).unwrap();
-        fs::write(&source_dir.path().join("tmp/test-file"), "foo").unwrap();
+        fs::write(source_dir.path().join("tmp/test-file"), "foo").unwrap();
         assert_eq!(entry.scan(&logger).await.unwrap(), 3); // root, ./tmp, test-file
 
         // Verify expected directory, file:
@@ -1269,19 +1291,26 @@ mod tests {
 
     #[tokio::test]
     #[serial]
+    #[cfg(not(target_arch = "aarch64"))]
     async fn create_tmpfs() {
         skip_if_not_root!();
 
         let logger = slog::Logger::root(slog::Discard, o!());
         let mut watcher = BindWatcher::default();
 
-        watcher.mount(&logger).await.unwrap();
-        assert!(is_mounted(WATCH_MOUNT_POINT_PATH).unwrap());
+        for mount_point in [WATCH_MOUNT_POINT_PATH, WATCH_MOUNT_POINT_PATH_PASSTHROUGH] {
+            fs::create_dir_all(mount_point).unwrap();
+            // ensure the watchable directory is deleted.
+            defer!(fs::remove_dir_all(mount_point).unwrap());
 
-        thread::sleep(Duration::from_millis(20));
+            watcher.mount(&logger).await.unwrap();
+            assert!(is_mounted(mount_point).unwrap());
 
-        watcher.cleanup();
-        assert!(!is_mounted(WATCH_MOUNT_POINT_PATH).unwrap());
+            thread::sleep(Duration::from_millis(20));
+
+            watcher.cleanup();
+            assert!(!is_mounted(mount_point).unwrap());
+        }
     }
 
     #[tokio::test]
@@ -1289,6 +1318,10 @@ mod tests {
     async fn spawn_thread() {
         skip_if_not_root!();
 
+        fs::create_dir_all(WATCH_MOUNT_POINT_PATH).unwrap();
+        // ensure the watchable directory is deleted.
+        defer!(fs::remove_dir_all(WATCH_MOUNT_POINT_PATH).unwrap());
+
         let source_dir = tempfile::tempdir().unwrap();
         fs::write(source_dir.path().join("1.txt"), "one").unwrap();
 
@@ -1319,6 +1352,10 @@ mod tests {
     async fn verify_container_cleanup_watching() {
         skip_if_not_root!();
 
+        fs::create_dir_all(WATCH_MOUNT_POINT_PATH).unwrap();
+        // ensure the watchable directory is deleted.
+        defer!(fs::remove_dir_all(WATCH_MOUNT_POINT_PATH).unwrap());
+
         let source_dir = tempfile::tempdir().unwrap();
         fs::write(source_dir.path().join("1.txt"), "one").unwrap();
 

src/agent/vsock-exporter/Cargo.toml

@@ -3,11 +3,12 @@ name = "vsock-exporter"
 version = "0.1.0"
 authors = ["James O. D. Hunt <james.o.hunt@intel.com>"]
 edition = "2018"
+license = "Apache-2.0"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-nix = "0.23.0"
+nix = "0.24.2"
 libc = "0.2.94"
 thiserror = "1.0.26"
 opentelemetry = { version = "0.14.0", features=["serialize"] }

src/dragonball/Cargo.toml

@@ -12,23 +12,23 @@ edition = "2018"
 [dependencies]
 arc-swap = "1.5.0"
 bytes = "1.1.0"
-dbs-address-space = "0.1.0"
+dbs-address-space = "0.2.0"
 dbs-allocator = "0.1.0"
-dbs-arch = "0.1.0"
-dbs-boot = "0.2.0"
-dbs-device = "0.1.0"
-dbs-interrupt = { version = "0.1.0", features = ["kvm-irq"] }
+dbs-arch = "0.2.0"
+dbs-boot = "0.3.0"
+dbs-device = "0.2.0"
+dbs-interrupt = { version = "0.2.0", features = ["kvm-irq"] }
 dbs-legacy-devices = "0.1.0"
 dbs-upcall = { version = "0.1.0", optional = true }
-dbs-utils = "0.1.0"
+dbs-utils = "0.2.0"
 dbs-virtio-devices = { version = "0.1.0", optional = true, features = ["virtio-mmio"] }
 kvm-bindings = "0.5.0"
 kvm-ioctls = "0.11.0"
 lazy_static = "1.2"
 libc = "0.2.39"
-linux-loader = "0.4.0"
+linux-loader = "0.6.0"
 log = "0.4.14"
-nix = "0.23.1"
+nix = "0.24.2"
 seccompiler = "0.2.0"
 serde = "1.0.27"
 serde_derive = "1.0.27"
@@ -36,30 +36,21 @@ serde_json = "1.0.9"
 slog = "2.5.2"
 slog-scope = "4.4.0"
 thiserror = "1"
-vmm-sys-util = "0.9.0"
-virtio-queue = { version = "0.1.0", optional = true }
-vm-memory = { version = "0.7.0", features = ["backend-mmap"] }
+vmm-sys-util = "0.11.0"
+virtio-queue = { version = "0.4.0", optional = true }
+vm-memory = { version = "0.9.0", features = ["backend-mmap"] }
 
 [dev-dependencies]
 slog-term = "2.9.0"
 slog-async = "2.7.0"
+test-utils = { path = "../libs/test-utils" }
 
 [features]
 acpi = []
-atomic-guest-memory = []
+atomic-guest-memory = [ "vm-memory/backend-atomic" ]
 hotplug = ["virtio-vsock"]
 virtio-vsock = ["dbs-virtio-devices/virtio-vsock", "virtio-queue"]
 virtio-blk = ["dbs-virtio-devices/virtio-blk", "virtio-queue"]
 virtio-net = ["dbs-virtio-devices/virtio-net", "virtio-queue"]
 # virtio-fs only work on atomic-guest-memory
 virtio-fs = ["dbs-virtio-devices/virtio-fs", "virtio-queue", "atomic-guest-memory"]
-
-[patch.'crates-io']
-dbs-device = { git = "https://github.com/openanolis/dragonball-sandbox.git", rev = "7a8e832b53d66994d6a16f0513d69f540583dcd0" }
-dbs-interrupt = { git = "https://github.com/openanolis/dragonball-sandbox.git", rev = "7a8e832b53d66994d6a16f0513d69f540583dcd0" }
-dbs-legacy-devices = { git = "https://github.com/openanolis/dragonball-sandbox.git", rev = "7a8e832b53d66994d6a16f0513d69f540583dcd0" }
-dbs-upcall = { git = "https://github.com/openanolis/dragonball-sandbox.git", rev = "7a8e832b53d66994d6a16f0513d69f540583dcd0" }
-dbs-utils = { git = "https://github.com/openanolis/dragonball-sandbox.git", rev = "7a8e832b53d66994d6a16f0513d69f540583dcd0" }
-dbs-virtio-devices = { git = "https://github.com/openanolis/dragonball-sandbox.git", rev = "7a8e832b53d66994d6a16f0513d69f540583dcd0" }
-dbs-boot = { git = "https://github.com/openanolis/dragonball-sandbox.git", rev = "7a8e832b53d66994d6a16f0513d69f540583dcd0" }
-dbs-arch = { git = "https://github.com/openanolis/dragonball-sandbox.git", rev = "7a8e832b53d66994d6a16f0513d69f540583dcd0" }

src/dragonball/Makefile

@@ -2,12 +2,22 @@
 # Copyright (c) 2019-2022 Ant Group. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
+include ../../utils.mk
+
+ifeq ($(ARCH), s390x)
+default build check test clippy:
+	@echo "s390x not support currently"
+	exit 0
+else
+
 default: build
 
 build:
-	# FIXME: This line will be removed when we solve the vm-memory dependency problem in Dragonball Sandbox
-	cargo update -p vm-memory:0.8.0 --precise 0.7.0
-	cargo build --all-features
+	@echo "INFO: cargo build..."
+	cargo build --all-features --target $(TRIPLE)
+
+static-checks-build:
+	@echo "INFO: static-checks-build do nothing.."
 
 check: clippy format
 
@@ -17,6 +27,9 @@ clippy:
 		-- \
 		-D warnings
 
+vendor:
+	@echo "INFO: vendor do nothing.."
+
 format:
 	@echo "INFO: cargo fmt..."
 	cargo fmt -- --check
@@ -25,5 +38,13 @@ clean:
 	cargo clean
 
 test:
-	@echo "INFO: testing dragonball for development build"
-	cargo test --all-features -- --nocapture
+ifdef SUPPORT_VIRTUALIZATION
+	cargo test --all-features --target $(TRIPLE) -- --nocapture
+else
+	@echo "INFO: skip testing dragonball, it need virtualization support."
+	exit 0
+endif
+
+endif # ifeq ($(ARCH), s390x)
+
+.DEFAULT_GOAL := default

src/dragonball/README.md

@@ -19,6 +19,7 @@ and configuration process.
 Device: [Device Document](docs/device.md)
 vCPU: [vCPU Document](docs/vcpu.md)
 API: [API Document](docs/api.md)
+`Upcall`: [`Upcall` Document](docs/upcall.md)
 
 Currently, the documents are still actively adding.
 You could see the [official documentation](docs/) page for more details.

src/dragonball/docs/images/upcall-architecture.svg

@@ -0,0 +1,177 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xl="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" version="1.1" viewBox="51 242 818 479" width="818" height="479">
+  <defs>
+    <marker orient="auto" overflow="visible" markerUnits="strokeWidth" id="FilledArrow_Marker" stroke-linejoin="miter" stroke-miterlimit="10" viewBox="-1 -4 10 8" markerWidth="10" markerHeight="8" color="black">
+      <g>
+        <path d="M 8 0 L 0 -3 L 0 3 Z" fill="currentColor" stroke="currentColor" stroke-width="1"/>
+      </g>
+    </marker>
+    <marker orient="auto" overflow="visible" markerUnits="strokeWidth" id="FilledArrow_Marker_2" stroke-linejoin="miter" stroke-miterlimit="10" viewBox="-9 -4 10 8" markerWidth="10" markerHeight="8" color="black">
+      <g>
+        <path d="M -8 0 L 0 3 L 0 -3 Z" fill="currentColor" stroke="currentColor" stroke-width="1"/>
+      </g>
+    </marker>
+  </defs>
+  <g id="Canvas_1" fill="none" fill-opacity="1" stroke="none" stroke-opacity="1" stroke-dasharray="none">
+    <title>Canvas 1</title>
+    <rect fill="white" x="51" y="242" width="818" height="479"/>
+    <g id="Canvas_1_Layer_1">
+      <title>Layer 1</title>
+      <g id="Line_4">
+        <line x1="153" y1="279.5" x2="856.1097" y2="279.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4.0,4.0" stroke-width="1"/>
+      </g>
+      <g id="Graphic_5">
+        <text transform="translate(56 247.5)" fill="black">
+          <tspan font-family="Alibaba PuHuiTi" font-size="16" fill="black" x="0" y="17">Guest User</tspan>
+        </text>
+      </g>
+      <g id="Graphic_6">
+        <text transform="translate(56 286)" fill="black">
+          <tspan font-family="Alibaba PuHuiTi" font-size="16" fill="black" x="0" y="17">Guest Kernel</tspan>
+        </text>
+      </g>
+      <g id="Line_7">
+        <line x1="153" y1="592" x2="856.1097" y2="592" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4.0,4.0" stroke-width="1"/>
+      </g>
+      <g id="Graphic_8">
+        <text transform="translate(62.76 597.5)" fill="black">
+          <tspan font-family="Alibaba PuHuiTi" font-size="16" fill="black" x="7531753e-19" y="17">Hypervisor</tspan>
+        </text>
+      </g>
+      <g id="Graphic_10">
+        <path d="M 264 328 L 347.456 328 C 354.0834 328 359.456 333.3726 359.456 340 L 359.456 524.5 C 359.456 531.1274 354.0834 536.5 347.456 536.5 L 264 536.5 C 257.37258 536.5 252 531.1274 252 524.5 L 252 340 C 252 333.3726 257.37258 328 264 328 Z" stroke="gray" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+      </g>
+      <g id="Graphic_11">
+        <text transform="translate(276.776 333)" fill="black">
+          <tspan font-family="Alibaba PuHuiTi" font-size="16" fill="black" x="0" y="17">socket</tspan>
+        </text>
+      </g>
+      <g id="Graphic_12">
+        <path d="M 582 294.5 L 672 294.5 C 678.6274 294.5 684 299.8726 684 306.5 L 684 354 C 684 360.6274 678.6274 366 672 366 L 582 366 C 575.3726 366 570 360.6274 570 354 L 570 306.5 C 570 299.8726 575.3726 294.5 582 294.5 Z" stroke="gray" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+        <text transform="translate(575 302.578)" fill="black">
+          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="27.704" y="15">Device </tspan>
+          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="20.44" y="33.448">Manager</tspan>
+          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="25.488" y="51.895996">Service</tspan>
+        </text>
+      </g>
+      <g id="Graphic_13">
+        <text transform="translate(284.824 374)" fill="black">
+          <tspan font-family="Alibaba PuHuiTi" font-size="16" fill="black" x="8135714e-19" y="17">bind</tspan>
+        </text>
+      </g>
+      <g id="Graphic_14">
+        <text transform="translate(280.528 416.25)" fill="black">
+          <tspan font-family="Alibaba PuHuiTi" font-size="16" fill="black" x="0" y="17">listen</tspan>
+        </text>
+      </g>
+      <g id="Graphic_15">
+        <text transform="translate(274.92 459.5)" fill="black">
+          <tspan font-family="Alibaba PuHuiTi" font-size="16" fill="black" x="0" y="17">accept</tspan>
+        </text>
+      </g>
+      <g id="Graphic_16">
+        <text transform="translate(256.372 503.5)" fill="black">
+          <tspan font-family="Alibaba PuHuiTi" font-size="16" fill="black" x="8668621e-19" y="17">new kthread</tspan>
+        </text>
+      </g>
+      <g id="Graphic_17">
+        <path d="M 268 566.5 L 807.5 566.5 C 813.0228 566.5 817.5 570.97715 817.5 576.5 L 817.5 576.5 C 817.5 582.02285 813.0228 586.5 807.5 586.5 L 268 586.5 C 262.47715 586.5 258 582.02285 258 576.5 L 258 576.5 C 258 570.97715 262.47715 566.5 268 566.5 Z" stroke="gray" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+        <text transform="translate(263 567.276)" fill="black">
+          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="226.454" y="15">virtio-vsocket</tspan>
+        </text>
+      </g>
+      <g id="Graphic_18">
+        <path d="M 268 598.5 L 807.5 598.5 C 813.0228 598.5 817.5 602.97715 817.5 608.5 L 817.5 608.5 C 817.5 614.02285 813.0228 618.5 807.5 618.5 L 268 618.5 C 262.47715 618.5 258 614.02285 258 608.5 L 258 608.5 C 258 602.97715 262.47715 598.5 268 598.5 Z" stroke="gray" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+        <text transform="translate(263 599.276)" fill="black">
+          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="193.254" y="15">virtio-vsocket backend</tspan>
+        </text>
+      </g>
+      <g id="Line_20">
+        <line x1="301.9" y1="352" x2="301.9" y2="369.84976" marker-end="url(#FilledArrow_Marker)" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+      </g>
+      <g id="Line_21">
+        <line x1="300.828" y1="394.6251" x2="300.828" y2="412.4749" marker-end="url(#FilledArrow_Marker)" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+      </g>
+      <g id="Line_22">
+        <line x1="300.828" y1="437.56256" x2="300.828" y2="455.4123" marker-end="url(#FilledArrow_Marker)" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+      </g>
+      <g id="Line_23">
+        <line x1="299.9" y1="480.1251" x2="299.9" y2="497.9749" marker-end="url(#FilledArrow_Marker)" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+      </g>
+      <g id="Graphic_24">
+        <rect x="266.5" y="541.5" width="71.188" height="20" stroke="gray" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+        <text transform="translate(271.5 540.5)" fill="black">
+          <tspan font-family="Alibaba PuHuiTi" font-size="16" fill="black" x="13.858" y="17">Port</tspan>
+        </text>
+      </g>
+      <g id="Graphic_27">
+        <path d="M 582 648.5 L 672 648.5 C 678.6274 648.5 684 653.8726 684 660.5 L 684 708 C 684 714.6274 678.6274 720 672 720 L 582 720 C 575.3726 720 570 714.6274 570 708 L 570 660.5 C 570 653.8726 575.3726 648.5 582 648.5 Z" stroke="gray" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+        <text transform="translate(575 656.578)" fill="black">
+          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="27.704" y="15">Device </tspan>
+          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="20.44" y="33.448">Manager</tspan>
+          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="20.288" y="51.895996">Backend</tspan>
+        </text>
+      </g>
+      <g id="Line_28">
+        <line x1="627" y1="375.9" x2="627" y2="638.6" marker-end="url(#FilledArrow_Marker)" marker-start="url(#FilledArrow_Marker_2)" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4.0,4.0" stroke-width="1"/>
+      </g>
+      <g id="Graphic_31">
+        <path d="M 711 294.5 L 801 294.5 C 807.6274 294.5 813 299.8726 813 306.5 L 813 354 C 813 360.6274 807.6274 366 801 366 L 711 366 C 704.3726 366 699 360.6274 699 354 L 699 306.5 C 699 299.8726 704.3726 294.5 711 294.5 Z" stroke="gray" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+        <text transform="translate(704 321.026)" fill="black">
+          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="17.784" y="15">Service B</tspan>
+        </text>
+      </g>
+      <g id="Graphic_30">
+        <path d="M 711 648.5 L 801 648.5 C 807.6274 648.5 813 653.8726 813 660.5 L 813 708 C 813 714.6274 807.6274 720 801 720 L 711 720 C 704.3726 720 699 714.6274 699 708 L 699 660.5 C 699 653.8726 704.3726 648.5 711 648.5 Z" stroke="gray" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+        <text transform="translate(704 675.026)" fill="black">
+          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="12.584" y="15">Backend B</tspan>
+        </text>
+      </g>
+      <g id="Line_29">
+        <line x1="756" y1="375.9" x2="756" y2="638.6" marker-end="url(#FilledArrow_Marker)" marker-start="url(#FilledArrow_Marker_2)" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4.0,4.0" stroke-width="1"/>
+      </g>
+      <g id="Graphic_32">
+        <text transform="translate(833 319.25)" fill="black">
+          <tspan font-family="Alibaba PuHuiTi" font-size="16" fill="black" x="58264504e-20" y="17">……</tspan>
+        </text>
+      </g>
+      <g id="Graphic_33">
+        <text transform="translate(833 673.25)" fill="black">
+          <tspan font-family="Alibaba PuHuiTi" font-size="16" fill="black" x="58264504e-20" y="17">……</tspan>
+        </text>
+      </g>
+      <g id="Graphic_34">
+        <text transform="translate(252.616 296)" fill="black">
+          <tspan font-family="Alibaba PuHuiTi" font-size="16" fill="black" x="0" y="17">Upcall Server</tspan>
+        </text>
+      </g>
+      <g id="Line_39">
+        <path d="M 251.372 514.94444 L 196.16455 515.40173 L 196.2135 443.25 L 290.92825 443.92903" marker-end="url(#FilledArrow_Marker)" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+      </g>
+      <g id="Graphic_41">
+        <text transform="translate(417 503.5)" fill="black">
+          <tspan font-family="Alibaba PuHuiTi" font-size="16" fill="black" x="0" y="17">Service handler</tspan>
+        </text>
+      </g>
+      <g id="Graphic_42">
+        <rect x="591.406" y="540.4723" width="71.188" height="20" stroke="gray" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+        <text transform="translate(596.406 539.4723)" fill="black">
+          <tspan font-family="Alibaba PuHuiTi" font-size="16" fill="black" x="10.386" y="17">Conn</tspan>
+        </text>
+      </g>
+      <g id="Graphic_43">
+        <rect x="720.406" y="541.4723" width="71.188" height="20" stroke="gray" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+        <text transform="translate(725.406 540.4723)" fill="black">
+          <tspan font-family="Alibaba PuHuiTi" font-size="16" fill="black" x="10.386" y="17">Conn</tspan>
+        </text>
+      </g>
+      <g id="Line_44">
+        <line x1="358.684" y1="514.5" x2="402.1" y2="514.5" marker-end="url(#FilledArrow_Marker)" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+      </g>
+      <g id="Line_46">
+        <path d="M 479.2467 498.5 L 480 328 L 560.10116 329.22604" marker-end="url(#FilledArrow_Marker)" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
+      </g>
+    </g>
+  </g>
+</svg>

src/dragonball/docs/upcall.md

@@ -0,0 +1,30 @@
+# `Upcall`
+
+## What is `Upcall`?
+
+`Upcall` is a direct communication tool between VMM and guest developed upon `vsock`. The server side of the `upcall` is a driver in guest kernel (kernel patches are needed for this feature) and it'll start to serve the requests after the kernel starts. And the client side is in Dragonball VMM , it'll be a thread that communicates with `vsock` through `uds`.
+
+We want to keep the lightweight of the VM through the implementation of the `upcall`.
+
+![architecture overview](images/upcall-architecture.svg)
+## What can `upcall` do?
+
+We define specific operations in the device manager service (one of the services in `upcall` we developed) to perform device hotplug / hot-unplug including vCPU hotplug, `virtio-mmio` hotplug, and memory hotplug. We have accomplished device hotplug / hot-unplug directly through `upcall` in order to avoid the virtualization of ACPI to minimize virtual machines overhead. And there could be many other uses if other services are implemented.
+
+## How to enable `upcall`?
+
+`Upcall` needs a server in the guest kernel which will be several kernel patches for the `upcall` server itself and different services registered in the `upcall` server. It's currently tested on upstream Linux kernel 5.10.
+
+To make it easy for users to use, we have open-source the `upcall` guest patches in [Dragonball experimental guest patches](../../../tools/packaging/kernel/patches/5.10.x/dragonball-experimental) and develop `upcall` support in [Kata guest kernel building script](../../../tools/packaging/kernel/build-kernel.sh).
+
+You could use following command to download the upstream kernel (currently Dragonball uses 5.10.25) and put the `upcall` patches and other Kata patches into kernel code.
+
+`sh build-kernel.sh -e -t dragonball -f setup`
+
+`-e` here means experimental, mainly because `upcall` patches are not in upstream Linux kernel.
+`-t dragonball` is for specifying hypervisor type
+`-f` is for generating `.config` file
+
+After this command, the kernel code with `upcall` and related `.config` file are all set up in the directory `kata-linux-dragonball-experimental-5.10.25-[config version]`. You can either manually compile the kernel with `make` command or following [Document for build-kernel.sh](../../../tools/packaging/kernel/README.md) to build and use this guest kernel.
+
+Also, a client-side is also needed in VMM. Dragonball has already open-source the way to implement `upcall` client and Dragonball compiled with `dbs-upcall` feature will enable Dragonball client side.

src/dragonball/src/address_space_manager.rs

@@ -33,10 +33,10 @@ use log::{debug, error, info, warn};
 use nix::sys::mman;
 use nix::unistd::dup;
 #[cfg(feature = "atomic-guest-memory")]
-use vm_memory::atomic::GuestMemoryAtomic;
+use vm_memory::GuestMemoryAtomic;
 use vm_memory::{
-    Address, FileOffset, GuestAddress, GuestAddressSpace, GuestMemoryMmap, GuestMemoryRegion,
-    GuestRegionMmap, GuestUsize, MemoryRegionAddress, MmapRegion,
+    address::Address, FileOffset, GuestAddress, GuestAddressSpace, GuestMemoryMmap,
+    GuestMemoryRegion, GuestRegionMmap, GuestUsize, MemoryRegionAddress, MmapRegion,
 };
 
 use crate::resource_manager::ResourceManager;
@@ -250,6 +250,11 @@ impl AddressSpaceMgr {
         self.address_space.as_ref()
     }
 
+    /// Get the guest memory.
+    pub fn vm_memory(&self) -> Option<<GuestAddressSpaceImpl as GuestAddressSpace>::T> {
+        self.get_vm_as().map(|m| m.memory())
+    }
+
     /// Create the address space for a virtual machine.
     ///
     /// This method is designed to be called when starting up a virtual machine instead of at
@@ -270,7 +275,7 @@ impl AddressSpaceMgr {
             let size = info
                 .size
                 .checked_shl(20)
-                .ok_or_else(|| AddressManagerError::InvalidOperation)?;
+                .ok_or(AddressManagerError::InvalidOperation)?;
 
             // Guest memory does not intersect with the MMIO hole.
             // TODO: make it work for ARM (issue #4307)
@@ -281,13 +286,13 @@ impl AddressSpaceMgr {
                 regions.push(region);
                 start_addr = start_addr
                     .checked_add(size)
-                    .ok_or_else(|| AddressManagerError::InvalidOperation)?;
+                    .ok_or(AddressManagerError::InvalidOperation)?;
             } else {
                 // Add guest memory below the MMIO hole, avoid splitting the memory region
                 // if the available address region is small than MINIMAL_SPLIT_SPACE MiB.
                 let mut below_size = dbs_boot::layout::MMIO_LOW_START
                     .checked_sub(start_addr)
-                    .ok_or_else(|| AddressManagerError::InvalidOperation)?;
+                    .ok_or(AddressManagerError::InvalidOperation)?;
                 if below_size < (MINIMAL_SPLIT_SPACE) {
                     below_size = 0;
                 } else {
@@ -299,12 +304,12 @@ impl AddressSpaceMgr {
                 let above_start = dbs_boot::layout::MMIO_LOW_END + 1;
                 let above_size = size
                     .checked_sub(below_size)
-                    .ok_or_else(|| AddressManagerError::InvalidOperation)?;
+                    .ok_or(AddressManagerError::InvalidOperation)?;
                 let region = self.create_region(above_start, above_size, info, &mut param)?;
                 regions.push(region);
                 start_addr = above_start
                     .checked_add(above_size)
-                    .ok_or_else(|| AddressManagerError::InvalidOperation)?;
+                    .ok_or(AddressManagerError::InvalidOperation)?;
             }
         }
 
@@ -401,9 +406,9 @@ impl AddressSpaceMgr {
             let flags = 0u32;
 
             let mem_region = kvm_userspace_memory_region {
-                slot: slot as u32,
+                slot,
                 guest_phys_addr: reg.start_addr().raw_value(),
-                memory_size: reg.len() as u64,
+                memory_size: reg.len(),
                 userspace_addr: host_addr as u64,
                 flags,
             };
@@ -421,7 +426,7 @@ impl AddressSpaceMgr {
         self.base_to_slot
             .lock()
             .unwrap()
-            .insert(reg.start_addr().raw_value(), slot as u32);
+            .insert(reg.start_addr().raw_value(), slot);
 
         Ok(())
     }
@@ -502,7 +507,7 @@ impl AddressSpaceMgr {
     fn configure_numa(&self, mmap_reg: &MmapRegion, node_id: u32) -> Result<()> {
         let nodemask = 1_u64
             .checked_shl(node_id)
-            .ok_or_else(|| AddressManagerError::InvalidOperation)?;
+            .ok_or(AddressManagerError::InvalidOperation)?;
         let res = unsafe {
             libc::syscall(
                 libc::SYS_mbind,

src/dragonball/src/api/v1/boot_source.rs

@@ -18,7 +18,7 @@ pub const DEFAULT_KERNEL_CMDLINE: &str = "reboot=k panic=1 pci=off nomodules 825
                                           i8042.noaux i8042.nomux i8042.nopnp i8042.dumbkbd";
 
 /// Strongly typed data structure used to configure the boot source of the microvm.
-#[derive(Clone, Debug, Deserialize, PartialEq, Serialize, Default)]
+#[derive(Clone, Debug, Deserialize, PartialEq, Eq, Serialize, Default)]
 #[serde(deny_unknown_fields)]
 pub struct BootSourceConfig {
     /// Path of the kernel image.

src/dragonball/src/api/v1/instance_info.rs

@@ -10,7 +10,7 @@ use serde_derive::{Deserialize, Serialize};
 /// When Dragonball starts, the instance state is Uninitialized. Once start_microvm method is
 /// called, the state goes from Uninitialized to Starting. The state is changed to Running until
 /// the start_microvm method ends. Halting and Halted are currently unsupported.
-#[derive(Copy, Clone, Debug, Deserialize, PartialEq, Serialize)]
+#[derive(Copy, Clone, Debug, Deserialize, PartialEq, Eq, Serialize)]
 pub enum InstanceState {
     /// Microvm is not initialized.
     Uninitialized,
@@ -29,7 +29,7 @@ pub enum InstanceState {
 }
 
 /// The state of async actions
-#[derive(Debug, Deserialize, Serialize, Clone, PartialEq)]
+#[derive(Debug, Deserialize, Serialize, Clone, PartialEq, Eq)]
 pub enum AsyncState {
     /// Uninitialized
     Uninitialized,

src/dragonball/src/api/v1/machine_config.rs

@@ -10,7 +10,7 @@ pub const MAX_SUPPORTED_VCPUS: u8 = 254;
 pub const MEMORY_HOTPLUG_ALIGHMENT: u8 = 64;
 
 /// Errors associated with configuring the microVM.
-#[derive(Debug, PartialEq, thiserror::Error)]
+#[derive(Debug, PartialEq, Eq, thiserror::Error)]
 pub enum VmConfigError {
     /// Cannot update the configuration of the microvm post boot.
     #[error("update operation is not allowed after boot")]