Compare commits

..

14 Commits

Author SHA1 Message Date
Aurélien Bombo
b87b4dc3be relax bind mount regex
the source path can be cached from the first container now

Signed-off-by: Aurélien Bombo <abombo@microsoft.com>
2026-02-13 12:42:49 -06:00
Aurélien Bombo
11dfe0ffac allow cached bundle-id from pause container
Signed-off-by: Aurélien Bombo <abombo@microsoft.com>
2026-02-13 12:42:49 -06:00
Aurélien Bombo
701e67cfd6 move cache handling to shared_fs=none branch
this should only be needed in that branch since virtio-fs should already handle dupes

Signed-off-by: Aurélien Bombo <abombo@microsoft.com>
2026-02-13 12:42:49 -06:00
Aurélien Bombo
d50f103a13 Revert "debug: fix cache key"
This reverts commit 2c3ee1eda5.
2026-02-13 12:42:49 -06:00
Aurélien Bombo
bd2428e19f Revert "debug: different approach"
This reverts commit c0d3c31ec8.
2026-02-13 12:42:49 -06:00
Aurélien Bombo
13b8dda322 debug: different approach
Signed-off-by: Aurélien Bombo <abombo@microsoft.com>
2026-02-13 12:42:49 -06:00
Aurélien Bombo
36ca7990aa tests: Introduce new env variables to ease development
It can be useful to set these variables during local testing:

 * AZ_REGION: Region for the cluster.
 * AZ_NODEPOOL_TAGS: Node pool tags for the cluster.
 * GENPOLICY_BINARY: Path to the genpolicy binary.
 * GENPOLICY_SETTINGS_DIR: Directory holding the genpolicy settings.

I've also made it so that tests_common.sh modifies the duplicated
genpolicy-settings.json (used for testing) instead of the original git-tracked
one.

Signed-off-by: Aurélien Bombo <abombo@microsoft.com>
2026-02-13 12:42:49 -06:00
Aurélien Bombo
9894e14e99 debug: fix cache key
Signed-off-by: Aurélien Bombo <abombo@microsoft.com>
2026-02-13 12:42:49 -06:00
Aurélien Bombo
7357373dff debug: properly invalidate cache
Signed-off-by: Aurélien Bombo <abombo@microsoft.com>
2026-02-13 12:42:49 -06:00
Aurélien Bombo
56254ecdff debug: smaller mutex critical sections
Signed-off-by: Aurélien Bombo <abombo@microsoft.com>
2026-02-13 12:42:49 -06:00
Aurélien Bombo
be8a112316 debug: enable disable_guest_empty_dir=true and shared_fs=none
Signed-off-by: Aurélien Bombo <abombo@microsoft.com>
2026-02-13 12:42:49 -06:00
Aurélien Bombo
ed415fa91a runtime-rs: Set disable_guest_empty_dir = true by default
This should be furthermore not be configurable in 4.0.

Signed-off-by: Aurélien Bombo <abombo@microsoft.com>
2026-02-13 12:42:49 -06:00
Aurélien Bombo
4a37f4c673 genpolicy: Assume disable_guest_empty_dir = true
This option should be removed for 4.0, so we don't handle `false`.

Signed-off-by: Aurélien Bombo <abombo@microsoft.com>
2026-02-13 12:42:49 -06:00
Aurélien Bombo
0db136cfa9 runtime: Set disable_guest_empty_dir = true by default
This makes the runtime share the host Kubelet emptyDir folder with the guest
instead of the agent creating an empty folder in the container rootfs. Doing so
enables the Kubelet to track emptyDir usage and evict greedy pods.

In other words, with virtio-fs the container rootfs uses host storage whether
this is true or false, however with true, Kata uses the k8s emptyDir folder so
the sizeLimit is properly enforced by k8s.

Addresses part of #12203.

Signed-off-by: Aurélien Bombo <abombo@microsoft.com>
2026-02-13 12:42:49 -06:00
597 changed files with 16142 additions and 52101 deletions

View File

@@ -1,36 +0,0 @@
# yaml-language-server: $schema=https://raw.githubusercontent.com/streetsidesoftware/cspell/main/cspell.schema.json
version: "0.2"
language: en,en-GB
dictionaryDefinitions:
- name: kata-terms
path: ./tests/spellcheck/kata-dictionary.txt
addWords: true
dictionaries:
- en-GB
- en_US
- bash
- git
- golang
- k8s
- python
- rust
- companies
- mnemonics
- peopleNames
- softwareTerms
- networking-terms
- kata-terms
ignoreRegExpList:
- /@[a-z\d](?:[a-z\d]|-(?=[a-z\d])){0,38}/gi # Ignores github handles
# Ignore code blocks
- /^\s*`{3,}[\s\S]*?^\s*`{3,}/gm
- /`[^`\n]+`/g
ignorePaths:
- "**/vendor/**" # vendor files aren't owned by us
- "**/src/runtime/virtcontainers/pkg/cloud-hypervisor/client/**" # Generated files
useGitignore: true

View File

@@ -28,9 +28,3 @@ self-hosted-runner:
- s390x-large
- tdx
- ubuntu-24.04-arm
paths:
.github/workflows/**/*.{yml,yaml}:
ignore:
# We use if: false to "temporarily" skip jobs with issues
- 'constant expression "false" in condition'

View File

@@ -15,8 +15,6 @@ updates:
- "/src/tools/trace-forwarder"
schedule:
interval: "daily"
cooldown:
default-days: 7
ignore:
# rust-vmm repos might cause incompatibilities on patch versions, so
# lets handle them manually for now.
@@ -87,12 +85,8 @@ updates:
- "src/tools/csi-kata-directvolume"
schedule:
interval: "daily"
cooldown:
default-days: 7
- package-ecosystem: "github-actions"
directory: "/"
schedule:
interval: "monthly"
cooldown:
default-days: 7

View File

@@ -13,13 +13,18 @@ concurrency:
jobs:
run-actionlint:
name: run-actionlint
env:
GH_TOKEN: ${{ github.token }}
runs-on: ubuntu-24.04
steps:
- name: Checkout the code
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
persist-credentials: false
- name: Install actionlint gh extension
run: gh extension install https://github.com/cschleiden/gh-actionlint
- name: Run actionlint
uses: raven-actions/actionlint@e01d1ea33dd6a5ed517d95b4c0c357560ac6f518 # v2.1.1
run: gh actionlint

View File

@@ -47,23 +47,6 @@ jobs:
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: Install yq
run: |
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
- name: Install dependencies
run: bash tests/integration/cri-containerd/gha-run.sh install-dependencies
env:

View File

@@ -47,25 +47,8 @@ jobs:
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: Install yq
run: |
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
- name: Install dependencies
run: bash tests/integration/cri-containerd/gha-run.sh install-dependencies
run: bash tests/integration/cri-containerd/gha-run.sh
env:
GH_TOKEN: ${{ github.token }}

View File

@@ -82,17 +82,11 @@ jobs:
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
- name: Install golang
if: contains(matrix.component.needs, 'golang')
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
if: contains(matrix.component.needs, 'golang')
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
./tests/install_go.sh -f -p
echo "/usr/local/go/bin" >> "$GITHUB_PATH"
- name: Setup rust
if: contains(matrix.component.needs, 'rust')
run: |

View File

@@ -94,19 +94,11 @@ jobs:
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
- name: Install golang
if: contains(matrix.component.needs, 'golang')
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
if: contains(matrix.component.needs, 'golang')
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
# Setup-go doesn't work properly with ppc64le: https://github.com/actions/setup-go/issues/648
architecture: ${{ contains(inputs.instance, 'ppc64le') && 'ppc64le' || '' }}
./tests/install_go.sh -f -p
echo "/usr/local/go/bin" >> "$GITHUB_PATH"
- name: Setup rust
if: contains(matrix.component.needs, 'rust')
run: |

View File

@@ -143,7 +143,7 @@ jobs:
if-no-files-found: error
- name: store-extratarballs-artifact ${{ matrix.asset }}
if: ${{ startsWith(matrix.asset, 'kernel-nvidia-gpu') }}
if: ${{ matrix.asset == 'kernel' || startsWith(matrix.asset, 'kernel-nvidia-gpu') }}
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: kata-artifacts-amd64-${{ matrix.asset }}-modules${{ inputs.tarball-suffix }}
@@ -168,6 +168,8 @@ jobs:
- rootfs-image-nvidia-gpu-confidential
- rootfs-initrd
- rootfs-initrd-confidential
- rootfs-initrd-nvidia-gpu
- rootfs-initrd-nvidia-gpu-confidential
steps:
- name: Login to Kata Containers quay.io
if: ${{ inputs.push-to-registry == 'yes' }}
@@ -233,6 +235,7 @@ jobs:
asset:
- busybox
- coco-guest-components
- kernel-modules
- kernel-nvidia-gpu-modules
- pause-image
steps:
@@ -347,16 +350,6 @@ jobs:
./tools/packaging/kata-deploy/local-build/kata-deploy-merge-builds.sh kata-artifacts versions.yaml
env:
RELEASE: ${{ inputs.stage == 'release' && 'yes' || 'no' }}
- name: Check kata tarball size (GitHub release asset limit)
run: |
# https://docs.github.com/en/repositories/releasing-projects-on-github/about-releases#storage-and-bandwidth-quotas
GITHUB_ASSET_MAX_BYTES=2147483648
tarball_size=$(stat -c "%s" kata-static.tar.zst)
if [[ "${tarball_size}" -ge "${GITHUB_ASSET_MAX_BYTES}" ]]; then
echo "::error::tarball size (${tarball_size} bytes) >= GitHub release asset limit (${GITHUB_ASSET_MAX_BYTES} bytes)"
exit 1
fi
echo "tarball size: ${tarball_size} bytes"
- name: store-artifacts
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
@@ -375,6 +368,7 @@ jobs:
matrix:
asset:
- agent-ctl
- csi-kata-directvolume
- genpolicy
- kata-ctl
- kata-manager
@@ -457,16 +451,6 @@ jobs:
./tools/packaging/kata-deploy/local-build/kata-deploy-merge-builds.sh kata-tools-artifacts versions.yaml kata-tools-static.tar.zst
env:
RELEASE: ${{ inputs.stage == 'release' && 'yes' || 'no' }}
- name: Check kata-tools tarball size (GitHub release asset limit)
run: |
# https://docs.github.com/en/repositories/releasing-projects-on-github/about-releases#storage-and-bandwidth-quotas
GITHUB_ASSET_MAX_BYTES=2147483648
tarball_size=$(stat -c "%s" kata-tools-static.tar.zst)
if [[ "${tarball_size}" -ge "${GITHUB_ASSET_MAX_BYTES}" ]]; then
echo "::error::tarball size (${tarball_size} bytes) >= GitHub release asset limit (${GITHUB_ASSET_MAX_BYTES} bytes)"
exit 1
fi
echo "tarball size: ${tarball_size} bytes"
- name: store-artifacts
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:

View File

@@ -152,6 +152,7 @@ jobs:
- rootfs-image
- rootfs-image-nvidia-gpu
- rootfs-initrd
- rootfs-initrd-nvidia-gpu
steps:
- name: Login to Kata Containers quay.io
if: ${{ inputs.push-to-registry == 'yes' }}
@@ -326,16 +327,6 @@ jobs:
./tools/packaging/kata-deploy/local-build/kata-deploy-merge-builds.sh kata-artifacts versions.yaml
env:
RELEASE: ${{ inputs.stage == 'release' && 'yes' || 'no' }}
- name: Check kata tarball size (GitHub release asset limit)
run: |
# https://docs.github.com/en/repositories/releasing-projects-on-github/about-releases#storage-and-bandwidth-quotas
GITHUB_ASSET_MAX_BYTES=2147483648
tarball_size=$(stat -c "%s" kata-static.tar.zst)
if [[ "${tarball_size}" -ge "${GITHUB_ASSET_MAX_BYTES}" ]]; then
echo "::error::tarball size (${tarball_size} bytes) >= GitHub release asset limit (${GITHUB_ASSET_MAX_BYTES} bytes)"
exit 1
fi
echo "tarball size: ${tarball_size} bytes"
- name: store-artifacts
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:

View File

@@ -262,16 +262,6 @@ jobs:
./tools/packaging/kata-deploy/local-build/kata-deploy-merge-builds.sh kata-artifacts versions.yaml
env:
RELEASE: ${{ inputs.stage == 'release' && 'yes' || 'no' }}
- name: Check kata tarball size (GitHub release asset limit)
run: |
# https://docs.github.com/en/repositories/releasing-projects-on-github/about-releases#storage-and-bandwidth-quotas
GITHUB_ASSET_MAX_BYTES=2147483648
tarball_size=$(stat -c "%s" kata-static.tar.zst)
if [[ "${tarball_size}" -ge "${GITHUB_ASSET_MAX_BYTES}" ]]; then
echo "::error::tarball size (${tarball_size} bytes) >= GitHub release asset limit (${GITHUB_ASSET_MAX_BYTES} bytes)"
exit 1
fi
echo "tarball size: ${tarball_size} bytes"
- name: store-artifacts
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:

View File

@@ -120,6 +120,15 @@ jobs:
retention-days: 15
if-no-files-found: error
- name: store-extratarballs-artifact ${{ matrix.asset }}
if: ${{ matrix.asset == 'kernel' }}
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: kata-artifacts-s390x-${{ matrix.asset }}-modules${{ inputs.tarball-suffix }}
path: kata-build/kata-static-${{ matrix.asset }}-modules.tar.zst
retention-days: 15
if-no-files-found: error
build-asset-rootfs:
name: build-asset-rootfs
runs-on: s390x
@@ -350,16 +359,6 @@ jobs:
./tools/packaging/kata-deploy/local-build/kata-deploy-merge-builds.sh kata-artifacts versions.yaml
env:
RELEASE: ${{ inputs.stage == 'release' && 'yes' || 'no' }}
- name: Check kata tarball size (GitHub release asset limit)
run: |
# https://docs.github.com/en/repositories/releasing-projects-on-github/about-releases#storage-and-bandwidth-quotas
GITHUB_ASSET_MAX_BYTES=2147483648
tarball_size=$(stat -c "%s" kata-static.tar.zst)
if [[ "${tarball_size}" -ge "${GITHUB_ASSET_MAX_BYTES}" ]]; then
echo "::error::tarball size (${tarball_size} bytes) >= GitHub release asset limit (${GITHUB_ASSET_MAX_BYTES} bytes)"
exit 1
fi
echo "tarball size: ${tarball_size} bytes"
- name: store-artifacts
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:

View File

@@ -17,7 +17,6 @@ jobs:
pr-number: "dev"
tag: ${{ github.sha }}-dev
target-branch: ${{ github.ref_name }}
extensive-matrix-autogenerated-policy: "yes"
secrets:
AUTHENTICATED_IMAGE_PASSWORD: ${{ secrets.AUTHENTICATED_IMAGE_PASSWORD }}

View File

@@ -22,7 +22,6 @@ jobs:
pr-number: "nightly"
tag: ${{ github.sha }}-nightly
target-branch: ${{ github.ref_name }}
extensive-matrix-autogenerated-policy: "yes"
secrets:
AUTHENTICATED_IMAGE_PASSWORD: ${{ secrets.AUTHENTICATED_IMAGE_PASSWORD }}
AZ_APPID: ${{ secrets.AZ_APPID }}

View File

@@ -19,10 +19,6 @@ on:
required: false
type: string
default: no
extensive-matrix-autogenerated-policy:
required: false
type: string
default: no
secrets:
AUTHENTICATED_IMAGE_PASSWORD:
required: true
@@ -216,6 +212,61 @@ jobs:
platforms: linux/amd64, linux/s390x
file: tests/integration/kubernetes/runtimeclass_workloads/confidential/unencrypted/Dockerfile
publish-csi-driver-amd64:
name: publish-csi-driver-amd64
needs: build-kata-static-tarball-amd64
permissions:
contents: read
packages: write
runs-on: ubuntu-22.04
steps:
- name: Checkout code
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
fetch-depth: 0
persist-credentials: false
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: get-kata-tools-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-tools-static-tarball-amd64-${{ inputs.tag }}
path: kata-tools-artifacts
- name: Install kata-tools
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Copy binary into Docker context
run: |
# Copy to the location where the Dockerfile expects the binary.
mkdir -p src/tools/csi-kata-directvolume/bin/
cp /opt/kata/bin/csi-kata-directvolume src/tools/csi-kata-directvolume/bin/directvolplugin
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Login to Kata Containers ghcr.io
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Docker build and push
uses: docker/build-push-action@ca052bb54ab0790a636c9b5f226502c73d547a25 # v5.4.0
with:
tags: ghcr.io/kata-containers/csi-kata-directvolume:${{ inputs.pr-number }}
push: true
context: src/tools/csi-kata-directvolume/
platforms: linux/amd64
file: src/tools/csi-kata-directvolume/Dockerfile
run-kata-monitor-tests:
if: ${{ inputs.skip-test != 'yes' }}
needs: build-kata-static-tarball-amd64
@@ -246,21 +297,6 @@ jobs:
AZ_TENANT_ID: ${{ secrets.AZ_TENANT_ID }}
AZ_SUBSCRIPTION_ID: ${{ secrets.AZ_SUBSCRIPTION_ID }}
run-k8s-tests-on-free-runner:
if: ${{ inputs.skip-test != 'yes' }}
needs: publish-kata-deploy-payload-amd64
permissions:
contents: read
uses: ./.github/workflows/run-k8s-tests-on-free-runner.yaml
with:
tarball-suffix: -${{ inputs.tag }}
registry: ghcr.io
repo: ${{ github.repository_owner }}/kata-deploy-ci
tag: ${{ inputs.tag }}-amd64
commit-hash: ${{ inputs.commit-hash }}
pr-number: ${{ inputs.pr-number }}
target-branch: ${{ inputs.target-branch }}
run-k8s-tests-on-arm64:
if: ${{ inputs.skip-test != 'yes' }}
needs: publish-kata-deploy-payload-arm64
@@ -294,6 +330,7 @@ jobs:
needs:
- publish-kata-deploy-payload-amd64
- build-and-publish-tee-confidential-unencrypted-image
- publish-csi-driver-amd64
uses: ./.github/workflows/run-kata-coco-tests.yaml
permissions:
contents: read
@@ -306,7 +343,6 @@ jobs:
commit-hash: ${{ inputs.commit-hash }}
pr-number: ${{ inputs.pr-number }}
target-branch: ${{ inputs.target-branch }}
extensive-matrix-autogenerated-policy: ${{ inputs.extensive-matrix-autogenerated-policy }}
secrets:
AUTHENTICATED_IMAGE_PASSWORD: ${{ secrets.AUTHENTICATED_IMAGE_PASSWORD }}
AZ_APPID: ${{ secrets.AZ_APPID }}

View File

@@ -72,7 +72,7 @@ jobs:
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@4bdb89f48054571735e3792627da6195c57459e2 # v3.31.10
uses: github/codeql-action/init@v3
with:
languages: ${{ matrix.language }}
build-mode: ${{ matrix.build-mode }}
@@ -95,6 +95,6 @@ jobs:
make -C src/runtime
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@4bdb89f48054571735e3792627da6195c57459e2 # v3.31.10
uses: github/codeql-action/analyze@v3
with:
category: "/language:${{matrix.language}}"

View File

@@ -31,22 +31,10 @@ jobs:
with:
persist-credentials: false
- name: Install yq
- name: Install golang
run: |
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
./tests/install_go.sh -f -p
echo "/usr/local/go/bin" >> "${GITHUB_PATH}"
- name: Install Rust
run: ./tests/install_rust.sh

View File

@@ -24,22 +24,10 @@ jobs:
fetch-depth: 0
persist-credentials: false
- name: Install yq
- name: Install golang
run: |
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
./tests/install_go.sh -f -p
echo "/usr/local/go/bin" >> "${GITHUB_PATH}"
- name: Docs URL Alive Check
run: |

View File

@@ -16,17 +16,17 @@ jobs:
url: ${{ steps.deployment.outputs.page_url }}
runs-on: ubuntu-latest
steps:
- uses: actions/configure-pages@983d7736d9b0ae728b81ab479565c72886d7745b # v5.0.0
- uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5.0.1
- uses: actions/configure-pages@v5
- uses: actions/checkout@v5
with:
persist-credentials: false
- uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
- uses: actions/setup-python@v5
with:
python-version: 3.x
- run: pip install zensical
- run: zensical build --clean
- uses: actions/upload-pages-artifact@7b1f4a764d45c48632c6b24a0339c27f5614fb0b # v4.0.0
- uses: actions/upload-pages-artifact@v4
with:
path: site
- uses: actions/deploy-pages@d6db90164ac5ed86f2b6aed7e0febac5b3c0c03e # v4.0.5
- uses: actions/deploy-pages@v4
id: deployment

View File

@@ -27,22 +27,10 @@ jobs:
fetch-depth: 0
persist-credentials: false
- name: Install yq
- name: Install golang
run: |
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
./tests/install_go.sh -f -p
echo "/usr/local/go/bin" >> "${GITHUB_PATH}"
- name: Install govulncheck
run: |

View File

@@ -19,25 +19,23 @@ permissions: {}
jobs:
scan-scheduled:
name: Scan of whole repo
permissions:
actions: read # # Required to upload SARIF file to CodeQL
contents: read # Read commit contents
security-events: write # Require writing security events to upload SARIF file to security tab
if: ${{ github.event_name == 'push' || github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
uses: "google/osv-scanner-action/.github/workflows/osv-scanner-reusable.yml@8ae4be80636b94886b3c271caad730985ce0611c" # v2.3.3
uses: "google/osv-scanner-action/.github/workflows/osv-scanner-reusable.yml@b00f71e051ddddc6e46a193c31c8c0bf283bf9e6" # v2.1.0
with:
scan-args: |-
-r
./
scan-pr:
name: Scan of just PR code
permissions:
actions: read # Required to upload SARIF file to CodeQL
contents: read # Read commit contents
security-events: write # Require writing security events to upload SARIF file to security tab
if: ${{ github.event_name == 'pull_request' }}
uses: "google/osv-scanner-action/.github/workflows/osv-scanner-reusable-pr.yml@8ae4be80636b94886b3c271caad730985ce0611c" # v2.3.3
uses: "google/osv-scanner-action/.github/workflows/osv-scanner-reusable-pr.yml@b00f71e051ddddc6e46a193c31c8c0bf283bf9e6" # v2.1.0
with:
# Example of specifying custom arguments
scan-args: |-

View File

@@ -35,6 +35,8 @@ on:
jobs:
run-cri-containerd:
name: run-cri-containerd-${{ inputs.arch }} (${{ inputs.containerd_version }}, ${{ inputs.vmm }})
strategy:
fail-fast: false
runs-on: ${{ inputs.runner }}
env:
CONTAINERD_VERSION: ${{ inputs.containerd_version }}
@@ -53,25 +55,6 @@ jobs:
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: Install yq
run: |
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
# Setup-go doesn't work properly with ppc64le: https://github.com/actions/setup-go/issues/648
architecture: ${{ inputs.arch == 'ppc64le' && 'ppc64le' || '' }}
- name: Install dependencies
timeout-minutes: 15
run: bash tests/integration/cri-containerd/gha-run.sh install-dependencies

View File

@@ -42,6 +42,17 @@ jobs:
strategy:
fail-fast: false
matrix:
host_os:
- ubuntu
vmm:
- clh
- dragonball
- qemu
- qemu-runtime-rs
- cloud-hypervisor
instance-type:
- small
- normal
include:
- host_os: cbl-mariner
vmm: clh
@@ -69,7 +80,6 @@ jobs:
KUBERNETES: "vanilla"
K8S_TEST_HOST_TYPE: ${{ matrix.instance-type }}
GENPOLICY_PULL_METHOD: ${{ matrix.genpolicy-pull-method }}
RUNS_ON_AKS: "true"
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:

View File

@@ -1,127 +0,0 @@
# Run Kubernetes integration tests on free GitHub runners with a locally
# deployed cluster (kubeadm).
name: CI | Run kubernetes tests on free runner
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
pr-number:
required: true
type: string
commit-hash:
required: false
type: string
target-branch:
required: false
type: string
default: ""
permissions: {}
jobs:
run-k8s-tests:
name: run-k8s-tests
strategy:
fail-fast: false
matrix:
environment: [
{ vmm: clh, containerd_version: lts },
{ vmm: clh, containerd_version: active },
{ vmm: dragonball, containerd_version: lts },
{ vmm: dragonball, containerd_version: active },
{ vmm: qemu, containerd_version: lts },
{ vmm: qemu, containerd_version: active },
{ vmm: qemu-runtime-rs, containerd_version: lts },
{ vmm: qemu-runtime-rs, containerd_version: active },
{ vmm: cloud-hypervisor, containerd_version: lts },
{ vmm: cloud-hypervisor, containerd_version: active },
]
runs-on: ubuntu-24.04
permissions:
contents: read
env:
DOCKER_REGISTRY: ${{ inputs.registry }}
DOCKER_REPO: ${{ inputs.repo }}
DOCKER_TAG: ${{ inputs.tag }}
GH_PR_NUMBER: ${{ inputs.pr-number }}
KATA_HOST_OS: ubuntu
KATA_HYPERVISOR: ${{ matrix.environment.vmm }}
KUBERNETES: vanilla
K8S_TEST_HOST_TYPE: baremetal-no-attestation
CONTAINER_ENGINE: containerd
CONTAINER_ENGINE_VERSION: ${{ matrix.environment.containerd_version }}
GH_TOKEN: ${{ github.token }}
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
fetch-depth: 0
persist-credentials: false
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: get-kata-tools-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-tools-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-tools-artifacts
- name: Install kata-tools
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Remove unnecessary directories to free up space
run: |
sudo rm -rf /usr/local/.ghcup
sudo rm -rf /opt/hostedtoolcache/CodeQL
sudo rm -rf /usr/local/lib/android
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf /usr/local/share/boost
sudo rm -rf /usr/lib/jvm
sudo rm -rf /usr/share/swift
sudo rm -rf /usr/local/share/powershell
sudo rm -rf /usr/local/julia*
sudo rm -rf /opt/az
sudo rm -rf /usr/local/share/chromium
sudo rm -rf /opt/microsoft
sudo rm -rf /opt/google
sudo rm -rf /usr/lib/firefox
- name: Deploy k8s (kubeadm)
run: bash tests/integration/kubernetes/gha-run.sh deploy-k8s
- name: Install `bats`
run: bash tests/integration/kubernetes/gha-run.sh install-bats
- name: Deploy Kata
timeout-minutes: 20
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata
- name: Run tests
timeout-minutes: 60
run: bash tests/integration/kubernetes/gha-run.sh run-tests
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Delete kata-deploy
if: always()
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh cleanup

View File

@@ -57,24 +57,10 @@ jobs:
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: Install yq
- name: Install golang
run: |
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
# Setup-go doesn't work properly with ppc64le: https://github.com/actions/setup-go/issues/648
architecture: 'ppc64le'
./tests/install_go.sh -f -p
echo "/usr/local/go/bin" >> "$GITHUB_PATH"
- name: Prepare the runner for k8s test suite
run: bash "${HOME}/scripts/k8s_cluster_prepare.sh"

View File

@@ -24,10 +24,6 @@ on:
required: false
type: string
default: ""
extensive-matrix-autogenerated-policy:
required: false
type: string
default: no
secrets:
AUTHENTICATED_IMAGE_PASSWORD:
required: true
@@ -110,6 +106,10 @@ jobs:
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh install-kbs-client
- name: Deploy CSI driver
timeout-minutes: 5
run: bash tests/integration/kubernetes/gha-run.sh deploy-csi-driver
- name: Run tests
timeout-minutes: 100
run: bash tests/integration/kubernetes/gha-run.sh run-tests
@@ -130,42 +130,52 @@ jobs:
[[ "${KATA_HYPERVISOR}" == "qemu-tdx" ]] && echo "ITA_KEY=${GH_ITA_KEY}" >> "${GITHUB_ENV}"
bash tests/integration/kubernetes/gha-run.sh delete-coco-kbs
- name: Delete CSI driver
timeout-minutes: 5
run: bash tests/integration/kubernetes/gha-run.sh delete-csi-driver
# Generate jobs for testing CoCo on non-TEE environments
run-k8s-tests-coco-nontee:
name: run-k8s-tests-coco-nontee
strategy:
fail-fast: false
matrix:
environment: [
{ vmm: qemu-coco-dev, snapshotter: nydus, pull_type: guest-pull },
{ vmm: qemu-coco-dev-runtime-rs, snapshotter: nydus, pull_type: guest-pull },
{ vmm: qemu-coco-dev, snapshotter: "", pull_type: experimental-force-guest-pull },
]
runs-on: ubuntu-24.04
vmm:
- qemu-coco-dev
- qemu-coco-dev-runtime-rs
snapshotter:
- nydus
pull-type:
- guest-pull
include:
- pull-type: experimental-force-guest-pull
vmm: qemu-coco-dev
snapshotter: ""
runs-on: ubuntu-22.04
permissions:
contents: read
id-token: write # Used for OIDC access to log into Azure
environment: ci
env:
DOCKER_REGISTRY: ${{ inputs.registry }}
DOCKER_REPO: ${{ inputs.repo }}
DOCKER_TAG: ${{ inputs.tag }}
GH_PR_NUMBER: ${{ inputs.pr-number }}
KATA_HYPERVISOR: ${{ matrix.environment.vmm }}
KATA_HYPERVISOR: ${{ matrix.vmm }}
# Some tests rely on that variable to run (or not)
KBS: "true"
# Set the KBS ingress handler (empty string disables handling)
KBS_INGRESS: "nodeport"
KBS_INGRESS: "aks"
KUBERNETES: "vanilla"
PULL_TYPE: ${{ matrix.environment.pull_type }}
PULL_TYPE: ${{ matrix.pull-type }}
AUTHENTICATED_IMAGE_USER: ${{ vars.AUTHENTICATED_IMAGE_USER }}
AUTHENTICATED_IMAGE_PASSWORD: ${{ secrets.AUTHENTICATED_IMAGE_PASSWORD }}
SNAPSHOTTER: ${{ matrix.environment.snapshotter }}
EXPERIMENTAL_FORCE_GUEST_PULL: ${{ matrix.environment.pull_type == 'experimental-force-guest-pull' && matrix.environment.vmm || '' }}
AUTO_GENERATE_POLICY: "yes"
SNAPSHOTTER: ${{ matrix.snapshotter }}
EXPERIMENTAL_FORCE_GUEST_PULL: ${{ matrix.pull-type == 'experimental-force-guest-pull' && matrix.vmm || '' }}
# Caution: current ingress controller used to expose the KBS service
# requires much vCPUs, lefting only a few for the tests. Depending on the
# host type chose it will result on the creation of a cluster with
# insufficient resources.
K8S_TEST_HOST_TYPE: "all"
CONTAINER_ENGINE: "containerd"
CONTAINER_ENGINE_VERSION: "active"
GH_TOKEN: ${{ github.token }}
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
@@ -188,36 +198,39 @@ jobs:
- name: Install kata-tools
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Remove unnecessary directories to free up space
run: |
sudo rm -rf /usr/local/.ghcup
sudo rm -rf /opt/hostedtoolcache/CodeQL
sudo rm -rf /usr/local/lib/android
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf /usr/local/share/boost
sudo rm -rf /usr/lib/jvm
sudo rm -rf /usr/share/swift
sudo rm -rf /usr/local/share/powershell
sudo rm -rf /usr/local/julia*
sudo rm -rf /opt/az
sudo rm -rf /usr/local/share/chromium
sudo rm -rf /opt/microsoft
sudo rm -rf /opt/google
sudo rm -rf /usr/lib/firefox
- name: Log into the Azure account
uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2.3.0
with:
client-id: ${{ secrets.AZ_APPID }}
tenant-id: ${{ secrets.AZ_TENANT_ID }}
subscription-id: ${{ secrets.AZ_SUBSCRIPTION_ID }}
- name: Deploy kubernetes
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh deploy-k8s
- name: Create AKS cluster
uses: nick-fields/retry@ce71cc2ab81d554ebbe88c79ab5975992d79ba08 # v3.0.2
with:
timeout_minutes: 15
max_attempts: 20
retry_on: error
retry_wait_seconds: 10
command: 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`
uses: azure/setup-kubectl@776406bce94f63e41d621b960d78ee25c8b76ede # v4.0.1
with:
version: 'latest'
- 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: 20
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata-aks
env:
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: ${{ matrix.environment.snapshotter == 'nydus' }}
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: ${{ env.SNAPSHOTTER == 'nydus' }}
AUTO_GENERATE_POLICY: ${{ env.PULL_TYPE == 'experimental-force-guest-pull' && 'no' || 'yes' }}
- name: Deploy CoCo KBS
timeout-minutes: 10
@@ -227,126 +240,9 @@ jobs:
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh install-kbs-client
- name: Run tests
timeout-minutes: 80
run: bash tests/integration/kubernetes/gha-run.sh run-tests
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Delete kata-deploy
if: always()
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh cleanup
- name: Delete CoCo KBS
if: always()
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh delete-coco-kbs
# Extensive matrix: autogenerated policy tests (nydus + experimental-force-guest-pull) on k0s, k3s, rke2, microk8s with qemu-coco-dev / qemu-coco-dev-runtime-rs
run-k8s-tests-coco-nontee-extensive-matrix:
if: ${{ inputs.extensive-matrix-autogenerated-policy == 'yes' }}
name: run-k8s-tests-coco-nontee-extensive-matrix
strategy:
fail-fast: false
matrix:
environment: [
{ k8s: k0s, vmm: qemu-coco-dev, snapshotter: nydus, pull_type: guest-pull },
{ k8s: k0s, vmm: qemu-coco-dev, snapshotter: "", pull_type: experimental-force-guest-pull },
{ k8s: k0s, vmm: qemu-coco-dev-runtime-rs, snapshotter: nydus, pull_type: guest-pull },
{ k8s: k3s, vmm: qemu-coco-dev, snapshotter: nydus, pull_type: guest-pull },
{ k8s: k3s, vmm: qemu-coco-dev, snapshotter: "", pull_type: experimental-force-guest-pull },
{ k8s: k3s, vmm: qemu-coco-dev-runtime-rs, snapshotter: nydus, pull_type: guest-pull },
{ k8s: rke2, vmm: qemu-coco-dev, snapshotter: nydus, pull_type: guest-pull },
{ k8s: rke2, vmm: qemu-coco-dev, snapshotter: "", pull_type: experimental-force-guest-pull },
{ k8s: rke2, vmm: qemu-coco-dev-runtime-rs, snapshotter: nydus, pull_type: guest-pull },
{ k8s: microk8s, vmm: qemu-coco-dev, snapshotter: nydus, pull_type: guest-pull },
{ k8s: microk8s, vmm: qemu-coco-dev, snapshotter: "", pull_type: experimental-force-guest-pull },
{ k8s: microk8s, vmm: qemu-coco-dev-runtime-rs, snapshotter: nydus, pull_type: guest-pull },
]
runs-on: ubuntu-24.04
permissions:
contents: read
environment: ci
env:
DOCKER_REGISTRY: ${{ inputs.registry }}
DOCKER_REPO: ${{ inputs.repo }}
DOCKER_TAG: ${{ inputs.tag }}
GH_PR_NUMBER: ${{ inputs.pr-number }}
KATA_HYPERVISOR: ${{ matrix.environment.vmm }}
KBS: "true"
KBS_INGRESS: "nodeport"
KUBERNETES: ${{ matrix.environment.k8s }}
SNAPSHOTTER: ${{ matrix.environment.snapshotter }}
PULL_TYPE: ${{ matrix.environment.pull_type }}
EXPERIMENTAL_FORCE_GUEST_PULL: ${{ matrix.environment.pull_type == 'experimental-force-guest-pull' && matrix.environment.vmm || '' }}
AUTHENTICATED_IMAGE_USER: ${{ vars.AUTHENTICATED_IMAGE_USER }}
AUTHENTICATED_IMAGE_PASSWORD: ${{ secrets.AUTHENTICATED_IMAGE_PASSWORD }}
AUTO_GENERATE_POLICY: "yes"
K8S_TEST_HOST_TYPE: "all"
GH_TOKEN: ${{ github.token }}
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
fetch-depth: 0
persist-credentials: false
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: get-kata-tools-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-tools-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-tools-artifacts
- name: Install kata-tools
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Remove unnecessary directories to free up space
run: |
sudo rm -rf /usr/local/.ghcup
sudo rm -rf /opt/hostedtoolcache/CodeQL
sudo rm -rf /usr/local/lib/android
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf /usr/local/share/boost
sudo rm -rf /usr/lib/jvm
sudo rm -rf /usr/share/swift
sudo rm -rf /usr/local/share/powershell
sudo rm -rf /usr/local/julia*
sudo rm -rf /opt/az
sudo rm -rf /usr/local/share/chromium
sudo rm -rf /opt/microsoft
sudo rm -rf /opt/google
sudo rm -rf /usr/lib/firefox
- name: Deploy ${{ matrix.environment.k8s }}
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh deploy-k8s
- name: Install `bats`
run: bash tests/integration/kubernetes/gha-run.sh install-bats
- name: Deploy Kata
timeout-minutes: 20
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata
env:
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: ${{ matrix.environment.snapshotter == 'nydus' }}
- name: Deploy CoCo KBS
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh deploy-coco-kbs
- name: Install `kbs-client`
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh install-kbs-client
- name: Deploy CSI driver
timeout-minutes: 5
run: bash tests/integration/kubernetes/gha-run.sh deploy-csi-driver
- name: Run tests
timeout-minutes: 80
@@ -356,15 +252,18 @@ jobs:
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Delete kata-deploy
- name: Refresh OIDC token in case access token expired
if: always()
uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2.3.0
with:
client-id: ${{ secrets.AZ_APPID }}
tenant-id: ${{ secrets.AZ_TENANT_ID }}
subscription-id: ${{ secrets.AZ_SUBSCRIPTION_ID }}
- name: Delete AKS cluster
if: always()
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh cleanup
- name: Delete CoCo KBS
if: always()
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh delete-coco-kbs
run: bash tests/integration/kubernetes/gha-run.sh delete-cluster
# Generate jobs for testing CoCo on non-TEE environments with erofs-snapshotter
run-k8s-tests-coco-nontee-with-erofs-snapshotter:
@@ -392,7 +291,7 @@ jobs:
KBS_INGRESS: ""
KUBERNETES: "vanilla"
CONTAINER_ENGINE: "containerd"
CONTAINER_ENGINE_VERSION: "active"
CONTAINER_ENGINE_VERSION: "v2.2"
PULL_TYPE: ${{ matrix.pull-type }}
SNAPSHOTTER: ${{ matrix.snapshotter }}
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: "true"
@@ -400,7 +299,6 @@ jobs:
# We are skipping the auto generated policy tests for now,
# but those should be enabled as soon as we work on that.
AUTO_GENERATE_POLICY: "no"
GH_TOKEN: ${{ github.token }}
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
@@ -444,6 +342,8 @@ jobs:
- name: Deploy kubernetes
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh deploy-k8s
env:
GH_TOKEN: ${{ github.token }}
- name: Install `bats`
run: bash tests/integration/kubernetes/gha-run.sh install-bats
@@ -452,6 +352,10 @@ jobs:
timeout-minutes: 20
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata
- name: Deploy CSI driver
timeout-minutes: 5
run: bash tests/integration/kubernetes/gha-run.sh deploy-csi-driver
- name: Run tests
timeout-minutes: 80
run: bash tests/integration/kubernetes/gha-run.sh run-tests
@@ -459,8 +363,3 @@ jobs:
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Delete kata-deploy
if: always()
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh cleanup

View File

@@ -55,6 +55,6 @@ jobs:
# Upload the results to GitHub's code scanning dashboard (optional).
# Commenting out will disable upload of results to your repo's Code Scanning dashboard
- name: "Upload to code-scanning"
uses: github/codeql-action/upload-sarif@4bdb89f48054571735e3792627da6195c57459e2 # v3.31.10
uses: github/codeql-action/upload-sarif@v3
with:
sarif_file: results.sarif

View File

@@ -1,30 +0,0 @@
name: Spelling check
on: ["pull_request"]
permissions: {}
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
jobs:
check-spelling:
name: check-spelling
runs-on: ubuntu-24.04
steps:
- name: Checkout code
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
fetch-depth: 0
persist-credentials: false
- name: Check Spelling
uses: streetsidesoftware/cspell-action@9cd41bb518a24fefdafd9880cbab8f0ceba04d28 # 8.3.0
with:
files: |
**/*.md
**/*.rst
**/*.txt
incremental_files_only: true
config: ".cspell.yaml"

View File

@@ -126,19 +126,14 @@ jobs:
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
- name: Install golang
run: |
cd "${GOPATH}/src/github.com/${GITHUB_REPOSITORY}"
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
./tests/install_go.sh -f -p
echo "/usr/local/go/bin" >> "$GITHUB_PATH"
- name: Install system dependencies
run: |
sudo apt-get update && sudo apt-get -y install moreutils
sudo apt-get update && sudo apt-get -y install moreutils hunspell hunspell-en-gb hunspell-en-us pandoc
- name: Install open-policy-agent
run: |
cd "${GOPATH}/src/github.com/${GITHUB_REPOSITORY}"

3
.gitignore vendored
View File

@@ -20,6 +20,3 @@ tools/packaging/static-build/agent/install_libseccomp.sh
.direnv
**/.DS_Store
site/
opt/
tools/packaging/kernel/configs/**/.config
root_hash.txt

1728
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -22,9 +22,6 @@ members = [
"src/dragonball/dbs_utils",
"src/dragonball/dbs_virtio_devices",
# genpolicy
"src/tools/genpolicy",
# runtime-rs
"src/runtime-rs",
"src/runtime-rs/crates/agent",
@@ -110,9 +107,6 @@ safe-path = { path = "src/libs/safe-path" }
shim-interface = { path = "src/libs/shim-interface" }
test-utils = { path = "src/libs/test-utils" }
# Local dependencies from `src/agent`
kata-agent-policy = { path = "src/agent/policy" }
# Outside dependencies
actix-rt = "2.7.0"
anyhow = "1.0"

View File

@@ -1 +1 @@
3.28.0
3.26.0

View File

@@ -378,7 +378,7 @@ that is used in the test" section. From there you can see exactly what you'll
have to use when deploying kata-deploy in your local cluster.
> [!NOTE]
> TODO: @wainersm TO FINISH THIS PART BASED ON HIS PR TO RUN A LOCAL CI
> TODO: WAINER TO FINISH THIS PART BASED ON HIS PR TO RUN A LOCAL CI
## Adding new runners

View File

@@ -98,7 +98,7 @@ Let's say the OCP pipeline passed running with
but failed running with
``quay.io/kata-containers/kata-deploy-ci:kata-containers-9f512c016e75599a4a921bd84ea47559fe610057-amd64``
and you'd like to know which PR caused the regression. You can either run with
all the 60 tags between or you can utilize the [`bisecter`](https://github.com/ldoktor/bisecter)
all the 60 tags between or you can utilize the [bisecter](https://github.com/ldoktor/bisecter)
to optimize the number of steps in between.
Before running the bisection you need a reproducer script. Sample one called

View File

@@ -730,7 +730,7 @@ sudo sed -i -e 's/^kernel_params = "\(.*\)"/kernel_params = "\1 agent.debug_cons
##### Connecting to the debug console
Next, connect to the debug console. The VSOCK paths vary slightly between each
Next, connect to the debug console. The VSOCKS paths vary slightly between each
VMM solution.
In case of cloud-hypervisor, connect to the `vsock` as shown:

View File

@@ -188,14 +188,15 @@ and compare them with standard tools (e.g. `diff(1)`).
# Spelling
Since this project uses a number of terms not found in conventional
dictionaries, we have a [kata-dictionary](../tests/spellcheck/kata-dictionary.txt)
that contains some project specific terms we use.
dictionaries, we have a
[spell checking tool](https://github.com/kata-containers/kata-containers/tree/main/tests/cmd/check-spelling)
that checks both dictionary words and the additional terms we use.
You can run the `cspell` checking tool on your document before raising a PR to ensure it
Run the spell checking tool on your document before raising a PR to ensure it
is free of mistakes.
If your document introduces new terms, you need to update the custom
dictionary to incorporate the new words.
dictionary used by the spell checking tool to incorporate the new words.
# Names

View File

@@ -187,10 +187,9 @@ different compared to `runc` containers:
into the guest and exposes it directly to the container.
**Mounting guest devices**: When the source path of a hostPath volume is
under `/dev` (or `/dev` itself), and the path corresponds to a
non-regular file (i.e., a device, directory, or any other special file)
or is not accessible by the Kata shim, the Kata agent bind mounts the
source path directly from the *guest* filesystem into the container.
under `/dev`, and the path either corresponds to a host device or is not
accessible by the Kata shim, the Kata agent bind mounts the source path
directly from the *guest* filesystem into the container.
[runtime-config]: /src/runtime/README.md#configuration
[k8s-hostpath]: https://kubernetes.io/docs/concepts/storage/volumes/#hostpath
@@ -227,35 +226,6 @@ Importantly, the default behavior to pass the host devices to a
privileged container is not supported in Kata Containers and needs to be
disabled, see [Privileged Kata Containers](how-to/privileged.md).
## Guest pulled container images
When using features like **nydus guest-pull**, set user/group IDs explicitly in the pod spec.
If the ID values are omitted:
- Your workload might be executed with unexpected user/group ID values, because image layers
may be unavailable to containerd, so image config (including user/group) is not applied.
- If using policy or genpolicy, the generated policy may detect these unexpected values and
reject the creation of workload containers.
Set `securityContext` explicitly. Use **pod-level** `spec.securityContext` (for Pods) or
`spec.template.spec.securityContext` (for controllers like Deployments) and/or **container-level**
`spec.containers[].securityContext`. Include at least:
- `runAsUser` — primary user ID
- `runAsGroup` — primary group ID
- `fsGroup` — volume group ownership (often reflected as a supplemental group)
- `supplementalGroups` — list of additional group IDs (if needed)
Example:
```yaml
# Explicit user/group/supplementary groups to support nydus guest-pull
securityContext:
runAsUser: 0
runAsGroup: 0
fsGroup: 0
supplementalGroups: [1, 2, 3, 4, 6, 10, 11, 20, 26, 27]
```
# Appendices
## The constraints challenge

View File

@@ -1,64 +1,57 @@
# How to do a Kata Containers Release
This document lists the tasks required to create a Kata Release.
## Requirements
- GitHub permissions to run workflows.
## Release Model
## Versioning
Kata Containers follows a rolling release model with monthly snapshots.
New features, bug fixes, and improvements are continuously integrated into
`main`. Each month, a snapshot is tagged as a new `MINOR` release.
The Kata Containers project uses [semantic versioning](http://semver.org/) for all releases.
Semantic versions are comprised of three fields in the form:
### Versioning
```
MAJOR.MINOR.PATCH
```
Releases use the `MAJOR.MINOR.PATCH` scheme. Monthly snapshots increment
`MINOR`; `PATCH` is typically `0`. Major releases are rare (years apart) and
signal significant architectural changes that may require updates to container
managers (Containerd, CRI-O) or other infrastructure. Breaking changes in
`MINOR` releases are avoided where possible, but may occasionally occur as
features are deprecated or removed.
When `MINOR` increases, the new release adds **new features** but *without changing the existing behavior*.
### No Stable Branches
When `MAJOR` increases, the new release adds **new features, bug fixes, or
both** and which **changes the behavior from the previous release** (incompatible with previous releases).
The Kata Containers project does not maintain stable branches (see
[#9064](https://github.com/kata-containers/kata-containers/issues/9064)).
Bug fixes land on `main` and ship in the next monthly snapshot rather than
being backported. Downstream projects that need extended support or compliance
certifications should select a monthly snapshot as their stable base and manage
their own validation and patch backporting from there.
A major release will also likely require a change of the container manager version used,
-for example Containerd or CRI-O. Please refer to the release notes for further details.
**Important** : the Kata Containers project doesn't have stable branches (see
[this issue](https://github.com/kata-containers/kata-containers/issues/9064) for details).
Bug fixes are released as part of `MINOR` or `MAJOR` releases only. `PATCH` is always `0`.
## Release Process
### Bump the `VERSION` and `Chart.yaml` file
When the `kata-containers/kata-containers` repository is ready for a new
release, first create a PR to set the release in the [`VERSION`](./../VERSION)
file and update the `version` and `appVersion` in the
[`Chart.yaml`](./../tools/packaging/kata-deploy/helm-chart/kata-deploy/Chart.yaml)
file and have it merged.
When the `kata-containers/kata-containers` repository is ready for a new release,
first create a PR to set the release in the [`VERSION`](./../VERSION) file and update the
`version` and `appVersion` in the
[`Chart.yaml`](./../tools/packaging/kata-deploy/helm-chart/kata-deploy/Chart.yaml) file and
have it merged.
### Lock the `main` branch
In order to prevent any PRs getting merged during the release process, and
slowing the release process down, by impacting the payload caches, we have
recently trialed setting the `main` branch to read only whilst the release
action runs.
In order to prevent any PRs getting merged during the release process, and slowing the release
process down, by impacting the payload caches, we have recently trailed setting the `main`
branch to read only whilst the release action runs.
> [!NOTE]
> Admin permission is needed to complete this task.
### Wait for the `VERSION` bump PR payload publish to complete
To reduce the chance of need to re-run the release workflow, check the [CI |
Publish Kata Containers
payload](https://github.com/kata-containers/kata-containers/actions/workflows/payload-after-push.yaml)
To reduce the chance of need to re-run the release workflow, check the
[CI | Publish Kata Containers payload](https://github.com/kata-containers/kata-containers/actions/workflows/payload-after-push.yaml)
once the `VERSION` PR bump has merged to check that the assets build correctly
and are cached, so that the release process can just download these artifacts
rather than needing to build them all, which takes time and can reveal errors in
infra.
rather than needing to build them all, which takes time and can reveal errors in infra.
### Check GitHub Actions
@@ -70,10 +63,11 @@ release artifacts.
> [!NOTE]
> Write permissions to trigger the action.
The action is manually triggered and is responsible for generating a new release
(including a new tag), pushing those to the `kata-containers/kata-containers`
repository. The new release is initially created as a draft. It is promoted to
an official release when the whole workflow has completed successfully.
The action is manually triggered and is responsible for generating a new
release (including a new tag), pushing those to the
`kata-containers/kata-containers` repository. The new release is initially
created as a draft. It is promoted to an official release when the whole
workflow has completed successfully.
Check the [actions status
page](https://github.com/kata-containers/kata-containers/actions) to verify all
@@ -81,13 +75,12 @@ steps in the actions workflow have completed successfully. On success, a static
tarball containing Kata release artifacts will be uploaded to the [Release
page](https://github.com/kata-containers/kata-containers/releases).
If the workflow fails because of some external environmental causes, e.g.
network timeout, simply re-run the failed jobs until they eventually succeed.
If the workflow fails because of some external environmental causes, e.g. network
timeout, simply re-run the failed jobs until they eventually succeed.
If for some reason you need to cancel the workflow or re-run it entirely, go
first to the [Release
page](https://github.com/kata-containers/kata-containers/releases) and delete
the draft release from the previous run.
If for some reason you need to cancel the workflow or re-run it entirely, go first
to the [Release page](https://github.com/kata-containers/kata-containers/releases) and
delete the draft release from the previous run.
### Unlock the `main` branch
@@ -97,8 +90,9 @@ an admin to do it.
### Improve the release notes
Release notes are auto-generated by the GitHub CLI tool used as part of our
release workflow. However, some manual tweaking may still be necessary in order
to highlight the most important features and bug fixes in a specific release.
release workflow. However, some manual tweaking may still be necessary in
order to highlight the most important features and bug fixes in a specific
release.
With this in mind, please, poke @channel on #kata-dev and people who worked on
the release will be able to contribute to that.

View File

@@ -231,6 +231,12 @@ Run the
[markdown checker](https://github.com/kata-containers/kata-containers/tree/main/tests/cmd/check-markdown)
on your documentation changes.
### Spell check
Run the
[spell checker](https://github.com/kata-containers/kata-containers/tree/main/tests/cmd/check-spelling)
on your documentation changes.
## Finally
You may wish to read the documentation that the

View File

@@ -43,7 +43,7 @@ To fulfill the [Kata design requirements](kata-design-requirements.md), and base
|`sandbox.AddInterface(inf)`| Add new NIC to the sandbox.|
|`sandbox.RemoveInterface(inf)`| Remove a NIC from the sandbox.|
|`sandbox.ListInterfaces()`| List all NICs and their configurations in the sandbox, return a `pbTypes.Interface` list.|
|`sandbox.UpdateRoutes(routes)`| Update the sandbox route table (e.g. for port mapping support), return a `pbTypes.Route` list.|
|`sandbox.UpdateRoutes(routes)`| Update the sandbox route table (e.g. for portmapping support), return a `pbTypes.Route` list.|
|`sandbox.ListRoutes()`| List the sandbox route table, return a `pbTypes.Route` list.|
### Sandbox Relay API

View File

@@ -8,7 +8,7 @@ The following benchmarking result shows the performance improvement compared wit
## Proposal - Bring `lazyload` ability to Kata Containers
`Nydusd` is a fuse/`virtiofs` daemon which is provided by `nydus` project and it supports `PassthroughFS` and [`rafs`](https://github.com/dragonflyoss/image-service/blob/master/docs/nydus-design.md) (Registry Acceleration File System) natively, so in Kata Containers, we can use `nydusd` in place of `virtiofsd` and mount `nydus` image to guest in the meanwhile.
`Nydusd` is a fuse/`virtiofs` daemon which is provided by `nydus` project and it supports `PassthroughFS` and [RAFS](https://github.com/dragonflyoss/image-service/blob/master/docs/nydus-design.md) (Registry Acceleration File System) natively, so in Kata Containers, we can use `nydusd` in place of `virtiofsd` and mount `nydus` image to guest in the meanwhile.
The process of creating/starting Kata Containers with `virtiofsd`,

View File

@@ -23,7 +23,7 @@ workloads with isolated sandboxes (i.e. Kata Containers).
As a result, the CRI implementations extended their semantics for the requirements:
- At the beginning, [`Frakti`](https://github.com/kubernetes/frakti) checks the network configuration of a Pod, and
- At the beginning, [Frakti](https://github.com/kubernetes/frakti) checks the network configuration of a Pod, and
treat Pod with `host` network as trusted, while others are treated as untrusted.
- The containerd introduced an annotation for untrusted Pods since [v1.0](https://github.com/containerd/cri/blob/v1.0.0-rc.0/docs/config.md):
```yaml

View File

@@ -18,7 +18,7 @@ The host kernel must be equal to or later than upstream version [6.11](https://c
[`sev-utils`](https://github.com/amd/sev-utils/blob/coco-202501150000/docs/snp.md) is an easy way to install the required host kernel with the `setup-host` command. However, it will also build compatible guest kernel, OVMF, and QEMU components which are not necessary as these components are packaged with kata. The `sev-utils` script utility can be used with these additional components to test the memory encrypted launch and attestation of a base QEMU SNP guest.
For a simplified way to build just the upstream compatible host kernel, use the Confidential Containers fork of [`amdese-amdsev`](https://github.com/confidential-containers/amdese-amdsev/tree/amd-snp-202501150000). Individual components can be built by running the following command:
For a simplified way to build just the upstream compatible host kernel, use the Confidential Containers fork of [AMDESE AMDSEV](https://github.com/confidential-containers/amdese-amdsev/tree/amd-snp-202501150000). Individual components can be built by running the following command:
```
./build.sh kernel host --install
@@ -65,7 +65,7 @@ $ ./configure --enable-virtfs --target-list=x86_64-softmmu --enable-debug
$ make -j "$(nproc)"
$ popd
```
- Create cert-chain for SNP attestation ( using [`snphost`](https://github.com/virtee/snphost/blob/main/docs/snphost.1.adoc) )
- Create cert-chain for SNP attestation ( using [snphost](https://github.com/virtee/snphost/blob/main/docs/snphost.1.adoc) )
```bash
$ git clone https://github.com/virtee/snphost.git && cd snphost/
$ cargo build
@@ -178,3 +178,4 @@ sudo reboot
```bash
sudo rmmod kvm_amd && sudo modprobe kvm_amd sev_snp=0
```

View File

@@ -49,8 +49,6 @@ In order to allow Kubelet to use containerd (using the CRI interface), configure
EOF
```
For Kata Containers (and especially CoCo / Confidential Containers tests), use at least `--runtime-request-timeout=600s` (10m) so CRI CreateContainerRequest does not time out.
- Inform systemd about the new configuration
```bash

View File

@@ -315,7 +315,7 @@ $ kata-agent-ctl connect --server-address "unix:///var/run/kata/$PODID/root/kata
### compact_threshold
Control the mem-agent compaction function compact threshold.<br>
compact_threshold is the pages number.<br>
When examining the `/proc/pagetypeinfo`, if there's an increase in the number of movable pages of orders smaller than the compact_order compared to the amount following the previous compaction period, and this increase surpasses a certain threshold specifically, more than compact_threshold number of pages, or the number of free pages has decreased by compact_threshold since the previous compaction. Current compact run period will not do compaction because there is no enough fragmented pages to be compaction.<br>
When examining the /proc/pagetypeinfo, if there's an increase in the number of movable pages of orders smaller than the compact_order compared to the amount following the previous compaction period, and this increase surpasses a certain threshold specifically, more than compact_threshold number of pages, or the number of free pages has decreased by compact_threshold since the previous compaction. Current compact run period will not do compaction because there is no enough fragmented pages to be compaction.<br>
This design aims to minimize the impact of unnecessary compaction calls on system performance.<br>
Default to 1024.

View File

@@ -99,9 +99,6 @@ The [`genpolicy`](../../src/tools/genpolicy/) application can be used to generat
**Warning** Users should review carefully the automatically-generated Policy, and modify the Policy file if needed to match better their use case, before using this Policy.
**Important — User / Group / Supplemental groups for Policy and genpolicy**
When using features like **nydus guest-pull**, set user/group IDs explicitly in the pod spec, as described in [Limitations](../Limitations.md#guest-pulled-container-images).
See the [`genpolicy` documentation](../../src/tools/genpolicy/README.md) and the [Policy contents examples](#policy-contents) for additional information.
## Policy contents

View File

@@ -8,7 +8,7 @@
> **Note:** `cri-tools` is only used for debugging and validation purpose, and don't use it to run production workloads.
> **Note:** For how to install and configure `cri-tools` with CRI runtimes like `containerd` or CRI-O, please also refer to other [how-tos](./README.md).
> **Note:** For how to install and configure `cri-tools` with CRI runtimes like `containerd` or CRI-O, please also refer to other [howtos](./README.md).
## Use `crictl` run Pods in Kata containers

View File

@@ -175,7 +175,7 @@ specific).
##### Dragonball networking
For Dragonball, the `virtio-net` backend default is within Dragonball's VMM.
For Dragonball, the `virtio-net` backend default is within Dragonbasll's VMM.
#### virtio-vsock

View File

@@ -1,8 +0,0 @@
[[IgnoredVulns]]
# yaml-rust is unmaintained.
# We tried the most promising alternative in https://github.com/kata-containers/kata-containers/pull/12509,
# but its literal quoting is not conformant.
id = "RUSTSEC-2024-0320"
ignoreUntil = 2026-10-01 # TODO(burgerdev): revisit yml library ecosystem
reason = "No alternative currently supports 'yes' strings correctly; genpolicy processes only trusted input."

View File

@@ -1,3 +1,3 @@
[toolchain]
# Keep in sync with versions.yaml
channel = "1.92"
channel = "1.91"

1868
src/agent/Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -63,9 +63,9 @@ cgroups = { package = "cgroups-rs", git = "https://github.com/kata-containers/cg
# Tracing
tracing = "0.1.41"
tracing-subscriber = "0.3.20"
tracing-opentelemetry = "0.17.0"
opentelemetry = { version = "0.17.0", features = ["rt-tokio"] }
tracing-subscriber = "0.2.18"
tracing-opentelemetry = "0.13.0"
opentelemetry = { version = "0.14.0", features = ["rt-tokio-current-thread"] }
# Configuration
serde = { version = "1.0.129", features = ["derive"] }
@@ -78,6 +78,7 @@ strum_macros = "0.26.2"
tempfile = "3.19.1"
which = "4.3.0"
rstest = "0.18.0"
async-std = { version = "1.12.0", features = ["attributes"] }
# Local dependencies
kata-agent-policy = { path = "policy" }
@@ -194,6 +195,7 @@ pv_core = { git = "https://github.com/ibm-s390-linux/s390-tools", rev = "4942504
tempfile.workspace = true
which.workspace = true
rstest.workspace = true
async-std.workspace = true
test-utils.workspace = true

View File

@@ -18,8 +18,6 @@ serde_json.workspace = true
# Agent Policy
regorus = { version = "0.2.8", default-features = false, features = [
"arc",
"base64",
"base64url",
"regex",
"std",
] }

View File

@@ -857,7 +857,7 @@ fn mount_from(
dest.as_str(),
Some(mount_typ.as_str()),
flags,
Some(d.as_str()).filter(|s| !s.is_empty()),
Some(d.as_str()),
)
.inspect_err(|e| log_child!(cfd_log, "mount error: {:?}", e))?;

View File

@@ -89,7 +89,7 @@ pub fn baremount(
let destination_str = destination.to_string_lossy();
if let Ok(m) = get_linux_mount_info(destination_str.deref()) {
if m.fs_type == fs_type && !flags.contains(MsFlags::MS_REMOUNT) {
slog::info!(logger, "{source:?} is already mounted at {destination:?}");
slog_info!(logger, "{source:?} is already mounted at {destination:?}");
return Ok(());
}
}

View File

@@ -110,10 +110,8 @@ impl Namespace {
unshare(cf)?;
if ns_type == NamespaceType::Uts {
if let Some(host) = hostname {
nix::unistd::sethostname(host)?;
}
if ns_type == NamespaceType::Uts && hostname.is_some() {
nix::unistd::sethostname(hostname.unwrap())?;
}
// Bind mount the new namespace from the current thread onto the mount point to persist it.

View File

@@ -2308,6 +2308,9 @@ fn is_sealed_secret_path(source_path: &str) -> bool {
}
async fn cdh_handler_trusted_storage(oci: &mut Spec) -> Result<()> {
if !confidential_data_hub::is_cdh_client_initialized() {
return Ok(());
}
let linux = oci
.linux()
.as_ref()
@@ -2317,10 +2320,23 @@ async fn cdh_handler_trusted_storage(oci: &mut Spec) -> Result<()> {
for specdev in devices.iter() {
if specdev.path().as_path().to_str() == Some(TRUSTED_IMAGE_STORAGE_DEVICE) {
let dev_major_minor = format!("{}:{}", specdev.major(), specdev.minor());
cdh_secure_mount(
"block-device",
&dev_major_minor,
"luks2",
let secure_storage_integrity = AGENT_CONFIG.secure_storage_integrity.to_string();
info!(
sl(),
"trusted_store device major:min {}, enable data integrity {}",
dev_major_minor,
secure_storage_integrity
);
let options = std::collections::HashMap::from([
("deviceId".to_string(), dev_major_minor),
("encryptType".to_string(), "LUKS".to_string()),
("dataIntegrity".to_string(), secure_storage_integrity),
]);
confidential_data_hub::secure_mount(
"BlockDevice",
&options,
vec![],
KATA_IMAGE_WORK_DIR,
)
.await?;
@@ -2331,49 +2347,6 @@ async fn cdh_handler_trusted_storage(oci: &mut Spec) -> Result<()> {
Ok(())
}
pub(crate) async fn cdh_secure_mount(
device_type: &str,
device_id: &str,
encrypt_type: &str,
mount_point: &str,
) -> Result<()> {
if !confidential_data_hub::is_cdh_client_initialized() {
return Ok(());
}
let integrity = AGENT_CONFIG.secure_storage_integrity.to_string();
info!(
sl(),
"cdh_secure_mount: device_type {}, device_id {}, encrypt_type {}, integrity {}",
device_type,
device_id,
encrypt_type,
integrity
);
let options = std::collections::HashMap::from([
("deviceId".to_string(), device_id.to_string()),
("sourceType".to_string(), "empty".to_string()),
("targetType".to_string(), "fileSystem".to_string()),
("filesystemType".to_string(), "ext4".to_string()),
("mkfsOpts".to_string(), "-E lazy_journal_init".to_string()),
("encryptionType".to_string(), encrypt_type.to_string()),
("dataIntegrity".to_string(), integrity),
]);
std::fs::create_dir_all(mount_point).inspect_err(|e| {
error!(
sl(),
"Failed to create mount point directory {}: {:?}", mount_point, e
);
})?;
confidential_data_hub::secure_mount(device_type, &options, vec![], mount_point).await?;
Ok(())
}
async fn cdh_handler_sealed_secrets(oci: &mut Spec) -> Result<()> {
if !confidential_data_hub::is_cdh_client_initialized() {
return Ok(());

View File

@@ -65,12 +65,6 @@ type UeventWatcher = (Box<dyn UeventMatcher>, oneshot::Sender<Uevent>);
pub struct StorageState {
count: Arc<AtomicU32>,
device: Arc<dyn StorageDevice>,
/// Whether the storage is shared across multiple containers (e.g.
/// block-based emptyDirs). Shared storages should not be cleaned up
/// when a container exits; cleanup happens only when the sandbox is
/// destroyed.
shared: bool,
}
impl Debug for StorageState {
@@ -80,11 +74,17 @@ impl Debug for StorageState {
}
impl StorageState {
fn new(shared: bool) -> Self {
fn new() -> Self {
StorageState {
count: Arc::new(AtomicU32::new(1)),
device: Arc::new(StorageDeviceGeneric::default()),
shared,
}
}
pub fn from_device(device: Arc<dyn StorageDevice>) -> Self {
Self {
count: Arc::new(AtomicU32::new(1)),
device,
}
}
@@ -92,10 +92,6 @@ impl StorageState {
self.device.path()
}
pub fn is_shared(&self) -> bool {
self.shared
}
pub async fn ref_count(&self) -> u32 {
self.count.load(Ordering::Relaxed)
}
@@ -175,10 +171,8 @@ impl Sandbox {
/// Add a new storage object or increase reference count of existing one.
/// The caller may detect new storage object by checking `StorageState.refcount == 1`.
/// The `shared` flag indicates if this storage is shared across multiple containers;
/// if true, cleanup will be skipped when containers exit.
#[instrument]
pub async fn add_sandbox_storage(&mut self, path: &str, shared: bool) -> StorageState {
pub async fn add_sandbox_storage(&mut self, path: &str) -> StorageState {
match self.storages.entry(path.to_string()) {
Entry::Occupied(e) => {
let state = e.get().clone();
@@ -186,7 +180,7 @@ impl Sandbox {
state
}
Entry::Vacant(e) => {
let state = StorageState::new(shared);
let state = StorageState::new();
e.insert(state.clone());
state
}
@@ -194,32 +188,22 @@ impl Sandbox {
}
/// Update the storage device associated with a path.
/// Preserves the existing shared flag and reference count.
pub fn update_sandbox_storage(
&mut self,
path: &str,
device: Arc<dyn StorageDevice>,
) -> std::result::Result<Arc<dyn StorageDevice>, Arc<dyn StorageDevice>> {
match self.storages.get(path) {
None => Err(device),
Some(existing) => {
let state = StorageState {
device,
..existing.clone()
};
// Safe to unwrap() because we have just ensured existence of entry via get().
let state = self.storages.insert(path.to_string(), state).unwrap();
Ok(state.device)
}
if !self.storages.contains_key(path) {
return Err(device);
}
let state = StorageState::from_device(device);
// Safe to unwrap() because we have just ensured existence of entry.
let state = self.storages.insert(path.to_string(), state).unwrap();
Ok(state.device)
}
/// Decrease reference count and destroy the storage object if reference count reaches zero.
///
/// For shared storages (e.g., emptyDir volumes), cleanup is skipped even when refcount
/// reaches zero. The storage entry is kept in the map so subsequent containers can reuse
/// the already-mounted storage. Actual cleanup happens when the sandbox is destroyed.
///
/// Returns `Ok(true)` if the reference count has reached zero and the storage object has been
/// removed.
#[instrument]
@@ -228,10 +212,6 @@ impl Sandbox {
None => Err(anyhow!("Sandbox storage with path {} not found", path)),
Some(state) => {
if state.dec_and_test_ref_count().await {
if state.is_shared() {
state.count.store(1, Ordering::Release);
return Ok(false);
}
if let Some(storage) = self.storages.remove(path) {
storage.device.cleanup()?;
}
@@ -740,7 +720,7 @@ mod tests {
let tmpdir_path = tmpdir.path().to_str().unwrap();
// Add a new sandbox storage
let new_storage = s.add_sandbox_storage(tmpdir_path, false).await;
let new_storage = s.add_sandbox_storage(tmpdir_path).await;
// Check the reference counter
let ref_count = new_storage.ref_count().await;
@@ -750,7 +730,7 @@ mod tests {
);
// Use the existing sandbox storage
let new_storage = s.add_sandbox_storage(tmpdir_path, false).await;
let new_storage = s.add_sandbox_storage(tmpdir_path).await;
// Since we are using existing storage, the reference counter
// should be 2 by now.
@@ -791,7 +771,7 @@ mod tests {
assert!(bind_mount(srcdir_path, destdir_path, &logger).is_ok());
s.add_sandbox_storage(destdir_path, false).await;
s.add_sandbox_storage(destdir_path).await;
let storage = StorageDeviceGeneric::new(destdir_path.to_string());
assert!(s
.update_sandbox_storage(destdir_path, Arc::new(storage))
@@ -809,7 +789,7 @@ mod tests {
let other_dir_path = other_dir.path().to_str().unwrap();
other_dir_str = other_dir_path.to_string();
s.add_sandbox_storage(other_dir_path, false).await;
s.add_sandbox_storage(other_dir_path).await;
let storage = StorageDeviceGeneric::new(other_dir_path.to_string());
assert!(s
.update_sandbox_storage(other_dir_path, Arc::new(storage))
@@ -828,9 +808,9 @@ mod tests {
let storage_path = "/tmp/testEphe";
// Add a new sandbox storage
s.add_sandbox_storage(storage_path, false).await;
s.add_sandbox_storage(storage_path).await;
// Use the existing sandbox storage
let state = s.add_sandbox_storage(storage_path, false).await;
let state = s.add_sandbox_storage(storage_path).await;
assert!(
state.ref_count().await > 1,
"Expects false as the storage is not new."

View File

@@ -6,7 +6,7 @@
use crate::linux_abi::pcipath_from_dev_tree_path;
use std::fs;
use std::os::unix::fs::{MetadataExt, PermissionsExt};
use std::os::unix::fs::PermissionsExt;
use std::path::Path;
use std::sync::Arc;
@@ -17,7 +17,6 @@ use kata_types::device::{
DRIVER_BLK_MMIO_TYPE, DRIVER_BLK_PCI_TYPE, DRIVER_NVDIMM_TYPE, DRIVER_SCSI_TYPE,
};
use kata_types::mount::StorageDevice;
use nix::sys::stat::{major, minor};
use protocols::agent::Storage;
use tracing::instrument;
@@ -30,45 +29,10 @@ use crate::device::block_device_handler::{
};
use crate::device::nvdimm_device_handler::wait_for_pmem_device;
use crate::device::scsi_device_handler::get_scsi_device_name;
use crate::storage::{
common_storage_handler, new_device, set_ownership, StorageContext, StorageHandler,
};
use slog::Logger;
use crate::storage::{common_storage_handler, new_device, StorageContext, StorageHandler};
#[cfg(target_arch = "s390x")]
use std::str::FromStr;
fn get_device_number(dev_path: &str, metadata: Option<&fs::Metadata>) -> Result<String> {
let dev_id = match metadata {
Some(m) => m.rdev(),
None => {
let m =
fs::metadata(dev_path).context(format!("get metadata on file {:?}", dev_path))?;
m.rdev()
}
};
Ok(format!("{}:{}", major(dev_id), minor(dev_id)))
}
async fn handle_block_storage(
logger: &Logger,
storage: &Storage,
dev_num: &str,
) -> Result<Arc<dyn StorageDevice>> {
let has_ephemeral_encryption = storage
.driver_options
.contains(&"encryption_key=ephemeral".to_string());
if has_ephemeral_encryption {
crate::rpc::cdh_secure_mount("block-device", dev_num, "luks2", &storage.mount_point)
.await?;
set_ownership(logger, storage)?;
new_device(storage.mount_point.clone())
} else {
let path = common_storage_handler(logger, storage)?;
new_device(path)
}
}
#[derive(Debug)]
pub struct VirtioBlkMmioHandler {}
@@ -111,8 +75,6 @@ impl StorageHandler for VirtioBlkPciHandler {
mut storage: Storage,
ctx: &mut StorageContext,
) -> Result<Arc<dyn StorageDevice>> {
let dev_num: String;
// If hot-plugged, get the device node path based on the PCI path
// otherwise use the virt path provided in Storage Source
if storage.source.starts_with("/dev") {
@@ -122,16 +84,15 @@ impl StorageHandler for VirtioBlkPciHandler {
if mode & libc::S_IFBLK == 0 {
return Err(anyhow!("Invalid device {}", &storage.source));
}
dev_num = get_device_number(&storage.source, Some(&metadata))?;
} else {
let (root_complex, pcipath) = pcipath_from_dev_tree_path(&storage.source)?;
let dev_path =
get_virtio_blk_pci_device_name(ctx.sandbox, root_complex, &pcipath).await?;
storage.source = dev_path;
dev_num = get_device_number(&storage.source, None)?;
}
handle_block_storage(ctx.logger, &storage, &dev_num).await
let path = common_storage_handler(ctx.logger, &storage)?;
new_device(path)
}
}
@@ -190,10 +151,10 @@ impl StorageHandler for ScsiHandler {
) -> Result<Arc<dyn StorageDevice>> {
// Retrieve the device path from SCSI address.
let dev_path = get_scsi_device_name(ctx.sandbox, &storage.source).await?;
storage.source = dev_path.clone();
storage.source = dev_path;
let dev_num = get_device_number(&dev_path, None)?;
handle_block_storage(ctx.logger, &storage, &dev_num).await
let path = common_storage_handler(ctx.logger, &storage)?;
new_device(path)
}
}

View File

@@ -172,11 +172,7 @@ pub async fn add_storages(
for storage in storages {
let path = storage.mount_point.clone();
let state = sandbox
.lock()
.await
.add_sandbox_storage(&path, storage.shared)
.await;
let state = sandbox.lock().await.add_sandbox_storage(&path).await;
if state.ref_count().await > 1 {
if let Some(path) = state.path() {
if !path.is_empty() {

View File

@@ -5,8 +5,7 @@
use anyhow::Result;
use opentelemetry::sdk::propagation::TraceContextPropagator;
use opentelemetry::trace::TracerProvider;
use opentelemetry::{global, sdk::trace::Config};
use opentelemetry::{global, sdk::trace::Config, trace::TracerProvider};
use slog::{info, o, Logger};
use std::collections::HashMap;
use tracing_opentelemetry::OpenTelemetryLayer;
@@ -24,12 +23,15 @@ pub fn setup_tracing(name: &'static str, logger: &Logger) -> Result<()> {
let config = Config::default();
let builder = opentelemetry::sdk::trace::TracerProvider::builder()
.with_batch_exporter(exporter, opentelemetry::runtime::Tokio)
.with_batch_exporter(exporter, opentelemetry::runtime::TokioCurrentThread)
.with_config(config);
let provider = builder.build();
let tracer = provider.tracer(name);
// We don't need a versioned tracer.
let version = None;
let tracer = provider.get_tracer(name, version);
let _global_provider = global::set_tracer_provider(provider);

View File

@@ -10,7 +10,7 @@ libc.workspace = true
thiserror.workspace = true
opentelemetry = { workspace = true, features = ["serialize"] }
tokio-vsock.workspace = true
serde_json = "1.0"
bincode = "1.3.3"
byteorder = "1.4.3"
slog = { workspace = true, features = [
"dynamic-keys",

View File

@@ -58,7 +58,7 @@ pub enum Error {
#[error("connection error: {0}")]
ConnectionError(String),
#[error("serialisation error: {0}")]
SerialisationError(#[from] serde_json::Error),
SerialisationError(#[from] bincode::Error),
#[error("I/O error: {0}")]
IOError(#[from] std::io::Error),
}
@@ -81,7 +81,8 @@ async fn write_span(
let mut writer = writer.lock().await;
let encoded_payload: Vec<u8> =
serde_json::to_vec(span).map_err(|e| make_io_error(e.to_string()))?;
bincode::serialize(&span).map_err(|e| make_io_error(e.to_string()))?;
let payload_len: u64 = encoded_payload.len() as u64;
let mut payload_len_as_bytes: [u8; HEADER_SIZE_BYTES as usize] =

View File

@@ -48,6 +48,7 @@ vmm-sys-util = { workspace = true }
virtio-queue = { workspace = true, optional = true }
vm-memory = { workspace = true, features = ["backend-mmap"] }
crossbeam-channel = "0.5.6"
fuse-backend-rs = "0.10.5"
vfio-bindings = { workspace = true, optional = true }
vfio-ioctls = { workspace = true, optional = true }
@@ -85,6 +86,3 @@ host-device = ["dep:vfio-bindings", "dep:vfio-ioctls", "dep:dbs-pci"]
unexpected_cfgs = { level = "warn", check-cfg = [
'cfg(feature, values("test-mock"))',
] }
[package.metadata.cargo-machete]
ignored = ["vfio-bindings"]

View File

@@ -10,10 +10,10 @@ This repository contains the following submodules:
| Name | Arch| Description |
| --- | --- | --- |
| [`bootparam`](src/x86_64/bootparam.rs) | x86_64 | Magic addresses externally used to lay out x86_64 VMs |
| [`fdt`](src/aarch64/fdt.rs) | aarch64| Create FDT for Aarch64 systems |
| [`layout`](src/x86_64/layout.rs) | x86_64 | x86_64 layout constants |
| [`layout`](src/aarch64/layout.rs/) | aarch64 | aarch64 layout constants |
| [`mptable`](src/x86_64/mptable.rs) | x86_64 | MP Table configurations used for defining VM boot status |
| [fdt](src/aarch64/fdt.rs) | aarch64| Create FDT for Aarch64 systems |
| [layout](src/x86_64/layout.rs) | x86_64 | x86_64 layout constants |
| [layout](src/aarch64/layout.rs/) | aarch64 | aarch64 layout constants |
| [mptable](src/x86_64/mptable.rs) | x86_64 | MP Table configurations used for defining VM boot status |
## Acknowledgement

View File

@@ -242,7 +242,7 @@ mod tests {
let metrics = Arc::new(SerialDeviceMetrics::default());
let out: Arc<Mutex<Option<Box<dyn std::io::Write + Send + 'static>>>> =
let out: Arc<Mutex<Option<Box<(dyn std::io::Write + Send + 'static)>>>> =
Arc::new(Mutex::new(Some(Box::new(std::io::sink()))));
let mut serial = SerialDevice {
serial: Serial::with_events(

View File

@@ -23,22 +23,24 @@ dbs-interrupt = { workspace = true, features = [
"kvm-legacy-irq",
"kvm-msi-irq",
] }
downcast-rs = "1.2.0"
byteorder = "1.4.3"
serde = "1.0.27"
vm-memory = { workspace = true }
kvm-ioctls = { workspace = true }
kvm-bindings = { workspace = true }
vfio-ioctls = { workspace = true }
vfio-bindings = { workspace = true }
vm-memory = {workspace = true}
kvm-ioctls = {workspace = true}
kvm-bindings = {workspace = true}
vfio-ioctls = {workspace = true}
vfio-bindings = {workspace = true}
libc = "0.2.39"
virtio-queue = { workspace = true }
dbs-utils = { workspace = true }
vmm-sys-util = {workspace = true}
virtio-queue = {workspace = true}
dbs-utils = {workspace = true}
[dev-dependencies]
dbs-arch = { workspace = true }
kvm-ioctls = { workspace = true }
kvm-ioctls = {workspace = true}
test-utils = { workspace = true }
nix = { workspace = true }

View File

@@ -1174,6 +1174,7 @@ pub(crate) mod tests {
use dbs_virtio_devices::Result as VirtIoResult;
use dbs_virtio_devices::{
ActivateResult, VirtioDeviceConfig, VirtioDeviceInfo, VirtioSharedMemory,
DEVICE_ACKNOWLEDGE, DEVICE_DRIVER, DEVICE_DRIVER_OK, DEVICE_FEATURES_OK, DEVICE_INIT,
};
use dbs_address_space::{AddressSpaceLayout, AddressSpaceRegion, AddressSpaceRegionType};

View File

@@ -3,7 +3,7 @@
This crate is a collection of modules that provides helpers and utilities to create a TDX Dragonball VM.
Currently this crate involves:
- `tdx-ioctls`
- tdx-ioctls
## Acknowledgement

View File

@@ -11,6 +11,7 @@ keywords = ["dragonball", "secure-sandbox", "devices", "upcall", "virtio"]
readme = "README.md"
[dependencies]
anyhow = "1"
log = "0.4.14"
thiserror = "1"
timerfd = "1.2.0"

View File

@@ -99,61 +99,76 @@ impl Default for EpollManager {
#[cfg(test)]
mod tests {
use super::*;
use std::os::fd::AsRawFd;
use std::sync::mpsc::channel;
use std::time::Duration;
use std::os::unix::io::AsRawFd;
use vmm_sys_util::{epoll::EventSet, eventfd::EventFd};
struct DummySubscriber {
pub event: Arc<EventFd>,
pub notify: std::sync::mpsc::Sender<()>,
pub event: EventFd,
}
impl DummySubscriber {
fn new(event: Arc<EventFd>, notify: std::sync::mpsc::Sender<()>) -> Self {
Self { event, notify }
fn new() -> Self {
Self {
event: EventFd::new(0).unwrap(),
}
}
}
impl MutEventSubscriber for DummySubscriber {
fn init(&mut self, ops: &mut EventOps) {
ops.add(Events::new(self.event.as_ref(), EventSet::IN))
.unwrap();
}
fn process(&mut self, events: Events, _ops: &mut EventOps) {
if events.fd() == self.event.as_raw_fd() && events.event_set().contains(EventSet::IN) {
let _ = self.event.read();
let _ = self.notify.send(());
let source = events.fd();
let event_set = events.event_set();
assert_ne!(source, self.event.as_raw_fd());
match event_set {
EventSet::IN => {
unreachable!()
}
EventSet::OUT => {
self.event.read().unwrap();
}
_ => {
unreachable!()
}
}
}
fn init(&mut self, _ops: &mut EventOps) {}
}
#[test]
fn test_epoll_manager() {
let epoll_manager = EpollManager::default();
let (stop_tx, stop_rx) = channel::<()>();
let worker_mgr = epoll_manager.clone();
let worker = std::thread::spawn(move || {
while stop_rx.try_recv().is_err() {
let _ = worker_mgr.handle_events(50);
let mut epoll_manager = EpollManager::default();
let epoll_manager_clone = epoll_manager.clone();
let thread = std::thread::spawn(move || loop {
let count = epoll_manager_clone.handle_events(-1).unwrap();
if count == 0 {
continue;
}
assert_eq!(count, 1);
break;
});
let (notify_tx, notify_rx) = channel::<()>();
let event = Arc::new(EventFd::new(0).unwrap());
let handler = DummySubscriber::new(event.clone(), notify_tx);
let handler = DummySubscriber::new();
let event = handler.event.try_clone().unwrap();
let id = epoll_manager.add_subscriber(Box::new(handler));
thread.join().unwrap();
epoll_manager
.add_event(id, Events::new(&event, EventSet::OUT))
.unwrap();
event.write(1).unwrap();
notify_rx
.recv_timeout(Duration::from_secs(2))
.expect("timeout waiting for subscriber to be processed");
let epoll_manager_clone = epoll_manager.clone();
let thread = std::thread::spawn(move || loop {
let count = epoll_manager_clone.handle_events(-1).unwrap();
if count == 0 {
continue;
}
assert_eq!(count, 2);
break;
});
epoll_manager.clone().remove_subscriber(id).unwrap();
let _ = stop_tx.send(());
worker.join().unwrap();
thread.join().unwrap();
epoll_manager.remove_subscriber(id).unwrap();
}
}

View File

@@ -24,8 +24,8 @@ dbs-boot = { workspace = true }
epoll = ">=4.3.1, <4.3.2"
io-uring = "0.5.2"
fuse-backend-rs = { version = "0.10.5", optional = true }
kvm-bindings = { workspace = true }
kvm-ioctls = { workspace = true }
kvm-bindings = { workspace = true}
kvm-ioctls = {workspace = true}
libc = "0.2.119"
log = "0.4.14"
nix = "0.24.3"
@@ -37,16 +37,19 @@ serde = "1.0.27"
serde_json = "1.0.9"
thiserror = "1"
threadpool = "1"
virtio-bindings = { workspace = true }
virtio-queue = { workspace = true }
vmm-sys-util = { workspace = true }
virtio-bindings = {workspace = true}
virtio-queue = {workspace = true}
vmm-sys-util = {workspace = true}
vm-memory = { workspace = true, features = ["backend-mmap"] }
sendfd = "0.4.3"
vhost-rs = { version = "0.6.1", package = "vhost", optional = true }
timerfd = "1.0"
[dev-dependencies]
vm-memory = { workspace = true, features = ["backend-mmap", "backend-atomic"] }
vm-memory = { workspace = true, features = [
"backend-mmap",
"backend-atomic",
] }
test-utils = { workspace = true }
[features]

View File

@@ -5,7 +5,6 @@
use std::any::Any;
use std::collections::HashMap;
use std::ffi::CString;
use std::fs;
use std::fs::File;
use std::io::{BufRead, BufReader, Read};
use std::marker::PhantomData;
@@ -454,17 +453,6 @@ impl<AS: GuestAddressSpace> VirtioFs<AS> {
prefetch_list_path: Option<String>,
) -> FsResult<()> {
debug!("http_server rafs");
let currentnetns = fs::read_link("/proc/self/ns/net").unwrap_or_default();
info!("========fupan====1==netns={:?}", currentnetns);
let tid = unsafe { libc::syscall(libc::SYS_gettid) as i32 };
let netnspath = format!("/proc/{}/ns/net", tid);
let netns = fs::read_link(netnspath.as_str()).unwrap_or_default();
info!("========fupan====2==netns={:?}", netns);
info!("========fupan====3==config={:?}", config);
let file = Path::new(&source);
let (mut rafs, rafs_cfg) = match config.as_ref() {
Some(cfg) => {

View File

@@ -439,19 +439,19 @@ pub mod tests {
VirtqDesc { desc }
}
pub fn addr(&self) -> VolatileRef<'_, u64> {
pub fn addr(&self) -> VolatileRef<u64> {
self.desc.get_ref(offset_of!(DescriptorTmp, addr)).unwrap()
}
pub fn len(&self) -> VolatileRef<'_, u32> {
pub fn len(&self) -> VolatileRef<u32> {
self.desc.get_ref(offset_of!(DescriptorTmp, len)).unwrap()
}
pub fn flags(&self) -> VolatileRef<'_, u16> {
pub fn flags(&self) -> VolatileRef<u16> {
self.desc.get_ref(offset_of!(DescriptorTmp, flags)).unwrap()
}
pub fn next(&self) -> VolatileRef<'_, u16> {
pub fn next(&self) -> VolatileRef<u16> {
self.desc.get_ref(offset_of!(DescriptorTmp, next)).unwrap()
}
@@ -513,11 +513,11 @@ pub mod tests {
self.start.unchecked_add(self.ring.len() as GuestUsize)
}
pub fn flags(&self) -> VolatileRef<'_, u16> {
pub fn flags(&self) -> VolatileRef<u16> {
self.ring.get_ref(0).unwrap()
}
pub fn idx(&self) -> VolatileRef<'_, u16> {
pub fn idx(&self) -> VolatileRef<u16> {
self.ring.get_ref(2).unwrap()
}
@@ -525,12 +525,12 @@ pub mod tests {
4 + mem::size_of::<T>() * (i as usize)
}
pub fn ring(&self, i: u16) -> VolatileRef<'_, T> {
pub fn ring(&self, i: u16) -> VolatileRef<T> {
assert!(i < self.qsize);
self.ring.get_ref(Self::ring_offset(i)).unwrap()
}
pub fn event(&self) -> VolatileRef<'_, u16> {
pub fn event(&self) -> VolatileRef<u16> {
self.ring.get_ref(Self::ring_offset(self.qsize)).unwrap()
}
@@ -602,7 +602,7 @@ pub mod tests {
(self.dtable.len() / VirtqDesc::dtable_len(1)) as u16
}
pub fn dtable(&self, i: u16) -> VirtqDesc<'_> {
pub fn dtable(&self, i: u16) -> VirtqDesc {
VirtqDesc::new(&self.dtable, i)
}

View File

@@ -690,15 +690,6 @@ mod tests {
use crate::tests::{create_address_space, create_vm_and_irq_manager};
use crate::{create_queue_notifier, VirtioQueueConfig};
fn unique_tap_name(prefix: &str) -> String {
use std::sync::atomic::{AtomicUsize, Ordering};
static CNT: AtomicUsize = AtomicUsize::new(0);
let n = CNT.fetch_add(1, Ordering::Relaxed);
// "vtap" + pid(<=5) + n(<=3) => max len <= 15
format!("{}{:x}{:x}", prefix, std::process::id() & 0xfff, n & 0xfff)
}
fn create_vhost_kern_net_epoll_handler(
id: String,
) -> NetEpollHandler<Arc<GuestMemoryMmap>, QueueSync, GuestRegionMmap> {
@@ -732,16 +723,13 @@ mod tests {
let guest_mac = MacAddr::parse_str(guest_mac_str).unwrap();
let queue_sizes = Arc::new(vec![128]);
let epoll_mgr = EpollManager::default();
let tap_name = unique_tap_name("vtap");
let dev_result: VirtioResult<Net<Arc<GuestMemoryMmap>, QueueSync, GuestRegionMmap>> =
Net::new(tap_name.clone(), Some(&guest_mac), queue_sizes, epoll_mgr);
let mut dev: Net<Arc<GuestMemoryMmap>, QueueSync, GuestRegionMmap> = match dev_result {
Ok(d) => d,
Err(e) => {
eprintln!("skip test: failed to create tap {}: {:?}", tap_name, e);
return;
}
};
let mut dev: Net<Arc<GuestMemoryMmap>, QueueSync, GuestRegionMmap> = Net::new(
String::from("test_vhosttap"),
Some(&guest_mac),
queue_sizes,
epoll_mgr,
)
.unwrap();
assert_eq!(dev.device_type(), TYPE_NET);
@@ -777,16 +765,14 @@ mod tests {
{
let queue_sizes = Arc::new(vec![128]);
let epoll_mgr = EpollManager::default();
let tap_name = unique_tap_name("vtap");
let dev_result: VirtioResult<Net<Arc<GuestMemoryMmap>, QueueSync, GuestRegionMmap>> =
Net::new(tap_name.clone(), Some(&guest_mac), queue_sizes, epoll_mgr);
let mut dev: Net<Arc<GuestMemoryMmap>, QueueSync, GuestRegionMmap> = match dev_result {
Ok(d) => d,
Err(e) => {
eprintln!("skip test: failed to create tap {}: {:?}", tap_name, e);
return;
}
};
let mut dev: Net<Arc<GuestMemoryMmap>, QueueSync, GuestRegionMmap> = Net::new(
String::from("test_vhosttap"),
Some(&guest_mac),
queue_sizes,
epoll_mgr,
)
.unwrap();
let queues = vec![
VirtioQueueConfig::create(128, 0).unwrap(),
VirtioQueueConfig::create(128, 0).unwrap(),
@@ -823,17 +809,13 @@ mod tests {
let queue_eventfd2 = Arc::new(EventFd::new(0).unwrap());
let queue_sizes = Arc::new(vec![128, 128]);
let epoll_mgr = EpollManager::default();
let tap_name = unique_tap_name("vtap");
let dev_result: VirtioResult<Net<Arc<GuestMemoryMmap>, Queue, GuestRegionMmap>> =
Net::new(tap_name.clone(), Some(&guest_mac), queue_sizes, epoll_mgr);
let mut dev: Net<Arc<GuestMemoryMmap>, Queue, GuestRegionMmap> = match dev_result {
Ok(d) => d,
Err(e) => {
eprintln!("skip test: failed to create tap {}: {:?}", tap_name, e);
return;
}
};
let mut dev: Net<Arc<GuestMemoryMmap>, Queue, GuestRegionMmap> = Net::new(
String::from("test_vhosttap"),
Some(&guest_mac),
queue_sizes,
epoll_mgr,
)
.unwrap();
let queues = vec![
VirtioQueueConfig::new(queue, queue_eventfd, notifier.clone(), 1),

View File

@@ -865,11 +865,11 @@ mod tests {
0
);
let config: [u8; 8] = [0; 8];
let _ = VirtioDevice::<Arc<GuestMemoryMmap<()>>, QueueSync, GuestRegionMmap>::write_config(
VirtioDevice::<Arc<GuestMemoryMmap<()>>, QueueSync, GuestRegionMmap>::write_config(
&mut dev, 0, &config,
);
let mut data: [u8; 8] = [1; 8];
let _ = VirtioDevice::<Arc<GuestMemoryMmap<()>>, QueueSync, GuestRegionMmap>::read_config(
VirtioDevice::<Arc<GuestMemoryMmap<()>>, QueueSync, GuestRegionMmap>::read_config(
&mut dev, 0, &mut data,
);
assert_eq!(config, data);

View File

@@ -590,7 +590,6 @@ where
mod tests {
use std::sync::Arc;
use std::thread;
use std::time::{Duration, Instant};
use dbs_device::resources::DeviceResources;
use dbs_interrupt::{InterruptManager, InterruptSourceType, MsiNotifier, NoopNotifier};
@@ -610,16 +609,19 @@ mod tests {
};
use crate::{VirtioDevice, VirtioDeviceConfig, VirtioQueueConfig, TYPE_NET};
fn connect_slave(path: &str, timeout: Duration) -> Option<Endpoint<MasterReq>> {
let deadline = Instant::now() + timeout;
fn connect_slave(path: &str) -> Option<Endpoint<MasterReq>> {
let mut retry_count = 5;
loop {
match Endpoint::<MasterReq>::connect(path) {
Ok(ep) => return Some(ep),
Ok(endpoint) => return Some(endpoint),
Err(_) => {
if Instant::now() >= deadline {
if retry_count > 0 {
std::thread::sleep(std::time::Duration::from_millis(100));
retry_count -= 1;
continue;
} else {
return None;
}
thread::sleep(Duration::from_millis(20));
}
}
}
@@ -637,88 +639,62 @@ mod tests {
#[test]
fn test_vhost_user_net_virtio_device_normal() {
let dir_path = std::path::Path::new("/tmp");
let socket_path = dir_path.join(format!(
"vhost-user-net-{}-{:?}.sock",
std::process::id(),
thread::current().id()
));
let socket_str = socket_path.to_str().unwrap().to_string();
let _ = std::fs::remove_file(&socket_path);
let queue_sizes = Arc::new(vec![128u16]);
let device_socket = concat!("vhost.", line!());
let queue_sizes = Arc::new(vec![128]);
let epoll_mgr = EpollManager::default();
let socket_for_slave = socket_str.clone();
let slave_th = thread::spawn(move || {
let mut slave = connect_slave(&socket_for_slave, Duration::from_secs(5))
.unwrap_or_else(|| panic!("slave connect timeout: {}", socket_for_slave));
let handler = thread::spawn(move || {
let mut slave = connect_slave(device_socket).unwrap();
create_vhost_user_net_slave(&mut slave);
});
let (tx, rx) = std::sync::mpsc::channel();
let socket_for_master = socket_str.clone();
let queue_sizes_for_master = queue_sizes.clone();
let epoll_mgr_for_master = epoll_mgr.clone();
thread::spawn(move || {
let res = VhostUserNet::<Arc<GuestMemoryMmap>>::new_server(
&socket_for_master,
None,
queue_sizes_for_master,
epoll_mgr_for_master,
);
let _ = tx.send(res);
});
let dev_res = rx
.recv_timeout(Duration::from_secs(5))
.unwrap_or_else(|_| panic!("new_server() stuck/timeout: {}", socket_str));
let dev: VhostUserNet<Arc<GuestMemoryMmap>> = dev_res.unwrap_or_else(|e| {
panic!(
"new_server() returned error: {:?}, socket={}",
e, socket_str
)
});
let mut dev: VhostUserNet<Arc<GuestMemoryMmap>> =
VhostUserNet::new_server(device_socket, None, queue_sizes, epoll_mgr).unwrap();
assert_eq!(
VirtioDevice::<Arc<GuestMemoryMmap<()>>, QueueSync, GuestRegionMmap>::device_type(&dev),
TYPE_NET
);
let queue_size = [128u16];
let queue_size = [128];
assert_eq!(
VirtioDevice::<Arc<GuestMemoryMmap<()>>, QueueSync, GuestRegionMmap>::queue_max_sizes(
&dev
),
&queue_size[..]
);
slave_th.join().unwrap();
let _ = std::fs::remove_file(&socket_path);
drop(dev);
assert_eq!(
VirtioDevice::<Arc<GuestMemoryMmap<()>>, QueueSync, GuestRegionMmap>::get_avail_features(&dev, 0),
dev.device().device_info.get_avail_features(0)
);
assert_eq!(
VirtioDevice::<Arc<GuestMemoryMmap<()>>, QueueSync, GuestRegionMmap>::get_avail_features(&dev, 1),
dev.device().device_info.get_avail_features(1)
);
assert_eq!(
VirtioDevice::<Arc<GuestMemoryMmap<()>>, QueueSync, GuestRegionMmap>::get_avail_features(&dev, 2),
dev.device().device_info.get_avail_features(2)
);
VirtioDevice::<Arc<GuestMemoryMmap<()>>, QueueSync, GuestRegionMmap>::set_acked_features(
&mut dev, 2, 0,
);
assert_eq!(VirtioDevice::<Arc<GuestMemoryMmap<()>>, QueueSync, GuestRegionMmap>::get_avail_features(&dev, 2), 0);
let config: [u8; 8] = [0; 8];
let _ = VirtioDevice::<Arc<GuestMemoryMmap<()>>, QueueSync, GuestRegionMmap>::write_config(
&mut dev, 0, &config,
);
let mut data: [u8; 8] = [1; 8];
let _ = VirtioDevice::<Arc<GuestMemoryMmap<()>>, QueueSync, GuestRegionMmap>::read_config(
&mut dev, 0, &mut data,
);
assert_eq!(config, data);
handler.join().unwrap();
}
#[test]
fn test_vhost_user_net_virtio_device_activate() {
skip_if_kvm_unaccessable!();
let dir_path = std::path::Path::new("/tmp");
let socket_path = dir_path.join(format!(
"vhost-user-net-{}-{:?}.sock",
std::process::id(),
thread::current().id()
));
let socket_str = socket_path.to_str().unwrap().to_string();
let _ = std::fs::remove_file(&socket_path);
let queue_sizes = Arc::new(vec![128u16]);
let device_socket = concat!("vhost.", line!());
let queue_sizes = Arc::new(vec![128]);
let epoll_mgr = EpollManager::default();
let socket_for_slave = socket_str.clone();
let slave_th = thread::spawn(move || {
let mut slave = connect_slave(&socket_for_slave, Duration::from_secs(10))
.unwrap_or_else(|| panic!("slave connect timeout: {}", socket_for_slave));
let handler = thread::spawn(move || {
let mut slave = connect_slave(device_socket).unwrap();
create_vhost_user_net_slave(&mut slave);
let mut pfeatures = VhostUserProtocolFeatures::all();
// A workaround for no support for `INFLIGHT_SHMFD`. File an issue to track
@@ -726,30 +702,8 @@ mod tests {
pfeatures -= VhostUserProtocolFeatures::INFLIGHT_SHMFD;
negotiate_slave(&mut slave, pfeatures, true, 1);
});
let (tx, rx) = std::sync::mpsc::channel();
let socket_for_master = socket_str.clone();
let queue_sizes_for_master = queue_sizes.clone();
let epoll_mgr_for_master = epoll_mgr.clone();
thread::spawn(move || {
let res = VhostUserNet::<Arc<GuestMemoryMmap>>::new_server(
&socket_for_master,
None,
queue_sizes_for_master,
epoll_mgr_for_master,
);
let _ = tx.send(res);
});
let mut dev: VhostUserNet<Arc<GuestMemoryMmap>> = rx
.recv_timeout(Duration::from_secs(10))
.unwrap_or_else(|_| panic!("new_server() stuck/timeout: {}", socket_str))
.unwrap_or_else(|e| {
panic!(
"new_server() returned error: {:?}, socket={}",
e, socket_str
)
});
let mut dev: VhostUserNet<Arc<GuestMemoryMmap>> =
VhostUserNet::new_server(device_socket, None, queue_sizes, epoll_mgr).unwrap();
// invalid queue size
{
let kvm = Kvm::new().unwrap();
@@ -806,9 +760,6 @@ mod tests {
);
dev.activate(config).unwrap();
}
slave_th.join().unwrap();
let _ = std::fs::remove_file(&socket_path);
drop(dev);
handler.join().unwrap();
}
}

View File

@@ -867,96 +867,56 @@ mod tests {
.set_read_timeout(Some(Duration::from_millis(150)))
.is_ok());
// stage:
// 0 = handler started
// 1 = first read timed out (main can do first write now)
// 2 = timeout cancelled, handler is about to do 3rd blocking read
let stage = Arc::new((Mutex::new(0u32), Condvar::new()));
let stage2 = Arc::clone(&stage);
let handler = thread::spawn(move || {
// notify started
{
let (lock, cvar) = &*stage2;
let mut s = lock.lock().unwrap();
*s = 0;
let cond_pair = Arc::new((Mutex::new(false), Condvar::new()));
let cond_pair_2 = Arc::clone(&cond_pair);
let handler = thread::Builder::new()
.spawn(move || {
// notify handler thread start
let (lock, cvar) = &*cond_pair_2;
let mut started = lock.lock().unwrap();
*started = true;
cvar.notify_one();
}
drop(started);
let mut reader_buf = [0u8; 5];
let start_time1 = Instant::now();
let mut reader_buf = [0; 5];
// first read would timed out
assert_eq!(
outer_stream.read_exact(&mut reader_buf).unwrap_err().kind(),
ErrorKind::TimedOut
);
let end_time1 = Instant::now().duration_since(start_time1).as_millis();
assert!((150..250).contains(&end_time1));
// 1) first read should timed out
let start_time1 = Instant::now();
assert_eq!(
outer_stream.read_exact(&mut reader_buf).unwrap_err().kind(),
ErrorKind::TimedOut
);
let end_time1 = start_time1.elapsed().as_millis();
assert!((150..300).contains(&end_time1));
// second read would ok
assert!(outer_stream.read_exact(&mut reader_buf).is_ok());
assert_eq!(reader_buf, [1, 2, 3, 4, 5]);
outer_stream
.set_read_timeout(Some(Duration::from_secs(10)))
.unwrap();
// cancel the read timeout
let start_time2 = Instant::now();
outer_stream.set_read_timeout(None).unwrap();
assert!(outer_stream.read_exact(&mut reader_buf).is_ok());
let end_time2 = Instant::now().duration_since(start_time2).as_millis();
assert!(end_time2 >= 500);
})
.unwrap();
// notify main: timeout observed, now do first write
{
let (lock, cvar) = &*stage2;
let mut s = lock.lock().unwrap();
*s = 1;
cvar.notify_one();
}
// 2) second read should ok (main will write after stage==1)
outer_stream.read_exact(&mut reader_buf).unwrap();
assert_eq!(reader_buf, [1, 2, 3, 4, 5]);
// 3) cancel timeout, then do a blocking read; notify main before blocking
outer_stream.set_read_timeout(None).unwrap();
{
let (lock, cvar) = &*stage2;
let mut s = lock.lock().unwrap();
*s = 2;
cvar.notify_one();
}
let start_time2 = Instant::now();
outer_stream.read_exact(&mut reader_buf).unwrap();
let end_time2 = start_time2.elapsed().as_millis();
assert!(end_time2 >= 500);
assert_eq!(reader_buf, [1, 2, 3, 4, 5]);
});
// wait handler started (stage==0)
{
let (lock, cvar) = &*stage;
let mut s = lock.lock().unwrap();
while *s != 0 {
s = cvar.wait(s).unwrap();
}
// wait handler thread started
let (lock, cvar) = &*cond_pair;
let mut started = lock.lock().unwrap();
while !*started {
started = cvar.wait(started).unwrap();
}
// wait first timeout done (stage==1), then do first write
{
let (lock, cvar) = &*stage;
let mut s = lock.lock().unwrap();
while *s < 1 {
s = cvar.wait(s).unwrap();
}
}
inner_stream.write_all(&[1, 2, 3, 4, 5]).unwrap();
// wait handler cancelled timeout and is about to block-read (stage==2)
{
let (lock, cvar) = &*stage;
let mut s = lock.lock().unwrap();
while *s < 2 {
s = cvar.wait(s).unwrap();
}
}
// sleep 300ms, test timeout
thread::sleep(Duration::from_millis(300));
let writer_buf = [1, 2, 3, 4, 5];
inner_stream.write_all(&writer_buf).unwrap();
// sleep 500ms again, test cancel timeout
thread::sleep(Duration::from_millis(500));
inner_stream.write_all(&[1, 2, 3, 4, 5]).unwrap();
let writer_buf = [1, 2, 3, 4, 5];
inner_stream.write_all(&writer_buf).unwrap();
handler.join().unwrap();
}

View File

@@ -339,7 +339,7 @@ mod tests {
}
}
pub fn create_event_handler_context(&self) -> EventHandlerContext<'_> {
pub fn create_event_handler_context(&self) -> EventHandlerContext {
const QSIZE: u16 = 256;
let guest_rxvq = GuestQ::new(GuestAddress(0x0010_0000), &self.mem, QSIZE);

View File

@@ -120,7 +120,7 @@ mod tests {
use libc::{cpu_set_t, syscall};
use std::convert::TryInto;
use std::{mem, thread};
use std::{mem, process, thread};
use seccompiler::{apply_filter, BpfProgram, SeccompAction, SeccompFilter};
@@ -157,16 +157,6 @@ mod tests {
let child = thread::spawn(move || {
assert!(register_signal_handlers().is_ok());
// Trigger SIGBUS/SIGSEGV *before* installing the seccomp filter.
// Call SIGBUS signal handler.
assert_eq!(METRICS.read().unwrap().signals.sigbus.count(), 0);
unsafe { libc::raise(SIGBUS) };
// Call SIGSEGV signal handler.
assert_eq!(METRICS.read().unwrap().signals.sigsegv.count(), 0);
unsafe { libc::raise(SIGSEGV) };
// Install a seccomp filter that traps a known syscall so that we can verify SIGSYS handling.
let filter = SeccompFilter::new(
vec![(libc::SYS_mkdirat, vec![])].into_iter().collect(),
SeccompAction::Allow,
@@ -178,8 +168,20 @@ mod tests {
assert!(apply_filter(&TryInto::<BpfProgram>::try_into(filter).unwrap()).is_ok());
assert_eq!(METRICS.read().unwrap().seccomp.num_faults.count(), 0);
// Invoke the blacklisted syscall to trigger SIGSYS and exercise the SIGSYS handler.
// Call the blacklisted `SYS_mkdirat`.
unsafe { syscall(libc::SYS_mkdirat, "/foo/bar\0") };
// Call SIGBUS signal handler.
assert_eq!(METRICS.read().unwrap().signals.sigbus.count(), 0);
unsafe {
syscall(libc::SYS_kill, process::id(), SIGBUS);
}
// Call SIGSEGV signal handler.
assert_eq!(METRICS.read().unwrap().signals.sigsegv.count(), 0);
unsafe {
syscall(libc::SYS_kill, process::id(), SIGSEGV);
}
});
assert!(child.join().is_ok());

View File

@@ -13,10 +13,13 @@ edition = "2018"
[dependencies]
anyhow = "1.0.31"
byteorder = "1.4.3"
chrono = "0.4.0"
common-path = "=1.0.0"
fail = "0.5.0"
lazy_static = "1.4.0"
libc = "0.2.100"
nix = "0.26.4"
once_cell = "1.9.0"
serde = { version = "1.0.138", features = ["derive"] }
serde_json = "1.0.73"
slog = "2.5.2"
@@ -31,7 +34,10 @@ mockall = "0.13.1"
kata-types = { path = "../kata-types" }
oci-spec = { version = "0.8.1", features = ["runtime"] }
runtime-spec = { path = "../runtime-spec" }
safe-path = { path = "../safe-path" }
[dev-dependencies]
num_cpus = "1.13.1"
serial_test = "0.5.1"
tempfile = "3.19.1"
test-utils = { path = "../test-utils" }

View File

@@ -29,14 +29,12 @@ serde-enum-str = "0.4"
sysinfo = "0.34.2"
sha2 = "0.10.8"
flate2 = "1.1"
nix = "0.26.4"
hex = "0.4"
oci-spec = { version = "0.8.1", features = ["runtime"] }
safe-path = { path = "../safe-path", optional = true }
[target.'cfg(target_os = "macos")'.dependencies]
sysctl = "0.7.1"
[dev-dependencies]
tempfile = "3.19.1"
test-utils = { path = "../test-utils" }

View File

@@ -13,7 +13,6 @@ use super::{default, register_hypervisor_plugin};
use crate::config::default::MAX_CH_VCPUS;
use crate::config::default::MIN_CH_MEMORY_SIZE_MB;
use crate::config::hypervisor::VIRTIO_BLK_MMIO;
use crate::config::{ConfigPlugin, TomlConfig};
use crate::{resolve_path, validate_path};
@@ -105,16 +104,6 @@ impl ConfigPlugin for CloudHypervisorConfig {
));
}
// CoCo guest hardening: virtio-mmio is not hardened for confidential computing.
if ch.security_info.confidential_guest
&& ch.boot_info.vm_rootfs_driver == VIRTIO_BLK_MMIO
{
return Err(std::io::Error::other(
"Confidential guests must not use virtio-blk-mmio (use virtio-blk-pci); \
virtio-mmio is not hardened for CoCo",
));
}
if ch.boot_info.kernel.is_empty() {
return Err(std::io::Error::other("Guest kernel image for CH is empty"));
}

View File

@@ -26,6 +26,7 @@
use super::{default, ConfigOps, ConfigPlugin, TomlConfig};
use crate::annotations::KATA_ANNO_CFG_HYPERVISOR_PREFIX;
use crate::{resolve_path, sl, validate_path};
use byte_unit::{Byte, Unit};
use lazy_static::lazy_static;
use regex::RegexSet;
use serde_enum_str::{Deserialize_enum_str, Serialize_enum_str};
@@ -33,6 +34,7 @@ use std::collections::HashMap;
use std::io::{self, Result};
use std::path::Path;
use std::sync::{Arc, Mutex};
use sysinfo::{MemoryRefreshKind, RefreshKind, System};
mod dragonball;
pub use self::dragonball::{DragonballConfig, HYPERVISOR_NAME_DRAGONBALL};
@@ -1005,57 +1007,6 @@ fn default_guest_swap_create_threshold_secs() -> u64 {
60
}
/// Get host memory size in MiB.
/// Retrieves the total physical memory of the host across different platforms.
fn host_memory_mib() -> io::Result<u64> {
// Select a platform-specific implementation via a function pointer.
let get_memory: fn() -> io::Result<u64> = {
#[cfg(target_os = "linux")]
{
|| {
let info = nix::sys::sysinfo::sysinfo().map_err(io::Error::other)?;
Ok(info.ram_total() / (1024 * 1024)) // MiB
}
}
#[cfg(target_os = "macos")]
{
|| {
use sysctl::{Ctl, CtlValue, Sysctl};
let v = Ctl::new("hw.memsize")
.map_err(io::Error::other)?
.value()
.map_err(io::Error::other)?;
let bytes = match v {
CtlValue::S64(x) if x >= 0 => x as u64,
other => {
return Err(io::Error::new(
io::ErrorKind::InvalidData,
format!("unexpected sysctl hw.memsize value type: {:?}", other),
));
}
};
Ok(bytes / (1024 * 1024)) // MiB
}
}
#[cfg(not(any(target_os = "linux", target_os = "macos")))]
{
|| {
Err(io::Error::new(
io::ErrorKind::Unsupported,
"host memory query not implemented on this platform",
))
}
}
};
get_memory()
}
impl MemoryInfo {
/// Adjusts the configuration information after loading from a configuration file.
///
@@ -1067,15 +1018,13 @@ impl MemoryInfo {
self.file_mem_backend,
"Memory backend file {} is invalid: {}"
)?;
let host_memory = host_memory_mib()?;
if u64::from(self.default_memory) > host_memory {
self.default_memory = host_memory as u32;
}
if self.default_maxmemory == 0 || u64::from(self.default_maxmemory) > host_memory {
self.default_maxmemory = host_memory as u32;
if self.default_maxmemory == 0 {
let s = System::new_with_specifics(
RefreshKind::nothing().with_memory(MemoryRefreshKind::everything()),
);
self.default_maxmemory = Byte::from_u64(s.total_memory())
.get_adjusted_unit(Unit::MiB)
.get_value() as u32;
}
Ok(())
}
@@ -1218,29 +1167,6 @@ pub struct SecurityInfo {
#[serde(default)]
pub sev_snp_guest: bool,
/// SNP 'ID Block' and 'ID Authentication Information Structure'.
/// If one of snp_id_block or snp_id_auth is specified, the other must be specified, too.
/// Notice that the default SNP policy of QEMU (0x30000) is used by Kata, if not explicitly
/// set via 'snp_guest_policy' option. The IDBlock contains the guest policy as field, and
/// it must match the value from 'snp_guest_policy' or, if unset, the QEMU default policy.
/// 96-byte, base64-encoded blob to provide the 'ID Block' structure for the
/// SNP_LAUNCH_FINISH command defined in the SEV-SNP firmware ABI (QEMU default: all-zero)
#[serde(default)]
pub snp_id_block: String,
/// 4096-byte, base64-encoded blob to provide the 'ID Authentication Information Structure'
/// for the SNP_LAUNCH_FINISH command defined in the SEV-SNP firmware ABI (QEMU default: all-zero)
#[serde(default)]
pub snp_id_auth: String,
/// SNP Guest Policy, the 'POLICY' parameter to the SNP_LAUNCH_START command.
/// If unset, the QEMU default policy (0x30000) will be used.
/// Notice that the guest policy is enforced at VM launch, and your pod VMs
/// won't start at all if the policy denys it. This will be indicated by a
/// 'SNP_LAUNCH_START' error.
#[serde(default = "default_snp_guest_policy")]
pub snp_guest_policy: u32,
/// Path to OCI hook binaries in the *guest rootfs*.
///
/// This setting does not affect host-side hooks, which must instead be
@@ -1302,10 +1228,6 @@ fn default_qgs_port() -> u32 {
4050
}
fn default_snp_guest_policy() -> u32 {
0x30000
}
impl SecurityInfo {
/// Adjusts the security configuration information after loading from a configuration file.
///

View File

@@ -124,17 +124,6 @@ impl ConfigPlugin for QemuConfig {
));
}
// CoCo guest hardening: virtio-mmio transport is not hardened for confidential
// computing; only virtio-pci is. Ensure we never use virtio-blk-mmio for rootfs.
if qemu.security_info.confidential_guest
&& qemu.boot_info.vm_rootfs_driver == VIRTIO_BLK_MMIO
{
return Err(std::io::Error::other(
"Confidential guests must not use virtio-blk-mmio (use virtio-blk-pci); \
virtio-mmio is not hardened for CoCo",
));
}
if qemu.boot_info.kernel.is_empty() {
return Err(std::io::Error::other(
"Guest kernel image for qemu is empty",

View File

@@ -10,6 +10,7 @@ anyhow = "1.0"
page_size = "0.6"
chrono = "0.4"
tokio = { version = "1.45.1", features = ["full"] }
async-trait = "0.1"
maplit = "1.0"
nix = { version = "0.30.1", features = ["fs", "sched"] }

View File

@@ -520,11 +520,6 @@ message Storage {
// FSGroup consists of the group ID and group ownership change policy
// that the mounted volume must have its group ID changed to when specified.
FSGroup fs_group = 7;
// Shared indicates this storage is shared across multiple containers
// (e.g., block-based emptyDirs). When true, the agent should not clean up
// the storage when a container using it exits, as other containers
// may still need it. Cleanup will happen when the sandbox is destroyed.
bool shared = 8;
}
// Device represents only the devices that could have been defined through the

View File

@@ -24,7 +24,9 @@ message SecureMountRequest {
string mount_point = 4;
}
message SecureMountResponse {}
message SecureMountResponse {
string mount_path = 1;
}
message ImagePullRequest {
// - `image_url`: The reference of the image to pull

View File

@@ -9,3 +9,4 @@ license = "Apache-2.0"
serde = "1.0.131"
serde_derive = "1.0.131"
serde_json = "1.0.73"
libc = "0.2.112"

View File

@@ -4,7 +4,7 @@ Safe Path
A library to safely handle filesystem paths, typically for container runtimes.
There are often path related attacks, such as symlink based attacks, time-of-check to time-of-use (TOCTOU) attacks. The `safe-path` crate
There are often path related attacks, such as symlink based attacks, TOCTTOU attacks. The `safe-path` crate
provides several functions and utility structures to protect against path resolution related attacks.
## Support

View File

@@ -28,4 +28,5 @@ nix = { workspace = true }
tokio = { workspace = true, features = ["rt", "rt-multi-thread"] }
shim = { path = "crates/shim" }
common = { workspace = true }
logging = { workspace = true }
runtimes = { workspace = true }

View File

@@ -15,11 +15,6 @@ PROJECT_URL = https://github.com/kata-containers
PROJECT_COMPONENT = containerd-shim-kata-v2
CONTAINERD_RUNTIME_NAME = io.containerd.kata.v2
# This snippet finds all packages inside runtime-rs. Used for tessting.
PACKAGES := $(shell cargo metadata --no-deps --format-version 1 | \
jq -r '.packages[] | select(.manifest_path | contains("runtime-rs")) | .name')
PACKAGE_FLAGS := $(patsubst %,-p %,$(PACKAGES))
include ../../utils.mk
ARCH_DIR = arch
@@ -50,9 +45,9 @@ test:
else
##TARGET default: build code
default: runtime show-header
##TARGET test: run cargo tests for runtime-rs and all its sub-crates.
##TARGET test: run cargo tests
test: static-checks-build
@cargo test $(PACKAGE_FLAGS) --target $(TRIPLE) $(EXTRA_RUSTFEATURES) -- --nocapture --skip bindgen
@cargo test --all --target $(TRIPLE) $(EXTRA_RUSTFEATURES) -- --nocapture --skip bindgen
install: install-runtime install-configs
endif
@@ -63,8 +58,6 @@ else
include $(ARCH_FILE)
endif
ifeq ($(PREFIX),)
PREFIX := /usr
EXEC_PREFIX := $(PREFIX)/local
@@ -187,7 +180,7 @@ DEFNETQUEUES := 1
DEFENABLEANNOTATIONS := [\"enable_iommu\", \"virtio_fs_extra_args\", \"kernel_params\", \"kernel_verity_params\", \"default_vcpus\", \"default_memory\"]
DEFENABLEANNOTATIONS_COCO := [\"enable_iommu\", \"virtio_fs_extra_args\", \"kernel_params\", \"kernel_verity_params\", \"default_vcpus\", \"default_memory\", \"cc_init_data\"]
DEFDISABLEGUESTSECCOMP := true
DEFDISABLEGUESTEMPTYDIR := false
DEFDISABLEGUESTEMPTYDIR := true
##VAR DEFAULTEXPFEATURES=[features] Default experimental features enabled
DEFAULTEXPFEATURES := []
DEFDISABLESELINUX := false
@@ -305,7 +298,7 @@ ifneq (,$(CLHCMD))
KERNELTYPE_CLH = uncompressed
KERNEL_NAME_CLH = $(call MAKE_KERNEL_NAME,$(KERNELTYPE_CLH))
KERNELPATH_CLH = $(KERNELDIR)/$(KERNEL_NAME_CLH)
VMROOTFSDRIVER_CLH := virtio-blk-pci
VMROOTFSDRIVER_CLH := virtio-pmem
DEFSANDBOXCGROUPONLY_CLH := true
DEFSTATICRESOURCEMGMT_CLH := false
@@ -740,7 +733,7 @@ static-checks-build: $(GENERATED_FILES)
$(TARGET): $(GENERATED_FILES) $(TARGET_PATH)
$(TARGET_PATH): $(SOURCES) | show-summary
@RUSTFLAGS="$(EXTRA_RUSTFLAGS) --deny warnings" cargo build -p runtime-rs --target $(TRIPLE) $(if $(findstring release,$(BUILD_TYPE)),--release) $(EXTRA_RUSTFEATURES)
@RUSTFLAGS="$(EXTRA_RUSTFLAGS) --deny warnings" cargo build --target $(TRIPLE) $(if $(findstring release,$(BUILD_TYPE)),--release) $(EXTRA_RUSTFEATURES)
$(GENERATED_FILES): %: %.in
@sed \
@@ -776,7 +769,7 @@ endif
##TARGET run: build and run agent
run:
@cargo run -p runtime-rs --target $(TRIPLE)
@cargo run --target $(TRIPLE)
show-header:
@printf "%s - version %s (commit %s)\n\n" "$(TARGET)" "$(VERSION)" "$(COMMIT_MSG)"

View File

@@ -22,8 +22,6 @@ rootfs_type = @DEFROOTFSTYPE@
# Block storage driver to be used for the VM rootfs is backed
# by a block device.
#
# virtio-pmem is not supported with Cloud Hypervisor.
vm_rootfs_driver = "@VMROOTFSDRIVER_CLH@"
# Path to the firmware.

View File

@@ -5,9 +5,13 @@ authors = { workspace = true }
edition = { workspace = true }
license = { workspace = true }
[dev-dependencies]
futures = "0.1.27"
[dependencies]
anyhow = { workspace = true }
async-trait = { workspace = true }
log = { workspace = true }
protobuf = { workspace = true }
serde = { workspace = true }
serde_json = { workspace = true }
@@ -27,6 +31,3 @@ protocols = { workspace = true, features = ["async"] }
[features]
default = []
[package.metadata.cargo-machete]
ignored = ["slog-scope"]

View File

@@ -28,6 +28,8 @@ path-clean = "1.0.1"
lazy_static = { workspace = true }
tracing = { workspace = true }
ttrpc = { workspace = true, features = ["async"] }
protobuf = { workspace = true }
oci-spec = { workspace = true }
futures = "0.3.25"
safe-path = "0.1.0"
crossbeam-channel = "0.5.6"
@@ -42,6 +44,7 @@ kata-sys-util = { workspace = true }
kata-types = { workspace = true }
logging = { workspace = true }
protocols = { workspace = true, features = ["async"] }
shim-interface = { workspace = true }
persist = { workspace = true }
ch-config = { workspace = true, optional = true }
tests_utils = { workspace = true }

View File

@@ -118,11 +118,13 @@ impl TryFrom<NamedHypervisorConfig> for VmConfig {
// Note how CH handles the different image types:
//
// - A standard image is specified in PmemConfig.
// - An initrd/initramfs is specified in PayloadConfig.
// - An image is specified in DiskConfig.
// Note: pmem is not used as it's not properly supported by Cloud Hypervisor.
// - A confidential guest image is specified by a DiskConfig.
// - If TDX is enabled, the firmware (`td-shim` [1]) must be
// specified in PayloadConfig.
// - A confidential guest initrd is specified by a PayloadConfig with
// firmware.
//
// [1] - https://github.com/confidential-containers/td-shim
let boot_info = cfg.boot_info;
@@ -138,6 +140,14 @@ impl TryFrom<NamedHypervisorConfig> for VmConfig {
return Err(VmConfigError::NoBootFile);
}
let pmem = if use_initrd || guest_protection_is_tdx(guest_protection_to_use.clone()) {
None
} else {
let pmem = PmemConfig::try_from(&boot_info).map_err(VmConfigError::PmemError)?;
Some(vec![pmem])
};
let payload = Some(
PayloadConfig::try_from((
boot_info.clone(),
@@ -149,7 +159,7 @@ impl TryFrom<NamedHypervisorConfig> for VmConfig {
let mut disks: Vec<DiskConfig> = vec![];
if use_image {
if use_image && guest_protection_is_tdx(guest_protection_to_use.clone()) {
let disk = DiskConfig::try_from(boot_info).map_err(VmConfigError::DiskError)?;
disks.push(disk);
@@ -189,6 +199,7 @@ impl TryFrom<NamedHypervisorConfig> for VmConfig {
fs,
net,
devices: host_devices,
pmem,
disks,
vsock: Some(vsock),
rng,
@@ -1645,6 +1656,7 @@ mod tests {
let (memory_info_confidential_guest, mem_config_confidential_guest) =
make_memory_objects(79, usable_max_mem_bytes, true);
let (_, pmem_config_with_image) = make_bootinfo_pmemconfig_objects(image);
let (machine_info, rng_config) = make_machineinfo_rngconfig_objects(entropy_source);
let payload_firmware = None;
@@ -1652,7 +1664,6 @@ mod tests {
let (boot_info_with_initrd, payload_config_with_initrd) =
make_bootinfo_payloadconfig_objects(kernel, initramfs, payload_firmware, None);
let (_, disk_config_with_image) = make_bootinfo_diskconfig_objects(image);
let (_, disk_config_confidential_guest_image) = make_bootinfo_diskconfig_objects(image);
let boot_info_tdx_image = BootInfo {
@@ -1751,7 +1762,7 @@ mod tests {
vsock: Some(valid_vsock.clone()),
// rootfs image specific
disks: Some(vec![disk_config_with_image]),
pmem: Some(vec![pmem_config_with_image]),
payload: Some(PayloadConfig {
kernel: Some(PathBuf::from(kernel)),

View File

@@ -110,16 +110,6 @@ pub struct DeviceConfig {
pub pci_segment: u16,
}
#[derive(Serialize, Deserialize, Clone, Copy, Debug, PartialEq, Eq, Default)]
pub enum ImageType {
FixedVhd,
Qcow2,
Raw,
Vhdx,
#[default]
Unknown,
}
#[derive(Clone, Debug, PartialEq, Eq, Deserialize, Serialize, Default)]
pub struct DiskConfig {
pub path: Option<PathBuf>,
@@ -145,8 +135,6 @@ pub struct DiskConfig {
pub disable_io_uring: bool,
#[serde(default)]
pub pci_segment: u16,
#[serde(default)]
pub image_type: ImageType,
}
#[derive(Clone, Debug, PartialEq, Eq, Deserialize, Serialize, Default)]

View File

@@ -123,12 +123,7 @@ impl CloudHypervisorInner {
}
}
pub fn set_hypervisor_config(&mut self, mut config: HypervisorConfig) {
// virtio-pmem is not supported for Cloud Hypervisor.
if config.boot_info.vm_rootfs_driver == crate::VM_ROOTFS_DRIVER_PMEM {
config.boot_info.vm_rootfs_driver = crate::VM_ROOTFS_DRIVER_BLK.to_string();
}
pub fn set_hypervisor_config(&mut self, config: HypervisorConfig) {
self.config = config;
}

View File

@@ -27,7 +27,6 @@ use ch_config::ch_api::{
};
use ch_config::convert::DEFAULT_NUM_PCI_SEGMENTS;
use ch_config::DiskConfig;
use ch_config::ImageType;
use ch_config::{net_util::MacAddr, DeviceConfig, FsConfig, NetConfig, VsockConfig};
use kata_sys_util::netns::NetnsGuard;
use kata_types::config::hypervisor::RateLimiterConfig;
@@ -470,10 +469,7 @@ impl CloudHypervisorInner {
net_config.id = None;
net_config.num_queues = network_queues_pairs * 2;
info!(
sl!(),
"network device queue pairs {:?}", network_queues_pairs
);
info!(sl!(), "network device queue pairs {:?}", network_queues_pairs);
// we need ensure opening network device happens in netns.
let netns = self.netns.clone().unwrap_or_default();
@@ -554,7 +550,6 @@ impl TryFrom<BlockConfig> for DiskConfig {
readonly: blkcfg.is_readonly,
num_queues: blkcfg.num_queues,
queue_size: blkcfg.queue_size as u16,
image_type: ImageType::Raw,
..Default::default()
};

Some files were not shown because too many files have changed in this diff Show More