Merge pull request #7523 from fidencio/3.2.0-rc0-branch-bump

# Kata Containers 3.2.0-rc0

.github/workflows/PR-wip-checks.yaml

@@ -9,6 +9,10 @@ on:
       - labeled
       - unlabeled
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
 jobs:
   pr_wip_check:
     runs-on: ubuntu-latest

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

@@ -10,6 +10,10 @@ on:
       - labeled
       - unlabeled
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
 jobs:
   check-issues:
     if: ${{ github.event.label.name != 'auto-backport' }}
@@ -62,15 +66,15 @@ jobs:
           has_backport_needed_label=${{ 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"
+          echo "add_backport_label=false" >> $GITHUB_OUTPUT
           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"
+              echo "add_backport_label=true" >> $GITHUB_OUTPUT
             fi
           fi
 
           # Do not spam comment, only if auto-backport label is going to be newly added.
-          echo "::set-output name=auto_backport_added::$CONTAINS_AUTO_BACKPORT"
+          echo "auto_backport_added=$CONTAINS_AUTO_BACKPORT" >> $GITHUB_OUTPUT
 
       - 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' }}
@@ -97,4 +101,4 @@ jobs:
         uses: andymckay/labeler@e6c4322d0397f3240f0e7e30a33b5c5df2d39e90
         with:
           add-labels: "auto-backport"
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
+          repo-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/add-issues-to-project.yaml

@@ -11,6 +11,10 @@ on:
       - opened
       - reopened
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
 jobs:
   add-new-issues-to-backlog:
     runs-on: ubuntu-latest

.github/workflows/add-pr-sizing-label.yaml

@@ -12,6 +12,10 @@ on:
       - reopened
       - synchronize
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
 jobs:
   add-pr-size-label:
     runs-on: ubuntu-latest

.github/workflows/auto-backport.yaml

@@ -2,6 +2,10 @@ on:
   pull_request_target:
     types: ["labeled", "closed"]
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
 jobs:
   backport:
     name: Backport PR

.github/workflows/build-kata-static-tarball-amd64.yaml

@@ -0,0 +1,109 @@
+name: CI | Build kata-static tarball for amd64
+on:
+  workflow_call:
+    inputs:
+      stage:
+        required: false
+        type: string
+        default: test
+      tarball-suffix:
+        required: false
+        type: string
+      push-to-registry:
+        required: false
+        type: string
+        default: no
+      commit-hash:
+        required: false
+        type: string
+
+jobs:
+  build-asset:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        asset:
+          - cloud-hypervisor
+          - cloud-hypervisor-glibc
+          - firecracker
+          - kernel
+          - kernel-sev
+          - kernel-dragonball-experimental
+          - kernel-tdx-experimental
+          - kernel-nvidia-gpu
+          - kernel-nvidia-gpu-snp
+          - kernel-nvidia-gpu-tdx-experimental
+          - nydus
+          - ovmf
+          - ovmf-sev
+          - qemu
+          - qemu-snp-experimental
+          - qemu-tdx-experimental
+          - rootfs-image
+          - rootfs-image-tdx
+          - rootfs-initrd
+          - rootfs-initrd-mariner
+          - rootfs-initrd-sev
+          - shim-v2
+          - tdvf
+          - virtiofsd
+        stage:
+          - ${{ inputs.stage }}
+        exclude:
+          - asset: cloud-hypervisor-glibc
+            stage: release
+    steps:
+      - name: Login to Kata Containers quay.io
+        if: ${{ inputs.push-to-registry == 'yes' }}
+        uses: docker/login-action@v2
+        with:
+          registry: quay.io
+          username: ${{ secrets.QUAY_DEPLOYER_USERNAME }}
+          password: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
+
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+          fetch-depth: 0 # This is needed in order to keep the commit ids history
+
+      - name: Build ${{ matrix.asset }}
+        run: |
+          make "${KATA_ASSET}-tarball"
+          build_dir=$(readlink -f build)
+          # store-artifact does not work with symlink
+          sudo cp -r "${build_dir}" "kata-build"
+        env:
+          KATA_ASSET: ${{ matrix.asset }}
+          TAR_OUTPUT: ${{ matrix.asset }}.tar.gz
+          PUSH_TO_REGISTRY: ${{ inputs.push-to-registry }}
+
+      - name: store-artifact ${{ matrix.asset }}
+        uses: actions/upload-artifact@v3
+        with:
+          name: kata-artifacts-amd64${{ inputs.tarball-suffix }}
+          path: kata-build/kata-static-${{ matrix.asset }}.tar.xz
+          retention-days: 1
+          if-no-files-found: error
+
+  create-kata-tarball:
+    runs-on: ubuntu-latest
+    needs: build-asset
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+      - name: get-artifacts
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-artifacts-amd64${{ inputs.tarball-suffix }}
+          path: kata-artifacts
+      - name: merge-artifacts
+        run: |
+          ./tools/packaging/kata-deploy/local-build/kata-deploy-merge-builds.sh kata-artifacts versions.yaml
+      - name: store-artifacts
+        uses: actions/upload-artifact@v3
+        with:
+          name: kata-static-tarball-amd64${{ inputs.tarball-suffix }}
+          path: kata-static.tar.xz
+          retention-days: 1
+          if-no-files-found: error

.github/workflows/build-kata-static-tarball-arm64.yaml

@@ -0,0 +1,99 @@
+name: CI | Build kata-static tarball for arm64
+on:
+  workflow_call:
+    inputs:
+      stage:
+        required: false
+        type: string
+        default: test
+      tarball-suffix:
+        required: false
+        type: string
+      push-to-registry:
+        required: false
+        type: string
+        default: no
+      commit-hash:
+        required: false
+        type: string
+
+jobs:
+  build-asset:
+    runs-on: arm64
+    strategy:
+      matrix:
+        asset:
+          - cloud-hypervisor
+          - firecracker
+          - kernel
+          - kernel-dragonball-experimental
+          - nydus
+          - qemu
+          - rootfs-image
+          - rootfs-initrd
+          - shim-v2
+          - virtiofsd
+        stage:
+          - ${{ inputs.stage }}
+    steps:
+      - name: Adjust a permission for repo
+        run: |
+          sudo chown -R $USER:$USER $GITHUB_WORKSPACE
+
+      - name: Login to Kata Containers quay.io
+        if: ${{ inputs.push-to-registry == 'yes' }}
+        uses: docker/login-action@v2
+        with:
+          registry: quay.io
+          username: ${{ secrets.QUAY_DEPLOYER_USERNAME }}
+          password: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
+
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+          fetch-depth: 0 # This is needed in order to keep the commit ids history
+      - name: Build ${{ matrix.asset }}
+        run: |
+          make "${KATA_ASSET}-tarball"
+          build_dir=$(readlink -f build)
+          # store-artifact does not work with symlink
+          sudo cp -r "${build_dir}" "kata-build"
+        env:
+          KATA_ASSET: ${{ matrix.asset }}
+          TAR_OUTPUT: ${{ matrix.asset }}.tar.gz
+          PUSH_TO_REGISTRY: ${{ inputs.push-to-registry }}
+
+      - name: store-artifact ${{ matrix.asset }}
+        uses: actions/upload-artifact@v3
+        with:
+          name: kata-artifacts-arm64${{ inputs.tarball-suffix }}
+          path: kata-build/kata-static-${{ matrix.asset }}.tar.xz
+          retention-days: 1
+          if-no-files-found: error
+
+  create-kata-tarball:
+    runs-on: arm64
+    needs: build-asset
+    steps:
+      - name: Adjust a permission for repo
+        run: |
+          sudo chown -R $USER:$USER $GITHUB_WORKSPACE
+
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+      - name: get-artifacts
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-artifacts-arm64${{ inputs.tarball-suffix }}
+          path: kata-artifacts
+      - name: merge-artifacts
+        run: |
+          ./tools/packaging/kata-deploy/local-build/kata-deploy-merge-builds.sh kata-artifacts versions.yaml
+      - name: store-artifacts
+        uses: actions/upload-artifact@v3
+        with:
+          name: kata-static-tarball-arm64${{ inputs.tarball-suffix }}
+          path: kata-static.tar.xz
+          retention-days: 1
+          if-no-files-found: error

.github/workflows/build-kata-static-tarball-s390x.yaml

@@ -0,0 +1,96 @@
+name: CI | Build kata-static tarball for s390x
+on:
+  workflow_call:
+    inputs:
+      stage:
+        required: false
+        type: string
+        default: test
+      tarball-suffix:
+        required: false
+        type: string
+      push-to-registry:
+        required: false
+        type: string
+        default: no
+      commit-hash:
+        required: false
+        type: string
+
+jobs:
+  build-asset:
+    runs-on: s390x
+    strategy:
+      matrix:
+        asset:
+          - kernel
+          - qemu
+          - rootfs-image
+          - rootfs-initrd
+          - shim-v2
+          - virtiofsd
+        stage:
+          - ${{ inputs.stage }}
+    steps:
+      - name: Adjust a permission for repo
+        run: |
+          sudo chown -R $USER:$USER $GITHUB_WORKSPACE
+
+      - name: Login to Kata Containers quay.io
+        if: ${{ inputs.push-to-registry == 'yes' }}
+        uses: docker/login-action@v2
+        with:
+          registry: quay.io
+          username: ${{ secrets.QUAY_DEPLOYER_USERNAME }}
+          password: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
+
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+          fetch-depth: 0 # This is needed in order to keep the commit ids history
+      - name: Build ${{ matrix.asset }}
+        run: |
+          make "${KATA_ASSET}-tarball"
+          build_dir=$(readlink -f build)
+          # store-artifact does not work with symlink
+          sudo cp -r "${build_dir}" "kata-build"
+          sudo chown -R $(id -u):$(id -g) "kata-build"
+        env:
+          KATA_ASSET: ${{ matrix.asset }}
+          TAR_OUTPUT: ${{ matrix.asset }}.tar.gz
+          PUSH_TO_REGISTRY: ${{ inputs.push-to-registry }}
+
+      - name: store-artifact ${{ matrix.asset }}
+        uses: actions/upload-artifact@v3
+        with:
+          name: kata-artifacts-s390x${{ inputs.tarball-suffix }}
+          path: kata-build/kata-static-${{ matrix.asset }}.tar.xz
+          retention-days: 1
+          if-no-files-found: error
+
+  create-kata-tarball:
+    runs-on: s390x
+    needs: build-asset
+    steps:
+      - name: Adjust a permission for repo
+        run: |
+          sudo chown -R $USER:$USER $GITHUB_WORKSPACE
+
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+      - name: get-artifacts
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-artifacts-s390x${{ inputs.tarball-suffix }}
+          path: kata-artifacts
+      - name: merge-artifacts
+        run: |
+          ./tools/packaging/kata-deploy/local-build/kata-deploy-merge-builds.sh kata-artifacts versions.yaml
+      - name: store-artifacts
+        uses: actions/upload-artifact@v3
+        with:
+          name: kata-static-tarball-s390x${{ inputs.tarball-suffix }}
+          path: kata-static.tar.xz
+          retention-days: 1
+          if-no-files-found: error

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

@@ -7,6 +7,11 @@ on:
       - reopened
       - synchronize
     paths-ignore: [ '**.md', '**.png', '**.jpg', '**.jpeg', '**.svg', '/docs/**' ]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
 jobs:
   cargo-deny-runner:
     runs-on: ubuntu-latest

.github/workflows/ci-nightly.yaml

@@ -0,0 +1,18 @@
+name: Kata Containers Nightly CI
+on:
+  schedule:
+    - cron: '0 0 * * *'
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  kata-containers-ci-on-push:
+    uses: ./.github/workflows/ci.yaml
+    with:
+      commit-hash: ${{ github.sha }}
+      pr-number: "nightly"
+      tag: ${{ github.sha }}-nightly
+    secrets: inherit

.github/workflows/ci-on-push.yaml

@@ -0,0 +1,31 @@
+name: Kata Containers CI
+on:
+  pull_request_target:
+    branches:
+      - 'main'
+      - 'stable-*'
+    types:
+      # Adding 'labeled' to the list of activity types that trigger this event
+      # (default: opened, synchronize, reopened) so that we can run this
+      # workflow when the 'ok-to-test' label is added.
+      # Reference: https://docs.github.com/en/actions/using-workflows/events-that-trigger-workflows#pull_request_target
+      - opened
+      - synchronize
+      - reopened
+      - labeled
+    paths-ignore:
+      - 'docs/**'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  kata-containers-ci-on-push:
+    if: ${{ contains(github.event.pull_request.labels.*.name, 'ok-to-test') }}
+    uses: ./.github/workflows/ci.yaml
+    with:
+      commit-hash: ${{ github.event.pull_request.head.sha }}
+      pr-number: ${{ github.event.pull_request.number }}
+      tag: ${{ github.event.pull_request.number }}-${{ github.event.pull_request.head.sha }}
+    secrets: inherit

.github/workflows/ci.yaml

@@ -0,0 +1,97 @@
+name: Run the Kata Containers CI
+on:
+  workflow_call:
+    inputs:
+      commit-hash:
+        required: true
+        type: string
+      pr-number:
+        required: true
+        type: string
+      tag:
+        required: true
+        type: string
+
+jobs:
+  build-kata-static-tarball-amd64:
+    uses: ./.github/workflows/build-kata-static-tarball-amd64.yaml
+    with:
+      tarball-suffix: -${{ inputs.tag }}
+      commit-hash: ${{ inputs.commit-hash }}
+
+  publish-kata-deploy-payload-amd64:
+    needs: build-kata-static-tarball-amd64
+    uses: ./.github/workflows/publish-kata-deploy-payload-amd64.yaml
+    with:
+      tarball-suffix: -${{ inputs.tag }}
+      registry: ghcr.io
+      repo: ${{ github.repository_owner }}/kata-deploy-ci
+      tag: ${{ inputs.tag }}-amd64
+      commit-hash: ${{ inputs.commit-hash }}
+    secrets: inherit
+
+  run-k8s-tests-on-aks:
+    needs: publish-kata-deploy-payload-amd64
+    uses: ./.github/workflows/run-k8s-tests-on-aks.yaml
+    with:
+      registry: ghcr.io
+      repo: ${{ github.repository_owner }}/kata-deploy-ci
+      tag: ${{ inputs.tag }}-amd64
+      commit-hash: ${{ inputs.commit-hash }}
+      pr-number: ${{ inputs.pr-number }}
+    secrets: inherit
+
+  run-k8s-tests-on-sev:
+    needs: publish-kata-deploy-payload-amd64
+    uses: ./.github/workflows/run-k8s-tests-on-sev.yaml
+    with:
+      registry: ghcr.io
+      repo: ${{ github.repository_owner }}/kata-deploy-ci
+      tag: ${{ inputs.tag }}-amd64
+      commit-hash: ${{ inputs.commit-hash }}
+
+  run-k8s-tests-on-snp:
+    needs: publish-kata-deploy-payload-amd64
+    uses: ./.github/workflows/run-k8s-tests-on-snp.yaml
+    with:
+      registry: ghcr.io
+      repo: ${{ github.repository_owner }}/kata-deploy-ci
+      tag: ${{ inputs.tag }}-amd64
+      commit-hash: ${{ inputs.commit-hash }}
+
+  run-k8s-tests-on-tdx:
+    needs: publish-kata-deploy-payload-amd64
+    uses: ./.github/workflows/run-k8s-tests-on-tdx.yaml
+    with:
+      registry: ghcr.io
+      repo: ${{ github.repository_owner }}/kata-deploy-ci
+      tag: ${{ inputs.tag }}-amd64
+      commit-hash: ${{ inputs.commit-hash }}
+
+  run-metrics-tests:
+    needs: build-kata-static-tarball-amd64
+    uses: ./.github/workflows/run-metrics.yaml
+    with:
+      tarball-suffix: -${{ inputs.tag }}
+      commit-hash: ${{ inputs.commit-hash }}
+
+  run-cri-containerd-tests:
+    needs: build-kata-static-tarball-amd64
+    uses: ./.github/workflows/run-cri-containerd-tests.yaml
+    with:
+      tarball-suffix: -${{ inputs.tag }}
+      commit-hash: ${{ inputs.commit-hash }}
+
+  run-nydus-tests:
+    needs: build-kata-static-tarball-amd64
+    uses: ./.github/workflows/run-nydus-tests.yaml
+    with:
+      tarball-suffix: -${{ inputs.tag }}
+      commit-hash: ${{ inputs.commit-hash }}
+
+  run-vfio-tests:
+    needs: build-kata-static-tarball-amd64
+    uses: ./.github/workflows/run-vfio-tests.yaml
+    with:
+      tarball-suffix: -${{ inputs.tag }}
+      commit-hash: ${{ inputs.commit-hash }}

.github/workflows/commit-message-check.yaml

@@ -6,6 +6,10 @@ on:
       - reopened
       - synchronize
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
 env:
   error_msg: |+
     See the document below for help on formatting commits for the project.
@@ -62,6 +66,9 @@ jobs:
         #   to be specified at the start of the regex as the action is passed
         #   the entire commit message.
         #
+        # - This check will pass if the commit message only contains a subject
+        #   line, as other body message properties are enforced elsewhere.
+        #
         # - Body lines *can* be longer than the maximum if they start
         #   with a non-alphabetic character or if there is no whitespace in
         #   the line.
@@ -75,7 +82,7 @@ jobs:
         #
         # - A SoB comment can be any length (as it is unreasonable to penalise
         #   people with long names/email addresses :)
-        pattern: '^.+(\n([a-zA-Z].{0,150}|[^a-zA-Z\n].*|[^\s\n]*|Signed-off-by:.*|))+$'
+        pattern: '(^[^\n]+$|^.+(\n([a-zA-Z].{0,150}|[^a-zA-Z\n].*|[^\s\n]*|Signed-off-by:.*|))+$)'
         error: 'Body line too long (max 150)'
         post_error: ${{ env.error_msg }}
 

.github/workflows/darwin-tests.yaml

@@ -6,6 +6,11 @@ on:
       - reopened
       - synchronize
     paths-ignore: [ '**.md', '**.png', '**.jpg', '**.jpeg', '**.svg', '/docs/**' ]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
 name: Darwin tests
 jobs:
   test:

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

@@ -1,80 +0,0 @@
-name: kata deploy build
-
-on: 
-  pull_request:
-    types:
-      - opened
-      - edited
-      - reopened
-      - synchronize
-    paths:
-      - tools/**
-      - versions.yaml
-
-jobs:
-  build-asset:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        asset:
-          - kernel
-          - kernel-dragonball-experimental
-          - shim-v2
-          - qemu
-          - cloud-hypervisor
-          - firecracker
-          - rootfs-image
-          - rootfs-initrd
-          - virtiofsd
-          - nydus
-    steps:
-      - uses: actions/checkout@v2
-      - name: Build ${{ matrix.asset }}
-        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-        run: |
-          make "${KATA_ASSET}-tarball"
-          build_dir=$(readlink -f build)
-          # store-artifact does not work with symlink
-          sudo cp -r --preserve=all "${build_dir}" "kata-build"
-        env:
-          KATA_ASSET: ${{ matrix.asset }}
-
-      - name: store-artifact ${{ matrix.asset }}
-        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-        uses: actions/upload-artifact@v2
-        with:
-          name: kata-artifacts
-          path: kata-build/kata-static-${{ matrix.asset }}.tar.xz
-          if-no-files-found: error
-
-  create-kata-tarball:
-    runs-on: ubuntu-latest
-    needs: build-asset
-    steps:
-      - uses: actions/checkout@v2
-      - name: get-artifacts
-        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-        uses: actions/download-artifact@v2
-        with:
-          name: kata-artifacts
-          path: build
-      - name: merge-artifacts
-        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-        run: |
-          make merge-builds
-      - name: store-artifacts
-        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-        uses: actions/upload-artifact@v2
-        with:
-          name: kata-static-tarball
-          path: kata-static.tar.xz
-
-  make-kata-tarball:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v2
-      - name: make kata-tarball
-        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-        run: |
-          make kata-tarball
-          sudo make install-tarball

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

@@ -1,164 +0,0 @@
-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]
-
-name: test-kata-deploy
-
-jobs:
-  check-comment-and-membership:
-    runs-on: ubuntu-latest
-    if: |
-      github.event.issue.pull_request
-      && 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 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 || 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 || 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}
-              echo 
-              echo Ensure you change your Organization Visibility to Public and
-              echo trigger the test again.
-              exit 1
-          fi
-
-  build-asset:
-    runs-on: ubuntu-latest
-    needs: check-comment-and-membership
-    strategy:
-      matrix:
-        asset:
-          - cloud-hypervisor
-          - firecracker
-          - kernel
-          - kernel-dragonball-experimental
-          - nydus
-          - qemu
-          - rootfs-image
-          - rootfs-initrd
-          - shim-v2
-          - virtiofsd
-    steps:
-      - name: get-PR-ref
-        id: get-PR-ref
-        run: |
-            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: Build ${{ matrix.asset }}
-        run: |
-          make "${KATA_ASSET}-tarball"
-          build_dir=$(readlink -f build)
-          # store-artifact does not work with symlink
-          sudo cp -r "${build_dir}" "kata-build"
-        env:
-          KATA_ASSET: ${{ matrix.asset }}
-          TAR_OUTPUT: ${{ matrix.asset }}.tar.gz
-
-      - name: store-artifact ${{ matrix.asset }}
-        uses: actions/upload-artifact@v2
-        with:
-          name: kata-artifacts
-          path: kata-build/kata-static-${{ matrix.asset }}.tar.xz
-          if-no-files-found: error
-
-  create-kata-tarball:
-    runs-on: ubuntu-latest
-    needs: build-asset
-    steps:
-      - name: get-PR-ref
-        id: get-PR-ref
-        run: |
-            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: get-artifacts
-        uses: actions/download-artifact@v2
-        with:
-          name: kata-artifacts
-          path: kata-artifacts
-      - name: merge-artifacts
-        run: |
-          ./tools/packaging/kata-deploy/local-build/kata-deploy-merge-builds.sh kata-artifacts
-      - name: store-artifacts
-        uses: actions/upload-artifact@v2
-        with:
-          name: kata-static-tarball
-          path: kata-static.tar.xz
-
-  kata-deploy:
-    needs: create-kata-tarball
-    runs-on: ubuntu-latest
-    steps:
-      - name: get-PR-ref
-        id: get-PR-ref
-        run: |
-            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: ${{ steps.get-PR-ref.outputs.pr-ref }}
-      - name: get-kata-tarball
-        uses: actions/download-artifact@v2
-        with:
-          name: kata-static-tarball
-      - name: build-and-push-kata-deploy-ci
-        id: build-and-push-kata-deploy-ci
-        run: |
-          PR_SHA=$(git log --format=format:%H -n1)
-          mv kata-static.tar.xz $GITHUB_WORKSPACE/tools/packaging/kata-deploy/kata-static.tar.xz
-          docker build --build-arg KATA_ARTIFACTS=kata-static.tar.xz -t quay.io/kata-containers/kata-deploy-ci:$PR_SHA $GITHUB_WORKSPACE/tools/packaging/kata-deploy
-          docker login -u ${{ secrets.QUAY_DEPLOYER_USERNAME }} -p ${{ secrets.QUAY_DEPLOYER_PASSWORD }} quay.io
-          docker push quay.io/kata-containers/kata-deploy-ci:$PR_SHA
-          mkdir -p packaging/kata-deploy
-          ln -s $GITHUB_WORKSPACE/tools/packaging/kata-deploy/action packaging/kata-deploy/action
-          echo "::set-output name=PKG_SHA::${PR_SHA}"
-      - name: test-kata-deploy-ci-in-aks
-        uses: ./packaging/kata-deploy/action
-        with:
-          packaging-sha: ${{steps.build-and-push-kata-deploy-ci.outputs.PKG_SHA}}
-        env:
-          PKG_SHA: ${{steps.build-and-push-kata-deploy-ci.outputs.PKG_SHA}}
-          AZ_APPID: ${{ secrets.AZ_APPID }}
-          AZ_PASSWORD: ${{ secrets.AZ_PASSWORD }}
-          AZ_SUBSCRIPTION_ID: ${{ secrets.AZ_SUBSCRIPTION_ID }}
-          AZ_TENANT_ID: ${{ secrets.AZ_TENANT_ID }}

.github/workflows/kata-runtime-classes-sync.yaml

@@ -0,0 +1,36 @@
+on:
+  pull_request:
+    types:
+      - opened
+      - edited
+      - reopened
+      - synchronize
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  kata-deploy-runtime-classes-check:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v3
+    - name: Ensure the split out runtime classes match the all-in-one file
+      run: |
+        pushd tools/packaging/kata-deploy/runtimeclasses/
+        echo "::group::Combine runtime classes"
+        for runtimeClass in `find . -type f \( -name "*.yaml" -and -not -name "kata-runtimeClasses.yaml" \) | sort`; do
+            echo "Adding ${runtimeClass} to the resultingRuntimeClasses.yaml"
+            cat ${runtimeClass} >> resultingRuntimeClasses.yaml;
+        done
+        echo "::endgroup::"
+        echo "::group::Displaying the content of resultingRuntimeClasses.yaml"
+        cat resultingRuntimeClasses.yaml
+        echo "::endgroup::"
+        echo ""
+        echo "::group::Displaying the content of kata-runtimeClasses.yaml"
+        cat kata-runtimeClasses.yaml
+        echo "::endgroup::"
+        echo ""
+        diff resultingRuntimeClasses.yaml kata-runtimeClasses.yaml

.github/workflows/payload-after-push.yaml

@@ -0,0 +1,84 @@
+name: CI | Publish Kata Containers payload
+on:
+  push:
+    branches:
+      - main
+      - stable-*
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build-assets-amd64:
+    uses: ./.github/workflows/build-kata-static-tarball-amd64.yaml
+    with:
+      commit-hash: ${{ github.sha }}
+      push-to-registry: yes
+    secrets: inherit
+
+  build-assets-arm64:
+    uses: ./.github/workflows/build-kata-static-tarball-arm64.yaml
+    with:
+      commit-hash: ${{ github.sha }}
+      push-to-registry: yes
+    secrets: inherit
+
+  build-assets-s390x:
+    uses: ./.github/workflows/build-kata-static-tarball-s390x.yaml
+    with:
+      commit-hash: ${{ github.sha }}
+      push-to-registry: yes
+    secrets: inherit
+
+  publish-kata-deploy-payload-amd64:
+    needs: build-assets-amd64
+    uses: ./.github/workflows/publish-kata-deploy-payload-amd64.yaml
+    with:
+      commit-hash: ${{ github.sha }}
+      registry: quay.io
+      repo: kata-containers/kata-deploy-ci
+      tag: kata-containers-amd64
+    secrets: inherit
+
+  publish-kata-deploy-payload-arm64:
+    needs: build-assets-arm64
+    uses: ./.github/workflows/publish-kata-deploy-payload-arm64.yaml
+    with:
+      commit-hash: ${{ github.sha }}
+      registry: quay.io
+      repo: kata-containers/kata-deploy-ci
+      tag: kata-containers-arm64
+    secrets: inherit
+
+  publish-kata-deploy-payload-s390x:
+    needs: build-assets-s390x
+    uses: ./.github/workflows/publish-kata-deploy-payload-s390x.yaml
+    with:
+      commit-hash: ${{ github.sha }}
+      registry: quay.io
+      repo: kata-containers/kata-deploy-ci
+      tag: kata-containers-s390x
+    secrets: inherit
+
+  publish-manifest:
+    runs-on: ubuntu-latest
+    needs: [publish-kata-deploy-payload-amd64, publish-kata-deploy-payload-arm64, publish-kata-deploy-payload-s390x]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Login to Kata Containers quay.io
+        uses: docker/login-action@v2
+        with:
+          registry: quay.io
+          username: ${{ secrets.QUAY_DEPLOYER_USERNAME }}
+          password: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
+
+      - name: Push multi-arch manifest
+        run: |
+          docker manifest create quay.io/kata-containers/kata-deploy-ci:kata-containers-latest \
+          --amend quay.io/kata-containers/kata-deploy-ci:kata-containers-amd64 \
+          --amend quay.io/kata-containers/kata-deploy-ci:kata-containers-arm64 \
+          --amend quay.io/kata-containers/kata-deploy-ci:kata-containers-s390x
+          docker manifest push quay.io/kata-containers/kata-deploy-ci:kata-containers-latest

.github/workflows/publish-kata-deploy-payload-amd64.yaml

@@ -0,0 +1,55 @@
+name: CI | Publish kata-deploy payload for amd64
+on:
+  workflow_call:
+    inputs:
+      tarball-suffix:
+        required: false
+        type: string
+      registry:
+        required: true
+        type: string
+      repo:
+        required: true
+        type: string
+      tag:
+        required: true
+        type: string
+      commit-hash:
+        required: false
+        type: string
+
+jobs:
+  kata-payload:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+
+      - name: get-kata-tarball
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-static-tarball-amd64${{ inputs.tarball-suffix }}
+
+      - name: Login to Kata Containers quay.io
+        if: ${{ inputs.registry == 'quay.io' }}
+        uses: docker/login-action@v2
+        with:
+          registry: quay.io
+          username: ${{ secrets.QUAY_DEPLOYER_USERNAME }}
+          password: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
+
+      - name: Login to Kata Containers ghcr.io
+        if: ${{ inputs.registry == 'ghcr.io' }}
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: build-and-push-kata-payload
+        id: build-and-push-kata-payload
+        run: |
+          ./tools/packaging/kata-deploy/local-build/kata-deploy-build-and-upload-payload.sh \
+          $(pwd)/kata-static.tar.xz \
+          ${{ inputs.registry }}/${{ inputs.repo }} ${{ inputs.tag }}

.github/workflows/publish-kata-deploy-payload-arm64.yaml

@@ -0,0 +1,60 @@
+name: CI | Publish kata-deploy payload for arm64
+on:
+  workflow_call:
+    inputs:
+      tarball-suffix:
+        required: false
+        type: string
+      registry:
+        required: true
+        type: string
+      repo:
+        required: true
+        type: string
+      tag:
+        required: true
+        type: string
+      commit-hash:
+        required: false
+        type: string
+
+jobs:
+  kata-payload:
+    runs-on: arm64
+    steps:
+      - name: Adjust a permission for repo
+        run: |
+          sudo chown -R $USER:$USER $GITHUB_WORKSPACE
+
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+
+      - name: get-kata-tarball
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-static-tarball-arm64${{ inputs.tarball-suffix }}
+
+      - name: Login to Kata Containers quay.io
+        if: ${{ inputs.registry == 'quay.io' }}
+        uses: docker/login-action@v2
+        with:
+          registry: quay.io
+          username: ${{ secrets.QUAY_DEPLOYER_USERNAME }}
+          password: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
+
+      - name: Login to Kata Containers ghcr.io
+        if: ${{ inputs.registry == 'ghcr.io' }}
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: build-and-push-kata-payload
+        id: build-and-push-kata-payload
+        run: |
+          ./tools/packaging/kata-deploy/local-build/kata-deploy-build-and-upload-payload.sh \
+          $(pwd)/kata-static.tar.xz \
+          ${{ inputs.registry }}/${{ inputs.repo }} ${{ inputs.tag }}
+

.github/workflows/publish-kata-deploy-payload-s390x.yaml

@@ -0,0 +1,59 @@
+name: CI | Publish kata-deploy payload for s390x
+on:
+  workflow_call:
+    inputs:
+      tarball-suffix:
+        required: false
+        type: string
+      registry:
+        required: true
+        type: string
+      repo:
+        required: true
+        type: string
+      tag:
+        required: true
+        type: string
+      commit-hash:
+        required: false
+        type: string
+
+jobs:
+  kata-payload:
+    runs-on: s390x
+    steps:
+      - name: Adjust a permission for repo
+        run: |
+          sudo chown -R $USER:$USER $GITHUB_WORKSPACE
+
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+
+      - name: get-kata-tarball
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-static-tarball-s390x${{ inputs.tarball-suffix }}
+
+      - name: Login to Kata Containers quay.io
+        if: ${{ inputs.registry == 'quay.io' }}
+        uses: docker/login-action@v2
+        with:
+          registry: quay.io
+          username: ${{ secrets.QUAY_DEPLOYER_USERNAME }}
+          password: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
+
+      - name: Login to Kata Containers ghcr.io
+        if: ${{ inputs.registry == 'ghcr.io' }}
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: build-and-push-kata-payload
+        id: build-and-push-kata-payload
+        run: |
+          ./tools/packaging/kata-deploy/local-build/kata-deploy-build-and-upload-payload.sh \
+          $(pwd)/kata-static.tar.xz \
+          ${{ inputs.registry }}/${{ inputs.repo }} ${{ inputs.tag }}

.github/workflows/release-amd64.yaml

@@ -0,0 +1,53 @@
+name: Publish Kata release artifacts for amd64
+on:
+  workflow_call:
+    inputs:
+      target-arch:
+        required: true
+        type: string
+
+jobs:
+  build-kata-static-tarball-amd64:
+    uses: ./.github/workflows/build-kata-static-tarball-amd64.yaml
+    with:
+      stage: release
+
+  kata-deploy:
+    needs: build-kata-static-tarball-amd64
+    runs-on: ubuntu-latest
+    steps:
+      - name: Login to Kata Containers docker.io
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Login to Kata Containers quay.io
+        uses: docker/login-action@v2
+        with:
+          registry: quay.io
+          username: ${{ secrets.QUAY_DEPLOYER_USERNAME }}
+          password: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
+
+      - uses: actions/checkout@v3
+      - name: get-kata-tarball
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-static-tarball-amd64
+
+      - name: build-and-push-kata-deploy-ci-amd64
+        id: build-and-push-kata-deploy-ci-amd64
+        run: |
+          # We need to do such trick here as the format of the $GITHUB_REF 
+          # is "refs/tags/<tag>"
+          tag=$(echo $GITHUB_REF | cut -d/ -f3-)
+          tags=($tag)
+          tags+=($([[ "$tag" =~ "alpha"|"rc" ]] && echo "latest" || echo "stable"))
+          for tag in ${tags[@]}; do
+              ./tools/packaging/kata-deploy/local-build/kata-deploy-build-and-upload-payload.sh \
+                  $(pwd)/kata-static.tar.xz "docker.io/katadocker/kata-deploy" \
+                  "${tag}-${{ inputs.target-arch }}"
+              ./tools/packaging/kata-deploy/local-build/kata-deploy-build-and-upload-payload.sh \
+                  $(pwd)/kata-static.tar.xz "quay.io/kata-containers/kata-deploy" \
+                  "${tag}-${{ inputs.target-arch }}"
+          done

.github/workflows/release-arm64.yaml

@@ -0,0 +1,53 @@
+name: Publish Kata release artifacts for arm64
+on:
+  workflow_call:
+    inputs:
+      target-arch:
+        required: true
+        type: string
+
+jobs:
+  build-kata-static-tarball-arm64:
+    uses: ./.github/workflows/build-kata-static-tarball-arm64.yaml
+    with:
+      stage: release
+
+  kata-deploy:
+    needs: build-kata-static-tarball-arm64
+    runs-on: arm64
+    steps:
+      - name: Login to Kata Containers docker.io
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Login to Kata Containers quay.io
+        uses: docker/login-action@v2
+        with:
+          registry: quay.io
+          username: ${{ secrets.QUAY_DEPLOYER_USERNAME }}
+          password: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
+
+      - uses: actions/checkout@v3
+      - name: get-kata-tarball
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-static-tarball-arm64
+
+      - name: build-and-push-kata-deploy-ci-arm64
+        id: build-and-push-kata-deploy-ci-arm64
+        run: |
+          # We need to do such trick here as the format of the $GITHUB_REF 
+          # is "refs/tags/<tag>"
+          tag=$(echo $GITHUB_REF | cut -d/ -f3-)
+          tags=($tag)
+          tags+=($([[ "$tag" =~ "alpha"|"rc" ]] && echo "latest" || echo "stable"))
+          for tag in ${tags[@]}; do
+              ./tools/packaging/kata-deploy/local-build/kata-deploy-build-and-upload-payload.sh \
+                  $(pwd)/kata-static.tar.xz "docker.io/katadocker/kata-deploy" \
+                  "${tag}-${{ inputs.target-arch }}"
+              ./tools/packaging/kata-deploy/local-build/kata-deploy-build-and-upload-payload.sh \
+                  $(pwd)/kata-static.tar.xz "quay.io/kata-containers/kata-deploy" \
+                  "${tag}-${{ inputs.target-arch }}"
+          done

.github/workflows/release-s390x.yaml

@@ -0,0 +1,53 @@
+name: Publish Kata release artifacts for s390x
+on:
+  workflow_call:
+    inputs:
+      target-arch:
+        required: true
+        type: string
+
+jobs:
+  build-kata-static-tarball-s390x:
+    uses: ./.github/workflows/build-kata-static-tarball-s390x.yaml
+    with:
+      stage: release
+
+  kata-deploy:
+    needs: build-kata-static-tarball-s390x
+    runs-on: s390x
+    steps:
+      - name: Login to Kata Containers docker.io
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Login to Kata Containers quay.io
+        uses: docker/login-action@v2
+        with:
+          registry: quay.io
+          username: ${{ secrets.QUAY_DEPLOYER_USERNAME }}
+          password: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
+
+      - uses: actions/checkout@v3
+      - name: get-kata-tarball
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-static-tarball-s390x
+
+      - name: build-and-push-kata-deploy-ci-s390x
+        id: build-and-push-kata-deploy-ci-s390x
+        run: |
+          # We need to do such trick here as the format of the $GITHUB_REF 
+          # is "refs/tags/<tag>"
+          tag=$(echo $GITHUB_REF | cut -d/ -f3-)
+          tags=($tag)
+          tags+=($([[ "$tag" =~ "alpha"|"rc" ]] && echo "latest" || echo "stable"))
+          for tag in ${tags[@]}; do
+              ./tools/packaging/kata-deploy/local-build/kata-deploy-build-and-upload-payload.sh \
+                  $(pwd)/kata-static.tar.xz "docker.io/katadocker/kata-deploy" \
+                  "${tag}-${{ inputs.target-arch }}"
+              ./tools/packaging/kata-deploy/local-build/kata-deploy-build-and-upload-payload.sh \
+                  $(pwd)/kata-static.tar.xz "quay.io/kata-containers/kata-deploy" \
+                  "${tag}-${{ inputs.target-arch }}"
+          done

.github/workflows/release.yaml

@@ -4,138 +4,143 @@ on:
     tags:
       - '[0-9]+.[0-9]+.[0-9]+*'
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
 jobs:
-  build-asset:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        asset:
-          - cloud-hypervisor
-          - firecracker
-          - kernel
-          - kernel-dragonball-experimental
-          - nydus
-          - qemu
-          - rootfs-image
-          - rootfs-initrd
-          - shim-v2
-          - virtiofsd
-    steps:
-      - uses: actions/checkout@v2
-      - name: Build ${{ matrix.asset }}
-        run: |
-          ./tools/packaging/kata-deploy/local-build/kata-deploy-copy-yq-installer.sh
-          ./tools/packaging/kata-deploy/local-build/kata-deploy-binaries-in-docker.sh --build="${KATA_ASSET}"
-          build_dir=$(readlink -f build)
-          # store-artifact does not work with symlink
-          sudo cp -r "${build_dir}" "kata-build"
-        env:
-          KATA_ASSET: ${{ matrix.asset }}
-          TAR_OUTPUT: ${{ matrix.asset }}.tar.gz
+  build-and-push-assets-amd64:
+    uses: ./.github/workflows/release-amd64.yaml
+    with:
+      target-arch: amd64
+    secrets: inherit
 
-      - name: store-artifact ${{ matrix.asset }}
-        uses: actions/upload-artifact@v2
-        with:
-          name: kata-artifacts
-          path: kata-build/kata-static-${{ matrix.asset }}.tar.xz
-          if-no-files-found: error
+  build-and-push-assets-arm64:
+    uses: ./.github/workflows/release-arm64.yaml
+    with:
+      target-arch: arm64
+    secrets: inherit
 
-  create-kata-tarball:
-    runs-on: ubuntu-latest
-    needs: build-asset
-    steps:
-      - uses: actions/checkout@v2
-      - name: get-artifacts
-        uses: actions/download-artifact@v2
-        with:
-          name: kata-artifacts
-          path: kata-artifacts
-      - name: merge-artifacts
-        run: |
-          ./tools/packaging/kata-deploy/local-build/kata-deploy-merge-builds.sh kata-artifacts
-      - name: store-artifacts
-        uses: actions/upload-artifact@v2
-        with:
-          name: kata-static-tarball
-          path: kata-static.tar.xz
+  build-and-push-assets-s390x:
+    uses: ./.github/workflows/release-s390x.yaml
+    with:
+      target-arch: s390x
+    secrets: inherit
 
-  kata-deploy:
-    needs: create-kata-tarball
+  publish-multi-arch-images:
     runs-on: ubuntu-latest
+    needs: [build-and-push-assets-amd64, build-and-push-assets-arm64, build-and-push-assets-s390x]
     steps:
-      - uses: actions/checkout@v2
-      - name: get-kata-tarball
-        uses: actions/download-artifact@v2
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Login to Kata Containers docker.io
+        uses: docker/login-action@v2
         with:
-          name: kata-static-tarball
-      - name: build-and-push-kata-deploy-ci
-        id: build-and-push-kata-deploy-ci
-        run: |
-          tag=$(echo $GITHUB_REF | cut -d/ -f3-)
-          pushd $GITHUB_WORKSPACE
-          git checkout $tag
-          pkg_sha=$(git rev-parse HEAD)
-          popd
-          mv kata-static.tar.xz $GITHUB_WORKSPACE/tools/packaging/kata-deploy/kata-static.tar.xz
-          docker build --build-arg KATA_ARTIFACTS=kata-static.tar.xz -t katadocker/kata-deploy-ci:$pkg_sha -t quay.io/kata-containers/kata-deploy-ci:$pkg_sha $GITHUB_WORKSPACE/tools/packaging/kata-deploy
-          docker login -u ${{ secrets.DOCKER_USERNAME }} -p ${{ secrets.DOCKER_PASSWORD }}
-          docker push katadocker/kata-deploy-ci:$pkg_sha
-          docker login -u ${{ secrets.QUAY_DEPLOYER_USERNAME }} -p ${{ secrets.QUAY_DEPLOYER_PASSWORD }} quay.io
-          docker push quay.io/kata-containers/kata-deploy-ci:$pkg_sha
-          mkdir -p packaging/kata-deploy
-          ln -s $GITHUB_WORKSPACE/tools/packaging/kata-deploy/action packaging/kata-deploy/action
-          echo "::set-output name=PKG_SHA::${pkg_sha}"
-      - name: test-kata-deploy-ci-in-aks
-        uses: ./packaging/kata-deploy/action
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Login to Kata Containers quay.io
+        uses: docker/login-action@v2
         with:
-          packaging-sha: ${{steps.build-and-push-kata-deploy-ci.outputs.PKG_SHA}}
-        env:
-          PKG_SHA: ${{steps.build-and-push-kata-deploy-ci.outputs.PKG_SHA}}
-          AZ_APPID: ${{ secrets.AZ_APPID }}
-          AZ_PASSWORD: ${{ secrets.AZ_PASSWORD }}
-          AZ_SUBSCRIPTION_ID: ${{ secrets.AZ_SUBSCRIPTION_ID }}
-          AZ_TENANT_ID: ${{ secrets.AZ_TENANT_ID }}
-      - name: push-tarball
+          registry: quay.io
+          username: ${{ secrets.QUAY_DEPLOYER_USERNAME }}
+          password: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
+
+      - name: Push multi-arch manifest
         run: |
           # tag the container image we created and push to DockerHub
           tag=$(echo $GITHUB_REF | cut -d/ -f3-)
           tags=($tag)
           tags+=($([[ "$tag" =~ "alpha"|"rc" ]] && echo "latest" || echo "stable"))
-          for tag in ${tags[@]}; do \
-            docker tag katadocker/kata-deploy-ci:${{steps.build-and-push-kata-deploy-ci.outputs.PKG_SHA}} katadocker/kata-deploy:${tag} && \
-            docker tag quay.io/kata-containers/kata-deploy-ci:${{steps.build-and-push-kata-deploy-ci.outputs.PKG_SHA}} quay.io/kata-containers/kata-deploy:${tag} && \
-            docker push katadocker/kata-deploy:${tag} && \
-            docker push quay.io/kata-containers/kata-deploy:${tag}; \
+          # push to quay.io and docker.io
+          for tag in ${tags[@]}; do
+            docker manifest create quay.io/kata-containers/kata-deploy:${tag} \
+              --amend quay.io/kata-containers/kata-deploy:${tag}-amd64 \
+              --amend quay.io/kata-containers/kata-deploy:${tag}-arm64 \
+              --amend quay.io/kata-containers/kata-deploy:${tag}-s390x
+
+            docker manifest create docker.io/katadocker/kata-deploy:${tag} \
+              --amend docker.io/katadocker/kata-deploy:${tag}-amd64 \
+              --amend docker.io/katadocker/kata-deploy:${tag}-arm64 \
+              --amend docker.io/katadocker/kata-deploy:${tag}-s390x
+
+            docker manifest push quay.io/kata-containers/kata-deploy:${tag}
+            docker manifest push docker.io/katadocker/kata-deploy:${tag}
           done
 
-  upload-static-tarball:
-    needs: kata-deploy
+  upload-multi-arch-static-tarball:
+    needs: publish-multi-arch-images
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - name: download-artifacts
-        uses: actions/download-artifact@v2
-        with:
-          name: kata-static-tarball
+      - uses: actions/checkout@v3
       - name: install hub
         run: |
           wget -q -O- https://github.com/mislav/hub/releases/download/v2.14.2/hub-linux-amd64-2.14.2.tgz | \
           tar xz --strip-components=2 --wildcards '*/bin/hub' && sudo mv hub /usr/local/bin/hub
-      - name: push static tarball to github
+
+      - name: download-artifacts-amd64
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-static-tarball-amd64
+      - name: push amd64 static tarball to github
         run: |
           tag=$(echo $GITHUB_REF | cut -d/ -f3-)
-          tarball="kata-static-$tag-x86_64.tar.xz"
+          tarball="kata-static-$tag-amd64.tar.xz"
           mv kata-static.tar.xz "$GITHUB_WORKSPACE/${tarball}"
           pushd $GITHUB_WORKSPACE
           echo "uploading asset '${tarball}' for tag: ${tag}"
           GITHUB_TOKEN=${{ secrets.GIT_UPLOAD_TOKEN }} hub release edit -m "" -a "${tarball}" "${tag}"
           popd
 
-  upload-cargo-vendored-tarball:
-    needs: upload-static-tarball
+      - name: download-artifacts-arm64
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-static-tarball-arm64
+      - name: push arm64 static tarball to github
+        run: |
+          tag=$(echo $GITHUB_REF | cut -d/ -f3-)
+          tarball="kata-static-$tag-arm64.tar.xz"
+          mv kata-static.tar.xz "$GITHUB_WORKSPACE/${tarball}"
+          pushd $GITHUB_WORKSPACE
+          echo "uploading asset '${tarball}' for tag: ${tag}"
+          GITHUB_TOKEN=${{ secrets.GIT_UPLOAD_TOKEN }} hub release edit -m "" -a "${tarball}" "${tag}"
+          popd
+
+      - name: download-artifacts-s390x
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-static-tarball-s390x
+      - name: push s390x static tarball to github
+        run: |
+          tag=$(echo $GITHUB_REF | cut -d/ -f3-)
+          tarball="kata-static-$tag-s390x.tar.xz"
+          mv kata-static.tar.xz "$GITHUB_WORKSPACE/${tarball}"
+          pushd $GITHUB_WORKSPACE
+          echo "uploading asset '${tarball}' for tag: ${tag}"
+          GITHUB_TOKEN=${{ secrets.GIT_UPLOAD_TOKEN }} hub release edit -m "" -a "${tarball}" "${tag}"
+          popd
+
+  upload-versions-yaml:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
+      - name: upload versions.yaml
+        env:
+          GITHUB_TOKEN: ${{ secrets.GIT_UPLOAD_TOKEN }}
+        run: |
+          tag=$(echo $GITHUB_REF | cut -d/ -f3-)
+          pushd $GITHUB_WORKSPACE
+          versions_file="kata-containers-$tag-versions.yaml"
+          cp versions.yaml ${versions_file}
+          hub release edit -m "" -a "${versions_file}" "${tag}"
+          popd
+
+  upload-cargo-vendored-tarball:
+    needs: upload-multi-arch-static-tarball
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
       - name: generate-and-upload-tarball
         run: |
           tag=$(echo $GITHUB_REF | cut -d/ -f3-)
@@ -149,7 +154,7 @@ jobs:
     needs: upload-cargo-vendored-tarball
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - name: download-and-upload-tarball
         env:
           GITHUB_TOKEN: ${{ secrets.GIT_UPLOAD_TOKEN }}

.github/workflows/require-pr-porting-labels.yaml

@@ -15,6 +15,10 @@ on:
     branches:
       - main
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
 jobs:
   check-pr-porting-labels:
     runs-on: ubuntu-latest

.github/workflows/run-cri-containerd-tests.yaml

@@ -0,0 +1,42 @@
+name: CI | Run cri-containerd tests
+on:
+  workflow_call:
+    inputs:
+      tarball-suffix:
+        required: false
+        type: string
+      commit-hash:
+        required: false
+        type: string
+
+jobs:
+  run-cri-containerd:
+    strategy:
+      fail-fast: true
+      matrix:
+        containerd_version: ['lts', 'active']
+        vmm: ['clh', 'qemu']
+    runs-on: garm-ubuntu-2204
+    env:
+      CONTAINERD_VERSION: ${{ matrix.containerd_version }}
+      GOPATH: ${{ github.workspace }}
+      KATA_HYPERVISOR: ${{ matrix.vmm }}
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+
+      - name: Install dependencies
+        run: bash tests/integration/cri-containerd/gha-run.sh install-dependencies
+
+      - name: get-kata-tarball
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-static-tarball-amd64${{ inputs.tarball-suffix }}
+          path: kata-artifacts
+
+      - name: Install kata
+        run: bash tests/integration/cri-containerd/gha-run.sh install-kata kata-artifacts
+
+      - name: Run cri-containerd tests
+        run: bash tests/integration/cri-containerd/gha-run.sh run

.github/workflows/run-k8s-tests-on-aks.yaml

@@ -0,0 +1,82 @@
+name: CI | Run kubernetes tests on AKS
+on:
+  workflow_call:
+    inputs:
+      registry:
+        required: true
+        type: string
+      repo:
+        required: true
+        type: string
+      tag:
+        required: true
+        type: string
+      pr-number:
+        required: true
+        type: string
+      commit-hash:
+        required: false
+        type: string
+
+jobs:
+  run-k8s-tests:
+    strategy:
+      fail-fast: false
+      matrix:
+        host_os:
+          - ubuntu
+        vmm:
+          - clh
+          - dragonball
+          - qemu
+        include:
+          - host_os: cbl-mariner
+            vmm: clh
+    runs-on: ubuntu-latest
+    env:
+      DOCKER_REGISTRY: ${{ inputs.registry }}
+      DOCKER_REPO: ${{ inputs.repo }}
+      DOCKER_TAG: ${{ inputs.tag }}
+      GH_PR_NUMBER: ${{ inputs.pr-number }}
+      KATA_HOST_OS: ${{ matrix.host_os }}
+      KATA_HYPERVISOR: ${{ matrix.vmm }}
+      USING_NFD: "false"
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+
+      - name: Download Azure CLI
+        run: bash tests/integration/kubernetes/gha-run.sh install-azure-cli
+
+      - name: Log into the Azure account
+        run: bash tests/integration/kubernetes/gha-run.sh login-azure
+        env:
+          AZ_APPID: ${{ secrets.AZ_APPID }}
+          AZ_PASSWORD: ${{ secrets.AZ_PASSWORD }}
+          AZ_TENANT_ID: ${{ secrets.AZ_TENANT_ID }}
+
+      - name: Create AKS cluster
+        timeout-minutes: 10
+        run: bash tests/integration/kubernetes/gha-run.sh create-cluster
+
+      - name: Install `bats`
+        run: bash tests/integration/kubernetes/gha-run.sh install-bats
+
+      - name: Install `kubectl`
+        run: bash tests/integration/kubernetes/gha-run.sh install-kubectl
+
+      - name: Download credentials for the Kubernetes CLI to use them
+        run: bash tests/integration/kubernetes/gha-run.sh get-cluster-credentials
+
+      - name: Deploy Kata
+        timeout-minutes: 10
+        run: bash tests/integration/kubernetes/gha-run.sh deploy-kata-aks
+      
+      - name: Run tests
+        timeout-minutes: 60
+        run: bash tests/integration/kubernetes/gha-run.sh run-tests
+
+      - name: Delete AKS cluster
+        if: always()
+        run: bash tests/integration/kubernetes/gha-run.sh delete-cluster

.github/workflows/run-k8s-tests-on-sev.yaml

@@ -0,0 +1,48 @@
+name: CI | Run kubernetes tests on SEV
+on:
+  workflow_call:
+    inputs:
+      registry:
+        required: true
+        type: string
+      repo:
+        required: true
+        type: string
+      tag:
+        required: true
+        type: string
+      commit-hash:
+        required: false
+        type: string
+
+jobs:
+  run-k8s-tests:
+    strategy:
+      fail-fast: false
+      matrix:
+        vmm:
+          - qemu-sev
+    runs-on: sev
+    env:
+      DOCKER_REGISTRY: ${{ inputs.registry }}
+      DOCKER_REPO: ${{ inputs.repo }}
+      DOCKER_TAG: ${{ inputs.tag }}
+      KATA_HYPERVISOR: ${{ matrix.vmm }}
+      KUBECONFIG: /home/kata/.kube/config
+      USING_NFD: "false"
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+
+      - name: Deploy Kata
+        timeout-minutes: 10
+        run: bash tests/integration/kubernetes/gha-run.sh deploy-kata-sev
+  
+      - name: Run tests
+        timeout-minutes: 30
+        run: bash tests/integration/kubernetes/gha-run.sh run-tests
+
+      - name: Delete kata-deploy
+        if: always()
+        run: bash tests/integration/kubernetes/gha-run.sh cleanup-sev

.github/workflows/run-k8s-tests-on-snp.yaml

@@ -0,0 +1,48 @@
+name: CI | Run kubernetes tests on SEV-SNP
+on:
+  workflow_call:
+    inputs:
+      registry:
+        required: true
+        type: string
+      repo:
+        required: true
+        type: string
+      tag:
+        required: true
+        type: string
+      commit-hash:
+        required: false
+        type: string
+
+jobs:
+  run-k8s-tests:
+    strategy:
+      fail-fast: false
+      matrix:
+        vmm:
+          - qemu-snp
+    runs-on: sev-snp
+    env:
+      DOCKER_REGISTRY: ${{ inputs.registry }}
+      DOCKER_REPO: ${{ inputs.repo }}
+      DOCKER_TAG: ${{ inputs.tag }}
+      KATA_HYPERVISOR: ${{ matrix.vmm }}
+      KUBECONFIG: /home/kata/.kube/config
+      USING_NFD: "false"
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+
+      - name: Deploy Kata
+        timeout-minutes: 10
+        run: bash tests/integration/kubernetes/gha-run.sh deploy-kata-snp
+  
+      - name: Run tests
+        timeout-minutes: 30
+        run: bash tests/integration/kubernetes/gha-run.sh run-tests
+      
+      - name: Delete kata-deploy
+        if: always()
+        run: bash tests/integration/kubernetes/gha-run.sh cleanup-snp

.github/workflows/run-k8s-tests-on-tdx.yaml

@@ -0,0 +1,47 @@
+name: CI | Run kubernetes tests on TDX
+on:
+  workflow_call:
+    inputs:
+      registry:
+        required: true
+        type: string
+      repo:
+        required: true
+        type: string
+      tag:
+        required: true
+        type: string
+      commit-hash:
+        required: false
+        type: string
+
+jobs:
+  run-k8s-tests:
+    strategy:
+      fail-fast: false
+      matrix:
+        vmm:
+          - qemu-tdx
+    runs-on: tdx
+    env:
+      DOCKER_REGISTRY: ${{ inputs.registry }}
+      DOCKER_REPO: ${{ inputs.repo }}
+      DOCKER_TAG: ${{ inputs.tag }}
+      KATA_HYPERVISOR: ${{ matrix.vmm }}
+      USING_NFD: "true"
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+
+      - name: Deploy Kata
+        timeout-minutes: 10
+        run: bash tests/integration/kubernetes/gha-run.sh deploy-kata-tdx
+  
+      - name: Run tests
+        timeout-minutes: 30
+        run: bash tests/integration/kubernetes/gha-run.sh run-tests
+  
+      - name: Delete kata-deploy
+        if: always()
+        run: bash tests/integration/kubernetes/gha-run.sh cleanup-tdx

.github/workflows/run-metrics.yaml

@@ -0,0 +1,64 @@
+name: CI | Run test metrics
+on:
+  workflow_call:
+    inputs:
+      tarball-suffix:
+        required: false
+        type: string
+      commit-hash:
+        required: false
+        type: string
+
+jobs:
+  run-metrics:
+    strategy:
+      fail-fast: true
+      matrix:
+        vmm: ['clh', 'qemu']
+      max-parallel: 1
+    runs-on: metrics
+    env:
+      GOPATH: ${{ github.workspace }}
+      KATA_HYPERVISOR: ${{ matrix.vmm }}
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+
+      - name: get-kata-tarball
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-static-tarball-amd64${{ inputs.tarball-suffix }}
+          path: kata-artifacts
+
+      - name: Install kata
+        run: bash tests/metrics/gha-run.sh install-kata kata-artifacts
+
+      - name: run launch times test
+        run: bash tests/metrics/gha-run.sh run-test-launchtimes
+
+      - name: run memory foot print test
+        run:  bash tests/metrics/gha-run.sh run-test-memory-usage
+
+      - name: run memory usage inside container test
+        run:  bash tests/metrics/gha-run.sh run-test-memory-usage-inside-container
+
+      - name: run blogbench test
+        run:  bash tests/metrics/gha-run.sh run-test-blogbench
+
+      - name: run tensorflow test
+        run:  bash tests/metrics/gha-run.sh run-test-tensorflow
+
+      - name: run fio test
+        run:  bash tests/metrics/gha-run.sh run-test-fio
+
+      - name: make metrics tarball ${{ matrix.vmm }}
+        run: bash tests/metrics/gha-run.sh make-tarball-results
+
+      - name: archive metrics results ${{ matrix.vmm }}
+        uses: actions/upload-artifact@v3
+        with:
+          name: metrics-artifacts-${{ matrix.vmm }}
+          path: results-${{ matrix.vmm }}.tar.gz
+          retention-days: 1
+          if-no-files-found: error

.github/workflows/run-nydus-tests.yaml

@@ -0,0 +1,42 @@
+name: CI | Run nydus tests
+on:
+  workflow_call:
+    inputs:
+      tarball-suffix:
+        required: false
+        type: string
+      commit-hash:
+        required: false
+        type: string
+
+jobs:
+  run-nydus:
+    strategy:
+      fail-fast: true
+      matrix:
+        containerd_version: ['lts', 'active']
+        vmm: ['clh', 'qemu', 'dragonball']
+    runs-on: garm-ubuntu-2204
+    env:
+      CONTAINERD_VERSION: ${{ matrix.containerd_version }}
+      GOPATH: ${{ github.workspace }}
+      KATA_HYPERVISOR: ${{ matrix.vmm }}
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+
+      - name: Install dependencies
+        run: bash tests/integration/nydus/gha-run.sh install-dependencies
+
+      - name: get-kata-tarball
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-static-tarball-amd64${{ inputs.tarball-suffix }}
+          path: kata-artifacts
+
+      - name: Install kata
+        run: bash tests/integration/nydus/gha-run.sh install-kata kata-artifacts
+
+      - name: Run nydus tests
+        run: bash tests/integration/nydus/gha-run.sh run

.github/workflows/run-vfio-tests.yaml

@@ -0,0 +1,37 @@
+name: CI | Run vfio tests
+on:
+  workflow_call:
+    inputs:
+      tarball-suffix:
+        required: false
+        type: string
+      commit-hash:
+        required: false
+        type: string
+
+jobs:
+  run-vfio:
+    strategy:
+      fail-fast: false
+      matrix:
+        vmm: ['clh', 'qemu']
+    runs-on: garm-ubuntu-2204
+    env:
+      GOPATH: ${{ github.workspace }}
+      KATA_HYPERVISOR: ${{ matrix.vmm }}
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.commit-hash }}
+
+      - name: Install dependencies
+        run: bash tests/functional/vfio/gha-run.sh install-dependencies
+
+      - name: get-kata-tarball
+        uses: actions/download-artifact@v3
+        with:
+          name: kata-static-tarball-amd64${{ inputs.tarball-suffix }}
+          path: kata-artifacts
+
+      - name: Run vfio tests
+        run: bash tests/functional/vfio/gha-run.sh run

.github/workflows/snap-release.yaml

@@ -1,52 +0,0 @@
-name: Release Kata in snapcraft store
-on:
-  push:
-    tags:
-      - '[0-9]+.[0-9]+.[0-9]+*'
-
-env:
-  SNAPCRAFT_STORE_CREDENTIALS: ${{ secrets.snapcraft_token }}
-
-jobs:
-  release-snap:
-    runs-on: ubuntu-20.04
-    steps:
-      - name: Check out Git repository
-        uses: actions/checkout@v2
-        with:
-          fetch-depth: 0
-
-      - name: Install Snapcraft
-        run: |
-          # Required to avoid snapcraft install failure
-          sudo chown root:root /
-
-          # "--classic" is needed for the GitHub action runner
-          # environment.
-          sudo snap install snapcraft --classic
-
-          # Allow other parts to access snap binaries
-          echo /snap/bin >> "$GITHUB_PATH"
-
-      - name: Build snap
-        run: |
-          # Removing man-db, workflow kept failing, fixes: #4480
-          sudo apt -y remove --purge man-db
-          sudo apt-get install -y git git-extras
-          kata_url="https://github.com/kata-containers/kata-containers"
-          latest_version=$(git ls-remote --tags ${kata_url}  | egrep -o "refs.*" | egrep -v "\-alpha|\-rc|{}" | egrep -o "[[:digit:]]+\.[[:digit:]]+\.[[:digit:]]+" | sort -V -r | head -1)
-          current_version="$(echo ${GITHUB_REF} | cut -d/ -f3)"
-          # Check semantic versioning format (x.y.z) and if the current tag is the latest tag
-          if echo "${current_version}" | grep -q "^[[:digit:]]\+\.[[:digit:]]\+\.[[:digit:]]\+$" && echo -e "$latest_version\n$current_version" | sort -C -V; then
-            # Current version is the latest version, build it
-            snapcraft snap --debug --destructive-mode
-          fi
-
-      - name: Upload snap
-        run: |
-          snap_version="$(echo ${GITHUB_REF} | cut -d/ -f3)"
-          snap_file="kata-containers_${snap_version}_amd64.snap"
-          # Upload the snap if it exists
-          if [ -f ${snap_file} ]; then
-            snapcraft upload --release=stable ${snap_file}
-          fi

.github/workflows/snap.yaml

@@ -1,37 +0,0 @@
-name: snap CI
-on:
-  pull_request:
-    types:
-      - opened
-      - synchronize
-      - reopened
-      - edited
-    paths-ignore: [ '**.md', '**.png', '**.jpg', '**.jpeg', '**.svg', '/docs/**' ]
-
-jobs:
-  test:
-    runs-on: ubuntu-20.04
-    steps:
-      - name: Check out
-        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-        uses: actions/checkout@v2
-        with:
-          fetch-depth: 0
-
-      - name: Install Snapcraft
-        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-        run: |
-          # Required to avoid snapcraft install failure
-          sudo chown root:root /
-
-          # "--classic" is needed for the GitHub action runner
-          # environment.
-          sudo snap install snapcraft --classic
-
-          # Allow other parts to access snap binaries
-          echo /snap/bin >> "$GITHUB_PATH"
-
-      - name: Build snap
-        if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-        run: |
-          snapcraft snap --debug --destructive-mode

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

@@ -7,10 +7,14 @@ on:
       - synchronize
     paths-ignore: [ '**.md', '**.png', '**.jpg', '**.jpeg', '**.svg', '/docs/**' ]
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
 name: Static checks dragonball
 jobs:
   test-dragonball:
-    runs-on: self-hosted
+    runs-on: dragonball
     env:
       RUST_BACKTRACE: "1"
     steps:
@@ -23,7 +27,7 @@ jobs:
         if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
         run: |
           ./ci/install_rust.sh
-          PATH=$PATH:"$HOME/.cargo/bin"
+          echo PATH="$HOME/.cargo/bin:$PATH" >> $GITHUB_ENV
       - name: Run Unit Test
         if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
         run: |

.github/workflows/static-checks.yaml

@@ -6,6 +6,10 @@ on:
       - reopened
       - synchronize
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
 name: Static checks
 jobs:
   static-checks:
@@ -19,13 +23,14 @@ jobs:
           - "make test"
           - "sudo -E PATH=\"$PATH\" make test"
     env:
-      TRAVIS: "true"
-      TRAVIS_BRANCH: ${{ github.base_ref }}
-      TRAVIS_PULL_REQUEST_BRANCH: ${{ github.head_ref }}
-      TRAVIS_PULL_REQUEST_SHA : ${{ github.event.pull_request.head.sha }}
       RUST_BACKTRACE: "1"
       target_branch: ${{ github.base_ref }}
+      GOPATH: ${{ github.workspace }}
     steps:
+    - name: Free disk space
+      run: |
+        sudo rm -rf /usr/share/dotnet
+        sudo rm -rf "$AGENT_TOOLSDIRECTORY"
     - name: Checkout code
       uses: actions/checkout@v3
       with:
@@ -35,16 +40,13 @@ jobs:
       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
+        if git diff --name-only origin/main..HEAD "${kernel_dir}" | grep "${kernel_dir}"; 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)
@@ -53,29 +55,14 @@ jobs:
           fi
           echo "Check passed"
         fi
-    - name: Setup GOPATH
+    - name: Set PATH
       if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
       run: |
-        echo "TRAVIS_BRANCH: ${TRAVIS_BRANCH}"
-        echo "TRAVIS_PULL_REQUEST_BRANCH: ${TRAVIS_PULL_REQUEST_BRANCH}"
-        echo "TRAVIS_PULL_REQUEST_SHA: ${TRAVIS_PULL_REQUEST_SHA}"
-        echo "TRAVIS: ${TRAVIS}"
-    - name: Set env
-      if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-      run: |
-        echo "GOPATH=${{ github.workspace }}" >> $GITHUB_ENV
         echo "${{ github.workspace }}/bin" >> $GITHUB_PATH
-    - name: Setup travis references
-      if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
-      run: |
-        echo "TRAVIS_BRANCH=${TRAVIS_BRANCH:-$(echo $GITHUB_REF | awk 'BEGIN { FS = \"/\" } ; { print $3 }')}"
-        target_branch=${TRAVIS_BRANCH}
     - name: Setup
       if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
       run: |
         cd ${GOPATH}/src/github.com/${{ github.repository }} && ./ci/setup.sh
-      env:
-        GOPATH: ${{ runner.workspace }}/kata-containers
     - name: Installing rust
       if: ${{ !contains(github.event.pull_request.labels.*.name, 'force-skip-ci') }}
       run: |

.gitignore

@@ -6,6 +6,8 @@
 **/.vscode
 **/.idea
 **/.fleet
+**/*.swp
+**/*.swo
 pkg/logging/Cargo.lock
 src/agent/src/version.rs
 src/agent/kata-agent.service

Makefile

@@ -18,11 +18,16 @@ TOOLS =
 TOOLS += agent-ctl
 TOOLS += kata-ctl
 TOOLS += log-parser
+TOOLS += log-parser-rs
 TOOLS += runk
 TOOLS += trace-forwarder
 
 STANDARD_TARGETS = build check clean install static-checks-build test vendor
 
+# Variables for the build-and-publish-kata-debug target
+KATA_DEBUG_REGISTRY ?= ""
+KATA_DEBUG_TAG ?= ""
+
 default: all
 
 include utils.mk
@@ -43,6 +48,9 @@ static-checks: static-checks-build
 docs-url-alive-check:
 	bash ci/docs-url-alive-check.sh
 
+build-and-publish-kata-debug:
+	bash tools/packaging/kata-debug/kata-debug-build-and-upload-payload.sh ${KATA_DEBUG_REGISTRY} ${KATA_DEBUG_TAG} 
+
 .PHONY: \
 	all \
 	kata-tarball \

README.md

@@ -1,4 +1,6 @@
-<img src="https://www.openstack.org/assets/kata/kata-vertical-on-white.png" width="150">
+<img src="https://object-storage-ca-ymq-1.vexxhost.net/swift/v1/6e4619c416ff4bd19e1c087f27a43eea/www-images-prod/openstack-logo/kata/SVG/kata-1.svg" width="900">
+
+[![CI | Publish Kata Containers payload](https://github.com/kata-containers/kata-containers/actions/workflows/payload-after-push.yaml/badge.svg)](https://github.com/kata-containers/kata-containers/actions/workflows/payload-after-push.yaml) [![Kata Containers Nightly CI](https://github.com/kata-containers/kata-containers/actions/workflows/ci-nightly.yaml/badge.svg)](https://github.com/kata-containers/kata-containers/actions/workflows/ci-nightly.yaml)
 
 # Kata Containers
 
@@ -132,8 +134,10 @@ The table below lists the remaining parts of the project:
 | [packaging](tools/packaging) | infrastructure | Scripts and metadata for producing packaged binaries<br/>(components, hypervisors, kernel and rootfs). |
 | [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. |
+| [kata-debug](tools/packaging/kata-debug/README.md) | infrastructure | Utility tool to gather Kata Containers debug information from Kubernetes clusters. |
 | [`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. |
+| [`log-parser-rs`](src/tools/log-parser-rs) | utility | Tool that aid in analyzing logs from the kata runtime. |
 | [`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. |
@@ -143,8 +147,10 @@ The table below lists the remaining parts of the project:
 
 Kata Containers is now
 [available natively for most distributions](docs/install/README.md#packaged-installation-methods).
-However, packaging scripts and metadata are still used to generate [snap](snap/local) and GitHub releases. See
-the [components](#components) section for further details.
+
+## Metrics tests
+
+See the [metrics documentation](tests/metrics/README.md).
 
 ## Glossary of Terms
 

VERSION

@@ -1 +1 @@
-3.1.3
+3.2.0-rc0

ci/install_libseccomp.sh

@@ -87,7 +87,8 @@ build_and_install_libseccomp() {
     curl -sLO "${libseccomp_tarball_url}"
     tar -xf "${libseccomp_tarball}"
     pushd "libseccomp-${libseccomp_version}"
-    ./configure --prefix="${libseccomp_install_dir}" CFLAGS="${cflags}" --enable-static --host="${arch}"
+    [ "${arch}" == $(uname -m) ] && cc_name="" || cc_name="${arch}-linux-gnu-gcc"
+    CC=${cc_name} ./configure --prefix="${libseccomp_install_dir}" CFLAGS="${cflags}" --enable-static --host="${arch}"
     make
     make install
     popd

docs/Developer-Guide.md

@@ -2,6 +2,8 @@
 
 This document is written **specifically for developers**: it is not intended for end users.
 
+If you want to contribute changes that you have made, please read the [community guidelines](https://github.com/kata-containers/community/blob/main/CONTRIBUTING.md) for information about our processes.
+
 # Assumptions
 
 - You are working on a non-critical test or development system.
@@ -585,10 +587,15 @@ $ sudo kata-monitor
 
 #### Connect to debug console
 
-Command `kata-runtime exec` is used to connect to the debug console.
+You need to start a container for example:
+```bash
+$ sudo ctr run  --runtime io.containerd.kata.v2 -d docker.io/library/ubuntu:latest testdebug
+```
+
+Then, you can use the command `kata-runtime exec <sandbox id>` to connect to the debug console.
 
 ```
-$ kata-runtime exec 1a9ab65be63b8b03dfd0c75036d27f0ed09eab38abb45337fea83acd3cd7bacd
+$ kata-runtime exec testdebug
 bash-4.2# id
 uid=0(root) gid=0(root) groups=0(root)
 bash-4.2# pwd
@@ -654,7 +661,7 @@ section when using rootfs, or when using initrd, complete the steps in the [Buil
 
 Install the image:
 
->**Note**: When using an initrd image, replace the below rootfs image name `kata-containers.img` 
+>**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
@@ -688,25 +695,25 @@ $ sudo crictl run -r kata container.yaml pod.yaml
 
 The steps required to enable debug console for QEMU slightly differ with
 those for firecracker / cloud-hypervisor.
- 
+
 ##### Enabling debug console for QEMU
 
-Add `agent.debug_console` to the guest kernel command line to allow the agent process to start a debug console. 
+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}"
 ```
 
-Here `kata_configuration_file` could point to `/etc/kata-containers/configuration.toml` 
+Here `kata_configuration_file` could point to `/etc/kata-containers/configuration.toml`
 or `/usr/share/defaults/kata-containers/configuration.toml`
 or `/opt/kata/share/defaults/kata-containers/configuration-{hypervisor}.toml`, if
 you installed Kata Containers using `kata-deploy`.
 
 ##### Enabling debug console for cloud-hypervisor / firecracker
 
-Slightly different configuration is required in case of firecracker and cloud hypervisor. 
-Firecracker and cloud-hypervisor don't have a UNIX socket connected to `/dev/console`. 
-Hence, the kernel command line option `agent.debug_console` will not work for them. 
+Slightly different configuration is required in case of firecracker and cloud hypervisor.
+Firecracker and cloud-hypervisor don't have a UNIX socket connected to `/dev/console`.
+Hence, the kernel command line option `agent.debug_console` will not work for them.
 These hypervisors support `hybrid vsocks`,  which can be used for communication
 between the host and the guest. The kernel command line option `agent.debug_console_vport`
  was added to allow developers specify on which `vsock` port the debugging console should be connected.
@@ -719,7 +726,7 @@ sudo sed -i -e 's/^kernel_params = "\(.*\)"/kernel_params = "\1 agent.debug_cons
 ```
 
 > **Note** Ports 1024 and 1025 are reserved for communication with the agent
-> and gathering of agent logs respectively. 
+> and gathering of agent logs respectively.
 
 ##### Connecting to the debug console
 

docs/Limitations.md

@@ -147,7 +147,8 @@ these commands is potentially challenging.
 See issue https://github.com/clearcontainers/runtime/issues/341 and [the constraints challenge](#the-constraints-challenge) for more information.
 
 For CPUs resource management see
-[CPU constraints](design/vcpu-handling.md).
+[CPU constraints(in runtime-go)](design/vcpu-handling-runtime-go.md).
+[CPU constraints(in runtime-rs)](design/vcpu-handling-runtime-rs.md).
 
 # Architectural limitations
 

docs/Release-Process.md

@@ -28,23 +28,6 @@
   $ ./update-repository-version.sh -p "$NEW_VERSION" "$BRANCH"
   ```
 
-### Point tests repository to stable branch
-
-  If you create a new stable branch, i.e. if your release changes a major or minor version number (not a patch release), then
-  you should modify the `tests` repository to point to that newly created stable branch and not the `main` branch.
-  The objective is that changes in the CI on the main branch will not impact the stable branch.
-
-  In the test directory, change references the main branch in:
-  * `README.md`
-  * `versions.yaml`
-  * `cmd/github-labels/labels.yaml.in`
-  * `cmd/pmemctl/pmemctl.sh`
-  * `.ci/lib.sh`
-  * `.ci/static-checks.sh`
-
-  See the commits in [the corresponding PR for stable-2.1](https://github.com/kata-containers/tests/pull/3504) for an example of the changes.
-
-
 ### Merge all bump version Pull requests
 
   - The above step will create a GitHub pull request in the Kata projects. Trigger the CI using `/test` command on each bump Pull request.
@@ -63,6 +46,24 @@
   $ ./tag_repos.sh -p -b "$BRANCH" tag
   ```
 
+### Point tests repository to stable branch
+
+  If your release changes a major or minor version number(not a patch release), then the above 
+  `./tag_repos.sh` script will create a new stable branch in all the repositories in addition to tagging them.
+  This happens when you are making the first `rc` release for a new major or minor version in Kata.
+  In this case, you should modify the `tests` repository to point to the newly created stable branch and not the `main` branch.
+  The objective is that changes in the CI on the main branch will not impact the stable branch.
+
+  In the test directory, change references of the `main` branch to the new stable branch in:
+  * `README.md`
+  * `versions.yaml`
+  * `cmd/github-labels/labels.yaml.in`
+  * `cmd/pmemctl/pmemctl.sh`
+  * `.ci/lib.sh`
+  * `.ci/static-checks.sh`
+
+  See the commits in [the corresponding PR for stable-2.1](https://github.com/kata-containers/tests/pull/3504) for an example of the changes.
+
 ### Check Git-hub Actions
 
   We make use of [GitHub actions](https://github.com/features/actions) in this [file](../.github/workflows/release.yaml) in the `kata-containers/kata-containers` repository to build and upload release artifacts. This action is auto triggered with the above step when a new tag is pushed to the `kata-containers/kata-containers` repository.

docs/design/README.md

@@ -6,15 +6,19 @@ Kata Containers design documents:
 - [API Design of Kata Containers](kata-api-design.md)
 - [Design requirements for Kata Containers](kata-design-requirements.md)
 - [VSocks](VSocks.md)
-- [VCPU handling](vcpu-handling.md)
+- [VCPU handling(in runtime-go)](vcpu-handling-runtime-go.md)
+- [VCPU handling(in runtime-rs)](vcpu-handling-runtime-rs.md)
 - [VCPU threads pinning](vcpu-threads-pinning.md)
 - [Host cgroups](host-cgroups.md)
 - [Agent systemd cgroup](agent-systemd-cgroup.md)
 - [`Inotify` support](inotify.md)
+- [`Hooks` support](hooks-handling.md)
 - [Metrics(Kata 2.0)](kata-2-0-metrics.md)
+- [Metrics in Rust Runtime(runtime-rs)](kata-metrics-in-runtime-rs.md)
 - [Design for Kata Containers `Lazyload` ability with `nydus`](kata-nydus-design.md)
 - [Design for direct-assigned volume](direct-blk-device-assignment.md)
 - [Design for core-scheduling](core-scheduling.md)
+- [Virtualization Reference Architecture](kata-vra.md)
 ---
 
 - [Design proposals](proposals)

docs/design/VSocks.md

@@ -78,4 +78,4 @@ with the containers is if the VM itself or the `containerd-shim-kata-v2` dies, i
 the containers are removed automatically.
 
 [1]: https://wiki.qemu.org/Features/VirtioVsock
-[2]: ./vcpu-handling.md#virtual-cpus-and-kubernetes-pods
+[2]: ./vcpu-handling-runtime-go.md#virtual-cpus-and-kubernetes-pods

docs/design/architecture/kubernetes.md

@@ -3,11 +3,11 @@
 [Kubernetes](https://github.com/kubernetes/kubernetes/), or K8s, is a popular open source
 container orchestration engine. In Kubernetes, a set of containers sharing resources
 such as networking, storage, mount, PID, etc. is called a
-[pod](https://kubernetes.io/docs/user-guide/pods/).
+[pod](https://kubernetes.io/docs/concepts/workloads/pods/).
 
 A node can have multiple pods, but at a minimum, a node within a Kubernetes cluster
 only needs to run a container runtime and a container agent (called a
-[Kubelet](https://kubernetes.io/docs/admin/kubelet/)).
+[Kubelet](https://kubernetes.io/docs/concepts/overview/components/#kubelet)).
 
 Kata Containers represents a Kubelet pod as a VM.
 

docs/design/architecture/networking.md

@@ -36,7 +36,7 @@ compatibility, and performance on par with MACVTAP.
 Kata Containers has deprecated support for bridge due to lacking performance relative to TC-filter and MACVTAP.
 
 Kata Containers supports both
-[CNM](https://github.com/docker/libnetwork/blob/master/docs/design.md#the-container-network-model)
+[CNM](https://github.com/moby/libnetwork/blob/master/docs/design.md#the-container-network-model)
 and [CNI](https://github.com/containernetworking/cni) for networking management.
 
 ## Network Hotplug

docs/design/hooks-handling.md

@@ -0,0 +1,63 @@
+# Kata Containers support for `Hooks`
+
+## Introduction
+
+During container's lifecycle, different Hooks can be executed to do custom actions. In Kata Containers, we support two types of Hooks, `OCI Hooks` and `Kata Hooks`.
+
+### OCI Hooks
+
+The OCI Spec stipulates six hooks that can be executed at different time points and namespaces, including `Prestart Hooks`, `CreateRuntime Hooks`, `CreateContainer Hooks`, `StartContainer Hooks`, `Poststart Hooks` and `Poststop Hooks`. We support these types of Hooks as compatible as possible in Kata Containers.
+
+The path and arguments of these hooks will be passed to Kata for execution via `bundle/config.json`. For example:
+```
+...
+"hooks": {
+  "prestart": [
+    {
+      "path": "/usr/bin/prestart-hook",
+      "args": ["prestart-hook", "arg1", "arg2"],
+      "env":  [ "key1=value1"]
+    }
+  ],
+  "createRuntime": [
+    {
+      "path": "/usr/bin/createRuntime-hook",
+      "args": ["createRuntime-hook", "arg1", "arg2"],
+      "env":  [ "key1=value1"]
+    }
+  ]
+}
+...
+```
+
+### Kata Hooks
+
+In Kata, we support another three kinds of hooks executed in guest VM, including `Guest Prestart Hook`, `Guest Poststart Hook`, `Guest Poststop Hook`.
+
+The executable files for Kata Hooks must be packaged in the *guest rootfs*. The file path to those guest hooks should be specified in the configuration file, and guest hooks must be stored in a subdirectory of `guest_hook_path` according to their hook type. For example:
+
++ In configuration file:
+```
+guest_hook_path="/usr/share/hooks"
+```
++ In guest rootfs, prestart-hook is stored in `/usr/share/hooks/prestart/prestart-hook`.
+
+## Execution
+The table below summarized when and where those different hooks will be executed in Kata Containers:
+
+| Hook Name | Hook Type | Hook Path | Exec Place | Exec Time |
+|---|---|---|---|---|
+| `Prestart(deprecated)` | OCI hook | host runtime namespace | host runtime namespace | After VM is started, before container is created. |
+| `CreateRuntime` | OCI hook | host runtime namespace | host runtime namespace | After VM is started, before container is created, after `Prestart` hooks. |
+| `CreateContainer` | OCI hook | host runtime namespace | host vmm namespace* | After VM is started, before container is created, after `CreateRuntime` hooks. |
+| `StartContainer` | OCI hook | guest container namespace | guest container namespace | After container is created, before container is started. |
+| `Poststart` | OCI hook | host runtime namespace | host runtime namespace | After container is started, before start operation returns. |
+| `Poststop` | OCI hook | host runtime namespace | host runtime namespace | After container is deleted, before delete operation returns. |
+| `Guest Prestart` | Kata hook | guest agent namespace | guest agent namespace | During start operation, before container command is executed. |
+| `Guest Poststart` | Kata hook | guest agent namespace | guest agent namespace | During start operation, after container command is executed, before start operation returns. |
+| `Guest Poststop` | Kata hook | guest agent namespace | guest agent namespace | During delete operation, after container is deleted, before delete operation returns. |
+
++ `Hook Path` specifies where hook's path be resolved.
++ `Exec Place` specifies in which namespace those hooks can be executed.
+  + For `CreateContainer` Hooks, OCI requires to run them inside the container namespace while the hook executable path is in the host runtime, which is a non-starter for VM-based containers. So we design to keep them running in the *host vmm namespace.* 
++ `Exec Time` specifies at which time point those hooks can be executed.

docs/design/kata-metrics-in-runtime-rs.md

@@ -0,0 +1,50 @@
+# Kata Metrics in Rust Runtime(runtime-rs)
+
+Rust Runtime(runtime-rs) is responsible for:
+
+- Gather metrics about `shim`.
+- Gather metrics from `hypervisor` (through `channel`).
+- Get metrics from `agent` (through `ttrpc`).
+
+---
+
+Here are listed all the metrics gathered by `runtime-rs`.
+
+> * Current status of each entry is marked as:
+>  * ✅：DONE
+>   * 🚧：TODO
+
+### Kata Shim
+
+| STATUS | Metric name                                                  | Type        | Units          | Labels                                                       |
+| ------ | ------------------------------------------------------------ | ----------- | -------------- | ------------------------------------------------------------ |
+| 🚧      | `kata_shim_agent_rpc_durations_histogram_milliseconds`: <br> RPC latency distributions. | `HISTOGRAM` | `milliseconds` | <ul><li>`action` (RPC actions of Kata agent)<ul><li>`grpc.CheckRequest`</li><li>`grpc.CloseStdinRequest`</li><li>`grpc.CopyFileRequest`</li><li>`grpc.CreateContainerRequest`</li><li>`grpc.CreateSandboxRequest`</li><li>`grpc.DestroySandboxRequest`</li><li>`grpc.ExecProcessRequest`</li><li>`grpc.GetMetricsRequest`</li><li>`grpc.GuestDetailsRequest`</li><li>`grpc.ListInterfacesRequest`</li><li>`grpc.ListProcessesRequest`</li><li>`grpc.ListRoutesRequest`</li><li>`grpc.MemHotplugByProbeRequest`</li><li>`grpc.OnlineCPUMemRequest`</li><li>`grpc.PauseContainerRequest`</li><li>`grpc.RemoveContainerRequest`</li><li>`grpc.ReseedRandomDevRequest`</li><li>`grpc.ResumeContainerRequest`</li><li>`grpc.SetGuestDateTimeRequest`</li><li>`grpc.SignalProcessRequest`</li><li>`grpc.StartContainerRequest`</li><li>`grpc.StatsContainerRequest`</li><li>`grpc.TtyWinResizeRequest`</li><li>`grpc.UpdateContainerRequest`</li><li>`grpc.UpdateInterfaceRequest`</li><li>`grpc.UpdateRoutesRequest`</li><li>`grpc.WaitProcessRequest`</li><li>`grpc.WriteStreamRequest`</li></ul></li><li>`sandbox_id`</li></ul> |
+| ✅      | `kata_shim_fds`: <br> Kata containerd shim v2 open FDs.      | `GAUGE`     |                | <ul><li>`sandbox_id`</li></ul>                               |
+| ✅      | `kata_shim_io_stat`: <br> Kata containerd shim v2 process IO statistics. | `GAUGE`     |                | <ul><li>`item` (see `/proc/<pid>/io`)<ul><li>`cancelledwritebytes`</li><li>`rchar`</li><li>`readbytes`</li><li>`syscr`</li><li>`syscw`</li><li>`wchar`</li><li>`writebytes`</li></ul></li><li>`sandbox_id`</li></ul> |
+| ✅      | `kata_shim_netdev`: <br> Kata containerd shim v2 network devices statistics. | `GAUGE`     |                | <ul><li>`interface` (network device name)</li><li>`item` (see `/proc/net/dev`)<ul><li>`recv_bytes`</li><li>`recv_compressed`</li><li>`recv_drop`</li><li>`recv_errs`</li><li>`recv_fifo`</li><li>`recv_frame`</li><li>`recv_multicast`</li><li>`recv_packets`</li><li>`sent_bytes`</li><li>`sent_carrier`</li><li>`sent_colls`</li><li>`sent_compressed`</li><li>`sent_drop`</li><li>`sent_errs`</li><li>`sent_fifo`</li><li>`sent_packets`</li></ul></li><li>`sandbox_id`</li></ul> |
+| 🚧      | `kata_shim_pod_overhead_cpu`: <br> Kata Pod overhead for CPU resources(percent). | `GAUGE`     | percent        | <ul><li>`sandbox_id`</li></ul>                               |
+| 🚧      | `kata_shim_pod_overhead_memory_in_bytes`: <br> Kata Pod overhead for memory resources(bytes). | `GAUGE`     | `bytes`        | <ul><li>`sandbox_id`</li></ul>                               |
+| ✅      | `kata_shim_proc_stat`: <br> Kata containerd shim v2 process statistics. | `GAUGE`     |                | <ul><li>`item` (see `/proc/<pid>/stat`)<ul><li>`cstime`</li><li>`cutime`</li><li>`stime`</li><li>`utime`</li></ul></li><li>`sandbox_id`</li></ul> |
+| ✅      | `kata_shim_proc_status`: <br> Kata containerd shim v2 process status. | `GAUGE`     |                | <ul><li>`item` (see `/proc/<pid>/status`)<ul><li>`hugetlbpages`</li><li>`nonvoluntary_ctxt_switches`</li><li>`rssanon`</li><li>`rssfile`</li><li>`rssshmem`</li><li>`vmdata`</li><li>`vmexe`</li><li>`vmhwm`</li><li>`vmlck`</li><li>`vmlib`</li><li>`vmpeak`</li><li>`vmpin`</li><li>`vmpmd`</li><li>`vmpte`</li><li>`vmrss`</li><li>`vmsize`</li><li>`vmstk`</li><li>`vmswap`</li><li>`voluntary_ctxt_switches`</li></ul></li><li>`sandbox_id`</li></ul> |
+| 🚧      | `kata_shim_process_cpu_seconds_total`: <br> Total user and system CPU time spent in seconds. | `COUNTER`   | `seconds`      | <ul><li>`sandbox_id`</li></ul>                               |
+| 🚧      | `kata_shim_process_max_fds`: <br> Maximum number of open file descriptors. | `GAUGE`     |                | <ul><li>`sandbox_id`</li></ul>                               |
+| 🚧      | `kata_shim_process_open_fds`: <br> Number of open file descriptors. | `GAUGE`     |                | <ul><li>`sandbox_id`</li></ul>                               |
+| 🚧      | `kata_shim_process_resident_memory_bytes`: <br> Resident memory size in bytes. | `GAUGE`     | `bytes`        | <ul><li>`sandbox_id`</li></ul>                               |
+| 🚧      | `kata_shim_process_start_time_seconds`: <br> Start time of the process since `unix` epoch in seconds. | `GAUGE`     | `seconds`      | <ul><li>`sandbox_id`</li></ul>                               |
+| 🚧      | `kata_shim_process_virtual_memory_bytes`: <br> Virtual memory size in bytes. | `GAUGE`     | `bytes`        | <ul><li>`sandbox_id`</li></ul>                               |
+| 🚧      | `kata_shim_process_virtual_memory_max_bytes`: <br> Maximum amount of virtual memory available in bytes. | `GAUGE`     | `bytes`        | <ul><li>`sandbox_id`</li></ul>                               |
+| 🚧      | `kata_shim_rpc_durations_histogram_milliseconds`: <br> RPC latency distributions. | `HISTOGRAM` | `milliseconds` | <ul><li>`action` (Kata shim v2 actions)<ul><li>`checkpoint`</li><li>`close_io`</li><li>`connect`</li><li>`create`</li><li>`delete`</li><li>`exec`</li><li>`kill`</li><li>`pause`</li><li>`pids`</li><li>`resize_pty`</li><li>`resume`</li><li>`shutdown`</li><li>`start`</li><li>`state`</li><li>`stats`</li><li>`update`</li><li>`wait`</li></ul></li><li>`sandbox_id`</li></ul> |
+| ✅      | `kata_shim_threads`: <br> Kata containerd shim v2 process threads. | `GAUGE`     |                | <ul><li>`sandbox_id`</li></ul>                               |
+
+### Kata Hypervisor
+
+Different from golang runtime, hypervisor and shim in runtime-rs belong to the **same process**, so all previous metrics for hypervisor and shim only need to be gathered once. Thus, we currently only collect previous metrics in kata shim.
+
+At the same time, we added the interface(`VmmAction::GetHypervisorMetrics`) to gather hypervisor metrics, in case we design tailor-made metrics for hypervisor in the future. Here're metrics exposed from [src/dragonball/src/metric.rs](https://github.com/kata-containers/kata-containers/blob/main/src/dragonball/src/metric.rs).
+
+| Metric name                                                  | Type       | Units | Labels                                                       |
+| ------------------------------------------------------------ | ---------- | ----- | ------------------------------------------------------------ |
+| `kata_hypervisor_scrape_count`: <br> Metrics scrape count    | `COUNTER`  |       | <ul><li>`sandbox_id`</li></ul>                               |
+| `kata_hypervisor_vcpu`: <br>Hypervisor metrics specific to VCPUs' mode of functioning. | `IntGauge` |       | <ul><li>`item`<ul><li>`exit_io_in`</li><li>`exit_io_out`</li><li>`exit_mmio_read`</li><li>`exit_mmio_write`</li><li>`failures`</li><li>`filter_cpuid`</li></ul></li><li>`sandbox_id`</li></ul> |
+| `kata_hypervisor_seccomp`: <br> Hypervisor metrics for the seccomp filtering. | `IntGauge` |       | <ul><li>`item`<ul><li>`num_faults`</li></ul></li><li>`sandbox_id`</li></ul> |
+| `kata_hypervisor_seccomp`: <br> Hypervisor metrics for the seccomp filtering. | `IntGauge` |       | <ul><li>`item`<ul><li>`sigbus`</li><li>`sigsegv`</li></ul></li><li>`sandbox_id`</li></ul> |

docs/design/kata-vra.md

@@ -0,0 +1,434 @@
+# Virtualization Reference Architecture
+
+## Subject to Change | © 2022 by NVIDIA Corporation. All rights reserved. | For test and development only_
+
+Before digging deeper into the virtualization reference architecture, let's
+first look at the various GPUDirect use cases in the following table. We’re
+distinguishing between two top-tier use cases where the devices are (1)
+passthrough and (2) virtualized, where a VM gets assigned a virtual function
+(VF) and not the physical function (PF). A combination of PF and VF would also
+be possible.
+
+| Device #1  (passthrough)  | Device #2 (passthrough) | P2P Compatibility and Mode                   |
+| ------------------------- | ----------------------- | -------------------------------------------- |
+| GPU PF                    | GPU PF                  | GPUDirect P2P                                |
+| GPU PF                    | NIC PF                  | GPUDirect RDMA                               |
+| MIG-slice                 | MIG-slice               | _No GPUDirect P2P_                           |
+| MIG-slice                 | NIC PF                  | GPUDirect RDMA                               |
+| **PDevice #1  (virtualized)** | **Device #2 (virtualized)** | **P2P Compatibility and   Mode**     |
+| Time-slice vGPU VF        | Time-slice vGPU VF      | _No GPUDirect P2P  but NVLINK P2P available_ |
+| Time-slice vGPU VF        | NIC VF                  | GPUDirect RDMA                               |
+| MIG-slice vGPU            | MIG-slice vGPU          | _No GPUDirect P2P_                           |
+| MIG-slice vGPU            | NIC VF                  | GPUDirect RDMA                               |
+
+In a virtualized environment we have several distinct features that may prevent
+Peer-to-peer (P2P) communication of two endpoints in a PCI Express topology. The
+IOMMU translates IO virtual addresses (IOVA) to physical addresses (PA). Each
+device behind an IOMMU has its own IOVA memory space, usually, no two devices
+share the same IOVA memory space but it’s up to the hypervisor or OS how it
+chooses to map devices to IOVA spaces.  Any PCI Express DMA transactions will
+use IOVAs, which the IOMMU must translate. By default, all the traffic is routed
+to the root complex and not issued directly to the peer device.
+
+An IOMMU can be used to isolate and protect devices even if virtualization is
+not used; since devices can only access memory regions that are mapped for it, a
+DMA from one device to another is not possible. DPDK uses the IOMMU to have
+better isolation between devices, another benefit is that IOVA space can be
+represented as a contiguous memory even if the PA space is heavily scattered.
+
+In the case of virtualization, the IOMMU is responsible for isolating the device
+and memory between VMs for safe device assignment without compromising the host
+and other guest OSes. Without an IOMMU, any device can access the entire system
+and perform DMA transactions _anywhere_.
+
+The second feature is ACS (Access Control Services), which controls which
+devices are allowed to communicate with one another and thus avoids improper
+routing of packets irrespectively of whether IOMMU is enabled or not.
+
+When IOMMU is enabled, ACS is normally configured to force all PCI Express DMA
+to go through the root complex so IOMMU can translate it, impacting performance
+between peers with higher latency and reduced bandwidth.
+
+A way to avoid the performance hit is to enable Address Translation Services
+(ATS). ATS-capable endpoints can prefetch IOVA -> PA translations from the IOMMU
+and then perform DMA transactions directly to another endpoint. Hypervisors
+enable this by enabling ATS in such endpoints, configuring ACS to enable Direct
+Translated P2P, and configuring the IOMMU to allow Address Translation requests.
+
+Another important factor is that the NVIDIA driver stack will use the PCI
+Express topology of the system it is running on to determine whether the
+hardware is capable of supporting P2P. The driver stack qualifies specific
+chipsets, and PCI Express switches for use with GPUDirect P2P. In virtual
+environments, the PCI Express topology is flattened and obfuscated to present a
+uniform environment to the software inside the VM, which breaks the GPUDirect
+P2P use case.
+
+On a bare metal machine, the driver stack groups GPUs into cliques that can
+perform GPUDirect P2P communication, excluding peer mappings where P2P
+communication is not possible, prominently if GPUs are attached to multiple CPU
+sockets.  
+
+CPUs and local memory banks are referred to as NUMA nodes. In a two-socket
+server, each of the CPUs has a local memory bank for a total of two NUMA nodes.
+Some servers provide the ability to configure additional NUMA nodes per CPU,
+which means a CPU socket can have two NUMA nodes  (some servers support four
+NUMA nodes per socket) with local memory banks and L3 NUMA domains for improved
+performance.
+
+One of the current solutions is that the hypervisor provides additional topology
+information that the driver stack can pick up and enable GPUDirect P2P between
+GPUs, even if the virtualized environment does not directly expose it. The PCI
+Express virtual P2P approval capability structure in the PCI configuration space
+is entirely emulated by the hypervisor of passthrough GPU devices.
+
+A clique ID is provided where GPUs with the same clique ID belong to a group of
+GPUs capable of P2P communication
+
+On vSphere, Azure, and other CPSs,  the hypervisor lays down a `topologies.xml`
+which NCCL can pick up and deduce the right P2P level[^1]. NCCL is leveraging
+Infiniband (IB) and/or Unified Communication X (UCX) for communication, and
+GPUDirect P2P and GPUDirect RDMA should just work in this case. The only culprit
+is that software or applications that do not use the XML file to deduce the
+topology will fail and not enable GPUDirect ( [`nccl-p2p-level`](https://docs.nvidia.com/deeplearning/nccl/user-guide/docs/env.html#nccl-p2p-level) )
+
+## Hypervisor PCI Express Topology
+
+To enable every part of the accelerator stack, we propose a virtualized
+reference architecture to enable GPUDirect P2P and GPUDirect RDMA for any
+hypervisor. The idea is split into two parts to enable the right PCI Express
+topology. The first part builds upon extending the PCI Express virtual P2P
+approval capability structure to every device that wants to do P2P in some way
+and groups devices by clique ID. The other part involves replicating a subset of
+the host topology so that applications running in the VM do not need to read
+additional information and enable the P2P capability like in the bare-metal use
+case described above. The driver stack can then deduce automatically if the
+topology presented in the VM is capable of P2P communication.
+
+We will work with the following host topology for the following sections. It is
+a system with two converged DPUs, each having an `A100X` GPU and two `ConnectX-6`
+network ports connected to the downstream ports of a PCI Express switch.
+
+```sh
++-00.0-[d8-df]----00.0-[d9-df]--+-00.0-[da-db]--+-00.0  Mellanox Tech MT42822 BlueField-2 integrated ConnectX-6 Dx network
+                                |               +-00.1  Mellanox Tech MT42822 BlueField-2 integrated ConnectX-6 Dx network
+                                |               \-00.2  Mellanox Tech MT42822 BlueField-2 SoC Management Interface
+                                 \-01.0-[dc-df]----00.0-[dd-df]----08.0-[de-df]----00.0  NVIDIA Corporation GA100 [A100X]
+
++-00.0-[3b-42]----00.0-[3c-42]--+-00.0-[3d-3e]--+-00.0  Mellanox Tech MT42822 BlueField-2 integrated ConnectX-6 Dx network
+                                |               +-00.1  Mellanox Tech MT42822 BlueField-2 integrated ConnectX-6 Dx network
+                                |               \-00.2  Mellanox Tech MT42822 BlueField-2 SoC Management Interface
+                                 \-01.0-[3f-42]----00.0-[40-42]----08.0-[41-42]----00.0  NVIDIA Corporation GA100 [A100X]
+```
+
+The green path highlighted above is the optimal and preferred path for
+efficient P2P communication.
+
+## PCI Express Virtual P2P Approval Capability
+
+Most of the time, the PCI Express topology is flattened and obfuscated to ensure
+easy migration of the VM image between different physical hardware topologies.
+In Kata, we can configure the hypervisor to use PCI Express root ports to
+hotplug the VFIO  devices one is passing through. A user can select how many PCI
+Express root ports to allocate depending on how many devices are passed through.
+A recent addition to Kata will detect the right amount of PCI Express devices
+that need hotplugging and bail out if the number of root ports is insufficient.
+In Kata, we do not automatically increase the number of root ports, we want the
+user to be in full control of the topology.
+
+```toml
+# /etc/kata-containers/configuration.toml
+
+# VFIO devices are hotplugged on a bridge by default.
+# Enable hot-plugging on the root bus. This may be required for devices with
+# a large PCI bar, as this is a current limitation with hot-plugging on
+# a bridge.
+# Default “bridge-port”
+hotplug_vfio = "root-port"
+
+# Before hot plugging a PCIe device, you need to add a pcie_root_port device.
+# Use this parameter when using some large PCI bar devices, such as NVIDIA GPU
+# The value means the number of pcie_root_port
+# This value is valid when hotplug_vfio_on_root_bus is true and machine_type is "q35"
+# Default 0
+pcie_root_port = 8
+```
+
+VFIO devices are hotplugged on a PCIe-PCI bridge by default. Hotplug of PCI
+Express devices is only supported on PCI Express root or downstream ports. With
+this configuration set, if we start up a Kata container, we can inspect our
+topology and see the allocated PCI Express root ports and the hotplugged
+devices.
+
+```sh
+$ lspci -tv
+ -[0000:00]-+-00.0  Intel Corporation 82G33/G31/P35/P31 Express DRAM Controller
+           +-01.0  Red Hat, Inc. Virtio console
+           +-02.0  Red Hat, Inc. Virtio SCSI
+           +-03.0  Red Hat, Inc. Virtio RNG
+           +-04.0-[01]----00.0  Mellanox Technologies MT42822 BlueField-2 integrated ConnectX-6
+           +-05.0-[02]----00.0  Mellanox Technologies MT42822 BlueField-2 integrated ConnectX-6
+           +-06.0-[03]----00.0  NVIDIA Corporation Device 20b8
+           +-07.0-[04]----00.0  NVIDIA Corporation Device 20b8
+           +-08.0-[05]--
+           +-09.0-[06]--
+           +-0a.0-[07]--
+           +-0b.0-[08]--
+           +-0c.0  Red Hat, Inc. Virtio socket
+           +-0d.0  Red Hat, Inc. Virtio file system
+           +-1f.0  Intel Corporation 82801IB (ICH9) LPC Interface Controller
+           +-1f.2  Intel Corporation 82801IR/IO/IH (ICH9R/DO/DH) 6 port SATA Controller
+           \-1f.3  Intel Corporation 82801I (ICH9 Family) SMBus Controller
+```
+
+For devices with huge BARs (Base Address Registers) like the GPU (we need to
+configure the PCI Express root port properly and allocate enough memory for
+mapping), we have added a heuristic to Kata to deduce the right settings. Hence,
+the BARs can be mapped correctly. This functionality is added to
+[`nvidia/go-nvlib1](https://gitlab.com/nvidia/cloud-native/go-nvlib) which is part
+of Kata now.
+
+```sh
+$ sudo dmesg | grep BAR
+[    0.179960] pci 0000:00:04.0: BAR 7: assigned [io  0x1000-0x1fff]
+[    0.179962] pci 0000:00:05.0: BAR 7: assigned [io  0x2000-0x2fff]
+[    0.179963] pci 0000:00:06.0: BAR 7: assigned [io  0x3000-0x3fff]
+[    0.179964] pci 0000:00:07.0: BAR 7: assigned [io  0x4000-0x4fff]
+[    0.179966] pci 0000:00:08.0: BAR 7: assigned [io  0x5000-0x5fff]
+[    0.179967] pci 0000:00:09.0: BAR 7: assigned [io  0x6000-0x6fff]
+[    0.179968] pci 0000:00:0a.0: BAR 7: assigned [io  0x7000-0x7fff]
+[    0.179969] pci 0000:00:0b.0: BAR 7: assigned [io  0x8000-0x8fff]
+[    2.115912] pci 0000:01:00.0: BAR 0: assigned [mem 0x13000000000-0x13001ffffff 64bit pref]
+[    2.116203] pci 0000:01:00.0: BAR 2: assigned [mem 0x13002000000-0x130027fffff 64bit pref]
+[    2.683132] pci 0000:02:00.0: BAR 0: assigned [mem 0x12000000000-0x12001ffffff 64bit pref]
+[    2.683419] pci 0000:02:00.0: BAR 2: assigned [mem 0x12002000000-0x120027fffff 64bit pref]
+[    2.959155] pci 0000:03:00.0: BAR 1: assigned [mem 0x11000000000-0x117ffffffff 64bit pref]
+[    2.959345] pci 0000:03:00.0: BAR 3: assigned [mem 0x11800000000-0x11801ffffff 64bit pref]
+[    2.959523] pci 0000:03:00.0: BAR 0: assigned [mem 0xf9000000-0xf9ffffff]
+[    2.966119] pci 0000:04:00.0: BAR 1: assigned [mem 0x10000000000-0x107ffffffff 64bit pref]
+[    2.966295] pci 0000:04:00.0: BAR 3: assigned [mem 0x10800000000-0x10801ffffff 64bit pref]
+[    2.966472] pci 0000:04:00.0: BAR 0: assigned [mem 0xf7000000-0xf7ffffff]
+```
+
+The NVIDIA driver stack in this case would refuse to do P2P communication since
+(1) the topology is not what it expects, (2)  we do not have a qualified
+chipset. Since our P2P devices are not connected to a PCI Express switch port,
+we need to provide additional information to support the P2P functionality. One
+way of providing such meta information would be to annotate the container; most
+of the settings in Kata's configuration file can be overridden via annotations,
+but this limits the flexibility, and a user would need to update all the
+containers that he wants to run with Kata. The goal is to make such things as
+transparent as possible, so we also introduced
+[CDI](https://github.com/container-orchestrated-devices/container-device-interface)
+(Container Device Interface) to Kata. CDI is a[
+specification](https://github.com/container-orchestrated-devices/container-device-interface/blob/master/SPEC.md)
+for container runtimes to support third-party devices.
+
+As written before, we can provide a clique ID for the devices that belong
+together and are capable of doing P2P. This information is provided to the
+hypervisor, which will set up things in the VM accordingly. Let's suppose the
+user wanted to do GPUDirect RDMA with the first GPU and the NIC that reside on
+the same DPU, one could provide the specification telling the hypervisor that
+they belong to the same clique.
+
+```yaml
+# /etc/cdi/nvidia.yaml
+cdiVersion: 0.4.0
+kind: nvidia.com/gpu
+devices:
+- name: gpu0
+  annotations:
+    bdf: “41:00.0”
+    clique-id: “0”
+  containerEdits:
+    deviceNodes:
+    - path: “/dev/vfio/71"
+
+# /etc/cdi/mellanox.yaml
+cdiVersion: 0.4.0
+kind: mellanox.com/nic
+devices:
+- name: nic0
+  annotations:
+    bdf: “3d:00.0”
+    clique-id: “0”
+    attach-pci: “true”
+  containerEdits:
+    deviceNodes:
+    - path: "/dev/vfio/66"
+```
+
+Since this setting is bound to the device and not the container we do not need
+to alter the container just allocate the right resource and GPUDirect RDMA would
+be set up correctly. Rather than exposing them separately, an idea would be to
+expose a GPUDirect RDMA device via NFD (Node Feature Discovery) that combines
+both of them; this way, we could make sure that the right pair is allocated and
+used more on  Kubernetes deployment in the next section.
+
+The GPU driver stack is leveraging the PCI Express virtual P2P approval
+capability, but the NIC stack does not use this now. One of the action items is
+to enable MOFED to read the P2P approval capability and enable ATS and ACS
+settings as described above.
+
+This way, we could enable GPUDirect P2P and GPUDirect RDMA on any topology
+presented to the VM application. It is the responsibility of the administrator
+or infrastructure engineer to provide the right information either via
+annotations or a CDI specification.
+
+## Host Topology Replication
+
+The other way to represent the PCI Express topology in the VM is to replicate a
+subset of the topology needed to support the P2P use case inside the VM. Similar
+to the configuration for the root ports, we can easily configure the usage of
+PCI Express switch ports to hotplug the devices.
+
+```toml
+# /etc/kata-containers/configuration.toml
+
+# VFIO devices are hotplugged on a bridge by default.
+# Enable hot plugging on the root bus. This may be required for devices with
+# a large PCI bar, as this is a current limitation with hot plugging on
+# a bridge.
+# Default “bridge-port”
+hotplug_vfio = "switch-port"
+
+# Before hot plugging a PCIe device, you need to add a pcie_root_port device.
+# Use this parameter when using some large PCI bar devices, such as Nvidia GPU
+# The value means the number of pcie_root_port
+# This value is valid when hotplug_vfio_on_root_bus is true and machine_type is "q35"
+# Default 0
+pcie_switch_port = 8
+```
+
+Each device that is passed through is attached to a PCI Express downstream port
+as illustrated below. We can even replicate the host’s two DPUs topologies with
+added metadata through the CDI. Most of the time, a container only needs one
+pair of GPU and NIC for GPUDirect RDMA. This is more of a showcase of what we
+can do with the power of Kata and CDI. One could even think of adding groups of
+devices that support P2P, even from different CPU sockets or NUMA nodes, into
+one container; indeed, the first group is NUMA node 0 (red), and the second
+group is NUMA node 1 (green). Since they are grouped correctly, P2P would be
+enabled naturally inside a group, aka clique ID.
+
+```sh
+$ lspci -tv
+ -[0000:00]-+-00.0  Intel Corporation 82G33/G31/P35/P31 Express DRAM Controller
+            +-01.0  Red Hat, Inc. Virtio console
+            +-02.0  Red Hat, Inc. Virtio SCSI
+            +-03.0  Red Hat, Inc. Virtio RNG
+            +-04.0-[01-04]----00.0-[02-04]--+-00.0-[03]----00.0  NVIDIA Corporation Device 20b8
+            |                               \-01.0-[04]----00.0  Mellanox Tech MT42822 BlueField-2 integrated ConnectX-6 Dx
+            +-05.0-[05-08]----00.0-[06-08]--+-00.0-[07]----00.0  Mellanox Tech MT42822 BlueField-2 integrated ConnectX-6 Dx
+            |                               \-01.0-[08]----00.0  NVIDIA Corporation Device 20b8
+            +-06.0  Red Hat, Inc. Virtio socket
+            +-07.0  Red Hat, Inc. Virtio file system
+            +-1f.0  Intel Corporation 82801IB (ICH9) LPC Interface Controller
+            +-1f.2  Intel Corporation 82801IR/IO/IH (ICH9R/DO/DH) 6 port SATA Controller [AHCI mode]
+            \-1f.3  Intel Corporation 82801I (ICH9 Family) SMBus Controller
+            \-1f.3  Intel Corporation 82801I (ICH9 Family) SMBus Controller
+```
+
+The configuration of using either the root port or switch port can be applied on
+a per Container or Pod basis, meaning we can switch PCI Express topologies on
+each run of an application.
+
+## Hypervisor Resource Limits
+
+Every hypervisor will have resource limits in terms of how many PCI Express root
+ports, switch ports, or bridge ports can be created, especially with devices
+that need to reserve a 4K IO range per PCI specification. Each instance of root
+or switch port will consume 4K IO of very limited capacity, 64k is the maximum.
+
+Simple math brings us to the conclusion that we can have a maximum of 16 PCI
+Express root ports or 16 PCI Express switch ports in QEMU if devices with IO
+BARs are used in the PCI Express hierarchy.
+
+Additionally, one can have 32 slots on the PCI root bus and a maximum of 256
+slots for the complete PCI(e) topology.
+
+Per default, QEMU will attach a multi-function device in the last slot on the
+PCI root bus,
+
+```sh
+ +-1f.0  Intel Corporation 82801IB (ICH9) LPC Interface Controller
+ +-1f.2  Intel Corporation 82801IR/IO/IH (ICH9R/DO/DH) 6 port SATA Controller [AHCI mode]
+ \-1f.3  Intel Corporation 82801I (ICH9 Family) SMBus Controller
+```
+
+Kata will additionally add `virtio-xxx-pci` devices consuming (5 slots) plus a
+PCIe-PCI-bridge (1 slot) and a DRAM controller (1 slot), meaning per default, we
+have already eight slots used. This leaves us 24 slots for adding other devices
+to the root bus.
+
+The problem that arises here is one use-case from a customer that uses recent
+RTX GPUs with Kata. The user wanted to pass through eight of these GPUs into one
+container and ran into issues. The problem is that those cards often consist of
+four individual device nodes: GPU, Audio, and two USB controller devices (some
+cards have a USB-C output).
+
+These devices are grouped into one IOMMU group. Since one needs to pass through
+the complete IOMMU group into the VM, we need to allocate 32 PCI Express root
+ports or 32 PCI Express switch ports, which is technically impossible due to the
+resource limits outlined above. Since all the devices appear as PCI Express
+devices, we need to hotplug those into a root or switch port.
+
+The solution to this problem is leveraging CDI. For each device, add the
+information if it is going to be hotplugged as a PCI Express or PCI device,
+which results in either using a PCI Express root/switch port or an ordinary PCI
+bridge. PCI bridges are not affected by the limited IO range. This way, the GPU
+is attached as a PCI Express device to a root/switch port and the other three
+PCI devices to a PCI bridge, leaving enough resources to create the needed PCI
+Express root/switch ports.  For example, we’re going to attach the GPUs to a PCI
+Express root port and the NICs to a PCI bridge.
+
+```jsonld
+# /etc/cdi/mellanox.json
+cdiVersion: 0.4.0
+kind: mellanox.com/nic
+devices:
+- name: nic0
+  annotations:
+    bdf: “3d:00.0”
+    clique-id: “0”
+    attach-pci: “true”
+  containerEdits:
+    deviceNodes:
+    - path: "/dev/vfio/66"
+- name: nic1
+  annotations:
+    bdf: “3d:00.1”
+    clique-id: “1”
+    attach-pci: “true”
+  containerEdits:
+    deviceNodes:
+    - path: "/dev/vfio/67”
+```
+
+The configuration is set to use eight root ports for the GPUs and attach the
+NICs to a PCI bridge which is connected to a PCI Express-PCI bridge which is the
+preferred way of introducing a PCI topology in a PCI Express machine.
+
+```sh
+$ lspci -tv
+-[0000:00]-+-00.0  Intel Corporation 82G33/G31/P35/P31 Express DRAM Controller
+           +-01.0  Red Hat, Inc. Virtio console
+           +-02.0  Red Hat, Inc. Virtio SCSI
+           +-03.0  Red Hat, Inc. Virtio RNG
+           +-04.0-[01]----00.0  NVIDIA Corporation Device 20b8
+           +-05.0-[02]----00.0  NVIDIA Corporation Device 20b8
+           +-06.0-[03]--
+           +-07.0-[04]--
+           +-08.0-[05]--
+           +-09.0-[06]--
+           +-0a.0-[07]--
+           +-0b.0-[08]--
+           +-0c.0-[09-0a]----00.0-[0a]--+-00.0  Mellanox Tech MT42822 BlueField-2 ConnectX-6
+           |                             \-01.0  Mellanox Tech MT42822 BlueField-2 ConnectX-6
+           +-0d.0  Red Hat, Inc. Virtio socket
+           +-0e.0  Red Hat, Inc. Virtio file system
+           +-1f.0  Intel Corporation 82801IB (ICH9) LPC Interface Controller
+           +-1f.2  Intel Corporation 82801IR/IO/IH (ICH9R/DO/DH) 6 port SATA Controller
+           \-1f.3  Intel Corporation 82801I (ICH9 Family) SMBus Controller
+```
+
+The PCI devices will consume a slot of which we have 256 in the PCI(e) topology
+and leave scarce resources for the needed PCI Express devices.

docs/design/vcpu-handling-runtime-rs.md

@@ -0,0 +1,51 @@
+# Virtual machine vCPU sizing in Kata Containers 3.0
+
+> Preview: 
+> [Kubernetes(since 1.23)][1] and [Containerd(since 1.6.0-beta4)][2] will help calculate `Sandbox Size` info and pass it to Kata Containers through annotations.
+> In order to adapt to this beneficial change and be compatible with the past, we have implemented the new vCPUs handling way in `runtime-rs`, which is slightly different from the original `runtime-go`'s design.
+
+## When do we need to handle vCPUs size?
+vCPUs sizing should be determined by the container workloads. So throughout the life cycle of Kata Containers, there are several points in time when we need to think about how many vCPUs should be at the time. Mainly including the time points of `CreateVM`, `CreateContainer`, `UpdateContainer`, and `DeleteContainer`.
+* `CreateVM`: When creating a sandbox, we need to know how many vCPUs to start the VM with.
+* `CreateContainer`: When creating a new container in the VM, we may need to hot-plug the vCPUs according to the requirements in container's spec.
+* `UpdateContainer`: When receiving the `UpdateContainer` request, we may need to update the vCPU resources according to the new requirements of the container.
+* `DeleteContainer`: When a container is removed from the VM, we may need to hot-unplug the vCPUs to reclaim the vCPU resources introduced by the container.
+
+## On what basis do we calculate the number of vCPUs?
+When Kata calculate the number of vCPUs, We have three data sources, the `default_vcpus` and `default_maxvcpus` specified in the configuration file (named `TomlConfig` later in the doc), the `io.kubernetes.cri.sandbox-cpu-quota` and `io.kubernetes.cri.sandbox-cpu-period` annotations passed by the upper layer runtime, and the corresponding CPU resource part in the container's spec for the container when `CreateContainer`/`UpdateContainer`/`DeleteContainer` is requested.
+
+Our understanding and priority of these resources are as follows, which will affect how we calculate the number of vCPUs later.
+
+* From `TomlConfig`:
+  * `default_vcpus`: default number of vCPUs when starting a VM.
+  * `default_maxvcpus`: maximum number of vCPUs.
+* From `Annotation`:
+  * `InitialSize`: we call the size of the resource passed from the annotations as `InitialSize`. Kubernetes will calculate the sandbox size according to the Pod's statement, which is the `InitialSize` here. This size should be the size we want to prioritize. 
+* From `Container Spec`:
+  * The amount of CPU resources that the Container wants to use will be declared through the spec. Including the aforementioned annotations, we mainly consider `cpu quota` and `cpuset` when calculating the number of vCPUs.
+  * `cpu quota`: `cpu quota` is the most common way to declare the amount of CPU resources. The number of vCPUs introduced by `cpu quota` declared in a container's spec is: `vCPUs = ceiling( quota / period )`.
+  * `cpuset`: `cpuset` is often used to bind the CPUs that tasks can run on. The number of vCPUs may introduced by `cpuset` declared in a container's spec is the number of CPUs specified in the set that do not overlap with other containers.
+
+
+## How to calculate and adjust the vCPUs size:
+There are two types of vCPUs that we need to consider, one is the number of vCPUs when starting the VM (named `Boot Size` in the doc). The second is the number of vCPUs when `CreateContainer`/`UpdateContainer`/`DeleteContainer` request is received (`Real-time Size` in the doc).
+
+### `Boot Size`
+The main considerations are `InitialSize` and `default_vcpus`. There are the following principles:
+`InitialSize` has priority over `default_vcpus` declared in `TomlConfig`.
+1. When there is such an annotation statement, the originally `default_vcpus` will be modified to the number of vCPUs in the `InitialSize` as the `Boot Size`. (Because not all runtimes support this annotation for the time being, we still keep the `default_cpus` in `TomlConfig`.)
+2. When the specs of all containers are aggregated for sandbox size calculation, the method is consistent with the calculation method of `InitialSize` here.
+
+### `Real-time Size`
+When we receive an OCI request, it may be for a single container. But what we have to consider is the number of vCPUs for the entire VM. So we will maintain a list. Every time there is a demand for adjustment, the entire list will be traversed to calculate a value for the number of vCPUs. In addition, there are the following principles:
+1. Do not cut computing power and try to keep the number of vCPUs specified by `InitialSize`.
+   * So the number of vCPUs after will not be less than the `Boot Size`.
+2. `cpu quota` takes precedence over `cpuset` and the setting history are took into account.
+   * We think quota describes the CPU time slice that a cgroup can use, and `cpuset` describes the actual CPU number that a cgroup can use. Quota can better describe the size of the CPU time slice that a cgroup actually wants to use. The `cpuset` only describes which CPUs the cgroup can use, but the cgroup can use the specified CPU but consumes a smaller time slice, so the quota takes precedence over the `cpuset`.
+   * On the one hand, when both `cpu quota` and `cpuset` are specified, we will calculate the number of vCPUs based on `cpu quota` and ignore `cpuset`. On the other hand, if `cpu quota` was used to control the number of vCPUs in the past, and only `cpuset` was updated during `UpdateContainer`, we will not adjust the number of vCPUs at this time.
+3. `StaticSandboxResourceMgmt` controls hotplug.
+   * Some VMMs and kernels of some architectures do not support hotplugging. We can accommodate this situation through `StaticSandboxResourceMgmt`. When `StaticSandboxResourceMgmt = true` is set, we don't make any further attempts to update the number of vCPUs after booting.
+
+
+[1]: https://github.com/kubernetes/kubernetes/pull/104886
+[2]: https://github.com/containerd/containerd/pull/6155

docs/how-to/README.md

@@ -45,3 +45,4 @@
 - [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)
+- [How to run Kata Containers with kinds of Block Volumes](how-to-run-kata-containers-with-kinds-of-Block-Volumes.md)

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

@@ -44,12 +44,11 @@ $ 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}"
+$ qemu_url="$(get_from_kata_deps "assets.hypervisor.qemu-snp-experimental.url")"
+$ qemu_tag="$(get_from_kata_deps "assets.hypervisor.qemu-snp-experimental.tag")"
+$ git clone "${qemu_url}"
 $ pushd qemu
-$ git checkout "${qemu_commit}"
+$ git checkout "${qemu_tag}"
 $ ./configure --enable-virtfs --target-list=x86_64-softmmu --enable-debug
 $ make -j "$(nproc)"
 $ popd

docs/how-to/how-to-run-kata-containers-with-kinds-of-Block-Volumes.md

@@ -0,0 +1,226 @@
+# A new way for Kata Containers to use Kinds of Block Volumes
+
+> **Note:** This guide is only available for runtime-rs with default Hypervisor Dragonball.
+> Now, other hypervisors are still ongoing, and it'll be updated when they're ready.
+
+
+## Background
+
+Currently, there is no widely applicable and convenient method available for users to use some kinds of backend storages, such as File on host based block volume, SPDK based volume or VFIO device based volume for Kata Containers, so we adopt [Proposal: Direct Block Device Assignment](https://github.com/kata-containers/kata-containers/blob/main/docs/design/direct-blk-device-assignment.md) to address it.
+
+## Solution
+
+According to the proposal, it requires to use the `kata-ctl direct-volume` command to add a direct assigned block volume device to the Kata Containers runtime. 
+
+And then with the help of method [get_volume_mount_info](https://github.com/kata-containers/kata-containers/blob/099b4b0d0e3db31b9054e7240715f0d7f51f9a1c/src/libs/kata-types/src/mount.rs#L95), get information from JSON file: `(mountinfo.json)` and parse them into structure [Direct Volume Info](https://github.com/kata-containers/kata-containers/blob/099b4b0d0e3db31b9054e7240715f0d7f51f9a1c/src/libs/kata-types/src/mount.rs#L70) which is used to save device-related information. 
+
+We only fill the `mountinfo.json`, such as `device` ,`volume_type`, `fs_type`, `metadata` and `options`, which correspond to the fields in [Direct Volume Info](https://github.com/kata-containers/kata-containers/blob/099b4b0d0e3db31b9054e7240715f0d7f51f9a1c/src/libs/kata-types/src/mount.rs#L70), to describe a device. 
+
+The JSON file `mountinfo.json` placed in a sub-path `/kubelet/kata-test-vol-001/volume001` which under fixed path `/run/kata-containers/shared/direct-volumes/`. 
+And the full path looks like: `/run/kata-containers/shared/direct-volumes/kubelet/kata-test-vol-001/volume001`, But for some security reasons. it is 
+encoded as `/run/kata-containers/shared/direct-volumes/L2t1YmVsZXQva2F0YS10ZXN0LXZvbC0wMDEvdm9sdW1lMDAx`.
+
+Finally, when running a Kata Containers with `ctr run --mount type=X, src=Y, dst=Z,,options=rbind:rw`, the `type=X` should be specified a proprietary type specifically designed for some kind of volume. 
+
+Now, supported types: 
+
+- `directvol` for direct volume
+- `vfiovol` for VFIO device based volume
+- `spdkvol` for SPDK/vhost-user based volume
+
+
+## Setup Device and Run a Kata-Containers
+
+### Direct Block Device Based Volume
+
+#### create raw block based backend storage
+
+> **Tips:** raw block based backend storage MUST be formatted with `mkfs`.
+
+```bash
+$ sudo dd if=/dev/zero of=/tmp/stor/rawdisk01.20g bs=1M count=20480
+$ sudo mkfs.ext4 /tmp/stor/rawdisk01.20g
+```
+
+#### setup direct block device for kata-containers
+
+```json
+{
+  "device": "/tmp/stor/rawdisk01.20g", 
+  "volume_type": "directvol", 
+  "fs_type": "ext4", 
+  "metadata":"{}", 
+  "options": []
+}
+```
+
+```bash
+$ sudo kata-ctl direct-volume add /kubelet/kata-direct-vol-002/directvol002 "{\"device\": \"/tmp/stor/rawdisk01.20g\", \"volume_type\": \"directvol\", \"fs_type\": \"ext4\", \"metadata\":"{}", \"options\": []}"
+$# /kubelet/kata-direct-vol-002/directvol002 <==> /run/kata-containers/shared/direct-volumes/W1lMa2F0ZXQva2F0YS10a2F0DAxvbC0wMDEvdm9sdW1lMDAx
+$ cat W1lMa2F0ZXQva2F0YS10a2F0DAxvbC0wMDEvdm9sdW1lMDAx/mountInfo.json 
+{"volume_type":"directvol","device":"/tmp/stor/rawdisk01.20g","fs_type":"ext4","metadata":{},"options":[]}
+```
+
+#### Run a Kata container with direct block device volume
+
+```bash
+$ # type=disrectvol,src=/kubelet/kata-direct-vol-002/directvol002,dst=/disk002,options=rbind:rw
+$ sudo ctr run -t --rm --runtime io.containerd.kata.v2 --mount type=directvol,src=/kubelet/kata-direct-vol-002/directvol002,dst=/disk002,options=rbind:rw "$image" kata-direct-vol-xx05302045 /bin/bash
+```
+
+
+### VFIO Device Based Block Volume
+
+#### create VFIO device based backend storage
+
+> **Tip:** It only supports `vfio-pci` based PCI device passthrough mode.
+
+In this scenario, the device's host kernel driver will be replaced by `vfio-pci`, and IOMMU group ID generated.
+And either device's BDF or its VFIO IOMMU group ID in `/dev/vfio/` is fine for "device" in `mountinfo.json`.
+
+```bash
+$ lspci -nn -k -s 45:00.1 
+45:00.1 SCSI storage controller 
+...
+Kernel driver in use: vfio-pci
+...
+$ ls /dev/vfio/110
+/dev/vfio/110
+$ ls /sys/kernel/iommu_groups/110/devices/
+0000:45:00.1
+```
+
+#### setup VFIO device for kata-containers
+
+First, configure the `mountinfo.json`, as below:
+
+- (1) device with `BB:DD:F`
+
+```json
+{
+  "device": "45:00.1",
+  "volume_type": "vfiovol", 
+  "fs_type": "ext4", 
+  "metadata":"{}", 
+  "options": []
+}
+```
+
+- (2) device with `DDDD:BB:DD:F`
+
+```json
+{
+  "device": "0000:45:00.1",
+  "volume_type": "vfiovol", 
+  "fs_type": "ext4", 
+  "metadata":"{}", 
+  "options": []
+}
+```
+
+- (3) device with `/dev/vfio/X`
+
+```json
+{
+  "device": "/dev/vfio/110", 
+  "volume_type": "vfiovol", 
+  "fs_type": "ext4", 
+  "metadata":"{}", 
+  "options": []
+}
+```
+
+Second, run kata-containers with device(`/dev/vfio/110`) as an example:
+
+```bash
+$ sudo kata-ctl direct-volume add /kubelet/kata-vfio-vol-003/vfiovol003 "{\"device\": \"/dev/vfio/110\", \"volume_type\": \"vfiovol\", \"fs_type\": \"ext4\", \"metadata\":"{}", \"options\": []}"
+$ # /kubelet/kata-vfio-vol-003/directvol003 <==> /run/kata-containers/shared/direct-volumes/F0va22F0ZvaS12F0YS10a2F0DAxvbC0F0ZXvdm9sdF0Z0YSx
+$ cat F0va22F0ZvaS12F0YS10a2F0DAxvbC0F0ZXvdm9sdF0Z0YSx/mountInfo.json 
+{"volume_type":"vfiovol","device":"/dev/vfio/110","fs_type":"ext4","metadata":{},"options":[]}
+```
+
+#### Run a Kata container with VFIO block device based volume
+
+```bash
+$ # type=disrectvol,src=/kubelet/kata-vfio-vol-003/vfiovol003,dst=/disk003,options=rbind:rw
+$ sudo ctr run -t --rm --runtime io.containerd.kata.v2 --mount type=vfiovol,src=/kubelet/kata-vfio-vol-003/vfiovol003,dst=/disk003,options=rbind:rw "$image" kata-vfio-vol-xx05302245 /bin/bash
+```
+
+
+### SPDK Device Based Block Volume
+
+SPDK vhost-user devices in runtime-rs, unlike runtime (golang version), there is no need to `mknod` device node under `/dev/` any more.
+Just using the `kata-ctl direct-volume add ..` to make a mount info config is enough.
+
+#### Run SPDK vhost target and Expose vhost block device
+
+Run a SPDK vhost target and get vhost-user block controller as an example:
+
+First, run SPDK vhost target:
+
+> **Tips:** If driver `vfio-pci` supported, you can run SPDK with `DRIVER_OVERRIDE=vfio-pci`
+> Otherwise, Just run without it `sudo HUGEMEM=4096 ./scripts/setup.sh`.
+
+```bash
+$ SPDK_DEVEL=/xx/spdk
+$ VHU_UDS_PATH=/tmp/vhu-targets
+$ RAW_DISKS=/xx/rawdisks
+$ # Reset first
+$ ${SPDK_DEVEL}/scripts/setup.sh reset
+$ sudo sysctl -w vm.nr_hugepages=2048
+$ #4G Huge Memory for spdk
+$ sudo HUGEMEM=4096 DRIVER_OVERRIDE=vfio-pci ${SPDK_DEVEL}/scripts/setup.sh
+$ sudo ${SPDK_DEVEL}/build/bin/spdk_tgt -S $VHU_UDS_PATH -s 1024 -m 0x3 &
+```
+
+Second, create a vhost controller:
+
+```bash
+$ sudo dd if=/dev/zero of=${RAW_DISKS}/rawdisk01.20g bs=1M count=20480
+$ sudo ${SPDK_DEVEL}/scripts/rpc.py bdev_aio_create ${RAW_DISKS}/rawdisk01.20g vhu-rawdisk01.20g 512
+$ sudo ${SPDK_DEVEL}/scripts/rpc.py vhost_create_blk_controller vhost-blk-rawdisk01.sock vhu-rawdisk01.20g
+```
+
+Here, a vhost controller `vhost-blk-rawdisk01.sock` is created, and the controller will
+be passed to Hypervisor, such as Dragonball, Cloud-Hypervisor, Firecracker or QEMU.
+
+
+#### setup vhost-user block device for kata-containers
+
+
+First, `mkdir` a sub-path `kubelet/kata-test-vol-001/` under `/run/kata-containers/shared/direct-volumes/`.
+
+Second, fill fields in `mountinfo.json`, it looks like as below:
+```json
+{
+  "device": "/tmp/vhu-targets/vhost-blk-rawdisk01.sock",
+  "volume_type": "spdkvol",
+  "fs_type": "ext4",
+  "metadata":"{}",
+  "options": []
+}
+```
+
+Third, with the help of `kata-ctl direct-volume` to add block device to generate `mountinfo.json`, and run a kata container with `--mount`.
+
+```bash
+$ # kata-ctl direct-volume add
+$ sudo kata-ctl direct-volume add /kubelet/kata-test-vol-001/volume001 "{\"device\": \"/tmp/vhu-targets/vhost-blk-rawdisk01.sock\", \"volume_type\":\"spdkvol\", \"fs_type\": \"ext4\", \"metadata\":"{}", \"options\": []}"
+$ # /kubelet/kata-test-vol-001/volume001 <==> /run/kata-containers/shared/direct-volumes/L2t1YmVsZXQva2F0YS10ZXN0LXZvbC0wMDEvdm9sdW1lMDAx
+$ cat L2t1YmVsZXQva2F0YS10ZXN0LXZvbC0wMDEvdm9sdW1lMDAx/mountInfo.json
+$ {"volume_type":"spdkvol","device":"/tmp/vhu-targets/vhost-blk-rawdisk01.sock","fs_type":"ext4","metadata":{},"options":[]}
+```
+
+As `/run/kata-containers/shared/direct-volumes/` is a fixed path , we will be able to run a kata pod with `--mount` and set
+`src` sub-path. And the `--mount` argument looks like: `--mount type=spdkvol,src=/kubelet/kata-test-vol-001/volume001,dst=/disk001`.
+
+
+#### Run a Kata container with SPDK vhost-user block device
+
+
+In the case, `ctr run --mount type=X, src=source, dst=dest`, the X will be set `spdkvol` which is a proprietary type specifically designed for SPDK volumes.
+
+```bash
+$ # ctr run with --mount type=spdkvol,src=/kubelet/kata-test-vol-001/volume001,dst=/disk001
+$ sudo ctr run -t --rm --runtime io.containerd.kata.v2 --mount type=spdkvol,src=/kubelet/kata-test-vol-001/volume001,dst=/disk001,options=rbind:rw "$image" kata-spdk-vol-xx0530 /bin/bash
+```

docs/how-to/how-to-run-rootless-vmm.md

@@ -1,5 +1,5 @@
 ## Introduction
-To improve security, Kata Container supports running the VMM process (currently only QEMU) as a non-`root` user.
+To improve security, Kata Container supports running the VMM process (QEMU and cloud-hypervisor) as a non-`root` user. 
 This document describes how to enable the rootless VMM mode and its limitations.
 
 ## Pre-requisites
@@ -27,7 +27,7 @@ Another necessary change is to move the hypervisor runtime files (e.g. `vhost-fs
 ## Limitations
 
 1. Only the VMM process is running as a non-root user. Other processes such as Kata Container shimv2 and `virtiofsd` still run as the root user.
-2. Currently, this feature is only supported in QEMU. Still need to bring it to Firecracker and Cloud Hypervisor (see https://github.com/kata-containers/kata-containers/issues/2567).
+2. Currently, this feature is only supported in QEMU and cloud-hypervisor. For firecracker, you can use jailer to run the VMM process with a non-root user.
 3. Certain features will not work when rootless VMM is enabled, including:
    1. Passing devices to the guest (`virtio-blk`, `virtio-scsi`) will not work if the non-privileged user does not have permission to access it (leading to a permission denied error). A more permissive permission (e.g. 666) may overcome this issue. However, you need to be aware of the potential security implications of reducing the security on such devices.
    2. `vfio` device will also not work because of permission denied error.

docs/install/README.md

@@ -19,7 +19,6 @@ Packaged installation methods uses your distribution's native package format (su
 |------------------------------------------------------|----------------------------------------------------------------------------------------------|-------------------|-----------------------------------------------------------------------------------------------|
 | [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. | 
 | [Using official distro packages](#official-packages) | Kata packages provided by Linux distributions official repositories                          | yes               | Recommended for most users.                                                                   |
-| [Using snap](#snap-installation)                     | Easy to install                                                                              | yes               | Good alternative to official distro packages.                                                 |
 | [Automatic](#automatic-installation)                 | Run a single command to install a full system                                                | **No!**           | For those wanting the latest release quickly.                                                 |
 | [Manual](#manual-installation)                       | Follow a guide step-by-step to install a working system                                      | **No!**           | For those who want the latest release with more control.                                      |
 | [Build from source](#build-from-source-installation) | Build the software components manually                                                       | **No!**           | Power users and developers only.                                                              |
@@ -42,12 +41,6 @@ Kata packages are provided by official distribution repositories for:
 | [CentOS](centos-installation-guide.md)                   | 8                                                                              |
 | [Fedora](fedora-installation-guide.md)                   | 34                                                                             |
 
-### Snap Installation
-
-The snap installation is available for all distributions which support `snapd`.
-
-[Use snap](snap-installation-guide.md) to install Kata Containers from https://snapcraft.io.
-
 ### Automatic Installation
 
 [Use `kata-manager`](/utils/README.md) to automatically install a working Kata Containers system.

docs/install/aws-installation-guide.md

@@ -123,7 +123,7 @@ Refer to [this guide](https://docs.aws.amazon.com/cli/latest/userguide/cli-ec2-l
 SSH into the machine
 
 ```bash
-$ ssh -i MyKeyPair.pen ubuntu@${IP}
+$ ssh -i MyKeyPair.pem ubuntu@${IP}
 ```
 
 Go onto the next step.

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

@@ -26,7 +26,6 @@ architectures:
 |------------------------------------------------------|----------------------------------------------------------------------------------------------|-------------------|-----------------------------------------------------------------------------------------------|----------- |
 | [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 |
 | [Manual](#manual-installation)                       | Follow a guide step-by-step to install a working system                                      | **No!**           | For those who want the latest release with more control.                                      | No |
 | [Build from source](#build-from-source-installation) | Build the software components manually                                                       | **No!**           | Power users and developers only.  | Yes |              
@@ -36,8 +35,6 @@ architectures:
 Follow the [`kata-deploy`](../../tools/packaging/kata-deploy/README.md).
 ### Official packages
 `ToDo`
-### Snap Installation
-`ToDo`
 ### Automatic Installation
 `ToDo`
 ### Manual Installation
@@ -49,14 +46,14 @@ Follow the [`kata-deploy`](../../tools/packaging/kata-deploy/README.md).
 
 * Download `Rustup` and install  `Rust`
     > **Notes:**
-    > Rust version 1.62.0 is needed
+    > For Rust version, please set `RUST_VERSION` to the value of `languages.rust.meta.newest-version key` in [`versions.yaml`](../../versions.yaml) or, if `yq` is available on your system, run `export RUST_VERSION=$(yq read versions.yaml languages.rust.meta.newest-version)`.
 
     Example for `x86_64`
     ```
     $ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
     $ source $HOME/.cargo/env
-    $ rustup install 1.62.0
-    $ rustup default 1.62.0-x86_64-unknown-linux-gnu
+    $ rustup install ${RUST_VERSION}
+    $ rustup default ${RUST_VERSION}-x86_64-unknown-linux-gnu
     ```
 
 * Musl support for fully static binary

docs/install/snap-installation-guide.md

@@ -1,52 +0,0 @@
-# Kata Containers snap package
-
-## Install Kata Containers
-
-Kata Containers can be installed in any Linux distribution that supports
-[snapd](https://docs.snapcraft.io/installing-snapd).
-
-Run the following command to install **Kata Containers**:
-
-```sh
-$ sudo snap install kata-containers --stable --classic
-```
-
-## Configure Kata Containers
-
-By default Kata Containers snap image is mounted at `/snap/kata-containers` as a
-read-only file system, therefore default configuration file can not be edited.
-Fortunately Kata Containers supports loading a configuration file from another
-path than the default.
-
-```sh
-$ sudo mkdir -p /etc/kata-containers
-$ sudo cp /snap/kata-containers/current/usr/share/defaults/kata-containers/configuration.toml /etc/kata-containers/
-$ $EDITOR /etc/kata-containers/configuration.toml
-```
-
-## Integration with shim v2 Container Engines
-
-The Container engine daemon (`cri-o`, `containerd`, etc) needs to be able to find the
-`containerd-shim-kata-v2` binary to allow Kata Containers to be created.
-Run the following command to create a symbolic link to the shim v2 binary.
-
-```sh
-$ sudo ln -sf /snap/kata-containers/current/usr/bin/containerd-shim-kata-v2 /usr/local/bin/containerd-shim-kata-v2
-```
-
-Once the symbolic link has been created and the engine daemon configured, `io.containerd.kata.v2`
-can be used as runtime.
-
-Read the following documents to know how to run Kata Containers 2.x with `containerd`.
-
-* [How to use Kata Containers and Containerd](../how-to/containerd-kata.md)
-* [Install Kata Containers with containerd](./container-manager/containerd/containerd-install.md)
-
-
-## Remove Kata Containers snap package
-
-Run the following command to remove the Kata Containers snap:
-
-```sh
-$ sudo snap remove kata-containers
-```

snap/local/README.md

@@ -1,101 +0,0 @@
-# Kata Containers snap image
-
-This directory contains the resources needed to build the Kata Containers
-[snap][1] image.
-
-## Initial setup
-
-Kata Containers can be installed in any Linux distribution that supports
-[snapd](https://docs.snapcraft.io/installing-snapd). For this example, we
-assume Ubuntu as your base distro.
-```sh
-$ sudo apt-get --no-install-recommends install -y apt-utils ca-certificates snapd snapcraft
-```
-
-## Install snap
-
-You can install the Kata Containers snap from the [snapcraft store][8] or by running the following command:
-
-```sh
-$ sudo snap install kata-containers --classic
-```
-
-## Build and install snap image
-
-Run the command below which will use the packaging Makefile to build the snap image:
-
-```sh
-$ make -C tools/packaging snap
-```
-
-> **Warning:**
->
-> By default, `snapcraft` will create a clean virtual machine
-> environment to build the snap in using the `multipass` tool.
->
-> However, `multipass` is silently disabled when `--destructive-mode` is
-> used.
->
-> Since building the Kata Containers package currently requires
-> `--destructive-mode`, the snap will be built using the host
-> environment. To avoid parts of the build auto-detecting additional
-> features to enable (for example for QEMU), we recommend that you
-> only run the snap build in a minimal host environment.
-
-To install the resulting snap image, snap must be put in [classic mode][3] and the
-security confinement must be disabled (`--classic`). Also since the resulting snap
-has not been signed the verification of signature must be omitted (`--dangerous`).
-
-```sh
-$ sudo snap install --classic --dangerous "kata-containers_${version}_${arch}.snap"
-```
-
-Replace `${version}` with the current version of Kata Containers and `${arch}` with
-the system architecture.
-
-## Configure Kata Containers
-
-By default Kata Containers snap image is mounted at `/snap/kata-containers` as a
-read-only file system, therefore default configuration file can not be edited.
-Fortunately [`kata-runtime`][4] supports loading a configuration file from another
-path than the default.
-
-```sh
-$ sudo mkdir -p /etc/kata-containers
-$ sudo cp /snap/kata-containers/current/usr/share/defaults/kata-containers/configuration.toml /etc/kata-containers/
-$ $EDITOR /etc/kata-containers/configuration.toml
-```
-
-## Integration with docker and Kubernetes
-
-The path to the runtime provided by the Kata Containers snap image is
-`/snap/kata-containers/current/usr/bin/kata-runtime`. You should use it to
-run Kata Containers with [docker][9] and [Kubernetes][10].
-
-## Remove snap
-
-You can remove the Kata Containers snap by running the following command:
-
-```sh
-$ sudo snap remove kata-containers
-```
-
-## Limitations
-
-The [miniOS image][2] is not included in the snap image as it is not possible for
-QEMU to open a guest RAM backing store on a read-only filesystem. Fortunately,
-you can start Kata Containers with a Linux initial RAM disk (initrd) that is
-included in the snap image. If you want to use the miniOS image instead of initrd,
-then a new configuration file can be [created](#configure-kata-containers)
-and [configured][7].
-
-[1]: https://docs.snapcraft.io/snaps/intro
-[2]: ../../docs/design/architecture/README.md#root-filesystem-image
-[3]: https://docs.snapcraft.io/reference/confinement#classic
-[4]: https://github.com/kata-containers/kata-containers/tree/main/src/runtime#configuration
-[5]: https://docs.docker.com/engine/reference/commandline/dockerd
-[6]: ../../docs/install/docker/ubuntu-docker-install.md
-[7]: ../../docs/Developer-Guide.md#configure-to-use-initrd-or-rootfs-image
-[8]: https://snapcraft.io/kata-containers
-[9]: ../../docs/Developer-Guide.md#run-kata-containers-with-docker
-[10]: ../../docs/Developer-Guide.md#run-kata-containers-with-kubernetes

snap/local/snap-common.sh

@@ -1,114 +0,0 @@
-#!/usr/bin/env bash
-#
-# Copyright (c) 2022 Intel Corporation
-#
-# SPDX-License-Identifier: Apache-2.0
-
-# Description: Idempotent script to be sourced by all parts in a
-#   snapcraft config file.
-
-set -o errexit
-set -o nounset
-set -o pipefail
-
-# XXX: Bash-specific code. zsh doesn't support this option and that *does*
-# matter if this script is run sourced... since it'll be using zsh! ;)
-[ -n "$BASH_VERSION" ] && set -o errtrace
-
-[ -n "${DEBUG:-}" ] && set -o xtrace
-
-die()
-{
-	echo >&2 "ERROR: $0: $*"
-}
-
-[ -n "${SNAPCRAFT_STAGE:-}" ] ||\
-	die "must be sourced from a snapcraft config file"
-
-snap_yq_version=3.4.1
-
-snap_common_install_yq()
-{
-      export yq="${SNAPCRAFT_STAGE}/bin/yq"
-
-      local yq_pkg
-      yq_pkg="github.com/mikefarah/yq"
-
-      local yq_url
-      yq_url="https://${yq_pkg}/releases/download/${snap_yq_version}/yq_${goos}_${goarch}"
-      curl -o "${yq}" -L "${yq_url}"
-      chmod +x "${yq}"
-}
-
-# Function that should be called for each snap "part" in
-# snapcraft.yaml.
-snap_common_main()
-{
-	# Architecture
-	arch="$(uname -m)"
-
-	case "${arch}" in
-		aarch64)
-			goarch="arm64"
-			qemu_arch="${arch}"
-			;;
-
-		ppc64le)
-			goarch="ppc64le"
-			qemu_arch="ppc64"
-			;;
-
-		s390x)
-			goarch="${arch}"
-			qemu_arch="${arch}"
-			;;
-
-		x86_64)
-			goarch="amd64"
-			qemu_arch="${arch}"
-			;;
-
-		*) die "unsupported architecture: ${arch}" ;;
-	esac
-
-	dpkg_arch=$(dpkg --print-architecture)
-
-	# golang
-	#
-	# We need the O/S name in golang format, but since we don't
-	# know if the godeps part has run, we don't know if golang is
-	# available yet, hence fall back to a standard system command.
-	goos="$(go env GOOS &>/dev/null || true)"
-	[ -z "$goos" ] && goos=$(uname -s|tr '[A-Z]' '[a-z]')
-
-	export GOROOT="${SNAPCRAFT_STAGE}"
-	export GOPATH="${GOROOT}/gopath"
-	export GO111MODULE="auto"
-
-	mkdir -p "${GOPATH}/bin"
-	export PATH="${GOPATH}/bin:${PATH}"
-
-	# Proxy
-	export http_proxy="${http_proxy:-}"
-	export https_proxy="${https_proxy:-}"
-
-	# Binaries
-	mkdir -p "${SNAPCRAFT_STAGE}/bin"
-
-	export PATH="$PATH:${SNAPCRAFT_STAGE}/bin"
-
-	# YAML query tool
-	export yq="${SNAPCRAFT_STAGE}/bin/yq"
-
-	# Kata paths
-	export kata_dir=$(printf "%s/src/github.com/%s/%s" \
-		"${GOPATH}" \
-		"${SNAPCRAFT_PROJECT_NAME}" \
-		"${SNAPCRAFT_PROJECT_NAME}")
-
-	export versions_file="${kata_dir}/versions.yaml"
-
-	[ -n "${yq:-}" ] && [ -x "${yq:-}" ] || snap_common_install_yq
-}
-
-snap_common_main

snap/snapcraft.yaml

@@ -1,371 +0,0 @@
-name: kata-containers
-website: https://github.com/kata-containers/kata-containers
-summary: Build lightweight VMs that seamlessly plug into the containers ecosystem
-description: |
-  Kata Containers is an open source project and community working to build a
-  standard implementation of lightweight Virtual Machines (VMs) that feel and
-  perform like containers, but provide the workload isolation and security
-  advantages of VMs
-confinement: classic
-adopt-info: metadata
-base: core20
-
-parts:
-  metadata:
-    plugin: nil
-    prime:
-      - -*
-    build-packages:
-      - git
-      - git-extras
-    override-pull: |
-      source "${SNAPCRAFT_PROJECT_DIR}/snap/local/snap-common.sh"
-
-      version="9999"
-
-      if echo "${GITHUB_REF:-}" | grep -q -E "^refs/tags"; then
-        version=$(echo ${GITHUB_REF:-} | cut -d/ -f3)
-        git checkout ${version}
-      fi
-
-      snapcraftctl set-grade "stable"
-      snapcraftctl set-version "${version}"
-
-      mkdir -p $(dirname ${kata_dir})
-      ln -sf $(realpath "${SNAPCRAFT_STAGE}/..") ${kata_dir}
-
-  godeps:
-    after: [metadata]
-    plugin: nil
-    prime:
-      - -*
-    build-packages:
-      - curl
-    override-build: |
-      source "${SNAPCRAFT_PROJECT_DIR}/snap/local/snap-common.sh"
-
-      # put everything in stage
-      cd "${SNAPCRAFT_STAGE}"
-
-      version="$(${yq} r ${kata_dir}/versions.yaml languages.golang.meta.newest-version)"
-      tarfile="go${version}.${goos}-${goarch}.tar.gz"
-      curl -LO https://golang.org/dl/${tarfile}
-      tar -xf ${tarfile} --strip-components=1
-
-  rustdeps:
-    after: [metadata]
-    plugin: nil
-    prime:
-      - -*
-    build-packages:
-      - curl
-    override-build: |
-      source "${SNAPCRAFT_PROJECT_DIR}/snap/local/snap-common.sh"
-
-      # put everything in stage
-      cd "${SNAPCRAFT_STAGE}"
-
-      version="$(${yq} r ${kata_dir}/versions.yaml languages.rust.meta.newest-version)"
-      if ! command -v rustup > /dev/null; then
-        curl https://sh.rustup.rs -sSf | sh -s -- -y --default-toolchain ${version}
-      fi
-
-      export PATH=${PATH}:${HOME}/.cargo/bin
-      rustup toolchain install ${version}
-      rustup default ${version}
-      if [ "${arch}" == "ppc64le" ] || [ "${arch}" == "s390x" ] ; then
-        [ "${arch}" == "ppc64le" ] && arch="powerpc64le"
-        rustup target add ${arch}-unknown-linux-gnu
-      else
-        rustup target add ${arch}-unknown-linux-musl
-        $([ "$(whoami)" != "root" ] && echo sudo) ln -sf /usr/bin/g++ /bin/musl-g++
-      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 $USER docker
-      echo "Starting docker"
-      sudo -E systemctl start docker || true
-
-  image:
-    after: [godeps, docker, qemu, kernel]
-    plugin: nil
-    build-packages:
-      - docker.io
-      - cpio
-      - git
-      - iptables
-      - software-properties-common
-      - uidmap
-      - gnupg2
-    override-build: |
-      source "${SNAPCRAFT_PROJECT_DIR}/snap/local/snap-common.sh"
-
-      [ "${arch}" = "ppc64le" ] || [ "${arch}" = "s390x" ] && sudo apt-get --no-install-recommends install -y protobuf-compiler
-
-      if [ -n "$http_proxy" ]; then
-        echo "Setting proxy $http_proxy"
-        sudo -E systemctl set-environment http_proxy="$http_proxy" || true
-        sudo -E systemctl set-environment https_proxy="$https_proxy" || true
-      fi
-
-      # Copy yq binary. It's used in the container
-      cp -a "${yq}" "${GOPATH}/bin/"
-
-      cd "${kata_dir}/tools/osbuilder"
-
-      # build image
-      export AGENT_INIT=yes
-      export USE_DOCKER=1
-      export DEBUG=1
-      initrd_distro=$(${yq} r -X ${kata_dir}/versions.yaml assets.initrd.architecture.${arch}.name)
-      image_distro=$(${yq} r -X ${kata_dir}/versions.yaml assets.image.architecture.${arch}.name)
-      case "$arch" in
-        x86_64)
-          # In some build systems it's impossible to build a rootfs image, try with the initrd image
-          sudo -E PATH=$PATH make image DISTRO="${image_distro}" || sudo -E PATH="$PATH" make initrd DISTRO="${initrd_distro}"
-        ;;
-
-        aarch64|ppc64le|s390x)
-          sudo -E PATH="$PATH" make initrd DISTRO="${initrd_distro}"
-        ;;
-
-        *) die "unsupported architecture: ${arch}" ;;
-      esac
-
-      # Install image
-      kata_image_dir="${SNAPCRAFT_PART_INSTALL}/usr/share/kata-containers"
-      mkdir -p "${kata_image_dir}"
-      cp kata-containers*.img "${kata_image_dir}"
-
-  runtime:
-    after: [godeps, image, cloud-hypervisor]
-    plugin: nil
-    build-attributes: [no-patchelf]
-    override-build: |
-      source "${SNAPCRAFT_PROJECT_DIR}/snap/local/snap-common.sh"
-
-      cd "${kata_dir}/src/runtime"
-
-      qemu_cmd="qemu-system-${qemu_arch}"
-
-      # build and install runtime
-      make \
-        PREFIX="/snap/${SNAPCRAFT_PROJECT_NAME}/current/usr" \
-        SKIP_GO_VERSION_CHECK=1 \
-        QEMUCMD="${qemu_cmd}"
-
-      make install \
-        PREFIX=/usr \
-        DESTDIR="${SNAPCRAFT_PART_INSTALL}" \
-        SKIP_GO_VERSION_CHECK=1 \
-        QEMUCMD="${qemu_cmd}"
-
-      if [ ! -f ${SNAPCRAFT_PART_INSTALL}/../../image/install/usr/share/kata-containers/kata-containers.img ]; then
-        sed -i -e "s|^image =.*|initrd = \"/snap/${SNAPCRAFT_PROJECT_NAME}/current/usr/share/kata-containers/kata-containers-initrd.img\"|" \
-          ${SNAPCRAFT_PART_INSTALL}/usr/share/defaults/${SNAPCRAFT_PROJECT_NAME}/configuration.toml
-      fi
-
-  kernel:
-    after: [godeps]
-    plugin: nil
-    build-packages:
-      - libelf-dev
-      - curl
-      - build-essential
-      - bison
-      - flex
-    override-build: |
-      source "${SNAPCRAFT_PROJECT_DIR}/snap/local/snap-common.sh"
-
-      kernel_version="$(${yq} r $versions_file assets.kernel.version)"
-      #Remove extra 'v'
-      kernel_version="${kernel_version#v}"
-
-      [ "${arch}" = "s390x" ] && sudo apt-get --no-install-recommends install -y libssl-dev
-
-      cd "${kata_dir}/tools/packaging/kernel"
-      kernel_dir_prefix="kata-linux-"
-
-      # Setup and build kernel
-      ./build-kernel.sh -v "${kernel_version}" -d setup
-      cd ${kernel_dir_prefix}*
-      make -j $(nproc ${CI:+--ignore 1}) EXTRAVERSION=".container"
-
-      kernel_suffix="${kernel_version}.container"
-      kata_kernel_dir="${SNAPCRAFT_PART_INSTALL}/usr/share/kata-containers"
-      mkdir -p "${kata_kernel_dir}"
-
-      # Install bz kernel
-      make install INSTALL_PATH="${kata_kernel_dir}" EXTRAVERSION=".container" || true
-      vmlinuz_name="vmlinuz-${kernel_suffix}"
-      ln -sf "${vmlinuz_name}" "${kata_kernel_dir}/vmlinuz.container"
-
-      # Install raw kernel
-      vmlinux_path="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}" "${kata_kernel_dir}/vmlinux.container"
-
-  qemu:
-    plugin: make
-    after: [godeps]
-    build-packages:
-      - gcc
-      - python3
-      - zlib1g-dev
-      - libcap-ng-dev
-      - libglib2.0-dev
-      - libpixman-1-dev
-      - libnuma-dev
-      - libltdl-dev
-      - libcap-dev
-      - libattr1-dev
-      - libfdt-dev
-      - curl
-      - libcapstone-dev
-      - bc
-      - libblkid-dev
-      - libffi-dev
-      - libmount-dev
-      - libseccomp-dev
-      - libselinux1-dev
-      - ninja-build
-    override-build: |
-      source "${SNAPCRAFT_PROJECT_DIR}/snap/local/snap-common.sh"
-
-      branch="$(${yq} r ${versions_file} assets.hypervisor.qemu.version)"
-      url="$(${yq} r ${versions_file} assets.hypervisor.qemu.url)"
-      commit=""
-      patches_dir="${kata_dir}/tools/packaging/qemu/patches/$(echo ${branch} | sed -e 's/.[[:digit:]]*$//' -e 's/^v//').x"
-      patches_version_dir="${kata_dir}/tools/packaging/qemu/patches/tag_patches/${branch}"
-
-      # download source
-      qemu_dir="${SNAPCRAFT_STAGE}/qemu"
-      rm -rf "${qemu_dir}"
-      git clone --depth 1 --branch ${branch} --single-branch ${url} "${qemu_dir}"
-      cd "${qemu_dir}"
-      [ -z "${commit}" ] || git checkout "${commit}"
-
-      [ -n "$(ls -A ui/keycodemapdb)" ] || git clone --depth 1 https://github.com/qemu/keycodemapdb ui/keycodemapdb/
-      [ -n "$(ls -A capstone)" ] || git clone --depth 1 https://github.com/qemu/capstone capstone
-
-      # Apply branch patches
-      [ -d "${patches_version_dir}" ] || mkdir "${patches_version_dir}"
-      ${kata_dir}/tools/packaging/scripts/apply_patches.sh "${patches_dir}"
-      ${kata_dir}/tools/packaging/scripts/apply_patches.sh "${patches_version_dir}"
-
-      # Only x86_64 supports libpmem
-      [ "${arch}" = "x86_64" ] && sudo apt-get --no-install-recommends install -y apt-utils ca-certificates libpmem-dev
-
-      configure_hypervisor="${kata_dir}/tools/packaging/scripts/configure-hypervisor.sh"
-      chmod +x "${configure_hypervisor}"
-      # static build. The --prefix, --libdir, --libexecdir, --datadir arguments are
-      # based on PREFIX and set by configure-hypervisor.sh
-      echo "$(PREFIX=/snap/${SNAPCRAFT_PROJECT_NAME}/current/usr ${configure_hypervisor} -s kata-qemu) \
-        --disable-rbd " \
-        | xargs ./configure
-
-      # Copy QEMU configurations (Kconfigs)
-      case "${branch}" in
-      "v5.1.0")
-        cp -a "${kata_dir}"/tools/packaging/qemu/default-configs/* default-configs
-        ;;
-
-      *)
-        cp -a "${kata_dir}"/tools/packaging/qemu/default-configs/* configs/devices/
-        ;;
-      esac
-
-      # build and install
-      make -j $(nproc ${CI:+--ignore 1})
-      make install DESTDIR="${SNAPCRAFT_PART_INSTALL}"
-    prime:
-      - -snap/
-      - -usr/bin/qemu-ga
-      - -usr/bin/qemu-pr-helper
-      - -usr/bin/virtfs-proxy-helper
-      - -usr/include/
-      - -usr/share/applications/
-      - -usr/share/icons/
-      - -usr/var/
-      - usr/*
-      - lib/*
-    organize:
-      # Hack: move qemu to /
-      "snap/kata-containers/current/": "./"
-
-  virtiofsd:
-    plugin: nil
-    after: [godeps, rustdeps, docker]
-    override-build: |
-      source "${SNAPCRAFT_PROJECT_DIR}/snap/local/snap-common.sh"
-
-      echo "INFO: Building rust version of virtiofsd"
-
-      cd "${SNAPCRAFT_PROJECT_DIR}"
-      # Clean-up build dir in case it already exists
-      sudo -E NO_TTY=true make virtiofsd-tarball
-
-      sudo install \
-        --owner='root' \
-        --group='root' \
-        --mode=0755 \
-        -D \
-        --target-directory="${SNAPCRAFT_PART_INSTALL}/usr/libexec/" \
-        build/virtiofsd/builddir/virtiofsd/virtiofsd
-
-  cloud-hypervisor:
-    plugin: nil
-    after: [godeps, docker]
-    override-build: |
-      source "${SNAPCRAFT_PROJECT_DIR}/snap/local/snap-common.sh"
-
-      if [ "${arch}" == "aarch64" ] || [ "${arch}" == "x86_64" ]; then
-          cd "${SNAPCRAFT_PROJECT_DIR}"
-          sudo -E NO_TTY=true make cloud-hypervisor-tarball
-
-          tarfile="${SNAPCRAFT_PROJECT_DIR}/tools/packaging/kata-deploy/local-build/build/kata-static-cloud-hypervisor.tar.xz"
-          tmpdir=$(mktemp -d)
-
-          tar -xvJpf "${tarfile}" -C "${tmpdir}"
-
-          install -D "${tmpdir}/opt/kata/bin/cloud-hypervisor" "${SNAPCRAFT_PART_INSTALL}/usr/bin/cloud-hypervisor"
-
-          rm -rf "${tmpdir}"
-      fi
-
-apps:
-  runtime:
-    command: usr/bin/kata-runtime
-  shim:
-    command: usr/bin/containerd-shim-kata-v2
-  collect-data:
-    command: usr/bin/kata-collect-data.sh

src/agent/Cargo.lock

@@ -422,6 +422,16 @@ dependencies = [
  "dirs-sys",
 ]
 
+[[package]]
+name = "dirs-next"
+version = "2.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b98cf8ebf19c3d1b223e151f99a4f9f0690dca41414773390fc824184ac833e1"
+dependencies = [
+ "cfg-if 1.0.0",
+ "dirs-sys-next",
+]
+
 [[package]]
 name = "dirs-sys"
 version = "0.3.7"
@@ -433,6 +443,17 @@ dependencies = [
  "winapi",
 ]
 
+[[package]]
+name = "dirs-sys-next"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4ebda144c4fe02d1f7ea1a7d9641b6fc6b580adcfa024ae48797ecdeb6825b4d"
+dependencies = [
+ "libc",
+ "redox_users",
+ "winapi",
+]
+
 [[package]]
 name = "either"
 version = "1.6.1"
@@ -495,7 +516,7 @@ checksum = "ec3245a0ca564e7f3c797d20d833a6870f57a728ac967d5225b3ffdef4465011"
 dependencies = [
  "lazy_static",
  "log",
- "rand 0.8.5",
+ "rand",
 ]
 
 [[package]]
@@ -633,17 +654,6 @@ dependencies = [
  "slab",
 ]
 
-[[package]]
-name = "getrandom"
-version = "0.1.16"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8fc3cb4d91f53b50155bdcfd23f6a4c39ae1969c2ae85982b135750cccaf5fce"
-dependencies = [
- "cfg-if 1.0.0",
- "libc",
- "wasi 0.9.0+wasi-snapshot-preview1",
-]
-
 [[package]]
 name = "getrandom"
 version = "0.2.7"
@@ -801,6 +811,7 @@ dependencies = [
  "async-recursion",
  "async-trait",
  "capctl",
+ "cfg-if 1.0.0",
  "cgroups-rs",
  "clap",
  "futures",
@@ -818,7 +829,7 @@ dependencies = [
  "opentelemetry",
  "procfs",
  "prometheus",
- "protobuf",
+ "protobuf 3.2.0",
  "protocols",
  "regex",
  "rtnetlink",
@@ -831,6 +842,7 @@ dependencies = [
  "slog",
  "slog-scope",
  "slog-stdlog",
+ "slog-term",
  "tempfile",
  "test-utils",
  "thiserror",
@@ -849,6 +861,7 @@ dependencies = [
 name = "kata-sys-util"
 version = "0.1.0"
 dependencies = [
+ "anyhow",
  "byteorder",
  "cgroups-rs",
  "chrono",
@@ -860,7 +873,7 @@ dependencies = [
  "nix 0.24.2",
  "oci",
  "once_cell",
- "rand 0.7.3",
+ "rand",
  "serde_json",
  "slog",
  "slog-scope",
@@ -881,6 +894,7 @@ dependencies = [
  "num_cpus",
  "oci",
  "regex",
+ "safe-path",
  "serde",
  "serde_json",
  "slog",
@@ -947,6 +961,7 @@ dependencies = [
  "slog-async",
  "slog-json",
  "slog-scope",
+ "slog-term",
 ]
 
 [[package]]
@@ -1182,7 +1197,7 @@ dependencies = [
  "lazy_static",
  "percent-encoding",
  "pin-project",
- "rand 0.8.5",
+ "rand",
  "serde",
  "thiserror",
  "tokio",
@@ -1430,7 +1445,7 @@ dependencies = [
  "memchr",
  "parking_lot 0.12.1",
  "procfs",
- "protobuf",
+ "protobuf 2.27.1",
  "thiserror",
 ]
 
@@ -1490,9 +1505,16 @@ name = "protobuf"
 version = "2.27.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cf7e6d18738ecd0902d30d1ad232c9125985a3422929b16c65517b38adc14f96"
+
+[[package]]
+name = "protobuf"
+version = "3.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b55bad9126f378a853655831eb7363b7b01b81d19f8cb1218861086ca4a1a61e"
 dependencies = [
- "serde",
- "serde_derive",
+ "once_cell",
+ "protobuf-support",
+ "thiserror",
 ]
 
 [[package]]
@@ -1501,17 +1523,47 @@ version = "2.27.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "aec1632b7c8f2e620343439a7dfd1f3c47b18906c4be58982079911482b5d707"
 dependencies = [
- "protobuf",
+ "protobuf 2.27.1",
 ]
 
 [[package]]
-name = "protobuf-codegen-pure"
-version = "2.27.1"
+name = "protobuf-codegen"
+version = "3.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9f8122fdb18e55190c796b088a16bdb70cd7acdcd48f7a8b796b58c62e532cc6"
+checksum = "0dd418ac3c91caa4032d37cb80ff0d44e2ebe637b2fb243b6234bf89cdac4901"
 dependencies = [
- "protobuf",
- "protobuf-codegen",
+ "anyhow",
+ "once_cell",
+ "protobuf 3.2.0",
+ "protobuf-parse",
+ "regex",
+ "tempfile",
+ "thiserror",
+]
+
+[[package]]
+name = "protobuf-parse"
+version = "3.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9d39b14605eaa1f6a340aec7f320b34064feb26c93aec35d6a9a2272a8ddfa49"
+dependencies = [
+ "anyhow",
+ "indexmap",
+ "log",
+ "protobuf 3.2.0",
+ "protobuf-support",
+ "tempfile",
+ "thiserror",
+ "which",
+]
+
+[[package]]
+name = "protobuf-support"
+version = "3.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a5d4d7b8601c814cfb36bcebb79f0e61e45e1e93640cf778837833bbed05c372"
+dependencies = [
+ "thiserror",
 ]
 
 [[package]]
@@ -1520,7 +1572,7 @@ version = "0.1.0"
 dependencies = [
  "async-trait",
  "oci",
- "protobuf",
+ "protobuf 3.2.0",
  "ttrpc",
  "ttrpc-codegen",
 ]
@@ -1534,19 +1586,6 @@ dependencies = [
  "proc-macro2",
 ]
 
-[[package]]
-name = "rand"
-version = "0.7.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6a6b1679d49b24bbfe0c803429aa1874472f50d9b363131f0e89fc356b544d03"
-dependencies = [
- "getrandom 0.1.16",
- "libc",
- "rand_chacha 0.2.2",
- "rand_core 0.5.1",
- "rand_hc",
-]
-
 [[package]]
 name = "rand"
 version = "0.8.5"
@@ -1554,18 +1593,8 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
 dependencies = [
  "libc",
- "rand_chacha 0.3.1",
- "rand_core 0.6.3",
-]
-
-[[package]]
-name = "rand_chacha"
-version = "0.2.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f4c8ed856279c9737206bf725bf36935d8666ead7aa69b52be55af369d193402"
-dependencies = [
- "ppv-lite86",
- "rand_core 0.5.1",
+ "rand_chacha",
+ "rand_core",
 ]
 
 [[package]]
@@ -1575,16 +1604,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88"
 dependencies = [
  "ppv-lite86",
- "rand_core 0.6.3",
-]
-
-[[package]]
-name = "rand_core"
-version = "0.5.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "90bde5296fc891b0cef12a6d03ddccc162ce7b2aff54160af9338f8d40df6d19"
-dependencies = [
- "getrandom 0.1.16",
+ "rand_core",
 ]
 
 [[package]]
@@ -1593,16 +1613,7 @@ version = "0.6.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d34f1408f55294453790c48b2f1ebbb1c5b4b7563eb1f418bcfcfdbb06ebb4e7"
 dependencies = [
- "getrandom 0.2.7",
-]
-
-[[package]]
-name = "rand_hc"
-version = "0.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ca3129af7b92a17112d59ad498c6f81eaf463253766b90396d39ea7a39d6613c"
-dependencies = [
- "rand_core 0.5.1",
+ "getrandom",
 ]
 
 [[package]]
@@ -1620,7 +1631,7 @@ version = "0.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b033d837a7cf162d7993aded9304e30a83213c648b6e389db233191f891e5c2b"
 dependencies = [
- "getrandom 0.2.7",
+ "getrandom",
  "redox_syscall",
  "thiserror",
 ]
@@ -1704,7 +1715,7 @@ dependencies = [
  "nix 0.24.2",
  "oci",
  "path-absolutize",
- "protobuf",
+ "protobuf 3.2.0",
  "protocols",
  "regex",
  "rlimit",
@@ -1723,12 +1734,25 @@ dependencies = [
  "zbus",
 ]
 
+[[package]]
+name = "rustversion"
+version = "1.0.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4f3208ce4d8448b3f3e7d168a73f5e0c43a61e32930de3bceeccedb388b6bf06"
+
 [[package]]
 name = "ryu"
 version = "1.0.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f3f6f92acf49d1b98f7a81226834412ada05458b7364277387724a237f062695"
 
+[[package]]
+name = "safe-path"
+version = "0.1.0"
+dependencies = [
+ "libc",
+]
+
 [[package]]
 name = "scan_fmt"
 version = "0.2.6"
@@ -1905,6 +1929,19 @@ dependencies = [
  "slog-scope",
 ]
 
+[[package]]
+name = "slog-term"
+version = "2.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "87d29185c55b7b258b4f120eab00f48557d4d9bc814f41713f449d35b0f8977c"
+dependencies = [
+ "atty",
+ "slog",
+ "term",
+ "thread_local",
+ "time 0.3.11",
+]
+
 [[package]]
 name = "smallvec"
 version = "1.8.0"
@@ -1985,6 +2022,17 @@ dependencies = [
  "winapi",
 ]
 
+[[package]]
+name = "term"
+version = "0.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c59df8ac95d96ff9bede18eb7300b0fda5e5d8d90960e76f8e14ae765eedbf1f"
+dependencies = [
+ "dirs-next",
+ "rustversion",
+ "winapi",
+]
+
 [[package]]
 name = "termcolor"
 version = "1.1.3"
@@ -2056,8 +2104,15 @@ dependencies = [
  "itoa",
  "libc",
  "num_threads",
+ "time-macros",
 ]
 
+[[package]]
+name = "time-macros"
+version = "0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "42657b1a6f4d817cda8e7a0ace261fe0cc946cf3a80314390b22cc61ae080792"
+
 [[package]]
 name = "tokio"
 version = "1.28.1"
@@ -2226,9 +2281,9 @@ dependencies = [
 
 [[package]]
 name = "ttrpc"
-version = "0.6.1"
+version = "0.7.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2ecfff459a859c6ba6668ff72b34c2f1d94d9d58f7088414c2674ad0f31cc7d8"
+checksum = "a35f22a2964bea14afee161665bb260b83cb48e665e0260ca06ec0e775c8b06c"
 dependencies = [
  "async-trait",
  "byteorder",
@@ -2236,8 +2291,8 @@ dependencies = [
  "libc",
  "log",
  "nix 0.23.1",
- "protobuf",
- "protobuf-codegen-pure",
+ "protobuf 3.2.0",
+ "protobuf-codegen 3.2.0",
  "thiserror",
  "tokio",
  "tokio-vsock",
@@ -2245,28 +2300,28 @@ dependencies = [
 
 [[package]]
 name = "ttrpc-codegen"
-version = "0.2.0"
+version = "0.4.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "809eda4e459820237104e4b61d6b41bbe6c9e1ce6adf4057955e6e6722a90408"
+checksum = "94d7f7631d7a9ebed715a47cd4cb6072cbc7ae1d4ec01598971bbec0024340c2"
 dependencies = [
- "protobuf",
- "protobuf-codegen",
- "protobuf-codegen-pure",
+ "protobuf 2.27.1",
+ "protobuf-codegen 3.2.0",
+ "protobuf-support",
  "ttrpc-compiler",
 ]
 
 [[package]]
 name = "ttrpc-compiler"
-version = "0.4.1"
+version = "0.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2978ed3fa047d8fd55cbeb4d4a61d461fb3021a90c9618519c73ce7e5bb66c15"
+checksum = "ec3cb5dbf1f0865a34fe3f722290fe776cacb16f50428610b779467b76ddf647"
 dependencies = [
  "derive-new",
  "prost",
  "prost-build",
  "prost-types",
- "protobuf",
- "protobuf-codegen",
+ "protobuf 2.27.1",
+ "protobuf-codegen 2.27.1",
  "tempfile",
 ]
 
@@ -2337,12 +2392,6 @@ version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9d5b2c62b4012a3e1eca5a7e077d13b3bf498c4073e33ccd58626607748ceeca"
 
-[[package]]
-name = "wasi"
-version = "0.9.0+wasi-snapshot-preview1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cccddf32554fecc6acb585f82a32a72e28b48f8c4c1883ddfeeeaa96f7d8e519"
-
 [[package]]
 name = "wasi"
 version = "0.10.0+wasi-snapshot-preview1"
@@ -2605,7 +2654,7 @@ dependencies = [
  "nix 0.23.1",
  "once_cell",
  "ordered-stream",
- "rand 0.8.5",
+ "rand",
  "serde",
  "serde_repr",
  "sha1",

src/agent/Cargo.toml

@@ -10,8 +10,8 @@ oci = { path = "../libs/oci" }
 rustjail = { path = "rustjail" }
 protocols = { path = "../libs/protocols", features = ["async"] }
 lazy_static = "1.3.0"
-ttrpc = { version = "0.6.0", features = ["async"], default-features = false }
-protobuf = "2.27.0"
+ttrpc = { version = "0.7.1", features = ["async"], default-features = false }
+protobuf = "3.2.0"
 libc = "0.2.58"
 nix = "0.24.2"
 capctl = "0.2.0"
@@ -43,11 +43,13 @@ ipnetwork = "0.17.0"
 logging = { path = "../libs/logging" }
 slog = "2.5.2"
 slog-scope = "4.1.2"
+slog-term = "2.9.0"
 
 # Redirect ttrpc log calls
 slog-stdlog = "4.0.0"
 log = "0.4.11"
 
+cfg-if = "1.0.0"
 prometheus = { version = "0.13.0", features = ["process"] }
 procfs = "0.12.0"
 anyhow = "1.0.32"

src/agent/Makefile

@@ -26,13 +26,19 @@ export VERSION_COMMIT := $(if $(COMMIT),$(VERSION)-$(COMMIT),$(VERSION))
 EXTRA_RUSTFEATURES :=
 
 ##VAR SECCOMP=yes|no define if agent enables seccomp feature
-SECCOMP := yes
+SECCOMP ?= yes
 
 # Enable seccomp feature of rust build
 ifeq ($(SECCOMP),yes)
     override EXTRA_RUSTFEATURES += seccomp
 endif
 
+include ../../utils.mk
+
+ifeq ($(ARCH), ppc64le)
+    override ARCH = powerpc64le
+endif
+
 ##VAR STANDARD_OCI_RUNTIME=yes|no define if agent enables standard oci runtime feature
 STANDARD_OCI_RUNTIME := no
 
@@ -45,8 +51,6 @@ ifneq ($(EXTRA_RUSTFEATURES),)
     override EXTRA_RUSTFEATURES := --features "$(EXTRA_RUSTFEATURES)"
 endif
 
-include ../../utils.mk
-
 TARGET_PATH = target/$(TRIPLE)/$(BUILD_TYPE)/$(TARGET)
 
 ##VAR DESTDIR=<path> is a directory prepended to each installed target file

src/agent/rustjail/Cargo.toml

@@ -18,7 +18,7 @@ scopeguard = "1.0.0"
 capctl = "0.2.0"
 lazy_static = "1.3.0"
 libc = "0.2.58"
-protobuf = "2.27.0"
+protobuf = "3.2.0"
 slog = "2.5.2"
 slog-scope = "4.1.2"
 scan_fmt = "0.2.6"

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

@@ -27,7 +27,7 @@ use oci::{
     LinuxNetwork, LinuxPids, LinuxResources,
 };
 
-use protobuf::{CachedSize, RepeatedField, SingularPtrField, UnknownFields};
+use protobuf::MessageField;
 use protocols::agent::{
     BlkioStats, BlkioStatsEntry, CgroupStats, CpuStats, CpuUsage, HugetlbStats, MemoryData,
     MemoryStats, PidsStats, ThrottlingData,
@@ -39,18 +39,16 @@ use std::path::Path;
 
 const GUEST_CPUS_PATH: &str = "/sys/devices/system/cpu/online";
 
-// Convenience macro to obtain the scope logger
-macro_rules! sl {
-    () => {
-        slog_scope::logger().new(o!("subsystem" => "cgroups"))
-    };
+// Convenience function to obtain the scope logger.
+fn sl() -> slog::Logger {
+    slog_scope::logger().new(o!("subsystem" => "cgroups"))
 }
 
 macro_rules! get_controller_or_return_singular_none {
     ($cg:ident) => {
         match $cg.controller_of() {
             Some(c) => c,
-            None => return SingularPtrField::none(),
+            None => return MessageField::none(),
         }
     };
 }
@@ -82,7 +80,7 @@ impl CgroupManager for Manager {
 
     fn set(&self, r: &LinuxResources, update: bool) -> Result<()> {
         info!(
-            sl!(),
+            sl(),
             "cgroup manager set resources for container. Resources input {:?}", r
         );
 
@@ -120,7 +118,7 @@ impl CgroupManager for Manager {
 
         // set devices resources
         set_devices_resources(&self.cgroup, &r.devices, res);
-        info!(sl!(), "resources after processed {:?}", res);
+        info!(sl(), "resources after processed {:?}", res);
 
         // apply resources
         self.cgroup.apply(res)?;
@@ -134,11 +132,10 @@ impl CgroupManager for Manager {
 
         let throttling_data = get_cpu_stats(&self.cgroup);
 
-        let cpu_stats = SingularPtrField::some(CpuStats {
+        let cpu_stats = MessageField::some(CpuStats {
             cpu_usage,
             throttling_data,
-            unknown_fields: UnknownFields::default(),
-            cached_size: CachedSize::default(),
+            ..Default::default()
         });
 
         // Memorystats
@@ -160,8 +157,7 @@ impl CgroupManager for Manager {
             pids_stats,
             blkio_stats,
             hugetlb_stats,
-            unknown_fields: UnknownFields::default(),
-            cached_size: CachedSize::default(),
+            ..Default::default()
         })
     }
 
@@ -199,7 +195,7 @@ impl CgroupManager for Manager {
         if guest_cpuset.is_empty() {
             return Ok(());
         }
-        info!(sl!(), "update_cpuset_path to: {}", guest_cpuset);
+        info!(sl(), "update_cpuset_path to: {}", guest_cpuset);
 
         let h = cgroups::hierarchies::auto();
         let root_cg = h.root_control_group();
@@ -207,12 +203,12 @@ impl CgroupManager for Manager {
         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);
+        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);
+        info!(sl(), "container cpuset path: {:?}", &path);
 
         let mut paths = vec![];
         for ancestor in container_path.ancestors() {
@@ -221,7 +217,7 @@ impl CgroupManager for Manager {
             }
             paths.push(ancestor);
         }
-        info!(sl!(), "parent paths to update cpuset: {:?}", &paths);
+        info!(sl(), "parent paths to update cpuset: {:?}", &paths);
 
         let mut i = paths.len();
         loop {
@@ -235,7 +231,7 @@ impl CgroupManager for Manager {
                 .to_str()
                 .unwrap()
                 .trim_start_matches(root_path.to_str().unwrap());
-            info!(sl!(), "updating cpuset for parent path {:?}", &r_path);
+            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)?;
@@ -243,7 +239,7 @@ impl CgroupManager for Manager {
 
         if !container_cpuset.is_empty() {
             info!(
-                sl!(),
+                sl(),
                 "updating cpuset for container path: {:?} cpuset: {}",
                 &container_path,
                 container_cpuset
@@ -278,7 +274,7 @@ fn set_network_resources(
     network: &LinuxNetwork,
     res: &mut cgroups::Resources,
 ) {
-    info!(sl!(), "cgroup manager set network");
+    info!(sl(), "cgroup manager set network");
 
     // set classid
     // description can be found at https://www.kernel.org/doc/html/latest/admin-guide/cgroup-v1/net_cls.html
@@ -305,7 +301,7 @@ fn set_devices_resources(
     device_resources: &[LinuxDeviceCgroup],
     res: &mut cgroups::Resources,
 ) {
-    info!(sl!(), "cgroup manager set devices");
+    info!(sl(), "cgroup manager set devices");
     let mut devices = vec![];
 
     for d in device_resources.iter() {
@@ -334,7 +330,7 @@ fn set_hugepages_resources(
     hugepage_limits: &[LinuxHugepageLimit],
     res: &mut cgroups::Resources,
 ) {
-    info!(sl!(), "cgroup manager set hugepage");
+    info!(sl(), "cgroup manager set hugepage");
     let mut limits = vec![];
     let hugetlb_controller = cg.controller_of::<HugeTlbController>();
 
@@ -348,7 +344,7 @@ fn set_hugepages_resources(
             limits.push(hr);
         } else {
             warn!(
-                sl!(),
+                sl(),
                 "{} page size support cannot be verified, dropping requested limit", l.page_size
             );
         }
@@ -361,7 +357,7 @@ fn set_block_io_resources(
     blkio: &LinuxBlockIo,
     res: &mut cgroups::Resources,
 ) {
-    info!(sl!(), "cgroup manager set block io");
+    info!(sl(), "cgroup manager set block io");
 
     res.blkio.weight = blkio.weight;
     res.blkio.leaf_weight = blkio.leaf_weight;
@@ -389,13 +385,13 @@ fn set_block_io_resources(
 }
 
 fn set_cpu_resources(cg: &cgroups::Cgroup, cpu: &LinuxCpu) -> Result<()> {
-    info!(sl!(), "cgroup manager set cpu");
+    info!(sl(), "cgroup manager set cpu");
 
     let cpuset_controller: &CpuSetController = cg.controller_of().unwrap();
 
     if !cpu.cpus.is_empty() {
         if let Err(e) = cpuset_controller.set_cpus(&cpu.cpus) {
-            warn!(sl!(), "write cpuset failed: {:?}", e);
+            warn!(sl(), "write cpuset failed: {:?}", e);
         }
     }
 
@@ -426,7 +422,7 @@ fn set_cpu_resources(cg: &cgroups::Cgroup, cpu: &LinuxCpu) -> Result<()> {
 }
 
 fn set_memory_resources(cg: &cgroups::Cgroup, memory: &LinuxMemory, update: bool) -> Result<()> {
-    info!(sl!(), "cgroup manager set memory");
+    info!(sl(), "cgroup manager set memory");
     let mem_controller: &MemController = cg.controller_of().unwrap();
 
     if !update {
@@ -446,14 +442,14 @@ fn set_memory_resources(cg: &cgroups::Cgroup, memory: &LinuxMemory, update: bool
         let memstat = get_memory_stats(cg)
             .into_option()
             .ok_or_else(|| anyhow!("failed to get the cgroup memory stats"))?;
-        let memusage = memstat.get_usage();
+        let memusage = memstat.usage();
 
         // When update memory limit, the kernel would check the current memory limit
         // set against the new swap setting, if the current memory limit is large than
         // the new swap, then set limit first, otherwise the kernel would complain and
         // refused to set; on the other hand, if the current memory limit is smaller than
         // the new swap, then we should set the swap first and then set the memor limit.
-        if swap == -1 || memusage.get_limit() < swap as u64 {
+        if swap == -1 || memusage.limit() < swap as u64 {
             mem_controller.set_memswap_limit(swap)?;
             set_resource!(mem_controller, set_limit, memory, limit);
         } else {
@@ -495,7 +491,7 @@ fn set_memory_resources(cg: &cgroups::Cgroup, memory: &LinuxMemory, update: bool
 }
 
 fn set_pids_resources(cg: &cgroups::Cgroup, pids: &LinuxPids) -> Result<()> {
-    info!(sl!(), "cgroup manager set pids");
+    info!(sl(), "cgroup manager set pids");
     let pid_controller: &PidController = cg.controller_of().unwrap();
     let v = if pids.limit > 0 {
         MaxValue::Value(pids.limit)
@@ -657,21 +653,20 @@ lazy_static! {
     };
 }
 
-fn get_cpu_stats(cg: &cgroups::Cgroup) -> SingularPtrField<ThrottlingData> {
+fn get_cpu_stats(cg: &cgroups::Cgroup) -> MessageField<ThrottlingData> {
     let cpu_controller: &CpuController = get_controller_or_return_singular_none!(cg);
     let stat = cpu_controller.cpu().stat;
     let h = lines_to_map(&stat);
 
-    SingularPtrField::some(ThrottlingData {
+    MessageField::some(ThrottlingData {
         periods: *h.get("nr_periods").unwrap_or(&0),
         throttled_periods: *h.get("nr_throttled").unwrap_or(&0),
         throttled_time: *h.get("throttled_time").unwrap_or(&0),
-        unknown_fields: UnknownFields::default(),
-        cached_size: CachedSize::default(),
+        ..Default::default()
     })
 }
 
-fn get_cpuacct_stats(cg: &cgroups::Cgroup) -> SingularPtrField<CpuUsage> {
+fn get_cpuacct_stats(cg: &cgroups::Cgroup) -> MessageField<CpuUsage> {
     if let Some(cpuacct_controller) = cg.controller_of::<CpuAcctController>() {
         let cpuacct = cpuacct_controller.cpuacct();
 
@@ -685,13 +680,12 @@ fn get_cpuacct_stats(cg: &cgroups::Cgroup) -> SingularPtrField<CpuUsage> {
 
         let percpu_usage = line_to_vec(&cpuacct.usage_percpu);
 
-        return SingularPtrField::some(CpuUsage {
+        return MessageField::some(CpuUsage {
             total_usage,
             percpu_usage,
             usage_in_kernelmode,
             usage_in_usermode,
-            unknown_fields: UnknownFields::default(),
-            cached_size: CachedSize::default(),
+            ..Default::default()
         });
     }
 
@@ -704,17 +698,16 @@ fn get_cpuacct_stats(cg: &cgroups::Cgroup) -> SingularPtrField<CpuUsage> {
     let total_usage = *h.get("usage_usec").unwrap_or(&0);
     let percpu_usage = vec![];
 
-    SingularPtrField::some(CpuUsage {
+    MessageField::some(CpuUsage {
         total_usage,
         percpu_usage,
         usage_in_kernelmode,
         usage_in_usermode,
-        unknown_fields: UnknownFields::default(),
-        cached_size: CachedSize::default(),
+        ..Default::default()
     })
 }
 
-fn get_memory_stats(cg: &cgroups::Cgroup) -> SingularPtrField<MemoryStats> {
+fn get_memory_stats(cg: &cgroups::Cgroup) -> MessageField<MemoryStats> {
     let memory_controller: &MemController = get_controller_or_return_singular_none!(cg);
 
     // cache from memory stat
@@ -726,52 +719,48 @@ fn get_memory_stats(cg: &cgroups::Cgroup) -> SingularPtrField<MemoryStats> {
     let use_hierarchy = value == 1;
 
     // get memory data
-    let usage = SingularPtrField::some(MemoryData {
+    let usage = MessageField::some(MemoryData {
         usage: memory.usage_in_bytes,
         max_usage: memory.max_usage_in_bytes,
         failcnt: memory.fail_cnt,
         limit: memory.limit_in_bytes as u64,
-        unknown_fields: UnknownFields::default(),
-        cached_size: CachedSize::default(),
+        ..Default::default()
     });
 
     // get swap usage
     let memswap = memory_controller.memswap();
 
-    let swap_usage = SingularPtrField::some(MemoryData {
+    let swap_usage = MessageField::some(MemoryData {
         usage: memswap.usage_in_bytes,
         max_usage: memswap.max_usage_in_bytes,
         failcnt: memswap.fail_cnt,
         limit: memswap.limit_in_bytes as u64,
-        unknown_fields: UnknownFields::default(),
-        cached_size: CachedSize::default(),
+        ..Default::default()
     });
 
     // get kernel usage
     let kmem_stat = memory_controller.kmem_stat();
 
-    let kernel_usage = SingularPtrField::some(MemoryData {
+    let kernel_usage = MessageField::some(MemoryData {
         usage: kmem_stat.usage_in_bytes,
         max_usage: kmem_stat.max_usage_in_bytes,
         failcnt: kmem_stat.fail_cnt,
         limit: kmem_stat.limit_in_bytes as u64,
-        unknown_fields: UnknownFields::default(),
-        cached_size: CachedSize::default(),
+        ..Default::default()
     });
 
-    SingularPtrField::some(MemoryStats {
+    MessageField::some(MemoryStats {
         cache,
         usage,
         swap_usage,
         kernel_usage,
         use_hierarchy,
         stats: memory.stat.raw,
-        unknown_fields: UnknownFields::default(),
-        cached_size: CachedSize::default(),
+        ..Default::default()
     })
 }
 
-fn get_pids_stats(cg: &cgroups::Cgroup) -> SingularPtrField<PidsStats> {
+fn get_pids_stats(cg: &cgroups::Cgroup) -> MessageField<PidsStats> {
     let pid_controller: &PidController = get_controller_or_return_singular_none!(cg);
 
     let current = pid_controller.get_pid_current().unwrap_or(0);
@@ -785,11 +774,10 @@ fn get_pids_stats(cg: &cgroups::Cgroup) -> SingularPtrField<PidsStats> {
         },
     } as u64;
 
-    SingularPtrField::some(PidsStats {
+    MessageField::some(PidsStats {
         current,
         limit,
-        unknown_fields: UnknownFields::default(),
-        cached_size: CachedSize::default(),
+        ..Default::default()
     })
 }
 
@@ -825,8 +813,8 @@ https://github.com/opencontainers/runc/blob/a5847db387ae28c0ca4ebe4beee1a76900c8
     Total 0
 */
 
-fn get_blkio_stat_blkiodata(blkiodata: &[BlkIoData]) -> RepeatedField<BlkioStatsEntry> {
-    let mut m = RepeatedField::new();
+fn get_blkio_stat_blkiodata(blkiodata: &[BlkIoData]) -> Vec<BlkioStatsEntry> {
+    let mut m = Vec::new();
     if blkiodata.is_empty() {
         return m;
     }
@@ -839,16 +827,15 @@ fn get_blkio_stat_blkiodata(blkiodata: &[BlkIoData]) -> RepeatedField<BlkioStats
             minor: d.minor as u64,
             op: op.clone(),
             value: d.data,
-            unknown_fields: UnknownFields::default(),
-            cached_size: CachedSize::default(),
+            ..Default::default()
         });
     }
 
     m
 }
 
-fn get_blkio_stat_ioservice(services: &[IoService]) -> RepeatedField<BlkioStatsEntry> {
-    let mut m = RepeatedField::new();
+fn get_blkio_stat_ioservice(services: &[IoService]) -> Vec<BlkioStatsEntry> {
+    let mut m = Vec::new();
 
     if services.is_empty() {
         return m;
@@ -872,17 +859,16 @@ fn build_blkio_stats_entry(major: i16, minor: i16, op: &str, value: u64) -> Blki
         minor: minor as u64,
         op: op.to_string(),
         value,
-        unknown_fields: UnknownFields::default(),
-        cached_size: CachedSize::default(),
+        ..Default::default()
     }
 }
 
-fn get_blkio_stats_v2(cg: &cgroups::Cgroup) -> SingularPtrField<BlkioStats> {
+fn get_blkio_stats_v2(cg: &cgroups::Cgroup) -> MessageField<BlkioStats> {
     let blkio_controller: &BlkIoController = get_controller_or_return_singular_none!(cg);
     let blkio = blkio_controller.blkio();
 
     let mut resp = BlkioStats::new();
-    let mut blkio_stats = RepeatedField::new();
+    let mut blkio_stats = Vec::new();
 
     let stat = blkio.io_stat;
     for s in stat {
@@ -898,10 +884,10 @@ fn get_blkio_stats_v2(cg: &cgroups::Cgroup) -> SingularPtrField<BlkioStats> {
 
     resp.io_service_bytes_recursive = blkio_stats;
 
-    SingularPtrField::some(resp)
+    MessageField::some(resp)
 }
 
-fn get_blkio_stats(cg: &cgroups::Cgroup) -> SingularPtrField<BlkioStats> {
+fn get_blkio_stats(cg: &cgroups::Cgroup) -> MessageField<BlkioStats> {
     if cg.v2() {
         return get_blkio_stats_v2(cg);
     }
@@ -934,7 +920,7 @@ fn get_blkio_stats(cg: &cgroups::Cgroup) -> SingularPtrField<BlkioStats> {
         m.sectors_recursive = get_blkio_stat_blkiodata(&blkio.sectors_recursive);
     }
 
-    SingularPtrField::some(m)
+    MessageField::some(m)
 }
 
 fn get_hugetlb_stats(cg: &cgroups::Cgroup) -> HashMap<String, HugetlbStats> {
@@ -958,8 +944,7 @@ fn get_hugetlb_stats(cg: &cgroups::Cgroup) -> HashMap<String, HugetlbStats> {
                 usage,
                 max_usage,
                 failcnt,
-                unknown_fields: UnknownFields::default(),
-                cached_size: CachedSize::default(),
+                ..Default::default()
             },
         );
     }
@@ -975,7 +960,7 @@ pub fn get_paths() -> Result<HashMap<String, String>> {
     for l in fs::read_to_string(PATHS)?.lines() {
         let fl: Vec<&str> = l.split(':').collect();
         if fl.len() != 3 {
-            info!(sl!(), "Corrupted cgroup data!");
+            info!(sl(), "Corrupted cgroup data!");
             continue;
         }
 
@@ -996,7 +981,7 @@ pub fn get_mounts(paths: &HashMap<String, String>) -> Result<HashMap<String, Str
         let post: Vec<&str> = p[1].split(' ').collect();
 
         if post.len() != 3 {
-            warn!(sl!(), "can't parse {} line {:?}", MOUNTS, l);
+            warn!(sl(), "can't parse {} line {:?}", MOUNTS, l);
             continue;
         }
 

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

@@ -3,7 +3,7 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
-use protobuf::{CachedSize, SingularPtrField, UnknownFields};
+use protobuf::MessageField;
 
 use crate::cgroups::Manager as CgroupManager;
 use crate::protocols::agent::{BlkioStats, CgroupStats, CpuStats, MemoryStats, PidsStats};
@@ -33,13 +33,12 @@ impl CgroupManager for Manager {
 
     fn get_stats(&self) -> Result<CgroupStats> {
         Ok(CgroupStats {
-            cpu_stats: SingularPtrField::some(CpuStats::default()),
-            memory_stats: SingularPtrField::some(MemoryStats::new()),
-            pids_stats: SingularPtrField::some(PidsStats::new()),
-            blkio_stats: SingularPtrField::some(BlkioStats::new()),
+            cpu_stats: MessageField::some(CpuStats::default()),
+            memory_stats: MessageField::some(MemoryStats::new()),
+            pids_stats: MessageField::some(PidsStats::new()),
+            blkio_stats: MessageField::some(BlkioStats::new()),
             hugetlb_stats: HashMap::new(),
-            unknown_fields: UnknownFields::default(),
-            cached_size: CachedSize::default(),
+            ..Default::default()
         })
     }
 

src/agent/rustjail/src/cgroups/notifier.rs

@@ -16,11 +16,9 @@ use inotify::{Inotify, WatchMask};
 use tokio::io::AsyncReadExt;
 use tokio::sync::mpsc::{channel, Receiver};
 
-// Convenience macro to obtain the scope logger
-macro_rules! sl {
-    () => {
-        slog_scope::logger().new(o!("subsystem" => "cgroups_notifier"))
-    };
+// Convenience function to obtain the scope logger.
+fn sl() -> slog::Logger {
+    slog_scope::logger().new(o!("subsystem" => "cgroups_notifier"))
 }
 
 pub async fn notify_oom(cid: &str, cg_dir: String) -> Result<Receiver<String>> {
@@ -38,7 +36,7 @@ pub async fn notify_oom(cid: &str, cg_dir: String) -> Result<Receiver<String>> {
 fn get_value_from_cgroup(path: &Path, key: &str) -> Result<i64> {
     let content = fs::read_to_string(path)?;
     info!(
-        sl!(),
+        sl(),
         "get_value_from_cgroup file: {:?}, content: {}", &path, &content
     );
 
@@ -67,11 +65,11 @@ async fn register_memory_event_v2(
     let event_control_path = Path::new(&cg_dir).join(memory_event_name);
     let cgroup_event_control_path = Path::new(&cg_dir).join(cgroup_event_name);
     info!(
-        sl!(),
+        sl(),
         "register_memory_event_v2 event_control_path: {:?}", &event_control_path
     );
     info!(
-        sl!(),
+        sl(),
         "register_memory_event_v2 cgroup_event_control_path: {:?}", &cgroup_event_control_path
     );
 
@@ -82,8 +80,8 @@ async fn register_memory_event_v2(
     // Because no `unix.IN_DELETE|unix.IN_DELETE_SELF` event for cgroup file system, so watching all process exited
     let cg_wd = inotify.add_watch(&cgroup_event_control_path, WatchMask::MODIFY)?;
 
-    info!(sl!(), "ev_wd: {:?}", ev_wd);
-    info!(sl!(), "cg_wd: {:?}", cg_wd);
+    info!(sl(), "ev_wd: {:?}", ev_wd);
+    info!(sl(), "cg_wd: {:?}", cg_wd);
 
     let (sender, receiver) = channel(100);
     let containere_id = containere_id.to_string();
@@ -97,17 +95,17 @@ async fn register_memory_event_v2(
         while let Some(event_or_error) = stream.next().await {
             let event = event_or_error.unwrap();
             info!(
-                sl!(),
+                sl(),
                 "container[{}] get event for container: {:?}", &containere_id, &event
             );
             // info!("is1: {}", event.wd == wd1);
-            info!(sl!(), "event.wd: {:?}", event.wd);
+            info!(sl(), "event.wd: {:?}", event.wd);
 
             if event.wd == ev_wd {
                 let oom = get_value_from_cgroup(&event_control_path, "oom_kill");
                 if oom.unwrap_or(0) > 0 {
                     let _ = sender.send(containere_id.clone()).await.map_err(|e| {
-                        error!(sl!(), "send containere_id failed, error: {:?}", e);
+                        error!(sl(), "send containere_id failed, error: {:?}", e);
                     });
                     return;
                 }
@@ -171,13 +169,13 @@ async fn register_memory_event(
             let mut buf = [0u8; 8];
             match eventfd_stream.read(&mut buf).await {
                 Err(err) => {
-                    warn!(sl!(), "failed to read from eventfd: {:?}", err);
+                    warn!(sl(), "failed to read from eventfd: {:?}", err);
                     return;
                 }
                 Ok(_) => {
                     let content = fs::read_to_string(path.clone());
                     info!(
-                        sl!(),
+                        sl(),
                         "cgroup event for container: {}, path: {:?}, content: {:?}",
                         &containere_id,
                         &path,
@@ -193,7 +191,7 @@ async fn register_memory_event(
             }
 
             let _ = sender.send(containere_id.clone()).await.map_err(|e| {
-                error!(sl!(), "send containere_id failed, error: {:?}", e);
+                error!(sl(), "send containere_id failed, error: {:?}", e);
             });
         }
     });

src/agent/rustjail/src/container.rs

@@ -48,7 +48,7 @@ use nix::unistd::{self, fork, ForkResult, Gid, Pid, Uid, User};
 use std::os::unix::fs::MetadataExt;
 use std::os::unix::io::AsRawFd;
 
-use protobuf::SingularPtrField;
+use protobuf::MessageField;
 
 use oci::State as OCIState;
 use regex::Regex;
@@ -374,13 +374,18 @@ fn do_init_child(cwfd: RawFd) -> Result<()> {
     let buf = read_sync(crfd)?;
     let spec_str = std::str::from_utf8(&buf)?;
     let spec: oci::Spec = serde_json::from_str(spec_str)?;
-
     log_child!(cfd_log, "notify parent to send oci process");
     write_sync(cwfd, SYNC_SUCCESS, "")?;
 
     let buf = read_sync(crfd)?;
     let process_str = std::str::from_utf8(&buf)?;
     let oci_process: oci::Process = serde_json::from_str(process_str)?;
+    log_child!(cfd_log, "notify parent to send oci state");
+    write_sync(cwfd, SYNC_SUCCESS, "")?;
+
+    let buf = read_sync(crfd)?;
+    let state_str = std::str::from_utf8(&buf)?;
+    let mut state: oci::State = serde_json::from_str(state_str)?;
     log_child!(cfd_log, "notify parent to send cgroup manager");
     write_sync(cwfd, SYNC_SUCCESS, "")?;
 
@@ -743,6 +748,19 @@ fn do_init_child(cwfd: RawFd) -> Result<()> {
         unistd::read(fd, buf)?;
     }
 
+    if init {
+        // StartContainer Hooks:
+        // * should be run in container namespace
+        // * should be run after container is created and before container is started (before user-specific command is executed)
+        // * spec details: https://github.com/opencontainers/runtime-spec/blob/c1662686cff159595277b79322d0272f5182941b/config.md#startcontainer-hooks
+        state.pid = std::process::id() as i32;
+        state.status = oci::ContainerState::Created;
+        if let Some(hooks) = spec.hooks.as_ref() {
+            let mut start_container_states = HookStates::new();
+            start_container_states.execute_hooks(&hooks.start_container, Some(state))?;
+        }
+    }
+
     // With NoNewPrivileges, we should set seccomp as close to
     // do_exec as possible in order to reduce the amount of
     // system calls in the seccomp profiles.
@@ -857,7 +875,7 @@ impl BaseContainer for LinuxContainer {
         // what about network interface stats?
 
         Ok(StatsContainerResponse {
-            cgroup_stats: SingularPtrField::some(self.cgroup_manager.as_ref().get_stats()?),
+            cgroup_stats: MessageField::some(self.cgroup_manager.as_ref().get_stats()?),
             ..Default::default()
         })
     }
@@ -1323,7 +1341,6 @@ async fn join_namespaces(
     write_async(pipe_w, SYNC_DATA, spec_str.as_str()).await?;
 
     info!(logger, "wait child received oci spec");
-
     read_async(pipe_r).await?;
 
     info!(logger, "send oci process from parent to child");
@@ -1333,6 +1350,13 @@ async fn join_namespaces(
     info!(logger, "wait child received oci process");
     read_async(pipe_r).await?;
 
+    info!(logger, "try to send state from parent to child");
+    let state_str = serde_json::to_string(st)?;
+    write_async(pipe_w, SYNC_DATA, state_str.as_str()).await?;
+
+    info!(logger, "wait child received oci state");
+    read_async(pipe_r).await?;
+
     let cm_str = if use_systemd_cgroup {
         serde_json::to_string(cm.as_any()?.downcast_ref::<SystemdManager>().unwrap())
     } else {
@@ -1572,10 +1596,8 @@ mod tests {
     use tempfile::tempdir;
     use test_utils::skip_if_not_root;
 
-    macro_rules! sl {
-        () => {
-            slog_scope::logger()
-        };
+    fn sl() -> slog::Logger {
+        slog_scope::logger()
     }
 
     #[test]
@@ -1830,7 +1852,7 @@ mod tests {
         let _ = new_linux_container_and_then(|mut c: LinuxContainer| {
             c.processes.insert(
                 1,
-                Process::new(&sl!(), &oci::Process::default(), "123", true, 1).unwrap(),
+                Process::new(&sl(), &oci::Process::default(), "123", true, 1).unwrap(),
             );
             let p = c.get_process("123");
             assert!(p.is_ok(), "Expecting Ok, Got {:?}", p);
@@ -1857,7 +1879,7 @@ mod tests {
         let (c, _dir) = new_linux_container();
         let ret = c
             .unwrap()
-            .start(Process::new(&sl!(), &oci::Process::default(), "123", true, 1).unwrap())
+            .start(Process::new(&sl(), &oci::Process::default(), "123", true, 1).unwrap())
             .await;
         assert!(ret.is_err(), "Expecting Err, Got {:?}", ret);
     }
@@ -1867,7 +1889,7 @@ mod tests {
         let (c, _dir) = new_linux_container();
         let ret = c
             .unwrap()
-            .run(Process::new(&sl!(), &oci::Process::default(), "123", true, 1).unwrap())
+            .run(Process::new(&sl(), &oci::Process::default(), "123", true, 1).unwrap())
             .await;
         assert!(ret.is_err(), "Expecting Err, Got {:?}", ret);
     }

src/agent/rustjail/src/lib.rs

@@ -82,11 +82,11 @@ pub fn process_grpc_to_oci(p: &grpc::Process) -> oci::Process {
         let cap = p.Capabilities.as_ref().unwrap();
 
         Some(oci::LinuxCapabilities {
-            bounding: cap.Bounding.clone().into_vec(),
-            effective: cap.Effective.clone().into_vec(),
-            inheritable: cap.Inheritable.clone().into_vec(),
-            permitted: cap.Permitted.clone().into_vec(),
-            ambient: cap.Ambient.clone().into_vec(),
+            bounding: cap.Bounding.clone(),
+            effective: cap.Effective.clone(),
+            inheritable: cap.Inheritable.clone(),
+            permitted: cap.Permitted.clone(),
+            ambient: cap.Ambient.clone(),
         })
     } else {
         None
@@ -108,8 +108,8 @@ pub fn process_grpc_to_oci(p: &grpc::Process) -> oci::Process {
         terminal: p.Terminal,
         console_size,
         user,
-        args: p.Args.clone().into_vec(),
-        env: p.Env.clone().into_vec(),
+        args: p.Args.clone(),
+        env: p.Env.clone(),
         cwd: p.Cwd.clone(),
         capabilities,
         rlimits,
@@ -130,9 +130,9 @@ fn root_grpc_to_oci(root: &grpc::Root) -> oci::Root {
 fn mount_grpc_to_oci(m: &grpc::Mount) -> oci::Mount {
     oci::Mount {
         destination: m.destination.clone(),
-        r#type: m.field_type.clone(),
+        r#type: m.type_.clone(),
         source: m.source.clone(),
-        options: m.options.clone().into_vec(),
+        options: m.options.clone(),
     }
 }
 
@@ -143,8 +143,8 @@ fn hook_grpc_to_oci(h: &[grpcHook]) -> Vec<oci::Hook> {
     for e in h.iter() {
         r.push(oci::Hook {
             path: e.Path.clone(),
-            args: e.Args.clone().into_vec(),
-            env: e.Env.clone().into_vec(),
+            args: e.Args.clone(),
+            env: e.Env.clone(),
             timeout: Some(e.Timeout as i32),
         });
     }
@@ -153,13 +153,17 @@ fn hook_grpc_to_oci(h: &[grpcHook]) -> Vec<oci::Hook> {
 
 fn hooks_grpc_to_oci(h: &grpc::Hooks) -> oci::Hooks {
     let prestart = hook_grpc_to_oci(h.Prestart.as_ref());
-
+    let create_runtime = hook_grpc_to_oci(h.CreateRuntime.as_ref());
+    let create_container = hook_grpc_to_oci(h.CreateContainer.as_ref());
+    let start_container = hook_grpc_to_oci(h.StartContainer.as_ref());
     let poststart = hook_grpc_to_oci(h.Poststart.as_ref());
-
     let poststop = hook_grpc_to_oci(h.Poststop.as_ref());
 
     oci::Hooks {
         prestart,
+        create_runtime,
+        create_container,
+        start_container,
         poststart,
         poststop,
     }
@@ -355,7 +359,7 @@ fn seccomp_grpc_to_oci(sec: &grpc::LinuxSeccomp) -> oci::LinuxSeccomp {
             let mut args = Vec::new();
 
             let errno_ret: u32 = if sys.has_errnoret() {
-                sys.get_errnoret()
+                sys.errnoret()
             } else {
                 libc::EPERM as u32
             };
@@ -370,7 +374,7 @@ fn seccomp_grpc_to_oci(sec: &grpc::LinuxSeccomp) -> oci::LinuxSeccomp {
             }
 
             r.push(oci::LinuxSyscall {
-                names: sys.Names.clone().into_vec(),
+                names: sys.Names.clone(),
                 action: sys.Action.clone(),
                 errno_ret,
                 args,
@@ -381,8 +385,8 @@ fn seccomp_grpc_to_oci(sec: &grpc::LinuxSeccomp) -> oci::LinuxSeccomp {
 
     oci::LinuxSeccomp {
         default_action: sec.DefaultAction.clone(),
-        architectures: sec.Architectures.clone().into_vec(),
-        flags: sec.Flags.clone().into_vec(),
+        architectures: sec.Architectures.clone(),
+        flags: sec.Flags.clone(),
         syscalls,
     }
 }
@@ -452,8 +456,8 @@ fn linux_grpc_to_oci(l: &grpc::Linux) -> oci::Linux {
         devices,
         seccomp,
         rootfs_propagation: l.RootfsPropagation.clone(),
-        masked_paths: l.MaskedPaths.clone().into_vec(),
-        readonly_paths: l.ReadonlyPaths.clone().into_vec(),
+        masked_paths: l.MaskedPaths.clone(),
+        readonly_paths: l.ReadonlyPaths.clone(),
         mount_label: l.MountLabel.clone(),
         intel_rdt,
     }
@@ -554,35 +558,30 @@ mod tests {
                 // All fields specified
                 grpcproc: grpc::Process {
                     Terminal: true,
-                    ConsoleSize: protobuf::SingularPtrField::<grpc::Box>::some(grpc::Box {
+                    ConsoleSize: protobuf::MessageField::<grpc::Box>::some(grpc::Box {
                         Height: 123,
                         Width: 456,
                         ..Default::default()
                     }),
-                    User: protobuf::SingularPtrField::<grpc::User>::some(grpc::User {
+                    User: protobuf::MessageField::<grpc::User>::some(grpc::User {
                         UID: 1234,
                         GID: 5678,
                         AdditionalGids: Vec::from([910, 1112]),
                         Username: String::from("username"),
                         ..Default::default()
                     }),
-                    Args: protobuf::RepeatedField::from(Vec::from([
-                        String::from("arg1"),
-                        String::from("arg2"),
-                    ])),
-                    Env: protobuf::RepeatedField::from(Vec::from([String::from("env")])),
+                    Args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                    Env: Vec::from([String::from("env")]),
                     Cwd: String::from("cwd"),
-                    Capabilities: protobuf::SingularPtrField::some(grpc::LinuxCapabilities {
-                        Bounding: protobuf::RepeatedField::from(Vec::from([String::from("bnd")])),
-                        Effective: protobuf::RepeatedField::from(Vec::from([String::from("eff")])),
-                        Inheritable: protobuf::RepeatedField::from(Vec::from([String::from(
-                            "inher",
-                        )])),
-                        Permitted: protobuf::RepeatedField::from(Vec::from([String::from("perm")])),
-                        Ambient: protobuf::RepeatedField::from(Vec::from([String::from("amb")])),
+                    Capabilities: protobuf::MessageField::some(grpc::LinuxCapabilities {
+                        Bounding: Vec::from([String::from("bnd")]),
+                        Effective: Vec::from([String::from("eff")]),
+                        Inheritable: Vec::from([String::from("inher")]),
+                        Permitted: Vec::from([String::from("perm")]),
+                        Ambient: Vec::from([String::from("amb")]),
                         ..Default::default()
                     }),
-                    Rlimits: protobuf::RepeatedField::from(Vec::from([
+                    Rlimits: Vec::from([
                         grpc::POSIXRlimit {
                             Type: String::from("r#type"),
                             Hard: 123,
@@ -595,7 +594,7 @@ mod tests {
                             Soft: 1011,
                             ..Default::default()
                         },
-                    ])),
+                    ]),
                     NoNewPrivileges: true,
                     ApparmorProfile: String::from("apparmor profile"),
                     OOMScoreAdj: 123456,
@@ -645,7 +644,7 @@ mod tests {
             TestData {
                 // None ConsoleSize
                 grpcproc: grpc::Process {
-                    ConsoleSize: protobuf::SingularPtrField::<grpc::Box>::none(),
+                    ConsoleSize: protobuf::MessageField::<grpc::Box>::none(),
                     OOMScoreAdj: 0,
                     ..Default::default()
                 },
@@ -658,7 +657,7 @@ mod tests {
             TestData {
                 // None User
                 grpcproc: grpc::Process {
-                    User: protobuf::SingularPtrField::<grpc::User>::none(),
+                    User: protobuf::MessageField::<grpc::User>::none(),
                     OOMScoreAdj: 0,
                     ..Default::default()
                 },
@@ -676,7 +675,7 @@ mod tests {
             TestData {
                 // None Capabilities
                 grpcproc: grpc::Process {
-                    Capabilities: protobuf::SingularPtrField::none(),
+                    Capabilities: protobuf::MessageField::none(),
                     OOMScoreAdj: 0,
                     ..Default::default()
                 },
@@ -777,60 +776,57 @@ mod tests {
             TestData {
                 // All specified
                 grpchooks: grpc::Hooks {
-                    Prestart: protobuf::RepeatedField::from(Vec::from([
+                    Prestart: Vec::from([
                         grpc::Hook {
                             Path: String::from("prestartpath"),
-                            Args: protobuf::RepeatedField::from(Vec::from([
-                                String::from("arg1"),
-                                String::from("arg2"),
-                            ])),
-                            Env: protobuf::RepeatedField::from(Vec::from([
-                                String::from("env1"),
-                                String::from("env2"),
-                            ])),
+                            Args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                            Env: Vec::from([String::from("env1"), String::from("env2")]),
                             Timeout: 10,
                             ..Default::default()
                         },
                         grpc::Hook {
                             Path: String::from("prestartpath2"),
-                            Args: protobuf::RepeatedField::from(Vec::from([
-                                String::from("arg3"),
-                                String::from("arg4"),
-                            ])),
-                            Env: protobuf::RepeatedField::from(Vec::from([
-                                String::from("env3"),
-                                String::from("env4"),
-                            ])),
+                            Args: Vec::from([String::from("arg3"), String::from("arg4")]),
+                            Env: Vec::from([String::from("env3"), String::from("env4")]),
                             Timeout: 25,
                             ..Default::default()
                         },
-                    ])),
-                    Poststart: protobuf::RepeatedField::from(Vec::from([grpc::Hook {
+                    ]),
+                    Poststart: Vec::from([grpc::Hook {
                         Path: String::from("poststartpath"),
-                        Args: protobuf::RepeatedField::from(Vec::from([
-                            String::from("arg1"),
-                            String::from("arg2"),
-                        ])),
-                        Env: protobuf::RepeatedField::from(Vec::from([
-                            String::from("env1"),
-                            String::from("env2"),
-                        ])),
+                        Args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        Env: Vec::from([String::from("env1"), String::from("env2")]),
                         Timeout: 10,
                         ..Default::default()
-                    }])),
-                    Poststop: protobuf::RepeatedField::from(Vec::from([grpc::Hook {
+                    }]),
+                    Poststop: Vec::from([grpc::Hook {
                         Path: String::from("poststoppath"),
-                        Args: protobuf::RepeatedField::from(Vec::from([
-                            String::from("arg1"),
-                            String::from("arg2"),
-                        ])),
-                        Env: protobuf::RepeatedField::from(Vec::from([
-                            String::from("env1"),
-                            String::from("env2"),
-                        ])),
+                        Args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        Env: Vec::from([String::from("env1"), String::from("env2")]),
                         Timeout: 10,
                         ..Default::default()
-                    }])),
+                    }]),
+                    CreateRuntime: Vec::from([grpc::Hook {
+                        Path: String::from("createruntimepath"),
+                        Args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        Env: Vec::from([String::from("env1"), String::from("env2")]),
+                        Timeout: 10,
+                        ..Default::default()
+                    }]),
+                    CreateContainer: Vec::from([grpc::Hook {
+                        Path: String::from("createcontainerpath"),
+                        Args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        Env: Vec::from([String::from("env1"), String::from("env2")]),
+                        Timeout: 10,
+                        ..Default::default()
+                    }]),
+                    StartContainer: Vec::from([grpc::Hook {
+                        Path: String::from("startcontainerpath"),
+                        Args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        Env: Vec::from([String::from("env1"), String::from("env2")]),
+                        Timeout: 10,
+                        ..Default::default()
+                    }]),
                     ..Default::default()
                 },
                 result: oci::Hooks {
@@ -860,38 +856,65 @@ mod tests {
                         env: Vec::from([String::from("env1"), String::from("env2")]),
                         timeout: Some(10),
                     }]),
+                    create_runtime: Vec::from([oci::Hook {
+                        path: String::from("createruntimepath"),
+                        args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        env: Vec::from([String::from("env1"), String::from("env2")]),
+                        timeout: Some(10),
+                    }]),
+                    create_container: Vec::from([oci::Hook {
+                        path: String::from("createcontainerpath"),
+                        args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        env: Vec::from([String::from("env1"), String::from("env2")]),
+                        timeout: Some(10),
+                    }]),
+                    start_container: Vec::from([oci::Hook {
+                        path: String::from("startcontainerpath"),
+                        args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        env: Vec::from([String::from("env1"), String::from("env2")]),
+                        timeout: Some(10),
+                    }]),
                 },
             },
             TestData {
                 // Prestart empty
                 grpchooks: grpc::Hooks {
-                    Prestart: protobuf::RepeatedField::from(Vec::from([])),
-                    Poststart: protobuf::RepeatedField::from(Vec::from([grpc::Hook {
+                    Prestart: Vec::from([]),
+                    Poststart: Vec::from([grpc::Hook {
                         Path: String::from("poststartpath"),
-                        Args: protobuf::RepeatedField::from(Vec::from([
-                            String::from("arg1"),
-                            String::from("arg2"),
-                        ])),
-                        Env: protobuf::RepeatedField::from(Vec::from([
-                            String::from("env1"),
-                            String::from("env2"),
-                        ])),
+                        Args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        Env: Vec::from([String::from("env1"), String::from("env2")]),
                         Timeout: 10,
                         ..Default::default()
-                    }])),
-                    Poststop: protobuf::RepeatedField::from(Vec::from([grpc::Hook {
+                    }]),
+                    Poststop: Vec::from([grpc::Hook {
                         Path: String::from("poststoppath"),
-                        Args: protobuf::RepeatedField::from(Vec::from([
-                            String::from("arg1"),
-                            String::from("arg2"),
-                        ])),
-                        Env: protobuf::RepeatedField::from(Vec::from([
-                            String::from("env1"),
-                            String::from("env2"),
-                        ])),
+                        Args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        Env: Vec::from([String::from("env1"), String::from("env2")]),
                         Timeout: 10,
                         ..Default::default()
-                    }])),
+                    }]),
+                    CreateRuntime: Vec::from([grpc::Hook {
+                        Path: String::from("createruntimepath"),
+                        Args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        Env: Vec::from([String::from("env1"), String::from("env2")]),
+                        Timeout: 10,
+                        ..Default::default()
+                    }]),
+                    CreateContainer: Vec::from([grpc::Hook {
+                        Path: String::from("createcontainerpath"),
+                        Args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        Env: Vec::from([String::from("env1"), String::from("env2")]),
+                        Timeout: 10,
+                        ..Default::default()
+                    }]),
+                    StartContainer: Vec::from([grpc::Hook {
+                        Path: String::from("startcontainerpath"),
+                        Args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        Env: Vec::from([String::from("env1"), String::from("env2")]),
+                        Timeout: 10,
+                        ..Default::default()
+                    }]),
                     ..Default::default()
                 },
                 result: oci::Hooks {
@@ -908,6 +931,24 @@ mod tests {
                         env: Vec::from([String::from("env1"), String::from("env2")]),
                         timeout: Some(10),
                     }]),
+                    create_runtime: Vec::from([oci::Hook {
+                        path: String::from("createruntimepath"),
+                        args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        env: Vec::from([String::from("env1"), String::from("env2")]),
+                        timeout: Some(10),
+                    }]),
+                    create_container: Vec::from([oci::Hook {
+                        path: String::from("createcontainerpath"),
+                        args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        env: Vec::from([String::from("env1"), String::from("env2")]),
+                        timeout: Some(10),
+                    }]),
+                    start_container: Vec::from([oci::Hook {
+                        path: String::from("startcontainerpath"),
+                        args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        env: Vec::from([String::from("env1"), String::from("env2")]),
+                        timeout: Some(10),
+                    }]),
                 },
             },
         ];
@@ -945,11 +986,8 @@ mod tests {
                 grpcmount: grpc::Mount {
                     destination: String::from("destination"),
                     source: String::from("source"),
-                    field_type: String::from("fieldtype"),
-                    options: protobuf::RepeatedField::from(Vec::from([
-                        String::from("option1"),
-                        String::from("option2"),
-                    ])),
+                    type_: String::from("fieldtype"),
+                    options: Vec::from([String::from("option1"), String::from("option2")]),
                     ..Default::default()
                 },
                 result: oci::Mount {
@@ -963,8 +1001,8 @@ mod tests {
                 grpcmount: grpc::Mount {
                     destination: String::from("destination"),
                     source: String::from("source"),
-                    field_type: String::from("fieldtype"),
-                    options: protobuf::RepeatedField::from(Vec::new()),
+                    type_: String::from("fieldtype"),
+                    options: Vec::new(),
                     ..Default::default()
                 },
                 result: oci::Mount {
@@ -978,8 +1016,8 @@ mod tests {
                 grpcmount: grpc::Mount {
                     destination: String::new(),
                     source: String::from("source"),
-                    field_type: String::from("fieldtype"),
-                    options: protobuf::RepeatedField::from(Vec::from([String::from("option1")])),
+                    type_: String::from("fieldtype"),
+                    options: Vec::from([String::from("option1")]),
                     ..Default::default()
                 },
                 result: oci::Mount {
@@ -993,8 +1031,8 @@ mod tests {
                 grpcmount: grpc::Mount {
                     destination: String::from("destination"),
                     source: String::from("source"),
-                    field_type: String::new(),
-                    options: protobuf::RepeatedField::from(Vec::from([String::from("option1")])),
+                    type_: String::new(),
+                    options: Vec::from([String::from("option1")]),
                     ..Default::default()
                 },
                 result: oci::Mount {
@@ -1054,27 +1092,15 @@ mod tests {
                 grpchook: &[
                     grpc::Hook {
                         Path: String::from("path"),
-                        Args: protobuf::RepeatedField::from(Vec::from([
-                            String::from("arg1"),
-                            String::from("arg2"),
-                        ])),
-                        Env: protobuf::RepeatedField::from(Vec::from([
-                            String::from("env1"),
-                            String::from("env2"),
-                        ])),
+                        Args: Vec::from([String::from("arg1"), String::from("arg2")]),
+                        Env: Vec::from([String::from("env1"), String::from("env2")]),
                         Timeout: 10,
                         ..Default::default()
                     },
                     grpc::Hook {
                         Path: String::from("path2"),
-                        Args: protobuf::RepeatedField::from(Vec::from([
-                            String::from("arg3"),
-                            String::from("arg4"),
-                        ])),
-                        Env: protobuf::RepeatedField::from(Vec::from([
-                            String::from("env3"),
-                            String::from("env4"),
-                        ])),
+                        Args: Vec::from([String::from("arg3"), String::from("arg4")]),
+                        Env: Vec::from([String::from("env3"), String::from("env4")]),
                         Timeout: 20,
                         ..Default::default()
                     },

src/agent/rustjail/src/mount.rs

@@ -35,7 +35,7 @@ use crate::log_child;
 // struct is populated from the content in the /proc/<pid>/mountinfo file.
 #[derive(std::fmt::Debug, PartialEq)]
 pub struct Info {
-    mount_point: String,
+    pub mount_point: String,
     optional: String,
     fstype: String,
 }
@@ -553,7 +553,7 @@ fn rootfs_parent_mount_private(path: &str) -> Result<()> {
 
 // Parse /proc/self/mountinfo because comparing Dev and ino does not work from
 // bind mounts
-fn parse_mount_table(mountinfo_path: &str) -> Result<Vec<Info>> {
+pub fn parse_mount_table(mountinfo_path: &str) -> Result<Vec<Info>> {
     let file = File::open(mountinfo_path)?;
     let reader = BufReader::new(file);
     let mut infos = Vec::new();
@@ -1118,6 +1118,7 @@ mod tests {
     use std::fs::create_dir;
     use std::fs::create_dir_all;
     use std::fs::remove_dir_all;
+    use std::fs::remove_file;
     use std::io;
     use std::os::unix::fs;
     use std::os::unix::io::AsRawFd;
@@ -1333,14 +1334,9 @@ mod tests {
     fn test_mknod_dev() {
         skip_if_not_root!();
 
-        let tempdir = tempdir().unwrap();
-
-        let olddir = unistd::getcwd().unwrap();
-        defer!(let _ = unistd::chdir(&olddir););
-        let _ = unistd::chdir(tempdir.path());
-
+        let path = "/dev/fifo-test";
         let dev = oci::LinuxDevice {
-            path: "/fifo".to_string(),
+            path: path.to_string(),
             r#type: "c".to_string(),
             major: 0,
             minor: 0,
@@ -1348,13 +1344,16 @@ mod tests {
             uid: Some(unistd::getuid().as_raw()),
             gid: Some(unistd::getgid().as_raw()),
         };
-        let path = Path::new("fifo");
 
-        let ret = mknod_dev(&dev, path);
+        let ret = mknod_dev(&dev, Path::new(path));
         assert!(ret.is_ok(), "Should pass. Got: {:?}", ret);
 
         let ret = stat::stat(path);
         assert!(ret.is_ok(), "Should pass. Got: {:?}", ret);
+
+        // clear test device node
+        let ret = remove_file(path);
+        assert!(ret.is_ok(), "Should pass, Got: {:?}", ret);
     }
 
     #[test]

src/agent/rustjail/src/process.rs

@@ -161,7 +161,7 @@ impl Process {
 
     pub fn notify_term_close(&mut self) {
         let notify = self.term_exit_notifier.clone();
-        notify.notify_one();
+        notify.notify_waiters();
     }
 
     pub fn close_stdin(&mut self) {

src/agent/src/ap.rs

@@ -0,0 +1,79 @@
+// Copyright (c) IBM Corp. 2023
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+use std::fmt;
+use std::str::FromStr;
+
+use anyhow::{anyhow, Context};
+
+// IBM Adjunct Processor (AP) is used for cryptographic operations
+// by IBM Crypto Express hardware security modules on IBM zSystem & LinuxONE (s390x).
+// In Linux, virtual cryptographic devices are called AP queues.
+// The name of an AP queue respects a format <xx>.<xxxx> in hexadecimal notation [1, p.467]:
+//   - <xx> is an adapter ID
+//   - <xxxx> is an adapter domain ID
+// [1] https://www.ibm.com/docs/en/linuxonibm/pdf/lku5dd05.pdf
+
+#[derive(Debug)]
+pub struct Address {
+    pub adapter_id: u8,
+    pub adapter_domain: u16,
+}
+
+impl Address {
+    pub fn new(adapter_id: u8, adapter_domain: u16) -> Address {
+        Address {
+            adapter_id,
+            adapter_domain,
+        }
+    }
+}
+
+impl FromStr for Address {
+    type Err = anyhow::Error;
+
+    fn from_str(s: &str) -> anyhow::Result<Self> {
+        let split: Vec<&str> = s.split('.').collect();
+        if split.len() != 2 {
+            return Err(anyhow!(
+                "Wrong AP bus format. It needs to be in the form <xx>.<xxxx> (e.g. 0a.003f), got {:?}",
+                s
+            ));
+        }
+
+        let adapter_id = u8::from_str_radix(split[0], 16).context(format!(
+            "Wrong AP bus format. AP ID needs to be in the form <xx> (e.g. 0a), got {:?}",
+            split[0]
+        ))?;
+        let adapter_domain = u16::from_str_radix(split[1], 16).context(format!(
+            "Wrong AP bus format. AP domain needs to be in the form <xxxx> (e.g. 003f), got {:?}",
+            split[1]
+        ))?;
+
+        Ok(Address::new(adapter_id, adapter_domain))
+    }
+}
+
+impl fmt::Display for Address {
+    fn fmt(&self, f: &mut fmt::Formatter) -> Result<(), fmt::Error> {
+        write!(f, "{:02x}.{:04x}", self.adapter_id, self.adapter_domain)
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_from_str() {
+        let device = Address::from_str("a.1").unwrap();
+        assert_eq!(format!("{}", device), "0a.0001");
+
+        assert!(Address::from_str("").is_err());
+        assert!(Address::from_str(".").is_err());
+        assert!(Address::from_str("0.0.0").is_err());
+        assert!(Address::from_str("0g.0000").is_err());
+        assert!(Address::from_str("0a.10000").is_err());
+    }
+}

src/agent/src/config.rs

@@ -200,7 +200,7 @@ impl AgentConfig {
         let config_position = args.iter().position(|a| a == "--config" || a == "-c");
         if let Some(config_position) = config_position {
             if let Some(config_file) = args.get(config_position + 1) {
-                return AgentConfig::from_config_file(config_file);
+                return AgentConfig::from_config_file(config_file).context("AgentConfig from args");
             } else {
                 panic!("The config argument wasn't formed properly: {:?}", args);
             }
@@ -216,7 +216,8 @@ impl AgentConfig {
             // or if it can't be parsed properly.
             if param.starts_with(format!("{}=", CONFIG_FILE).as_str()) {
                 let config_file = get_string_value(param)?;
-                return AgentConfig::from_config_file(&config_file);
+                return AgentConfig::from_config_file(&config_file)
+                    .context("AgentConfig from kernel cmdline");
             }
 
             // parse cmdline flags
@@ -304,7 +305,8 @@ impl AgentConfig {
 
     #[instrument]
     pub fn from_config_file(file: &str) -> Result<AgentConfig> {
-        let config = fs::read_to_string(file)?;
+        let config = fs::read_to_string(file)
+            .with_context(|| format!("Failed to read config file {}", file))?;
         AgentConfig::from_str(&config)
     }
 

src/agent/src/device.rs

@@ -16,26 +16,23 @@ use std::str::FromStr;
 use std::sync::Arc;
 use tokio::sync::Mutex;
 
-#[cfg(target_arch = "s390x")]
-use crate::ccw;
 use crate::linux_abi::*;
 use crate::pci;
 use crate::sandbox::Sandbox;
 use crate::uevent::{wait_for_uevent, Uevent, UeventMatcher};
 use anyhow::{anyhow, Context, Result};
+use cfg_if::cfg_if;
 use oci::{LinuxDeviceCgroup, LinuxResources, Spec};
 use protocols::agent::Device;
 use tracing::instrument;
 
-// Convenience macro to obtain the scope logger
-macro_rules! sl {
-    () => {
-        slog_scope::logger().new(o!("subsystem" => "device"))
-    };
+// Convenience function to obtain the scope logger.
+fn sl() -> slog::Logger {
+    slog_scope::logger().new(o!("subsystem" => "device"))
 }
 
 const VM_ROOTFS: &str = "/";
-
+const BLOCK: &str = "block";
 pub const DRIVER_9P_TYPE: &str = "9p";
 pub const DRIVER_VIRTIOFS_TYPE: &str = "virtio-fs";
 pub const DRIVER_BLK_TYPE: &str = "blk";
@@ -46,14 +43,22 @@ pub const DRIVER_NVDIMM_TYPE: &str = "nvdimm";
 pub const DRIVER_EPHEMERAL_TYPE: &str = "ephemeral";
 pub const DRIVER_LOCAL_TYPE: &str = "local";
 pub const DRIVER_WATCHABLE_BIND_TYPE: &str = "watchable-bind";
-// VFIO device to be bound to a guest kernel driver
-pub const DRIVER_VFIO_GK_TYPE: &str = "vfio-gk";
-// VFIO device to be bound to vfio-pci and made available inside the
+// VFIO PCI device to be bound to a guest kernel driver
+pub const DRIVER_VFIO_PCI_GK_TYPE: &str = "vfio-pci-gk";
+// VFIO PCI device to be bound to vfio-pci and made available inside the
 // container as a VFIO device node
-pub const DRIVER_VFIO_TYPE: &str = "vfio";
+pub const DRIVER_VFIO_PCI_TYPE: &str = "vfio-pci";
+pub const DRIVER_VFIO_AP_TYPE: &str = "vfio-ap";
 pub const DRIVER_OVERLAYFS_TYPE: &str = "overlayfs";
 pub const FS_TYPE_HUGETLB: &str = "hugetlbfs";
 
+cfg_if! {
+    if #[cfg(target_arch = "s390x")] {
+        use crate::ap;
+        use crate::ccw;
+    }
+}
+
 #[instrument]
 pub fn online_device(path: &str) -> Result<()> {
     fs::write(path, "1")?;
@@ -71,7 +76,7 @@ where
 {
     let syspci = Path::new(&syspci);
     let drv = drv.as_ref();
-    info!(sl!(), "rebind_pci_driver: {} => {:?}", dev, drv);
+    info!(sl(), "rebind_pci_driver: {} => {:?}", dev, drv);
 
     let devpath = syspci.join("devices").join(dev.to_string());
     let overridepath = &devpath.join("driver_override");
@@ -197,7 +202,7 @@ impl ScsiBlockMatcher {
 
 impl UeventMatcher for ScsiBlockMatcher {
     fn is_match(&self, uev: &Uevent) -> bool {
-        uev.subsystem == "block" && uev.devpath.contains(&self.search) && !uev.devname.is_empty()
+        uev.subsystem == BLOCK && uev.devpath.contains(&self.search) && !uev.devname.is_empty()
     }
 }
 
@@ -231,7 +236,7 @@ impl VirtioBlkPciMatcher {
 
 impl UeventMatcher for VirtioBlkPciMatcher {
     fn is_match(&self, uev: &Uevent) -> bool {
-        uev.subsystem == "block" && self.rex.is_match(&uev.devpath) && !uev.devname.is_empty()
+        uev.subsystem == BLOCK && self.rex.is_match(&uev.devpath) && !uev.devname.is_empty()
     }
 }
 
@@ -280,7 +285,7 @@ pub async fn get_virtio_blk_ccw_device_name(
     sandbox: &Arc<Mutex<Sandbox>>,
     device: &ccw::Device,
 ) -> Result<String> {
-    let matcher = VirtioBlkCCWMatcher::new(&create_ccw_root_bus_path(), device);
+    let matcher = VirtioBlkCCWMatcher::new(CCW_ROOT_BUS_PATH, device);
     let uev = wait_for_uevent(sandbox, matcher).await?;
     let devname = uev.devname;
     return match Path::new(SYSTEM_DEV_PATH).join(&devname).to_str() {
@@ -304,7 +309,7 @@ impl PmemBlockMatcher {
 
 impl UeventMatcher for PmemBlockMatcher {
     fn is_match(&self, uev: &Uevent) -> bool {
-        uev.subsystem == "block"
+        uev.subsystem == BLOCK
             && uev.devpath.starts_with(ACPI_DEV_PATH)
             && uev.devpath.ends_with(&self.suffix)
             && !uev.devname.is_empty()
@@ -401,6 +406,81 @@ async fn get_vfio_device_name(sandbox: &Arc<Mutex<Sandbox>>, grp: IommuGroup) ->
     Ok(format!("{}/{}", SYSTEM_DEV_PATH, &uev.devname))
 }
 
+#[cfg(target_arch = "s390x")]
+#[derive(Debug)]
+struct ApMatcher {
+    syspath: String,
+}
+
+#[cfg(target_arch = "s390x")]
+impl ApMatcher {
+    fn new(address: ap::Address) -> ApMatcher {
+        ApMatcher {
+            syspath: format!(
+                "{}/card{:02x}/{}",
+                AP_ROOT_BUS_PATH, address.adapter_id, address
+            ),
+        }
+    }
+}
+
+#[cfg(target_arch = "s390x")]
+impl UeventMatcher for ApMatcher {
+    fn is_match(&self, uev: &Uevent) -> bool {
+        uev.action == "add" && uev.devpath == self.syspath
+    }
+}
+
+#[cfg(target_arch = "s390x")]
+#[instrument]
+async fn wait_for_ap_device(sandbox: &Arc<Mutex<Sandbox>>, address: ap::Address) -> Result<()> {
+    let matcher = ApMatcher::new(address);
+    wait_for_uevent(sandbox, matcher).await?;
+    Ok(())
+}
+
+#[derive(Debug)]
+struct MmioBlockMatcher {
+    suffix: String,
+}
+
+impl MmioBlockMatcher {
+    fn new(devname: &str) -> MmioBlockMatcher {
+        MmioBlockMatcher {
+            suffix: format!(r"/block/{}", devname),
+        }
+    }
+}
+
+impl UeventMatcher for MmioBlockMatcher {
+    fn is_match(&self, uev: &Uevent) -> bool {
+        uev.subsystem == BLOCK && uev.devpath.ends_with(&self.suffix) && !uev.devname.is_empty()
+    }
+}
+
+#[instrument]
+pub async fn get_virtio_mmio_device_name(
+    sandbox: &Arc<Mutex<Sandbox>>,
+    devpath: &str,
+) -> Result<()> {
+    let devname = devpath
+        .strip_prefix("/dev/")
+        .ok_or_else(|| anyhow!("Storage source '{}' must start with /dev/", devpath))?;
+
+    let matcher = MmioBlockMatcher::new(devname);
+    let uev = wait_for_uevent(sandbox, matcher)
+        .await
+        .context("failed to wait for uevent")?;
+    if uev.devname != devname {
+        return Err(anyhow!(
+            "Unexpected device name {} for mmio device (expected {})",
+            uev.devname,
+            devname
+        ));
+    }
+    Ok(())
+}
+
 /// Scan SCSI bus for the given SCSI address(SCSI-Id and LUN)
 #[instrument]
 fn scan_scsi_bus(scsi_addr: &str) -> Result<()> {
@@ -524,7 +604,7 @@ fn update_spec_devices(spec: &mut Spec, mut updates: HashMap<&str, DevUpdate>) -
             let host_minor = specdev.minor;
 
             info!(
-                sl!(),
+                sl(),
                 "update_spec_devices() updating device";
                 "container_path" => &specdev.path,
                 "type" => &specdev.r#type,
@@ -575,7 +655,7 @@ fn update_spec_devices(spec: &mut Spec, mut updates: HashMap<&str, DevUpdate>) -
                 if let Some(update) = res_updates.get(&(r.r#type.as_str(), host_major, host_minor))
                 {
                     info!(
-                        sl!(),
+                        sl(),
                         "update_spec_devices() updating resource";
                         "type" => &r.r#type,
                         "host_major" => host_major,
@@ -636,12 +716,18 @@ pub fn update_env_pci(
 #[instrument]
 async fn virtiommio_blk_device_handler(
     device: &Device,
-    _sandbox: &Arc<Mutex<Sandbox>>,
+    sandbox: &Arc<Mutex<Sandbox>>,
 ) -> Result<SpecUpdate> {
     if device.vm_path.is_empty() {
         return Err(anyhow!("Invalid path for virtio mmio blk device"));
     }
 
+    if !Path::new(&device.vm_path).exists() {
+        get_virtio_mmio_device_name(sandbox, &device.vm_path.to_string())
+            .await
+            .context("failed to get mmio device name")?;
+    }
+
     Ok(DevNumUpdate::from_vm_path(&device.vm_path)?.into())
 }
 
@@ -699,7 +785,7 @@ async fn virtio_nvdimm_device_handler(
     Ok(DevNumUpdate::from_vm_path(&device.vm_path)?.into())
 }
 
-fn split_vfio_option(opt: &str) -> Option<(&str, &str)> {
+fn split_vfio_pci_option(opt: &str) -> Option<(&str, &str)> {
     let mut tokens = opt.split('=');
     let hostbdf = tokens.next()?;
     let path = tokens.next()?;
@@ -714,14 +800,18 @@ fn split_vfio_option(opt: &str) -> Option<(&str, &str)> {
 // Each option should have the form "DDDD:BB:DD.F=<pcipath>"
 //     DDDD:BB:DD.F is the device's PCI address in the host
 //     <pcipath> is a PCI path to the device in the guest (see pci.rs)
-async fn vfio_device_handler(device: &Device, sandbox: &Arc<Mutex<Sandbox>>) -> Result<SpecUpdate> {
-    let vfio_in_guest = device.field_type != DRIVER_VFIO_GK_TYPE;
+#[instrument]
+async fn vfio_pci_device_handler(
+    device: &Device,
+    sandbox: &Arc<Mutex<Sandbox>>,
+) -> Result<SpecUpdate> {
+    let vfio_in_guest = device.type_ != DRIVER_VFIO_PCI_GK_TYPE;
     let mut pci_fixups = Vec::<(pci::Address, pci::Address)>::new();
     let mut group = None;
 
     for opt in device.options.iter() {
-        let (host, pcipath) =
-            split_vfio_option(opt).ok_or_else(|| anyhow!("Malformed VFIO option {:?}", opt))?;
+        let (host, pcipath) = split_vfio_pci_option(opt)
+            .ok_or_else(|| anyhow!("Malformed VFIO PCI option {:?}", opt))?;
         let host =
             pci::Address::from_str(host).context("Bad host PCI address in VFIO option {:?}")?;
         let pcipath = pci::Path::from_str(pcipath)?;
@@ -763,6 +853,28 @@ async fn vfio_device_handler(device: &Device, sandbox: &Arc<Mutex<Sandbox>>) ->
     })
 }
 
+// The VFIO AP (Adjunct Processor) device handler takes all the APQNs provided as device options
+// and awaits them. It sets the minimum AP rescan time of 5 seconds and temporarily adds that
+// amount to the hotplug timeout.
+#[cfg(target_arch = "s390x")]
+#[instrument]
+async fn vfio_ap_device_handler(
+    device: &Device,
+    sandbox: &Arc<Mutex<Sandbox>>,
+) -> Result<SpecUpdate> {
+    // Force AP bus rescan
+    fs::write(AP_SCANS_PATH, "1")?;
+    for apqn in device.options.iter() {
+        wait_for_ap_device(sandbox, ap::Address::from_str(apqn)?).await?;
+    }
+    Ok(Default::default())
+}
+
+#[cfg(not(target_arch = "s390x"))]
+async fn vfio_ap_device_handler(_: &Device, _: &Arc<Mutex<Sandbox>>) -> Result<SpecUpdate> {
+    Err(anyhow!("AP is only supported on s390x"))
+}
+
 #[instrument]
 pub async fn add_devices(
     devices: &[Device],
@@ -807,10 +919,10 @@ pub async fn add_devices(
 #[instrument]
 async fn add_device(device: &Device, sandbox: &Arc<Mutex<Sandbox>>) -> Result<SpecUpdate> {
     // log before validation to help with debugging gRPC protocol version differences.
-    info!(sl!(), "device-id: {}, device-type: {}, device-vm-path: {}, device-container-path: {}, device-options: {:?}",
-          device.id, device.field_type, device.vm_path, device.container_path, device.options);
+    info!(sl(), "device-id: {}, device-type: {}, device-vm-path: {}, device-container-path: {}, device-options: {:?}",
+          device.id, device.type_, device.vm_path, device.container_path, device.options);
 
-    if device.field_type.is_empty() {
+    if device.type_.is_empty() {
         return Err(anyhow!("invalid type for device {:?}", device));
     }
 
@@ -822,14 +934,17 @@ async fn add_device(device: &Device, sandbox: &Arc<Mutex<Sandbox>>) -> Result<Sp
         return Err(anyhow!("invalid container path for device {:?}", device));
     }
 
-    match device.field_type.as_str() {
+    match device.type_.as_str() {
         DRIVER_BLK_TYPE => virtio_blk_device_handler(device, sandbox).await,
         DRIVER_BLK_CCW_TYPE => virtio_blk_ccw_device_handler(device, sandbox).await,
         DRIVER_MMIO_BLK_TYPE => virtiommio_blk_device_handler(device, sandbox).await,
         DRIVER_NVDIMM_TYPE => virtio_nvdimm_device_handler(device, sandbox).await,
         DRIVER_SCSI_TYPE => virtio_scsi_device_handler(device, sandbox).await,
-        DRIVER_VFIO_GK_TYPE | DRIVER_VFIO_TYPE => vfio_device_handler(device, sandbox).await,
-        _ => Err(anyhow!("Unknown device type {}", device.field_type)),
+        DRIVER_VFIO_PCI_GK_TYPE | DRIVER_VFIO_PCI_TYPE => {
+            vfio_pci_device_handler(device, sandbox).await
+        }
+        DRIVER_VFIO_AP_TYPE => vfio_ap_device_handler(device, sandbox).await,
+        _ => Err(anyhow!("Unknown device type {}", device.type_)),
     }
 }
 
@@ -1325,7 +1440,7 @@ mod tests {
 
         let mut uev = crate::uevent::Uevent::default();
         uev.action = crate::linux_abi::U_EVENT_ACTION_ADD.to_string();
-        uev.subsystem = "block".to_string();
+        uev.subsystem = BLOCK.to_string();
         uev.devpath = devpath.clone();
         uev.devname = devname.to_string();
 
@@ -1359,7 +1474,7 @@ mod tests {
         let mut uev_a = crate::uevent::Uevent::default();
         let relpath_a = "/0000:00:0a.0";
         uev_a.action = crate::linux_abi::U_EVENT_ACTION_ADD.to_string();
-        uev_a.subsystem = "block".to_string();
+        uev_a.subsystem = BLOCK.to_string();
         uev_a.devname = devname.to_string();
         uev_a.devpath = format!("{}{}/virtio4/block/{}", root_bus, relpath_a, devname);
         let matcher_a = VirtioBlkPciMatcher::new(relpath_a);
@@ -1378,7 +1493,7 @@ mod tests {
     #[cfg(target_arch = "s390x")]
     #[tokio::test]
     async fn test_virtio_blk_ccw_matcher() {
-        let root_bus = create_ccw_root_bus_path();
+        let root_bus = CCW_ROOT_BUS_PATH;
         let subsystem = "block";
         let devname = "vda";
         let relpath = "0.0.0002";
@@ -1443,7 +1558,7 @@ mod tests {
         let mut uev_a = crate::uevent::Uevent::default();
         let addr_a = "0:0";
         uev_a.action = crate::linux_abi::U_EVENT_ACTION_ADD.to_string();
-        uev_a.subsystem = "block".to_string();
+        uev_a.subsystem = BLOCK.to_string();
         uev_a.devname = devname.to_string();
         uev_a.devpath = format!(
             "{}/0000:00:00.0/virtio0/host0/target0:0:0/0:0:{}/block/sda",
@@ -1486,14 +1601,41 @@ mod tests {
         assert!(!matcher_a.is_match(&uev_b));
     }
 
+    #[tokio::test]
+    async fn test_mmio_block_matcher() {
+        let devname_a = "vda";
+        let devname_b = "vdb";
+        let mut uev_a = crate::uevent::Uevent::default();
+        uev_a.action = crate::linux_abi::U_EVENT_ACTION_ADD.to_string();
+        uev_a.subsystem = BLOCK.to_string();
+        uev_a.devname = devname_a.to_string();
+        uev_a.devpath = format!(
+            "/sys/devices/virtio-mmio-cmdline/virtio-mmio.0/virtio0/block/{}",
+            devname_a
+        );
+        let matcher_a = MmioBlockMatcher::new(devname_a);
+
+        let mut uev_b = uev_a.clone();
+        uev_b.devpath = format!(
+            "/sys/devices/virtio-mmio-cmdline/virtio-mmio.4/virtio4/block/{}",
+            devname_b
+        );
+        let matcher_b = MmioBlockMatcher::new(devname_b);
+
+        assert!(matcher_a.is_match(&uev_a));
+        assert!(matcher_b.is_match(&uev_b));
+        assert!(!matcher_b.is_match(&uev_a));
+        assert!(!matcher_a.is_match(&uev_b));
+    }
+
     #[test]
-    fn test_split_vfio_option() {
+    fn test_split_vfio_pci_option() {
         assert_eq!(
-            split_vfio_option("0000:01:00.0=02/01"),
+            split_vfio_pci_option("0000:01:00.0=02/01"),
             Some(("0000:01:00.0", "02/01"))
         );
-        assert_eq!(split_vfio_option("0000:01:00.0=02/01=rubbish"), None);
-        assert_eq!(split_vfio_option("0000:01:00.0"), None);
+        assert_eq!(split_vfio_pci_option("0000:01:00.0=02/01=rubbish"), None);
+        assert_eq!(split_vfio_pci_option("0000:01:00.0"), None);
     }
 
     #[test]
@@ -1572,4 +1714,35 @@ mod tests {
         // Test dev2
         assert!(pci_iommu_group(&syspci, dev2).is_err());
     }
+
+    #[cfg(target_arch = "s390x")]
+    #[tokio::test]
+    async fn test_vfio_ap_matcher() {
+        let subsystem = "ap";
+        let card = "0a";
+        let relpath = format!("{}.0001", card);
+
+        let mut uev = Uevent::default();
+        uev.action = U_EVENT_ACTION_ADD.to_string();
+        uev.subsystem = subsystem.to_string();
+        uev.devpath = format!("{}/card{}/{}", AP_ROOT_BUS_PATH, card, relpath);
+
+        let ap_address = ap::Address::from_str(&relpath).unwrap();
+        let matcher = ApMatcher::new(ap_address);
+
+        assert!(matcher.is_match(&uev));
+
+        let mut uev_remove = uev.clone();
+        uev_remove.action = U_EVENT_ACTION_REMOVE.to_string();
+        assert!(!matcher.is_match(&uev_remove));
+
+        let mut uev_other_device = uev.clone();
+        uev_other_device.devpath = format!(
+            "{}/card{}/{}",
+            AP_ROOT_BUS_PATH,
+            card,
+            format!("{}.0002", card)
+        );
+        assert!(!matcher.is_match(&uev_other_device));
+    }
 }

src/agent/src/linux_abi.rs

@@ -3,6 +3,8 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
+use cfg_if::cfg_if;
+
 /// Linux ABI related constants.
 
 #[cfg(target_arch = "aarch64")]
@@ -31,7 +33,7 @@ pub fn create_pci_root_bus_path() -> String {
 
     // check if there is pci bus path for acpi
     acpi_sysfs_dir.push_str(&acpi_root_bus_path);
-    if let Ok(_) = fs::metadata(&acpi_sysfs_dir) {
+    if fs::metadata(&acpi_sysfs_dir).is_ok() {
         return acpi_root_bus_path;
     }
 
@@ -64,10 +66,14 @@ pub fn create_pci_root_bus_path() -> String {
     ret
 }
 
-#[cfg(target_arch = "s390x")]
-pub fn create_ccw_root_bus_path() -> String {
-    String::from("/devices/css0")
+cfg_if! {
+    if #[cfg(target_arch = "s390x")] {
+        pub const CCW_ROOT_BUS_PATH: &str = "/devices/css0";
+        pub const AP_ROOT_BUS_PATH: &str = "/devices/ap";
+        pub const AP_SCANS_PATH: &str = "/sys/bus/ap/scans";
+    }
 }
+
 // From https://www.kernel.org/doc/Documentation/acpi/namespace.txt
 // The Linux kernel's core ACPI subsystem creates struct acpi_device
 // objects for ACPI namespace objects representing devices, power resources
@@ -75,7 +81,8 @@ pub fn create_ccw_root_bus_path() -> String {
 // sysfs as directories in the subtree under /sys/devices/LNXSYSTM:00
 pub const ACPI_DEV_PATH: &str = "/devices/LNXSYSTM";
 
-pub const SYSFS_CPU_ONLINE_PATH: &str = "/sys/devices/system/cpu";
+pub const SYSFS_CPU_PATH: &str = "/sys/devices/system/cpu";
+pub const SYSFS_CPU_ONLINE_PATH: &str = "/sys/devices/system/cpu/online";
 
 pub const SYSFS_MEMORY_BLOCK_SIZE_PATH: &str = "/sys/devices/system/memory/block_size_bytes";
 pub const SYSFS_MEMORY_HOTPLUG_PROBE_PATH: &str = "/sys/devices/system/memory/probe";

src/agent/src/main.rs

@@ -20,6 +20,7 @@ extern crate scopeguard;
 extern crate slog;
 
 use anyhow::{anyhow, Context, Result};
+use cfg_if::cfg_if;
 use clap::{AppSettings, Parser};
 use nix::fcntl::OFlag;
 use nix::sys::socket::{self, AddressFamily, SockFlag, SockType, VsockAddr};
@@ -34,8 +35,6 @@ use std::process::exit;
 use std::sync::Arc;
 use tracing::{instrument, span};
 
-#[cfg(target_arch = "s390x")]
-mod ccw;
 mod config;
 mod console;
 mod device;
@@ -66,7 +65,7 @@ use tokio::{
     io::AsyncWrite,
     sync::{
         watch::{channel, Receiver},
-        Mutex, RwLock,
+        Mutex,
     },
     task::JoinHandle,
 };
@@ -74,15 +73,21 @@ use tokio::{
 mod rpc;
 mod tracer;
 
+cfg_if! {
+    if #[cfg(target_arch = "s390x")] {
+        mod ap;
+        mod ccw;
+    }
+}
+
 const NAME: &str = "kata-agent";
 
 lazy_static! {
-    static ref AGENT_CONFIG: Arc<RwLock<AgentConfig>> = Arc::new(RwLock::new(
+    static ref AGENT_CONFIG: AgentConfig =
         // Note: We can't do AgentOpts.parse() here to send through the processed arguments to AgentConfig
         // clap::Parser::parse() greedily process all command line input including cargo test parameters,
         // so should only be used inside main.
-        AgentConfig::from_cmdline("/proc/cmdline", env::args().collect()).unwrap()
-    ));
+        AgentConfig::from_cmdline("/proc/cmdline", env::args().collect()).unwrap();
 }
 
 #[derive(Parser)]
@@ -175,13 +180,13 @@ async fn real_main() -> std::result::Result<(), Box<dyn std::error::Error>> {
 
         lazy_static::initialize(&AGENT_CONFIG);
 
-        init_agent_as_init(&logger, AGENT_CONFIG.read().await.unified_cgroup_hierarchy)?;
+        init_agent_as_init(&logger, AGENT_CONFIG.unified_cgroup_hierarchy)?;
         drop(logger_async_guard);
     } else {
         lazy_static::initialize(&AGENT_CONFIG);
     }
 
-    let config = AGENT_CONFIG.read().await;
+    let config = &AGENT_CONFIG;
     let log_vport = config.log_vport as u32;
 
     let log_handle = tokio::spawn(create_logger_task(rfd, log_vport, shutdown_rx.clone()));
@@ -194,7 +199,7 @@ async fn real_main() -> std::result::Result<(), Box<dyn std::error::Error>> {
     let (logger, logger_async_guard) =
         logging::create_logger(NAME, "agent", config.log_level, writer);
 
-    announce(&logger, &config);
+    announce(&logger, config);
 
     // This variable is required as it enables the global (and crucially static) logger,
     // which is required to satisfy the the lifetime constraints of the auto-generated gRPC code.
@@ -222,7 +227,7 @@ async fn real_main() -> std::result::Result<(), Box<dyn std::error::Error>> {
     let span_guard = root_span.enter();
 
     // Start the sandbox and wait for its ttRPC server to end
-    start_sandbox(&logger, &config, init_mode, &mut tasks, shutdown_rx.clone()).await?;
+    start_sandbox(&logger, config, init_mode, &mut tasks, shutdown_rx.clone()).await?;
 
     // Install a NOP logger for the remainder of the shutdown sequence
     // to ensure any log calls made by local crates using the scope logger

src/agent/src/metrics.rs

@@ -15,11 +15,9 @@ use tracing::instrument;
 const NAMESPACE_KATA_AGENT: &str = "kata_agent";
 const NAMESPACE_KATA_GUEST: &str = "kata_guest";
 
-// Convenience macro to obtain the scope logger
-macro_rules! sl {
-    () => {
-        slog_scope::logger().new(o!("subsystem" => "metrics"))
-    };
+// Convenience function to obtain the scope logger.
+fn sl() -> slog::Logger {
+    slog_scope::logger().new(o!("subsystem" => "metrics"))
 }
 
 lazy_static! {
@@ -139,7 +137,7 @@ fn update_agent_metrics() -> Result<()> {
         Ok(p) => p,
         Err(e) => {
             // FIXME: return Ok for all errors?
-            warn!(sl!(), "failed to create process instance: {:?}", e);
+            warn!(sl(), "failed to create process instance: {:?}", e);
 
             return Ok(());
         }
@@ -160,7 +158,7 @@ fn update_agent_metrics() -> Result<()> {
     // io
     match me.io() {
         Err(err) => {
-            info!(sl!(), "failed to get process io stat: {:?}", err);
+            info!(sl(), "failed to get process io stat: {:?}", err);
         }
         Ok(io) => {
             set_gauge_vec_proc_io(&AGENT_IO_STAT, &io);
@@ -169,7 +167,7 @@ fn update_agent_metrics() -> Result<()> {
 
     match me.stat() {
         Err(err) => {
-            info!(sl!(), "failed to get process stat: {:?}", err);
+            info!(sl(), "failed to get process stat: {:?}", err);
         }
         Ok(stat) => {
             set_gauge_vec_proc_stat(&AGENT_PROC_STAT, &stat);
@@ -177,7 +175,7 @@ fn update_agent_metrics() -> Result<()> {
     }
 
     match me.status() {
-        Err(err) => error!(sl!(), "failed to get process status: {:?}", err),
+        Err(err) => error!(sl(), "failed to get process status: {:?}", err),
         Ok(status) => set_gauge_vec_proc_status(&AGENT_PROC_STATUS, &status),
     }
 
@@ -189,7 +187,7 @@ fn update_guest_metrics() {
     // try get load and task info
     match procfs::LoadAverage::new() {
         Err(err) => {
-            info!(sl!(), "failed to get guest LoadAverage: {:?}", err);
+            info!(sl(), "failed to get guest LoadAverage: {:?}", err);
         }
         Ok(load) => {
             GUEST_LOAD
@@ -209,7 +207,7 @@ fn update_guest_metrics() {
     // try to get disk stats
     match procfs::diskstats() {
         Err(err) => {
-            info!(sl!(), "failed to get guest diskstats: {:?}", err);
+            info!(sl(), "failed to get guest diskstats: {:?}", err);
         }
         Ok(diskstats) => {
             for diskstat in diskstats {
@@ -221,7 +219,7 @@ fn update_guest_metrics() {
     // try to get vm stats
     match procfs::vmstat() {
         Err(err) => {
-            info!(sl!(), "failed to get guest vmstat: {:?}", err);
+            info!(sl(), "failed to get guest vmstat: {:?}", err);
         }
         Ok(vmstat) => {
             for (k, v) in vmstat {
@@ -233,7 +231,7 @@ fn update_guest_metrics() {
     // cpu stat
     match procfs::KernelStats::new() {
         Err(err) => {
-            info!(sl!(), "failed to get guest KernelStats: {:?}", err);
+            info!(sl(), "failed to get guest KernelStats: {:?}", err);
         }
         Ok(kernel_stats) => {
             set_gauge_vec_cpu_time(&GUEST_CPU_TIME, "total", &kernel_stats.total);
@@ -246,7 +244,7 @@ fn update_guest_metrics() {
     // try to get net device stats
     match procfs::net::dev_status() {
         Err(err) => {
-            info!(sl!(), "failed to get guest net::dev_status: {:?}", err);
+            info!(sl(), "failed to get guest net::dev_status: {:?}", err);
         }
         Ok(devs) => {
             // netdev: map[string]procfs::net::DeviceStatus
@@ -259,7 +257,7 @@ fn update_guest_metrics() {
     // get statistics about memory from /proc/meminfo
     match procfs::Meminfo::new() {
         Err(err) => {
-            info!(sl!(), "failed to get guest Meminfo: {:?}", err);
+            info!(sl(), "failed to get guest Meminfo: {:?}", err);
         }
         Ok(meminfo) => {
             set_gauge_vec_meminfo(&GUEST_MEMINFO, &meminfo);

src/agent/src/mount.rs

@@ -21,10 +21,11 @@ use nix::unistd::{Gid, Uid};
 use regex::Regex;
 
 use crate::device::{
-    get_scsi_device_name, get_virtio_blk_pci_device_name, online_device, wait_for_pmem_device,
-    DRIVER_9P_TYPE, DRIVER_BLK_CCW_TYPE, DRIVER_BLK_TYPE, DRIVER_EPHEMERAL_TYPE, DRIVER_LOCAL_TYPE,
-    DRIVER_MMIO_BLK_TYPE, DRIVER_NVDIMM_TYPE, DRIVER_OVERLAYFS_TYPE, DRIVER_SCSI_TYPE,
-    DRIVER_VIRTIOFS_TYPE, DRIVER_WATCHABLE_BIND_TYPE, FS_TYPE_HUGETLB,
+    get_scsi_device_name, get_virtio_blk_pci_device_name, get_virtio_mmio_device_name,
+    online_device, wait_for_pmem_device, DRIVER_9P_TYPE, DRIVER_BLK_CCW_TYPE, DRIVER_BLK_TYPE,
+    DRIVER_EPHEMERAL_TYPE, DRIVER_LOCAL_TYPE, DRIVER_MMIO_BLK_TYPE, DRIVER_NVDIMM_TYPE,
+    DRIVER_OVERLAYFS_TYPE, DRIVER_SCSI_TYPE, DRIVER_VIRTIOFS_TYPE, DRIVER_WATCHABLE_BIND_TYPE,
+    FS_TYPE_HUGETLB,
 };
 use crate::linux_abi::*;
 use crate::pci;
@@ -35,6 +36,7 @@ use crate::Sandbox;
 use crate::{ccw, device::get_virtio_blk_ccw_device_name};
 use anyhow::{anyhow, Context, Result};
 use slog::Logger;
+
 use tracing::instrument;
 
 pub const TYPE_ROOTFS: &str = "rootfs";
@@ -144,6 +146,11 @@ pub const STORAGE_HANDLER_LIST: &[&str] = &[
     DRIVER_WATCHABLE_BIND_TYPE,
 ];
 
+#[instrument]
+pub fn get_mounts() -> Result<String, std::io::Error> {
+    fs::read_to_string("/proc/mounts")
+}
+
 #[instrument]
 pub fn baremount(
     source: &Path,
@@ -167,6 +174,31 @@ pub fn baremount(
         return Err(anyhow!("need mount FS type"));
     }
 
+    let destination_str = destination.to_string_lossy();
+    let mounts = get_mounts().unwrap_or_else(|_| String::new());
+    let already_mounted = mounts
+        .lines()
+        .map(|line| line.split_whitespace().collect::<Vec<&str>>())
+        .filter(|parts| parts.len() >= 3) // ensure we have at least [source}, destination, and fs_type
+        .any(|parts| {
+            // Check if source, destination and fs_type match any entry in /proc/mounts
+            // minimal check is for destination an fstype since source can have different names like:
+            // udev /dev devtmpfs
+            //  dev /dev devtmpfs
+            // depending on which entity is mounting the dev/fs/pseudo-fs
+            parts[1] == destination_str && parts[2] == fs_type
+        });
+
+    if already_mounted {
+        slog_info!(
+            logger,
+            "{:?} is already mounted at {:?}",
+            source,
+            destination
+        );
+        return Ok(());
+    }
+
     info!(
         logger,
         "baremount source={:?}, dest={:?}, fs_type={:?}, options={:?}, flags={:?}",
@@ -211,10 +243,10 @@ async fn ephemeral_storage_handler(
     // By now we only support one option field: "fsGroup" which
     // isn't an valid mount option, thus we should remove it when
     // do mount.
-    if storage.options.len() > 0 {
+    if !storage.options.is_empty() {
         // ephemeral_storage didn't support mount options except fsGroup.
         let mut new_storage = storage.clone();
-        new_storage.options = protobuf::RepeatedField::default();
+        new_storage.options = Default::default();
         common_storage_handler(logger, &new_storage)?;
 
         let opts_vec: Vec<String> = storage.options.to_vec();
@@ -240,6 +272,70 @@ async fn ephemeral_storage_handler(
     Ok("".to_string())
 }
 
+// update_ephemeral_mounts takes a list of ephemeral mounts and remounts them
+// with mount options passed by the caller
+#[instrument]
+pub async fn update_ephemeral_mounts(
+    logger: Logger,
+    storages: Vec<Storage>,
+    sandbox: Arc<Mutex<Sandbox>>,
+) -> Result<()> {
+    for (_, storage) in storages.iter().enumerate() {
+        let handler_name = storage.driver.clone();
+        let logger = logger.new(o!(
+	    "msg" => "updating tmpfs storage",
+            "subsystem" => "storage",
+            "storage-type" => handler_name.to_owned()));
+
+        match handler_name.as_str() {
+            DRIVER_EPHEMERAL_TYPE => {
+                fs::create_dir_all(Path::new(&storage.mount_point))?;
+
+                if storage.options.is_empty() {
+                    continue;
+                } else {
+                    // assume that fsGid has already been set
+                    let mut opts = Vec::<&str>::new();
+                    for (_, opt) in storage.options.iter().enumerate() {
+                        if opt.starts_with(FS_GID) {
+                            continue;
+                        }
+                        opts.push(opt)
+                    }
+                    let mount_path = Path::new(&storage.mount_point);
+                    let src_path = Path::new(&storage.source);
+
+                    let (flags, options) = parse_mount_flags_and_options(opts);
+
+                    info!(logger, "mounting storage";
+                    "mount-source" => src_path.display(),
+                    "mount-destination" => mount_path.display(),
+                    "mount-fstype"  => storage.fstype.as_str(),
+                    "mount-options" => options.as_str(),
+                    );
+
+                    return baremount(
+                        src_path,
+                        mount_path,
+                        storage.fstype.as_str(),
+                        flags,
+                        options.as_str(),
+                        &logger,
+                    );
+                }
+            }
+            _ => {
+                return Err(anyhow!(
+                    "Unsupported storage type for syncing mounts {}. Only ephemeral storage update is supported",
+                    storage.driver.to_owned()
+                ));
+            }
+        };
+    }
+
+    Ok(())
+}
+
 #[instrument]
 async fn overlayfs_storage_handler(
     logger: &Logger,
@@ -409,8 +505,14 @@ async fn virtiommio_blk_storage_handler(
     storage: &Storage,
     sandbox: Arc<Mutex<Sandbox>>,
 ) -> Result<String> {
+    let storage = storage.clone();
+    if !Path::new(&storage.source).exists() {
+        get_virtio_mmio_device_name(&sandbox, &storage.source)
+            .await
+            .context("failed to get mmio device name")?;
+    }
     //The source path is VmPath
-    common_storage_handler(logger, storage)
+    common_storage_handler(logger, &storage)
 }
 
 // virtiofs_storage_handler handles the storage for virtio-fs.
@@ -590,7 +692,7 @@ pub fn set_ownership(logger: &Logger, storage: &Storage) -> Result<()> {
     if storage.fs_group.is_none() {
         return Ok(());
     }
-    let fs_group = storage.get_fs_group();
+    let fs_group = storage.fs_group();
 
     let mut read_only = false;
     let opts_vec: Vec<String> = storage.options.to_vec();
@@ -607,7 +709,7 @@ pub fn set_ownership(logger: &Logger, storage: &Storage) -> Result<()> {
         err
     })?;
 
-    if fs_group.group_change_policy == FSGroupChangePolicy::OnRootMismatch
+    if fs_group.group_change_policy == FSGroupChangePolicy::OnRootMismatch.into()
         && metadata.gid() == fs_group.group_id
     {
         let mut mask = if read_only { RO_MASK } else { RW_MASK };
@@ -654,6 +756,14 @@ pub fn recursive_ownership_change(
         mask |= EXEC_MASK;
         mask |= MODE_SETGID;
     }
+
+    // We do not want to change the permission of the underlying file
+    // using symlink. Hence we skip symlinks from recursive ownership
+    // and permission changes.
+    if path.is_symlink() {
+        return Ok(());
+    }
+
     nix::unistd::chown(path, uid, gid)?;
 
     if gid.is_some() {
@@ -1030,8 +1140,8 @@ fn parse_options(option_list: Vec<String>) -> HashMap<String, String> {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use protobuf::RepeatedField;
     use protocols::agent::FSGroup;
+    use slog::Drain;
     use std::fs::File;
     use std::fs::OpenOptions;
     use std::io::Write;
@@ -1042,6 +1152,31 @@ mod tests {
         skip_if_not_root, skip_loop_by_user, skip_loop_if_not_root, skip_loop_if_root,
     };
 
+    #[test]
+    fn test_already_baremounted() {
+        let plain = slog_term::PlainSyncDecorator::new(std::io::stdout());
+        let logger = Logger::root(slog_term::FullFormat::new(plain).build().fuse(), o!());
+
+        let test_cases = [
+            ("dev", "/dev", "devtmpfs"),
+            ("udev", "/dev", "devtmpfs"),
+            ("proc", "/proc", "proc"),
+            ("sysfs", "/sys", "sysfs"),
+        ];
+
+        for &(source, destination, fs_type) in &test_cases {
+            let source = Path::new(source);
+            let destination = Path::new(destination);
+            let flags = MsFlags::MS_RDONLY;
+            let options = "mode=755";
+            println!(
+                "testing if already mounted baremount({:?} {:?} {:?})",
+                source, destination, fs_type
+            );
+            assert!(baremount(source, destination, fs_type, flags, options, &logger).is_ok());
+        }
+    }
+
     #[test]
     fn test_mount() {
         #[derive(Debug)]
@@ -1951,9 +2086,8 @@ mod tests {
                 mount_path: "rw_mount",
                 fs_group: Some(FSGroup {
                     group_id: 3000,
-                    group_change_policy: FSGroupChangePolicy::Always,
-                    unknown_fields: Default::default(),
-                    cached_size: Default::default(),
+                    group_change_policy: FSGroupChangePolicy::Always.into(),
+                    ..Default::default()
                 }),
                 read_only: false,
                 expected_group_id: 3000,
@@ -1963,9 +2097,8 @@ mod tests {
                 mount_path: "ro_mount",
                 fs_group: Some(FSGroup {
                     group_id: 3000,
-                    group_change_policy: FSGroupChangePolicy::OnRootMismatch,
-                    unknown_fields: Default::default(),
-                    cached_size: Default::default(),
+                    group_change_policy: FSGroupChangePolicy::OnRootMismatch.into(),
+                    ..Default::default()
                 }),
                 read_only: true,
                 expected_group_id: 3000,
@@ -1985,10 +2118,7 @@ mod tests {
             let directory_mode = mount_dir.as_path().metadata().unwrap().permissions().mode();
             let mut storage_data = Storage::new();
             if d.read_only {
-                storage_data.set_options(RepeatedField::from_slice(&[
-                    "foo".to_string(),
-                    "ro".to_string(),
-                ]));
+                storage_data.set_options(vec!["foo".to_string(), "ro".to_string()]);
             }
             if let Some(fs_group) = d.fs_group.clone() {
                 storage_data.set_fs_group(fs_group);

src/agent/src/netlink.rs

@@ -7,7 +7,6 @@ use anyhow::{anyhow, Context, Result};
 use futures::{future, StreamExt, TryStreamExt};
 use ipnetwork::{IpNetwork, Ipv4Network, Ipv6Network};
 use nix::errno::Errno;
-use protobuf::RepeatedField;
 use protocols::types::{ARPNeighbor, IPAddress, IPFamily, Interface, Route};
 use rtnetlink::{new_connection, packet, IpVersion};
 use std::convert::{TryFrom, TryInto};
@@ -83,13 +82,34 @@ impl Handle {
 
         // Add new ip addresses from request
         for ip_address in &iface.IPAddresses {
-            let ip = IpAddr::from_str(ip_address.get_address())?;
-            let mask = ip_address.get_mask().parse::<u8>()?;
+            let ip = IpAddr::from_str(ip_address.address())?;
+            let mask = ip_address.mask().parse::<u8>()?;
 
             self.add_addresses(link.index(), std::iter::once(IpNetwork::new(ip, mask)?))
                 .await?;
         }
 
+        // we need to update the link's interface name, thus we should rename the existed link whose name
+        // is the same with the link's request name, otherwise, it would update the link failed with the
+        // name conflicted.
+        let mut new_link = None;
+        if link.name() != iface.name {
+            if let Ok(link) = self.find_link(LinkFilter::Name(iface.name.as_str())).await {
+                // update the existing interface name with a temporary name, otherwise
+                // it would failed to udpate this interface with an existing name.
+                let mut request = self.handle.link().set(link.index());
+                request.message_mut().header = link.header.clone();
+
+                request
+                    .name(format!("{}_temp", link.name()))
+                    .up()
+                    .execute()
+                    .await?;
+
+                new_link = Some(link);
+            }
+        }
+
         // Update link
         let mut request = self.handle.link().set(link.index());
         request.message_mut().header = link.header.clone();
@@ -102,6 +122,14 @@ impl Handle {
             .execute()
             .await?;
 
+        // swap the updated iface's name.
+        if let Some(nlink) = new_link {
+            let mut request = self.handle.link().set(nlink.index());
+            request.message_mut().header = nlink.header.clone();
+
+            request.name(link.name()).up().execute().await?;
+        }
+
         Ok(())
     }
 
@@ -152,7 +180,7 @@ impl Handle {
                 .map(|p| p.try_into())
                 .collect::<Result<Vec<IPAddress>>>()?;
 
-            iface.IPAddresses = RepeatedField::from_vec(ips);
+            iface.IPAddresses = ips;
 
             list.push(iface);
         }
@@ -334,7 +362,7 @@ impl Handle {
 
             // `rtnetlink` offers a separate request builders for different IP versions (IP v4 and v6).
             // This if branch is a bit clumsy because it does almost the same.
-            if route.get_family() == IPFamily::v6 {
+            if route.family() == IPFamily::v6 {
                 let dest_addr = if !route.dest.is_empty() {
                     Ipv6Network::from_str(&route.dest)?
                 } else {
@@ -368,9 +396,9 @@ impl Handle {
                     if Errno::from_i32(message.code.abs()) != Errno::EEXIST {
                         return Err(anyhow!(
                             "Failed to add IP v6 route (src: {}, dst: {}, gtw: {},Err: {})",
-                            route.get_source(),
-                            route.get_dest(),
-                            route.get_gateway(),
+                            route.source(),
+                            route.dest(),
+                            route.gateway(),
                             message
                         ));
                     }
@@ -409,9 +437,9 @@ impl Handle {
                     if Errno::from_i32(message.code.abs()) != Errno::EEXIST {
                         return Err(anyhow!(
                             "Failed to add IP v4 route (src: {}, dst: {}, gtw: {},Err: {})",
-                            route.get_source(),
-                            route.get_dest(),
-                            route.get_gateway(),
+                            route.source(),
+                            route.dest(),
+                            route.gateway(),
                             message
                         ));
                     }
@@ -506,7 +534,7 @@ impl Handle {
             self.add_arp_neighbor(&neigh).await.map_err(|err| {
                 anyhow!(
                     "Failed to add ARP neighbor {}: {:?}",
-                    neigh.get_toIPAddress().get_address(),
+                    neigh.toIPAddress().address(),
                     err
                 )
             })?;
@@ -725,7 +753,7 @@ impl TryFrom<Address> for IPAddress {
         let mask = format!("{}", value.0.header.prefix_len);
 
         Ok(IPAddress {
-            family,
+            family: family.into(),
             address,
             mask,
             ..Default::default()

src/agent/src/network.rs

@@ -7,6 +7,7 @@ use anyhow::{anyhow, Result};
 use nix::mount::{self, MsFlags};
 use slog::Logger;
 use std::fs;
+use std::path;
 
 const KATA_GUEST_SANDBOX_DNS_FILE: &str = "/run/kata-containers/sandbox/resolv.conf";
 const GUEST_DNS_FILE: &str = "/etc/resolv.conf";
@@ -64,6 +65,12 @@ fn do_setup_guest_dns(logger: Logger, dns_list: Vec<String>, src: &str, dst: &st
         .map(|x| x.trim())
         .collect::<Vec<&str>>()
         .join("\n");
+
+    // make sure the src file's parent path exist.
+    let file_path = path::Path::new(src);
+    if let Some(p) = file_path.parent() {
+        fs::create_dir_all(p)?;
+    }
     fs::write(src, content)?;
 
     // bind mount to /etc/resolv.conf

src/agent/src/sandbox.rs

@@ -12,6 +12,7 @@ use crate::pci;
 use crate::uevent::{Uevent, UeventMatcher};
 use crate::watcher::BindWatcher;
 use anyhow::{anyhow, Context, Result};
+use kata_types::cpu::CpuSet;
 use libc::pid_t;
 use oci::{Hook, Hooks};
 use protocols::agent::OnlineCPUMemRequest;
@@ -25,6 +26,7 @@ use std::collections::HashMap;
 use std::fs;
 use std::os::unix::fs::PermissionsExt;
 use std::path::Path;
+use std::str::FromStr;
 use std::sync::Arc;
 use std::{thread, time};
 use tokio::sync::mpsc::{channel, Receiver, Sender};
@@ -263,12 +265,12 @@ impl Sandbox {
     pub fn online_cpu_memory(&self, req: &OnlineCPUMemRequest) -> Result<()> {
         if req.nb_cpus > 0 {
             // online cpus
-            online_cpus(&self.logger, req.nb_cpus as i32)?;
+            online_cpus(&self.logger, req.nb_cpus as i32).context("online cpus")?;
         }
 
         if !req.cpu_only {
             // online memory
-            online_memory(&self.logger)?;
+            online_memory(&self.logger).context("online memory")?;
         }
 
         if req.nb_cpus == 0 {
@@ -431,27 +433,37 @@ fn online_resources(logger: &Logger, path: &str, pattern: &str, num: i32) -> Res
 }
 
 // max wait for all CPUs to online will use 50 * 100 = 5 seconds.
-const ONLINE_CPUMEM_WATI_MILLIS: u64 = 50;
-const ONLINE_CPUMEM_MAX_RETRIES: u32 = 100;
+const ONLINE_CPUMEM_WAIT_MILLIS: u64 = 50;
+const ONLINE_CPUMEM_MAX_RETRIES: i32 = 100;
 
 #[instrument]
 fn online_cpus(logger: &Logger, num: i32) -> Result<i32> {
-    let mut onlined_count: i32 = 0;
+    let mut onlined_cpu_count = onlined_cpus().context("onlined cpu count")?;
+    // for some vmms, like dragonball, they will online cpus for us
+    // so check first whether agent need to do the online operation
+    if onlined_cpu_count >= num {
+        return Ok(num);
+    }
 
     for i in 0..ONLINE_CPUMEM_MAX_RETRIES {
-        let r = online_resources(
+        // online num resources
+        online_resources(
             logger,
-            SYSFS_CPU_ONLINE_PATH,
+            SYSFS_CPU_PATH,
             r"cpu[0-9]+",
-            num - onlined_count,
-        );
+            num - onlined_cpu_count,
+        )
+        .context("online cpu resource")?;
 
-        onlined_count += r?;
-        if onlined_count == num {
-            info!(logger, "online {} CPU(s) after {} retries", num, i);
+        onlined_cpu_count = onlined_cpus().context("onlined cpu count")?;
+        if onlined_cpu_count >= num {
+            info!(
+                logger,
+                "Currently {} onlined CPU(s) after {} retries", onlined_cpu_count, i
+            );
             return Ok(num);
         }
-        thread::sleep(time::Duration::from_millis(ONLINE_CPUMEM_WATI_MILLIS));
+        thread::sleep(time::Duration::from_millis(ONLINE_CPUMEM_WAIT_MILLIS));
     }
 
     Err(anyhow!(
@@ -463,10 +475,18 @@ fn online_cpus(logger: &Logger, num: i32) -> Result<i32> {
 
 #[instrument]
 fn online_memory(logger: &Logger) -> Result<()> {
-    online_resources(logger, SYSFS_MEMORY_ONLINE_PATH, r"memory[0-9]+", -1)?;
+    online_resources(logger, SYSFS_MEMORY_ONLINE_PATH, r"memory[0-9]+", -1)
+        .context("online memory resource")?;
     Ok(())
 }
 
+fn onlined_cpus() -> Result<i32> {
+    let content =
+        fs::read_to_string(SYSFS_CPU_ONLINE_PATH).context("read sysfs cpu online file")?;
+    let online_cpu_set = CpuSet::from_str(content.trim())?;
+    Ok(online_cpu_set.len() as i32)
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;

src/agent/src/signal.rs

@@ -57,7 +57,7 @@ async fn handle_sigchild(logger: Logger, sandbox: Arc<Mutex<Sandbox>>) -> Result
                 continue;
             }
 
-            let mut p = process.unwrap();
+            let p = process.unwrap();
 
             let ret: i32 = match wait_status {
                 WaitStatus::Exited(_, c) => c,

src/agent/src/tracer.rs

@@ -69,7 +69,7 @@ macro_rules! trace_rpc_call {
             propagator.extract(&extract_carrier_from_ttrpc($ctx))
         });
 
-        info!(sl!(), "rpc call from shim to agent: {:?}", $name);
+        info!(sl(), "rpc call from shim to agent: {:?}", $name);
 
         // generate tracing span
         let rpc_span = span!(tracing::Level::INFO, $name, "mod"="rpc.rs", req=?$req);

src/agent/src/uevent.rs

@@ -19,11 +19,9 @@ use tokio::sync::watch::Receiver;
 use tokio::sync::Mutex;
 use tracing::instrument;
 
-// Convenience macro to obtain the scope logger
-macro_rules! sl {
-    () => {
-        slog_scope::logger().new(o!("subsystem" => "uevent"))
-    };
+// Convenience function to obtain the scope logger.
+fn sl() -> slog::Logger {
+    slog_scope::logger().new(o!("subsystem" => "uevent"))
 }
 
 #[derive(Debug, Default, Clone, PartialEq, Eq)]
@@ -120,11 +118,11 @@ pub async fn wait_for_uevent(
 ) -> Result<Uevent> {
     let logprefix = format!("Waiting for {:?}", &matcher);
 
-    info!(sl!(), "{}", logprefix);
+    info!(sl(), "{}", logprefix);
     let mut sb = sandbox.lock().await;
     for uev in sb.uevent_map.values() {
         if matcher.is_match(uev) {
-            info!(sl!(), "{}: found {:?} in uevent map", logprefix, &uev);
+            info!(sl(), "{}: found {:?} in uevent map", logprefix, &uev);
             return Ok(uev.clone());
         }
     }
@@ -139,9 +137,9 @@ pub async fn wait_for_uevent(
     sb.uevent_watchers.push(Some((Box::new(matcher), tx)));
     drop(sb); // unlock
 
-    info!(sl!(), "{}: waiting on channel", logprefix);
+    info!(sl(), "{}: waiting on channel", logprefix);
 
-    let hotplug_timeout = AGENT_CONFIG.read().await.hotplug_timeout;
+    let hotplug_timeout = AGENT_CONFIG.hotplug_timeout;
 
     let uev = match tokio::time::timeout(hotplug_timeout, rx).await {
         Ok(v) => v?,
@@ -157,7 +155,7 @@ pub async fn wait_for_uevent(
         }
     };
 
-    info!(sl!(), "{}: found {:?} on channel", logprefix, &uev);
+    info!(sl(), "{}: found {:?} on channel", logprefix, &uev);
     Ok(uev)
 }
 

src/dragonball/Cargo.toml

@@ -10,25 +10,28 @@ license = "Apache-2.0"
 edition = "2018"
 
 [dependencies]
+anyhow = "1.0.32"
 arc-swap = "1.5.0"
 bytes = "1.1.0"
-dbs-address-space = "0.2.0"
-dbs-allocator = "0.1.0"
-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 = "0.2.0"
-dbs-virtio-devices = { version = "0.1.0", optional = true, features = ["virtio-mmio"] }
-kvm-bindings = "0.5.0"
-kvm-ioctls = "0.11.0"
+dbs-address-space =  { path = "./src/dbs_address_space" }
+dbs-allocator = { path = "./src/dbs_allocator" }
+dbs-arch = { path = "./src/dbs_arch" }
+dbs-boot = { path = "./src/dbs_boot" }
+dbs-device = { path = "./src/dbs_device" }
+dbs-interrupt = { path = "./src/dbs_interrupt", features = ["kvm-irq"] }
+dbs-legacy-devices = { path = "./src/dbs_legacy_devices" }
+dbs-upcall = { path = "./src/dbs_upcall" , optional = true }
+dbs-utils = { path = "./src/dbs_utils" }
+dbs-virtio-devices = { path = "./src/dbs_virtio_devices", optional = true, features = ["virtio-mmio"] }
+kvm-bindings = "0.6.0"
+kvm-ioctls = "0.12.0"
 lazy_static = "1.2"
 libc = "0.2.39"
 linux-loader = "0.6.0"
 log = "0.4.14"
 nix = "0.24.2"
+procfs = "0.12.0"
+prometheus = { version = "0.13.0", features = ["process"] }
 seccompiler = "0.2.0"
 serde = "1.0.27"
 serde_derive = "1.0.27"
@@ -37,20 +40,23 @@ slog = "2.5.2"
 slog-scope = "4.4.0"
 thiserror = "1"
 vmm-sys-util = "0.11.0"
-virtio-queue = { version = "0.4.0", optional = true }
+virtio-queue = { version = "0.6.0", optional = true }
 vm-memory = { version = "0.9.0", features = ["backend-mmap"] }
+crossbeam-channel = "0.5.6"
 
 [dev-dependencies]
-slog-term = "2.9.0"
 slog-async = "2.7.0"
+slog-term = "2.9.0"
 test-utils = { path = "../libs/test-utils" }
 
 [features]
 acpi = []
-atomic-guest-memory = [ "vm-memory/backend-atomic" ]
+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"]
+virtio-mem = ["dbs-virtio-devices/virtio-mem", "virtio-queue", "atomic-guest-memory"]
+virtio-balloon = ["dbs-virtio-devices/virtio-balloon", "virtio-queue"]

src/dragonball/Makefile

@@ -39,12 +39,15 @@ clean:
 
 test:
 ifdef SUPPORT_VIRTUALIZATION
-	cargo test --all-features --target $(TRIPLE) -- --nocapture
+	RUST_BACKTRACE=1 cargo test --all-features --target $(TRIPLE) -- --nocapture --test-threads=1
 else
 	@echo "INFO: skip testing dragonball, it need virtualization support."
 	exit 0
 endif
 
+coverage:
+	RUST_BACKTRACE=1 cargo llvm-cov --all-features --target $(TRIPLE) -- --nocapture --test-threads=1
+
 endif # ifeq ($(ARCH), s390x)
 
 .DEFAULT_GOAL := default

src/dragonball/README.md

@@ -16,10 +16,22 @@ and configuration process.
 
 # Documentation
 
-Device: [Device Document](docs/device.md)
-vCPU: [vCPU Document](docs/vcpu.md)
-API: [API Document](docs/api.md)
-`Upcall`: [`Upcall` Document](docs/upcall.md)
+- Device: [Device Document](docs/device.md)
+- vCPU: [vCPU Document](docs/vcpu.md)
+- API: [API Document](docs/api.md)
+- `Upcall`: [`Upcall` Document](docs/upcall.md)
+- `dbs_acpi`: [`dbs_acpi` Document](src/dbs_acpi/README.md)
+- `dbs_address_space`: [`dbs_address_space` Document](src/dbs_address_space/README.md)
+- `dbs_allocator`: [`dbs_allocator` Document](src/dbs_allocator/README.md)
+- `dbs_arch`: [`dbs_arch` Document](src/dbs_arch/README.md)
+- `dbs_boot`: [`dbs_boot` Document](src/dbs_boot/README.md)
+- `dbs_device`: [`dbs_device` Document](src/dbs_device/README.md)
+- `dbs_interrupt`: [`dbs_interrput` Document](src/dbs_interrupt/README.md)
+- `dbs_legacy_devices`: [`dbs_legacy_devices` Document](src/dbs_legacy_devices/README.md)
+- `dbs_tdx`: [`dbs_tdx` Document](src/dbs_tdx/README.md)
+- `dbs_upcall`: [`dbs_upcall` Document](src/dbs_upcall/README.md)
+- `dbs_utils`: [`dbs_utils` Document](src/dbs_utils/README.md)
+- `dbs_virtio_devices`: [`dbs_virtio_devices` Document](src/dbs_virtio_devices/README.md)
 
 Currently, the documents are still actively adding.
 You could see the [official documentation](docs/) page for more details.

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

@@ -50,6 +50,8 @@ pub struct InstanceInfo {
     pub vmm_version: String,
     /// The pid of the current VMM process.
     pub pid: u32,
+    /// The tid of the current VMM master thread.
+    pub master_tid: u32,
     /// The state of async actions.
     pub async_state: AsyncState,
     /// List of tids of vcpu threads (vcpu index, tid)
@@ -66,6 +68,7 @@ impl InstanceInfo {
             state: InstanceState::Uninitialized,
             vmm_version,
             pid: std::process::id(),
+            master_tid: 0,
             async_state: AsyncState::Uninitialized,
             tids: Vec::new(),
             last_instance_downtime: 0,
@@ -80,6 +83,7 @@ impl Default for InstanceInfo {
             state: InstanceState::Uninitialized,
             vmm_version: env!("CARGO_PKG_VERSION").to_string(),
             pid: std::process::id(),
+            master_tid: 0,
             async_state: AsyncState::Uninitialized,
             tids: Vec::new(),
             last_instance_downtime: 0,

src/dragonball/src/api/v1/vmm_action.rs

@@ -7,8 +7,8 @@
 // found in the THIRD-PARTY file.
 
 use std::fs::File;
-use std::sync::mpsc::{Receiver, Sender, TryRecvError};
 
+use crossbeam_channel::{Receiver, Sender, TryRecvError};
 use log::{debug, error, info, warn};
 
 use crate::error::{Result, StartMicroVmError, StopMicrovmError};
@@ -16,9 +16,13 @@ use crate::event_manager::EventManager;
 use crate::vm::{CpuTopology, KernelConfigInfo, VmConfigInfo};
 use crate::vmm::Vmm;
 
+use crate::hypervisor_metrics::get_hypervisor_metrics;
+
 use self::VmConfigError::*;
 use self::VmmActionError::MachineConfig;
 
+#[cfg(feature = "virtio-balloon")]
+pub use crate::device_manager::balloon_dev_mgr::{BalloonDeviceConfigInfo, BalloonDeviceError};
 #[cfg(feature = "virtio-blk")]
 pub use crate::device_manager::blk_dev_mgr::{
     BlockDeviceConfigInfo, BlockDeviceConfigUpdateInfo, BlockDeviceError, BlockDeviceMgr,
@@ -27,6 +31,8 @@ pub use crate::device_manager::blk_dev_mgr::{
 pub use crate::device_manager::fs_dev_mgr::{
     FsDeviceConfigInfo, FsDeviceConfigUpdateInfo, FsDeviceError, FsDeviceMgr, FsMountConfigInfo,
 };
+#[cfg(feature = "virtio-mem")]
+pub use crate::device_manager::mem_dev_mgr::{MemDeviceConfigInfo, MemDeviceError};
 #[cfg(feature = "virtio-net")]
 pub use crate::device_manager::virtio_net_dev_mgr::{
     VirtioNetDeviceConfigInfo, VirtioNetDeviceConfigUpdateInfo, VirtioNetDeviceError,
@@ -34,7 +40,6 @@ pub use crate::device_manager::virtio_net_dev_mgr::{
 };
 #[cfg(feature = "virtio-vsock")]
 pub use crate::device_manager::vsock_dev_mgr::{VsockDeviceConfigInfo, VsockDeviceError};
-
 #[cfg(feature = "hotplug")]
 pub use crate::vcpu::{VcpuResizeError, VcpuResizeInfo};
 
@@ -55,6 +60,11 @@ pub enum VmmActionError {
     #[error("Upcall not ready, can't hotplug device.")]
     UpcallServerNotReady,
 
+    /// Error when get prometheus metrics.
+    /// Currently does not distinguish between error types for metrics.
+    #[error("failed to get hypervisor metrics")]
+    GetHypervisorMetrics,
+
     /// The action `ConfigureBootSource` failed either because of bad user input or an internal
     /// error.
     #[error("failed to configure boot source for VM: {0}")]
@@ -97,6 +107,20 @@ pub enum VmmActionError {
     /// The action `ResizeVcpu` Failed
     #[error("vcpu resize error : {0}")]
     ResizeVcpu(#[source] VcpuResizeError),
+
+    /// Cannot access address space.
+    #[error("Cannot access address space.")]
+    AddressSpaceNotInitialized,
+
+    #[cfg(feature = "virtio-mem")]
+    /// Mem device related errors.
+    #[error("virtio-mem device error: {0}")]
+    Mem(#[source] MemDeviceError),
+
+    #[cfg(feature = "virtio-balloon")]
+    /// Balloon device related errors.
+    #[error("virtio-balloon device error: {0}")]
+    Balloon(#[source] BalloonDeviceError),
 }
 
 /// This enum represents the public interface of the VMM. Each action contains various
@@ -118,6 +142,9 @@ pub enum VmmAction {
     /// Get the configuration of the microVM.
     GetVmConfiguration,
 
+    /// Get Prometheus Metrics.
+    GetHypervisorMetrics,
+
     /// Set the microVM configuration (memory & vcpu) using `VmConfig` as input. This
     /// action can only be called before the microVM has booted.
     SetVmConfiguration(VmConfigInfo),
@@ -172,6 +199,15 @@ pub enum VmmAction {
     #[cfg(feature = "hotplug")]
     /// Resize Vcpu number in the guest.
     ResizeVcpu(VcpuResizeInfo),
+
+    #[cfg(feature = "virtio-mem")]
+    /// Add a new mem device or update one that already exists using the `MemDeviceConfig` as input.
+    InsertMemDevice(MemDeviceConfigInfo),
+
+    #[cfg(feature = "virtio-balloon")]
+    /// Add a new balloon device or update one that already exists using the `BalloonDeviceConfig`
+    /// as input.
+    InsertBalloonDevice(BalloonDeviceConfigInfo),
 }
 
 /// The enum represents the response sent by the VMM in case of success. The response is either
@@ -182,6 +218,8 @@ pub enum VmmData {
     Empty,
     /// The microVM configuration represented by `VmConfigInfo`.
     MachineConfiguration(Box<VmConfigInfo>),
+    /// Prometheus Metrics represented by String.
+    HypervisorMetrics(String),
 }
 
 /// Request data type used to communicate between the API and the VMM.
@@ -236,6 +274,7 @@ impl VmmService {
             VmmAction::GetVmConfiguration => Ok(VmmData::MachineConfiguration(Box::new(
                 self.machine_config.clone(),
             ))),
+            VmmAction::GetHypervisorMetrics => self.get_hypervisor_metrics(),
             VmmAction::SetVmConfiguration(machine_config) => {
                 self.set_vm_configuration(vmm, machine_config)
             }
@@ -274,6 +313,12 @@ impl VmmService {
             }
             #[cfg(feature = "hotplug")]
             VmmAction::ResizeVcpu(vcpu_resize_cfg) => self.resize_vcpu(vmm, vcpu_resize_cfg),
+            #[cfg(feature = "virtio-mem")]
+            VmmAction::InsertMemDevice(mem_cfg) => self.add_mem_device(vmm, event_mgr, mem_cfg),
+            #[cfg(feature = "virtio-balloon")]
+            VmmAction::InsertBalloonDevice(balloon_cfg) => {
+                self.add_balloon_device(vmm, event_mgr, balloon_cfg)
+            }
         };
 
         debug!("send vmm response: {:?}", response);
@@ -349,6 +394,13 @@ impl VmmService {
         Ok(VmmData::Empty)
     }
 
+    /// Get prometheus metrics.
+    fn get_hypervisor_metrics(&self) -> VmmRequestResult {
+        get_hypervisor_metrics()
+            .map_err(|_| VmmActionError::GetHypervisorMetrics)
+            .map(VmmData::HypervisorMetrics)
+    }
+
     /// Set virtual machine configuration.
     pub fn set_vm_configuration(
         &mut self,
@@ -486,7 +538,9 @@ impl VmmService {
                 VmmActionError::Block(BlockDeviceError::UpdateNotAllowedPostBoot)
             })?;
 
-        BlockDeviceMgr::insert_device(vm.device_manager_mut(), ctx, config)
+        vm.device_manager_mut()
+            .block_manager
+            .insert_device(ctx, config)
             .map(|_| VmmData::Empty)
             .map_err(VmmActionError::Block)
     }
@@ -500,7 +554,9 @@ impl VmmService {
     ) -> VmmRequestResult {
         let vm = vmm.get_vm_mut().ok_or(VmmActionError::InvalidVMID)?;
 
-        BlockDeviceMgr::update_device_ratelimiters(vm.device_manager_mut(), config)
+        vm.device_manager_mut()
+            .block_manager
+            .update_device_ratelimiters(config)
             .map(|_| VmmData::Empty)
             .map_err(VmmActionError::Block)
     }
@@ -518,7 +574,9 @@ impl VmmService {
             .create_device_op_context(Some(event_mgr.epoll_manager()))
             .map_err(|_| VmmActionError::Block(BlockDeviceError::UpdateNotAllowedPostBoot))?;
 
-        BlockDeviceMgr::remove_device(vm.device_manager_mut(), ctx, drive_id)
+        vm.device_manager_mut()
+            .block_manager
+            .remove_device(ctx, drive_id)
             .map(|_| VmmData::Empty)
             .map_err(VmmActionError::Block)
     }
@@ -543,7 +601,9 @@ impl VmmService {
                 }
             })?;
 
-        VirtioNetDeviceMgr::insert_device(vm.device_manager_mut(), ctx, config)
+        vm.device_manager_mut()
+            .virtio_net_manager
+            .insert_device(ctx, config)
             .map(|_| VmmData::Empty)
             .map_err(VmmActionError::VirtioNet)
     }
@@ -556,7 +616,9 @@ impl VmmService {
     ) -> VmmRequestResult {
         let vm = vmm.get_vm_mut().ok_or(VmmActionError::InvalidVMID)?;
 
-        VirtioNetDeviceMgr::update_device_ratelimiters(vm.device_manager_mut(), config)
+        vm.device_manager_mut()
+            .virtio_net_manager
+            .update_device_ratelimiters(config)
             .map(|_| VmmData::Empty)
             .map_err(VmmActionError::VirtioNet)
     }
@@ -616,12 +678,6 @@ impl VmmService {
 
     #[cfg(feature = "hotplug")]
     fn resize_vcpu(&mut self, vmm: &mut Vmm, config: VcpuResizeInfo) -> VmmRequestResult {
-        if !cfg!(target_arch = "x86_64") {
-            // TODO: Arm need to support vcpu hotplug. issue: #6010
-            warn!("This arch do not support vm resize!");
-            return Ok(VmmData::Empty);
-        }
-
         if !cfg!(feature = "dbs-upcall") {
             warn!("We only support cpu resize through upcall server in the guest kernel now, please enable dbs-upcall feature.");
             return Ok(VmmData::Empty);
@@ -644,6 +700,62 @@ impl VmmService {
 
         Ok(VmmData::Empty)
     }
+
+    #[cfg(feature = "virtio-mem")]
+    fn add_mem_device(
+        &mut self,
+        vmm: &mut Vmm,
+        event_mgr: &mut EventManager,
+        config: MemDeviceConfigInfo,
+    ) -> VmmRequestResult {
+        let vm = vmm.get_vm_mut().ok_or(VmmActionError::InvalidVMID)?;
+
+        let ctx = vm
+            .create_device_op_context(Some(event_mgr.epoll_manager()))
+            .map_err(|e| {
+                if let StartMicroVmError::UpcallServerNotReady = e {
+                    VmmActionError::UpcallServerNotReady
+                } else {
+                    VmmActionError::StartMicroVm(e)
+                }
+            })?;
+
+        vm.device_manager_mut()
+            .mem_manager
+            .insert_or_update_device(ctx, config)
+            .map(|_| VmmData::Empty)
+            .map_err(VmmActionError::Mem)
+    }
+
+    #[cfg(feature = "virtio-balloon")]
+    fn add_balloon_device(
+        &mut self,
+        vmm: &mut Vmm,
+        event_mgr: &mut EventManager,
+        config: BalloonDeviceConfigInfo,
+    ) -> VmmRequestResult {
+        let vm = vmm.get_vm_mut().ok_or(VmmActionError::InvalidVMID)?;
+
+        if config.size_mib != 0 {
+            info!("add_balloon_device: wait prealloc");
+            vm.stop_prealloc().map_err(VmmActionError::StartMicroVm)?;
+        }
+        let ctx = vm
+            .create_device_op_context(Some(event_mgr.epoll_manager()))
+            .map_err(|e| {
+                if let StartMicroVmError::UpcallServerNotReady = e {
+                    VmmActionError::UpcallServerNotReady
+                } else {
+                    VmmActionError::StartMicroVm(e)
+                }
+            })?;
+
+        vm.device_manager_mut()
+            .balloon_manager
+            .insert_or_update_device(ctx, config)
+            .map(|_| VmmData::Empty)
+            .map_err(VmmActionError::Balloon)
+    }
 }
 
 fn handle_cpu_topology(
@@ -676,9 +788,9 @@ fn handle_cpu_topology(
 
 #[cfg(test)]
 mod tests {
-    use std::sync::mpsc::channel;
     use std::sync::{Arc, Mutex};
 
+    use crossbeam_channel::unbounded;
     use dbs_utils::epoll_manager::EpollManager;
     use test_utils::skip_if_not_root;
     use vmm_sys_util::tempfile::TempFile;
@@ -702,8 +814,8 @@ mod tests {
         }
 
         fn check_request(&mut self) {
-            let (to_vmm, from_api) = channel();
-            let (to_api, from_vmm) = channel();
+            let (to_vmm, from_api) = unbounded();
+            let (to_api, from_vmm) = unbounded();
 
             let epoll_mgr = EpollManager::default();
             let vmm = Arc::new(Mutex::new(create_vmm_instance(epoll_mgr.clone())));
@@ -728,8 +840,8 @@ mod tests {
     fn test_vmm_action_receive_unknown() {
         skip_if_not_root!();
 
-        let (_to_vmm, from_api) = channel();
-        let (to_api, _from_vmm) = channel();
+        let (_to_vmm, from_api) = unbounded();
+        let (to_api, _from_vmm) = unbounded();
         let epoll_mgr = EpollManager::default();
         let vmm = Arc::new(Mutex::new(create_vmm_instance(epoll_mgr.clone())));
         let mut vservice = VmmService::new(from_api, to_api);
@@ -742,8 +854,8 @@ mod tests {
     #[should_panic]
     #[test]
     fn test_vmm_action_disconnected() {
-        let (to_vmm, from_api) = channel();
-        let (to_api, _from_vmm) = channel();
+        let (to_vmm, from_api) = unbounded();
+        let (to_api, _from_vmm) = unbounded();
         let epoll_mgr = EpollManager::default();
         let vmm = Arc::new(Mutex::new(create_vmm_instance(epoll_mgr.clone())));
         let mut vservice = VmmService::new(from_api, to_api);
@@ -1452,4 +1564,84 @@ mod tests {
             t.check_request();
         }
     }
+
+    #[cfg(feature = "virtio-mem")]
+    #[test]
+    fn test_vmm_action_insert_mem_device() {
+        skip_if_not_root!();
+
+        let tests = &mut [
+            // hotplug unready
+            TestData::new(
+                VmmAction::InsertMemDevice(MemDeviceConfigInfo::default()),
+                InstanceState::Running,
+                &|result| {
+                    assert!(matches!(
+                        result,
+                        Err(VmmActionError::StartMicroVm(
+                            StartMicroVmError::UpcallMissVsock
+                        ))
+                    ));
+                    let err_string = format!("{}", result.unwrap_err());
+                    let expected_err = String::from(
+                        "failed to boot the VM: \
+                        the upcall client needs a virtio-vsock device for communication",
+                    );
+                    assert_eq!(err_string, expected_err);
+                },
+            ),
+            // success
+            TestData::new(
+                VmmAction::InsertMemDevice(MemDeviceConfigInfo::default()),
+                InstanceState::Uninitialized,
+                &|result| {
+                    assert!(result.is_ok());
+                },
+            ),
+        ];
+
+        for t in tests.iter_mut() {
+            t.check_request();
+        }
+    }
+
+    #[cfg(feature = "virtio-balloon")]
+    #[test]
+    fn test_vmm_action_insert_balloon_device() {
+        skip_if_not_root!();
+
+        let tests = &mut [
+            // hotplug unready
+            TestData::new(
+                VmmAction::InsertBalloonDevice(BalloonDeviceConfigInfo::default()),
+                InstanceState::Running,
+                &|result| {
+                    assert!(matches!(
+                        result,
+                        Err(VmmActionError::StartMicroVm(
+                            StartMicroVmError::UpcallMissVsock
+                        ))
+                    ));
+                    let err_string = format!("{}", result.unwrap_err());
+                    let expected_err = String::from(
+                        "failed to boot the VM: \
+                        the upcall client needs a virtio-vsock device for communication",
+                    );
+                    assert_eq!(err_string, expected_err);
+                },
+            ),
+            // success
+            TestData::new(
+                VmmAction::InsertBalloonDevice(BalloonDeviceConfigInfo::default()),
+                InstanceState::Uninitialized,
+                &|result| {
+                    assert!(result.is_ok());
+                },
+            ),
+        ];
+
+        for t in tests.iter_mut() {
+            t.check_request();
+        }
+    }
 }

src/dragonball/src/config_manager.rs

@@ -231,7 +231,7 @@ where
                         info.config.check_conflicts(config)?;
                     }
                 }
-                self.info_list[index] = device_info;
+                self.info_list[index].config = config.clone();
                 index
             }
             None => {
@@ -278,6 +278,11 @@ where
         self.info_list.iter_mut()
     }
 
+    /// Remove the last device config info from the `info_list`.
+    pub fn pop(&mut self) -> Option<DeviceConfigInfo<T>> {
+        self.info_list.pop()
+    }
+
     fn get_index_by_id(&self, config: &T) -> Option<usize> {
         self.info_list
             .iter()

src/dragonball/src/dbs_acpi/Cargo.toml

@@ -0,0 +1,14 @@
+[package]
+name = "dbs-acpi"
+version = "0.1.0"
+authors = ["Alibaba Dragonball Team"]
+description = "acpi definitions for virtual machines."
+license = "Apache-2.0"
+edition = "2018"
+homepage = "https://github.com/openanolis/dragonball-sandbox"
+repository = "https://github.com/openanolis/dragonball-sandbox"
+keywords = ["dragonball", "acpi", "vmm", "secure-sandbox"]
+readme = "README.md"
+
+[dependencies]
+vm-memory = "0.9.0"

src/dragonball/src/dbs_acpi/README.md

@@ -0,0 +1,11 @@
+# dbs-acpi
+
+`dbs-acpi` provides ACPI data structures for VMM to emulate ACPI behavior.
+
+## Acknowledgement
+
+Part of the code is derived from the [Cloud Hypervisor](https://github.com/cloud-hypervisor/cloud-hypervisor) project.
+
+## License
+
+This project is licensed under [Apache License, Version 2.0](http://www.apache.org/licenses/LICENSE-2.0).