From 38ce4a32af80a493b1570cbe7f4341ce80bf0401 Mon Sep 17 00:00:00 2001 From: Tobin Feldman-Fitzthum Date: Fri, 21 Apr 2023 15:41:39 +0000 Subject: [PATCH 01/13] local-build: add support to build QEMU for SEV-SNP Add Make targets and helper functions to build the QEMU needed for SEV-SNP. Signed-off-by: Tobin Feldman-Fitzthum Signed-off-by: Alex Carter --- tools/packaging/kata-deploy/local-build/Makefile | 4 ++++ .../local-build/kata-deploy-binaries.sh | 15 +++++++++++++++ 2 files changed, 19 insertions(+) diff --git a/tools/packaging/kata-deploy/local-build/Makefile b/tools/packaging/kata-deploy/local-build/Makefile index 91d76dab0b..a7c3234448 100644 --- a/tools/packaging/kata-deploy/local-build/Makefile +++ b/tools/packaging/kata-deploy/local-build/Makefile @@ -31,6 +31,7 @@ all: serial-targets \ kernel-gpu-tdx-experimental-tarball \ nydus-tarball \ ovmf-sev-tarball \ + qemu-snp-experimental-tarball \ qemu-tarball \ qemu-tdx-experimental-tarball \ shim-v2-tarball \ @@ -83,6 +84,9 @@ nydus-tarball: ovmf-sev-tarball: ${MAKE} $@-build +qemu-snp-experimental-tarball: + ${MAKE} $@-build + qemu-tarball: ${MAKE} $@-build diff --git a/tools/packaging/kata-deploy/local-build/kata-deploy-binaries.sh b/tools/packaging/kata-deploy/local-build/kata-deploy-binaries.sh index 81784379a9..cf2953c7fb 100755 --- a/tools/packaging/kata-deploy/local-build/kata-deploy-binaries.sh +++ b/tools/packaging/kata-deploy/local-build/kata-deploy-binaries.sh @@ -89,6 +89,7 @@ options: nydus ovmf-sev qemu + qemu-snp-experimental qemu-tdx-experimental rootfs-image rootfs-initrd @@ -362,6 +363,17 @@ install_qemu_tdx_experimental() { "${qemu_experimental_builder}" } +install_qemu_snp_experimental() { + export qemu_suffix="snp-experimental" + export qemu_tarball_name="kata-static-qemu-${qemu_suffix}.tar.gz" + + install_qemu_helper \ + "assets.hypervisor.qemu-${qemu_suffix}.url" \ + "assets.hypervisor.qemu-${qemu_suffix}.tag" \ + "qemu-${qemu_suffix}" \ + "${qemu_experimental_builder}" +} + # Install static firecracker asset install_firecracker() { install_cached_tarball_component \ @@ -522,6 +534,7 @@ handle_build() { install_nydus install_ovmf_sev install_qemu + install_qemu_snp_experimental install_qemu_tdx_experimental install_shimv2 install_tdvf @@ -554,6 +567,8 @@ handle_build() { qemu) install_qemu ;; + qemu-snp-experimental) install_qemu_snp_experimental ;; + qemu-tdx-experimental) install_qemu_tdx_experimental ;; rootfs-image) install_image ;; From 879333bfc78a5231224a17a940accc70f0259c0e Mon Sep 17 00:00:00 2001 From: Tobin Feldman-Fitzthum Date: Fri, 21 Apr 2023 15:50:59 +0000 Subject: [PATCH 02/13] versions: update SNP QEMU version Refactor SNP QEMU entry in versions.yaml to match qemu-experimental and qemu-tdx-experimental. Also, update the version of QEMU to what we are using in CCv0. This is the non-UPM QEMU and it does not have kernel hashes support. Signed-off-by: Tobin Feldman-Fitzthum Signed-off-by: Alex Carter --- .../no_patches.txt | 0 versions.yaml | 10 +++++----- 2 files changed, 5 insertions(+), 5 deletions(-) create mode 100644 tools/packaging/qemu/patches/tag_patches/3b6a2b6b7466f6dea53243900b7516c3f29027b7/no_patches.txt diff --git a/tools/packaging/qemu/patches/tag_patches/3b6a2b6b7466f6dea53243900b7516c3f29027b7/no_patches.txt b/tools/packaging/qemu/patches/tag_patches/3b6a2b6b7466f6dea53243900b7516c3f29027b7/no_patches.txt new file mode 100644 index 0000000000..e69de29bb2 diff --git a/versions.yaml b/versions.yaml index 4f6e81e4b2..a61d893510 100644 --- a/versions.yaml +++ b/versions.yaml @@ -98,11 +98,6 @@ assets: uscan-url: >- https://github.com/qemu/qemu/tags .*/v?(\d\S+)\.tar\.gz - snp: - description: "VMM that uses KVM and supports AMD SEV-SNP" - url: "https://github.com/AMDESE/qemu" - branch: "snp-v3" - commit: "ffa95097ee" qemu-experimental: description: "QEMU with virtiofs support" @@ -115,6 +110,11 @@ assets: url: "https://github.com/kata-containers/qemu" tag: "ad4c7f529a279685da84297773b4ec8080153c2d-plus-TDX-v1.3" + qemu-snp-experimental: + description: "QEMU with experimental SNP support (no UPM)" + url: "https://github.com/AMDESE/qemu" + tag: "3b6a2b6b7466f6dea53243900b7516c3f29027b7" + image: description: | Root filesystem disk image used to boot the guest virtual From 7a58a91fa6d64b8a4324061f56d7733dd6c7e242 Mon Sep 17 00:00:00 2001 From: Tobin Feldman-Fitzthum Date: Fri, 21 Apr 2023 15:58:12 +0000 Subject: [PATCH 03/13] docs: update SNP guide Since we reshuffled versions.yaml, update the guide so that we can find the SNP QEMU info. Once runtime support is merged we should overhaul or remove this guide, but let's keep it for now. Signed-off-by: Tobin Feldman-Fitzthum --- docs/how-to/how-to-run-kata-containers-with-SNP-VMs.md | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/docs/how-to/how-to-run-kata-containers-with-SNP-VMs.md b/docs/how-to/how-to-run-kata-containers-with-SNP-VMs.md index a87c9be62b..3a56cbba27 100644 --- a/docs/how-to/how-to-run-kata-containers-with-SNP-VMs.md +++ b/docs/how-to/how-to-run-kata-containers-with-SNP-VMs.md @@ -44,12 +44,11 @@ $ popd - Build a custom QEMU ```bash $ source kata-containers/tools/packaging/scripts/lib.sh -$ qemu_url="$(get_from_kata_deps "assets.hypervisor.qemu.snp.url")" -$ qemu_branch="$(get_from_kata_deps "assets.hypervisor.qemu.snp.branch")" -$ qemu_commit="$(get_from_kata_deps "assets.hypervisor.qemu.snp.commit")" -$ git clone -b "${qemu_branch}" "${qemu_url}" +$ qemu_url="$(get_from_kata_deps "assets.hypervisor.qemu-snp-experimental.url")" +$ qemu_tag="$(get_from_kata_deps "assets.hypervisor.qemu-snp-experimental.tag")" +$ git clone "${qemu_url}" $ pushd qemu -$ git checkout "${qemu_commit}" +$ git checkout "${qemu_tag}" $ ./configure --enable-virtfs --target-list=x86_64-softmmu --enable-debug $ make -j "$(nproc)" $ popd From f4ee00576a8647dbad18174daad55070338a7afb Mon Sep 17 00:00:00 2001 From: Tobin Feldman-Fitzthum Date: Fri, 21 Apr 2023 16:32:21 +0000 Subject: [PATCH 04/13] gha: Build and ship QEMU for SNP Now that we can build SNP QEMU, let's do that for tests and release. Signed-off-by: Tobin Feldman-Fitzthum --- .github/workflows/build-kata-static-tarball-amd64.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/build-kata-static-tarball-amd64.yaml b/.github/workflows/build-kata-static-tarball-amd64.yaml index b49f4ca5c1..c2b9617309 100644 --- a/.github/workflows/build-kata-static-tarball-amd64.yaml +++ b/.github/workflows/build-kata-static-tarball-amd64.yaml @@ -28,6 +28,7 @@ jobs: - nydus - ovmf-sev - qemu + - qemu-snp-experimental - qemu-tdx-experimental - rootfs-image - rootfs-initrd From db095ddeb4b7a363cc18de9f1faf339d2db75341 Mon Sep 17 00:00:00 2001 From: Tobin Feldman-Fitzthum Date: Fri, 21 Apr 2023 16:37:05 +0000 Subject: [PATCH 05/13] cache: add SNP flavor to comments Update comments to include new SNP QEMU option Signed-off-by: Tobin Feldman-Fitzthum --- tools/packaging/static-build/cache_components_main.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/packaging/static-build/cache_components_main.sh b/tools/packaging/static-build/cache_components_main.sh index 1c46c1e01f..28e6bfacf0 100755 --- a/tools/packaging/static-build/cache_components_main.sh +++ b/tools/packaging/static-build/cache_components_main.sh @@ -14,7 +14,7 @@ source "${script_dir}/../scripts/lib.sh" KERNEL_FLAVOUR="${KERNEL_FLAVOUR:-kernel}" # kernel | kernel-experimental | kernel-arm-experimental | kernel-dragonball-experimental | kernel-tdx-experimental OVMF_FLAVOUR="${OVMF_FLAVOUR:-x86_64}" # x86_64 | tdx -QEMU_FLAVOUR="${QEMU_FLAVOUR:-qemu}" # qemu | qemu-tdx-experimental +QEMU_FLAVOUR="${QEMU_FLAVOUR:-qemu}" # qemu | qemu-tdx-experimental | qemu-snp-experimental ROOTFS_IMAGE_TYPE="${ROOTFS_IMAGE_TYPE:-image}" # image | initrd cache_clh_artifacts() { @@ -134,7 +134,7 @@ Usage: $0 "[options]" The default KERNEL_FLAVOUR value is "kernel" -n Nydus cache -q QEMU cache - * Export QEMU_FLAVOUR="qemu | qemu-tdx-experimental" for a specific build + * Export QEMU_FLAVOUR="qemu | qemu-tdx-experimental | qemu-snp-experimental" for a specific build The default QEMU_FLAVOUR value is "qemu" -r RootFS cache * Export ROOTFS_IMAGE_TYPE="image|initrd" for one of those two types From cf0ca265f993537d485cb6e381cf5b12b87309dd Mon Sep 17 00:00:00 2001 From: Tobin Feldman-Fitzthum Date: Fri, 21 Apr 2023 18:36:09 +0000 Subject: [PATCH 06/13] local-build: Add x86_64 OVMF target Add targets to build the "plain" x86_64 OVMF. This will be used by anyone who is using SEV or SNP without kernel hashes. The SNP QEMU does not yet support kernel hashes so the OvmfPkg will be used by default. Signed-off-by: Tobin Feldman-Fitzthum Signed-off-by: Alex Carter --- tools/packaging/kata-deploy/local-build/Makefile | 4 ++++ .../kata-deploy/local-build/kata-deploy-binaries.sh | 12 ++++++++---- 2 files changed, 12 insertions(+), 4 deletions(-) diff --git a/tools/packaging/kata-deploy/local-build/Makefile b/tools/packaging/kata-deploy/local-build/Makefile index a7c3234448..fc3bbcb6e5 100644 --- a/tools/packaging/kata-deploy/local-build/Makefile +++ b/tools/packaging/kata-deploy/local-build/Makefile @@ -31,6 +31,7 @@ all: serial-targets \ kernel-gpu-tdx-experimental-tarball \ nydus-tarball \ ovmf-sev-tarball \ + ovmf-tarball \ qemu-snp-experimental-tarball \ qemu-tarball \ qemu-tdx-experimental-tarball \ @@ -84,6 +85,9 @@ nydus-tarball: ovmf-sev-tarball: ${MAKE} $@-build +ovmf-tarball: + ${MAKE} $@-build + qemu-snp-experimental-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 cf2953c7fb..7b80d000ef 100755 --- a/tools/packaging/kata-deploy/local-build/kata-deploy-binaries.sh +++ b/tools/packaging/kata-deploy/local-build/kata-deploy-binaries.sh @@ -87,6 +87,7 @@ options: kernel-gpu-snp kernel-gpu-tdx-experimental nydus + ovmf ovmf-sev qemu qemu-snp-experimental @@ -532,6 +533,7 @@ handle_build() { install_kernel_dragonball_experimental install_kernel_tdx_experimental install_nydus + install_ovmf install_ovmf_sev install_qemu install_qemu_snp_experimental @@ -547,8 +549,6 @@ handle_build() { kernel) install_kernel ;; - nydus) install_nydus ;; - kernel-dragonball-experimental) install_kernel_dragonball_experimental ;; kernel-experimental) install_kernel_experimental ;; @@ -557,14 +557,18 @@ handle_build() { kernel-sev) install_kernel_sev ;; - ovmf-sev) install_ovmf_sev ;; - kernel-gpu) install_kernel_gpu ;; kernel-gpu-snp) install_kernel_gpu_snp;; kernel-gpu-tdx-experimental) install_kernel_gpu_tdx_experimental;; + nydus) install_nydus ;; + + ovmf) install_ovmf ;; + + ovmf-sev) install_ovmf_sev ;; + qemu) install_qemu ;; qemu-snp-experimental) install_qemu_snp_experimental ;; From b8bbe6325fca03101049cb8ccc31a7580c7a13ac Mon Sep 17 00:00:00 2001 From: Tobin Feldman-Fitzthum Date: Fri, 21 Apr 2023 19:05:18 +0000 Subject: [PATCH 07/13] gha: build OVMF for tests and release The x86_64 package of OVMF is required for deployments that don't use kernel hashes, which includes SEV-SNP in the short term. We should keep this in the bundle in the long term in case someone wants to disable kernel hashes. Signed-off-by: Tobin Feldman-Fitzthum --- .github/workflows/build-kata-static-tarball-amd64.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/build-kata-static-tarball-amd64.yaml b/.github/workflows/build-kata-static-tarball-amd64.yaml index c2b9617309..d582f340b1 100644 --- a/.github/workflows/build-kata-static-tarball-amd64.yaml +++ b/.github/workflows/build-kata-static-tarball-amd64.yaml @@ -26,6 +26,7 @@ jobs: - kernel-gpu-snp - kernel-gpu-tdx-experimental - nydus + - ovmf - ovmf-sev - qemu - qemu-snp-experimental From dbcc3b5cc8770db187a3824dbc0ff576171fc5b9 Mon Sep 17 00:00:00 2001 From: Tobin Feldman-Fitzthum Date: Fri, 21 Apr 2023 19:38:44 +0000 Subject: [PATCH 08/13] local-build: fix default values for OVMF build Existing value has wrong name and compression type leading to installation failure. Signed-off-by: Tobin Feldman-Fitzthum --- tools/packaging/kata-deploy/local-build/kata-deploy-binaries.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 7b80d000ef..101f32cd04 100755 --- a/tools/packaging/kata-deploy/local-build/kata-deploy-binaries.sh +++ b/tools/packaging/kata-deploy/local-build/kata-deploy-binaries.sh @@ -479,7 +479,7 @@ install_shimv2() { install_ovmf() { ovmf_type="${1:-x86_64}" - tarball_name="${2:-edk2.tar.xz}" + tarball_name="${2:-edk2-x86_64.tar.gz}" local component_name="ovmf" local component_version="$(get_from_kata_deps "externals.ovmf.${ovmf_type}.version")" From af7f2519bf5cf9b8dadce8a0e30863220ebac84f Mon Sep 17 00:00:00 2001 From: Tobin Feldman-Fitzthum Date: Fri, 21 Apr 2023 20:28:40 +0000 Subject: [PATCH 09/13] versions: update SEV kernel description SNP and SEV will share a (guest) kernel. Update the description in versions.yaml to mention this. Signed-off-by: Tobin Feldman-Fitzthum --- versions.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/versions.yaml b/versions.yaml index a61d893510..e2a32b7f4c 100644 --- a/versions.yaml +++ b/versions.yaml @@ -165,7 +165,7 @@ assets: url: "https://cdn.kernel.org/pub/linux/kernel/v5.x/" version: "v5.19.2" sev: - description: "Linux kernel that supports SEV" + description: "Linux kernel that supports SEV and SNP" url: "https://cdn.kernel.org/pub/linux/kernel/v5.x/" version: "v5.19.2" snp: From 0bb37bff78a4707f3c84815423be315ca3226794 Mon Sep 17 00:00:00 2001 From: Tobin Feldman-Fitzthum Date: Mon, 24 Apr 2023 21:38:27 +0000 Subject: [PATCH 10/13] config: Add SNP configuration SNP requires many specific configurations, so let's make a new SNP configuration file that we can use with the kata-qemu-snp runtime class. Signed-off-by: Tobin Feldman-Fitzthum Signed-off-by: Alex Carter --- src/runtime/Makefile | 34 + src/runtime/arch/amd64-options.mk | 1 + .../config/configuration-qemu-snp.toml.in | 690 ++++++++++++++++++ 3 files changed, 725 insertions(+) create mode 100644 src/runtime/config/configuration-qemu-snp.toml.in diff --git a/src/runtime/Makefile b/src/runtime/Makefile index ee3896c771..776da3ef49 100644 --- a/src/runtime/Makefile +++ b/src/runtime/Makefile @@ -98,6 +98,7 @@ GENERATED_VARS = \ CONFIG_QEMU_IN \ CONFIG_QEMU_SEV_IN \ CONFIG_QEMU_TDX_IN \ + CONFIG_QEMU_SNP_IN \ CONFIG_QEMU_GPU_IN \ CONFIG_CLH_IN \ CONFIG_FC_IN \ @@ -130,6 +131,7 @@ FIRMWARETDVFPATH := $(PREFIXDEPS)/share/tdvf/OVMF.fd FIRMWARETDVFVOLUMEPATH := FIRMWARESEVPATH := $(PREFIXDEPS)/share/ovmf/AMDSEV.fd +FIRMWARESNPPATH := $(PREFIXDEPS)/share/ovmf/OVMF.fd # Name of default configuration file the runtime will use. CONFIG_FILE = configuration.toml @@ -151,6 +153,9 @@ QEMUVALIDHYPERVISORPATHS := [\"$(QEMUPATH)\"] QEMUTDXPATH := $(QEMUBINDIR)/$(QEMUTDXCMD) QEMUTDXVALIDHYPERVISORPATHS := [\"$(QEMUTDXPATH)\"] +QEMUSNPPATH := $(QEMUBINDIR)/$(QEMUSNPCMD) +QEMUSNPVALIDHYPERVISORPATHS := [\"$(QEMUSNPPATH)\"] + QEMUVIRTIOFSPATH := $(QEMUBINDIR)/$(QEMUVIRTIOFSCMD) CLHPATH := $(CLHBINDIR)/$(CLHCMD) @@ -210,6 +215,7 @@ DEFSHAREDFS_CLH_VIRTIOFS := virtio-fs DEFSHAREDFS_QEMU_VIRTIOFS := virtio-fs DEFSHAREDFS_QEMU_TDX_VIRTIOFS := virtio-9p DEFSHAREDFS_QEMU_SEV_VIRTIOFS := virtio-9p +DEFSHAREDFS_QEMU_SNP_VIRTIOFS := virtio-9p DEFVIRTIOFSDAEMON := $(LIBEXECDIR)/virtiofsd ifeq ($(ARCH),ppc64le) DEFVIRTIOFSDAEMON := $(LIBEXECDIR)/qemu/virtiofsd @@ -307,6 +313,18 @@ ifneq (,$(QEMUCMD)) CONFIGS += $(CONFIG_QEMU_SEV) + CONFIG_FILE_QEMU_SNP = configuration-qemu-snp.toml + CONFIG_QEMU_SNP = config/$(CONFIG_FILE_QEMU_SNP) + CONFIG_QEMU_SNP_IN = $(CONFIG_QEMU_SNP).in + + CONFIG_PATH_QEMU_SNP = $(abspath $(CONFDIR)/$(CONFIG_FILE_QEMU_SNP)) + CONFIG_PATHS += $(CONFIG_PATH_QEMU_SNP) + + SYSCONFIG_QEMU_SNP = $(abspath $(SYSCONFDIR)/$(CONFIG_FILE_QEMU_SNP)) + SYSCONFIG_PATHS_SNP += $(SYSCONFIG_QEMU_SNP) + + CONFIGS += $(CONFIG_QEMU_SNP) + CONFIG_FILE_QEMU_GPU = configuration-qemu-gpu.toml CONFIG_QEMU_GPU = config/$(CONFIG_FILE_QEMU_GPU) CONFIG_QEMU_GPU_IN = $(CONFIG_QEMU_GPU).in @@ -329,6 +347,11 @@ ifneq (,$(QEMUCMD)) KERNELTDXTYPE = compressed KERNELTDXNAME = $(call MAKE_KERNEL_TDX_NAME,$(KERNELTDXTYPE)) KERNELTDXPATH = $(KERNELDIR)/$(KERNELTDXNAME) + + KERNELSNPTYPE = compressed + KERNELSNPNAME = $(call MAKE_KERNEL_SNP_NAME,$(KERNELSNPTYPE)) + KERNELSNPPATH = $(KERNELDIR)/$(KERNELSNPNAME) + endif ifneq (,$(CLHCMD)) @@ -488,6 +511,7 @@ USER_VARS += KERNELPATH_ACRN USER_VARS += KERNELPATH USER_VARS += KERNELSEVPATH USER_VARS += KERNELTDXPATH +USER_VARS += KERNELSNPPATH USER_VARS += KERNELPATH_CLH USER_VARS += KERNELPATH_FC USER_VARS += KERNELVIRTIOFSPATH @@ -496,6 +520,7 @@ USER_VARS += FIRMWARESEVPATH USER_VARS += FIRMWARETDVFPATH USER_VARS += FIRMWAREVOLUMEPATH USER_VARS += FIRMWARETDVFVOLUMEPATH +USER_VARS += FIRMWARESNPPATH USER_VARS += MACHINEACCELERATORS USER_VARS += CPUFEATURES USER_VARS += TDXCPUFEATURES @@ -518,10 +543,13 @@ USER_VARS += PROJECT_URL USER_VARS += QEMUBINDIR USER_VARS += QEMUCMD USER_VARS += QEMUTDXCMD +USER_VARS += QEMUSNPCMD USER_VARS += QEMUPATH USER_VARS += QEMUTDXPATH +USER_VARS += QEMUSNPPATH USER_VARS += QEMUVALIDHYPERVISORPATHS USER_VARS += QEMUTDXVALIDHYPERVISORPATHS +USER_VARS += QEMUSNPVALIDHYPERVISORPATHS USER_VARS += QEMUVIRTIOFSCMD USER_VARS += QEMUVIRTIOFSPATH USER_VARS += RUNTIME_NAME @@ -553,6 +581,7 @@ USER_VARS += DEFSHAREDFS_CLH_VIRTIOFS USER_VARS += DEFSHAREDFS_QEMU_VIRTIOFS USER_VARS += DEFSHAREDFS_QEMU_TDX_VIRTIOFS USER_VARS += DEFSHAREDFS_QEMU_SEV_VIRTIOFS +USER_VARS += DEFSHAREDFS_QEMU_SNP_VIRTIOFS USER_VARS += DEFVIRTIOFSDAEMON USER_VARS += DEFVALIDVIRTIOFSDAEMONPATHS USER_VARS += DEFVIRTIOFSCACHESIZE @@ -667,6 +696,11 @@ define MAKE_KERNEL_TDX_NAME $(if $(findstring uncompressed,$1),vmlinux-tdx.container,vmlinuz-tdx.container) endef +# SNP configuration uses the SEV kernel +define MAKE_KERNEL_SNP_NAME +$(if $(findstring uncompressed,$1),vmlinux-sev.container,vmlinuz-sev.container) +endef + GENERATED_FILES += pkg/katautils/config-settings.go $(RUNTIME_OUTPUT): $(SOURCES) $(GENERATED_FILES) $(MAKEFILE_LIST) | show-summary diff --git a/src/runtime/arch/amd64-options.mk b/src/runtime/arch/amd64-options.mk index ab82539ba1..ab2b1d2d2c 100644 --- a/src/runtime/arch/amd64-options.mk +++ b/src/runtime/arch/amd64-options.mk @@ -12,6 +12,7 @@ CPUFEATURES := pmu=off QEMUCMD := qemu-system-x86_64 QEMUTDXCMD := qemu-system-x86_64-tdx-experimental +QEMUSNPCMD := qemu-system-x86_64-snp-experimental TDXCPUFEATURES := -vmx-rdseed-exit,pmu=off # Firecracker binary name diff --git a/src/runtime/config/configuration-qemu-snp.toml.in b/src/runtime/config/configuration-qemu-snp.toml.in new file mode 100644 index 0000000000..e09f149917 --- /dev/null +++ b/src/runtime/config/configuration-qemu-snp.toml.in @@ -0,0 +1,690 @@ +# Copyright (c) 2017-2019 Intel Corporation +# Copyright (c) 2021 Adobe Inc. +# Copyright (c) 2023 IBM Inc. +# +# SPDX-License-Identifier: Apache-2.0 +# + +# XXX: WARNING: this file is auto-generated. +# XXX: +# XXX: Source file: "@CONFIG_QEMU_SNP_IN@" +# XXX: Project: +# XXX: Name: @PROJECT_NAME@ +# XXX: Type: @PROJECT_TYPE@ + +[hypervisor.qemu] +path = "@QEMUSNPPATH@" +kernel = "@KERNELSNPPATH@" +#image = "@IMAGEPATH@" +initrd = "@INITRDPATH@" +machine_type = "@MACHINETYPE@" + +# rootfs filesystem type: +# - ext4 (default) +# - xfs +# - erofs +rootfs_type=@DEFROOTFSTYPE@ + +# 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 SEV SNP VMs +sev_snp_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 = @QEMUSNPVALIDHYPERVISORPATHS@ + +# 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 = "@KERNELPARAMS@" + +# Path to the firmware. +# If you want that qemu uses the default firmware leave this option empty +firmware = "@FIRMWARESNPPATH@" + +# 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 = "@FIRMWARETDVFVOLUMEPATH@" + +# 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="@CPUFEATURES@" + +# 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_SNP_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@ + +# Default size of virtqueues +virtio_fs_queue_size = @DEFVIRTIOFSQUEUESIZE@ + +# 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: +# +# - never +# 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@" + +# aio is the I/O mechanism used by qemu +# Options: +# +# - threads +# Pthread based disk I/O. +# +# - native +# Native Linux I/O. +# +# - io_uring +# Linux io_uring API. This provides the fastest I/O operations on Linux, requires kernel>5.1 and +# qemu >=5.0. +block_device_aio = "@DEFBLOCKDEVICEAIO_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@ + +# The timeout for reconnecting on non-server spdk sockets when the remote end goes away. +# qemu will delay this many seconds and then attempt to reconnect. +# Zero disables reconnecting, and the default is zero. +vhost_user_reconnect_timeout_sec = 0 + +# 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 = "" + +# 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. And Debug also enable the hmp socket. +# +# 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@ + +# disable applying SELinux on the container process +# If set to false, the type `container_t` is applied to the container process by default. +# Note: To enable guest SELinux, the guest rootfs must be CentOS that is created and built +# with `SELINUX=yes`. +# (default: true) +disable_guest_selinux=@DEFDISABLEGUESTSELINUX@ + + +[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: 90) +dial_timeout = 90 + +[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@ + +# vCPUs pinning settings +# if enabled, each vCPU thread will be scheduled to a fixed CPU +# qualified condition: num(vCPU threads) == num(CPUs in sandbox's CPUSet) +# enable_vcpus_pinning = false + +# Apply a custom SELinux security policy to the container process inside the VM. +# This is used when you want to apply a type other than the default `container_t`, +# so general users should not uncomment and apply it. +# (format: "user:role:type") +# Note: You cannot specify MCS policy with the label because the sensitivity levels and +# categories are determined automatically by high-level container runtimes such as containerd. +#guest_selinux_label="@DEFGUESTSELINUXLABEL@" + +# 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 = true + +# 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/ From 14dd0537582c32f3f3e20850b1b74a13f5cb6ac3 Mon Sep 17 00:00:00 2001 From: Tobin Feldman-Fitzthum Date: Fri, 28 Apr 2023 19:29:36 +0000 Subject: [PATCH 11/13] kata-deploy: add kata-qemu-snp runtimeclass Since SEV-SNP has limited hotplug support, increase the pod overhead to account for fixed resource usage. Signed-off-by: Tobin Feldman-Fitzthum --- .../runtimeclasses/kata-runtimeClasses.yaml | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/tools/packaging/kata-deploy/runtimeclasses/kata-runtimeClasses.yaml b/tools/packaging/kata-deploy/runtimeclasses/kata-runtimeClasses.yaml index 00197ed3b7..4e8da4fea9 100644 --- a/tools/packaging/kata-deploy/runtimeclasses/kata-runtimeClasses.yaml +++ b/tools/packaging/kata-deploy/runtimeclasses/kata-runtimeClasses.yaml @@ -40,6 +40,19 @@ scheduling: --- kind: RuntimeClass apiVersion: node.k8s.io/v1 +metadata: + name: kata-qemu-snp +handler: kata-qemu-snp +overhead: + podFixed: + memory: "2048Mi" + cpu: "1.0" +scheduling: + nodeSelector: + katacontainers.io/kata-runtime: "true" +--- +kind: RuntimeClass +apiVersion: node.k8s.io/v1 metadata: name: kata-clh handler: kata-clh From 4da6eb588d148b1bf1479e3b86e9f1a08c58afc6 Mon Sep 17 00:00:00 2001 From: Tobin Feldman-Fitzthum Date: Wed, 3 May 2023 20:14:50 +0000 Subject: [PATCH 12/13] kata-deploy: Add qemu-snp shim Now that we have the SNP components in place, make sure that kata-deploy knows about the qemu-snp shim so that it will be added to containerd config. Fixes: #6575 Signed-off-by: Tobin Feldman-Fitzthum --- tools/packaging/kata-deploy/scripts/kata-deploy.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/packaging/kata-deploy/scripts/kata-deploy.sh b/tools/packaging/kata-deploy/scripts/kata-deploy.sh index 5ae15802a3..d6be5019f4 100755 --- a/tools/packaging/kata-deploy/scripts/kata-deploy.sh +++ b/tools/packaging/kata-deploy/scripts/kata-deploy.sh @@ -18,6 +18,7 @@ shims=( "qemu" "qemu-tdx" "qemu-gpu" + "qemu-snp" "clh" "dragonball" ) From 2c90cac75169d1835892d77c8c79705d27f6dc7f Mon Sep 17 00:00:00 2001 From: Tobin Feldman-Fitzthum Date: Wed, 10 May 2023 21:23:38 +0000 Subject: [PATCH 13/13] local-build: fixup alphabetization A few pieces of the local-build tooling are supposed to be alphabetized. Fixup a couple minor issues that have accumulated. Signed-off-by: Tobin Feldman-Fitzthum --- tools/packaging/kata-deploy/local-build/Makefile | 10 +++++----- .../kata-deploy/local-build/kata-deploy-binaries.sh | 12 ++++++------ 2 files changed, 11 insertions(+), 11 deletions(-) diff --git a/tools/packaging/kata-deploy/local-build/Makefile b/tools/packaging/kata-deploy/local-build/Makefile index fc3bbcb6e5..26454b1077 100644 --- a/tools/packaging/kata-deploy/local-build/Makefile +++ b/tools/packaging/kata-deploy/local-build/Makefile @@ -23,12 +23,12 @@ all-parallel: $(MK_DIR)/dockerbuild/install_yq.sh all: serial-targets \ firecracker-tarball \ - kernel-tarball \ kernel-dragonball-experimental-tarball \ - kernel-tdx-experimental-tarball \ kernel-gpu \ kernel-gpu-snp-tarball \ kernel-gpu-tdx-experimental-tarball \ + kernel-tarball \ + kernel-tdx-experimental-tarball \ nydus-tarball \ ovmf-sev-tarball \ ovmf-tarball \ @@ -55,10 +55,10 @@ cloud-hypervisor-tarball: firecracker-tarball: ${MAKE} $@-build -kernel-tarball: +kernel-dragonball-experimental-tarball: ${MAKE} $@-build -kernel-dragonball-experimental-tarball: +kernel-experimental-tarball: ${MAKE} $@-build kernel-gpu-tarball: @@ -70,7 +70,7 @@ kernel-gpu-snp-tarball: kernel-gpu-tdx-experimental-tarball: ${MAKE} $@-build -kernel-experimental-tarball: +kernel-tarball: ${MAKE} $@-build kernel-tdx-experimental-tarball: 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 101f32cd04..51e0e8da93 100755 --- a/tools/packaging/kata-deploy/local-build/kata-deploy-binaries.sh +++ b/tools/packaging/kata-deploy/local-build/kata-deploy-binaries.sh @@ -81,11 +81,11 @@ options: kernel kernel-dragonball-experimental kernel-experimental - kernel-tdx-experimental - kernel-sev-tarball kernel-gpu kernel-gpu-snp kernel-gpu-tdx-experimental + kernel-sev-tarball + kernel-tdx-experimental nydus ovmf ovmf-sev @@ -553,16 +553,16 @@ handle_build() { kernel-experimental) install_kernel_experimental ;; - kernel-tdx-experimental) install_kernel_tdx_experimental ;; - - kernel-sev) install_kernel_sev ;; - kernel-gpu) install_kernel_gpu ;; kernel-gpu-snp) install_kernel_gpu_snp;; kernel-gpu-tdx-experimental) install_kernel_gpu_tdx_experimental;; + kernel-tdx-experimental) install_kernel_tdx_experimental ;; + + kernel-sev) install_kernel_sev ;; + nydus) install_nydus ;; ovmf) install_ovmf ;;