de95c74a76
Now when mount in /etc/fstab fails, systemd would not consider it as
critical and it would continue to boot. In fact, emergency service is
triggered, but not in a isolation mode, and it results in the emergency
service getting shutdown at some point later of the boot process. We
need isolation otherwise we won't see any emergency service.
That is because in kdump initramfs, mount units specified in /etc/fstab
are required by "local-fs.target". When any of these mounts fails,
local-fs.target fails.
For kdump initramfs, we need to isolate to emergency service on any of
the mount failure, that said, every service should be stopped and onlu
emergency service would run. But local-fs.target won't trigger that on
its failure. That means in case of mount failure, local-fs.target also
enters failure state, but all the service will continue without any
interruption.
After digging looking into source code of systemd-fstab-generator. I
find "x-initrd.mount" using in initramfs mount, will make the mount
units required by "initrd-root-fs.target" rather than it's used to be
"local-fs.target".
"initrd-root-fs.target" is suitable to us because if it fails, it will
isolate to emergency service. That means in case of any mount failure,
the emergeny service will start and everything else will stop. We want
this effect because we need to take kdump fail-safe action when there's
a mount failure.
From systemd unit point of view, "initrd-root-fs.target" has
OnFailureIsolate=yes, but "local-fs.target" doesn't. From
systemd.unit(5):
OnFailureIsolate=
Takes a boolean argument. If true, the unit listed in OnFailure=
will be enqueued in isolation mode, i.e. all units that are not its
dependency will be stopped. If this is set, only a single unit may
be listed in OnFailure=. Defaults to false.
NOTE: Harald who contributed "x-initrd.mount" in systemd, confirmed that
this feature will stay.
Signed-off-by: WANG Chao <chaowang@redhat.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
581 lines
15 KiB
Bash
581 lines
15 KiB
Bash
#!/bin/bash --norc
|
|
# New mkdumprd
|
|
#
|
|
# Copyright 2011 Red Hat, Inc.
|
|
#
|
|
# Written by Cong Wang <amwang@redhat.com>
|
|
#
|
|
|
|
. /lib/kdump/kdump-lib.sh
|
|
export IN_KDUMP=1
|
|
|
|
conf_file="/etc/kdump.conf"
|
|
SSH_KEY_LOCATION="/root/.ssh/kdump_id_rsa"
|
|
SAVE_PATH=$(grep ^path $conf_file| cut -d' ' -f2)
|
|
[ -z "$SAVE_PATH" ] && SAVE_PATH=$DEFAULT_PATH
|
|
extra_modules=""
|
|
dracut_args=("--hostonly" "-o" "plymouth dash resume")
|
|
OVERRIDE_RESETTABLE=0
|
|
|
|
perror_exit() {
|
|
echo $@ >&2
|
|
exit 1
|
|
}
|
|
|
|
perror() {
|
|
echo $@ >&2
|
|
}
|
|
|
|
get_persistent_dev() {
|
|
local i _tmp _dev
|
|
|
|
_dev=$(udevadm info --query=name --name="$1" 2>/dev/null)
|
|
[ -z "$_dev" ] && {
|
|
perror_exit "Kernel dev name of $1 is not found."
|
|
}
|
|
|
|
for i in /dev/mapper/* /dev/disk/by-uuid/* /dev/disk/by-id/*; do
|
|
_tmp=$(udevadm info --query=name --name="$i" 2>/dev/null)
|
|
if [ "$_tmp" = "$_dev" ]; then
|
|
echo $i
|
|
return
|
|
fi
|
|
done
|
|
|
|
perror "WARNING: Persistent device name of $1 not found. Using $1 as dump target name"
|
|
echo $1
|
|
}
|
|
|
|
add_dracut_arg() {
|
|
local arg qarg is_quoted=0
|
|
while [ $# -gt 0 ];
|
|
do
|
|
arg="${1//\'/\"}"
|
|
#Handle quoted substring properly for passing it to dracut_args array.
|
|
if [ $is_quoted -eq 0 ]; then
|
|
if [[ "$arg" == "\"" ]] || [[ $arg != ${arg#\"} ]]; then
|
|
is_quoted=1
|
|
arg=${arg#\"}
|
|
fi
|
|
fi
|
|
if [ $is_quoted -eq 1 ]; then
|
|
qarg="$qarg $arg"
|
|
if [[ "$arg" == "\"" ]] || [[ $arg != ${arg%\"} ]]; then
|
|
is_quoted=0
|
|
arg=${qarg%\"}
|
|
qarg=""
|
|
else
|
|
shift
|
|
continue
|
|
fi
|
|
fi
|
|
dracut_args+=("$arg")
|
|
shift
|
|
done
|
|
}
|
|
|
|
add_dracut_module() {
|
|
add_dracut_arg "--add" "$1"
|
|
}
|
|
|
|
add_dracut_mount() {
|
|
add_dracut_arg "--mount" "$1"
|
|
}
|
|
|
|
add_dracut_sshkey() {
|
|
add_dracut_arg "--sshkey" "$1"
|
|
}
|
|
|
|
# Generic substring function. If $2 is in $1, return 0.
|
|
strstr() { [[ $1 =~ $2 ]]; }
|
|
|
|
target_is_root() {
|
|
local _t
|
|
_t=$(findmnt -k -n -r -o TARGET $1|sort|head -1)
|
|
[ "$_t" = "/" ]
|
|
}
|
|
|
|
# caller should ensure $1 is valid and mounted in 1st kernel
|
|
to_mount() {
|
|
local _dev=$1 _source _target _fstype _options _mntopts _pdev
|
|
|
|
_source=$(findmnt -k -f -n -r -o SOURCE $_dev)
|
|
_target=$(findmnt -k -f -n -r -o TARGET $_dev)
|
|
# mount under /sysroot in 2nd kernel, and we umount -R /sysroot before exit
|
|
_target="/sysroot$_target"
|
|
_fstype=$(findmnt -k -f -n -r -o FSTYPE $_dev)
|
|
_options=$(findmnt -k -f -n -r -o OPTIONS $_dev)
|
|
_options=${_options/#ro/rw} #mount fs target as rw in 2nd kernel
|
|
# "x-initrd.mount" mount failure will trigger isolate emergency service
|
|
# W/o this, systemd won't isolate, thus we won't get to emergency.
|
|
# This is not applicable to remote fs mount, because if we use
|
|
# "x-initrd.mount", remote mount will become required by
|
|
# "initrd-root-fs.target", instead of "remote-fs.target". That's how it is
|
|
# handled within systemd internal. We need remote mount to be required
|
|
# "remote-fs.target", because we need to bring up network before any remote
|
|
# mount and "remote-fs.target" can be a checkpoint of that.
|
|
# If remote mount fails, dracut-initqueue will still start and once
|
|
# dracut-initqueue finishes, kdump service will start. Because remote mount
|
|
# failed, kdump service will fail and it will lead to kdump error handler.
|
|
if ! is_nfs_dump_target; then
|
|
_options="$_options,x-initrd.mount"
|
|
fi
|
|
_mntopts="$_target $_fstype $_options"
|
|
#for non-nfs _dev converting to use udev persistent name
|
|
if [ -b "$_source" ]; then
|
|
_pdev="$(get_persistent_dev $_source)"
|
|
if [ $? -ne 0 ]; then
|
|
return 1
|
|
fi
|
|
|
|
else
|
|
_pdev=$_dev
|
|
fi
|
|
|
|
echo "$_pdev $_mntopts"
|
|
}
|
|
|
|
to_mount_point() {
|
|
echo $(findmnt -k -f -n -r -o TARGET $1)
|
|
}
|
|
|
|
is_readonly_mount() {
|
|
local _mnt
|
|
_mnt=$(findmnt -k -f -n -r -o OPTIONS $1)
|
|
|
|
#fs/proc_namespace.c: show_mountinfo():
|
|
#seq_puts(m, mnt->mnt_flags & MNT_READONLY ? " ro" : " rw");
|
|
[[ "$_mnt" =~ ^ro ]]
|
|
}
|
|
|
|
#Function: get_ssh_size
|
|
#$1=dump target
|
|
#called from while loop and shouldn't read from stdin, so we're using "ssh -n"
|
|
get_ssh_size() {
|
|
local _opt _out _size
|
|
_opt="-i $SSH_KEY_LOCATION -o BatchMode=yes -o StrictHostKeyChecking=yes"
|
|
_out=$(ssh -q -n $_opt $1 "df -P $SAVE_PATH")
|
|
[ $? -ne 0 ] && {
|
|
perror_exit "checking remote ssh server available size failed."
|
|
}
|
|
|
|
#ssh output removed the line break, so print field NF-2
|
|
_size=$(echo -n $_out| awk '{avail=NF-2; print $avail}')
|
|
echo -n $_size
|
|
}
|
|
|
|
#mkdir if save path does not exist on ssh dump target
|
|
#$1=ssh dump target
|
|
#caller should ensure write permission on $DUMP_TARGET:$SAVE_PATH
|
|
#called from while loop and shouldn't read from stdin, so we're using "ssh -n"
|
|
mkdir_save_path_ssh()
|
|
{
|
|
local _opt _dir
|
|
_opt="-i $SSH_KEY_LOCATION -o BatchMode=yes -o StrictHostKeyChecking=yes"
|
|
ssh -qn $_opt $1 mkdir -p $SAVE_PATH 2>&1 > /dev/null
|
|
_ret=$?
|
|
if [ $_ret -ne 0 ]; then
|
|
perror_exit "mkdir failed on $DUMP_TARGET:$SAVE_PATH"
|
|
fi
|
|
|
|
#check whether user has write permission on $SAVE_PATH/$DUMP_TARGET
|
|
_dir=$(ssh -qn $_opt $1 mktemp -dqp $SAVE_PATH 2>/dev/null)
|
|
_ret=$?
|
|
if [ $_ret -ne 0 ]; then
|
|
perror_exit "Could not create temporary directory on $DUMP_TARGET:$SAVE_PATH. Make sure user has write permission on destination"
|
|
fi
|
|
ssh -qn $_opt $1 rmdir $_dir
|
|
|
|
return 0
|
|
}
|
|
|
|
#Function: get_fs_size
|
|
#$1=dump target
|
|
get_fs_size() {
|
|
local _mnt=$(to_mount_point $1)
|
|
echo -n $(df -P "${_mnt}/$SAVE_PATH"|tail -1|awk '{print $4}')
|
|
}
|
|
|
|
#Function: get_raw_size
|
|
#$1=dump target
|
|
get_raw_size() {
|
|
echo -n $(fdisk -s "$1")
|
|
}
|
|
|
|
#Function: check_size
|
|
#$1: dump type string ('raw', 'fs', 'ssh')
|
|
#$2: dump target
|
|
check_size() {
|
|
local avail memtotal
|
|
|
|
memtotal=$(awk '/MemTotal/{print $2}' /proc/meminfo)
|
|
case "$1" in
|
|
raw)
|
|
avail=$(get_raw_size "$2")
|
|
;;
|
|
ssh)
|
|
avail=$(get_ssh_size "$2")
|
|
;;
|
|
fs)
|
|
avail=$(get_fs_size "$2")
|
|
;;
|
|
*)
|
|
return
|
|
esac
|
|
|
|
if [ $? -ne 0 ]; then
|
|
perror_exit "Check dump target size failed"
|
|
fi
|
|
|
|
if [ $avail -lt $memtotal ]; then
|
|
echo "Warning: There might not be enough space to save a vmcore."
|
|
echo " The size of $2 should be greater than $memtotal kilo bytes."
|
|
fi
|
|
}
|
|
|
|
# $1: core_collector config value
|
|
verify_core_collector() {
|
|
if grep -q "^raw" $conf_file && [ "${1%% *}" != "makedumpfile" ]; then
|
|
echo "Warning: specifying a non-makedumpfile core collector, you will have to recover the vmcore manually."
|
|
fi
|
|
if is_ssh_dump_target || is_raw_dump_target; then
|
|
if [ "${1%% *}" = "makedumpfile" ]; then
|
|
! strstr "$1" "-F" && {
|
|
perror_exit "The specified dump target needs makedumpfile \"-F\" option."
|
|
}
|
|
fi
|
|
fi
|
|
}
|
|
|
|
add_mount() {
|
|
if ! target_is_root "$1"; then
|
|
local _mnt=$(to_mount "$1")
|
|
if [ $? -ne 0 ]; then
|
|
exit 1
|
|
fi
|
|
add_dracut_mount "$_mnt"
|
|
fi
|
|
}
|
|
|
|
# get_maj_min <device>
|
|
# Prints the major and minor of a device node.
|
|
# Example:
|
|
# $ get_maj_min /dev/sda2
|
|
# 8:2
|
|
get_maj_min() {
|
|
local _dev
|
|
_dev=$(stat -L -c '$((0x%t)):$((0x%T))' "$1" 2>/dev/null)
|
|
_dev=$(eval "echo $_dev")
|
|
echo $_dev
|
|
}
|
|
|
|
# ugly workaround for the lvm design
|
|
# There is no volume group device,
|
|
# so, there are no slave devices for volume groups.
|
|
# Logical volumes only have the slave devices they really live on,
|
|
# but you cannot create the logical volume without the volume group.
|
|
# And the volume group might be bigger than the devices the LV needs.
|
|
check_vol_slaves() {
|
|
local _lv _vg _pv
|
|
for i in /dev/mapper/*; do
|
|
_lv=$(get_maj_min $i)
|
|
if [[ $_lv = $2 ]]; then
|
|
_vg=$(lvm lvs --noheadings -o vg_name $i 2>/dev/null)
|
|
# strip space
|
|
_vg=$(echo $_vg)
|
|
if [[ $_vg ]]; then
|
|
for _pv in $(lvm vgs --noheadings -o pv_name "$_vg" 2>/dev/null)
|
|
do
|
|
check_block_and_slaves $1 $(get_maj_min $_pv) && return 0
|
|
done
|
|
fi
|
|
fi
|
|
done
|
|
return 1
|
|
}
|
|
|
|
# Walk all the slave relationships for a given block device.
|
|
# Stop when our helper function returns success
|
|
# $1 = function to call on every found block device
|
|
# $2 = block device in major:minor format
|
|
check_block_and_slaves() {
|
|
local _x
|
|
[[ -b /dev/block/$2 ]] || return 1 # Not a block device? So sorry.
|
|
"$1" $2 && return
|
|
check_vol_slaves "$@" && return 0
|
|
if [[ -f /sys/dev/block/$2/../dev ]]; then
|
|
check_block_and_slaves $1 $(cat "/sys/dev/block/$2/../dev") && return 0
|
|
fi
|
|
[[ -d /sys/dev/block/$2/slaves ]] || return 1
|
|
for _x in /sys/dev/block/$2/slaves/*/dev; do
|
|
[[ -f $_x ]] || continue
|
|
check_block_and_slaves $1 $(cat "$_x") && return 0
|
|
done
|
|
return 1
|
|
}
|
|
|
|
to_dev_name() {
|
|
local dev="${1//\"/}"
|
|
|
|
case "$dev" in
|
|
UUID=*)
|
|
dev=`blkid -U "${dev#UUID=}"`
|
|
;;
|
|
LABEL=*)
|
|
dev=`blkid -L "${dev#LABEL=}"`
|
|
;;
|
|
esac
|
|
echo $dev
|
|
}
|
|
|
|
get_block_dump_target()
|
|
{
|
|
local _target
|
|
|
|
|
|
_target=$(get_user_configured_dump_disk)
|
|
[ -n "$_target" ] && echo $(to_dev_name $_target) && return
|
|
|
|
#get rootfs device name
|
|
_target=$(get_root_fs_device)
|
|
[ -b "$_target" ] && echo $(to_dev_name $_target)
|
|
}
|
|
|
|
#handle the case user does not specify the dump target explicitly
|
|
handle_default_dump_target()
|
|
{
|
|
local _target
|
|
local _mntpoint
|
|
local _fstype
|
|
|
|
is_user_configured_dump_target && return
|
|
|
|
check_save_path_fs $SAVE_PATH
|
|
|
|
_mntpoint=$(get_mntpoint_from_path $SAVE_PATH)
|
|
_target=$(get_target_from_path $SAVE_PATH)
|
|
if [ "$_mntpoint" != "/" ]; then
|
|
SAVE_PATH=${SAVE_PATH##"$_mntpoint"}
|
|
_fstype=$(get_fs_type_from_target $_target)
|
|
|
|
if $(is_fs_type_nfs $_fstype); then
|
|
add_dracut_module "nfs"
|
|
fi
|
|
|
|
add_mount "$_target"
|
|
check_size fs $_target
|
|
fi
|
|
}
|
|
|
|
get_default_action_target()
|
|
{
|
|
local _target
|
|
local _action=$(grep "^default" /etc/kdump.conf 2>/dev/null | awk '{print $2}')
|
|
if [ -n "$_action" ] && [ "$_action" = "dump_to_rootfs" ]; then
|
|
#get rootfs device name
|
|
_target=$(findmnt -k -f -n -o SOURCE /)
|
|
[ -b "$_target" ] && echo $(to_dev_name $_target)
|
|
fi
|
|
return
|
|
}
|
|
|
|
get_override_resettable()
|
|
{
|
|
local override_resettable
|
|
|
|
override_resettable=$(grep "^override_resettable" $conf_file)
|
|
if [ -n "$override_resettable" ]; then
|
|
OVERRIDE_RESETTABLE=$(echo $override_resettable | cut -d' ' -f2)
|
|
if [ "$OVERRIDE_RESETTABLE" != "0" ] && [ "$OVERRIDE_RESETTABLE" != "1" ];then
|
|
perror_exit "override_resettable value $OVERRIDE_RESETTABLE is invalid"
|
|
fi
|
|
fi
|
|
}
|
|
|
|
|
|
# $1: function name
|
|
for_each_block_target()
|
|
{
|
|
local dev majmin
|
|
|
|
#check dump target
|
|
dev=$(get_block_dump_target)
|
|
|
|
if [ -n "$dev" ]; then
|
|
majmin=$(get_maj_min $dev)
|
|
check_block_and_slaves $1 $majmin && return 1
|
|
fi
|
|
|
|
#check rootfs when default action dump_to_rootfs is set
|
|
dev=$(get_default_action_target)
|
|
if [ -n "$dev" ]; then
|
|
majmin=$(get_maj_min $dev)
|
|
check_block_and_slaves $1 $majmin && return 2
|
|
fi
|
|
|
|
return 0
|
|
}
|
|
|
|
|
|
|
|
#judge if a specific device with $1 is unresettable
|
|
#return false if unresettable.
|
|
is_unresettable()
|
|
{
|
|
local path="/sys/$(udevadm info --query=all --path=/sys/dev/block/$1 | awk '/^P:/ {print $2}' | sed -e 's/\(cciss[0-9]\+\/\).*/\1/g' -e 's/\/block\/.*$//')/resettable"
|
|
local resettable=1
|
|
|
|
if [ -f "$path" ]
|
|
then
|
|
resettable="$(cat $path)"
|
|
[ $resettable -eq 0 -a "$OVERRIDE_RESETTABLE" -eq 0 ] && {
|
|
local device=$(udevadm info --query=all --path=/sys/dev/block/$1 | awk -F= '/DEVNAME/{print $2}')
|
|
echo "Device $device is unresettable"
|
|
return 0
|
|
}
|
|
fi
|
|
|
|
return 1
|
|
}
|
|
|
|
#check if machine is resettable.
|
|
#return true if resettable
|
|
check_resettable()
|
|
{
|
|
local _ret _target
|
|
|
|
get_override_resettable
|
|
|
|
for_each_block_target is_unresettable
|
|
_ret=$?
|
|
|
|
[ $_ret -eq 0 ] && return
|
|
|
|
if [ $_ret -eq 1 ]; then
|
|
_target=$(get_block_dump_target)
|
|
perror "Can not save vmcore to target device $_target . This device can not be initialized in kdump kernel as it is not resettable"
|
|
elif [ $_ret -eq 2 ]; then
|
|
_target=$(get_default_action_target)
|
|
perror "Rootfs device $_target is not resettable, can not be used as the default target, please specify a default action"
|
|
fi
|
|
|
|
return 1
|
|
}
|
|
|
|
# $1: maj:min
|
|
is_crypt()
|
|
{
|
|
local majmin=$1 dev line ID_FS_TYPE=""
|
|
|
|
line=$(udevadm info --query=property --path=/sys/dev/block/$majmin \
|
|
| grep "^ID_FS_TYPE")
|
|
eval "$line"
|
|
[[ "$ID_FS_TYPE" = "crypto_LUKS" ]] && {
|
|
dev=$(udevadm info --query=all --path=/sys/dev/block/$majmin | awk -F= '/DEVNAME/{print $2}')
|
|
echo "Device $dev is encrypted."
|
|
return 0
|
|
}
|
|
return 1
|
|
}
|
|
|
|
check_crypt()
|
|
{
|
|
local _ret _target
|
|
|
|
for_each_block_target is_crypt
|
|
_ret=$?
|
|
|
|
[ $_ret -eq 0 ] && return
|
|
|
|
return 1
|
|
}
|
|
|
|
if ! check_resettable; then
|
|
exit 1
|
|
fi
|
|
|
|
if ! check_crypt; then
|
|
echo "Warning: Encrypted device is in dump path. User will prompted for password during second kernel boot."
|
|
fi
|
|
|
|
# firstly get right SSH_KEY_LOCATION
|
|
keyfile=$(awk '/^sshkey/ {print $2}' $conf_file)
|
|
if [ -f "$keyfile" ]; then
|
|
# canonicalize the path
|
|
SSH_KEY_LOCATION=$(/usr/bin/readlink -m $keyfile)
|
|
fi
|
|
|
|
if [ "$(uname -m)" = "s390x" ]; then
|
|
add_dracut_module "znet"
|
|
fi
|
|
|
|
while read config_opt config_val;
|
|
do
|
|
# remove inline comments after the end of a directive.
|
|
config_val=$(strip_comments $config_val)
|
|
case "$config_opt" in
|
|
extra_modules)
|
|
extra_modules="$extra_modules $config_val"
|
|
;;
|
|
ext[234]|xfs|btrfs|minix|nfs)
|
|
if ! findmnt $config_val >/dev/null; then
|
|
perror_exit "Dump target $config_val is probably not mounted."
|
|
fi
|
|
|
|
if [ "$config_opt" = "nfs" ]; then
|
|
add_dracut_module "nfs"
|
|
fi
|
|
add_mount "$config_val"
|
|
check_save_path_fs $(make_absolute_save_path $config_val)
|
|
check_size fs $config_val
|
|
;;
|
|
raw)
|
|
#checking raw disk writable
|
|
dd if=$config_val count=1 of=/dev/null > /dev/null 2>&1 || {
|
|
perror_exit "Bad raw disk $config_val"
|
|
}
|
|
_praw=$(get_persistent_dev $config_val)
|
|
if [ $? -ne 0 ]; then
|
|
exit 1
|
|
fi
|
|
add_dracut_arg "--device" "$_praw"
|
|
check_size raw $config_val
|
|
;;
|
|
ssh)
|
|
if strstr "$config_val" "@";
|
|
then
|
|
check_size ssh $config_val
|
|
mkdir_save_path_ssh $config_val
|
|
add_dracut_module "ssh-client"
|
|
add_dracut_sshkey "$SSH_KEY_LOCATION"
|
|
else
|
|
perror_exit "Bad ssh dump target $config_val"
|
|
fi
|
|
;;
|
|
core_collector)
|
|
verify_core_collector "$config_val"
|
|
;;
|
|
dracut_args)
|
|
add_dracut_arg $config_val
|
|
;;
|
|
*)
|
|
if [ -n $(echo $config_opt | grep "^#.*$") ]
|
|
then
|
|
continue
|
|
fi
|
|
;;
|
|
esac
|
|
done < $conf_file
|
|
|
|
handle_default_dump_target
|
|
|
|
if [ -n "$extra_modules" ]
|
|
then
|
|
add_dracut_arg "--add-drivers" "$extra_modules"
|
|
fi
|
|
|
|
dracut "${dracut_args[@]}" "$@"
|
|
_rc=$?
|
|
sync
|
|
exit $_rc
|