kexec-tools/kdumpctl

#! /bin/sh
KEXEC=/sbin/kexec

KDUMP_KERNELVER=""
KDUMP_COMMANDLINE=""
KEXEC_ARGS=""
KDUMP_CONFIG_FILE="/etc/kdump.conf"
MKDUMPRD="/sbin/mkdumprd -f"
SAVE_PATH=/var/crash
SSH_KEY_LOCATION="/root/.ssh/kdump_id_rsa"
DUMP_TARGET=""

LOGGER="/usr/bin/logger -p info -t kdump"

standard_kexec_args="-p"

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

function save_core()
{
	coredir="/var/crash/`date +"%Y-%m-%d-%H:%M"`"

	mkdir -p $coredir
	cp --sparse=always /proc/vmcore $coredir/vmcore-incomplete
	if [ $? == 0 ]; then
		mv $coredir/vmcore-incomplete $coredir/vmcore
		$LOGGER "saved a vmcore to $coredir"
	else
		$LOGGER "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
		makedumpfile --dump-dmesg $coredir/vmcore $coredir/dmesg >/dev/null 2>&1
		dumpoops -d $coredir/dmesg >/dev/null 2>&1
		if [ $? == 0 ]; then
			$LOGGER "kernel oops has been collected by abrt tool"
		fi
	fi
}

function rebuild_initrd()
{
	$MKDUMPRD $kdump_initrd $kdump_kver
	if [ $? != 0 ]; then
		echo "Failed to run mkdumprd"
		$LOGGER "mkdumprd: failed to make kdump initrd"
		return 1
	fi
}

#$1: the files to be checked with IFS=' '
function check_exist()
{
	for file in $1; do
		if [ ! -f "$file" ]; then
			echo -n "Error: $file not found."; echo
			return 1
		fi
	done
}

#$1: the files to be checked with IFS=' '
function check_executable()
{
	for file in $1; do
		if [ ! -x "$file" ]; then
			echo -n "Error: $file is not executable."; echo
			return 1
		fi
	done
}

function check_config()
{
	local extra_modules modified_files=""
	local force_rebuild=0

	if [ -z "$KDUMP_KERNELVER" ]; then
		kdump_kver=`uname -r`
	else
		kdump_kver=$KDUMP_KERNELVER
	fi

	kdump_kernel="${KDUMP_BOOTDIR}/${KDUMP_IMG}-${kdump_kver}${KDUMP_IMG_EXT}"
	kdump_initrd="${KDUMP_BOOTDIR}/initramfs-${kdump_kver}kdump.img"

	#will rebuild every time if extra_modules are specified
	extra_modules=`grep ^extra_modules $KDUMP_CONFIG_FILE`
	[ -n "$extra_modules" ] && force_rebuild=1

	#check to see if dependent files has been modified
	#since last build of the image file
	if [ -f $kdump_initrd ]; then
		image_time=`stat -c "%Y" $kdump_initrd 2>/dev/null`
	else
		image_time=0
	fi


	EXTRA_BINS=`grep ^extra_bins $KDUMP_CONFIG_FILE | cut -d\  -f2-`
	files="$KDUMP_CONFIG_FILE $kdump_kernel $EXTRA_BINS"

	check_exist "$files" && check_executable "$EXTRA_BINS"
	[ $? -ne 0 ] && return 1

	for file in $files; do
		time_stamp=`stat -c "%Y" $file`
		if [ "$time_stamp" -gt "$image_time" ]; then
			modified_files="$modified_files $file"
		fi
	done

	if [ $image_time -eq 0 ]; then
		echo  -n "No kdump initial ramdisk found."; echo
	elif [ "$force_rebuild" -ne 0 ]; then
		echo -n "Force rebuild $kdump_initrd"; echo
	elif [ -n "$modified_files" ]; then
		echo "Detected change(s) the following file(s):"
		echo -n "  "; echo "$modified_files" | sed 's/\s/\n  /g'
	else
		return 0
	fi

	echo "Rebuilding $kdump_initrd"
	rebuild_initrd
	return $?
}

# This function check iomem and determines if we have more than
# 4GB of ram available. Returns 1 if we do, 0 if we dont
function need_64bit_headers()
{
    return `tail -n 1 /proc/iomem | awk '{ split ($1, r, "-"); \
    print (strtonum("0x" r[2]) > strtonum("0xffffffff")); }'`
}

# Load the kdump kerel specified in /etc/sysconfig/kdump
# If none is specified, try to load a kdump kernel with the same version
# as the currently running kernel.
function load_kdump()
{

	if [ -z "$KDUMP_COMMANDLINE" ]
	then
		KDUMP_COMMANDLINE=`cat /proc/cmdline`
	fi

	ARCH=`uname -m`
	if [ "$ARCH" == "ppc64" ]
	then
		MEM_RESERVED=`grep "crashkernel=[0-9]\+[MmKkGg]@[0-9]\+[MmGgKk]" /proc/cmdline`
		if [ -z "$MEM_RESERVED" ] 
		then
			MEM_RESERVED=`grep "crashkernel=[0-9]\+[MmKkGg]" /proc/cmdline`
		fi
	else
		MEM_RESERVED=`grep "Crash kernel" /proc/iomem | grep -v "00000000-00000000"`
	fi

	if [ -z "$MEM_RESERVED" ]
	then
		$LOGGER "No crashkernel parameter specified for running kernel"
		return 1
	fi

	if [ "$ARCH" == "i686" -o "$ARCH" == "i386" ]
	then

		need_64bit_headers
		if [ $? == 1 ]
		then
			FOUND_ELF_ARGS=`echo $KEXEC_ARGS | grep elf32-core-headers`
			if [ -n "$FOUND_ELF_ARGS" ]
			then
				echo -n "Warning: elf32-core-headers overrides correct elf64 setting"
				echo
			else	
				KEXEC_ARGS="$KEXEC_ARGS --elf64-core-headers"
			fi
		else
			FOUND_ELF_ARGS=`echo $KEXEC_ARGS | grep elf64-core-headers`
			if [ -z "$FOUND_ELF_ARGS" ]
			then
				KEXEC_ARGS="$KEXEC_ARGS --elf32-core-headers"
			fi
		fi
	fi

	KDUMP_COMMANDLINE=`echo $KDUMP_COMMANDLINE | sed -e 's/crashkernel=[^ ]*//'`
	KDUMP_COMMANDLINE="${KDUMP_COMMANDLINE} ${KDUMP_COMMANDLINE_APPEND}"

	$KEXEC $KEXEC_ARGS $standard_kexec_args \
		--command-line="$KDUMP_COMMANDLINE" \
		--initrd=$kdump_initrd $kdump_kernel 2>/dev/null
	if [ $? == 0 ]; then
		$LOGGER "kexec: loaded kdump kernel"
		return 0
	else
		$LOGGER "kexec: failed to load kdump kernel"
		return 1
	fi
}

function check_ssh_config()
{
	while read config_opt config_val; do
		case "$config_opt" in
		sshkey)
			if [ -f "$config_val" ]; then
				# canonicalize the path
				SSH_KEY_LOCATION=$(/usr/bin/readlink -m $config_val)
			else
				echo "WARNING: '$config_val' doesn't exist, using default value '$SSH_KEY_LOCATION'"
			fi
			;;
		path)
			SAVE_PATH=$config_val
			;;
		net)
			DUMP_TARGET=$config_val
			;;
		*)
			;;
		esac
	done < $KDUMP_CONFIG_FILE

	#make sure they've configured kdump.conf for ssh dumps
	local SSH_TARGET=`echo -n $DUMP_TARGET | sed -n '/.*@/p'`
	if [ -z "$SSH_TARGET" ]; then
		return 1
	fi
	return 0
}

function check_ssh_target()
{
    ssh -q -i $SSH_KEY_LOCATION -o BatchMode=yes $DUMP_TARGET mkdir -p $SAVE_PATH
    if [ $? -ne 0 ]; then
        echo "Could not create $DUMP_TARGET:$SAVE_PATH, you probably need to run \"service kdump propagate\""
        exit $?
    fi
    return 0
}

function propagate_ssh_key()
{
	check_ssh_config
	if [ $? -ne 0 ]; then
		echo "No ssh config specified in $KDUMP_CONFIG_FILE.  Can't propagate"
		$LOGGER "$errmsg, no ssh config specified in $KDUMP_CONFIG_FILE"
		exit 1
	fi

	#Check if selinux is on... must flip to permissive mode
	#for the moment to create key, then flip back...
	se_enforce=`/usr/sbin/sestatus | grep -c "^Current mode.*enforcing"`
	if [ "$se_enforce" -ge 1 ]; then
		/usr/sbin/setenforce 0 2>&1 > /dev/null
	fi

	local KEYFILE=$SSH_KEY_LOCATION
	local errmsg="Failed to propagate ssh key"

	#Check to see if we already created key, if not, create it.
	if [ -f $KEYFILE ]; then
		echo "Using existing keys..."
	else
		echo -n "Generating new ssh keys... "
		/usr/bin/ssh-keygen -t rsa -f $KEYFILE -N "" 2>&1 > /dev/null
		echo "done."
	fi

	#If necessary, flip selinux back to enforcing
	if [ "$se_enforce" -ge 1 ]; then
		/usr/sbin/setenforce 1 2>&1 > /dev/null
	fi
	
	#now find the target ssh user and server to contact.
	SSH_USER=`echo $DUMP_TARGET | cut -d\  -f2 | cut -d@ -f1`
	SSH_SERVER=`echo $DUMP_TARGET | sed -e's/\(.*@\)\(.*$\)/\2/'`
 
	#now send the found key to the found server
	ssh-copy-id -i $KEYFILE $SSH_USER@$SSH_SERVER
	RET=$?
	if [ $RET == 0 ]; then
		echo $KEYFILE has been added to ~$SSH_USER/.ssh/authorized_keys on $SSH_SERVER
		$LOGGER "propagated ssh key (ssh server: $SSH_SERVER)"
		return 0
	else
		echo $KEYFILE failed in transfer to $SSH_SERVER
		$LOGGER "$errmsg, unable to transfer $KEYFILE to $SSH_SERVER"
		exit 1
	fi
		
}

function status()
{
	if [ ! -e /sys/kernel/kexec_crash_loaded ]
	then
		return 2 
	fi
	rc=`cat /sys/kernel/kexec_crash_loaded`
	if [ $rc == 1 ]; then
		return 0
	else
		return 1
	fi
}

function save_raw()
{
	local kdump_dir
	local raw_target

	raw_target=$(awk '$1 ~ /^raw$/ { print $2; }' $KDUMP_CONFIG_FILE)
	[ -z "$raw_target" ] && return 0
	[ -b "$raw_target" ] || {
		echo "raw partition $raw_target not found"
		return 1
	}
	kdump_dir=`grep ^path $KDUMP_CONFIG_FILE | cut -d' '  -f2-`
	if [ -z "${kdump_dir}" ]; then
		coredir="/var/crash/`date +"%Y-%m-%d-%H:%M"`"
	else
		coredir="${kdump_dir}/`date +"%Y-%m-%d-%H:%M"`"
	fi

	mkdir -p "$coredir"
	[ -d "$coredir" ] || {
		echo "failed to create $coredir"
		return 1
	}
	if makedumpfile -R $coredir/vmcore <$raw_target >/dev/null 2>&1; then
		# dump found
		echo "Dump saved to $coredir/vmcore"
		# wipe makedumpfile header
		dd if=/dev/zero of=$raw_target bs=1b count=1 2>/dev/null
	else
		rm -rf "$coredir"
	fi

	return 0
}

function start()
{
	local nr
	nr=$(awk 'BEGIN{cnt=0} /^raw|^net|^ext[234]|^xfs|^btrfs|^minix/{cnt++} END{print cnt}' $KDUMP_CONFIG_FILE)
	[ $nr -gt 1 ] && {
		echo -n "Error: More than one dump targets specified"; echo
		return 1
	}

	save_raw
	if [ $? -ne 0 ]; then
		echo -n "Starting kdump:"; echo
		$LOGGER "failed to start up"
		return 1
	fi

	status 
	rc=$?
	if [ $rc == 2 ]; then
		echo -n "Kdump is not supported on this kernel"; echo
		return 1;
	else
		if [ $rc == 0 ]; then
			echo -n "Kdump already running";  echo
			return 0
		fi
	fi

        check_ssh_config && check_ssh_target

	check_config
	if [ $? != 0 ]; then
		echo -n "Starting kdump:"; echo
		$LOGGER "failed to start up, config file incorrect"
		return 1
	fi
	load_kdump
	if [ $? != 0 ]; then
		echo -n "Starting kdump:"; echo
		$LOGGER "failed to start up"
		return 1
	fi

	echo -n "Starting kdump:";  echo
	$LOGGER "started up"
}

function stop()
{
	$KEXEC -p -u 2>/dev/null
	if [ $? == 0 ]; then
		$LOGGER "kexec: unloaded kdump kernel"
		echo -n "Stopping kdump:";  echo
		$LOGGER "stopped"
		return 0
	else
		$LOGGER "kexec: failed to unload kdump kernel"
		echo -n "Stopping kdump:"; echo
		$LOGGER "failed to stop"
		return 1
	fi
}

if [ ! -f "$KDUMP_CONFIG_FILE" ]; then
	echo -n "No kdump config file found!"; echo
	exit 1
fi

case "$1" in
  start)
	if [ -s /proc/vmcore ]; then
		save_core
		reboot
	else
		start
	fi
	;;
  stop)
	stop
	;;
  status)
	EXIT_CODE=0
	status
	case "$?" in
	0)
		echo "Kdump is operational"
		EXIT_CODE=0
		;;
	1)
		echo "Kdump is not operational"
		EXIT_CODE=3
		;;
	2)
		echo "Kdump is unsupported on this kernel"
		EXIT_CODE=3
		;;
	esac
	exit $EXIT_CODE
	;;
  restart)
	stop
	start
	;;
  condrestart)
	;;
  propagate)
	propagate_ssh_key
	;;
  *)
	echo $"Usage: $0 {start|stop|status|restart|propagate}"
	exit 1
esac

exit $?