#!/bin/sh
#
# vdev_id: udev helper to generate user-friendly names for JBOD disks
#
# This script parses the file /etc/zfs/vdev_id.conf to map a
# physical path in a storage topology to a channel name.  The
# channel name is combined with a disk enclosure slot number to
# create an alias that reflects the physical location of the drive.
# This is particularly helpful when it comes to tasks like replacing
# failed drives.  Slot numbers may also be re-mapped in case the
# default numbering is unsatisfactory.  The drive aliases will be
# created as symbolic links in /dev/disk/by-vdev.
#
# The currently supported topologies are sas_direct and sas_switch.
# A multipath mode is supported in which dm-mpath devices are
# handled by examining the first-listed running component disk.  In
# multipath mode the configuration file should contain a channel
# definition with the same name for each path to a given enclosure.
#
# The alias keyword provides a simple way to map already-existing
# device symlinks to more convenient names.  It is suitable for
# small, static configurations or for sites that have some automated
# way to generate the mapping file.
#
#
# Some example configuration files are given below.

# #
# # Example vdev_id.conf - sas_direct.
# #
#
# multipath     no
# topology      sas_direct
# phys_per_port 4
#
# #       PCI_ID  HBA PORT  CHANNEL NAME
# channel 85:00.0 1         A
# channel 85:00.0 0         B
# channel 86:00.0 1         C
# channel 86:00.0 0         D
#
# #    Linux	Mapped
# #    Slot	Slot
# slot 1        7
# slot 2        10
# slot 3        3
# slot 4        6
# slot 5        2
# slot 6        8
# slot 7        1
# slot 8        4
# slot 9        9
# slot 10       5

# #
# # Example vdev_id.conf - sas_switch
# #
#
# topology      sas_switch
#
# #       SWITCH PORT  CHANNEL NAME
# channel 1            A
# channel 2            B
# channel 3            C
# channel 4            D

# #
# # Example vdev_id.conf - multipath
# #
#
# multipath yes
#
# #       PCI_ID  HBA PORT  CHANNEL NAME
# channel 85:00.0 1         A
# channel 85:00.0 0         B
# channel 86:00.0 1         A
# channel 86:00.0 0         B

# #
# # Example vdev_id.conf - alias
# #
#
# #     by-vdev
# #     name     fully qualified or base name of device link
# alias d1       /dev/disk/by-id/wwn-0x5000c5002de3b9ca
# alias d2       wwn-0x5000c5002def789e

PATH=/bin:/sbin:/usr/bin:/usr/sbin
CONFIG=/etc/zfs/vdev_id.conf
PHYS_PER_PORT=
DEV=
MULTIPATH=
TOPOLOGY=

usage() {
	cat << EOF
Usage: vdev_id [-h]
       vdev_id <-d device> [-c config_file] [-p phys_per_port]
               [-g sas_direct|sas_switch] [-m]

  -c    specify name of alernate config file [default=$CONFIG]
  -d    specify basename of device (i.e. sda)
  -g    Storage network topology [default="$TOPOLOGY"]
  -m    Run in multipath mode
  -p    number of phy's per switch port [default=$PHYS_PER_PORT]
  -h    show this summary
EOF
	exit 0
}

map_slot() {
	local LINUX_SLOT=$1
	local MAPPED_SLOT=

	MAPPED_SLOT=`awk "\\$1 == \"slot\" && \\$2 == ${LINUX_SLOT} \
			{ print \\$3; exit }" $CONFIG`
	if [ -z "$MAPPED_SLOT" ] ; then
		MAPPED_SLOT=$LINUX_SLOT
	fi
	printf "%d" ${MAPPED_SLOT}
}

map_channel() {
	local MAPPED_CHAN=
	local PCI_ID=$1
	local PORT=$2

	case $TOPOLOGY in
		"sas_switch")
		MAPPED_CHAN=`awk "\\$1 == \"channel\" && \\$2 == ${PORT} \
			{ print \\$3; exit }" $CONFIG`
		;;
		"sas_direct")
		MAPPED_CHAN=`awk "\\$1 == \"channel\" && \
			\\$2 == \"${PCI_ID}\" && \\$3 == ${PORT} \
			{ print \\$4; exit }" $CONFIG`
		;;
	esac
	printf "%s" ${MAPPED_CHAN}
}

sas_handler() {
	if [ -z "$PHYS_PER_PORT" ] ; then
		PHYS_PER_PORT=`awk "\\$1 == \"phys_per_port\" \
			{print \\$2; exit}" $CONFIG`
	fi
	PHYS_PER_PORT=${PHYS_PER_PORT:-4}
	if ! echo $PHYS_PER_PORT | grep -q -E '^[0-9]+$' ; then
		echo "Error: phys_per_port value $PHYS_PER_PORT is non-numeric"
		exit 1
	fi

	if [ -z "$MULTIPATH_MODE" ] ; then
		MULTIPATH_MODE=`awk "\\$1 == \"multipath\" \
			{print \\$2; exit}" $CONFIG`
	fi

	# Use first running component device if we're handling a dm-mpath device
	if [ "$MULTIPATH_MODE" = "yes" ] ; then
		# If udev didn't tell us the UUID via DM_NAME, check /dev/mapper
		if [ -z "$DM_NAME" ] ; then
			DM_NAME=`ls -l --full-time /dev/mapper |
				awk "/\/$DEV$/{print \\$9}"`
		fi

		# For raw disks udev exports DEVTYPE=partition when
		# handling partitions, and the rules can be written to
		# take advantage of this to append a -part suffix.  For
		# dm devices we get DEVTYPE=disk even for partitions so
		# we have to append the -part suffix directly in the
		# helper.
		if [ "$DEVTYPE" != "partition" ] ; then
			PART=`echo $DM_NAME | awk -Fp '/p/{print "-part"$2}'`
		fi

		# Strip off partition information.
		DM_NAME=`echo $DM_NAME | sed 's/p[0-9][0-9]*$//'`
		if [ -z "$DM_NAME" ] ; then
			return
		fi

		# Get the raw scsi device name from multipath -l.
		DEV=`multipath -l $DM_NAME |awk '/running/{print $3 ; exit}'`
		if [ -z "$DEV" ] ; then
			return
		fi
	fi

	if echo $DEV | grep -q ^/devices/ ; then
		sys_path=$DEV
	else
		sys_path=`udevadm info -q path -p /sys/block/$DEV 2>/dev/null`
	fi

	# Use positional parameters as an ad-hoc array
	set -- $(echo "$sys_path" | tr / ' ')
	num_dirs=$#
	scsi_host_dir="/sys"

	# Get path up to /sys/.../hostX
	i=1
	while [ $i -le $num_dirs ] ; do
		d=$(eval echo \${$i})
		scsi_host_dir="$scsi_host_dir/$d"
		echo $d | grep -q -E '^host[0-9]+$' && break
		i=$(($i + 1))
	done

	if [ $i = $num_dirs ] ; then
		return
	fi

	PCI_ID=$(eval echo \${$(($i -1))} | awk -F: '{print $2":"$3}')

	# In sas_switch mode, the directory four levels beneath
	# /sys/.../hostX contains symlinks to phy devices that reveal
	# the switch port number.  In sas_direct mode, the phy links one
	# directory down reveal the HBA port.
	port_dir=$scsi_host_dir
	case $TOPOLOGY in
		"sas_switch") j=$(($i + 4)) ;;
		"sas_direct") j=$(($i + 1)) ;;
	esac

	i=$(($i + 1))
	while [ $i -le $j ] ; do
		port_dir="$port_dir/$(eval echo \${$i})"
		i=$(($i + 1))
	done

	PHY=`ls -d $port_dir/phy* 2>/dev/null | head -1 | awk -F: '{print $NF}'`
	if [ -z "$PHY" ] ; then
		return
	fi
	PORT=$(( $PHY / $PHYS_PER_PORT ))

	# Look in /sys/.../sas_device/end_device-X for the bay_identifier
	# attribute.
	end_device_dir=$port_dir
	while [ $i -lt $num_dirs ] ; do
		d=$(eval echo \${$i})
		end_device_dir="$end_device_dir/$d"
		if echo $d | grep -q '^end_device' ; then
			end_device_dir="$end_device_dir/sas_device/$d"
			break
		fi
		i=$(($i + 1))
	done

	SLOT=`cat $end_device_dir/bay_identifier 2>/dev/null`
	if [ -z "$SLOT" ] ; then
		return
	fi

	SLOT=`map_slot $SLOT`
	CHAN=`map_channel $PCI_ID $PORT`
	if [ -z "$CHAN" ] ; then
		return
	fi
	echo ${CHAN}${SLOT}${PART}
}

alias_handler () {
	# Special handling is needed to correctly append a -part suffix
	# to partitions of device mapper devices.  The DEVTYPE attribute
	# is normally set to "disk" instead of "partition" in this case,
	# so the udev rules won't handle that for us as they do for
	# "plain" block devices.
	#
	# For example, we may have the following links for a device and its
	# partitions,
	#
	#  /dev/disk/by-id/dm-name-isw_dibgbfcije_ARRAY0   -> ../../dm-0
	#  /dev/disk/by-id/dm-name-isw_dibgbfcije_ARRAY0p1 -> ../../dm-1
	#  /dev/disk/by-id/dm-name-isw_dibgbfcije_ARRAY0p2 -> ../../dm-3
	#
	# and the following alias in vdev_id.conf.
	#
	#   alias A0 dm-name-isw_dibgbfcije_ARRAY0
	#
	# The desired outcome is for the following links to be created
	# without having explicitly defined aliases for the partitions.
	#
	#  /dev/disk/by-vdev/A0       -> ../../dm-0
	#  /dev/disk/by-vdev/A0-part1 -> ../../dm-1
	#  /dev/disk/by-vdev/A0-part2 -> ../../dm-3
	#
	# Warning: The following grep pattern will misidentify whole-disk
	#          devices whose names end with 'p' followed by a string of
	#          digits as partitions, causing alias creation to fail. This
	#          ambiguity seems unavoidable, so devices using this facility
	#          must not use such names.
	local DM_PART=
	if echo $DM_NAME | grep -q -E 'p[0-9][0-9]*$' ; then
		if [ "$DEVTYPE" != "partition" ] ; then
			DM_PART=`echo $DM_NAME | awk -Fp '/p/{print "-part"$2}'`
		fi
	fi

	# DEVLINKS attribute must have been populated by already-run udev rules.
	for link in $DEVLINKS ; do
		# Remove partition information to match key of top-level device.
		if [ -n "$DM_PART" ] ; then
			link=`echo $link | sed 's/p[0-9][0-9]*$//'`
		fi
		# Check both the fully qualified and the base name of link.
		for l in $link `basename $link` ; do
			alias=`awk "\\$1 == \"alias\" && \\$3 == \"${l}\" \
					{ print \\$2; exit }" $CONFIG`
			if [ -n "$alias" ] ; then
				echo ${alias}${DM_PART}
				return
			fi
		done
	done
}

while getopts 'c:d:g:mp:h' OPTION; do
	case ${OPTION} in
	c)
		CONFIG=${OPTARG}
		;;
	d)
		DEV=${OPTARG}
		;;
	g)
		TOPOLOGY=$OPTARG
		;;
	p)
		PHYS_PER_PORT=${OPTARG}
		;;
	m)
		MULTIPATH_MODE=yes
		;;
	h)
		usage
		;;
	esac
done

if [ ! -r $CONFIG ] ; then
	exit 0
fi

if [ -z "$DEV" ] ; then
	echo "Error: missing required option -d"
	exit 1
fi

if [ -z "$TOPOLOGY" ] ; then
	TOPOLOGY=`awk "\\$1 == \"topology\" {print \\$2; exit}" $CONFIG`
fi

# First check if an alias was defined for this device.
ID_VDEV=`alias_handler`

if [ -z "$ID_VDEV" ] ; then
	TOPOLOGY=${TOPOLOGY:-sas_direct}
	case $TOPOLOGY in
		sas_direct|sas_switch)
			ID_VDEV=`sas_handler`
			;;
		*)
			echo "Error: unknown topology $TOPOLOGY"
			exit 1
			;;
	esac
fi

if [ -n "$ID_VDEV" ] ; then
	echo "ID_VDEV=${ID_VDEV}"
	echo "ID_VDEV_PATH=disk/by-vdev/${ID_VDEV}"
fi