From 6f16071359636d1d8f58d5683d1d269dc43e0521 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Fabiano=20Fid=C3=AAncio?= Date: Tue, 1 Nov 2022 13:45:52 +0100 Subject: [PATCH 1/7] guest-image: Allow passing the image / initrd suffix MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This will become very handy by the moment we start building different images targetting different TEEs. Signed-off-by: Fabiano Fidêncio --- tools/packaging/guest-image/build_image.sh | 25 ++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) diff --git a/tools/packaging/guest-image/build_image.sh b/tools/packaging/guest-image/build_image.sh index d32a0130a6..ae8bf8ef4b 100755 --- a/tools/packaging/guest-image/build_image.sh +++ b/tools/packaging/guest-image/build_image.sh @@ -21,6 +21,11 @@ patches_path="" readonly default_patches_dir="${packaging_root_dir}/kernel/patches" export GOPATH=${GOPATH:-${HOME}/go} + +final_image_name="kata-containers" +final_initrd_name="kata-containers-initrd" +image_initrd_extension=".img" + source "${packaging_root_dir}/scripts/lib.sh" arch_target="$(uname -m)" @@ -53,7 +58,7 @@ build_initrd() { mv "kata-containers-initrd.img" "${install_dir}/${initrd_name}" ( cd "${install_dir}" - ln -sf "${initrd_name}" kata-containers-initrd.img + ln -sf "${initrd_name}" "${final_initrd_name}${image_initrd_extension}" ) } @@ -73,7 +78,7 @@ build_image() { fi ( cd "${install_dir}" - ln -sf "${image_name}" kata-containers.img + ln -sf "${image_name}" "${final_image_name}${image_initrd_extension}" ) } @@ -90,6 +95,7 @@ Options: --imagetype=${image_type} --prefix=${prefix} --destdir=${destdir} + --image_initrd_sufix=${image_initrd_suffix} EOF exit "${return_code}" @@ -99,6 +105,7 @@ main() { image_type=image destdir="$PWD" prefix="/opt/kata" + image_initrd_suffix="" builddir="${PWD}" while getopts "h-:" opt; do case "$opt" in @@ -118,6 +125,20 @@ main() { initrd_os_version=$(get_from_kata_deps "assets.initrd.architecture.${arch_target}.version") initrd_name="kata-${initrd_distro}-${initrd_os_version}.${image_type}" ;; + image_initrd_suffix=*) + image_initrd_suffix=${OPTARG#*=} + if [ -n "${image_initrd_suffix}" ]; then + img_distro=$(get_from_kata_deps "assets.image.architecture.${arch_target}.name") + img_os_version=$(get_from_kata_deps "assets.image.architecture.${arch_target}.version") + image_name="kata-${img_distro}-${img_os_version}-${image_initrd_suffix}.${image_type}" + final_image_name="${final_image_name}-${image_initrd_suffix}" + + initrd_distro=$(get_from_kata_deps "assets.initrd.architecture.${arch_target}.name") + initrd_os_version=$(get_from_kata_deps "assets.initrd.architecture.${arch_target}.version") + initrd_name="kata-${initrd_distro}-${initrd_os_version}-${image_initrd_suffix}.${image_type}" + final_initrd_name="${final_initrd_name}-${image_initrd_suffix}" + fi + ;; prefix=*) prefix=${OPTARG#*=} ;; From 68956ad1270511953e841c162867cd511b82c89c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Fabiano=20Fid=C3=AAncio?= Date: Tue, 1 Nov 2022 14:32:57 +0100 Subject: [PATCH 2/7] osbuilder: Add /etc/tdx-attest.conf when using eaa_kbc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit First of all, EAA KBC is only used with TDX, thus we can safely assume that eaa_kbc means TDX, at least for now. A `/etc/tdx-attest.conf` file, with the data "port=4050" is needed as that's the default configuration for the Quote Generation Service (QGS) which is present on the guest side. Signed-off-by: Fabiano Fidêncio --- tools/osbuilder/rootfs-builder/ubuntu/rootfs_lib.sh | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/osbuilder/rootfs-builder/ubuntu/rootfs_lib.sh b/tools/osbuilder/rootfs-builder/ubuntu/rootfs_lib.sh index d9a08b754a..6c47b41fc5 100644 --- a/tools/osbuilder/rootfs-builder/ubuntu/rootfs_lib.sh +++ b/tools/osbuilder/rootfs-builder/ubuntu/rootfs_lib.sh @@ -47,6 +47,8 @@ echo 'deb [arch=amd64] https://download.01.org/intel-sgx/sgx_repo/ubuntu focal m echo 'deb [arch=amd64] http://mirrors.openanolis.cn/inclavare-containers/ubuntu${VERSION_ID} focal main' | tee /etc/apt/sources.list.d/inclavare-containers.list apt-get update apt-get install -y rats-tls-tdx + +echo 'port=4050' | tee /etc/tdx-attest.conf EOF else echo "rats-tls-tdx is only provided for Ubuntu 20.04, there's yet no packages for Ubuntu ${VERSION_ID}" From af75ce04c17d154f40bb15dbdfc5b256337be75e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Fabiano=20Fid=C3=AAncio?= Date: Wed, 2 Nov 2022 16:39:41 +0100 Subject: [PATCH 3/7] osbuilder: Manually add universe repo MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Let's do that instead of updating and installing the `software-properties-common` package, as it reduces the final size of the image. Signed-off-by: Fabiano Fidêncio --- tools/osbuilder/rootfs-builder/ubuntu/rootfs_lib.sh | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/tools/osbuilder/rootfs-builder/ubuntu/rootfs_lib.sh b/tools/osbuilder/rootfs-builder/ubuntu/rootfs_lib.sh index 6c47b41fc5..aedceb1bce 100644 --- a/tools/osbuilder/rootfs-builder/ubuntu/rootfs_lib.sh +++ b/tools/osbuilder/rootfs-builder/ubuntu/rootfs_lib.sh @@ -40,9 +40,7 @@ EOF curl -L http://mirrors.openanolis.cn/inclavare-containers/ubuntu${VERSION_ID}/DEB-GPG-KEY.key | chroot "$rootfs_dir" apt-key add - curl -L https://download.01.org/intel-sgx/sgx_repo/ubuntu/intel-sgx-deb.key | chroot "${rootfs_dir}" apt-key add - cat << EOF | chroot "$rootfs_dir" -apt-get update -apt-get install -y software-properties-common -add-apt-repository universe +echo 'deb [arch=amd64] http://security.ubuntu.com/ubuntu focal-security main universe' | tee /etc/apt/sources.list.d/universe.list echo 'deb [arch=amd64] https://download.01.org/intel-sgx/sgx_repo/ubuntu focal main' | tee /etc/apt/sources.list.d/intel-sgx.list echo 'deb [arch=amd64] http://mirrors.openanolis.cn/inclavare-containers/ubuntu${VERSION_ID} focal main' | tee /etc/apt/sources.list.d/inclavare-containers.list apt-get update From 05db886e27428ddf47627884f56494f3d3b4b8f9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Fabiano=20Fid=C3=AAncio?= Date: Wed, 2 Nov 2022 16:41:12 +0100 Subject: [PATCH 4/7] osbuilder: Remove non-needed packages at the end MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of removing the non-needed packages under `/usr/share` and then installing new components, let's make sure we do the removal at the end of our script. Signed-off-by: Fabiano Fidêncio --- tools/osbuilder/rootfs-builder/ubuntu/rootfs_lib.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/osbuilder/rootfs-builder/ubuntu/rootfs_lib.sh b/tools/osbuilder/rootfs-builder/ubuntu/rootfs_lib.sh index aedceb1bce..9eb118fe49 100644 --- a/tools/osbuilder/rootfs-builder/ubuntu/rootfs_lib.sh +++ b/tools/osbuilder/rootfs-builder/ubuntu/rootfs_lib.sh @@ -30,9 +30,6 @@ EOF cp --remove-destination "$file" "$rootfs_dir$file" done - # Reduce image size and memory footprint by removing unnecessary files and directories. - rm -rf $rootfs_dir/usr/share/{bash-completion,bug,doc,info,lintian,locale,man,menu,misc,pixmaps,terminfo,zsh} - if [ "${AA_KBC}" == "eaa_kbc" ] && [ "${ARCH}" == "x86_64" ]; then source /etc/os-release @@ -52,4 +49,7 @@ EOF echo "rats-tls-tdx is only provided for Ubuntu 20.04, there's yet no packages for Ubuntu ${VERSION_ID}" fi fi + + # Reduce image size and memory footprint by removing unnecessary files and directories. + rm -rf $rootfs_dir/usr/share/{bash-completion,bug,doc,info,lintian,locale,man,menu,misc,pixmaps,terminfo,zsh} } From c72fdaf91696114d90c389d5caa79ec50bbe20fa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Fabiano=20Fid=C3=AAncio?= Date: Tue, 1 Nov 2022 13:53:02 +0100 Subject: [PATCH 5/7] packaging: Build TDX specific guest image MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The specific TDX image relies on having EAA KBC, instead of using the default `offline_fs_kbc`. This image is, with this commit, built and distributed, but not yet used by TDX specific configurations, which will be done in a follow-up commit. Signed-off-by: Fabiano Fidêncio --- .github/workflows/cc-payload-after-push.yaml | 1 + .github/workflows/cc-payload.yaml | 1 + tools/packaging/kata-deploy/local-build/Makefile | 6 +++++- .../kata-deploy/local-build/kata-deploy-binaries.sh | 12 +++++++++++- 4 files changed, 18 insertions(+), 2 deletions(-) diff --git a/.github/workflows/cc-payload-after-push.yaml b/.github/workflows/cc-payload-after-push.yaml index b7b08dd230..7d524de881 100644 --- a/.github/workflows/cc-payload-after-push.yaml +++ b/.github/workflows/cc-payload-after-push.yaml @@ -20,6 +20,7 @@ jobs: - cc-sev-ovmf - cc-sev-rootfs-initrd - cc-tdx-kernel + - cc-tdx-rootfs-image - cc-tdx-qemu - cc-tdx-td-shim - cc-tdx-tdvf diff --git a/.github/workflows/cc-payload.yaml b/.github/workflows/cc-payload.yaml index 44d6e4442f..ca9b38a549 100644 --- a/.github/workflows/cc-payload.yaml +++ b/.github/workflows/cc-payload.yaml @@ -20,6 +20,7 @@ jobs: - cc-sev-ovmf - cc-sev-rootfs-initrd - cc-tdx-kernel + - cc-tdx-rootfs-image - cc-tdx-qemu - cc-tdx-td-shim - cc-tdx-tdvf diff --git a/tools/packaging/kata-deploy/local-build/Makefile b/tools/packaging/kata-deploy/local-build/Makefile index 6c09ab87a6..8cf603e57e 100644 --- a/tools/packaging/kata-deploy/local-build/Makefile +++ b/tools/packaging/kata-deploy/local-build/Makefile @@ -91,7 +91,8 @@ cc: cc-cloud-hypervisor-tarball \ cc-tdx-td-shim-tarball \ cc-tdx-tdvf-tarball \ cc-sev-ovmf-tarball \ - cc-sev-rootfs-initrd-tarball + cc-sev-rootfs-initrd-tarball \ + cc-tdx-rootfs-tarball cc-cloud-hypervisor-tarball: ${MAKE} $@-build @@ -108,6 +109,9 @@ cc-rootfs-image-tarball: cc-sev-rootfs-initrd-tarball: cc-sev-kernel-tarball ${MAKE} $@-build +cc-tdx-rootfs-image-tarball: + ${MAKE} $@-build + cc-shim-v2-tarball: ${MAKE} $@-build diff --git a/tools/packaging/kata-deploy/local-build/kata-deploy-binaries.sh b/tools/packaging/kata-deploy/local-build/kata-deploy-binaries.sh index efbbe646f1..3b4f19f4f2 100755 --- a/tools/packaging/kata-deploy/local-build/kata-deploy-binaries.sh +++ b/tools/packaging/kata-deploy/local-build/kata-deploy-binaries.sh @@ -118,10 +118,11 @@ install_cc_clh() { install_cc_image() { export AA_KBC="${1:-offline_fs_kbc}" image_type="${2:-image}" + image_initrd_suffix="${3:-""}" export KATA_BUILD_CC=yes info "Create CC image configured with AA_KBC=${AA_KBC}" - "${rootfs_builder}" --imagetype="${image_type}" --prefix="${cc_prefix}" --destdir="${destdir}" + "${rootfs_builder}" --imagetype="${image_type}" --prefix="${cc_prefix}" --destdir="${destdir}" --image_initrd_suffix="${image_initrd_suffix}" } install_cc_sev_image() { @@ -130,6 +131,13 @@ install_cc_sev_image() { install_cc_image "${AA_KBC}" "${image_type}" } +install_cc_tdx_image() { + AA_KBC="eaa_kbc" + image_type="image" + image_suffix="tdx" + install_cc_image "${AA_KBC}" "${image_type}" "${image_suffix}" +} + #Install CC kernel asset install_cc_kernel() { export KATA_BUILD_CC=yes @@ -359,6 +367,8 @@ handle_build() { cc-sev-rootfs-initrd) install_cc_sev_image ;; + cc-tdx-rootfs-image) install_cc_tdx_image ;; + cc-shim-v2) install_cc_shimv2 ;; cc-virtiofsd) install_cc_virtiofsd ;; From b14921937a9aac442aa068e9aac81fde9d6392b5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Fabiano=20Fid=C3=AAncio?= Date: Tue, 1 Nov 2022 14:40:29 +0100 Subject: [PATCH 6/7] config: Add specific config for TDX + EAA KBC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As we're switching TDX to using EAA KBC instead of OfflineFS KBC, let's add the configuration files needed for testing this before we fully switch TDX to using such an image. Fixes: #5563 Signed-off-by: Fabiano Fidêncio --- src/runtime/Makefile | 28 + .../configuration-clh-tdx-eaa-kbc.toml.in | 428 ++++++++++++ .../configuration-qemu-tdx-eaa-kbc.toml.in | 636 ++++++++++++++++++ .../kata-deploy-cc/scripts/kata-deploy.sh | 2 + 4 files changed, 1094 insertions(+) create mode 100644 src/runtime/config/configuration-clh-tdx-eaa-kbc.toml.in create mode 100644 src/runtime/config/configuration-qemu-tdx-eaa-kbc.toml.in diff --git a/src/runtime/Makefile b/src/runtime/Makefile index 87949626b6..b0784f6119 100644 --- a/src/runtime/Makefile +++ b/src/runtime/Makefile @@ -56,6 +56,7 @@ BINLIBEXECLIST := BIN_PREFIX = $(PROJECT_TYPE) PROJECT_DIR = $(PROJECT_TAG) IMAGENAME = $(PROJECT_TAG).img +IMAGETDXNAME = $(PROJECT_TAG)-tdx.img INITRDNAME = $(PROJECT_TAG)-initrd.img TARGET = $(BIN_PREFIX)-runtime @@ -115,6 +116,7 @@ KERNELDIR := $(PKGDATADIR) IMAGEPATH := $(PKGDATADIR)/$(IMAGENAME) INITRDPATH := $(PKGDATADIR)/$(INITRDNAME) +IMAGETDXPATH := $(PKGDATADIR)/$(IMAGETDXNAME) FIRMWAREPATH := FIRMWAREVOLUMEPATH := TDVFFIRMWAREPATH := $(PREFIXDEPS)/share/tdvf/OVMF_CODE.fd @@ -295,6 +297,18 @@ ifneq (,$(QEMUCMD)) CONFIGS += $(CONFIG_QEMU_TDX) + CONFIG_FILE_QEMU_TDX_EAA_KBC = configuration-qemu-tdx-eaa-kbc.toml + CONFIG_QEMU_TDX_EAA_KBC = config/$(CONFIG_FILE_QEMU_TDX_EAA_KBC) + CONFIG_QEMU_TDX_EAA_KBC_IN = $(CONFIG_QEMU_TDX_EAA_KBC).in + + CONFIG_PATH_QEMU_TDX_EAA_KBC = $(abspath $(CONFDIR)/$(CONFIG_FILE_QEMU_TDX_EAA_KBC)) + CONFIG_PATHS += $(CONFIG_PATH_QEMU_TDX_EAA_KBC) + + SYSCONFIG_QEMU_TDX_EAA_KBC = $(abspath $(SYSCONFDIR)/$(CONFIG_FILE_QEMU_TDX_EAA_KBC)) + SYSCONFIG_PATHS += $(SYSCONFIG_QEMU_TDX_EAA_KBC) + + CONFIGS += $(CONFIG_QEMU_TDX_EAA_KBC) + CONFIG_FILE_QEMU_SEV = configuration-qemu-sev.toml CONFIG_QEMU_SEV = config/$(CONFIG_FILE_QEMU_SEV) CONFIG_QEMU_SEV_IN = $(CONFIG_QEMU_SEV).in @@ -351,6 +365,18 @@ ifneq (,$(CLHCMD)) CONFIGS += $(CONFIG_CLH_TDX) + CONFIG_FILE_CLH_TDX_EAA_KBC = configuration-clh-tdx-eaa-kbc.toml + CONFIG_CLH_TDX_EAA_KBC = config/$(CONFIG_FILE_CLH_TDX_EAA_KBC) + CONFIG_CLH_TDX_EAA_KBC_IN = $(CONFIG_CLH_TDX_EAA_KBC).in + + CONFIG_PATH_CLH_TDX_EAA_KBC = $(abspath $(CONFDIR)/$(CONFIG_FILE_CLH_TDX_EAA_KBC)) + CONFIG_PATHS += $(CONFIG_PATH_CLH_TDX_EAA_KBC) + + SYSCONFIG_CLH_TDX_EAA_KBC = $(abspath $(SYSCONFDIR)/$(CONFIG_FILE_CLH_TDX_EAA_KBC)) + SYSCONFIG_PATHS += $(SYSCONFIG_CLH_TDX_EAA_KBC) + + CONFIGS += $(CONFIG_CLH_TDX_EAA_KBC) + # CLH-specific options (all should be suffixed by "_CLH") # currently, huge pages are required for virtiofsd support DEFNETWORKMODEL_CLH := tcfilter @@ -482,6 +508,8 @@ USER_VARS += FCVALIDJAILERPATHS USER_VARS += SYSCONFIG USER_VARS += IMAGENAME USER_VARS += IMAGEPATH +USER_VARS += IMAGETDXNAME +USER_VARS += IMAGETDXPATH USER_VARS += INITRDNAME USER_VARS += INITRDPATH USER_VARS += MACHINETYPE diff --git a/src/runtime/config/configuration-clh-tdx-eaa-kbc.toml.in b/src/runtime/config/configuration-clh-tdx-eaa-kbc.toml.in new file mode 100644 index 0000000000..155ec05dbf --- /dev/null +++ b/src/runtime/config/configuration-clh-tdx-eaa-kbc.toml.in @@ -0,0 +1,428 @@ +# Copyright (c) 2019 Ericsson Eurolab Deutschland GmbH +# Copyright (c) 2021 Adobe Inc. +# +# SPDX-License-Identifier: Apache-2.0 +# + +# XXX: WARNING: this file is auto-generated. +# XXX: +# XXX: Source file: "@CONFIG_CLH_IN@" +# XXX: Project: +# XXX: Name: @PROJECT_NAME@ +# XXX: Type: @PROJECT_TYPE@ + +[hypervisor.clh] +path = "@CLHPATH@" +kernel = "@KERNELTDXPATH_CLH@" +image = "@IMAGETDXPATH@" + +# Enable confidential guest support. +# Toggling that setting may trigger different hardware features, ranging +# from memory encryption to both memory and CPU-state encryption and integrity. +# The Kata Containers runtime dynamically detects the available feature set and +# aims at enabling the largest possible one, returning an error if none is +# available, or none is supported by the hypervisor. +# +# Known limitations: +# * Does not work by design: +# - CPU Hotplug +# - Memory Hotplug +# - NVDIMM devices +# +# Supported TEEs: +# * Intel TDX +# +# Default false +confidential_guest = true + +# disable applying SELinux on the VMM process (default false) +disable_selinux=@DEFDISABLESELINUX@ + +# Path to the firmware. +# If you want Cloud Hypervisor to use a specific firmware, set its path below. +# This is option is only used when confidential_guest is enabled. +# +# For more information about firmwared that can be used with specific TEEs, +# please, refer to: +# * Intel TDX: +# - td-shim: https://github.com/confidential-containers/td-shim +# +firmware = "@TDSHIMFIRMWAREPATH@" + +# List of valid annotation names for the hypervisor +# Each member of the list is a regular expression, which is the base name +# of the annotation, e.g. "path" for io.katacontainers.config.hypervisor.path" +enable_annotations = @DEFENABLEANNOTATIONS@ + +# List of valid annotations values for the hypervisor +# Each member of the list is a path pattern as described by glob(3). +# The default if not set is empty (all annotations rejected.) +# Your distribution recommends: @CLHVALIDHYPERVISORPATHS@ +valid_hypervisor_paths = @CLHVALIDHYPERVISORPATHS@ + +# Optional space-separated list of options to pass to the guest kernel. +# For example, use `kernel_params = "vsyscall=emulate"` if you are having +# trouble running pre-2.15 glibc. +# +# WARNING: - any parameter specified here will take priority over the default +# parameter value of the same name used to start the virtual machine. +# Do not set values here unless you understand the impact of doing so as you +# may stop the virtual machine from booting. +# To see the list of default parameters, enable hypervisor debug, create a +# container and look for 'default-kernel-parameters' log entries. +kernel_params = "@TDXKERNELPARAMS@" + +# Default number of vCPUs per SB/VM: +# unspecified or 0 --> will be set to @DEFVCPUS@ +# < 0 --> will be set to the actual number of physical cores +# > 0 <= number of physical cores --> will be set to the specified number +# > number of physical cores --> will be set to the actual number of physical cores +default_vcpus = 1 + +# Default maximum number of vCPUs per SB/VM: +# unspecified or == 0 --> will be set to the actual number of physical cores or to the maximum number +# of vCPUs supported by KVM if that number is exceeded +# > 0 <= number of physical cores --> will be set to the specified number +# > number of physical cores --> will be set to the actual number of physical cores or to the maximum number +# of vCPUs supported by KVM if that number is exceeded +# WARNING: Depending of the architecture, the maximum number of vCPUs supported by KVM is used when +# the actual number of physical cores is greater than it. +# WARNING: Be aware that this value impacts the virtual machine's memory footprint and CPU +# the hotplug functionality. For example, `default_maxvcpus = 240` specifies that until 240 vCPUs +# can be added to a SB/VM, but the memory footprint will be big. Another example, with +# `default_maxvcpus = 8` the memory footprint will be small, but 8 will be the maximum number of +# vCPUs supported by the SB/VM. In general, we recommend that you do not edit this variable, +# unless you know what are you doing. +default_maxvcpus = @DEFMAXVCPUS@ + +# Default memory size in MiB for SB/VM. +# If unspecified then it will be set @DEFMEMSZ@ MiB. +default_memory = @DEFMEMSZ@ + +# Default memory slots per SB/VM. +# If unspecified then it will be set @DEFMEMSLOTS@. +# This is will determine the times that memory will be hotadded to sandbox/VM. +#memory_slots = @DEFMEMSLOTS@ + +# Default maximum memory in MiB per SB / VM +# unspecified or == 0 --> will be set to the actual amount of physical RAM +# > 0 <= amount of physical RAM --> will be set to the specified number +# > amount of physical RAM --> will be set to the actual amount of physical RAM +default_maxmemory = @DEFMAXMEMSZ@ + +# Shared file system type: +# - virtio-fs (default) +# - virtio-fs-nydus +shared_fs = "@DEFSHAREDFS_CLH_VIRTIOFS@" + +# Path to vhost-user-fs daemon. +virtio_fs_daemon = "@DEFVIRTIOFSDAEMON@" + +# List of valid annotations values for the virtiofs daemon +# The default if not set is empty (all annotations rejected.) +# Your distribution recommends: @DEFVALIDVIRTIOFSDAEMONPATHS@ +valid_virtio_fs_daemon_paths = @DEFVALIDVIRTIOFSDAEMONPATHS@ + +# Default size of DAX cache in MiB +virtio_fs_cache_size = @DEFVIRTIOFSCACHESIZE@ + +# Extra args for virtiofsd daemon +# +# Format example: +# ["-o", "arg1=xxx,arg2", "-o", "hello world", "--arg3=yyy"] +# Examples: +# Set virtiofsd log level to debug : ["-o", "log_level=debug"] or ["-d"] +# see `virtiofsd -h` for possible options. +virtio_fs_extra_args = @DEFVIRTIOFSEXTRAARGS@ + +# Cache mode: +# +# - none +# Metadata, data, and pathname lookup are not cached in guest. They are +# always fetched from host and any changes are immediately pushed to host. +# +# - auto +# Metadata and pathname lookup cache expires after a configured amount of +# time (default is 1 second). Data is cached while the file is open (close +# to open consistency). +# +# - always +# Metadata, data, and pathname lookup are cached in guest and never expire. +virtio_fs_cache = "@DEFVIRTIOFSCACHE@" + +# Block storage driver to be used for the hypervisor in case the container +# rootfs is backed by a block device. This is virtio-blk. +block_device_driver = "virtio-blk" + +# Enable huge pages for VM RAM, default false +# Enabling this will result in the VM memory +# being allocated using huge pages. +#enable_hugepages = true + +# Disable the 'seccomp' feature from Cloud Hypervisor, default false +# disable_seccomp = true + +# This option changes the default hypervisor and kernel parameters +# to enable debug output where available. +# +# Default false +#enable_debug = true + +# Path to OCI hook binaries in the *guest rootfs*. +# This does not affect host-side hooks which must instead be added to +# the OCI spec passed to the runtime. +# +# You can create a rootfs with hooks by customizing the osbuilder scripts: +# https://github.com/kata-containers/kata-containers/tree/main/tools/osbuilder +# +# Hooks must be stored in a subdirectory of guest_hook_path according to their +# hook type, i.e. "guest_hook_path/{prestart,poststart,poststop}". +# The agent will scan these directories for executable files and add them, in +# lexicographical order, to the lifecycle of the guest container. +# Hooks are executed in the runtime namespace of the guest. See the official documentation: +# https://github.com/opencontainers/runtime-spec/blob/v1.0.1/config.md#posix-platform-hooks +# Warnings will be logged if any error is encountered while scanning for hooks, +# but it will not abort container execution. +#guest_hook_path = "/usr/share/oci/hooks" +# +# These options are related to network rate limiter at the VMM level, and are +# based on the Cloud Hypervisor I/O throttling. Those are disabled by default +# and we strongly advise users to refer the Cloud Hypervisor official +# documentation for a better understanding of its internals: +# https://github.com/cloud-hypervisor/cloud-hypervisor/blob/main/docs/io_throttling.md +# +# Bandwidth rate limiter options +# +# net_rate_limiter_bw_max_rate controls network I/O bandwidth (size in bits/sec +# for SB/VM). +# The same value is used for inbound and outbound bandwidth. +# Default 0-sized value means unlimited rate. +#net_rate_limiter_bw_max_rate = 0 +# +# net_rate_limiter_bw_one_time_burst increases the initial max rate and this +# initial extra credit does *NOT* affect the overall limit and can be used for +# an *initial* burst of data. +# This is *optional* and only takes effect if net_rate_limiter_bw_max_rate is +# set to a non zero value. +#net_rate_limiter_bw_one_time_burst = 0 +# +# Operation rate limiter options +# +# net_rate_limiter_ops_max_rate controls network I/O bandwidth (size in ops/sec +# for SB/VM). +# The same value is used for inbound and outbound bandwidth. +# Default 0-sized value means unlimited rate. +#net_rate_limiter_ops_max_rate = 0 +# +# net_rate_limiter_ops_one_time_burst increases the initial max rate and this +# initial extra credit does *NOT* affect the overall limit and can be used for +# an *initial* burst of data. +# This is *optional* and only takes effect if net_rate_limiter_bw_max_rate is +# set to a non zero value. +#net_rate_limiter_ops_one_time_burst = 0 +# +# These options are related to disk rate limiter at the VMM level, and are +# based on the Cloud Hypervisor I/O throttling. Those are disabled by default +# and we strongly advise users to refer the Cloud Hypervisor official +# documentation for a better understanding of its internals: +# https://github.com/cloud-hypervisor/cloud-hypervisor/blob/main/docs/io_throttling.md +# +# Bandwidth rate limiter options +# +# disk_rate_limiter_bw_max_rate controls disk I/O bandwidth (size in bits/sec +# for SB/VM). +# The same value is used for inbound and outbound bandwidth. +# Default 0-sized value means unlimited rate. +#disk_rate_limiter_bw_max_rate = 0 +# +# disk_rate_limiter_bw_one_time_burst increases the initial max rate and this +# initial extra credit does *NOT* affect the overall limit and can be used for +# an *initial* burst of data. +# This is *optional* and only takes effect if disk_rate_limiter_bw_max_rate is +# set to a non zero value. +#disk_rate_limiter_bw_one_time_burst = 0 +# +# Operation rate limiter options +# +# disk_rate_limiter_ops_max_rate controls disk I/O bandwidth (size in ops/sec +# for SB/VM). +# The same value is used for inbound and outbound bandwidth. +# Default 0-sized value means unlimited rate. +#disk_rate_limiter_ops_max_rate = 0 +# +# disk_rate_limiter_ops_one_time_burst increases the initial max rate and this +# initial extra credit does *NOT* affect the overall limit and can be used for +# an *initial* burst of data. +# This is *optional* and only takes effect if disk_rate_limiter_bw_max_rate is +# set to a non zero value. +#disk_rate_limiter_ops_one_time_burst = 0 + +[agent.@PROJECT_TYPE@] +# If enabled, make the agent display debug-level messages. +# (default: disabled) +#enable_debug = true + +# Enable agent tracing. +# +# If enabled, the agent will generate OpenTelemetry trace spans. +# +# Notes: +# +# - If the runtime also has tracing enabled, the agent spans will be +# associated with the appropriate runtime parent span. +# - If enabled, the runtime will wait for the container to shutdown, +# increasing the container shutdown time slightly. +# +# (default: disabled) +#enable_tracing = true + +# Enable debug console. + +# If enabled, user can connect guest OS running inside hypervisor +# through "kata-runtime exec " command + +#debug_console_enabled = true + +# Agent connection dialing timeout value in seconds +# (default: 30) +#dial_timeout = 30 + +[runtime] +# If enabled, the runtime will log additional debug messages to the +# system log +# (default: disabled) +#enable_debug = true +# +# Internetworking model +# Determines how the VM should be connected to the +# the container network interface +# Options: +# +# - macvtap +# Used when the Container network interface can be bridged using +# macvtap. +# +# - none +# Used when customize network. Only creates a tap device. No veth pair. +# +# - tcfilter +# Uses tc filter rules to redirect traffic from the network interface +# provided by plugin to a tap interface connected to the VM. +# +internetworking_model="@DEFNETWORKMODEL_CLH@" + +# disable guest seccomp +# Determines whether container seccomp profiles are passed to the virtual +# machine and applied by the kata agent. If set to true, seccomp is not applied +# within the guest +# (default: true) +disable_guest_seccomp=@DEFDISABLEGUESTSECCOMP@ + +# If enabled, the runtime will create opentracing.io traces and spans. +# (See https://www.jaegertracing.io/docs/getting-started). +# (default: disabled) +#enable_tracing = true + +# Set the full url to the Jaeger HTTP Thrift collector. +# The default if not set will be "http://localhost:14268/api/traces" +#jaeger_endpoint = "" + +# Sets the username to be used if basic auth is required for Jaeger. +#jaeger_user = "" + +# Sets the password to be used if basic auth is required for Jaeger. +#jaeger_password = "" + +# If enabled, the runtime will not create a network namespace for shim and hypervisor processes. +# This option may have some potential impacts to your host. It should only be used when you know what you're doing. +# `disable_new_netns` conflicts with `internetworking_model=tcfilter` and `internetworking_model=macvtap`. It works only +# with `internetworking_model=none`. The tap device will be in the host network namespace and can connect to a bridge +# (like OVS) directly. +# (default: false) +#disable_new_netns = true + +# if enabled, the runtime will add all the kata processes inside one dedicated cgroup. +# The container cgroups in the host are not created, just one single cgroup per sandbox. +# The runtime caller is free to restrict or collect cgroup stats of the overall Kata sandbox. +# The sandbox cgroup path is the parent cgroup of a container with the PodSandbox annotation. +# The sandbox cgroup is constrained if there is no container type annotation. +# See: https://pkg.go.dev/github.com/kata-containers/kata-containers/src/runtime/virtcontainers#ContainerType +sandbox_cgroup_only=@DEFSANDBOXCGROUPONLY@ + +# If enabled, the runtime will attempt to determine appropriate sandbox size (memory, CPU) before booting the virtual machine. In +# this case, the runtime will not dynamically update the amount of memory and CPU in the virtual machine. This is generally helpful +# when a hardware architecture or hypervisor solutions is utilized which does not support CPU and/or memory hotplug. +# Compatibility for determining appropriate sandbox (VM) size: +# - When running with pods, sandbox sizing information will only be available if using Kubernetes >= 1.23 and containerd >= 1.6. CRI-O +# does not yet support sandbox sizing annotations. +# - When running single containers using a tool like ctr, container sizing information will be available. +static_sandbox_resource_mgmt=@DEFSTATICRESOURCEMGMT@ + +# If specified, sandbox_bind_mounts identifieds host paths to be mounted (ro) into the sandboxes shared path. +# This is only valid if filesystem sharing is utilized. The provided path(s) will be bindmounted into the shared fs directory. +# If defaults are utilized, these mounts should be available in the guest at `/run/kata-containers/shared/containers/sandbox-mounts` +# These will not be exposed to the container workloads, and are only provided for potential guest services. +sandbox_bind_mounts=@DEFBINDMOUNTS@ + +# VFIO Mode +# Determines how VFIO devices should be be presented to the container. +# Options: +# +# - vfio +# Matches behaviour of OCI runtimes (e.g. runc) as much as +# possible. VFIO devices will appear in the container as VFIO +# character devices under /dev/vfio. The exact names may differ +# from the host (they need to match the VM's IOMMU group numbers +# rather than the host's) +# +# - guest-kernel +# This is a Kata-specific behaviour that's useful in certain cases. +# The VFIO device is managed by whatever driver in the VM kernel +# claims it. This means it will appear as one or more device nodes +# or network interfaces depending on the nature of the device. +# Using this mode requires specially built workloads that know how +# to locate the relevant device interfaces within the VM. +# +vfio_mode="@DEFVFIOMODE@" + +# If enabled, the runtime will not create Kubernetes emptyDir mounts on the guest filesystem. Instead, emptyDir mounts will +# be created on the host and shared via virtio-fs. This is potentially slower, but allows sharing of files from host to guest. +disable_guest_empty_dir=@DEFDISABLEGUESTEMPTYDIR@ + +# Enabled experimental feature list, format: ["a", "b"]. +# Experimental features are features not stable enough for production, +# they may break compatibility, and are prepared for a big version bump. +# Supported experimental features: +# (default: []) +experimental=@DEFAULTEXPFEATURES@ + +# If enabled, user can run pprof tools with shim v2 process through kata-monitor. +# (default: false) +# enable_pprof = true + +# WARNING: All the options in the following section have not been implemented yet. +# This section was added as a placeholder. DO NOT USE IT! +[image] +# Container image service. +# +# Offload the CRI image management service to the Kata agent. +# (default: false) +service_offload = @DEFSERVICEOFFLOAD@ + +# Container image decryption keys provisioning. +# Applies only if service_offload is true. +# Keys can be provisioned locally (e.g. through a special command or +# a local file) or remotely (usually after the guest is remotely attested). +# The provision setting is a complete URL that lets the Kata agent decide +# which method to use in order to fetch the keys. +# +# Keys can be stored in a local file, in a measured and attested initrd: +#provision=data:///local/key/file +# +# Keys could be fetched through a special command or binary from the +# initrd (guest) image, e.g. a firmware call: +#provision=file:///path/to/bin/fetcher/in/guest +# +# Keys can be remotely provisioned. The Kata agent fetches them from e.g. +# a HTTPS URL: +#provision=https://my-key-broker.foo/tenant/ diff --git a/src/runtime/config/configuration-qemu-tdx-eaa-kbc.toml.in b/src/runtime/config/configuration-qemu-tdx-eaa-kbc.toml.in new file mode 100644 index 0000000000..79907f16be --- /dev/null +++ b/src/runtime/config/configuration-qemu-tdx-eaa-kbc.toml.in @@ -0,0 +1,636 @@ +# Copyright (c) 2017-2019 Intel Corporation +# Copyright (c) 2021 Adobe Inc. +# +# SPDX-License-Identifier: Apache-2.0 +# + +# XXX: WARNING: this file is auto-generated. +# XXX: +# XXX: Source file: "@CONFIG_QEMU_IN@" +# XXX: Project: +# XXX: Name: @PROJECT_NAME@ +# XXX: Type: @PROJECT_TYPE@ + +[hypervisor.qemu] +path = "@QEMUTDXPATH@" +kernel = "@KERNELTDXPATH@" +image = "@IMAGETDXPATH@" +machine_type = "@MACHINETYPE@" + +# Enable confidential guest support. +# Toggling that setting may trigger different hardware features, ranging +# from memory encryption to both memory and CPU-state encryption and integrity. +# The Kata Containers runtime dynamically detects the available feature set and +# aims at enabling the largest possible one, returning an error if none is +# available, or none is supported by the hypervisor. +# +# Known limitations: +# * Does not work by design: +# - CPU Hotplug +# - Memory Hotplug +# - NVDIMM devices +# +# Default false +confidential_guest = true + +# Enable running QEMU VMM as a non-root user. +# By default QEMU VMM run as root. When this is set to true, QEMU VMM process runs as +# a non-root random user. See documentation for the limitations of this mode. +# rootless = true + +# List of valid annotation names for the hypervisor +# Each member of the list is a regular expression, which is the base name +# of the annotation, e.g. "path" for io.katacontainers.config.hypervisor.path" +enable_annotations = @DEFENABLEANNOTATIONS@ + +# List of valid annotations values for the hypervisor +# Each member of the list is a path pattern as described by glob(3). +# The default if not set is empty (all annotations rejected.) +# Your distribution recommends: @QEMUVALIDHYPERVISORPATHS@ +valid_hypervisor_paths = @QEMUTDXVALIDHYPERVISORPATHS@ + +# Optional space-separated list of options to pass to the guest kernel. +# For example, use `kernel_params = "vsyscall=emulate"` if you are having +# trouble running pre-2.15 glibc. +# +# WARNING: - any parameter specified here will take priority over the default +# parameter value of the same name used to start the virtual machine. +# Do not set values here unless you understand the impact of doing so as you +# may stop the virtual machine from booting. +# To see the list of default parameters, enable hypervisor debug, create a +# container and look for 'default-kernel-parameters' log entries. +kernel_params = "@TDXKERNELPARAMS@" + +# Path to the firmware. +# If you want that qemu uses the default firmware leave this option empty +firmware = "@TDVFFIRMWAREPATH@" + +# Path to the firmware volume. +# firmware TDVF or OVMF can be split into FIRMWARE_VARS.fd (UEFI variables +# as configuration) and FIRMWARE_CODE.fd (UEFI program image). UEFI variables +# can be customized per each user while UEFI code is kept same. +firmware_volume = "@TDVFFIRMWAREVOLUMEPATH@" + +# Machine accelerators +# comma-separated list of machine accelerators to pass to the hypervisor. +# For example, `machine_accelerators = "nosmm,nosmbus,nosata,nopit,static-prt,nofw"` +machine_accelerators="@MACHINEACCELERATORS@" + +# Qemu seccomp sandbox feature +# comma-separated list of seccomp sandbox features to control the syscall access. +# For example, `seccompsandbox= "on,obsolete=deny,spawn=deny,resourcecontrol=deny"` +# Note: "elevateprivileges=deny" doesn't work with daemonize option, so it's removed from the seccomp sandbox +# Another note: enabling this feature may reduce performance, you may enable +# /proc/sys/net/core/bpf_jit_enable to reduce the impact. see https://man7.org/linux/man-pages/man8/bpfc.8.html +#seccompsandbox="@DEFSECCOMPSANDBOXPARAM@" + +# CPU features +# comma-separated list of cpu features to pass to the cpu +# For example, `cpu_features = "pmu=off,vmx=off" +cpu_features="@TDXCPUFEATURES@" + +# Default number of vCPUs per SB/VM: +# unspecified or 0 --> will be set to @DEFVCPUS@ +# < 0 --> will be set to the actual number of physical cores +# > 0 <= number of physical cores --> will be set to the specified number +# > number of physical cores --> will be set to the actual number of physical cores +default_vcpus = 1 + +# Default maximum number of vCPUs per SB/VM: +# unspecified or == 0 --> will be set to the actual number of physical cores or to the maximum number +# of vCPUs supported by KVM if that number is exceeded +# > 0 <= number of physical cores --> will be set to the specified number +# > number of physical cores --> will be set to the actual number of physical cores or to the maximum number +# of vCPUs supported by KVM if that number is exceeded +# WARNING: Depending of the architecture, the maximum number of vCPUs supported by KVM is used when +# the actual number of physical cores is greater than it. +# WARNING: Be aware that this value impacts the virtual machine's memory footprint and CPU +# the hotplug functionality. For example, `default_maxvcpus = 240` specifies that until 240 vCPUs +# can be added to a SB/VM, but the memory footprint will be big. Another example, with +# `default_maxvcpus = 8` the memory footprint will be small, but 8 will be the maximum number of +# vCPUs supported by the SB/VM. In general, we recommend that you do not edit this variable, +# unless you know what are you doing. +# NOTICE: on arm platform with gicv2 interrupt controller, set it to 8. +default_maxvcpus = @DEFMAXVCPUS@ + +# Bridges can be used to hot plug devices. +# Limitations: +# * Currently only pci bridges are supported +# * Until 30 devices per bridge can be hot plugged. +# * Until 5 PCI bridges can be cold plugged per VM. +# This limitation could be a bug in qemu or in the kernel +# Default number of bridges per SB/VM: +# unspecified or 0 --> will be set to @DEFBRIDGES@ +# > 1 <= 5 --> will be set to the specified number +# > 5 --> will be set to 5 +default_bridges = @DEFBRIDGES@ + +# Default memory size in MiB for SB/VM. +# If unspecified then it will be set @DEFMEMSZ@ MiB. +default_memory = @DEFMEMSZ@ +# +# Default memory slots per SB/VM. +# If unspecified then it will be set @DEFMEMSLOTS@. +# This is will determine the times that memory will be hotadded to sandbox/VM. +#memory_slots = @DEFMEMSLOTS@ + +# Default maximum memory in MiB per SB / VM +# unspecified or == 0 --> will be set to the actual amount of physical RAM +# > 0 <= amount of physical RAM --> will be set to the specified number +# > amount of physical RAM --> will be set to the actual amount of physical RAM +default_maxmemory = @DEFMAXMEMSZ@ + +# The size in MiB will be plused to max memory of hypervisor. +# It is the memory address space for the NVDIMM devie. +# If set block storage driver (block_device_driver) to "nvdimm", +# should set memory_offset to the size of block device. +# Default 0 +#memory_offset = 0 + +# Specifies virtio-mem will be enabled or not. +# Please note that this option should be used with the command +# "echo 1 > /proc/sys/vm/overcommit_memory". +# Default false +#enable_virtio_mem = true + +# Disable block device from being used for a container's rootfs. +# In case of a storage driver like devicemapper where a container's +# root file system is backed by a block device, the block device is passed +# directly to the hypervisor for performance reasons. +# This flag prevents the block device from being passed to the hypervisor, +# virtio-fs is used instead to pass the rootfs. +disable_block_device_use = @DEFDISABLEBLOCK@ + +# Shared file system type: +# - virtio-fs (default) +# - virtio-9p +# - virtio-fs-nydus +shared_fs = "@DEFSHAREDFS_QEMU_VIRTIOFS@" + +# Path to vhost-user-fs daemon. +virtio_fs_daemon = "@DEFVIRTIOFSDAEMON@" + +# List of valid annotations values for the virtiofs daemon +# The default if not set is empty (all annotations rejected.) +# Your distribution recommends: @DEFVALIDVIRTIOFSDAEMONPATHS@ +valid_virtio_fs_daemon_paths = @DEFVALIDVIRTIOFSDAEMONPATHS@ + +# Default size of DAX cache in MiB +virtio_fs_cache_size = @DEFVIRTIOFSCACHESIZE@ + +# Extra args for virtiofsd daemon +# +# Format example: +# ["-o", "arg1=xxx,arg2", "-o", "hello world", "--arg3=yyy"] +# Examples: +# Set virtiofsd log level to debug : ["-o", "log_level=debug"] or ["-d"] +# +# see `virtiofsd -h` for possible options. +virtio_fs_extra_args = @DEFVIRTIOFSEXTRAARGS@ + +# Cache mode: +# +# - none +# Metadata, data, and pathname lookup are not cached in guest. They are +# always fetched from host and any changes are immediately pushed to host. +# +# - auto +# Metadata and pathname lookup cache expires after a configured amount of +# time (default is 1 second). Data is cached while the file is open (close +# to open consistency). +# +# - always +# Metadata, data, and pathname lookup are cached in guest and never expire. +virtio_fs_cache = "@DEFVIRTIOFSCACHE@" + +# Block storage driver to be used for the hypervisor in case the container +# rootfs is backed by a block device. This is virtio-scsi, virtio-blk +# or nvdimm. +block_device_driver = "@DEFBLOCKSTORAGEDRIVER_QEMU@" + +# Specifies cache-related options will be set to block devices or not. +# Default false +#block_device_cache_set = true + +# Specifies cache-related options for block devices. +# Denotes whether use of O_DIRECT (bypass the host page cache) is enabled. +# Default false +#block_device_cache_direct = true + +# Specifies cache-related options for block devices. +# Denotes whether flush requests for the device are ignored. +# Default false +#block_device_cache_noflush = true + +# Enable iothreads (data-plane) to be used. This causes IO to be +# handled in a separate IO thread. This is currently only implemented +# for SCSI. +# +enable_iothreads = @DEFENABLEIOTHREADS@ + +# Enable pre allocation of VM RAM, default false +# Enabling this will result in lower container density +# as all of the memory will be allocated and locked +# This is useful when you want to reserve all the memory +# upfront or in the cases where you want memory latencies +# to be very predictable +# Default false +#enable_mem_prealloc = true + +# Enable huge pages for VM RAM, default false +# Enabling this will result in the VM memory +# being allocated using huge pages. +# This is useful when you want to use vhost-user network +# stacks within the container. This will automatically +# result in memory pre allocation +#enable_hugepages = true + +# Enable vhost-user storage device, default false +# Enabling this will result in some Linux reserved block type +# major range 240-254 being chosen to represent vhost-user devices. +enable_vhost_user_store = @DEFENABLEVHOSTUSERSTORE@ + +# The base directory specifically used for vhost-user devices. +# Its sub-path "block" is used for block devices; "block/sockets" is +# where we expect vhost-user sockets to live; "block/devices" is where +# simulated block device nodes for vhost-user devices to live. +vhost_user_store_path = "@DEFVHOSTUSERSTOREPATH@" + +# Enable vIOMMU, default false +# Enabling this will result in the VM having a vIOMMU device +# This will also add the following options to the kernel's +# command line: intel_iommu=on,iommu=pt +#enable_iommu = true + +# Enable IOMMU_PLATFORM, default false +# Enabling this will result in the VM device having iommu_platform=on set +#enable_iommu_platform = true + +# List of valid annotations values for the vhost user store path +# The default if not set is empty (all annotations rejected.) +# Your distribution recommends: @DEFVALIDVHOSTUSERSTOREPATHS@ +valid_vhost_user_store_paths = @DEFVALIDVHOSTUSERSTOREPATHS@ + +# Enable file based guest memory support. The default is an empty string which +# will disable this feature. In the case of virtio-fs, this is enabled +# automatically and '/dev/shm' is used as the backing folder. +# This option will be ignored if VM templating is enabled. +#file_mem_backend = "@DEFFILEMEMBACKEND@" + +# List of valid annotations values for the file_mem_backend annotation +# The default if not set is empty (all annotations rejected.) +# Your distribution recommends: @DEFVALIDFILEMEMBACKENDS@ +valid_file_mem_backends = @DEFVALIDFILEMEMBACKENDS@ + +# -pflash can add image file to VM. The arguments of it should be in format +# of ["/path/to/flash0.img", "/path/to/flash1.img"] +pflashes = [] + +# This option changes the default hypervisor and kernel parameters +# to enable debug output where available. +# +# Default false +#enable_debug = true + +# Disable the customizations done in the runtime when it detects +# that it is running on top a VMM. This will result in the runtime +# behaving as it would when running on bare metal. +# +#disable_nesting_checks = true + +# This is the msize used for 9p shares. It is the number of bytes +# used for 9p packet payload. +#msize_9p = @DEFMSIZE9P@ + +# If false and nvdimm is supported, use nvdimm device to plug guest image. +# Otherwise virtio-block device is used. +# +# nvdimm is not supported when `confidential_guest = true`. +# +# Default is false +#disable_image_nvdimm = true + +# VFIO devices are hotplugged on a bridge by default. +# Enable hotplugging on root bus. This may be required for devices with +# a large PCI bar, as this is a current limitation with hotplugging on +# a bridge. +# Default false +#hotplug_vfio_on_root_bus = true + +# Before hot plugging a PCIe device, you need to add a pcie_root_port device. +# Use this parameter when using some large PCI bar devices, such as Nvidia GPU +# The value means the number of pcie_root_port +# This value is valid when hotplug_vfio_on_root_bus is true and machine_type is "q35" +# Default 0 +#pcie_root_port = 2 + +# If vhost-net backend for virtio-net is not desired, set to true. Default is false, which trades off +# security (vhost-net runs ring0) for network I/O performance. +#disable_vhost_net = true + +# +# Default entropy source. +# The path to a host source of entropy (including a real hardware RNG) +# /dev/urandom and /dev/random are two main options. +# Be aware that /dev/random is a blocking source of entropy. If the host +# runs out of entropy, the VMs boot time will increase leading to get startup +# timeouts. +# The source of entropy /dev/urandom is non-blocking and provides a +# generally acceptable source of entropy. It should work well for pretty much +# all practical purposes. +#entropy_source= "@DEFENTROPYSOURCE@" + +# List of valid annotations values for entropy_source +# The default if not set is empty (all annotations rejected.) +# Your distribution recommends: @DEFVALIDENTROPYSOURCES@ +valid_entropy_sources = @DEFVALIDENTROPYSOURCES@ + +# Path to OCI hook binaries in the *guest rootfs*. +# This does not affect host-side hooks which must instead be added to +# the OCI spec passed to the runtime. +# +# You can create a rootfs with hooks by customizing the osbuilder scripts: +# https://github.com/kata-containers/kata-containers/tree/main/tools/osbuilder +# +# Hooks must be stored in a subdirectory of guest_hook_path according to their +# hook type, i.e. "guest_hook_path/{prestart,poststart,poststop}". +# The agent will scan these directories for executable files and add them, in +# lexicographical order, to the lifecycle of the guest container. +# Hooks are executed in the runtime namespace of the guest. See the official documentation: +# https://github.com/opencontainers/runtime-spec/blob/v1.0.1/config.md#posix-platform-hooks +# Warnings will be logged if any error is encountered while scanning for hooks, +# but it will not abort container execution. +#guest_hook_path = "/usr/share/oci/hooks" +# +# Use rx Rate Limiter to control network I/O inbound bandwidth(size in bits/sec for SB/VM). +# In Qemu, we use classful qdiscs HTB(Hierarchy Token Bucket) to discipline traffic. +# Default 0-sized value means unlimited rate. +#rx_rate_limiter_max_rate = 0 +# Use tx Rate Limiter to control network I/O outbound bandwidth(size in bits/sec for SB/VM). +# In Qemu, we use classful qdiscs HTB(Hierarchy Token Bucket) and ifb(Intermediate Functional Block) +# to discipline traffic. +# Default 0-sized value means unlimited rate. +#tx_rate_limiter_max_rate = 0 + +# Set where to save the guest memory dump file. +# If set, when GUEST_PANICKED event occurred, +# guest memeory will be dumped to host filesystem under guest_memory_dump_path, +# This directory will be created automatically if it does not exist. +# +# The dumped file(also called vmcore) can be processed with crash or gdb. +# +# WARNING: +# Dump guest’s memory can take very long depending on the amount of guest memory +# and use much disk space. +#guest_memory_dump_path="/var/crash/kata" + +# If enable paging. +# Basically, if you want to use "gdb" rather than "crash", +# or need the guest-virtual addresses in the ELF vmcore, +# then you should enable paging. +# +# See: https://www.qemu.org/docs/master/qemu-qmp-ref.html#Dump-guest-memory for details +#guest_memory_dump_paging=false + +# Enable swap in the guest. Default false. +# When enable_guest_swap is enabled, insert a raw file to the guest as the swap device +# if the swappiness of a container (set by annotation "io.katacontainers.container.resource.swappiness") +# is bigger than 0. +# The size of the swap device should be +# swap_in_bytes (set by annotation "io.katacontainers.container.resource.swap_in_bytes") - memory_limit_in_bytes. +# If swap_in_bytes is not set, the size should be memory_limit_in_bytes. +# If swap_in_bytes and memory_limit_in_bytes is not set, the size should +# be default_memory. +#enable_guest_swap = true + +# use legacy serial for guest console if available and implemented for architecture. Default false +#use_legacy_serial = true + +# disable applying SELinux on the VMM process (default false) +disable_selinux=@DEFDISABLESELINUX@ + +[factory] +# VM templating support. Once enabled, new VMs are created from template +# using vm cloning. They will share the same initial kernel, initramfs and +# agent memory by mapping it readonly. It helps speeding up new container +# creation and saves a lot of memory if there are many kata containers running +# on the same host. +# +# When disabled, new VMs are created from scratch. +# +# Note: Requires "initrd=" to be set ("image=" is not supported). +# +# Default false +#enable_template = true + +# Specifies the path of template. +# +# Default "/run/vc/vm/template" +#template_path = "/run/vc/vm/template" + +# The number of caches of VMCache: +# unspecified or == 0 --> VMCache is disabled +# > 0 --> will be set to the specified number +# +# VMCache is a function that creates VMs as caches before using it. +# It helps speed up new container creation. +# The function consists of a server and some clients communicating +# through Unix socket. The protocol is gRPC in protocols/cache/cache.proto. +# The VMCache server will create some VMs and cache them by factory cache. +# It will convert the VM to gRPC format and transport it when gets +# requestion from clients. +# Factory grpccache is the VMCache client. It will request gRPC format +# VM and convert it back to a VM. If VMCache function is enabled, +# kata-runtime will request VM from factory grpccache when it creates +# a new sandbox. +# +# Default 0 +#vm_cache_number = 0 + +# Specify the address of the Unix socket that is used by VMCache. +# +# Default /var/run/kata-containers/cache.sock +#vm_cache_endpoint = "/var/run/kata-containers/cache.sock" + +[agent.@PROJECT_TYPE@] +# If enabled, make the agent display debug-level messages. +# (default: disabled) +#enable_debug = true + +# Enable agent tracing. +# +# If enabled, the agent will generate OpenTelemetry trace spans. +# +# Notes: +# +# - If the runtime also has tracing enabled, the agent spans will be +# associated with the appropriate runtime parent span. +# - If enabled, the runtime will wait for the container to shutdown, +# increasing the container shutdown time slightly. +# +# (default: disabled) +#enable_tracing = true + +# Comma separated list of kernel modules and their parameters. +# These modules will be loaded in the guest kernel using modprobe(8). +# The following example can be used to load two kernel modules with parameters +# - kernel_modules=["e1000e InterruptThrottleRate=3000,3000,3000 EEE=1", "i915 enable_ppgtt=0"] +# The first word is considered as the module name and the rest as its parameters. +# Container will not be started when: +# * A kernel module is specified and the modprobe command is not installed in the guest +# or it fails loading the module. +# * The module is not available in the guest or it doesn't met the guest kernel +# requirements, like architecture and version. +# +kernel_modules=[] + +# Enable debug console. + +# If enabled, user can connect guest OS running inside hypervisor +# through "kata-runtime exec " command + +#debug_console_enabled = true + +# Agent connection dialing timeout value in seconds +# (default: 30) +#dial_timeout = 30 + +[runtime] +# If enabled, the runtime will log additional debug messages to the +# system log +# (default: disabled) +#enable_debug = true +# +# Internetworking model +# Determines how the VM should be connected to the +# the container network interface +# Options: +# +# - macvtap +# Used when the Container network interface can be bridged using +# macvtap. +# +# - none +# Used when customize network. Only creates a tap device. No veth pair. +# +# - tcfilter +# Uses tc filter rules to redirect traffic from the network interface +# provided by plugin to a tap interface connected to the VM. +# +internetworking_model="@DEFNETWORKMODEL_QEMU@" + +# disable guest seccomp +# Determines whether container seccomp profiles are passed to the virtual +# machine and applied by the kata agent. If set to true, seccomp is not applied +# within the guest +# (default: true) +disable_guest_seccomp=@DEFDISABLEGUESTSECCOMP@ + +# If enabled, the runtime will create opentracing.io traces and spans. +# (See https://www.jaegertracing.io/docs/getting-started). +# (default: disabled) +#enable_tracing = true + +# Set the full url to the Jaeger HTTP Thrift collector. +# The default if not set will be "http://localhost:14268/api/traces" +#jaeger_endpoint = "" + +# Sets the username to be used if basic auth is required for Jaeger. +#jaeger_user = "" + +# Sets the password to be used if basic auth is required for Jaeger. +#jaeger_password = "" + +# If enabled, the runtime will not create a network namespace for shim and hypervisor processes. +# This option may have some potential impacts to your host. It should only be used when you know what you're doing. +# `disable_new_netns` conflicts with `internetworking_model=tcfilter` and `internetworking_model=macvtap`. It works only +# with `internetworking_model=none`. The tap device will be in the host network namespace and can connect to a bridge +# (like OVS) directly. +# (default: false) +#disable_new_netns = true + +# if enabled, the runtime will add all the kata processes inside one dedicated cgroup. +# The container cgroups in the host are not created, just one single cgroup per sandbox. +# The runtime caller is free to restrict or collect cgroup stats of the overall Kata sandbox. +# The sandbox cgroup path is the parent cgroup of a container with the PodSandbox annotation. +# The sandbox cgroup is constrained if there is no container type annotation. +# See: https://pkg.go.dev/github.com/kata-containers/kata-containers/src/runtime/virtcontainers#ContainerType +sandbox_cgroup_only=@DEFSANDBOXCGROUPONLY@ + +# If enabled, the runtime will attempt to determine appropriate sandbox size (memory, CPU) before booting the virtual machine. In +# this case, the runtime will not dynamically update the amount of memory and CPU in the virtual machine. This is generally helpful +# when a hardware architecture or hypervisor solutions is utilized which does not support CPU and/or memory hotplug. +# Compatibility for determining appropriate sandbox (VM) size: +# - When running with pods, sandbox sizing information will only be available if using Kubernetes >= 1.23 and containerd >= 1.6. CRI-O +# does not yet support sandbox sizing annotations. +# - When running single containers using a tool like ctr, container sizing information will be available. +static_sandbox_resource_mgmt=@DEFSTATICRESOURCEMGMT@ + +# If specified, sandbox_bind_mounts identifieds host paths to be mounted (ro) into the sandboxes shared path. +# This is only valid if filesystem sharing is utilized. The provided path(s) will be bindmounted into the shared fs directory. +# If defaults are utilized, these mounts should be available in the guest at `/run/kata-containers/shared/containers/sandbox-mounts` +# These will not be exposed to the container workloads, and are only provided for potential guest services. +sandbox_bind_mounts=@DEFBINDMOUNTS@ + +# VFIO Mode +# Determines how VFIO devices should be be presented to the container. +# Options: +# +# - vfio +# Matches behaviour of OCI runtimes (e.g. runc) as much as +# possible. VFIO devices will appear in the container as VFIO +# character devices under /dev/vfio. The exact names may differ +# from the host (they need to match the VM's IOMMU group numbers +# rather than the host's) +# +# - guest-kernel +# This is a Kata-specific behaviour that's useful in certain cases. +# The VFIO device is managed by whatever driver in the VM kernel +# claims it. This means it will appear as one or more device nodes +# or network interfaces depending on the nature of the device. +# Using this mode requires specially built workloads that know how +# to locate the relevant device interfaces within the VM. +# +vfio_mode="@DEFVFIOMODE@" + +# If enabled, the runtime will not create Kubernetes emptyDir mounts on the guest filesystem. Instead, emptyDir mounts will +# be created on the host and shared via virtio-fs. This is potentially slower, but allows sharing of files from host to guest. +disable_guest_empty_dir=@DEFDISABLEGUESTEMPTYDIR@ + +# Enabled experimental feature list, format: ["a", "b"]. +# Experimental features are features not stable enough for production, +# they may break compatibility, and are prepared for a big version bump. +# Supported experimental features: +# (default: []) +experimental=@DEFAULTEXPFEATURES@ + +# If enabled, user can run pprof tools with shim v2 process through kata-monitor. +# (default: false) +# enable_pprof = true + +# WARNING: All the options in the following section have not been implemented yet. +# This section was added as a placeholder. DO NOT USE IT! +[image] +# Container image service. +# +# Offload the CRI image management service to the Kata agent. +# (default: false) +service_offload = @DEFSERVICEOFFLOAD@ + +# Container image decryption keys provisioning. +# Applies only if service_offload is true. +# Keys can be provisioned locally (e.g. through a special command or +# a local file) or remotely (usually after the guest is remotely attested). +# The provision setting is a complete URL that lets the Kata agent decide +# which method to use in order to fetch the keys. +# +# Keys can be stored in a local file, in a measured and attested initrd: +#provision=data:///local/key/file +# +# Keys could be fetched through a special command or binary from the +# initrd (guest) image, e.g. a firmware call: +#provision=file:///path/to/bin/fetcher/in/guest +# +# Keys can be remotely provisioned. The Kata agent fetches them from e.g. +# a HTTPS URL: +#provision=https://my-key-broker.foo/tenant/ diff --git a/tools/packaging/kata-deploy-cc/scripts/kata-deploy.sh b/tools/packaging/kata-deploy-cc/scripts/kata-deploy.sh index 977004dc68..3532f6ffed 100755 --- a/tools/packaging/kata-deploy-cc/scripts/kata-deploy.sh +++ b/tools/packaging/kata-deploy-cc/scripts/kata-deploy.sh @@ -14,9 +14,11 @@ containerd_conf_file_backup="${containerd_conf_file}.bak" shims=( "qemu" "qemu-tdx" + "qemu-tdx-eaa-kbc" "qemu-sev" "clh" "clh-tdx" + "clh-tdx-eaa-kbc" ) default_shim="qemu" From 1f799d6a29b1a0e9142a83f7e90cad0fe6b56fbe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Fabiano=20Fid=C3=AAncio?= Date: Thu, 3 Nov 2022 10:37:47 +0100 Subject: [PATCH 7/7] config: Add AGENT_AA_KBC_PARAMS to the kernel config MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Let's ensure we add the option for the user, at build time, to set the AGENT_AA_KBC_PARAMS passed to the agent, via the kernel command line. Signed-off-by: Fabiano Fidêncio --- src/runtime/Makefile | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/src/runtime/Makefile b/src/runtime/Makefile index b0784f6119..c7e1cd6d12 100644 --- a/src/runtime/Makefile +++ b/src/runtime/Makefile @@ -128,9 +128,12 @@ AGENTCONFIGFILEPATH := /etc/agent-config.toml AGENTCONFIGFILEKERNELPARAM := agent.config_file=$(AGENTCONFIGFILEPATH) ROOTMEASURECONFIG ?= "" -TDXKERNELPARAMS := tdx_disable_filter $(ROOTMEASURECONFIG) agent.enable_signature_verification=false -SEVKERNELPARAMS := $(AGENTCONFIGFILEKERNELPARAM) $(ROOTMEASURECONFIG) agent.enable_signature_verification=false -KERNELPARAMS += $(ROOTMEASURECONFIG) agent.enable_signature_verification=false +AGENT_AA_KBC_PARAMS ?= "" +AGENT_AA_KBC_PARAMS_TDX ?= "" +AGENT_AA_KBC_PARAMS_SEV ?= "" +TDXKERNELPARAMS := tdx_disable_filter $(ROOTMEASURECONFIG) agent.enable_signature_verification=false $(AGENT_AA_KBC_PARAMS_TDX) +SEVKERNELPARAMS := $(AGENTCONFIGFILEKERNELPARAM) $(ROOTMEASURECONFIG) agent.enable_signature_verification=false $(AGENT_AA_KBC_PARAMS_SEV) +KERNELPARAMS += $(ROOTMEASURECONFIG) agent.enable_signature_verification=false $(AGENT_AA_KBC_PARAMS) # Name of default configuration file the runtime will use. CONFIG_FILE = configuration.toml