VSHA-536 Zero md Superblocks

90metalmdsquash/metal-genrules.sh

@@ -29,7 +29,7 @@ command -v getarg > /dev/null 2>&1 || . /lib/dracut-lib.sh
 
 case "$(getarg root)" in 
     kdump)
-        /sbin/initqueue --settled /sbin/metal-md-scan
+        /sbin/initqueue --settled --onetime --unique /sbin/metal-md-scan
 
         # Ensure nothing else in this script is invoked in this case.
         exit 0
@@ -59,7 +59,7 @@ case "${metal_uri_scheme:-}" in
         ;;
     '')
         # Boot from block device.
-        /sbin/initqueue --settled /sbin/metal-md-scan
+        /sbin/initqueue --settled --onetime --unique /sbin/metal-md-scan
         ;;
     *)
         warn "Unknown driver $metal_server; metal.server ignored/discarded"

90metalmdsquash/metal-kdump.sh

@@ -33,8 +33,7 @@ command -v _overlayFS_path_spec > /dev/null 2>&1 || . /lib/metal-lib.sh
 
 case "$(getarg root)" in 
     kdump)
-        /sbin/initqueue --settled /sbin/metal-md-scan
-
+
         # Ensure nothing else in this script is invoked in this case.
         exit 0
         ;;

90metalmdsquash/metal-lib.sh

@@ -76,10 +76,26 @@ _load_dracut_dep
 export METAL_LOG_DIR='/var/log/metal'
 mkdir -p $METAL_LOG_DIR
 
+##############################################################################
+# constant: METAL_HASH
+# constant: METAL_DOCS_URL
+#
+# This is the VCS hash for commit that produced this library, it is auto-filled
+# when this module is built into an OS package.
+# This is useful for printing URLs to documentation that are relevant to the
+# library running in an initramFS.
+METAL_HASH='@@metal-hash@@'
+if [[ ${METAL_HASH} =~ 'metal-hash' ]]; then
+    # Default to main if this is running directly out of the repo.
+    METAL_HASH='main'
+fi
+export METAL_HASH
+export METAL_DOCS_URL=https://github.com/Cray-HPE/dracut-metal-mdsquash/tree/${METAL_HASH}
+
 ##############################################################################
 # constant: METAL_DONE_FILE_PAVED
 #
-# This file path present a file that the wipe function creates when it is 
+# This file path present a file that the wipe function creates when it is
 # invoked. The existence of the file implies the wipe code as been invoked,
 # the contents of the file can be interpretted to determine what the wipe
 # function actually did (see func metal_paved).
@@ -169,7 +185,7 @@ metal_die() {
     fi
     type die
     echo >&2 "metal_die: $*"
-    echo >&2 "GitHub/Docs: https://github.com/Cray-HPE/dracut-metal-mdsquash"
+    echo >&2 "GitHub/Docs: ${METAL_DOCS_URL}/README.adoc"
     sleep 30 # Leaving time (30seconds) for console/log buffers to catch up.
     if [ "$_reset" = 1 ]; then
 

90metalmdsquash/metal-md-disks.sh

@@ -39,12 +39,12 @@ disks_exist || exit 1
 # Now that disks exist it's worthwhile to load the libraries.
 command -v pave > /dev/null 2>&1 || . /lib/metal-md-lib.sh
 
-# Wipe; this returns early if a wipe was already done.
-pave
-
 # Check for existing RAIDs
 /sbin/metal-md-scan
 
+# Wipe; this returns early if a wipe was already done.
+pave
+
 # At this point this module is required; a disk must be created or the system has nothing to boot.
 # Die if no viable disks are found; otherwise continue to disk creation functions.
 if [ ! -f /tmp/metalsqfsdisk.done ] && [ "${metal_nowipe}" -eq 0 ]; then
@@ -65,7 +65,7 @@ if [ ! -f /tmp/metalsqfsdisk.done ] && [ "${metal_nowipe}" -eq 0 ]; then
         metal_die "No disks were found for the OS that were [$metal_disk_small] (in bytes) or larger, all were too small or had filesystems present!"
         exit 1
     else
-        echo >&2 "Found the following disks for the main RAID array (qty. [$metal_disks]): [${md_disks[*]}]"
+        echo >&2 "Found the following disk(s) for the main RAID array (qty. [$metal_disks]): [${md_disks[*]}]"
     fi
 fi
 

90metalmdsquash/metal-md-lib.sh

@@ -71,7 +71,7 @@ boot_drive_authority=${boot_fallback#*=}
 [ -z "$boot_drive_authority" ] && boot_drive_authority=BOOTRAID
 case $boot_drive_scheme in
     PATH | path | UUID | uuid | LABEL | label)
-        info "bootloader will be located on ${boot_drive_scheme}=${boot_drive_authority}"
+        printf '%-12s: %s\n' 'bootloader' "${boot_drive_scheme}=${boot_drive_authority}"
         ;;
     '')
         # no-op; drive disabled
@@ -88,7 +88,7 @@ esac
 [ -z "${sqfs_drive_authority}" ] && sqfs_drive_scheme=SQFSRAID
 case $sqfs_drive_scheme in
     PATH | path | UUID | uuid | LABEL | label)
-        info "SquashFS file is on ${sqfs_drive_scheme}=${sqfs_drive_authority}"
+        printf '%-12s: %s\n' 'squashFS' "${sqfs_drive_scheme}=${sqfs_drive_authority}"
         ;;
     *)
         metal_die "Unsupported sqfs-drive-scheme ${sqfs_drive_scheme}\nSupported schemes: PATH, UUID, and LABEL"
@@ -100,7 +100,7 @@ oval_drive_scheme=${metal_overlay%%=*}
 oval_drive_authority=${metal_overlay#*=}
 case "$oval_drive_scheme" in
     PATH | path | UUID | uuid | LABEL | label)
-        info "Overlay is on ${oval_drive_scheme}=${oval_drive_authority}"
+        printf '%-12s: %s\n' 'overlay' "${oval_drive_scheme}=${oval_drive_authority}"
         ;;
     '')
         # no-op; disabled
@@ -218,10 +218,10 @@ add_overlayfs() {
     [ -f /tmp/metalovalimg.done ] && return
     local mpoint=/metal/ovaldisk
     mkdir -pv ${mpoint}
-    if ! mount -v -n -t xfs /dev/md/ROOT "$mpoint"; then
+    if ! mount -n -t xfs /dev/md/ROOT "$mpoint"; then
 
         # try shasta-1.3 formatting or die.
-        mount -v -n -t ext4 /dev/md/ROOT "$mpoint" \
+        mount -n -t ext4 /dev/md/ROOT "$mpoint" \
             || metal_die "Failed to mount ${oval_drive_authority} as xfs or ext4"
     fi
 
@@ -233,7 +233,7 @@ add_overlayfs() {
         "${mpoint}/${live_dir}/${metal_overlayfs_id}" \
         "${mpoint}/${live_dir}/${metal_overlayfs_id}/../ovlwork"
     echo 1 > /tmp/metalovalimg.done && info 'OverlayFS is ready ...'
-    umount -v ${mpoint}
+    umount ${mpoint}
 }
 
 ###############################################################################
@@ -261,13 +261,13 @@ fetch_sqfs() {
 
         # Mount read-only to prevent harm to the device; we literally just need to pull the files off it.
         mkdir -vp /tmp/source
-        mount -v  -n -o ro -L "$metal_local_url_authority" /tmp/source || metal_die "Failed to mount $metal_local_url_authority from $metal_server"
+        mount -n -o ro -L "$metal_local_url_authority" /tmp/source || metal_die "Failed to mount $metal_local_url_authority from $metal_server"
         (
             set -e
             cd "$1"
             cp -pv "/tmp/source/${metal_local_dir#//}/${squashfs_file}" . && echo "copied ${squashfs_file} ... " > debug_log
         ) || warn 'Failed to copy ; may retry'
-        umount -v /tmp/source
+        umount /tmp/source
     fi
     if [ -f "$1/${squashfs_file}" ]; then
         echo 1 > /tmp/metalsqfsimg.done
@@ -316,10 +316,10 @@ add_sqfs() {
         info "URI host ${uri_host} responds ... "
     fi
     mkdir -pv $sqfs_store
-    if mount -v -n -t xfs /dev/md/SQFS $sqfs_store; then
+    if mount -n -t xfs /dev/md/SQFS $sqfs_store; then
         mkdir -pv "$sqfs_store/$live_dir"
         fetch_sqfs "$sqfs_store/$live_dir" || metal_die 'Failed to fetch squashFS into squashFS storage!'
-        umount -v $sqfs_store
+        umount $sqfs_store
     else
         # No RAID mount, issue warning, delete mount-point and return
         metal_die "Failed to mount /dev/md/SQFS at $sqfs_store"
@@ -348,7 +348,7 @@ pave() {
     # the original run.
     if [ -f "$METAL_DONE_FILE_PAVED" ]; then
         echo "${FUNCNAME[0]} already done" >>"$log"
-        echo "wipe done file already exists ($METAL_DONE_FILE_PAVED); not wiping disks"
+        echo "wipe 'done file' already exists ($METAL_DONE_FILE_PAVED); not wiping disks"
         return 0
     fi
     {
@@ -361,17 +361,19 @@ pave() {
     } >>"$log" 2>&1
 
     if [ "$metal_nowipe" -ne 0 ]; then
-        echo "${FUNCNAME[0]} skipped: metal.no-wipe=${metal_nowipe}" >>$log
         warn 'local storage device wipe [ safeguard: ENABLED  ]'
-        warn 'local storage devices will not be wiped.'
+        warn "local storage devices will not be wiped (${METAL_DOCS_URL}#metalno-wipe)"
         echo 0 > "$METAL_DONE_FILE_PAVED" && return 0
     else
         warn 'local storage device wipe [ safeguard: DISABLED ]'
+        warn "local storage devices WILL be wiped (${METAL_DOCS_URL}#metalno-wipe)"
     fi
-    warn 'local storage device wipe commencing (USB devices are ignored) ...'
+    warn 'local storage device wipe commencing ...'
+    warn "local storage device wipe ignores USB devices and block devices smaller than [$metal_ignore_threshold] bytes."
 
     warn 'nothing can be done to stop this except one one thing ...'
-    warn "... power this node off within the next [$metal_wipe_delay] seconds to prevent any and all operations ..."
+    warn "power this node off within the next [$metal_wipe_delay] second(s) to cancel."
+    warn "NOTE: this delay can be adjusted, see: ${METAL_DOCS_URL}#metalwipe-delay"
     while [ "${metal_wipe_delay}" -ge 0 ]; do
         [ "${metal_wipe_delay}" = 2 ] && unit='second' || unit='seconds'
         sleep 1 && local metal_wipe_delay=$((${metal_wipe_delay} - 1)) && echo "${metal_wipe_delay} $unit"
@@ -402,28 +404,27 @@ pave() {
     doomed_raids="$(lsblk -l -o NAME,TYPE | grep raid | sort -u | awk '{print "/dev/"$1}' | tr '\n' ' ' | sed 's/ *$//')"
     warn "local storage device wipe is targeting the following RAID(s): [$doomed_raids]"
     for doomed_raid in $doomed_raids; do
-        wipefs --all --force "$doomed_raid" >>"$log" 2>&1
+        {
+        wipefs --all --force "$doomed_raid"
+        mdadm --stop "$doomed_raid"
+        } >>"$log" 2>&1
     done
 
     # 3. NUKE BLOCKs
     # Wipe each selected disk and its partitions.
     doomed_disks="$(lsblk -b -d -l -o NAME,SUBSYSTEMS,SIZE | grep -E '('"$metal_subsystems"')' | grep -v -E '('"$metal_subsystems_ignore"')' | sort -u | awk '{print ($3 > '$metal_ignore_threshold') ? "/dev/"$1 : ""}' | tr '\n' ' ' | sed 's/ *$//')"
     warn "local storage device wipe is targeting the following block devices: [$doomed_disks]"
     for doomed_disk in $doomed_disks; do
-        wipefs --all --force "$doomed_disk"*
+        {
+            mdadm --zero-superblock "$doomed_disk"*
+            wipefs --all --force "$doomed_disk"*
+        } >>"$log" 2>&1
     done
 
-    # 4. Cleanup mdadm
-    # Now that the signatures and volume groups are wiped/gone, mdraid-cleanup can mop up and left
-    # over /dev/md handles.
-    {
-        lsblk
-        mdraid-cleanup
-        lsblk
-    } >>"$log" 2>&1
+    _trip_udev
 
-    # 5. Notify the kernel of the partition changes
-    # NOTE: This could be done in the same loop that we wipe devices, however mileage has varied.
+    # 4. Notify the kernel of the partition changes
+    # NOTE: This could be done in the same loop where we wipe devices, however mileage has varied.
     #       Running this as a standalone step has had better results.
     for doomed_disk in $doomed_disks; do
         {
@@ -433,8 +434,6 @@ pave() {
         } >>"$log" 2>&1
     done
 
-    _trip_udev
-
     warn 'local storage disk wipe complete' && echo 1 > "$METAL_DONE_FILE_PAVED"
     {
         mount -v

Makefile

@@ -46,7 +46,7 @@ rpm_package_source:
 	tar --transform 'flags=r;s,^,/${NAME}-${VERSION}/,' --exclude .git --exclude dist -cvjf $(SOURCE_PATH) .
 
 rpm_build_source:
-	BUILD_METADATA=$(BUILD_METADATA) rpmbuild --nodeps -ts $(SOURCE_PATH) --define "_topdir $(BUILD_DIR)"
+	rpmbuild --nodeps -ts $(SOURCE_PATH) --define "_topdir $(BUILD_DIR)"
 
 rpm_build:
-	BUILD_METADATA=$(BUILD_METADATA) rpmbuild --nodeps -ba $(SPEC_FILE) --define "_topdir $(BUILD_DIR)"
+	rpmbuild --nodeps -ba $(SPEC_FILE) --define "_topdir $(BUILD_DIR)"