mirror_zfs/scripts/common.sh.in
Brian Behlendorf ba6a24026c Remove ZFC_IOC_*_MINOR ioctl()s
Early versions of ZFS coordinated the creation and destruction
of device minors from userspace.  This was inherently racy and
in late 2009 these ioctl()s were removed leaving everything up
to the kernel.  This significantly simplified the code.

However, we never picked up these changes in ZoL since we'd
already significantly adjusted this code for Linux.  This patch
aims to rectify that by finally removing ZFC_IOC_*_MINOR ioctl()s
and moving all the functionality down in to the kernel.  Since
this cleanup will change the kernel/user ABI it's being done
in the same tag as the previous libzfs_core ABI changes.  This
will minimize, but not eliminate, the disruption to end users.

Once merged ZoL, Illumos, and FreeBSD will basically be back
in sync in regards to handling ZVOLs in the common code.  While
each platform must have its own custom zvol.c implemenation the
interfaces provided are consistent.

NOTES:

1) This patch introduces one subtle change in behavior which
   could not be easily avoided.  Prior to this change callers
   of 'zfs create -V ...' were guaranteed that upon exit the
   /dev/zvol/ block device link would be created or an error
   returned.  That's no longer the case.  The utilities will no
   longer block waiting for the symlink to be created.  Callers
   are now responsible for blocking, this is why a 'udev_wait'
   call was added to the 'label' function in scripts/common.sh.

2) The read-only behavior of a ZVOL now solely depends on if
   the ZVOL_RDONLY bit is set in zv->zv_flags.  The redundant
   policy setting in the gendisk structure was removed.  This
   both simplifies the code and allows us to safely leverage
   set_disk_ro() to issue a KOBJ_CHANGE uevent.  See the
   comment in the code for futher details on this.

3) Because __zvol_create_minor() and zvol_alloc() may now be
   called in a sync task they must use KM_PUSHPAGE.

References:
  illumos/illumos-gate@681d9761e8

Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ned Bass <bass6@llnl.gov>
Signed-off-by: Tim Chase <tim@chase2k.com>
Closes #1969
2013-12-16 09:15:57 -08:00

748 lines
16 KiB
Bash

#!/bin/bash
#
# Common support functions for testing scripts. If a script-config
# files is available it will be sourced so in-tree kernel modules and
# utilities will be used. If no script-config can be found then the
# installed kernel modules and utilities will be used.
basedir="$(dirname $0)"
SCRIPT_CONFIG=zfs-script-config.sh
if [ -f "${basedir}/../${SCRIPT_CONFIG}" ]; then
. "${basedir}/../${SCRIPT_CONFIG}"
else
KERNEL_MODULES=(zlib_deflate zlib_inflate)
MODULES=(spl splat zavl znvpair zunicode zcommon zfs)
fi
PROG="<define PROG>"
CLEANUP=
VERBOSE=
VERBOSE_FLAG=
FORCE=
FORCE_FLAG=
DUMP_LOG=
ERROR=
RAID0S=()
RAID10S=()
RAIDZS=()
RAIDZ2S=()
TESTS_RUN=${TESTS_RUN:-'*'}
TESTS_SKIP=${TESTS_SKIP:-}
prefix=@prefix@
exec_prefix=@exec_prefix@
pkgdatadir=@datarootdir@/@PACKAGE@
bindir=@bindir@
sbindir=@sbindir@
udevdir=@udevdir@
udevruledir=@udevruledir@
sysconfdir=@sysconfdir@
ETCDIR=${ETCDIR:-/etc}
DEVDIR=${DEVDIR:-/dev/disk/by-vdev}
ZPOOLDIR=${ZPOOLDIR:-${pkgdatadir}/zpool-config}
ZPIOSDIR=${ZPIOSDIR:-${pkgdatadir}/zpios-test}
ZPIOSPROFILEDIR=${ZPIOSPROFILEDIR:-${pkgdatadir}/zpios-profile}
ZDB=${ZDB:-${sbindir}/zdb}
ZFS=${ZFS:-${sbindir}/zfs}
ZINJECT=${ZINJECT:-${sbindir}/zinject}
ZPOOL=${ZPOOL:-${sbindir}/zpool}
ZTEST=${ZTEST:-${sbindir}/ztest}
ZPIOS=${ZPIOS:-${sbindir}/zpios}
COMMON_SH=${COMMON_SH:-${pkgdatadir}/common.sh}
ZFS_SH=${ZFS_SH:-${pkgdatadir}/zfs.sh}
ZPOOL_CREATE_SH=${ZPOOL_CREATE_SH:-${pkgdatadir}/zpool-create.sh}
ZPIOS_SH=${ZPIOS_SH:-${pkgdatadir}/zpios.sh}
ZPIOS_SURVEY_SH=${ZPIOS_SURVEY_SH:-${pkgdatadir}/zpios-survey.sh}
LDMOD=${LDMOD:-/sbin/modprobe}
LSMOD=${LSMOD:-/sbin/lsmod}
RMMOD=${RMMOD:-/sbin/rmmod}
INFOMOD=${INFOMOD:-/sbin/modinfo}
LOSETUP=${LOSETUP:-/sbin/losetup}
MDADM=${MDADM:-/sbin/mdadm}
PARTED=${PARTED:-/sbin/parted}
BLOCKDEV=${BLOCKDEV:-/sbin/blockdev}
LSSCSI=${LSSCSI:-/usr/bin/lsscsi}
SCSIRESCAN=${SCSIRESCAN:-/usr/bin/scsi-rescan}
SYSCTL=${SYSCTL:-/sbin/sysctl}
UDEVADM=${UDEVADM:-/sbin/udevadm}
AWK=${AWK:-/usr/bin/awk}
COLOR_BLACK="\033[0;30m"
COLOR_DK_GRAY="\033[1;30m"
COLOR_BLUE="\033[0;34m"
COLOR_LT_BLUE="\033[1;34m"
COLOR_GREEN="\033[0;32m"
COLOR_LT_GREEN="\033[1;32m"
COLOR_CYAN="\033[0;36m"
COLOR_LT_CYAN="\033[1;36m"
COLOR_RED="\033[0;31m"
COLOR_LT_RED="\033[1;31m"
COLOR_PURPLE="\033[0;35m"
COLOR_LT_PURPLE="\033[1;35m"
COLOR_BROWN="\033[0;33m"
COLOR_YELLOW="\033[1;33m"
COLOR_LT_GRAY="\033[0;37m"
COLOR_WHITE="\033[1;37m"
COLOR_RESET="\033[0m"
die() {
echo -e "${PROG}: $1" >&2
exit 1
}
msg() {
if [ ${VERBOSE} ]; then
echo "$@"
fi
}
pass() {
echo -e "${COLOR_GREEN}Pass${COLOR_RESET}"
}
fail() {
echo -e "${COLOR_RED}Fail${COLOR_RESET} ($1)"
exit $1
}
skip() {
echo -e "${COLOR_BROWN}Skip${COLOR_RESET}"
}
populate() {
local ROOT=$1
local MAX_DIR_SIZE=$2
local MAX_FILE_SIZE=$3
mkdir -p $ROOT/{a,b,c,d,e,f,g}/{h,i}
DIRS=`find $ROOT`
for DIR in $DIRS; do
COUNT=$(($RANDOM % $MAX_DIR_SIZE))
for i in `seq $COUNT`; do
FILE=`mktemp -p ${DIR}`
SIZE=$(($RANDOM % $MAX_FILE_SIZE))
dd if=/dev/urandom of=$FILE bs=1k count=$SIZE &>/dev/null
done
done
return 0
}
init() {
# Disable the udev rule 90-zfs.rules to prevent the zfs module
# stack from being loaded due to the detection of a zfs device.
# This is important because the test scripts require full control
# over when and how the modules are loaded/unloaded. A trap is
# set to ensure the udev rule is correctly replaced on exit.
local RULE=${udevruledir}/90-zfs.rules
if test -e ${RULE}; then
trap "mv ${RULE}.disabled ${RULE}" INT TERM EXIT
mv ${RULE} ${RULE}.disabled
fi
# Create a random directory tree of files and sub-directories to
# to act as a copy source for the various regression tests.
SRC_DIR=`mktemp -d -p /var/tmp/ zfs.src.XXXXXXXX`
trap "rm -Rf $SRC_DIR" INT TERM EXIT
populate $SRC_DIR 10 100
}
spl_dump_log() {
${SYSCTL} -w kernel.spl.debug.dump=1 &>/dev/null
local NAME=`dmesg | tail -n 1 | cut -f5 -d' '`
${SPLBUILD}/cmd/spl ${NAME} >${NAME}.log
echo
echo "Dumped debug log: ${NAME}.log"
tail -n1 ${NAME}.log
echo
return 0
}
check_modules() {
local LOADED_MODULES=()
local MISSING_MODULES=()
for MOD in ${MODULES[*]}; do
local NAME=`basename $MOD .ko`
if ${LSMOD} | egrep -q "^${NAME}"; then
LOADED_MODULES=(${NAME} ${LOADED_MODULES[*]})
fi
if [ ${INFOMOD} ${MOD} 2>/dev/null ]; then
MISSING_MODULES=("\t${MOD}\n" ${MISSING_MODULES[*]})
fi
done
if [ ${#LOADED_MODULES[*]} -gt 0 ]; then
ERROR="Unload these modules with '${PROG} -u':\n"
ERROR="${ERROR}${LOADED_MODULES[*]}"
return 1
fi
if [ ${#MISSING_MODULES[*]} -gt 0 ]; then
ERROR="The following modules can not be found,"
ERROR="${ERROR} ensure your source trees are built:\n"
ERROR="${ERROR}${MISSING_MODULES[*]}"
return 1
fi
return 0
}
load_module() {
local NAME=`basename $1 .ko`
if [ ${VERBOSE} ]; then
echo "Loading ${NAME} ($@)"
fi
${LDMOD} $* &>/dev/null || ERROR="Failed to load $1" return 1
return 0
}
load_modules() {
mkdir -p /etc/zfs
for MOD in ${KERNEL_MODULES[*]}; do
load_module ${MOD}
done
for MOD in ${MODULES[*]}; do
local NAME=`basename ${MOD} .ko`
local VALUE=
for OPT in "$@"; do
OPT_NAME=`echo ${OPT} | cut -f1 -d'='`
if [ ${NAME} = "${OPT_NAME}" ]; then
VALUE=`echo ${OPT} | cut -f2- -d'='`
fi
done
load_module ${MOD} ${VALUE} || return 1
done
if [ ${VERBOSE} ]; then
echo "Successfully loaded ZFS module stack"
fi
return 0
}
unload_module() {
local NAME=`basename $1 .ko`
if [ ${VERBOSE} ]; then
echo "Unloading ${NAME} ($@)"
fi
${RMMOD} ${NAME} || ERROR="Failed to unload ${NAME}" return 1
return 0
}
unload_modules() {
local MODULES_REVERSE=( $(echo ${MODULES[@]} |
${AWK} '{for (i=NF;i>=1;i--) printf $i" "} END{print ""}') )
for MOD in ${MODULES_REVERSE[*]}; do
local NAME=`basename ${MOD} .ko`
local USE_COUNT=`${LSMOD} |
egrep "^${NAME} "| ${AWK} '{print $3}'`
if [ "${USE_COUNT}" = 0 ] ; then
if [ "${DUMP_LOG}" -a ${NAME} = "spl" ]; then
spl_dump_log
fi
unload_module ${MOD} || return 1
fi
done
if [ ${VERBOSE} ]; then
echo "Successfully unloaded ZFS module stack"
fi
return 0
}
#
# Check that the mdadm utilities are installed.
#
check_loop_utils() {
test -f ${LOSETUP} || die "${LOSETUP} utility must be installed"
}
#
# Find and return an unused loopback device.
#
unused_loop_device() {
for DEVICE in `ls -1 /dev/loop[0-9]* 2>/dev/null`; do
${LOSETUP} ${DEVICE} &>/dev/null
if [ $? -ne 0 ]; then
echo ${DEVICE}
return
fi
done
die "Error: Unable to find unused loopback device"
}
#
# This can be slightly dangerous because the loop devices we are
# cleaning up may not be ours. However, if the devices are currently
# in use we will not be able to remove them, and we only remove
# devices which include 'zpool' in the name. So any damage we might
# do should be limited to other zfs related testing.
#
cleanup_loop_devices() {
local TMP_FILE=`mktemp`
${LOSETUP} -a | tr -d '()' >${TMP_FILE}
${AWK} -F":" -v losetup="$LOSETUP" \
'/zpool/ { system("losetup -d "$1) }' ${TMP_FILE}
${AWK} -F" " '/zpool/ { system("rm -f "$3) }' ${TMP_FILE}
rm -f ${TMP_FILE}
}
#
# Destroy the passed loopback devices, this is used when you know
# the names of the loopback devices.
#
destroy_loop_devices() {
local LODEVICES="$1"
msg "Destroying ${LODEVICES}"
${LOSETUP} -d ${LODEVICES} || \
die "Error $? destroying ${FILE} -> ${DEVICE} loopback"
rm -f ${FILES}
return 0
}
#
# Create a device label taking care to briefly wait if udev needs to settle.
#
label() {
local DEVICE=$1
local LABEL=$2
wait_udev ${DEVICE} 30 || return 1
${PARTED} ${DEVICE} --script -- mklabel ${LABEL} || return 2
return 0
}
#
# Create a primary partition on a block device.
#
partition() {
local DEVICE=$1
local TYPE=$2
local START=$3
local END=$4
${PARTED} --align optimal ${DEVICE} --script -- \
mkpart ${TYPE} ${START} ${END} || return 1
udev_trigger
return 0
}
#
# Create a filesystem on the block device
#
format() {
local DEVICE=$1
local FSTYPE=$2
# Force 4K blocksize, else mkfs.ext2 tries to use 8K, which
# won't mount
/sbin/mkfs.${FSTYPE} -b 4096 -F -q ${DEVICE} >/dev/null || return 1
return 0
}
#
# Check that the mdadm utilities are installed.
#
check_md_utils() {
test -f ${MDADM} || die "${MDADM} utility must be installed"
test -f ${PARTED} || die "${PARTED} utility must be installed"
}
check_md_partitionable() {
local LOFILE=`mktemp -p /tmp zpool-lo.XXXXXXXX`
local LODEVICE=`unused_loop_device`
local MDDEVICE=`unused_md_device`
local RESULT=1
check_md_utils
rm -f ${LOFILE}
dd if=/dev/zero of=${LOFILE} bs=1M count=0 seek=16 \
&>/dev/null || return ${RESULT}
msg "Creating ${LODEVICE} using ${LOFILE}"
${LOSETUP} ${LODEVICE} ${LOFILE}
if [ $? -ne 0 ]; then
rm -f ${LOFILE}
return ${RESULT}
fi
msg "Creating ${MDDEVICE} using ${LODEVICE}"
${MDADM} --build ${MDDEVICE} --level=faulty \
--raid-devices=1 ${LODEVICE} &>/dev/null
if [ $? -ne 0 ]; then
destroy_loop_devices ${LODEVICE}
rm -f ${LOFILE}
return ${RESULT}
fi
wait_udev ${MDDEVICE} 30
${BLOCKDEV} --rereadpt ${MDDEVICE} 2>/dev/null
RESULT=$?
destroy_md_devices ${MDDEVICE}
destroy_loop_devices ${LODEVICE}
rm -f ${LOFILE}
return ${RESULT}
}
#
# Find and return an unused md device.
#
unused_md_device() {
for (( i=0; i<32; i++ )); do
MDDEVICE=md${i}
# Skip active devicesudo in /proc/mdstat.
grep -q "${MDDEVICE} " /proc/mdstat && continue
# Device doesn't exist, use it.
if [ ! -e $/dev/{MDDEVICE} ]; then
echo /dev/${MDDEVICE}
return
fi
# Device exists but may not be in use.
if [ -b /dev/${MDDEVICE} ]; then
${MDADM} --detail /dev/${MDDEVICE} &>/dev/null
if [ $? -eq 1 ]; then
echo /dev/${MDDEVICE}
return
fi
fi
done
die "Error: Unable to find unused md device"
}
#
# This can be slightly dangerous because it is possible the md devices
# we are cleaning up may not be ours. However, if the devices are
# currently in use we will not be able to remove them, and even if
# we remove devices which were not out we do not zero the super block
# so you should be able to reconstruct them.
#
cleanup_md_devices() {
destroy_md_devices "`ls /dev/md* 2>/dev/null | grep -v p`"
udev_trigger
}
#
# Destroy the passed md devices, this is used when you know
# the names of the md devices.
#
destroy_md_devices() {
local MDDEVICES="$1"
msg "Destroying ${MDDEVICES}"
for MDDEVICE in ${MDDEVICES}; do
${MDADM} --stop ${MDDEVICE} &>/dev/null
${MDADM} --remove ${MDDEVICE} &>/dev/null
${MDADM} --detail ${MDDEVICE} &>/dev/null
done
return 0
}
#
# Check that the scsi utilities are installed.
#
check_sd_utils() {
${INFOMOD} scsi_debug &>/dev/null || die "scsi_debug module required"
test -f ${LSSCSI} || die "${LSSCSI} utility must be installed"
}
#
# Rescan the scsi bus for scsi_debug devices. It is preferable to use the
# scsi-rescan tool if it is installed, but if it's not we can fall back to
# removing and readding the device manually. This rescan will only effect
# the first scsi_debug device if scsi-rescan is missing.
#
scsi_rescan() {
local AWK_SCRIPT="/scsi_debug/ { print \$1; exit }"
if [ -f ${SCSIRESCAN} ]; then
${SCSIRESCAN} --forcerescan --remove &>/dev/null
else
local SCSIID=`${LSSCSI} | ${AWK} "${AWK_SCRIPT}" | tr -d '[]'`
local SCSIHOST=`echo ${SCSIID} | cut -f1 -d':'`
echo 1 >"/sys/class/scsi_device/${SCSIID}/device/delete"
udev_trigger
echo "- - -" >/sys/class/scsi_host/host${SCSIHOST}/scan
udev_trigger
fi
}
#
# Trigger udev and wait for it to settle.
#
udev_trigger() {
if [ -f ${UDEVADM} ]; then
${UDEVADM} trigger --action=change --subsystem-match=block
${UDEVADM} settle
else
/sbin/udevtrigger
/sbin/udevsettle
fi
}
#
# The following udev helper functions assume that the provided
# udev rules file will create a /dev/disk/by-vdev/<CHANNEL><RANK>
# disk mapping. In this mapping each CHANNEL is represented by
# the letters a-z, and the RANK is represented by the numbers
# 1-n. A CHANNEL should identify a group of RANKS which are all
# attached to a single controller, each RANK represents a disk.
# This provides a simply mechanism to locate a specific drive
# given a known hardware configuration.
#
udev_setup() {
local SRC_PATH=$1
# When running in tree manually contruct symlinks in tree to
# the proper devices. Symlinks are installed for all entires
# in the config file regardless of if that device actually
# exists. When installed as a package udev can be relied on for
# this and it will only create links for devices which exist.
if [ ${INTREE} ]; then
PWD=`pwd`
mkdir -p ${DEVDIR}/
cd ${DEVDIR}/
${AWK} '!/^#/ && /./ { system( \
"ln -f -s /dev/disk/by-path/"$2" "$1";" \
"ln -f -s /dev/disk/by-path/"$2"-part1 "$1"p1;" \
"ln -f -s /dev/disk/by-path/"$2"-part9 "$1"p9;" \
) }' $SRC_PATH
cd ${PWD}
else
DST_FILE=`basename ${SRC_PATH} | cut -f1-2 -d'.'`
DST_PATH=/etc/zfs/${DST_FILE}
if [ -e ${DST_PATH} ]; then
die "Error: Config ${DST_PATH} already exists"
fi
cp ${SRC_PATH} ${DST_PATH}
udev_trigger
fi
return 0
}
udev_cleanup() {
local SRC_PATH=$1
if [ ${INTREE} ]; then
PWD=`pwd`
cd ${DEVDIR}/
${AWK} '!/^#/ && /./ { system( \
"rm -f "$1" "$1"p1 "$1"p9") }' $SRC_PATH
cd ${PWD}
fi
return 0
}
udev_cr2d() {
local CHANNEL=`echo "obase=16; $1+96" | bc`
local RANK=$2
printf "\x${CHANNEL}${RANK}"
}
udev_raid0_setup() {
local RANKS=$1
local CHANNELS=$2
local IDX=0
RAID0S=()
for RANK in `seq 1 ${RANKS}`; do
for CHANNEL in `seq 1 ${CHANNELS}`; do
DISK=`udev_cr2d ${CHANNEL} ${RANK}`
RAID0S[${IDX}]="${DEVDIR}/${DISK}"
let IDX=IDX+1
done
done
return 0
}
udev_raid10_setup() {
local RANKS=$1
local CHANNELS=$2
local IDX=0
RAID10S=()
for RANK in `seq 1 ${RANKS}`; do
for CHANNEL1 in `seq 1 2 ${CHANNELS}`; do
let CHANNEL2=CHANNEL1+1
DISK1=`udev_cr2d ${CHANNEL1} ${RANK}`
DISK2=`udev_cr2d ${CHANNEL2} ${RANK}`
GROUP="${DEVDIR}/${DISK1} ${DEVDIR}/${DISK2}"
RAID10S[${IDX}]="mirror ${GROUP}"
let IDX=IDX+1
done
done
return 0
}
udev_raidz_setup() {
local RANKS=$1
local CHANNELS=$2
RAIDZS=()
for RANK in `seq 1 ${RANKS}`; do
RAIDZ=("raidz")
for CHANNEL in `seq 1 ${CHANNELS}`; do
DISK=`udev_cr2d ${CHANNEL} ${RANK}`
RAIDZ[${CHANNEL}]="${DEVDIR}/${DISK}"
done
RAIDZS[${RANK}]="${RAIDZ[*]}"
done
return 0
}
udev_raidz2_setup() {
local RANKS=$1
local CHANNELS=$2
RAIDZ2S=()
for RANK in `seq 1 ${RANKS}`; do
RAIDZ2=("raidz2")
for CHANNEL in `seq 1 ${CHANNELS}`; do
DISK=`udev_cr2d ${CHANNEL} ${RANK}`
RAIDZ2[${CHANNEL}]="${DEVDIR}/${DISK}"
done
RAIDZ2S[${RANK}]="${RAIDZ2[*]}"
done
return 0
}
run_one_test() {
local TEST_NUM=$1
local TEST_NAME=$2
printf "%-4d %-34s " ${TEST_NUM} "${TEST_NAME}"
test_${TEST_NUM}
}
skip_one_test() {
local TEST_NUM=$1
local TEST_NAME=$2
printf "%-4d %-34s " ${TEST_NUM} "${TEST_NAME}"
skip
}
run_test() {
local TEST_NUM=$1
local TEST_NAME=$2
for i in ${TESTS_SKIP[@]}; do
if [[ $i == ${TEST_NUM} ]] ; then
skip_one_test ${TEST_NUM} "${TEST_NAME}"
return 0
fi
done
if [ "${TESTS_RUN[0]}" = "*" ]; then
run_one_test ${TEST_NUM} "${TEST_NAME}"
else
for i in ${TESTS_RUN[@]}; do
if [[ $i == ${TEST_NUM} ]] ; then
run_one_test ${TEST_NUM} "${TEST_NAME}"
return 0
fi
done
skip_one_test ${TEST_NUM} "${TEST_NAME}"
fi
}
wait_udev() {
local DEVICE=$1
local DELAY=$2
local COUNT=0
udev_trigger
while [ ! -e ${DEVICE} ]; do
if [ ${COUNT} -gt ${DELAY} ]; then
return 1
fi
let COUNT=${COUNT}+1
sleep 1
done
return 0
}
stack_clear() {
local STACK_MAX_SIZE=/sys/kernel/debug/tracing/stack_max_size
local STACK_TRACER_ENABLED=/proc/sys/kernel/stack_tracer_enabled
if [ -e $STACK_MAX_SIZE ]; then
echo 1 >$STACK_TRACER_ENABLED
echo 0 >$STACK_MAX_SIZE
fi
}
stack_check() {
local STACK_MAX_SIZE=/sys/kernel/debug/tracing/stack_max_size
local STACK_TRACE=/sys/kernel/debug/tracing/stack_trace
local STACK_LIMIT=7000
if [ -e $STACK_MAX_SIZE ]; then
STACK_SIZE=`cat $STACK_MAX_SIZE`
if [ $STACK_SIZE -ge $STACK_LIMIT ]; then
echo
echo "Warning: max stack size $STACK_SIZE bytes"
cat $STACK_TRACE
fi
fi
}