Debug auto_replace_001_pos failures

[mirror_zfs.git] / tests / zfs-tests / include / libtest.shlib

#
# CDDL HEADER START
#
# The contents of this file are subject to the terms of the
# Common Development and Distribution License (the "License").
# You may not use this file except in compliance with the License.
#
# You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
# or https://opensource.org/licenses/CDDL-1.0.
# See the License for the specific language governing permissions
# and limitations under the License.
#
# When distributing Covered Code, include this CDDL HEADER in each
# file and include the License file at usr/src/OPENSOLARIS.LICENSE.
# If applicable, add the following below this CDDL HEADER, with the
# fields enclosed by brackets "[]" replaced with your own identifying
# information: Portions Copyright [yyyy] [name of copyright owner]
#
# CDDL HEADER END
#

#
# Copyright (c) 2009, Sun Microsystems Inc. All rights reserved.
# Copyright (c) 2012, 2020, Delphix. All rights reserved.
# Copyright (c) 2017, Tim Chase. All rights reserved.
# Copyright (c) 2017, Nexenta Systems Inc. All rights reserved.
# Copyright (c) 2017, Lawrence Livermore National Security LLC.
# Copyright (c) 2017, Datto Inc. All rights reserved.
# Copyright (c) 2017, Open-E Inc. All rights reserved.
# Copyright (c) 2021, The FreeBSD Foundation.
# Use is subject to license terms.
#

. ${STF_SUITE}/include/tunables.cfg

. ${STF_TOOLS}/include/logapi.shlib
. ${STF_SUITE}/include/math.shlib
. ${STF_SUITE}/include/blkdev.shlib

#
# Apply constrained path when available.  This is required since the
# PATH may have been modified by sudo's secure_path behavior.
#
if [ -n "$STF_PATH" ]; then
	export PATH="$STF_PATH"
fi

#
# Generic dot version comparison function
#
# Returns success when version $1 is greater than or equal to $2.
#
function compare_version_gte
{
	[ "$(printf "$1\n$2" | sort -V | tail -n1)" = "$1" ]
}

# Linux kernel version comparison function
#
# $1 Linux version ("4.10", "2.6.32") or blank for installed Linux version
#
# Used for comparison: if [ $(linux_version) -ge $(linux_version "2.6.32") ]
#
function linux_version
{
	typeset ver="$1"

	[ -z "$ver" ] && ver=$(uname -r | grep -Eo "^[0-9]+\.[0-9]+\.[0-9]+")

	typeset version major minor _
	IFS='.' read -r version major minor _ <<<"$ver"

	[ -z "$version" ] && version=0
	[ -z "$major" ] && major=0
	[ -z "$minor" ] && minor=0

	echo $((version * 100000 + major * 1000 + minor))
}

# Determine if this is a Linux test system
#
# Return 0 if platform Linux, 1 if otherwise

function is_linux
{
	[ "$UNAME" = "Linux" ]
}

# Determine if this is an illumos test system
#
# Return 0 if platform illumos, 1 if otherwise
function is_illumos
{
	[ "$UNAME" = "illumos" ]
}

# Determine if this is a FreeBSD test system
#
# Return 0 if platform FreeBSD, 1 if otherwise

function is_freebsd
{
	[ "$UNAME" = "FreeBSD" ]
}

# Determine if this is a 32-bit system
#
# Return 0 if platform is 32-bit, 1 if otherwise

function is_32bit
{
	[ $(getconf LONG_BIT) = "32" ]
}

# Determine if kmemleak is enabled
#
# Return 0 if kmemleak is enabled, 1 if otherwise

function is_kmemleak
{
	is_linux && [ -e /sys/kernel/debug/kmemleak ]
}

# Determine whether a dataset is mounted
#
# $1 dataset name
# $2 filesystem type; optional - defaulted to zfs
#
# Return 0 if dataset is mounted; 1 if unmounted; 2 on error

function ismounted
{
	typeset fstype=$2
	[[ -z $fstype ]] && fstype=zfs
	typeset out dir name

	case $fstype in
		zfs)
			if [[ "$1" == "/"* ]] ; then
				! zfs mount | awk -v fs="$1" '$2 == fs {exit 1}'
			else
				! zfs mount | awk -v ds="$1" '$1 == ds {exit 1}'
			fi
		;;
		ufs|nfs)
			if is_freebsd; then
				mount -pt $fstype | while read dev dir _t _flags; do
					[[ "$1" == "$dev" || "$1" == "$dir" ]] && return 0
				done
			else
				out=$(df -F $fstype $1 2>/dev/null) || return

				dir=${out%%\(*}
				dir=${dir%% *}
				name=${out##*\(}
				name=${name%%\)*}
				name=${name%% *}

				[[ "$1" == "$dir" || "$1" == "$name" ]] && return 0
			fi
		;;
		ext*)
			df -t $fstype $1 > /dev/null 2>&1
		;;
		zvol)
			if [[ -L "$ZVOL_DEVDIR/$1" ]]; then
				link=$(readlink -f $ZVOL_DEVDIR/$1)
				[[ -n "$link" ]] && \
					mount | grep -q "^$link" && \
						return 0
			fi
		;;
		*)
			false
		;;
	esac
}

# Return 0 if a dataset is mounted; 1 otherwise
#
# $1 dataset name
# $2 filesystem type; optional - defaulted to zfs

function mounted
{
	ismounted $1 $2
}

# Return 0 if a dataset is unmounted; 1 otherwise
#
# $1 dataset name
# $2 filesystem type; optional - defaulted to zfs

function unmounted
{
	! ismounted $1 $2
}

function default_setup
{
	default_setup_noexit "$@"

	log_pass
}

function default_setup_no_mountpoint
{
	default_setup_noexit "$1" "$2" "$3" "yes"

	log_pass
}

#
# Given a list of disks, setup storage pools and datasets.
#
function default_setup_noexit
{
	typeset disklist=$1
	typeset container=$2
	typeset volume=$3
	typeset no_mountpoint=$4
	log_note begin default_setup_noexit

	if is_global_zone; then
		if poolexists $TESTPOOL ; then
			destroy_pool $TESTPOOL
		fi
		[[ -d /$TESTPOOL ]] && rm -rf /$TESTPOOL
		log_must zpool create -f $TESTPOOL $disklist
	else
		reexport_pool
	fi

	rm -rf $TESTDIR  || log_unresolved Could not remove $TESTDIR
	mkdir -p $TESTDIR || log_unresolved Could not create $TESTDIR

	log_must zfs create $TESTPOOL/$TESTFS
	if [[ -z $no_mountpoint ]]; then
		log_must zfs set mountpoint=$TESTDIR $TESTPOOL/$TESTFS
	fi

	if [[ -n $container ]]; then
		rm -rf $TESTDIR1  || \
			log_unresolved Could not remove $TESTDIR1
		mkdir -p $TESTDIR1 || \
			log_unresolved Could not create $TESTDIR1

		log_must zfs create $TESTPOOL/$TESTCTR
		log_must zfs set canmount=off $TESTPOOL/$TESTCTR
		log_must zfs create $TESTPOOL/$TESTCTR/$TESTFS1
		if [[ -z $no_mountpoint ]]; then
			log_must zfs set mountpoint=$TESTDIR1 \
			    $TESTPOOL/$TESTCTR/$TESTFS1
		fi
	fi

	if [[ -n $volume ]]; then
		if is_global_zone ; then
			log_must zfs create -V $VOLSIZE $TESTPOOL/$TESTVOL
			block_device_wait
		else
			log_must zfs create $TESTPOOL/$TESTVOL
		fi
	fi
}

#
# Given a list of disks, setup a storage pool, file system and
# a container.
#
function default_container_setup
{
	typeset disklist=$1

	default_setup "$disklist" "true"
}

#
# Given a list of disks, setup a storage pool,file system
# and a volume.
#
function default_volume_setup
{
	typeset disklist=$1

	default_setup "$disklist" "" "true"
}

#
# Given a list of disks, setup a storage pool,file system,
# a container and a volume.
#
function default_container_volume_setup
{
	typeset disklist=$1

	default_setup "$disklist" "true" "true"
}

#
# Create a snapshot on a filesystem or volume. Defaultly create a snapshot on
# filesystem
#
# $1 Existing filesystem or volume name. Default, $TESTPOOL/$TESTFS
# $2 snapshot name. Default, $TESTSNAP
#
function create_snapshot
{
	typeset fs_vol=${1:-$TESTPOOL/$TESTFS}
	typeset snap=${2:-$TESTSNAP}

	[[ -z $fs_vol ]] && log_fail "Filesystem or volume's name is undefined."
	[[ -z $snap ]] && log_fail "Snapshot's name is undefined."

	if snapexists $fs_vol@$snap; then
		log_fail "$fs_vol@$snap already exists."
	fi
	datasetexists $fs_vol || \
		log_fail "$fs_vol must exist."

	log_must zfs snapshot $fs_vol@$snap
}

#
# Create a clone from a snapshot, default clone name is $TESTCLONE.
#
# $1 Existing snapshot, $TESTPOOL/$TESTFS@$TESTSNAP is default.
# $2 Clone name, $TESTPOOL/$TESTCLONE is default.
#
function create_clone   # snapshot clone
{
	typeset snap=${1:-$TESTPOOL/$TESTFS@$TESTSNAP}
	typeset clone=${2:-$TESTPOOL/$TESTCLONE}

	[[ -z $snap ]] && \
		log_fail "Snapshot name is undefined."
	[[ -z $clone ]] && \
		log_fail "Clone name is undefined."

	log_must zfs clone $snap $clone
}

#
# Create a bookmark of the given snapshot.  Defaultly create a bookmark on
# filesystem.
#
# $1 Existing filesystem or volume name. Default, $TESTFS
# $2 Existing snapshot name. Default, $TESTSNAP
# $3 bookmark name. Default, $TESTBKMARK
#
function create_bookmark
{
	typeset fs_vol=${1:-$TESTFS}
	typeset snap=${2:-$TESTSNAP}
	typeset bkmark=${3:-$TESTBKMARK}

	[[ -z $fs_vol ]] && log_fail "Filesystem or volume's name is undefined."
	[[ -z $snap ]] && log_fail "Snapshot's name is undefined."
	[[ -z $bkmark ]] && log_fail "Bookmark's name is undefined."

	if bkmarkexists $fs_vol#$bkmark; then
		log_fail "$fs_vol#$bkmark already exists."
	fi
	datasetexists $fs_vol || \
		log_fail "$fs_vol must exist."
	snapexists $fs_vol@$snap || \
		log_fail "$fs_vol@$snap must exist."

	log_must zfs bookmark $fs_vol@$snap $fs_vol#$bkmark
}

#
# Create a temporary clone result of an interrupted resumable 'zfs receive'
# $1 Destination filesystem name. Must not exist, will be created as the result
#    of this function along with its %recv temporary clone
# $2 Source filesystem name. Must not exist, will be created and destroyed
#
function create_recv_clone
{
	typeset recvfs="$1"
	typeset sendfs="${2:-$TESTPOOL/create_recv_clone}"
	typeset snap="$sendfs@snap1"
	typeset incr="$sendfs@snap2"
	typeset mountpoint="$TESTDIR/create_recv_clone"
	typeset sendfile="$TESTDIR/create_recv_clone.zsnap"

	[[ -z $recvfs ]] && log_fail "Recv filesystem's name is undefined."

	datasetexists $recvfs && log_fail "Recv filesystem must not exist."
	datasetexists $sendfs && log_fail "Send filesystem must not exist."

	log_must zfs create -o compression=off -o mountpoint="$mountpoint" $sendfs
	log_must zfs snapshot $snap
	log_must eval "zfs send $snap | zfs recv -u $recvfs"
	log_must mkfile 1m "$mountpoint/data"
	log_must zfs snapshot $incr
	log_must eval "zfs send -i $snap $incr | dd bs=10K count=1 \
	    iflag=fullblock > $sendfile"
	log_mustnot eval "zfs recv -su $recvfs < $sendfile"
	destroy_dataset "$sendfs" "-r"
	log_must rm -f "$sendfile"

	if [[ $(get_prop 'inconsistent' "$recvfs/%recv") -ne 1 ]]; then
		log_fail "Error creating temporary $recvfs/%recv clone"
	fi
}

function default_mirror_setup
{
	default_mirror_setup_noexit $1 $2 $3

	log_pass
}

#
# Given a pair of disks, set up a storage pool and dataset for the mirror
# @parameters: $1 the primary side of the mirror
#   $2 the secondary side of the mirror
# @uses: ZPOOL ZFS TESTPOOL TESTFS
function default_mirror_setup_noexit
{
	readonly func="default_mirror_setup_noexit"
	typeset primary=$1
	typeset secondary=$2

	[[ -z $primary ]] && \
		log_fail "$func: No parameters passed"
	[[ -z $secondary ]] && \
		log_fail "$func: No secondary partition passed"
	[[ -d /$TESTPOOL ]] && rm -rf /$TESTPOOL
	log_must zpool create -f $TESTPOOL mirror $@
	log_must zfs create $TESTPOOL/$TESTFS
	log_must zfs set mountpoint=$TESTDIR $TESTPOOL/$TESTFS
}

#
# Destroy the configured testpool mirrors.
# the mirrors are of the form ${TESTPOOL}{number}
# @uses: ZPOOL ZFS TESTPOOL
function destroy_mirrors
{
	default_cleanup_noexit

	log_pass
}

function default_raidz_setup
{
	default_raidz_setup_noexit "$*"

	log_pass
}

#
# Given a minimum of two disks, set up a storage pool and dataset for the raid-z
# $1 the list of disks
#
function default_raidz_setup_noexit
{
	typeset disklist="$*"
	disks=(${disklist[*]})

	if [[ ${#disks[*]} -lt 2 ]]; then
		log_fail "A raid-z requires a minimum of two disks."
	fi

	[[ -d /$TESTPOOL ]] && rm -rf /$TESTPOOL
	log_must zpool create -f $TESTPOOL raidz $disklist
	log_must zfs create $TESTPOOL/$TESTFS
	log_must zfs set mountpoint=$TESTDIR $TESTPOOL/$TESTFS
}

#
# Common function used to cleanup storage pools and datasets.
#
# Invoked at the start of the test suite to ensure the system
# is in a known state, and also at the end of each set of
# sub-tests to ensure errors from one set of tests doesn't
# impact the execution of the next set.

function default_cleanup
{
	default_cleanup_noexit

	log_pass
}

#
# Utility function used to list all available pool names.
#
# NOTE: $KEEP is a variable containing pool names, separated by a newline
# character, that must be excluded from the returned list.
#
function get_all_pools
{
	zpool list -H -o name | grep -Fvx "$KEEP" | grep -v "$NO_POOLS"
}

function default_cleanup_noexit
{
	typeset pool=""
	#
	# Destroying the pool will also destroy any
	# filesystems it contains.
	#
	if is_global_zone; then
		zfs unmount -a > /dev/null 2>&1
		ALL_POOLS=$(get_all_pools)
		# Here, we loop through the pools we're allowed to
		# destroy, only destroying them if it's safe to do
		# so.
		while [ ! -z ${ALL_POOLS} ]
		do
			for pool in ${ALL_POOLS}
			do
				if safe_to_destroy_pool $pool ;
				then
					destroy_pool $pool
				fi
			done
			ALL_POOLS=$(get_all_pools)
		done

		zfs mount -a
	else
		typeset fs=""
		for fs in $(zfs list -H -o name \
		    | grep "^$ZONE_POOL/$ZONE_CTR[01234]/"); do
			destroy_dataset "$fs" "-Rf"
		done

		# Need cleanup here to avoid garbage dir left.
		for fs in $(zfs list -H -o name); do
			[[ $fs == /$ZONE_POOL ]] && continue
			[[ -d $fs ]] && log_must rm -rf $fs/*
		done

		#
		# Reset the $ZONE_POOL/$ZONE_CTR[01234] file systems property to
		# the default value
		#
		for fs in $(zfs list -H -o name); do
			if [[ $fs == $ZONE_POOL/$ZONE_CTR[01234] ]]; then
				log_must zfs set reservation=none $fs
				log_must zfs set recordsize=128K $fs
				log_must zfs set mountpoint=/$fs $fs
				typeset enc=$(get_prop encryption $fs)
				if [ -z "$enc" ] || [ "$enc" = "off" ]; then
					log_must zfs set checksum=on $fs
				fi
				log_must zfs set compression=off $fs
				log_must zfs set atime=on $fs
				log_must zfs set devices=off $fs
				log_must zfs set exec=on $fs
				log_must zfs set setuid=on $fs
				log_must zfs set readonly=off $fs
				log_must zfs set snapdir=hidden $fs
				log_must zfs set aclmode=groupmask $fs
				log_must zfs set aclinherit=secure $fs
			fi
		done
	fi

	[[ -d $TESTDIR ]] && \
		log_must rm -rf $TESTDIR

	disk1=${DISKS%% *}
	if is_mpath_device $disk1; then
		delete_partitions
	fi

	rm -f $TEST_BASE_DIR/{err,out}
}


#
# Common function used to cleanup storage pools, file systems
# and containers.
#
function default_container_cleanup
{
	if ! is_global_zone; then
		reexport_pool
	fi

	ismounted $TESTPOOL/$TESTCTR/$TESTFS1 &&
	    log_must zfs unmount $TESTPOOL/$TESTCTR/$TESTFS1

	destroy_dataset "$TESTPOOL/$TESTCTR/$TESTFS1" "-R"
	destroy_dataset "$TESTPOOL/$TESTCTR" "-Rf"

	[[ -e $TESTDIR1 ]] && \
	    log_must rm -rf $TESTDIR1

	default_cleanup
}

#
# Common function used to cleanup snapshot of file system or volume. Default to
# delete the file system's snapshot
#
# $1 snapshot name
#
function destroy_snapshot
{
	typeset snap=${1:-$TESTPOOL/$TESTFS@$TESTSNAP}

	if ! snapexists $snap; then
		log_fail "'$snap' does not exist."
	fi

	#
	# For the sake of the value which come from 'get_prop' is not equal
	# to the really mountpoint when the snapshot is unmounted. So, firstly
	# check and make sure this snapshot's been mounted in current system.
	#
	typeset mtpt=""
	if ismounted $snap; then
		mtpt=$(get_prop mountpoint $snap)
	fi

	destroy_dataset "$snap"
	[[ $mtpt != "" && -d $mtpt ]] && \
		log_must rm -rf $mtpt
}

#
# Common function used to cleanup clone.
#
# $1 clone name
#
function destroy_clone
{
	typeset clone=${1:-$TESTPOOL/$TESTCLONE}

	if ! datasetexists $clone; then
		log_fail "'$clone' does not existed."
	fi

	# With the same reason in destroy_snapshot
	typeset mtpt=""
	if ismounted $clone; then
		mtpt=$(get_prop mountpoint $clone)
	fi

	destroy_dataset "$clone"
	[[ $mtpt != "" && -d $mtpt ]] && \
		log_must rm -rf $mtpt
}

#
# Common function used to cleanup bookmark of file system or volume.  Default
# to delete the file system's bookmark.
#
# $1 bookmark name
#
function destroy_bookmark
{
	typeset bkmark=${1:-$TESTPOOL/$TESTFS#$TESTBKMARK}

	if ! bkmarkexists $bkmark; then
		log_fail "'$bkmarkp' does not existed."
	fi

	destroy_dataset "$bkmark"
}

# Return 0 if a snapshot exists; $? otherwise
#
# $1 - snapshot name

function snapexists
{
	zfs list -H -t snapshot "$1" > /dev/null 2>&1
}

#
# Return 0 if a bookmark exists; $? otherwise
#
# $1 - bookmark name
#
function bkmarkexists
{
	zfs list -H -t bookmark "$1" > /dev/null 2>&1
}

#
# Return 0 if a hold exists; $? otherwise
#
# $1 - hold tag
# $2 - snapshot name
#
function holdexists
{
	! zfs holds "$2" | awk -v t="$1" '$2 ~ t { exit 1 }'
}

#
# Set a property to a certain value on a dataset.
# Sets a property of the dataset to the value as passed in.
# @param:
#	$1 dataset who's property is being set
#	$2 property to set
#	$3 value to set property to
# @return:
#	0 if the property could be set.
#	non-zero otherwise.
# @use: ZFS
#
function dataset_setprop
{
	typeset fn=dataset_setprop

	if (($# < 3)); then
		log_note "$fn: Insufficient parameters (need 3, had $#)"
		return 1
	fi
	typeset output=
	output=$(zfs set $2=$3 $1 2>&1)
	typeset rv=$?
	if ((rv != 0)); then
		log_note "Setting property on $1 failed."
		log_note "property $2=$3"
		log_note "Return Code: $rv"
		log_note "Output: $output"
		return $rv
	fi
	return 0
}

#
# Check a numeric assertion
# @parameter: $@ the assertion to check
# @output: big loud notice if assertion failed
# @use: log_fail
#
function assert
{
	(($@)) || log_fail "$@"
}

#
# Function to format partition size of a disk
# Given a disk cxtxdx reduces all partitions
# to 0 size
#
function zero_partitions #<whole_disk_name>
{
	typeset diskname=$1
	typeset i

	if is_freebsd; then
		gpart destroy -F $diskname
	elif is_linux; then
		DSK=$DEV_DSKDIR/$diskname
		DSK=$(echo $DSK | sed -e "s|//|/|g")
		log_must parted $DSK -s -- mklabel gpt
		blockdev --rereadpt $DSK 2>/dev/null
		block_device_wait
	else
		for i in 0 1 3 4 5 6 7
		do
			log_must set_partition $i "" 0mb $diskname
		done
	fi

	return 0
}

#
# Given a slice, size and disk, this function
# formats the slice to the specified size.
# Size should be specified with units as per
# the `format` command requirements eg. 100mb 3gb
#
# NOTE: This entire interface is problematic for the Linux parted utility
# which requires the end of the partition to be specified.  It would be
# best to retire this interface and replace it with something more flexible.
# At the moment a best effort is made.
#
# arguments: <slice_num> <slice_start> <size_plus_units>  <whole_disk_name>
function set_partition
{
	typeset -i slicenum=$1
	typeset start=$2
	typeset size=$3
	typeset disk=${4#$DEV_DSKDIR/}
	disk=${disk#$DEV_RDSKDIR/}

	case "$UNAME" in
	Linux)
		if [[ -z $size || -z $disk ]]; then
			log_fail "The size or disk name is unspecified."
		fi
		disk=$DEV_DSKDIR/$disk
		typeset size_mb=${size%%[mMgG]}

		size_mb=${size_mb%%[mMgG][bB]}
		if [[ ${size:1:1} == 'g' ]]; then
			((size_mb = size_mb * 1024))
		fi

		# Create GPT partition table when setting slice 0 or
		# when the device doesn't already contain a GPT label.
		parted $disk -s -- print 1 >/dev/null
		typeset ret_val=$?
		if [[ $slicenum -eq 0 || $ret_val -ne 0 ]]; then
			if ! parted $disk -s -- mklabel gpt; then
				log_note "Failed to create GPT partition table on $disk"
				return 1
			fi
		fi

		# When no start is given align on the first cylinder.
		if [[ -z "$start" ]]; then
			start=1
		fi

		# Determine the cylinder size for the device and using
		# that calculate the end offset in cylinders.
		typeset -i cly_size_kb=0
		cly_size_kb=$(parted -m $disk -s -- unit cyl print |
			awk -F '[:k.]' 'NR == 3 {print $4}')
		((end = (size_mb * 1024 / cly_size_kb) + start))

		parted $disk -s -- \
		    mkpart part$slicenum ${start}cyl ${end}cyl
		typeset ret_val=$?
		if [[ $ret_val -ne 0 ]]; then
			log_note "Failed to create partition $slicenum on $disk"
			return 1
		fi

		blockdev --rereadpt $disk 2>/dev/null
		block_device_wait $disk
		;;
	FreeBSD)
		if [[ -z $size || -z $disk ]]; then
			log_fail "The size or disk name is unspecified."
		fi
		disk=$DEV_DSKDIR/$disk

		if [[ $slicenum -eq 0 ]] || ! gpart show $disk >/dev/null 2>&1; then
			gpart destroy -F $disk >/dev/null 2>&1
			if ! gpart create -s GPT $disk; then
				log_note "Failed to create GPT partition table on $disk"
				return 1
			fi
		fi

		typeset index=$((slicenum + 1))

		if [[ -n $start ]]; then
			start="-b $start"
		fi
		gpart add -t freebsd-zfs $start -s $size -i $index $disk
		if [[ $ret_val -ne 0 ]]; then
			log_note "Failed to create partition $slicenum on $disk"
			return 1
		fi

		block_device_wait $disk
		;;
	*)
		if [[ -z $slicenum || -z $size || -z $disk ]]; then
			log_fail "The slice, size or disk name is unspecified."
		fi

		typeset format_file=/var/tmp/format_in.$$

		echo "partition" >$format_file
		echo "$slicenum" >> $format_file
		echo "" >> $format_file
		echo "" >> $format_file
		echo "$start" >> $format_file
		echo "$size" >> $format_file
		echo "label" >> $format_file
		echo "" >> $format_file
		echo "q" >> $format_file
		echo "q" >> $format_file

		format -e -s -d $disk -f $format_file
		typeset ret_val=$?
		rm -f $format_file
		;;
	esac

	if [[ $ret_val -ne 0 ]]; then
		log_note "Unable to format $disk slice $slicenum to $size"
		return 1
	fi
	return 0
}

#
# Delete all partitions on all disks - this is specifically for the use of multipath
# devices which currently can only be used in the test suite as raw/un-partitioned
# devices (ie a zpool cannot be created on a whole mpath device that has partitions)
#
function delete_partitions
{
	typeset disk

	if [[ -z $DISKSARRAY ]]; then
		DISKSARRAY=$DISKS
	fi

	if is_linux; then
		typeset -i part
		for disk in $DISKSARRAY; do
			for (( part = 1; part < MAX_PARTITIONS; part++ )); do
				typeset partition=${disk}${SLICE_PREFIX}${part}
				parted $DEV_DSKDIR/$disk -s rm $part > /dev/null 2>&1
				if lsblk | grep -qF ${partition}; then
					log_fail "Partition ${partition} not deleted"
				else
					log_note "Partition ${partition} deleted"
				fi
			done
		done
	elif is_freebsd; then
		for disk in $DISKSARRAY; do
			if gpart destroy -F $disk; then
				log_note "Partitions for ${disk} deleted"
			else
				log_fail "Partitions for ${disk} not deleted"
			fi
		done
	fi
}

#
# Get the end cyl of the given slice
#
function get_endslice #<disk> <slice>
{
	typeset disk=$1
	typeset slice=$2
	if [[ -z $disk || -z $slice ]] ; then
		log_fail "The disk name or slice number is unspecified."
	fi

	case "$UNAME" in
	Linux)
		endcyl=$(parted -s $DEV_DSKDIR/$disk -- unit cyl print | \
			awk "/part${slice}/"' {sub(/cyl/, "", $3); print $3}')
		((endcyl = (endcyl + 1)))
		;;
	FreeBSD)
		disk=${disk#/dev/zvol/}
		disk=${disk%p*}
		slice=$((slice + 1))
		endcyl=$(gpart show $disk | \
			awk -v slice=$slice '$3 == slice { print $1 + $2 }')
		;;
	*)
		disk=${disk#/dev/dsk/}
		disk=${disk#/dev/rdsk/}
		disk=${disk%s*}

		typeset -i ratio=0
		ratio=$(prtvtoc /dev/rdsk/${disk}s2 | \
		    awk '/sectors\/cylinder/ {print $2}')

		if ((ratio == 0)); then
			return
		fi

		typeset -i endcyl=$(prtvtoc -h /dev/rdsk/${disk}s2 |
		    awk -v token="$slice" '$1 == token {print $6}')

		((endcyl = (endcyl + 1) / ratio))
		;;
	esac

	echo $endcyl
}


#
# Given a size,disk and total slice number,  this function formats the
# disk slices from 0 to the total slice number with the same specified
# size.
#
function partition_disk	#<slice_size> <whole_disk_name>	<total_slices>
{
	typeset -i i=0
	typeset slice_size=$1
	typeset disk_name=$2
	typeset total_slices=$3
	typeset cyl

	zero_partitions $disk_name
	while ((i < $total_slices)); do
		if ! is_linux; then
			if ((i == 2)); then
				((i = i + 1))
				continue
			fi
		fi
		log_must set_partition $i "$cyl" $slice_size $disk_name
		cyl=$(get_endslice $disk_name $i)
		((i = i+1))
	done
}

#
# This function continues to write to a filenum number of files into dirnum
# number of directories until either file_write returns an error or the
# maximum number of files per directory have been written.
#
# Usage:
# fill_fs [destdir] [dirnum] [filenum] [bytes] [num_writes] [data]
#
# Return value: 0 on success
#		non 0 on error
#
# Where :
#	destdir:    is the directory where everything is to be created under
#	dirnum:	    the maximum number of subdirectories to use, -1 no limit
#	filenum:    the maximum number of files per subdirectory
#	bytes:	    number of bytes to write
#	num_writes: number of types to write out bytes
#	data:	    the data that will be written
#
#	E.g.
#	fill_fs /testdir 20 25 1024 256 0
#
# Note: bytes * num_writes equals the size of the testfile
#
function fill_fs # destdir dirnum filenum bytes num_writes data
{
	typeset destdir=${1:-$TESTDIR}
	typeset -i dirnum=${2:-50}
	typeset -i filenum=${3:-50}
	typeset -i bytes=${4:-8192}
	typeset -i num_writes=${5:-10240}
	typeset data=${6:-0}

	mkdir -p $destdir/{1..$dirnum}
	for f in $destdir/{1..$dirnum}/$TESTFILE{1..$filenum}; do
		file_write -o create -f $f -b $bytes -c $num_writes -d $data \
		|| return
	done
}

# Get the specified dataset property in parsable format or fail
function get_prop # property dataset
{
	typeset prop=$1
	typeset dataset=$2

	zfs get -Hpo value "$prop" "$dataset" || log_fail "zfs get $prop $dataset"
}

# Get the specified pool property in parsable format or fail
function get_pool_prop # property pool
{
	typeset prop=$1
	typeset pool=$2

	zpool get -Hpo value "$prop" "$pool" || log_fail "zpool get $prop $pool"
}

# Return 0 if a pool exists; $? otherwise
#
# $1 - pool name

function poolexists
{
	typeset pool=$1

	if [[ -z $pool ]]; then
		log_note "No pool name given."
		return 1
	fi

	zpool get name "$pool" > /dev/null 2>&1
}

# Return 0 if all the specified datasets exist; $? otherwise
#
# $1-n  dataset name
function datasetexists
{
	if (($# == 0)); then
		log_note "No dataset name given."
		return 1
	fi

	zfs get name "$@" > /dev/null 2>&1
}

# return 0 if none of the specified datasets exists, otherwise return 1.
#
# $1-n  dataset name
function datasetnonexists
{
	if (($# == 0)); then
		log_note "No dataset name given."
		return 1
	fi

	while (($# > 0)); do
		zfs list -H -t filesystem,snapshot,volume $1 > /dev/null 2>&1 \
		    && return 1
		shift
	done

	return 0
}

# FreeBSD breaks exports(5) at whitespace and doesn't process escapes
# Solaris just breaks
#
# cf. https://github.com/openzfs/zfs/pull/13165#issuecomment-1059845807
#
# Linux can have spaces (which are \OOO-escaped),
# but can't have backslashes because they're parsed recursively
function shares_can_have_whitespace
{
	is_linux
}

function is_shared_freebsd
{
	typeset fs=$1

	pgrep -q mountd && showmount -E | grep -qx "$fs"
}

function is_shared_illumos
{
	typeset fs=$1
	typeset mtpt

	for mtpt in `share | awk '{print $2}'` ; do
		if [[ $mtpt == $fs ]] ; then
			return 0
		fi
	done

	typeset stat=$(svcs -H -o STA nfs/server:default)
	if [[ $stat != "ON" ]]; then
		log_note "Current nfs/server status: $stat"
	fi

	return 1
}

function is_shared_linux
{
	typeset fs=$1
	! exportfs -s | awk -v fs="${fs//\\/\\\\}" '/^\// && $1 == fs {exit 1}'
}

#
# Given a mountpoint, or a dataset name, determine if it is shared via NFS.
#
# Returns 0 if shared, 1 otherwise.
#
function is_shared
{
	typeset fs=$1
	typeset mtpt

	if [[ $fs != "/"* ]] ; then
		if datasetnonexists "$fs" ; then
			return 1
		else
			mtpt=$(get_prop mountpoint "$fs")
			case "$mtpt" in
				none|legacy|-) return 1
					;;
				*)	fs=$mtpt
					;;
			esac
		fi
	fi

	case "$UNAME" in
	FreeBSD)	is_shared_freebsd "$fs"	;;
	Linux)		is_shared_linux "$fs"	;;
	*)		is_shared_illumos "$fs"	;;
	esac
}

function is_exported_illumos
{
	typeset fs=$1
	typeset mtpt _

	while read -r mtpt _; do
		[ "$mtpt" = "$fs" ] && return
	done < /etc/dfs/sharetab

	return 1
}

function is_exported_freebsd
{
	typeset fs=$1
	typeset mtpt _

	while read -r mtpt _; do
		[ "$mtpt" = "$fs" ] && return
	done < /etc/zfs/exports

	return 1
}

function is_exported_linux
{
	typeset fs=$1
	typeset mtpt _

	while read -r mtpt _; do
		[ "$(printf "$mtpt")" = "$fs" ] && return
	done < /etc/exports.d/zfs.exports

	return 1
}

#
# Given a mountpoint, or a dataset name, determine if it is exported via
# the os-specific NFS exports file.
#
# Returns 0 if exported, 1 otherwise.
#
function is_exported
{
	typeset fs=$1
	typeset mtpt

	if [[ $fs != "/"* ]] ; then
		if datasetnonexists "$fs" ; then
			return 1
		else
			mtpt=$(get_prop mountpoint "$fs")
			case $mtpt in
				none|legacy|-) return 1
					;;
				*)	fs=$mtpt
					;;
			esac
		fi
	fi

	case "$UNAME" in
	FreeBSD)	is_exported_freebsd "$fs"	;;
	Linux)		is_exported_linux "$fs"	;;
	*)		is_exported_illumos "$fs"	;;
	esac
}

#
# Given a dataset name determine if it is shared via SMB.
#
# Returns 0 if shared, 1 otherwise.
#
function is_shared_smb
{
	typeset fs=$1

	datasetexists "$fs" || return

	if is_linux; then
		net usershare list | grep -xFq "${fs//[-\/]/_}"
	else
		log_note "SMB on $UNAME currently unsupported by the test framework"
		return 1
	fi
}

#
# Given a mountpoint, determine if it is not shared via NFS.
#
# Returns 0 if not shared, 1 otherwise.
#
function not_shared
{
	! is_shared $1
}

#
# Given a dataset determine if it is not shared via SMB.
#
# Returns 0 if not shared, 1 otherwise.
#
function not_shared_smb
{
	! is_shared_smb $1
}

#
# Helper function to unshare a mountpoint.
#
function unshare_fs #fs
{
	typeset fs=$1

	if is_shared $fs || is_shared_smb $fs; then
		log_must zfs unshare $fs
	fi
}

#
# Helper function to share a NFS mountpoint.
#
function share_nfs #fs
{
	typeset fs=$1

	is_shared "$fs" && return

	case "$UNAME" in
	Linux)
		log_must exportfs "*:$fs"
		;;
	FreeBSD)
		typeset mountd
		read -r mountd < /var/run/mountd.pid
		log_must eval "printf '%s\t\n' \"$fs\" >> /etc/zfs/exports"
		log_must kill -s HUP "$mountd"
		;;
	*)
		log_must share -F nfs "$fs"
		;;
	esac

	return 0
}

#
# Helper function to unshare a NFS mountpoint.
#
function unshare_nfs #fs
{
	typeset fs=$1

	! is_shared "$fs" && return

	case "$UNAME" in
	Linux)
		log_must exportfs -u "*:$fs"
		;;
	FreeBSD)
		typeset mountd
		read -r mountd < /var/run/mountd.pid
		awk -v fs="${fs//\\/\\\\}" '$1 != fs' /etc/zfs/exports > /etc/zfs/exports.$$
		log_must mv /etc/zfs/exports.$$ /etc/zfs/exports
		log_must kill -s HUP "$mountd"
		;;
	*)
		log_must unshare -F nfs $fs
		;;
	esac

	return 0
}

#
# Helper function to show NFS shares.
#
function showshares_nfs
{
	case "$UNAME" in
	Linux)
		exportfs -v
		;;
	FreeBSD)
		showmount
		;;
	*)
		share -F nfs
		;;
	esac
}

function check_nfs
{
	case "$UNAME" in
	Linux)
		exportfs -s
		;;
	FreeBSD)
		showmount -e
		;;
	*)
		log_unsupported "Unknown platform"
		;;
	esac || log_unsupported "The NFS utilities are not installed"
}

#
# Check NFS server status and trigger it online.
#
function setup_nfs_server
{
	# Cannot share directory in non-global zone.
	#
	if ! is_global_zone; then
		log_note "Cannot trigger NFS server by sharing in LZ."
		return
	fi

	if is_linux; then
		#
		# Re-synchronize /var/lib/nfs/etab with /etc/exports and
		# /etc/exports.d./* to provide a clean test environment.
		#
		log_must exportfs -r

		log_note "NFS server must be started prior to running ZTS."
		return
	elif is_freebsd; then
		log_must kill -s HUP $(</var/run/mountd.pid)

		log_note "NFS server must be started prior to running ZTS."
		return
	fi

	typeset nfs_fmri="svc:/network/nfs/server:default"
	if [[ $(svcs -Ho STA $nfs_fmri) != "ON" ]]; then
		#
		# Only really sharing operation can enable NFS server
		# to online permanently.
		#
		typeset dummy=/tmp/dummy

		if [[ -d $dummy ]]; then
			log_must rm -rf $dummy
		fi

		log_must mkdir $dummy
		log_must share $dummy

		#
		# Waiting for fmri's status to be the final status.
		# Otherwise, in transition, an asterisk (*) is appended for
		# instances, unshare will reverse status to 'DIS' again.
		#
		# Waiting for 1's at least.
		#
		log_must sleep 1
		timeout=10
		while [[ timeout -ne 0 && $(svcs -Ho STA $nfs_fmri) == *'*' ]]
		do
			log_must sleep 1

			((timeout -= 1))
		done

		log_must unshare $dummy
		log_must rm -rf $dummy
	fi

	log_note "Current NFS status: '$(svcs -Ho STA,FMRI $nfs_fmri)'"
}

#
# To verify whether calling process is in global zone
#
# Return 0 if in global zone, 1 in non-global zone
#
function is_global_zone
{
	if is_linux || is_freebsd; then
		return 0
	else
		typeset cur_zone=$(zonename 2>/dev/null)
		[ $cur_zone = "global" ]
	fi
}

#
# Verify whether test is permitted to run from
# global zone, local zone, or both
#
# $1 zone limit, could be "global", "local", or "both"(no limit)
#
# Return 0 if permitted, otherwise exit with log_unsupported
#
function verify_runnable # zone limit
{
	typeset limit=$1

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

	if is_global_zone ; then
		case $limit in
			global|both)
				;;
			local)	log_unsupported "Test is unable to run from "\
					"global zone."
				;;
			*)	log_note "Warning: unknown limit $limit - " \
					"use both."
				;;
		esac
	else
		case $limit in
			local|both)
				;;
			global)	log_unsupported "Test is unable to run from "\
					"local zone."
				;;
			*)	log_note "Warning: unknown limit $limit - " \
					"use both."
				;;
		esac

		reexport_pool
	fi

	return 0
}

# Return 0 if create successfully or the pool exists; $? otherwise
# Note: In local zones, this function should return 0 silently.
#
# $1 - pool name
# $2-n - [keyword] devs_list

function create_pool #pool devs_list
{
	typeset pool=${1%%/*}

	shift

	if [[ -z $pool ]]; then
		log_note "Missing pool name."
		return 1
	fi

	if poolexists $pool ; then
		destroy_pool $pool
	fi

	if is_global_zone ; then
		[[ -d /$pool ]] && rm -rf /$pool
		log_must zpool create -f $pool $@
	fi

	return 0
}

# Return 0 if destroy successfully or the pool exists; $? otherwise
# Note: In local zones, this function should return 0 silently.
#
# $1 - pool name
# Destroy pool with the given parameters.

function destroy_pool #pool
{
	typeset pool=${1%%/*}
	typeset mtpt

	if [[ -z $pool ]]; then
		log_note "No pool name given."
		return 1
	fi

	if is_global_zone ; then
		if poolexists "$pool" ; then
			mtpt=$(get_prop mountpoint "$pool")

			# At times, syseventd/udev activity can cause attempts
			# to destroy a pool to fail with EBUSY. We retry a few
			# times allowing failures before requiring the destroy
			# to succeed.
			log_must_busy zpool destroy -f $pool

			[[ -d $mtpt ]] && \
				log_must rm -rf $mtpt
		else
			log_note "Pool does not exist. ($pool)"
			return 1
		fi
	fi

	return 0
}

# Return 0 if created successfully; $? otherwise
#
# $1 - dataset name
# $2-n - dataset options

function create_dataset #dataset dataset_options
{
	typeset dataset=$1

	shift

	if [[ -z $dataset ]]; then
		log_note "Missing dataset name."
		return 1
	fi

	if datasetexists $dataset ; then
		destroy_dataset $dataset
	fi

	log_must zfs create $@ $dataset

	return 0
}

# Return 0 if destroy successfully or the dataset exists; $? otherwise
# Note: In local zones, this function should return 0 silently.
#
# $1 - dataset name
# $2 - custom arguments for zfs destroy
# Destroy dataset with the given parameters.

function destroy_dataset # dataset [args]
{
	typeset dataset=$1
	typeset mtpt
	typeset args=${2:-""}

	if [[ -z $dataset ]]; then
		log_note "No dataset name given."
		return 1
	fi

	if is_global_zone ; then
		if datasetexists "$dataset" ; then
			mtpt=$(get_prop mountpoint "$dataset")
			log_must_busy zfs destroy $args $dataset

			[ -d $mtpt ] && log_must rm -rf $mtpt
		else
			log_note "Dataset does not exist. ($dataset)"
			return 1
		fi
	fi

	return 0
}

#
# Reexport TESTPOOL & TESTPOOL(1-4)
#
function reexport_pool
{
	typeset -i cntctr=5
	typeset -i i=0

	while ((i < cntctr)); do
		if ((i == 0)); then
			TESTPOOL=$ZONE_POOL/$ZONE_CTR$i
			if ! ismounted $TESTPOOL; then
				log_must zfs mount $TESTPOOL
			fi
		else
			eval TESTPOOL$i=$ZONE_POOL/$ZONE_CTR$i
			if eval ! ismounted \$TESTPOOL$i; then
				log_must eval zfs mount \$TESTPOOL$i
			fi
		fi
		((i += 1))
	done
}

#
# Verify a given disk or pool state
#
# Return 0 is pool/disk matches expected state, 1 otherwise
#
function check_state # pool disk state{online,offline,degraded}
{
	typeset pool=$1
	typeset disk=${2#$DEV_DSKDIR/}
	typeset state=$3

	[[ -z $pool ]] || [[ -z $state ]] \
	    && log_fail "Arguments invalid or missing"

	if [[ -z $disk ]]; then
		#check pool state only
		zpool get -H -o value health $pool | grep -qi "$state"
	else
		zpool status -v $pool | grep "$disk" | grep -qi "$state"
	fi
}

#
# Get the mountpoint of snapshot
# For the snapshot use <mp_filesystem>/.zfs/snapshot/<snap>
# as its mountpoint
#
function snapshot_mountpoint
{
	typeset dataset=${1:-$TESTPOOL/$TESTFS@$TESTSNAP}

	if [[ $dataset != *@* ]]; then
		log_fail "Error name of snapshot '$dataset'."
	fi

	typeset fs=${dataset%@*}
	typeset snap=${dataset#*@}

	if [[ -z $fs || -z $snap ]]; then
		log_fail "Error name of snapshot '$dataset'."
	fi

	echo $(get_prop mountpoint $fs)/.zfs/snapshot/$snap
}

#
# Given a device and 'ashift' value verify it's correctly set on every label
#
function verify_ashift # device ashift
{
	typeset device="$1"
	typeset ashift="$2"

	zdb -e -lll $device | awk -v ashift=$ashift '
	    /ashift: / {
	        if (ashift != $2)
	            exit 1;
	        else
	            count++;
	    }
	    END {
	        exit (count != 4);
	    }'
}

#
# Given a pool and file system, this function will verify the file system
# using the zdb internal tool. Note that the pool is exported and imported
# to ensure it has consistent state.
#
function verify_filesys # pool filesystem dir
{
	typeset pool="$1"
	typeset filesys="$2"
	typeset zdbout="/tmp/zdbout.$$"

	shift
	shift
	typeset dirs=$@
	typeset search_path=""

	log_note "Calling zdb to verify filesystem '$filesys'"
	zfs unmount -a > /dev/null 2>&1
	log_must zpool export $pool

	if [[ -n $dirs ]] ; then
		for dir in $dirs ; do
			search_path="$search_path -d $dir"
		done
	fi

	log_must zpool import $search_path $pool

	if ! zdb -cudi $filesys > $zdbout 2>&1; then
		log_note "Output: zdb -cudi $filesys"
		cat $zdbout
		rm -f $zdbout
		log_fail "zdb detected errors with: '$filesys'"
	fi

	log_must zfs mount -a
	log_must rm -rf $zdbout
}

#
# Given a pool issue a scrub and verify that no checksum errors are reported.
#
function verify_pool
{
	typeset pool=${1:-$TESTPOOL}

	log_must zpool scrub $pool
	log_must wait_scrubbed $pool

	typeset -i cksum=$(zpool status $pool | awk '
	    !NF { isvdev = 0 }
	    isvdev { errors += $NF }
	    /CKSUM$/ { isvdev = 1 }
	    END { print errors }
	')
	if [[ $cksum != 0 ]]; then
		log_must zpool status -v
	        log_fail "Unexpected CKSUM errors found on $pool ($cksum)"
	fi
}

#
# Given a pool, and this function list all disks in the pool
#
function get_disklist # pool
{
	echo $(zpool iostat -v $1 | awk '(NR > 4) {print $1}' | \
	    grep -vEe '^-----' -e "^(mirror|raidz[1-3]|draid[1-3]|spare|log|cache|special|dedup)|\-[0-9]$")
}

#
# Given a pool, and this function list all disks in the pool with their full
# path (like "/dev/sda" instead of "sda").
#
function get_disklist_fullpath # pool
{
	get_disklist "-P $1"
}



# /**
#  This function kills a given list of processes after a time period. We use
#  this in the stress tests instead of STF_TIMEOUT so that we can have processes
#  run for a fixed amount of time, yet still pass. Tests that hit STF_TIMEOUT
#  would be listed as FAIL, which we don't want : we're happy with stress tests
#  running for a certain amount of time, then finishing.
#
# @param $1 the time in seconds after which we should terminate these processes
# @param $2..$n the processes we wish to terminate.
# */
function stress_timeout
{
	typeset -i TIMEOUT=$1
	shift
	typeset cpids="$@"

	log_note "Waiting for child processes($cpids). " \
		"It could last dozens of minutes, please be patient ..."
	log_must sleep $TIMEOUT

	log_note "Killing child processes after ${TIMEOUT} stress timeout."
	typeset pid
	for pid in $cpids; do
		ps -p $pid > /dev/null 2>&1 &&
			log_must kill -USR1 $pid
	done
}

#
# Verify a given hotspare disk is inuse or avail
#
# Return 0 is pool/disk matches expected state, 1 otherwise
#
function check_hotspare_state # pool disk state{inuse,avail}
{
	typeset pool=$1
	typeset disk=${2#$DEV_DSKDIR/}
	typeset state=$3

	cur_state=$(get_device_state $pool $disk "spares")

	[ $state = $cur_state ]
}

#
# Wait until a hotspare transitions to a given state or times out.
#
# Return 0 when  pool/disk matches expected state, 1 on timeout.
#
function wait_hotspare_state # pool disk state timeout
{
	typeset pool=$1
	typeset disk=${2#*$DEV_DSKDIR/}
	typeset state=$3
	typeset timeout=${4:-60}
	typeset -i i=0

	while [[ $i -lt $timeout ]]; do
		if check_hotspare_state $pool $disk $state; then
			return 0
		fi

		i=$((i+1))
		sleep 1
	done

	return 1
}

#
# Verify a given vdev disk is inuse or avail
#
# Return 0 is pool/disk matches expected state, 1 otherwise
#
function check_vdev_state # pool disk state{online,offline,unavail,removed}
{
	typeset pool=$1
	typeset disk=${2#*$DEV_DSKDIR/}
	typeset state=$3

	cur_state=$(get_device_state $pool $disk)

	[ $state = $cur_state ]
}

#
# Wait until a vdev transitions to a given state or times out.
#
# Return 0 when  pool/disk matches expected state, 1 on timeout.
#
function wait_vdev_state # pool disk state timeout
{
	typeset pool=$1
	typeset disk=${2#*$DEV_DSKDIR/}
	typeset state=$3
	typeset timeout=${4:-60}
	typeset -i i=0

	while [[ $i -lt $timeout ]]; do
		if check_vdev_state $pool $disk $state; then
			return 0
		fi

		i=$((i+1))
		sleep 1
	done

	return 1
}

#
# Check the output of 'zpool status -v <pool>',
# and to see if the content of <token> contain the <keyword> specified.
#
# Return 0 is contain, 1 otherwise
#
function check_pool_status # pool token keyword <verbose>
{
	typeset pool=$1
	typeset token=$2
	typeset keyword=$3
	typeset verbose=${4:-false}

	scan=$(zpool status -v "$pool" 2>/dev/null | awk -v token="$token:" '$1==token')
	if [[ $verbose == true ]]; then
		log_note $scan
	fi
	echo $scan | grep -qi "$keyword"
}

#
# The following functions are instance of check_pool_status()
#	is_pool_resilvering - to check if the pool resilver is in progress
#	is_pool_resilvered - to check if the pool resilver is completed
#	is_pool_scrubbing - to check if the pool scrub is in progress
#	is_pool_scrubbed - to check if the pool scrub is completed
#	is_pool_scrub_stopped - to check if the pool scrub is stopped
#	is_pool_scrub_paused - to check if the pool scrub has paused
#	is_pool_removing - to check if the pool removing is a vdev
#	is_pool_removed - to check if the pool remove is completed
#	is_pool_discarding - to check if the pool checkpoint is being discarded
#	is_pool_replacing - to check if the pool is performing a replacement
#
function is_pool_resilvering #pool <verbose>
{
	check_pool_status "$1" "scan" \
	    "resilver[ ()0-9A-Za-z:_-]* in progress since" $2
}

function is_pool_resilvered #pool <verbose>
{
	check_pool_status "$1" "scan" "resilvered " $2
}

function is_pool_scrubbing #pool <verbose>
{
	check_pool_status "$1" "scan" "scrub in progress since " $2
}

function is_pool_scrubbed #pool <verbose>
{
	check_pool_status "$1" "scan" "scrub repaired" $2
}

function is_pool_scrub_stopped #pool <verbose>
{
	check_pool_status "$1" "scan" "scrub canceled" $2
}

function is_pool_scrub_paused #pool <verbose>
{
	check_pool_status "$1" "scan" "scrub paused since " $2
}

function is_pool_removing #pool
{
	check_pool_status "$1" "remove" "in progress since "
}

function is_pool_removed #pool
{
	check_pool_status "$1" "remove" "completed on"
}

function is_pool_discarding #pool
{
	check_pool_status "$1" "checkpoint" "discarding"
}
function is_pool_replacing #pool
{
	zpool status "$1" | grep -qE 'replacing-[0-9]+'
}

function wait_for_degraded
{
	typeset pool=$1
	typeset timeout=${2:-30}
	typeset t0=$SECONDS

	while :; do
		[[ $(get_pool_prop health $pool) == "DEGRADED" ]] && break
		log_note "$pool is not yet degraded."
		sleep 1
		if ((SECONDS - t0 > $timeout)); then
			log_note "$pool not degraded after $timeout seconds."
			return 1
		fi
	done

	return 0
}

#
# Use create_pool()/destroy_pool() to clean up the information in
# in the given disk to avoid slice overlapping.
#
function cleanup_devices #vdevs
{
	typeset pool="foopool$$"

	for vdev in $@; do
		zero_partitions $vdev
	done

	poolexists $pool && destroy_pool $pool
	create_pool $pool $@
	destroy_pool $pool

	return 0
}

#/**
# A function to find and locate free disks on a system or from given
# disks as the parameter. It works by locating disks that are in use
# as swap devices and dump devices, and also disks listed in /etc/vfstab
#
# $@ given disks to find which are free, default is all disks in
# the test system
#
# @return a string containing the list of available disks
#*/
function find_disks
{
	# Trust provided list, no attempt is made to locate unused devices.
	if is_linux || is_freebsd; then
		echo "$@"
		return
	fi


	sfi=/tmp/swaplist.$$
	dmpi=/tmp/dumpdev.$$
	max_finddisksnum=${MAX_FINDDISKSNUM:-6}

	swap -l > $sfi
	dumpadm > $dmpi 2>/dev/null

	disks=${@:-$(echo "" | format -e 2>/dev/null | awk '
BEGIN { FS="."; }

/^Specify disk/{
	searchdisks=0;
}

{
	if (searchdisks && $2 !~ "^$"){
		split($2,arr," ");
		print arr[1];
	}
}

/^AVAILABLE DISK SELECTIONS:/{
	searchdisks=1;
}
')}

	unused=""
	for disk in $disks; do
	# Check for mounted
		grep -q "${disk}[sp]" /etc/mnttab && continue
	# Check for swap
		grep -q "${disk}[sp]" $sfi && continue
	# check for dump device
		grep -q "${disk}[sp]" $dmpi && continue
	# check to see if this disk hasn't been explicitly excluded
	# by a user-set environment variable
		echo "${ZFS_HOST_DEVICES_IGNORE}" | grep -q "${disk}" && continue
		unused_candidates="$unused_candidates $disk"
	done
	rm $sfi $dmpi

# now just check to see if those disks do actually exist
# by looking for a device pointing to the first slice in
# each case. limit the number to max_finddisksnum
	count=0
	for disk in $unused_candidates; do
		if is_disk_device $DEV_DSKDIR/${disk}s0 && \
		    [ $count -lt $max_finddisksnum ]; then
			unused="$unused $disk"
			# do not impose limit if $@ is provided
			[[ -z $@ ]] && ((count = count + 1))
		fi
	done

# finally, return our disk list
	echo $unused
}

function add_user_freebsd #<group_name> <user_name> <basedir>
{
	typeset group=$1
	typeset user=$2
	typeset basedir=$3

	# Check to see if the user exists.
	if id $user > /dev/null 2>&1; then
		return 0
	fi

	# Assign 1000 as the base uid
	typeset -i uid=1000
	while true; do
		pw useradd -u $uid -g $group -d $basedir/$user -m -n $user
		case $? in
			0) break ;;
			# The uid is not unique
			65) ((uid += 1)) ;;
			*) return 1 ;;
		esac
		if [[ $uid == 65000 ]]; then
			log_fail "No user id available under 65000 for $user"
		fi
	done

	# Silence MOTD
	touch $basedir/$user/.hushlogin

	return 0
}

#
# Delete the specified user.
#
# $1 login name
#
function del_user_freebsd #<logname>
{
	typeset user=$1

	if id $user > /dev/null 2>&1; then
		log_must pw userdel $user
	fi

	return 0
}

#
# Select valid gid and create specified group.
#
# $1 group name
#
function add_group_freebsd #<group_name>
{
	typeset group=$1

	# See if the group already exists.
	if pw groupshow $group >/dev/null 2>&1; then
		return 0
	fi

	# Assign 1000 as the base gid
	typeset -i gid=1000
	while true; do
		pw groupadd -g $gid -n $group > /dev/null 2>&1
		case $? in
			0) return 0 ;;
			# The gid is not  unique
			65) ((gid += 1)) ;;
			*) return 1 ;;
		esac
		if [[ $gid == 65000 ]]; then
			log_fail "No user id available under 65000 for $group"
		fi
	done
}

#
# Delete the specified group.
#
# $1 group name
#
function del_group_freebsd #<group_name>
{
	typeset group=$1

	pw groupdel -n $group > /dev/null 2>&1
	case $? in
		# Group does not exist, or was deleted successfully.
		0|6|65) return 0 ;;
		# Name already exists as a group name
		9) log_must pw groupdel $group ;;
		*) return 1 ;;
	esac

	return 0
}

function add_user_illumos #<group_name> <user_name> <basedir>
{
	typeset group=$1
	typeset user=$2
	typeset basedir=$3

	log_must useradd -g $group -d $basedir/$user -m $user

	return 0
}

function del_user_illumos #<user_name>
{
	typeset user=$1

	if id $user > /dev/null 2>&1; then
		log_must_retry "currently used" 6 userdel $user
	fi

	return 0
}

function add_group_illumos #<group_name>
{
	typeset group=$1

	typeset -i gid=100
	while true; do
		groupadd -g $gid $group > /dev/null 2>&1
		case $? in
			0) return 0 ;;
			# The gid is not  unique
			4) ((gid += 1)) ;;
			*) return 1 ;;
		esac
	done
}

function del_group_illumos #<group_name>
{
	typeset group=$1

	groupmod -n $grp $grp > /dev/null 2>&1
	case $? in
		# Group does not exist.
		6) return 0 ;;
		# Name already exists as a group name
		9) log_must groupdel $grp ;;
		*) return 1 ;;
	esac
}

function add_user_linux #<group_name> <user_name> <basedir>
{
	typeset group=$1
	typeset user=$2
	typeset basedir=$3

	log_must useradd -g $group -d $basedir/$user -m $user

	# Add new users to the same group and the command line utils.
	# This allows them to be run out of the original users home
	# directory as long as it permissioned to be group readable.
	cmd_group=$(stat --format="%G" $(command -v zfs))
	log_must usermod -a -G $cmd_group $user

	return 0
}

function del_user_linux #<user_name>
{
	typeset user=$1

	if id $user > /dev/null 2>&1; then
		log_must_retry "currently used" 6 userdel $user
	fi
}

function add_group_linux #<group_name>
{
	typeset group=$1

	# Assign 100 as the base gid, a larger value is selected for
	# Linux because for many distributions 1000 and under are reserved.
	while true; do
		groupadd $group > /dev/null 2>&1
		case $? in
			0) return 0 ;;
			*) return 1 ;;
		esac
	done
}

function del_group_linux #<group_name>
{
	typeset group=$1

	getent group $group > /dev/null 2>&1
	case $? in
		# Group does not exist.
		2) return 0 ;;
		# Name already exists as a group name
		0) log_must groupdel $group ;;
		*) return 1 ;;
	esac

	return 0
}

#
# Add specified user to specified group
#
# $1 group name
# $2 user name
# $3 base of the homedir (optional)
#
function add_user #<group_name> <user_name> <basedir>
{
	typeset group=$1
	typeset user=$2
	typeset basedir=${3:-"/var/tmp"}

	if ((${#group} == 0 || ${#user} == 0)); then
		log_fail "group name or user name are not defined."
	fi

	case "$UNAME" in
	FreeBSD)
		add_user_freebsd "$group" "$user" "$basedir"
		;;
	Linux)
		add_user_linux "$group" "$user" "$basedir"
		;;
	*)
		add_user_illumos "$group" "$user" "$basedir"
		;;
	esac

	return 0
}

#
# Delete the specified user.
#
# $1 login name
# $2 base of the homedir (optional)
#
function del_user #<logname> <basedir>
{
	typeset user=$1
	typeset basedir=${2:-"/var/tmp"}

	if ((${#user} == 0)); then
		log_fail "login name is necessary."
	fi

	case "$UNAME" in
	FreeBSD)
		del_user_freebsd "$user"
		;;
	Linux)
		del_user_linux "$user"
		;;
	*)
		del_user_illumos "$user"
		;;
	esac

	[[ -d $basedir/$user ]] && rm -fr $basedir/$user

	return 0
}

#
# Select valid gid and create specified group.
#
# $1 group name
#
function add_group #<group_name>
{
	typeset group=$1

	if ((${#group} == 0)); then
		log_fail "group name is necessary."
	fi

	case "$UNAME" in
	FreeBSD)
		add_group_freebsd "$group"
		;;
	Linux)
		add_group_linux "$group"
		;;
	*)
		add_group_illumos "$group"
		;;
	esac

	return 0
}

#
# Delete the specified group.
#
# $1 group name
#
function del_group #<group_name>
{
	typeset group=$1

	if ((${#group} == 0)); then
		log_fail "group name is necessary."
	fi

	case "$UNAME" in
	FreeBSD)
		del_group_freebsd "$group"
		;;
	Linux)
		del_group_linux "$group"
		;;
	*)
		del_group_illumos "$group"
		;;
	esac

	return 0
}

#
# This function will return true if it's safe to destroy the pool passed
# as argument 1. It checks for pools based on zvols and files, and also
# files contained in a pool that may have a different mountpoint.
#
function safe_to_destroy_pool { # $1 the pool name

	typeset pool=""
	typeset DONT_DESTROY=""

	# We check that by deleting the $1 pool, we're not
	# going to pull the rug out from other pools. Do this
	# by looking at all other pools, ensuring that they
	# aren't built from files or zvols contained in this pool.

	for pool in $(zpool list -H -o name)
	do
		ALTMOUNTPOOL=""

		# this is a list of the top-level directories in each of the
		# files that make up the path to the files the pool is based on
		FILEPOOL=$(zpool status -v $pool | awk -v pool="/$1/" '$0 ~ pool {print $1}')

		# this is a list of the zvols that make up the pool
		ZVOLPOOL=$(zpool status -v $pool | awk -v zvols="$ZVOL_DEVDIR/$1$" '$0 ~ zvols {print $1}')

		# also want to determine if it's a file-based pool using an
		# alternate mountpoint...
		POOL_FILE_DIRS=$(zpool status -v $pool | \
					awk '/\// {print $1}' | \
					awk -F/ '!/dev/ {print $2}')

		for pooldir in $POOL_FILE_DIRS
		do
			OUTPUT=$(zfs list -H -r -o mountpoint $1 | \
					awk -v pd="${pooldir}$" '$0 ~ pd {print $1}')

			ALTMOUNTPOOL="${ALTMOUNTPOOL}${OUTPUT}"
		done


		if [ ! -z "$ZVOLPOOL" ]
		then
			DONT_DESTROY="true"
			log_note "Pool $pool is built from $ZVOLPOOL on $1"
		fi

		if [ ! -z "$FILEPOOL" ]
		then
			DONT_DESTROY="true"
			log_note "Pool $pool is built from $FILEPOOL on $1"
		fi

		if [ ! -z "$ALTMOUNTPOOL" ]
		then
			DONT_DESTROY="true"
			log_note "Pool $pool is built from $ALTMOUNTPOOL on $1"
		fi
	done

	if [ -z "${DONT_DESTROY}" ]
	then
		return 0
	else
		log_note "Warning: it is not safe to destroy $1!"
		return 1
	fi
}

#
# Verify zfs operation with -p option work as expected
# $1 operation, value could be create, clone or rename
# $2 dataset type, value could be fs or vol
# $3 dataset name
# $4 new dataset name
#
function verify_opt_p_ops
{
	typeset ops=$1
	typeset datatype=$2
	typeset dataset=$3
	typeset newdataset=$4

	if [[ $datatype != "fs" && $datatype != "vol" ]]; then
		log_fail "$datatype is not supported."
	fi

	# check parameters accordingly
	case $ops in
		create)
			newdataset=$dataset
			dataset=""
			if [[ $datatype == "vol" ]]; then
				ops="create -V $VOLSIZE"
			fi
			;;
		clone)
			if [[ -z $newdataset ]]; then
				log_fail "newdataset should not be empty" \
					"when ops is $ops."
			fi
			log_must datasetexists $dataset
			log_must snapexists $dataset
			;;
		rename)
			if [[ -z $newdataset ]]; then
				log_fail "newdataset should not be empty" \
					"when ops is $ops."
			fi
			log_must datasetexists $dataset
			;;
		*)
			log_fail "$ops is not supported."
			;;
	esac

	# make sure the upper level filesystem does not exist
	destroy_dataset "${newdataset%/*}" "-rRf"

	# without -p option, operation will fail
	log_mustnot zfs $ops $dataset $newdataset
	log_mustnot datasetexists $newdataset ${newdataset%/*}

	# with -p option, operation should succeed
	log_must zfs $ops -p $dataset $newdataset
	block_device_wait

	if ! datasetexists $newdataset ; then
		log_fail "-p option does not work for $ops"
	fi

	# when $ops is create or clone, redo the operation still return zero
	if [[ $ops != "rename" ]]; then
		log_must zfs $ops -p $dataset $newdataset
	fi

	return 0
}

#
# Get configuration of pool
# $1 pool name
# $2 config name
#
function get_config
{
	typeset pool=$1
	typeset config=$2

	if ! poolexists "$pool" ; then
		return 1
	fi
	if [ "$(get_pool_prop cachefile "$pool")" = "none" ]; then
		zdb -e $pool
	else
		zdb -C $pool
	fi | awk -F: -v cfg="$config:" '$0 ~ cfg {sub(/^'\''/, $2); sub(/'\''$/, $2); print $2}'
}

#
# Privated function. Random select one of items from arguments.
#
# $1 count
# $2-n string
#
function _random_get
{
	typeset cnt=$1
	shift

	typeset str="$@"
	typeset -i ind
	((ind = RANDOM % cnt + 1))

	echo "$str" | cut -f $ind -d ' '
}

#
# Random select one of item from arguments which include NONE string
#
function random_get_with_non
{
	typeset -i cnt=$#
	((cnt =+ 1))

	_random_get "$cnt" "$@"
}

#
# Random select one of item from arguments which doesn't include NONE string
#
function random_get
{
	_random_get "$#" "$@"
}

#
# The function will generate a dataset name with specific length
# $1, the length of the name
# $2, the base string to construct the name
#
function gen_dataset_name
{
	typeset -i len=$1
	typeset basestr="$2"
	typeset -i baselen=${#basestr}
	typeset -i iter=0
	typeset l_name=""

	if ((len % baselen == 0)); then
		((iter = len / baselen))
	else
		((iter = len / baselen + 1))
	fi
	while ((iter > 0)); do
		l_name="${l_name}$basestr"

		((iter -= 1))
	done

	echo $l_name
}

#
# Get cksum tuple of dataset
# $1 dataset name
#
# sample zdb output:
# Dataset data/test [ZPL], ID 355, cr_txg 2413856, 31.0K, 7 objects, rootbp
# DVA[0]=<0:803046400:200> DVA[1]=<0:81199000:200> [L0 DMU objset] fletcher4
# lzjb LE contiguous unique double size=800L/200P birth=2413856L/2413856P
# fill=7 cksum=11ce125712:643a9c18ee2:125e25238fca0:254a3f74b59744
function datasetcksum
{
	typeset cksum
	sync
	sync_all_pools
	zdb -vvv $1 | awk -F= -v ds="^Dataset $1 "'\\[' '$0 ~ ds && /cksum/ {print $7}'
}

#
# Get the given disk/slice state from the specific field of the pool
#
function get_device_state #pool disk field("", "spares","logs")
{
	typeset pool=$1
	typeset disk=${2#$DEV_DSKDIR/}
	typeset field=${3:-$pool}

	zpool status -v "$pool" 2>/dev/null | \
		awk -v device=$disk -v pool=$pool -v field=$field \
		'BEGIN {startconfig=0; startfield=0; }
		/config:/ {startconfig=1}
		(startconfig==1) && ($1==field) {startfield=1; next;}
		(startfield==1) && ($1==device) {print $2; exit;}
		(startfield==1) &&
		($1==field || $1 ~ "^spares$" || $1 ~ "^logs$") {startfield=0}'
}

#
# get the root filesystem name if it's zfsroot system.
#
# return: root filesystem name
function get_rootfs
{
	typeset rootfs=""

	if is_freebsd; then
		rootfs=$(mount -p | awk '$2 == "/" && $3 == "zfs" {print $1}')
	elif ! is_linux; then
		rootfs=$(awk '$2 == "/" && $3 == "zfs" {print $1}' \
			/etc/mnttab)
	fi
	if [[ -z "$rootfs" ]]; then
		log_fail "Can not get rootfs"
	fi
	if datasetexists $rootfs; then
		echo $rootfs
	else
		log_fail "This is not a zfsroot system."
	fi
}

#
# get the rootfs's pool name
# return:
#       rootpool name
#
function get_rootpool
{
	typeset rootfs=$(get_rootfs)
	echo ${rootfs%%/*}
}

#
# To verify if the require numbers of disks is given
#
function verify_disk_count
{
	typeset -i min=${2:-1}

	typeset -i count=$(echo "$1" | wc -w)

	if ((count < min)); then
		log_untested "A minimum of $min disks is required to run." \
			" You specified $count disk(s)"
	fi
}

function ds_is_volume
{
	typeset type=$(get_prop type $1)
	[ $type = "volume" ]
}

function ds_is_filesystem
{
	typeset type=$(get_prop type $1)
	[ $type = "filesystem" ]
}

#
# Check if Trusted Extensions are installed and enabled
#
function is_te_enabled
{
	svcs -H -o state labeld 2>/dev/null | grep -q "enabled"
}

# Return the number of CPUs (cross-platform)
function get_num_cpus
{
	if is_linux ; then
		grep -c '^processor' /proc/cpuinfo
	elif is_freebsd; then
		sysctl -n kern.smp.cpus
	else
		psrinfo | wc -l
	fi
}

# Utility function to determine if a system has multiple cpus.
function is_mp
{
	[[ $(get_num_cpus) -gt 1 ]]
}

function get_cpu_freq
{
	if is_linux; then
		lscpu | awk '/CPU MHz/ { print $3 }'
	elif is_freebsd; then
		sysctl -n hw.clockrate
	else
		psrinfo -v 0 | awk '/processor operates at/ {print $6}'
	fi
}

# Run the given command as the user provided.
function user_run
{
	typeset user=$1
	shift

	log_note "user: $user"
	log_note "cmd: $*"

	typeset out=$TEST_BASE_DIR/out
	typeset err=$TEST_BASE_DIR/err

	sudo -Eu $user env PATH="$PATH" ksh <<<"$*" >$out 2>$err
	typeset res=$?
	log_note "out: $(<$out)"
	log_note "err: $(<$err)"
	return $res
}

#
# Check if the pool contains the specified vdevs
#
# $1 pool
# $2..n <vdev> ...
#
# Return 0 if the vdevs are contained in the pool, 1 if any of the specified
# vdevs is not in the pool, and 2 if pool name is missing.
#
function vdevs_in_pool
{
	typeset pool=$1
	typeset vdev

	if [[ -z $pool ]]; then
		log_note "Missing pool name."
		return 2
	fi

	shift

	# We could use 'zpool list' to only get the vdevs of the pool but we
	# can't reference a mirror/raidz vdev using its ID (i.e mirror-0),
	# therefore we use the 'zpool status' output.
	typeset tmpfile=$(mktemp)
	zpool status -v "$pool" | grep -A 1000 "config:" >$tmpfile
	for vdev in "$@"; do
		grep -wq ${vdev##*/} $tmpfile || return 1
	done

	rm -f $tmpfile
	return 0
}

function get_max
{
	typeset -l i max=$1
	shift

	for i in "$@"; do
		max=$((max > i ? max : i))
	done

	echo $max
}

# Write data that can be compressed into a directory
function write_compressible
{
	typeset dir=$1
	typeset megs=$2
	typeset nfiles=${3:-1}
	typeset bs=${4:-1024k}
	typeset fname=${5:-file}

	[[ -d $dir ]] || log_fail "No directory: $dir"

	# Under Linux fio is not currently used since its behavior can
	# differ significantly across versions.  This includes missing
	# command line options and cases where the --buffer_compress_*
	# options fail to behave as expected.
	if is_linux; then
		typeset file_bytes=$(to_bytes $megs)
		typeset bs_bytes=4096
		typeset blocks=$(($file_bytes / $bs_bytes))

		for (( i = 0; i < $nfiles; i++ )); do
			truncate -s $file_bytes $dir/$fname.$i

			# Write every third block to get 66% compression.
			for (( j = 0; j < $blocks; j += 3 )); do
				dd if=/dev/urandom of=$dir/$fname.$i \
				    seek=$j bs=$bs_bytes count=1 \
				    conv=notrunc >/dev/null 2>&1
			done
		done
	else
		command -v fio > /dev/null || log_unsupported "fio missing"
		log_must eval fio \
		    --name=job \
		    --fallocate=0 \
		    --minimal \
		    --randrepeat=0 \
		    --buffer_compress_percentage=66 \
		    --buffer_compress_chunk=4096 \
		    --directory="$dir" \
		    --numjobs="$nfiles" \
		    --nrfiles="$nfiles" \
		    --rw=write \
		    --bs="$bs" \
		    --filesize="$megs" \
		    "--filename_format='$fname.\$jobnum' >/dev/null"
	fi
}

function get_objnum
{
	typeset pathname=$1
	typeset objnum

	[[ -e $pathname ]] || log_fail "No such file or directory: $pathname"
	if is_freebsd; then
		objnum=$(stat -f "%i" $pathname)
	else
		objnum=$(stat -c %i $pathname)
	fi
	echo $objnum
}

#
# Sync data to the pool
#
# $1 pool name
# $2 boolean to force uberblock (and config including zpool cache file) update
#
function sync_pool #pool <force>
{
	typeset pool=${1:-$TESTPOOL}
	typeset force=${2:-false}

	if [[ $force == true ]]; then
		log_must zpool sync -f $pool
	else
		log_must zpool sync $pool
	fi

	return 0
}

#
# Sync all pools
#
# $1 boolean to force uberblock (and config including zpool cache file) update
#
function sync_all_pools #<force>
{
	typeset force=${1:-false}

	if [[ $force == true ]]; then
		log_must zpool sync -f
	else
		log_must zpool sync
	fi

	return 0
}

#
# Wait for zpool 'freeing' property drops to zero.
#
# $1 pool name
#
function wait_freeing #pool
{
	typeset pool=${1:-$TESTPOOL}
	while true; do
		[[ "0" == "$(zpool list -Ho freeing $pool)" ]] && break
		log_must sleep 1
	done
}

#
# Wait for every device replace operation to complete
#
# $1 pool name
# $2 timeout
#
function wait_replacing #pool timeout
{
	typeset timeout=${2:-300}
	typeset pool=${1:-$TESTPOOL}
	for (( timer = 0; timer < $timeout; timer++ )); do
		is_pool_replacing $pool || break;
		sleep 1;
	done
}

# Wait for a pool to be scrubbed
#
# $1 pool name
# $2 timeout
#
function wait_scrubbed #pool timeout
{
       typeset timeout=${2:-300}
       typeset pool=${1:-$TESTPOOL}
       for (( timer = 0; timer < $timeout; timer++ )); do
               is_pool_scrubbed $pool && break;
               sleep 1;
       done
}

# Backup the zed.rc in our test directory so that we can edit it for our test.
#
# Returns: Backup file name.  You will need to pass this to zed_rc_restore().
function zed_rc_backup
{
	zedrc_backup="$(mktemp)"
	cp $ZEDLET_DIR/zed.rc $zedrc_backup
	echo $zedrc_backup
}

function zed_rc_restore
{
	mv $1 $ZEDLET_DIR/zed.rc
}

#
# Setup custom environment for the ZED.
#
# $@ Optional list of zedlets to run under zed.
function zed_setup
{
	if ! is_linux; then
		log_unsupported "No zed on $UNAME"
	fi

	if [[ ! -d $ZEDLET_DIR ]]; then
		log_must mkdir $ZEDLET_DIR
	fi

	if [[ ! -e $VDEVID_CONF ]]; then
		log_must touch $VDEVID_CONF
	fi

	if [[ -e $VDEVID_CONF_ETC ]]; then
		log_fail "Must not have $VDEVID_CONF_ETC file present on system"
	fi
	EXTRA_ZEDLETS=$@

	# Create a symlink for /etc/zfs/vdev_id.conf file.
	log_must ln -s $VDEVID_CONF $VDEVID_CONF_ETC

	# Setup minimal ZED configuration.  Individual test cases should
	# add additional ZEDLETs as needed for their specific test.
	log_must cp ${ZEDLET_ETC_DIR}/zed.rc $ZEDLET_DIR
	log_must cp ${ZEDLET_ETC_DIR}/zed-functions.sh $ZEDLET_DIR

	# Scripts must only be user writable.
	if [[ -n "$EXTRA_ZEDLETS" ]] ; then
		saved_umask=$(umask)
		log_must umask 0022
		for i in $EXTRA_ZEDLETS ; do
			log_must cp ${ZEDLET_LIBEXEC_DIR}/$i $ZEDLET_DIR
		done
		log_must umask $saved_umask
	fi

	# Customize the zed.rc file to enable the full debug log.
	log_must sed -i '/\#ZED_DEBUG_LOG=.*/d' $ZEDLET_DIR/zed.rc
	echo "ZED_DEBUG_LOG=$ZED_DEBUG_LOG" >>$ZEDLET_DIR/zed.rc

}

#
# Cleanup custom ZED environment.
#
# $@ Optional list of zedlets to remove from our test zed.d directory.
function zed_cleanup
{
	if ! is_linux; then
		return
	fi

	for extra_zedlet; do
		log_must rm -f ${ZEDLET_DIR}/$extra_zedlet
	done
	log_must rm -fd ${ZEDLET_DIR}/zed.rc ${ZEDLET_DIR}/zed-functions.sh ${ZEDLET_DIR}/all-syslog.sh ${ZEDLET_DIR}/all-debug.sh ${ZEDLET_DIR}/state \
	                $ZED_LOG $ZED_DEBUG_LOG $VDEVID_CONF_ETC $VDEVID_CONF \
	                $ZEDLET_DIR
}

#
# Check if ZED is currently running; if so, returns PIDs
#
function zed_check
{
	if ! is_linux; then
		return
	fi
	zedpids="$(pgrep -x zed)"
	zedpids2="$(pgrep -x lt-zed)"
	echo ${zedpids} ${zedpids2}
}

#
# Check if ZED is currently running, if not start ZED.
#
function zed_start
{
	if ! is_linux; then
		return
	fi

	# ZEDLET_DIR=/var/tmp/zed
	if [[ ! -d $ZEDLET_DIR ]]; then
		log_must mkdir $ZEDLET_DIR
	fi

	# Verify the ZED is not already running.
	zedpids=$(zed_check)
	if [ -n "$zedpids" ]; then
		# We never, ever, really want it to just keep going if zed
		# is already running - usually this implies our test cases
		# will break very strangely because whatever we wanted to
		# configure zed for won't be listening to our changes in the
		# tmpdir
		log_fail "ZED already running - ${zedpids}"
	else
		log_note "Starting ZED"
		# run ZED in the background and redirect foreground logging
		# output to $ZED_LOG.
		log_must truncate -s 0 $ZED_DEBUG_LOG
		log_must eval "zed -vF -d $ZEDLET_DIR -P $PATH" \
		    "-s $ZEDLET_DIR/state -j 1 2>$ZED_LOG &"
	fi

	return 0
}

#
# Kill ZED process
#
function zed_stop
{
	if ! is_linux; then
		return ""
	fi

	log_note "Stopping ZED"
	while true; do
		zedpids=$(zed_check)
		[ ! -n "$zedpids" ] && break

		log_must kill $zedpids
		sleep 1
	done
	return 0
}

#
# Drain all zevents
#
function zed_events_drain
{
	while [ $(zpool events -H | wc -l) -ne 0 ]; do
		sleep 1
		zpool events -c >/dev/null
	done
}

# Set a variable in zed.rc to something, un-commenting it in the process.
#
# $1 variable
# $2 value
function zed_rc_set
{
	var="$1"
	val="$2"
	# Remove the line
	cmd="'/$var/d'"
	eval sed -i $cmd $ZEDLET_DIR/zed.rc

	# Add it at the end
	echo "$var=$val" >> $ZEDLET_DIR/zed.rc
}


#
# Check is provided device is being active used as a swap device.
#
function is_swap_inuse
{
	typeset device=$1

	if [[ -z $device ]] ; then
		log_note "No device specified."
		return 1
	fi

	case "$UNAME" in
	Linux)
		swapon -s | grep -wq $(readlink -f $device)
		;;
	FreeBSD)
		swapctl -l | grep -wq $device
		;;
	*)
		swap -l | grep -wq $device
		;;
	esac
}

#
# Setup a swap device using the provided device.
#
function swap_setup
{
	typeset swapdev=$1

	case "$UNAME" in
	Linux)
		log_must eval "mkswap $swapdev > /dev/null 2>&1"
		log_must swapon $swapdev
		;;
	FreeBSD)
		log_must swapctl -a $swapdev
		;;
	*)
    log_must swap -a $swapdev
		;;
	esac

	return 0
}

#
# Cleanup a swap device on the provided device.
#
function swap_cleanup
{
	typeset swapdev=$1

	if is_swap_inuse $swapdev; then
		if is_linux; then
			log_must swapoff $swapdev
		elif is_freebsd; then
			log_must swapoff $swapdev
		else
			log_must swap -d $swapdev
		fi
	fi

	return 0
}

#
# Set a global system tunable (64-bit value)
#
# $1 tunable name (use a NAME defined in tunables.cfg)
# $2 tunable values
#
function set_tunable64
{
	set_tunable_impl "$1" "$2" Z
}

#
# Set a global system tunable (32-bit value)
#
# $1 tunable name (use a NAME defined in tunables.cfg)
# $2 tunable values
#
function set_tunable32
{
	set_tunable_impl "$1" "$2" W
}

function set_tunable_impl
{
	typeset name="$1"
	typeset value="$2"
	typeset mdb_cmd="$3"

	eval "typeset tunable=\$$name"
	case "$tunable" in
	UNSUPPORTED)
		log_unsupported "Tunable '$name' is unsupported on $UNAME"
		;;
	"")
		log_fail "Tunable '$name' must be added to tunables.cfg"
		;;
	*)
		;;
	esac

	[[ -z "$value" ]] && return 1
	[[ -z "$mdb_cmd" ]] && return 1

	case "$UNAME" in
	Linux)
		typeset zfs_tunables="/sys/module/zfs/parameters"
		echo "$value" >"$zfs_tunables/$tunable"
		;;
	FreeBSD)
		sysctl vfs.zfs.$tunable=$value
		;;
	SunOS)
		echo "${tunable}/${mdb_cmd}0t${value}" | mdb -kw
		;;
	esac
}

#
# Get a global system tunable
#
# $1 tunable name (use a NAME defined in tunables.cfg)
#
function get_tunable
{
	get_tunable_impl "$1"
}

function get_tunable_impl
{
	typeset name="$1"
	typeset module="${2:-zfs}"
	typeset check_only="$3"

	eval "typeset tunable=\$$name"
	case "$tunable" in
	UNSUPPORTED)
		if [ -z "$check_only" ] ; then
			log_unsupported "Tunable '$name' is unsupported on $UNAME"
		else
			return 1
		fi
		;;
	"")
		if [ -z "$check_only" ] ; then
			log_fail "Tunable '$name' must be added to tunables.cfg"
		else
			return 1
		fi
		;;
	*)
		;;
	esac

	case "$UNAME" in
	Linux)
		typeset zfs_tunables="/sys/module/$module/parameters"
		cat $zfs_tunables/$tunable
		;;
	FreeBSD)
		sysctl -n vfs.zfs.$tunable
		;;
	SunOS)
		[[ "$module" -eq "zfs" ]] || return 1
		;;
	esac
}

# Does a tunable exist?
#
# $1: Tunable name
function tunable_exists
{
	get_tunable_impl $1 "zfs" 1
}

#
# Compute MD5 digest for given file or stdin if no file given.
# Note: file path must not contain spaces
#
function md5digest
{
	typeset file=$1

	case "$UNAME" in
	FreeBSD)
		md5 -q $file
		;;
	*)
		typeset sum _
		read -r sum _ < <(md5sum -b $file)
		echo $sum
		;;
	esac
}

#
# Compute SHA256 digest for given file or stdin if no file given.
# Note: file path must not contain spaces
#
function sha256digest
{
	typeset file=$1

	case "$UNAME" in
	FreeBSD)
		sha256 -q $file
		;;
	*)
		typeset sum _
		read -r sum _ < <(sha256sum -b $file)
		echo $sum
		;;
	esac
}

function new_fs #<args>
{
	case "$UNAME" in
	FreeBSD)
		newfs "$@"
		;;
	*)
		echo y | newfs -v "$@"
		;;
	esac
}

function stat_size #<path>
{
	typeset path=$1

	case "$UNAME" in
	FreeBSD)
		stat -f %z "$path"
		;;
	*)
		stat -c %s "$path"
		;;
	esac
}

function stat_mtime #<path>
{
	typeset path=$1

	case "$UNAME" in
	FreeBSD)
		stat -f %m "$path"
		;;
	*)
		stat -c %Y "$path"
		;;
	esac
}

function stat_ctime #<path>
{
	typeset path=$1

	case "$UNAME" in
	FreeBSD)
		stat -f %c "$path"
		;;
	*)
		stat -c %Z "$path"
		;;
	esac
}

function stat_crtime #<path>
{
	typeset path=$1

	case "$UNAME" in
	FreeBSD)
		stat -f %B "$path"
		;;
	*)
		stat -c %W "$path"
		;;
	esac
}

function stat_generation #<path>
{
	typeset path=$1

	case "$UNAME" in
	Linux)
		getversion "${path}"
		;;
	*)
		stat -f %v "${path}"
		;;
	esac
}

# Run a command as if it was being run in a TTY.
#
# Usage:
#
#    faketty command
#
function faketty
{
    if is_freebsd; then
        script -q /dev/null env "$@"
    else
        script --return --quiet -c "$*" /dev/null
    fi
}

#
# Produce a random permutation of the integers in a given range (inclusive).
#
function range_shuffle # begin end
{
	typeset -i begin=$1
	typeset -i end=$2

	seq ${begin} ${end} | sort -R
}

#
# Cross-platform xattr helpers
#

function get_xattr # name path
{
	typeset name=$1
	typeset path=$2

	case "$UNAME" in
	FreeBSD)
		getextattr -qq user "${name}" "${path}"
		;;
	*)
		attr -qg "${name}" "${path}"
		;;
	esac
}

function set_xattr # name value path
{
	typeset name=$1
	typeset value=$2
	typeset path=$3

	case "$UNAME" in
	FreeBSD)
		setextattr user "${name}" "${value}" "${path}"
		;;
	*)
		attr -qs "${name}" -V "${value}" "${path}"
		;;
	esac
}

function set_xattr_stdin # name value
{
	typeset name=$1
	typeset path=$2

	case "$UNAME" in
	FreeBSD)
		setextattr -i user "${name}" "${path}"
		;;
	*)
		attr -qs "${name}" "${path}"
		;;
	esac
}

function rm_xattr # name path
{
	typeset name=$1
	typeset path=$2

	case "$UNAME" in
	FreeBSD)
		rmextattr -q user "${name}" "${path}"
		;;
	*)
		attr -qr "${name}" "${path}"
		;;
	esac
}

function ls_xattr # path
{
	typeset path=$1

	case "$UNAME" in
	FreeBSD)
		lsextattr -qq user "${path}"
		;;
	*)
		attr -ql "${path}"
		;;
	esac
}

function kstat # stat flags?
{
	typeset stat=$1
	typeset flags=${2-"-n"}

	case "$UNAME" in
	FreeBSD)
		sysctl $flags kstat.zfs.misc.$stat
		;;
	Linux)
		cat "/proc/spl/kstat/zfs/$stat" 2>/dev/null
		;;
	*)
		false
		;;
	esac
}

function get_arcstat # stat
{
	typeset stat=$1

	case "$UNAME" in
	FreeBSD)
		kstat arcstats.$stat
		;;
	Linux)
		kstat arcstats | awk "/$stat/"' { print $3 }'
		;;
	*)
		false
		;;
	esac
}

function punch_hole # offset length file
{
	typeset offset=$1
	typeset length=$2
	typeset file=$3

	case "$UNAME" in
	FreeBSD)
		truncate -d -o $offset -l $length "$file"
		;;
	Linux)
		fallocate --punch-hole --offset $offset --length $length "$file"
		;;
	*)
		false
		;;
	esac
}

function zero_range # offset length file
{
	typeset offset=$1
	typeset length=$2
	typeset file=$3

	case "$UNAME" in
	Linux)
		fallocate --zero-range --offset $offset --length $length "$file"
		;;
	*)
		false
		;;
	esac
}

#
# Wait for the specified arcstat to reach non-zero quiescence.
# If echo is 1 echo the value after reaching quiescence, otherwise
# if echo is 0 print the arcstat we are waiting on.
#
function arcstat_quiescence # stat echo
{
	typeset stat=$1
	typeset echo=$2
	typeset do_once=true

	if [[ $echo -eq 0 ]]; then
		echo "Waiting for arcstat $1 quiescence."
	fi

	while $do_once || [ $stat1 -ne $stat2 ] || [ $stat2 -eq 0 ]; do
		typeset stat1=$(get_arcstat $stat)
		sleep 2
		typeset stat2=$(get_arcstat $stat)
		do_once=false
	done

	if [[ $echo -eq 1 ]]; then
		echo $stat2
	fi
}

function arcstat_quiescence_noecho # stat
{
	typeset stat=$1
	arcstat_quiescence $stat 0
}

function arcstat_quiescence_echo # stat
{
	typeset stat=$1
	arcstat_quiescence $stat 1
}

#
# Given an array of pids, wait until all processes
# have completed and check their return status.
#
function wait_for_children #children
{
	rv=0
	children=("$@")
	for child in "${children[@]}"
	do
		child_exit=0
		wait ${child} || child_exit=$?
		if [ $child_exit -ne 0 ]; then
			echo "child ${child} failed with ${child_exit}"
			rv=1
		fi
	done
	return $rv
}

#
# Compare two directory trees recursively in a manner similar to diff(1), but
# using rsync. If there are any discrepancies, a summary of the differences are
# output and a non-zero error is returned.
#
# If you're comparing a directory after a ZIL replay, you should set
# LIBTEST_DIFF_ZIL_REPLAY=1 or use replay_directory_diff which will cause
# directory_diff to ignore mtime changes (the ZIL replay won't fix up mtime
# information).
#
function directory_diff # dir_a dir_b
{
	dir_a="$1"
	dir_b="$2"
	zil_replay="${LIBTEST_DIFF_ZIL_REPLAY:-0}"

	# If one of the directories doesn't exist, return 2. This is to match the
	# semantics of diff.
	if ! [ -d "$dir_a" -a -d "$dir_b" ]; then
		return 2
	fi

	# Run rsync with --dry-run --itemize-changes to get something akin to diff
	# output, but rsync is far more thorough in detecting differences (diff
	# doesn't compare file metadata, and cannot handle special files).
	#
	# Also make sure to filter out non-user.* xattrs when comparing. On
	# SELinux-enabled systems the copied tree will probably have different
	# SELinux labels.
	args=("-nicaAHX" '--filter=-x! user.*' "--delete")

	# NOTE: Quite a few rsync builds do not support --crtimes which would be
	# necessary to verify that creation times are being maintained properly.
	# Unfortunately because of this we cannot use it unconditionally but we can
	# check if this rsync build supports it and use it then. This check is
	# based on the same check in the rsync test suite (testsuite/crtimes.test).
	#
	# We check ctimes even with zil_replay=1 because the ZIL does store
	# creation times and we should make sure they match (if the creation times
	# do not match there is a "c" entry in one of the columns).
	if rsync --version | grep -q "[, ] crtimes"; then
		args+=("--crtimes")
	else
		log_note "This rsync package does not support --crtimes (-N)."
	fi

	# If we are testing a ZIL replay, we need to ignore timestamp changes.
	# Unfortunately --no-times doesn't do what we want -- it will still tell
	# you if the timestamps don't match but rsync will set the timestamps to
	# the current time (leading to an itemised change entry). It's simpler to
	# just filter out those lines.
	if [ "$zil_replay" -eq 0 ]; then
		filter=("cat")
	else
		# Different rsync versions have different numbers of columns. So just
		# require that aside from the first two, all other columns must be
		# blank (literal ".") or a timestamp field ("[tT]").
		filter=("grep" "-v" '^\..[.Tt]\+ ')
	fi

	diff="$(rsync "${args[@]}" "$dir_a/" "$dir_b/" | "${filter[@]}")"
	rv=0
	if [ -n "$diff" ]; then
		echo "$diff"
		rv=1
	fi
	return $rv
}

#
# Compare two directory trees recursively, without checking whether the mtimes
# match (creation times will be checked if the available rsync binary supports
# it). This is necessary for ZIL replay checks (because the ZIL does not
# contain mtimes and thus after a ZIL replay, mtimes won't match).
#
# This is shorthand for LIBTEST_DIFF_ZIL_REPLAY=1 directory_diff <...>.
#
function replay_directory_diff # dir_a dir_b
{
	LIBTEST_DIFF_ZIL_REPLAY=1 directory_diff "$@"
}

#
# Put coredumps into $1/core.{basename}
#
# Output must be saved and passed to pop_coredump_pattern on cleanup
#
function push_coredump_pattern # dir
{
	ulimit -c unlimited
	case "$UNAME" in
	Linux)
		cat /proc/sys/kernel/core_pattern /proc/sys/kernel/core_uses_pid
		echo "$1/core.%e" >/proc/sys/kernel/core_pattern &&
		    echo 0 >/proc/sys/kernel/core_uses_pid
		;;
	FreeBSD)
		sysctl -n kern.corefile
		sysctl kern.corefile="$1/core.%N" >/dev/null
		;;
	*)
		# Nothing to output – set only for this shell
		coreadm -p "$1/core.%f"
		;;
	esac
}

#
# Put coredumps back into the default location
#
function pop_coredump_pattern
{
	[ -s "$1" ] || return 0
	case "$UNAME" in
	Linux)
		typeset pat pid
		{ read -r pat; read -r pid; } < "$1"
		echo "$pat" >/proc/sys/kernel/core_pattern &&
		    echo "$pid" >/proc/sys/kernel/core_uses_pid
		;;
	FreeBSD)
		sysctl kern.corefile="$(<"$1")" >/dev/null
		;;
	esac
}