#!/bin/bash

KEXEC=/sbin/kexec

KDUMP_KERNELVER=""

KDUMP_KERNEL=""

KDUMP_COMMANDLINE=""

KEXEC_ARGS=""

KDUMP_LOG_PATH="/var/log"

MKDUMPRD="/sbin/mkdumprd -f"

MKFADUMPRD="/sbin/mkfadumprd"

DRACUT_MODULES_FILE="/usr/lib/dracut/modules.txt"

SAVE_PATH=/var/crash

SSH_KEY_LOCATION="/root/.ssh/kdump_id_rsa"

INITRD_CHECKSUM_LOCATION="/boot/.fadump_initrd_checksum"

DUMP_TARGET=""

DEFAULT_INITRD=""

DEFAULT_INITRD_BAK=""

KDUMP_INITRD=""

TARGET_INITRD=""

FADUMP_REGISTER_SYS_NODE="/sys/kernel/fadump_registered"

#kdump shall be the default dump mode

DEFAULT_DUMP_MODE="kdump"

image_time=0

standard_kexec_args="-d -p"

# Some default values in case /etc/sysconfig/kdump doesn't include

KDUMP_COMMANDLINE_REMOVE="hugepages hugepagesz slub_debug"

if [[ -f /etc/sysconfig/kdump ]]; then

	. /etc/sysconfig/kdump

fi

[[ $dracutbasedir ]] || dracutbasedir=/usr/lib/dracut

. $dracutbasedir/dracut-functions.sh

. /lib/kdump/kdump-lib.sh

. /lib/kdump/kdump-logger.sh

#initiate the kdump logger

if ! dlog_init; then

	echo "failed to initiate the kdump logger."

	exit 1

fi

single_instance_lock()

{

	local rc timeout=5

	if ! exec 9> /var/lock/kdump; then

		derror "Create file lock failed"

		exit 1

	fi

	flock -n 9

	rc=$?

	while [[ $rc -ne 0 ]]; do

		dinfo "Another app is currently holding the kdump lock; waiting for it to exit..."

		flock -w $timeout 9

		rc=$?

	done

}

determine_dump_mode()

{

	# Check if firmware-assisted dump is enabled

	# if yes, set the dump mode as fadump

	if is_fadump_capable; then

		dinfo "Dump mode is fadump"

		DEFAULT_DUMP_MODE="fadump"

	fi

	ddebug "DEFAULT_DUMP_MODE=$DEFAULT_DUMP_MODE"

}

save_core()

{

	coredir="/var/crash/$(date +"%Y-%m-%d-%H:%M")"

	mkdir -p "$coredir"

	ddebug "cp --sparse=always /proc/vmcore $coredir/vmcore-incomplete"

	if cp --sparse=always /proc/vmcore "$coredir/vmcore-incomplete"; then

		mv "$coredir/vmcore-incomplete" "$coredir/vmcore"

		dinfo "saved a vmcore to $coredir"

	else

		derror "failed to save a vmcore to $coredir"

	fi

	# pass the dmesg to Abrt tool if exists, in order

	# to collect the kernel oops message.

	# https://fedorahosted.org/abrt/

	if [[ -x /usr/bin/dumpoops ]]; then

		ddebug "makedumpfile --dump-dmesg $coredir/vmcore $coredir/dmesg"

		makedumpfile --dump-dmesg "$coredir/vmcore" "$coredir/dmesg" > /dev/null 2>&1

		ddebug "dumpoops -d $coredir/dmesg"

		if dumpoops -d "$coredir/dmesg" > /dev/null 2>&1; then

			dinfo "kernel oops has been collected by abrt tool"

		fi

	fi

}

rebuild_fadump_initrd()

{

	if ! $MKFADUMPRD "$DEFAULT_INITRD_BAK" "$TARGET_INITRD" --kver "$KDUMP_KERNELVER"; then

		derror "mkfadumprd: failed to make fadump initrd"

		return 1

	fi

	return 0

}

check_earlykdump_is_enabled()

{

	grep -q -w "rd.earlykdump" /proc/cmdline

	return $?

}

rebuild_kdump_initrd()

{

	ddebug "rebuild kdump initrd: $MKDUMPRD $TARGET_INITRD $KDUMP_KERNELVER"

	if ! $MKDUMPRD "$TARGET_INITRD" "$KDUMP_KERNELVER"; then

		derror "mkdumprd: failed to make kdump initrd"

		return 1

	fi

	if check_earlykdump_is_enabled; then

		dwarn "Tips: If early kdump is enabled, also require rebuilding the system initramfs to make the changes take effect for early kdump."

	fi

	return 0

}

rebuild_initrd()

{

	if [[ ! -w $(dirname "$TARGET_INITRD") ]]; then

		derror "$(dirname "$TARGET_INITRD") does not have write permission. Cannot rebuild $TARGET_INITRD"

		return 1

	fi

	if [[ $DEFAULT_DUMP_MODE == "fadump" ]]; then

		rebuild_fadump_initrd

	else

		rebuild_kdump_initrd

	fi

	return $?

}

#$1: the files to be checked with IFS=' '

check_exist()

{

	for file in $1; do

		if [[ ! -e $file ]]; then

			derror "Error: $file not found."

			return 1

		fi

	done

}

#$1: the files to be checked with IFS=' '

check_executable()

{

	for file in $1; do

		if [[ ! -x $file ]]; then

			derror "Error: $file is not executable."

			return 1

		fi

	done

}

backup_default_initrd()

{

	ddebug "backup default initrd: $DEFAULT_INITRD"

	if [[ ! -f $DEFAULT_INITRD ]]; then

		return

	fi

	if [[ ! -e $DEFAULT_INITRD_BAK ]]; then

		dinfo "Backing up $DEFAULT_INITRD before rebuild."

		# save checksum to verify before restoring

		sha1sum "$DEFAULT_INITRD" > "$INITRD_CHECKSUM_LOCATION"

		if ! cp "$DEFAULT_INITRD" "$DEFAULT_INITRD_BAK"; then

			dwarn "WARNING: failed to backup $DEFAULT_INITRD."

			rm -f "$DEFAULT_INITRD_BAK"

		fi

	fi

}

restore_default_initrd()

{

	ddebug "restore default initrd: $DEFAULT_INITRD"

	if [[ ! -f $DEFAULT_INITRD ]]; then

		return

	fi

	# If a backup initrd exists, we must be switching back from

	# fadump to kdump. Restore the original default initrd.

	if [[ -f $DEFAULT_INITRD_BAK ]] && [[ -f $INITRD_CHECKSUM_LOCATION ]]; then

		# verify checksum before restoring

		backup_checksum=$(sha1sum "$DEFAULT_INITRD_BAK" | awk '{ print $1 }')

		default_checksum=$(awk '{ print $1 }' "$INITRD_CHECKSUM_LOCATION")

		if [[ $default_checksum != "$backup_checksum" ]]; then

			dwarn "WARNING: checksum mismatch! Can't restore original initrd.."

		else

			rm -f $INITRD_CHECKSUM_LOCATION

			if mv "$DEFAULT_INITRD_BAK" "$DEFAULT_INITRD"; then

				derror "Restoring original initrd as fadump mode is disabled."

				sync

			fi

		fi

	fi

}

check_config()

{

	local -A _opt_rec

	while read -r config_opt config_val; do

		case "$config_opt" in

		dracut_args)

			if [[ $config_val == *--mount* ]]; then

				if [[ $(echo "$config_val" | grep -o "\-\-mount" | wc -l) -ne 1 ]]; then

					derror 'Multiple mount targets specified in one "dracut_args".'

					return 1

				fi

				config_opt=_target

			fi

			;;

		raw)

			if [[ -d "/proc/device-tree/ibm,opal/dump" ]]; then

				dwarn "WARNING: Won't capture opalcore when 'raw' dump target is used."

			fi

			config_opt=_target

			;;

		ext[234] | minix | btrfs | xfs | nfs | ssh)

			config_opt=_target

			;;

		sshkey | path | core_collector | kdump_post | kdump_pre | extra_bins | extra_modules | failure_action | default | final_action | force_rebuild | force_no_rebuild | fence_kdump_args | fence_kdump_nodes) ;;

		net | options | link_delay | disk_timeout | debug_mem_level | blacklist)

			derror "Deprecated kdump config option: $config_opt. Refer to kdump.conf manpage for alternatives."

			return 1

			;;

		'')

			continue

			;;

		*)

			derror "Invalid kdump config option $config_opt"

			return 1

			;;

		esac

		if [[ -z $config_val ]]; then

			derror "Invalid kdump config value for option '$config_opt'"

			return 1

		fi

		if [[ -n ${_opt_rec[$config_opt]} ]]; then

			if [[ $config_opt == _target ]]; then

				derror "More than one dump targets specified"

			else

				derror "Duplicated kdump config value of option $config_opt"

			fi

			return 1

		fi

		_opt_rec[$config_opt]="$config_val"

	done <<< "$(kdump_read_conf)"

	check_failure_action_config || return 1

	check_final_action_config || return 1

	check_fence_kdump_config || return 1

	return 0

}

# get_pcs_cluster_modified_files <image timestamp>

# return list of modified file for fence_kdump modified in Pacemaker cluster

get_pcs_cluster_modified_files()

{

	local time_stamp

	local modified_files

	is_generic_fence_kdump && return 1

	is_pcs_fence_kdump || return 1

	time_stamp=$(pcs cluster cib | xmllint --xpath 'string(/cib/@cib-last-written)' - | xargs -0 date +%s --date)

	if [[ -n $time_stamp ]] && [[ $time_stamp -gt $image_time ]]; then

		modified_files="cluster-cib"

	fi

	if [[ -f $FENCE_KDUMP_CONFIG_FILE ]]; then

		time_stamp=$(stat -c "%Y" "$FENCE_KDUMP_CONFIG_FILE")

		if [[ $time_stamp -gt $image_time ]]; then

			modified_files="$modified_files $FENCE_KDUMP_CONFIG_FILE"

		fi

	fi

	echo "$modified_files"

}

setup_initrd()

{

	if ! prepare_kdump_bootinfo; then

		derror "failed to prepare for kdump bootinfo."

		return 1

	fi

	DEFAULT_INITRD_BAK="$KDUMP_BOOTDIR/.$(basename "$DEFAULT_INITRD").default"

	if [[ $DEFAULT_DUMP_MODE == "fadump" ]]; then

		TARGET_INITRD="$DEFAULT_INITRD"

		# backup initrd for reference before replacing it

		# with fadump aware initrd

		backup_default_initrd

	else

		TARGET_INITRD="$KDUMP_INITRD"

		# check if a backup of default initrd exists. If yes,

		# it signifies a switch from fadump mode. So, restore

		# the backed up default initrd.

		restore_default_initrd

	fi

}

check_files_modified()

{

	local modified_files=""

	#also rebuild when Pacemaker cluster conf is changed and fence kdump is enabled.

	modified_files=$(get_pcs_cluster_modified_files)

	EXTRA_BINS=$(kdump_get_conf_val kdump_post)

	CHECK_FILES=$(kdump_get_conf_val kdump_pre)

	HOOKS="/etc/kdump/post.d/ /etc/kdump/pre.d/"

	if [[ -d /etc/kdump/post.d ]]; then

		for file in /etc/kdump/post.d/*; do

			if [[ -x $file ]]; then

				POST_FILES="$POST_FILES $file"

			fi

		done

	fi

	if [[ -d /etc/kdump/pre.d ]]; then

		for file in /etc/kdump/pre.d/*; do

			if [[ -x $file ]]; then

				PRE_FILES="$PRE_FILES $file"

			fi

		done

	fi

	HOOKS="$HOOKS $POST_FILES $PRE_FILES"

	CORE_COLLECTOR=$(kdump_get_conf_val core_collector | awk '{print $1}')

	CORE_COLLECTOR=$(type -P "$CORE_COLLECTOR")

	# POST_FILES and PRE_FILES are already checked against executable, need not to check again.

	EXTRA_BINS="$EXTRA_BINS $CHECK_FILES"

	CHECK_FILES=$(kdump_get_conf_val extra_bins)

	EXTRA_BINS="$EXTRA_BINS $CHECK_FILES"

	files="$KDUMP_CONFIG_FILE $KDUMP_KERNEL $EXTRA_BINS $CORE_COLLECTOR"

	[[ -e /etc/fstab ]] && files="$files /etc/fstab"

	# Check for any updated extra module

	EXTRA_MODULES="$(kdump_get_conf_val extra_modules)"

	if [[ -n $EXTRA_MODULES ]]; then

		if [[ -e /lib/modules/$KDUMP_KERNELVER/modules.dep ]]; then

			files="$files /lib/modules/$KDUMP_KERNELVER/modules.dep"

		fi

		for _module in $EXTRA_MODULES; do

			if _module_file="$(modinfo --set-version "$KDUMP_KERNELVER" --filename "$_module" 2> /dev/null)"; then

				files="$files $_module_file"

				for _dep_modules in $(modinfo -F depends "$_module" | tr ',' ' '); do

					files="$files $(modinfo --set-version "$KDUMP_KERNELVER" --filename "$_dep_modules" 2> /dev/null)"

				done

			else

				# If it's not a module nor builtin, give an error

				if ! (modprobe --set-version "$KDUMP_KERNELVER" --dry-run "$_module" &> /dev/null); then

					dwarn "Module $_module not found"

				fi

			fi

		done

	fi

	# HOOKS is mandatory and need to check the modification time

	files="$files $HOOKS"

	check_exist "$files" && check_executable "$EXTRA_BINS" || return 2

	for file in $files; do

		if [[ -e $file ]]; then

			time_stamp=$(stat -c "%Y" "$file")

			if [[ $time_stamp -gt $image_time ]]; then

				modified_files="$modified_files $file"

			fi

			if [[ -L $file ]]; then

				file=$(readlink -m "$file")

				time_stamp=$(stat -c "%Y" "$file")

				if [[ $time_stamp -gt $image_time ]]; then

					modified_files="$modified_files $file"

				fi

			fi

		else

			dwarn "$file doesn't exist"

		fi

	done

	if [[ -n $modified_files ]]; then

		dinfo "Detected change(s) in the following file(s): $modified_files"

		return 1

	fi

	return 0

}

check_drivers_modified()

{

	local _target _new_drivers _old_drivers _module_name _module_filename

	# If it's dump target is on block device, detect the block driver

	_target=$(get_block_dump_target)

	if [[ -n $_target ]]; then

		_record_block_drivers()

		{

			local _drivers

			_drivers=$(udevadm info -a "/dev/block/$1" | sed -n 's/\s*DRIVERS=="\(\S\+\)"/\1/p')

			for _driver in $_drivers; do

				if ! [[ " $_new_drivers " == *" $_driver "* ]]; then

					_new_drivers="$_new_drivers $_driver"

				fi

			done

			ddebug "MAJ:MIN=$1 drivers='$_drivers'"

		}

		check_block_and_slaves_all _record_block_drivers "$(get_maj_min "$_target")"

	fi

	# Include watchdog drivers if watchdog module is not omitted

	is_dracut_mod_omitted watchdog || _new_drivers+=" $(get_watchdog_drvs)"

	[[ -z $_new_drivers ]] && return 0

	if is_fadump_capable; then

		_old_drivers="$(lsinitrd "$TARGET_INITRD" -f /usr/lib/dracut/fadump-kernel-modules.txt | tr '\n' ' ')"

	else

		_old_drivers="$(lsinitrd "$TARGET_INITRD" -f /usr/lib/dracut/hostonly-kernel-modules.txt | tr '\n' ' ')"

	fi

	ddebug "Modules required for kdump: '$_new_drivers'"

	ddebug "Modules included in old initramfs: '$_old_drivers'"

	for _driver in $_new_drivers; do

		# Skip deprecated/invalid driver name or built-in module

		_module_name=$(modinfo --set-version "$KDUMP_KERNELVER" -F name "$_driver" 2> /dev/null)

		_module_filename=$(modinfo --set-version "$KDUMP_KERNELVER" -n "$_driver" 2> /dev/null)

		if [[ -z $_module_name ]] || [[ -z $_module_filename ]] || [[ $_module_filename == *"(builtin)"* ]]; then

			continue

		fi

		if ! [[ " $_old_drivers " == *" $_module_name "* ]]; then

			dinfo "Detected change in block device driver, new loaded module: $_module_name"

			return 1

		fi

	done

}

check_fs_modified()

{

	local _old_dev _old_mntpoint _old_fstype

	local _new_dev _new_mntpoint _new_fstype

	local _target _dracut_args

	# No need to check in case of mount target specified via "dracut_args".

	if is_mount_in_dracut_args; then

		return 0

	fi

	# No need to check in case of raw target.

	# Currently we do not check also if ssh/nfs target is specified

	if is_ssh_dump_target || is_nfs_dump_target || is_raw_dump_target; then

		return 0

	fi

	_target=$(get_block_dump_target)

	_new_fstype=$(get_fs_type_from_target "$_target")

	if [[ -z $_target ]] || [[ -z $_new_fstype ]]; then

		derror "Dump target is invalid"

		return 2

	fi

	ddebug "_target=$_target _new_fstype=$_new_fstype"

	_new_dev=$(kdump_get_persistent_dev "$_target")

	if [[ -z $_new_dev ]]; then

		perror "Get persistent device name failed"

		return 2

	fi

	_new_mntpoint="$(get_kdump_mntpoint_from_target "$_target")"

	_dracut_args=$(lsinitrd "$TARGET_INITRD" -f usr/lib/dracut/build-parameter.txt)

	if [[ -z $_dracut_args ]]; then

		dwarn "Warning: No dracut arguments found in initrd"

		return 0

	fi

	# if --mount argument present then match old and new target, mount

	# point and file system. If any of them mismatches then rebuild

	if echo "$_dracut_args" | grep -q "\-\-mount"; then

		# shellcheck disable=SC2046

		set -- $(echo "$_dracut_args" | awk -F "--mount '" '{print $2}' | cut -d' ' -f1,2,3)

		_old_dev=$1

		_old_mntpoint=$2

		_old_fstype=$3

		[[ $_new_dev == "$_old_dev" && $_new_mntpoint == "$_old_mntpoint" && $_new_fstype == "$_old_fstype" ]] && return 0

	# otherwise rebuild if target device is not a root device

	else

		[[ $_target == "$(get_root_fs_device)" ]] && return 0

	fi

	dinfo "Detected change in File System"

	return 1

}

# returns 0 if system is not modified

# returns 1 if system is modified

# returns 2 if system modification is invalid

check_system_modified()

{

	local ret

	[[ -f $TARGET_INITRD ]] || return 1

	check_files_modified

	ret=$?

	if [[ $ret -ne 0 ]]; then

		return $ret

	fi

	check_fs_modified

	ret=$?

	if [[ $ret -ne 0 ]]; then

		return $ret

	fi

	check_drivers_modified

	ret=$?

	if [[ $ret -ne 0 ]]; then

		return $ret

	fi

	return 0

}

check_rebuild()

{

	local capture_capable_initrd="1"

	local force_rebuild force_no_rebuild

	local ret system_modified="0"

	setup_initrd || return 1

	force_no_rebuild=$(kdump_get_conf_val force_no_rebuild)

	force_no_rebuild=${force_no_rebuild:-0}

	if [[ $force_no_rebuild != "0" ]] && [[ $force_no_rebuild != "1" ]]; then

		derror "Error: force_no_rebuild value is invalid"

		return 1

	fi

	force_rebuild=$(kdump_get_conf_val force_rebuild)

	force_rebuild=${force_rebuild:-0}

	if [[ $force_rebuild != "0" ]] && [[ $force_rebuild != "1" ]]; then

		derror "Error: force_rebuild value is invalid"

		return 1

	fi

	if [[ $force_no_rebuild == "1" && $force_rebuild == "1" ]]; then

		derror "Error: force_rebuild and force_no_rebuild are enabled simultaneously in kdump.conf"

		return 1

	fi

	# Will not rebuild kdump initrd

	if [[ $force_no_rebuild == "1" ]]; then

		return 0

	fi

	#check to see if dependent files has been modified

	#since last build of the image file

	if [[ -f $TARGET_INITRD ]]; then

		image_time=$(stat -c "%Y" "$TARGET_INITRD" 2> /dev/null)

		#in case of fadump mode, check whether the default/target

		#initrd is already built with dump capture capability

		if [[ $DEFAULT_DUMP_MODE == "fadump" ]]; then

			capture_capable_initrd=$(lsinitrd -f $DRACUT_MODULES_FILE "$TARGET_INITRD" | grep -c -e ^kdumpbase$ -e ^zz-fadumpinit$)

		fi

	fi

	check_system_modified

	ret=$?

	if [[ $ret -eq 2 ]]; then

		return 1

	elif [[ $ret -eq 1 ]]; then

		system_modified="1"

	fi

	if [[ $image_time -eq 0 ]]; then

		dinfo "No kdump initial ramdisk found."

	elif [[ $capture_capable_initrd == "0" ]]; then

		dinfo "Rebuild $TARGET_INITRD with dump capture support"

	elif [[ $force_rebuild != "0" ]]; then

		dinfo "Force rebuild $TARGET_INITRD"

	elif [[ $system_modified != "0" ]]; then

		:

	else

		return 0

	fi

	dinfo "Rebuilding $TARGET_INITRD"

	rebuild_initrd

	return $?

}

# Load the kdump kernel specified in /etc/sysconfig/kdump

# If none is specified, try to load a kdump kernel with the same version

# as the currently running kernel.

load_kdump()

{

	local ret

	KEXEC_ARGS=$(prepare_kexec_args "${KEXEC_ARGS}")

	KDUMP_COMMANDLINE=$(prepare_cmdline "${KDUMP_COMMANDLINE}" "${KDUMP_COMMANDLINE_REMOVE}" "${KDUMP_COMMANDLINE_APPEND}")

	# For secureboot enabled machines, use new kexec file based syscall.

	# Old syscall will always fail as it does not have capability to

	# to kernel signature verification.

	if is_secure_boot_enforced; then

		dinfo "Secure Boot is enabled. Using kexec file based syscall."

		KEXEC_ARGS="$KEXEC_ARGS -s"

	fi

	ddebug "$KEXEC $KEXEC_ARGS $standard_kexec_args --command-line=$KDUMP_COMMANDLINE --initrd=$TARGET_INITRD $KDUMP_KERNEL"

	# The '12' represents an intermediate temporary file descriptor

	# to store the standard error file descriptor '2', and later

	# restore the error file descriptor with the file descriptor '12'

	# and release it.

	exec 12>&2

	exec 2>> $KDUMP_LOG_PATH/kdump.log

	PS4='+ $(date "+%Y-%m-%d %H:%M:%S") ${BASH_SOURCE}@${LINENO}: '

	set -x

	# shellcheck disable=SC2086

	$KEXEC $KEXEC_ARGS $standard_kexec_args \

		--command-line="$KDUMP_COMMANDLINE" \

		--initrd="$TARGET_INITRD" "$KDUMP_KERNEL"

	ret=$?

	set +x

	exec 2>&12 12>&-

	if [[ $ret == 0 ]]; then

		dinfo "kexec: loaded kdump kernel"

		return 0

	else

		derror "kexec: failed to load kdump kernel"

		return 1

	fi

}

check_ssh_config()

{

	local SSH_TARGET

	while read -r config_opt config_val; do

		case "$config_opt" in

		sshkey)

			# remove inline comments after the end of a directive.

			if [[ -f $config_val ]]; then

				# canonicalize the path

				SSH_KEY_LOCATION=$(/usr/bin/readlink -m "$config_val")

			else

				dwarn "WARNING: '$config_val' doesn't exist, using default value '$SSH_KEY_LOCATION'"

			fi

			;;

		path)

			SAVE_PATH=$config_val

			;;

		ssh)

			DUMP_TARGET=$config_val

			;;

		*) ;;

		esac

	done <<< "$(kdump_read_conf)"

	#make sure they've configured kdump.conf for ssh dumps

	SSH_TARGET=$(echo -n "$DUMP_TARGET" | sed -n '/.*@/p')

	if [[ -z $SSH_TARGET ]]; then

		return 1

	fi

	return 0

}

# ipv6 host address may takes a long time to be ready.

# Instead of checking against ipv6 address, we just check the network reachable

# by the return val of 'ssh'

check_and_wait_network_ready()

{

	local start_time

	local warn_once=1

	local cur

	local diff

	local retval

	local errmsg

	start_time=$(date +%s)

	while true; do

		errmsg=$(ssh -i "$SSH_KEY_LOCATION" -o BatchMode=yes "$DUMP_TARGET" mkdir -p "$SAVE_PATH" 2>&1)

		retval=$?

		# ssh exits with the exit status of the remote command or with 255 if an error occurred

		if [[ $retval -eq 0 ]]; then

			return 0

		elif [[ $retval -ne 255 ]]; then

			derror "Could not create $DUMP_TARGET:$SAVE_PATH, you should check the privilege on server side"

			return 1

		fi