[pve-devel] [PATCH pve-kernel-meta 3/5] proxmox-boot: fix #3671 add pin/unpin for kernel-version

[Stoiko Ivanov <s.ivanov@proxmox.com>]

The 2 commands follow the mechanics of p-b-t kernel add/remove in
writing the desired abi-version to a config-file in /etc/kernel and
actually modifying the boot-loader configuration upon p-b-t refresh.

A dedicated new file is used instead of writing the version (with some
kind of annotation) to the manual kernel list to keep parsing the file
simple (and hopefully also cause fewer problems with manually edited
files)

For systemd-boot we write the entry into the loader.conf on the ESP(s)
instead of relying on the `bootctl set-default` mechanics (bootctl(1))
which write the entry in an EFI-var. This was preferred, because of a
few reports of unwriteable EFI-vars on some systems (e.g. DELL servers
have a setting preventing writing EFI-vars from the OS). The rationale
in `Why not simply rely on the EFI boot menu logic?` from [0] also
makes a few points in that direction.

For grub the following choices were made:
* write the pinned version (or actually the menu-path leading to it)
  to /etc/default/grub instead of editing the grub.cfg files on the
  partition. Mostly to divert as little as possible from the
  grub-workflow I assume people are used to.
* the 'root-device-id' part of the menu-entries is parsed from
  /boot/grub/grug.cfg since it was stable (the same on all ESPs and in
  /boot/grub), saves us from copying the part of "find device behind
  /, mangle it if zfs/btrfs, call grub_probe a few times" part of
  grub-mkconfig - and seems a bit more robust

Tested with a BIOS and an UEFI VM with / on ZFS.

[0] https://systemd.io/BOOT_LOADER_SPECIFICATION/

Signed-off-by: Stoiko Ivanov <s.ivanov@proxmox.com>
---
 bin/proxmox-boot-tool        | 47 +++++++++++++++++++++++++++++++++---
 proxmox-boot/functions       | 37 ++++++++++++++++++++++++++++
 proxmox-boot/zz-proxmox-boot |  6 +++++
 3 files changed, 86 insertions(+), 4 deletions(-)

diff --git a/bin/proxmox-boot-tool b/bin/proxmox-boot-tool
index 93760fb..75eea0e 100755
--- a/bin/proxmox-boot-tool
+++ b/bin/proxmox-boot-tool
@@ -286,6 +286,13 @@ list_kernels() {
 	echo ""
 	echo "Automatically selected kernels:"
 	echo "$boot_kernels"
+
+	if [ -e "$PINNED_KERNEL_CONF" ]; then
+		pinned_kernel="$(get_first_line "$PINNED_KERNEL_CONF" || true )"
+		echo ""
+		echo "Pinned kernel:"
+		echo "$pinned_kernel"
+	fi
 }
 
 usage() {
@@ -295,8 +302,8 @@ usage() {
 	warn "       $0 init <partition>"
 	warn "       $0 clean [--dry-run]"
 	warn "       $0 refresh [--hook <name>]"
-	warn "       $0 kernel <add|remove> <kernel-version>"
-	warn "       $0 kernel list"
+	warn "       $0 kernel <add|remove|pin> <kernel-version>"
+	warn "       $0 kernel <list|unpin>"
 	warn "       $0 status [--quiet]"
 	warn "       $0 help"
 }
@@ -318,14 +325,16 @@ help() {
 	echo ""
 	echo "    refresh all configured EFI system partitions. Use --hook to only run the specified hook, omit to run all."
 	echo ""
-	echo "USAGE: $0 kernel <add|remove> <kernel-version>"
+	echo "USAGE: $0 kernel <add|remove|pin> <kernel-version>"
 	echo ""
 	echo "    add/remove pve-kernel with ABI <kernel-version> to list of synced kernels, in addition to automatically selected ones."
 	echo "    NOTE: you need to manually run 'refresh' once you're finished with adding/removing kernels from the list"
+	echo "    pin pve-kernel with ABI <kernel-version> sets it as the default entry to be booted."
 	echo ""
-	echo "USAGE: $0 kernel list"
+	echo "USAGE: $0 kernel <list|unpin>"
 	echo ""
 	echo "    list kernel versions currently selected for inclusion on ESPs."
+	echo "    unpin sets the latest kernel as the default entry (undoes a previous pin)"
 	echo ""
 	echo "USAGE: $0 status [--quiet]"
 	echo ""
@@ -392,6 +401,28 @@ status() {
 	fi
 }
 
+pin_kernel() {
+	ver="$1"
+
+	if [ -z "$ver" ]; then
+		warn "E: <kernel-version> is mandatory"
+		warn ""
+		exit 1
+	fi
+
+	if [ ! -e "/boot/vmlinuz-$ver" ]; then
+		warn "E: no kernel image found in /boot for '$ver', not setting default."
+		exit 1
+	fi
+	echo "$ver" > "$PINNED_KERNEL_CONF"
+	echo "Set kernel '$ver' $PINNED_KERNEL_CONF. Use the 'refresh' command to update the ESPs."
+}
+
+unpin_kernel() {
+	rm -f "$PINNED_KERNEL_CONF"
+	echo "Removed $PINNED_KERNEL_CONF. Use the 'refresh' command to update the ESPs."
+}
+
 if [ -z "$1" ]; then
     usage
     exit 0
@@ -460,6 +491,14 @@ case "$1" in
 				list_kernels
 				exit 0
 			;;
+			'pin')
+				pin_kernel "$2"
+				exit 0
+			;;
+			'unpin')
+				unpin_kernel "$2"
+				exit 0
+			;;
 			*)
 				warn "E: invalid 'kernel' subcommand '$cmd'."
 				warn ""
diff --git a/proxmox-boot/functions b/proxmox-boot/functions
index 4515a2d..9fa29ca 100755
--- a/proxmox-boot/functions
+++ b/proxmox-boot/functions
@@ -5,6 +5,7 @@ ESP_LIST="/etc/kernel/proxmox-boot-uuids"
 ESPTYPE='c12a7328-f81f-11d2-ba4b-00a0c93ec93b'
 
 MANUAL_KERNEL_LIST="/etc/kernel/pve-efiboot-manual-kernels"
+PINNED_KERNEL_CONF="/etc/kernel/proxmox-boot-pin"
 
 MOUNTROOT="${TMPDIR:-/var/tmp}/espmounts"
 # relative to the ESP mountpoint
@@ -56,6 +57,10 @@ kernel_keep_versions() {
 		manual_kernels="$(cat "$MANUAL_KERNEL_LIST")"
 	fi
 
+	if [ -e "$PINNED_KERNEL_CONF" ]; then
+		pinned_kernel="$(get_first_line "$PINNED_KERNEL_CONF")"
+	fi
+
 	kernels="$(cat <<-EOF
 		$running_version
 		$install_version
@@ -63,6 +68,7 @@ kernel_keep_versions() {
 		$latest_2_versions
 		$series_metapackages
 		$oldseries_latest_kernel
+		$pinned_kernel
 		EOF
 	)"
 
@@ -109,3 +115,34 @@ get_first_line() {
 	done < "${file}"
 	echo "$line"
 }
+
+set_grub_default() {
+	kver="$1"
+	if [ -z "${kver}" ]; then
+		entry="0"
+	else
+		# grub menu entry ids contain the internal root-device id
+		# (e.g. for zfs the GUID of the pool printed in hex) as this
+		# as this is independent of the ESP (or grub location) take
+		# it from /boot/grub/grub.cfg
+		root_devid=$(sed -rn "s/.*gnulinux-advanced-(.+)['] \{$/\1/p" \
+			/boot/grub/grub.cfg)
+		entry="gnulinux-advanced-${root_devid}>gnulinux-${kver}-advanced-${root_devid}"
+	fi
+	sed -ri "/^GRUB_DEFAULT/{h;s/=.*\$/=\"${entry}\"/};\${x;/^$/{s//GRUB_DEFAULT=\"${entry}\"/;H};x}" \
+		/etc/default/grub
+}
+
+set_systemd_boot_default() {
+	mountpoint="$1"
+	kver="$2"
+	if [ -z "${kver}" ]; then
+		entry="proxmox-*"
+	else
+		entry="proxmox-${kver}.conf"
+	fi
+
+	sed -ri "/^default /{h;s/ .*\$/ ${entry}/};\${x;/^$/{s//default ${entry}/;H};x}" \
+		"${mountpoint}/$PMX_LOADER_CONF"
+
+}
diff --git a/proxmox-boot/zz-proxmox-boot b/proxmox-boot/zz-proxmox-boot
index db73166..27448b2 100755
--- a/proxmox-boot/zz-proxmox-boot
+++ b/proxmox-boot/zz-proxmox-boot
@@ -90,9 +90,15 @@ update_esp_func() {
 	fi
 	warn "Copying and configuring kernels on ${path}"
 	copy_and_config_kernels "${mountpoint}"
+
+	if [ -e "${PINNED_KERNEL_CONF}" ]; then
+	    pinned_kernel=$(get_first_line "${PINNED_KERNEL_CONF}")
+	fi
 	if [ -d /sys/firmware/efi ]; then
+		set_systemd_boot_default "${mountpoint}" "${pinned_kernel}"
 		remove_old_kernels_efi "${mountpoint}"
 	else
+		set_grub_default "${pinned_kernel}"
 		remove_old_kernels_legacy "${mountpoint}"
 		mount --bind "${mountpoint}" "/boot"
 		update-grub
-- 
2.30.2