Merge pull request #3241 from flatcar/kai/initrd-in-usr

Use a minimal initrd to switch to the full initrd stored in /usr

Author: pothos

.github/workflows/portage-stable-packages-list

@@ -581,6 +581,7 @@ sys-apps/acl
 sys-apps/attr
 sys-apps/azure-vm-utils
 sys-apps/bubblewrap
+sys-apps/busybox
 sys-apps/checkpolicy
 sys-apps/config-site
 sys-apps/coreutils

build_library/build_image_util.sh

@@ -582,6 +582,8 @@ finish_image() {
   local image_initrd_contents="${11}"
   local image_initrd_contents_wtd="${12}"
   local image_disk_space_usage="${13}"
+  local image_realinitrd_contents="${14}"
+  local image_realinitrd_contents_wtd="${15}"
 
   local install_grub=0
   local disk_img="${BUILD_DIR}/${image_name}"
@@ -877,6 +879,20 @@ EOF
       rm -rf "${BUILD_DIR}/tmp_initrd_contents"
   fi
 
+  if [[ -n ${image_realinitrd_contents} || -n ${image_realinitrd_contents_wtd} ]]; then
+        mkdir -p "${BUILD_DIR}/tmp_initrd_contents"
+        sudo mount "${root_fs_dir}/usr/lib/flatcar/bootengine.img" "${BUILD_DIR}/tmp_initrd_contents"
+        if [[ -n ${image_realinitrd_contents} ]]; then
+            write_contents "${BUILD_DIR}/tmp_initrd_contents" "${BUILD_DIR}/${image_realinitrd_contents}"
+        fi
+
+        if [[ -n ${image_realinitrd_contents_wtd} ]]; then
+            write_contents_with_technical_details "${BUILD_DIR}/tmp_initrd_contents" "${BUILD_DIR}/${image_realinitrd_contents_wtd}"
+        fi
+        sudo umount "${BUILD_DIR}/tmp_initrd_contents"
+        rm -rf "${BUILD_DIR}/tmp_initrd_contents"
+    fi
+
   if [[ -n "${image_disk_space_usage}" ]]; then
       write_disk_space_usage "${root_fs_dir}" "${BUILD_DIR}/${image_disk_space_usage}"
   fi

build_library/prod_image_util.sh

@@ -83,6 +83,8 @@ create_prod_image() {
   local image_initrd_contents="${image_name%.bin}_initrd_contents.txt"
   local image_initrd_contents_wtd="${image_name%.bin}_initrd_contents_wtd.txt"
   local image_disk_usage="${image_name%.bin}_disk_usage.txt"
+  local image_realinitrd_contents="${image_name%.bin}_realinitrd_contents.txt"
+  local image_realinitrd_contents_wtd="${image_name%.bin}_realinitrd_contents_wtd.txt"
   local image_sysext_base="${image_name%.bin}_sysext.squashfs"
 
   start_image "${image_name}" "${disk_layout}" "${root_fs_dir}" "${update_group}"
@@ -180,7 +182,9 @@ EOF
       "${image_kconfig}" \
       "${image_initrd_contents}" \
       "${image_initrd_contents_wtd}" \
-      "${image_disk_usage}"
+      "${image_disk_usage}" \
+      "${image_realinitrd_contents}" \
+      "${image_realinitrd_contents_wtd}"
 
   # Official builds will sign and upload these files later, so remove them to
   # prevent them from being uploaded now.

changelog/changes/2025-09-19-minimal-initrd.md

@@ -0,0 +1 @@
+- Reduced the kernel+initrd size on `/boot` by half. Flatcar now uses a minimal first stage initrd just to access the `/usr` partition and then switches to the full initrd that does the full system preparation as before. Since this means that the set of kernel modules available in the first initrd is reduced, please report any impact.

ci-automation/image_changes.sh

@@ -729,6 +729,15 @@ function print_image_reports() {
     echo "Note that vmlinuz-a also contains the kernel code, which might have changed too, so the reported difference does not accurately describe the change in initrd."
     echo
 
+    yell "Real/full init ramdisk (bootengine.img) differences compared to ${previous_version_description}"
+    underline "Real/full init ramdisk (bootengine.img) file changes, compared to ${previous_version_description}:"
+    env \
+        "${package_diff_env[@]}" FILE=flatcar_production_image_realinitrd_contents.txt FILESONLY=1 CUTKERNEL=1 \
+        "${flatcar_build_scripts_repo}/package-diff" "${package_diff_params[@]}" 2>&1 || true
+
+    underline "Real/full init ramdisk (bootengine.img) file size changes, compared to ${previous_version_description}:"
+    "${size_changes_invocation[@]}" "${size_change_report_params[@]/%/:realinitrd-wtd}" 2>&1 || true
+
     local base_sysext
     for base_sysext in "${base_sysexts[@]}"; do
         yell "Base sysext ${base_sysext} changes compared to ${previous_version_description}"

sdk_container/src/third_party/coreos-overlay/sys-apps/seismograph/seismograph-9999.ebuild

@@ -7,7 +7,7 @@ EGIT_REPO_URI="https://github.com/flatcar/seismograph.git"
 if [[ "${PV}" == 9999 ]]; then
 	KEYWORDS="~amd64 ~arm ~arm64 ~x86"
 else
-	EGIT_COMMIT="e32ac4d13ca44333dc77e5872dbf23f964b6f1e2" # main
+	EGIT_COMMIT="231f8b31c576133f75151d34cb90890bfaf15ebe" # main
 	KEYWORDS="amd64 arm arm64 x86"
 fi
 

sdk_container/src/third_party/coreos-overlay/sys-kernel/bootengine/bootengine-9999.ebuild

@@ -7,7 +7,7 @@ EGIT_REPO_URI="https://github.com/flatcar/bootengine.git"
 if [[ "${PV}" == 9999 ]]; then
 	KEYWORDS="~amd64 ~arm ~arm64 ~x86"
 else
-	EGIT_COMMIT="daf43bf9c1ca45bf1a43566c3a6f96ec0cb44a36" # flatcar-master
+	EGIT_COMMIT="0b9d52e647289fe7793839265617afc5178d5f00" # flatcar-master
 	KEYWORDS="amd64 arm arm64 x86"
 fi
 
@@ -23,6 +23,7 @@ src_install() {
 	insinto /usr/lib/dracut/modules.d/
 	doins -r dracut/.
 	dosbin update-bootengine
+	dosbin minimal-init
 
 	# must be executable since dracut's install scripts just
 	# re-use existing filesystem permissions during initrd creation.

sdk_container/src/third_party/coreos-overlay/sys-kernel/coreos-kernel/coreos-kernel-6.12.51.ebuild

@@ -26,6 +26,7 @@ DEPEND="
 	coreos-base/coreos-init:=
 	sys-apps/azure-vm-utils[dracut]
 	sys-apps/baselayout
+	sys-apps/busybox
 	sys-apps/coreutils
 	sys-apps/findutils
 	sys-apps/grep
@@ -89,6 +90,59 @@ src_compile() {
 
 	tc-export PKG_CONFIG
 	"${ESYSROOT}"/usr/bin/update-bootengine -k "${KV_FULL}" -o "${S}"/build/bootengine.cpio "${BE_ARGS[@]}" || die
+	# Copy full initrd over to /usr as filesystem image
+	mkdir "${S}"/build/bootengine || die
+	pushd "${S}"/build/bootengine || die
+	lsinitrd --kver SILENCEERROR --unpack "${S}"/build/bootengine.cpio || die
+	mksquashfs . "${S}"/build/bootengine.img -noappend -xattrs-exclude ^btrfs. || die
+	popd || die
+	# Create minimal initrd
+	if use amd64; then
+		mkdir "${S}"/build/early-cpio || die
+		pushd "${S}"/build/early-cpio || die
+		lsinitrd --kver SILENCEERROR --unpackearly "${S}"/build/bootengine.cpio || die
+		# Recreate to only contain the early cpio for microcode
+		find . -print0 | cpio --null --create --verbose --format=newc > "${S}"/build/bootengine.cpio || die
+		# Debug: List contents after recreation
+		cpio -t < "${S}"/build/bootengine.cpio
+		popd || die
+	else
+		# No early cpio, drop full initrd
+		> "${S}"/build/bootengine.cpio
+	fi
+	mkdir "${S}"/build/minimal || die
+	pushd "${S}"/build/minimal || die
+	mkdir -p {etc,dev,proc,sys,dev,usr/bin,usr/lib64,realinit,sysusr/usr} || die
+	ln -s usr/bin bin || die
+	ln -s usr/bin sbin || die
+	ln -s bin usr/sbin || die
+	ln -s usr/lib64 lib || die
+	ln -s usr/lib64 lib64 || die
+	ln -s lib64 usr/lib || die
+	mkdir -p lib/modules/"${KV_FULL}"/ || die
+	# Instead from ESYSROOT we can also copy kernel modules from the dracut pre-selection
+	cp "${S}"/build/bootengine/usr/lib/modules/"${KV_FULL}"/modules.* lib/modules/"${KV_FULL}"/ || die
+	mkdir -p lib/modprobe.d/ || die
+	cp "${S}"/build/bootengine/lib/modprobe.d/* lib/modprobe.d/ || die
+	# Only include modules related to mounting /usr and for interacting with the emergency console
+	pushd "${S}/build/bootengine/usr/lib/modules/${KV_FULL}" || die
+	find kernel/drivers/{ata,block,hid,hv,input/serio,mmc,nvme,pci,scsi,usb} kernel/fs/{btrfs,overlayfs,squashfs} kernel/security/keys -name "*.ko.*" -printf "%f\0" | DRACUT_NO_XATTR=1 xargs --null "${BROOT}"/usr/lib/dracut/dracut-install --destrootdir "${S}"/build/minimal --kerneldir . --sysrootdir "${S}"/build/bootengine/ --firmwaredirs "${S}"/build/bootengine/usr/lib/firmware --module dm-verity dm-mod virtio_console || die
+	popd || die
+	echo '$MODALIAS=.*	0:0 660 @/sbin/modprobe "$MODALIAS"' > ./etc/mdev.conf || die
+	# We can't use busybox's modprobe because it doesn't support the globs in module.alias, breaking module loading
+	DRACUT_NO_XATTR=1 "${BROOT}"/usr/lib/dracut/dracut-install --destrootdir . --sysrootdir "${ESYSROOT}" --ldd /bin/veritysetup /bin/dmsetup /bin/busybox /sbin/modprobe || die
+	cp -a "${ESYSROOT}"/usr/bin/minimal-init ./init || die
+	# Make it easier to debug by not relying too much on the first commands
+	ln -s busybox ./bin/sh || die
+	mknod ./dev/console c 5 1 || die
+	mknod ./dev/null c 1 3 || die
+	mknod ./dev/tty c 5 0 || die
+	mknod ./dev/urandom c 1 9 || die
+	mknod ./dev/random c 1 8 || die
+	mknod ./dev/zero c 1 5 || die
+	# No compression because CONFIG_INITRAMFS_COMPRESSION_XZ should take care of it
+	find . -print0 | cpio --null --create --verbose --format=newc >> "${S}"/build/bootengine.cpio || die
+	popd || die
 	kmake "$(kernel_target)"
 
 	# sanity check :)
@@ -111,4 +165,7 @@ src_install() {
 	# For easy access to vdso debug symbols in gdb:
 	#   set debug-file-directory /usr/lib/debug/usr/lib/modules/${KV_FULL}/vdso/
 	kmake INSTALL_MOD_PATH="${ED}/usr/lib/debug/usr" vdso_install
+
+	insinto "/usr/lib/flatcar"
+	doins build/bootengine.img
 }

sdk_container/src/third_party/coreos-overlay/sys-kernel/coreos-sources/coreos-sources-6.12.51.ebuild

@@ -43,4 +43,5 @@ UNIPATCH_LIST="
 	${PATCH_DIR}/z0006-mtd-disable-slram-and-phram-when-locked-down.patch \
 	${PATCH_DIR}/z0007-arm64-add-kernel-config-option-to-lock-down-when.patch \
 	${PATCH_DIR}/z0008-tools-hv-fix-cross-compilation-for-ARM64.patch \
+	${PATCH_DIR}/z0009-block-add-partition-uuid-into-uevent.patch \
 "

sdk_container/src/third_party/coreos-overlay/sys-kernel/coreos-sources/files/6.12/z0009-block-add-partition-uuid-into-uevent.patch

@@ -0,0 +1,36 @@
+From 758737d86f8a2d74c0fa9f8b2523fa7fd1e0d0aa Mon Sep 17 00:00:00 2001
+From: Konstantin Khlebnikov <[email protected]>
+Date: Fri, 4 Oct 2024 17:13:43 -0700
+Subject: [PATCH] block: add partition uuid into uevent as "PARTUUID"
+
+Both most common formats have uuid in addition to partition name:
+GPT: standard uuid xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
+DOS: 4 byte disk signature and 1 byte partition xxxxxxxx-xx
+
+Tools from util-linux use the same notation for them.
+
+Signed-off-by: Konstantin Khlebnikov <[email protected]>
+Reviewed-by: Kyle Fortin <[email protected]>
+[dianders: rebased to modern kernels]
+Signed-off-by: Douglas Anderson <[email protected]>
+Signed-off-by: Douglas Anderson <[email protected]>
+Reviewed-by: Christoph Hellwig <[email protected]>
+Link: https://lore.kernel.org/r/20241004171340.v2.1.I938c91d10e454e841fdf5d64499a8ae8514dc004@changeid
+Signed-off-by: Jens Axboe <[email protected]>
+---
+ block/partitions/core.c | 2 ++
+ 1 file changed, 2 insertions(+)
+
+diff --git a/block/partitions/core.c b/block/partitions/core.c
+index cdad05f9764768..815ed33caa1b86 100644
+--- a/block/partitions/core.c
++++ b/block/partitions/core.c
+@@ -256,6 +256,8 @@ static int part_uevent(const struct device *dev, struct kobj_uevent_env *env)
+ 	add_uevent_var(env, "PARTN=%u", bdev_partno(part));
+ 	if (part->bd_meta_info && part->bd_meta_info->volname[0])
+ 		add_uevent_var(env, "PARTNAME=%s", part->bd_meta_info->volname);
++	if (part->bd_meta_info && part->bd_meta_info->uuid[0])
++		add_uevent_var(env, "PARTUUID=%s", part->bd_meta_info->uuid);
+ 	return 0;
+ }
+