kexec-tools/dracut-module-setup.sh

885 lines
28 KiB
Bash
Raw Normal View History

#!/bin/bash
. $dracutfunctions
. /lib/kdump/kdump-lib.sh
if ! [[ -d "${initdir}/tmp" ]]; then
mkdir -p "${initdir}/tmp"
fi
check() {
[[ $debug ]] && set -x
#kdumpctl sets this explicitly
if [ -z "$IN_KDUMP" ] || [ ! -f /etc/kdump.conf ]
then
return 1
fi
return 0
}
depends() {
local _dep="base shutdown"
is_squash_available() {
for kmodule in squashfs overlay loop; do
if [ -z "$KDUMP_KERNELVER" ]; then
modprobe --dry-run $kmodule &>/dev/null || return 1
else
modprobe -S $KDUMP_KERNELVER --dry-run $kmodule &>/dev/null || return 1
fi
done
}
if is_squash_available && ! is_fadump_capable; then
_dep="$_dep squash"
else
dwarning "Required modules to build a squashed kdump image is missing!"
fi
if [ -n "$( find /sys/devices -name drm )" ] || [ -d /sys/module/hyperv_fb ]; then
_dep="$_dep drm"
fi
if is_generic_fence_kdump -o is_pcs_fence_kdump; then
_dep="$_dep network"
fi
echo $_dep
return 0
}
kdump_get_persistent_dev() {
local dev="${1//\"/}"
case "$dev" in
UUID=*)
dev=`blkid -U "${dev#UUID=}"`
;;
LABEL=*)
dev=`blkid -L "${dev#LABEL=}"`
;;
esac
echo $(get_persistent_dev "$dev")
}
kdump_is_bridge() {
[ -d /sys/class/net/"$1"/bridge ]
}
kdump_is_bond() {
[ -d /sys/class/net/"$1"/bonding ]
}
kdump_is_team() {
[ -f /usr/bin/teamnl ] && teamnl $1 ports &> /dev/null
}
kdump_is_vlan() {
[ -f /proc/net/vlan/"$1" ]
}
# $1: netdev name
source_ifcfg_file() {
local ifcfg_file
ifcfg_file=$(get_ifcfg_filename $1)
if [ -f "${ifcfg_file}" ]; then
. ${ifcfg_file}
else
dwarning "The ifcfg file of $1 is not found!"
fi
}
# $1: netdev name
kdump_setup_dns() {
local _nameserver _dns
local _dnsfile=${initdir}/etc/cmdline.d/42dns.conf
source_ifcfg_file $1
[ -n "$DNS1" ] && echo "nameserver=$DNS1" > "$_dnsfile"
[ -n "$DNS2" ] && echo "nameserver=$DNS2" >> "$_dnsfile"
while read content;
do
_nameserver=$(echo $content | grep ^nameserver)
[ -z "$_nameserver" ] && continue
_dns=$(echo $_nameserver | cut -d' ' -f2)
[ -z "$_dns" ] && continue
if [ ! -f $_dnsfile ] || [ ! $(cat $_dnsfile | grep -q $_dns) ]; then
echo "nameserver=$_dns" >> "$_dnsfile"
fi
done < "/etc/resolv.conf"
}
#$1: netdev name
#$2: srcaddr
#if it use static ip echo it, or echo null
kdump_static_ip() {
local _netdev="$1" _srcaddr="$2" _ipv6_flag
local _netmask _gateway _ipaddr _target _nexthop
_ipaddr=$(ip addr show dev $_netdev permanent | awk "/ $_srcaddr\/.* /{print \$2}")
if is_ipv6_address $_srcaddr; then
_ipv6_flag="-6"
fi
if [ -n "$_ipaddr" ]; then
_gateway=$(ip $_ipv6_flag route list dev $_netdev | \
awk '/^default /{print $3}' | head -n 1)
if [ "x" != "x"$_ipv6_flag ]; then
# _ipaddr="2002::56ff:feb6:56d5/64", _netmask is the number after "/"
_netmask=${_ipaddr#*\/}
_srcaddr="[$_srcaddr]"
_gateway="[$_gateway]"
else
_netmask=$(ipcalc -m $_ipaddr | cut -d'=' -f2)
fi
echo -n "${_srcaddr}::${_gateway}:${_netmask}::"
fi
/sbin/ip $_ipv6_flag route show | grep -v default |\
grep ".*via.* $_netdev " | grep -v "^[[:space:]]*nexthop" |\
while read _route; do
_target=`echo $_route | cut -d ' ' -f1`
_nexthop=`echo $_route | cut -d ' ' -f3`
if [ "x" != "x"$_ipv6_flag ]; then
_target="[$_target]"
_nexthop="[$_nexthop]"
fi
echo "rd.route=$_target:$_nexthop:$_netdev"
done >> ${initdir}/etc/cmdline.d/45route-static.conf
kdump_handle_mulitpath_route $_netdev $_srcaddr
}
kdump_handle_mulitpath_route() {
local _netdev="$1" _srcaddr="$2" _ipv6_flag
local _target _nexthop _route _weight _max_weight _rule
if is_ipv6_address $_srcaddr; then
_ipv6_flag="-6"
fi
while IFS="" read _route; do
if [[ "$_route" =~ [[:space:]]+nexthop ]]; then
_route=$(echo "$_route" | sed -e 's/^[[:space:]]*//')
# Parse multipath route, using previous _target
[[ "$_target" == 'default' ]] && continue
[[ "$_route" =~ .*via.*\ $_netdev ]] || continue
_weight=`echo "$_route" | cut -d ' ' -f7`
if [[ "$_weight" -gt "$_max_weight" ]]; then
_nexthop=`echo "$_route" | cut -d ' ' -f3`
_max_weight=$_weight
if [ "x" != "x"$_ipv6_flag ]; then
_rule="rd.route=[$_target]:[$_nexthop]:$_netdev"
else
_rule="rd.route=$_target:$_nexthop:$_netdev"
fi
fi
else
[[ -n "$_rule" ]] && echo "$_rule"
_target=`echo "$_route" | cut -d ' ' -f1`
_rule="" _max_weight=0 _weight=0
fi
done >> ${initdir}/etc/cmdline.d/45route-static.conf\
< <(/sbin/ip $_ipv6_flag route show)
[[ -n $_rule ]] && echo $_rule >> ${initdir}/etc/cmdline.d/45route-static.conf
}
kdump_get_mac_addr() {
cat /sys/class/net/$1/address
}
#Bonding or team master modifies the mac address
#of its slaves, we should use perm address
kdump_get_perm_addr() {
local addr=$(ethtool -P $1 | sed -e 's/Permanent address: //')
if [ -z "$addr" ] || [ "$addr" = "00:00:00:00:00:00" ]
then
derror "Can't get the permanent address of $1"
else
echo "$addr"
fi
}
# Prefix kernel assigned names with "kdump-". EX: eth0 -> kdump-eth0
# Because kernel assigned names are not persistent between 1st and 2nd
# kernel. We could probably end up with eth0 being eth1, eth0 being
# eth1, and naming conflict happens.
kdump_setup_ifname() {
local _ifname
kdump/fadump: fix network interface name when switching from fadump to kdump When a remote dump target is specified, kdump dracut module prefixes 'kdump-' to network interface name (ifname) as kernel assigned names are not persistent. In fadump mode, kdump dracut module is added to the default initrd, which adds the 'kdump-' prefix to the ifname of the prodcution kernel itself. If fadump mode is disabled after this, kdump dracut module picks the ifname that is already prefixed with 'kdump-' in the production kernel and adds another 'kdump-' to it, making the ifname something like kdump-kdump-eth0 for kdump kernel. Eventually, kdump kernel fails with below traces: dracut-initqueue[246]: RTNETLINK answers: Network is unreachable dracut-initqueue[246]: arping: Device kdump-kdump-eth0 not available. The ip command shows the below: kdump:/# ip addr show kdump-kdump-eth0 2: kdump-kdump-eth: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 \ qdisc pfifo_fast state UNKNOWN qlen 1000 link/ether 22:82:87:7b:98:02 brd ff:ff:ff:ff:ff:ff inet6 2002:903:15f:550:2082:87ff:fe7b:9802/64 scope global \ mngtmpaddr dynamic valid_lft 2591890sec preferred_lft 604690sec inet6 fe80::2082:87ff:fe7b:9802/64 scope link valid_lft forever preferred_lft forever kdump:/# The trailing 0 from kdump-kdump-eth0 is missing in the ifname, probably truncated owing to ifname length limit, while setting. This patch fixes this by avoiding addition of the prefix 'kdump-' when such prefix is already present in the ifname. Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com> Acked-by: Dave Young <dyoung@redhat.com>
2016-11-03 18:46:14 +00:00
# If ifname already has 'kdump-' prefix, we must be switching from
# fadump to kdump. Skip prefixing 'kdump-' in this case as adding
# another prefix may truncate the ifname. Since an ifname with
# 'kdump-' is already persistent, this should be fine.
if [[ $1 =~ eth* ]] && [[ ! $1 =~ ^kdump-* ]]; then
_ifname="kdump-$1"
else
_ifname="$1"
fi
echo "$_ifname"
}
kdump_setup_bridge() {
local _netdev=$1
local _brif _dev _mac _kdumpdev
for _dev in `ls /sys/class/net/$_netdev/brif/`; do
_kdumpdev=$_dev
if kdump_is_bond "$_dev"; then
kdump_setup_bond "$_dev"
elif kdump_is_team "$_dev"; then
kdump_setup_team "$_dev"
elif kdump_is_vlan "$_dev"; then
kdump_setup_vlan "$_dev"
else
_mac=$(kdump_get_mac_addr $_dev)
_kdumpdev=$(kdump_setup_ifname $_dev)
echo -n " ifname=$_kdumpdev:$_mac" >> ${initdir}/etc/cmdline.d/41bridge.conf
fi
_brif+="$_kdumpdev,"
done
echo " bridge=$_netdev:$(echo $_brif | sed -e 's/,$//')" >> ${initdir}/etc/cmdline.d/41bridge.conf
}
kdump_setup_bond() {
local _netdev=$1
local _dev _mac _slaves _kdumpdev
for _dev in `cat /sys/class/net/$_netdev/bonding/slaves`; do
_mac=$(kdump_get_perm_addr $_dev)
_kdumpdev=$(kdump_setup_ifname $_dev)
echo -n " ifname=$_kdumpdev:$_mac" >> ${initdir}/etc/cmdline.d/42bond.conf
_slaves+="$_kdumpdev,"
done
echo -n " bond=$_netdev:$(echo $_slaves | sed 's/,$//')" >> ${initdir}/etc/cmdline.d/42bond.conf
# Get bond options specified in ifcfg
source_ifcfg_file $_netdev
bondoptions=":$(echo $BONDING_OPTS | xargs echo | tr " " ",")"
echo "$bondoptions" >> ${initdir}/etc/cmdline.d/42bond.conf
}
kdump_setup_team() {
local _netdev=$1
local _dev _mac _slaves _kdumpdev
for _dev in `teamnl $_netdev ports | awk -F':' '{print $2}'`; do
_mac=$(kdump_get_perm_addr $_dev)
_kdumpdev=$(kdump_setup_ifname $_dev)
echo -n " ifname=$_kdumpdev:$_mac" >> ${initdir}/etc/cmdline.d/44team.conf
_slaves+="$_kdumpdev,"
done
echo " team=$_netdev:$(echo $_slaves | sed -e 's/,$//')" >> ${initdir}/etc/cmdline.d/44team.conf
#Buggy version teamdctl outputs to stderr!
#Try to use the latest version of teamd.
teamdctl "$_netdev" config dump > ${initdir}/tmp/$$-$_netdev.conf
if [ $? -ne 0 ]
then
derror "teamdctl failed."
exit 1
fi
inst_dir /etc/teamd
inst_simple ${initdir}/tmp/$$-$_netdev.conf "/etc/teamd/$_netdev.conf"
rm -f ${initdir}/tmp/$$-$_netdev.conf
}
kdump_setup_vlan() {
local _netdev=$1
local _phydev="$(awk '/^Device:/{print $2}' /proc/net/vlan/"$_netdev")"
local _netmac="$(kdump_get_mac_addr $_phydev)"
local _kdumpdev
#Just support vlan over bond, it is not easy
#to support all other complex setup
if kdump_is_bridge "$_phydev"; then
derror "Vlan over bridge is not supported!"
exit 1
elif kdump_is_team "$_phydev"; then
derror "Vlan over team is not supported!"
exit 1
elif kdump_is_bond "$_phydev"; then
kdump_setup_bond "$_phydev"
echo " vlan=$_netdev:$_phydev" > ${initdir}/etc/cmdline.d/43vlan.conf
else
_kdumpdev="$(kdump_setup_ifname $_phydev)"
echo " vlan=$_netdev:$_kdumpdev ifname=$_kdumpdev:$_netmac" > ${initdir}/etc/cmdline.d/43vlan.conf
fi
}
# setup s390 znet cmdline
# $1: netdev name
kdump_setup_znet() {
local _options=""
source_ifcfg_file $1
for i in $OPTIONS; do
_options=${_options},$i
done
echo rd.znet=${NETTYPE},${SUBCHANNELS}${_options} > ${initdir}/etc/cmdline.d/30znet.conf
}
# Setup dracut to bringup a given network interface
kdump_setup_netdev() {
local _netdev=$1 _srcaddr=$2
local _static _proto _ip_conf _ip_opts _ifname_opts
local _netmac=$(kdump_get_mac_addr $_netdev)
if [ "$(uname -m)" = "s390x" ]; then
kdump_setup_znet $_netdev
fi
_static=$(kdump_static_ip $_netdev $_srcaddr)
if [ -n "$_static" ]; then
_proto=none
elif is_ipv6_address $_srcaddr; then
_proto=either6
else
_proto=dhcp
fi
_ip_conf="${initdir}/etc/cmdline.d/40ip.conf"
_ip_opts=" ip=${_static}$(kdump_setup_ifname $_netdev):${_proto}"
# dracut doesn't allow duplicated configuration for same NIC, even they're exactly the same.
# so we have to avoid adding duplicates
# We should also check /proc/cmdline for existing ip=xx arg.
# For example, iscsi boot will specify ip=xxx arg in cmdline.
if [ ! -f $_ip_conf ] || ! grep -q $_ip_opts $_ip_conf &&\
! grep -q "ip=[^[:space:]]*$_netdev" /proc/cmdline; then
echo "$_ip_opts" >> $_ip_conf
fi
if kdump_is_bridge "$_netdev"; then
kdump_setup_bridge "$_netdev"
elif kdump_is_bond "$_netdev"; then
kdump_setup_bond "$_netdev"
elif kdump_is_team "$_netdev"; then
kdump_setup_team "$_netdev"
elif kdump_is_vlan "$_netdev"; then
kdump_setup_vlan "$_netdev"
else
_ifname_opts=" ifname=$(kdump_setup_ifname $_netdev):$_netmac"
echo "$_ifname_opts" >> $_ip_conf
fi
kdump_setup_dns "$_netdev"
}
get_ip_route_field()
{
if `echo $1 | grep -q $2`; then
echo ${1##*$2} | cut -d ' ' -f1
fi
}
#Function:kdump_install_net
#$1: config values of net line in kdump.conf
#$2: srcaddr of network device
kdump_install_net() {
local _server _netdev _srcaddr _route _serv_tmp
local config_val="$1"
_server=$(get_remote_host $config_val)
if is_hostname $_server; then
_serv_tmp=`getent ahosts $_server | grep -v : | head -n 1`
if [ -z "$_serv_tmp" ]; then
_serv_tmp=`getent ahosts $_server | head -n 1`
fi
_server=`echo $_serv_tmp | cut -d' ' -f1`
fi
_route=`/sbin/ip -o route get to $_server 2>&1`
[ $? != 0 ] && echo "Bad kdump location: $config_val" && exit 1
#the field in the ip output changes if we go to another subnet
_srcaddr=$(get_ip_route_field "$_route" "src")
_netdev=$(get_ip_route_field "$_route" "dev")
kdump_setup_netdev "${_netdev}" "${_srcaddr}"
#save netdev used for kdump as cmdline
# Whoever calling kdump_install_net() is setting up the default gateway,
# ie. bootdev/kdumpnic. So don't override the setting if calling
# kdump_install_net() for another time. For example, after setting eth0 as
# the default gate way for network dump, eth1 in the fence kdump path will
# call kdump_install_net again and we don't want eth1 to be the default
# gateway.
if [ ! -f ${initdir}/etc/cmdline.d/60kdumpnic.conf ] &&
[ ! -f ${initdir}/etc/cmdline.d/70bootdev.conf ]; then
echo "kdumpnic=$(kdump_setup_ifname $_netdev)" > ${initdir}/etc/cmdline.d/60kdumpnic.conf
echo "bootdev=$(kdump_setup_ifname $_netdev)" > ${initdir}/etc/cmdline.d/70bootdev.conf
fi
}
default_dump_target_install_conf()
{
local _target _fstype
local _mntpoint _save_path
is_user_configured_dump_target && return
_save_path=$(get_option_value "path")
[ -z "$_save_path" ] && _save_path=$DEFAULT_PATH
# strip the duplicated "/"
_save_path=$(echo $_save_path | tr -s /)
_mntpoint=$(get_mntpoint_from_path $_save_path)
_target=$(get_target_from_path $_save_path)
if is_atomic && is_bind_mount $_mntpoint; then
_save_path=${_save_path##"$_mntpoint"}
# the real dump path in the 2nd kernel, if the mount point is bind mounted.
_save_path=$(get_bind_mount_directory $_mntpoint)/$_save_path
_mntpoint=$(get_mntpoint_from_target $_target)
# the absolute path in the 1st kernel
_save_path=$_mntpoint/$_save_path
fi
_fstype=$(get_fs_type_from_target $_target)
if is_fs_type_nfs $_fstype; then
kdump_install_net "$_target"
_fstype="nfs"
else
_target=$(kdump_get_persistent_dev $_target)
fi
echo "$_fstype $_target" >> ${initdir}/tmp/$$-kdump.conf
# strip the duplicated "/"
_save_path=$(echo $_save_path | tr -s /)
# don't touch the path under root mount
if [ "$_mntpoint" != "/" ]; then
_save_path=${_save_path##"$_mntpoint"}
fi
#erase the old path line, then insert the parsed path
sed -i "/^path/d" ${initdir}/tmp/$$-kdump.conf
echo "path $_save_path" >> ${initdir}/tmp/$$-kdump.conf
}
adjust_bind_mount_path()
{
local _target=$1
local _save_path=$(get_option_value "path")
[ -z "$_save_path" ] && _save_path=$DEFAULT_PATH
# strip the duplicated "/"
_save_path=$(echo $_save_path | tr -s /)
local _absolute_save_path=$(get_mntpoint_from_target $_target)/$_save_path
_absolute_save_path=$(echo "$_absolute_save_path" | tr -s /)
local _mntpoint=$(get_mntpoint_from_path $_absolute_save_path)
if is_bind_mount $_mntpoint; then
_save_path=${_absolute_save_path##"$_mntpoint"}
# the real dump path in the 2nd kernel, if the mount point is bind mounted.
_save_path=$(get_bind_mount_directory $_mntpoint)/$_save_path
#erase the old path line, then insert the parsed path
sed -i "/^path/d" ${initdir}/tmp/$$-kdump.conf
echo "path $_save_path" >> ${initdir}/tmp/$$-kdump.conf
fi
}
#install kdump.conf and what user specifies in kdump.conf
kdump_install_conf() {
local _opt _val _pdev
sed -ne '/^#/!p' /etc/kdump.conf > ${initdir}/tmp/$$-kdump.conf
while read _opt _val;
do
# remove inline comments after the end of a directive.
case "$_opt" in
raw)
_pdev=$(persistent_policy="by-id" kdump_get_persistent_dev $_val)
sed -i -e "s#^$_opt[[:space:]]\+$_val#$_opt $_pdev#" ${initdir}/tmp/$$-kdump.conf
;;
ext[234]|xfs|btrfs|minix)
_pdev=$(kdump_get_persistent_dev $_val)
sed -i -e "s#^$_opt[[:space:]]\+$_val#$_opt $_pdev#" ${initdir}/tmp/$$-kdump.conf
if is_atomic; then
adjust_bind_mount_path "$_val"
fi
;;
ssh|nfs)
kdump_install_net "$_val"
;;
2016-08-26 03:23:35 +00:00
dracut_args)
if [[ $(get_dracut_args_fstype "$_val") = nfs* ]] ; then
kdump_install_net "$(get_dracut_args_target "$_val")"
2016-08-26 03:23:35 +00:00
fi
;;
kdump_pre|kdump_post|extra_bins)
dracut_install $_val
;;
core_collector)
dracut_install "${_val%%[[:blank:]]*}"
;;
esac
done <<< "$(read_strip_comments /etc/kdump.conf)"
default_dump_target_install_conf
kdump_configure_fence_kdump "${initdir}/tmp/$$-kdump.conf"
inst "${initdir}/tmp/$$-kdump.conf" "/etc/kdump.conf"
rm -f ${initdir}/tmp/$$-kdump.conf
}
# Default sysctl parameters should suffice for kdump kernel.
# Remove custom configurations sysctl.conf & sysctl.d/*
remove_sysctl_conf() {
# As custom configurations like vm.min_free_kbytes can lead
# to OOM issues in kdump kernel, avoid them
rm -f "${initdir}/etc/sysctl.conf"
rm -rf "${initdir}/etc/sysctl.d"
rm -rf "${initdir}/run/sysctl.d"
rm -rf "${initdir}/usr/lib/sysctl.d"
}
kdump_iscsi_get_rec_val() {
local result
# The open-iscsi 742 release changed to using flat files in
# /var/lib/iscsi.
result=$(/sbin/iscsiadm --show -m session -r ${1} | grep "^${2} = ")
result=${result##* = }
echo $result
}
kdump_get_iscsi_initiator() {
local _initiator
local initiator_conf="/etc/iscsi/initiatorname.iscsi"
[ -f "$initiator_conf" ] || return 1
while read _initiator; do
[ -z "${_initiator%%#*}" ] && continue # Skip comment lines
case $_initiator in
InitiatorName=*)
initiator=${_initiator#InitiatorName=}
echo "rd.iscsi.initiator=${initiator}"
return 0;;
*) ;;
esac
done < ${initiator_conf}
return 1
}
# Figure out iBFT session according to session type
is_ibft() {
[ "$(kdump_iscsi_get_rec_val $1 "node.discovery_type")" = fw ]
}
kdump_setup_iscsi_device() {
local path=$1
local tgt_name; local tgt_ipaddr;
local username; local password; local userpwd_str;
local username_in; local password_in; local userpwd_in_str;
local netdev
local srcaddr
local idev
local netroot_str ; local initiator_str;
local netroot_conf="${initdir}/etc/cmdline.d/50iscsi.conf"
local initiator_conf="/etc/iscsi/initiatorname.iscsi"
dinfo "Found iscsi component $1"
module-setup: suppress the early iscsi error messages Currently, we throw the error message at the very beginning, as a result on a pure-hardware(all-offload) iscsi machine with many iscsi partitions, we suffered from too much noise as follows: iscsiadm: No records found Unable to find iscsi record for /sys/devices/pci0000:00/0000:00:06.0/0000:07:00.0/0000:08:01.1/host0/session1 iscsiadm: No records found Unable to find iscsi record for /sys/devices/pci0000:00/0000:00:06.0/0000:07:00.0/0000:08:01.3/host1/session2 iscsiadm: No records found Unable to find iscsi record for /sys/devices/pci0000:00/0000:00:06.0/0000:07:00.0/0000:08:01.1/host0/session1 iscsiadm: No records found Unable to find iscsi record for /sys/devices/pci0000:00/0000:00:06.0/0000:07:00.0/0000:08:01.3/host1/session2 iscsiadm: No records found Unable to find iscsi record for /sys/devices/pci0000:00/0000:00:06.0/0000:07:00.0/0000:08:01.1/host0/session1 iscsiadm: No records found Unable to find iscsi record for /sys/devices/pci0000:00/0000:00:06.0/0000:07:00.0/0000:08:01.3/host1/session2 iscsiadm: No records found Unable to find iscsi record for /sys/devices/pci0000:00/0000:00:06.0/0000:07:00.0/0000:08:01.1/host0/session1 iscsiadm: No records found Unable to find iscsi record for /sys/devices/pci0000:00/0000:00:06.0/0000:07:00.0/0000:08:01.3/host1/session2 iscsiadm: No records found Unable to find iscsi record for /sys/devices/pci0000:00/0000:00:06.0/0000:07:00.0/0000:08:01.1/host0/session1 iscsiadm: No records found Unable to find iscsi record for /sys/devices/pci0000:00/0000:00:06.0/0000:07:00.0/0000:08:01.3/host1/session2 kexec: loaded kdump kernel Starting kdump: [OK] There's no need to know the very early error messages, we can remove the error output which is actually normal for the pure hardware iscsi. As for unexpected errors, we kept the error outputs in the succeeding kdump_iscsi_get_rec_val() calls by not appending "2>/dev/null". Signed-off-by: Xunlei Pang <xlpang@redhat.com> Acked-by: Dave Young <dyoung@redhat.com>
2017-07-24 13:31:39 +00:00
# Check once before getting explicit values, so we can bail out early,
# e.g. in case of pure-hardware(all-offload) iscsi.
if ! /sbin/iscsiadm -m session -r ${path} &>/dev/null ; then
return 1
fi
if is_ibft ${path}; then
return
fi
# Remove software iscsi cmdline generated by 95iscsi,
# and let kdump regenerate here.
rm -f ${initdir}/etc/cmdline.d/95iscsi.conf
tgt_name=$(kdump_iscsi_get_rec_val ${path} "node.name")
tgt_ipaddr=$(kdump_iscsi_get_rec_val ${path} "node.conn\[0\].address")
# get and set username and password details
username=$(kdump_iscsi_get_rec_val ${path} "node.session.auth.username")
[ "$username" == "<empty>" ] && username=""
password=$(kdump_iscsi_get_rec_val ${path} "node.session.auth.password")
[ "$password" == "<empty>" ] && password=""
username_in=$(kdump_iscsi_get_rec_val ${path} "node.session.auth.username_in")
[ -n "$username" ] && userpwd_str="$username:$password"
# get and set incoming username and password details
[ "$username_in" == "<empty>" ] && username_in=""
password_in=$(kdump_iscsi_get_rec_val ${path} "node.session.auth.password_in")
[ "$password_in" == "<empty>" ] && password_in=""
[ -n "$username_in" ] && userpwd_in_str=":$username_in:$password_in"
netdev=$(/sbin/ip route get to ${tgt_ipaddr} | \
sed 's|.*dev \(.*\).*|\1|g')
srcaddr=$(echo $netdev | awk '{ print $3; exit }')
netdev=$(echo $netdev | awk '{ print $1; exit }')
kdump_setup_netdev $netdev $srcaddr
# prepare netroot= command line
# FIXME: Do we need to parse and set other parameters like protocol, port
# iscsi_iface_name, netdev_name, LUN etc.
if is_ipv6_address $tgt_ipaddr; then
tgt_ipaddr="[$tgt_ipaddr]"
fi
netroot_str="netroot=iscsi:${userpwd_str}${userpwd_in_str}@$tgt_ipaddr::::$tgt_name"
[[ -f $netroot_conf ]] || touch $netroot_conf
# If netroot target does not exist already, append.
if ! grep -q $netroot_str $netroot_conf; then
echo $netroot_str >> $netroot_conf
dinfo "Appended $netroot_str to $netroot_conf"
fi
# Setup initator
initiator_str=$(kdump_get_iscsi_initiator)
[ $? -ne "0" ] && derror "Failed to get initiator name" && return 1
# If initiator details do not exist already, append.
if ! grep -q "$initiator_str" $netroot_conf; then
echo "$initiator_str" >> $netroot_conf
dinfo "Appended "$initiator_str" to $netroot_conf"
fi
}
kdump_check_iscsi_targets () {
# If our prerequisites are not met, fail anyways.
type -P iscsistart >/dev/null || return 1
kdump_check_setup_iscsi() (
local _dev
_dev=$1
[[ -L /sys/dev/block/$_dev ]] || return
cd "$(readlink -f /sys/dev/block/$_dev)"
until [[ -d sys || -d iscsi_session ]]; do
cd ..
done
[[ -d iscsi_session ]] && kdump_setup_iscsi_device "$PWD"
)
[[ $hostonly ]] || [[ $mount_needs ]] && {
for_each_host_dev_and_slaves_all kdump_check_setup_iscsi
}
}
# hostname -a is deprecated, do it by ourself
get_alias() {
local ips
local entries
local alias_set
ips=$(hostname -I)
for ip in $ips
do
entries=$(grep $ip /etc/hosts | awk '{ $1=$2=""; print $0 }')
if [ $? -eq 0 ]; then
alias_set="$alias_set $entries"
fi
done
echo $alias_set
}
is_localhost() {
local hostnames=$(hostname -A)
local shortnames=$(hostname -A -s)
local aliasname=$(get_alias)
local nodename=$1
hostnames="$hostnames $shortnames $aliasname"
for name in ${hostnames}; do
if [ "$name" == "$nodename" ]; then
return 0
fi
done
return 1
}
# retrieves fence_kdump nodes from Pacemaker cluster configuration
get_pcs_fence_kdump_nodes() {
local nodes
# get cluster nodes from cluster cib, get interface and ip address
nodelist=`pcs cluster cib | xmllint --xpath "/cib/status/node_state/@uname" -`
# nodelist is formed as 'uname="node1" uname="node2" ... uname="nodeX"'
# we need to convert each to node1, node2 ... nodeX in each iteration
for node in ${nodelist}; do
# convert $node from 'uname="nodeX"' to 'nodeX'
eval $node
nodename=$uname
# Skip its own node name
if is_localhost $nodename; then
continue
fi
nodes="$nodes $nodename"
done
echo $nodes
}
# retrieves fence_kdump args from config file
get_pcs_fence_kdump_args() {
if [ -f $FENCE_KDUMP_CONFIG_FILE ]; then
. $FENCE_KDUMP_CONFIG_FILE
echo $FENCE_KDUMP_OPTS
fi
}
get_generic_fence_kdump_nodes() {
local filtered
local nodes
nodes=$(get_option_value "fence_kdump_nodes")
for node in ${nodes}; do
# Skip its own node name
if is_localhost $node; then
continue
fi
filtered="$filtered $node"
done
echo $filtered
}
# setup fence_kdump in cluster
# setup proper network and install needed files
kdump_configure_fence_kdump () {
local kdump_cfg_file=$1
local nodes
local args
if is_generic_fence_kdump; then
nodes=$(get_generic_fence_kdump_nodes)
elif is_pcs_fence_kdump; then
nodes=$(get_pcs_fence_kdump_nodes)
# set appropriate options in kdump.conf
echo "fence_kdump_nodes $nodes" >> ${kdump_cfg_file}
args=$(get_pcs_fence_kdump_args)
if [ -n "$args" ]; then
echo "fence_kdump_args $args" >> ${kdump_cfg_file}
fi
else
# fence_kdump not configured
return 1
fi
# setup network for each node
for node in ${nodes}; do
kdump_install_net $node
done
dracut_install /etc/hosts
dracut_install /etc/nsswitch.conf
dracut_install $FENCE_KDUMP_SEND
}
# Install a random seed used to feed /dev/urandom
# By the time kdump service starts, /dev/uramdom is already fed by systemd
kdump_install_random_seed() {
local poolsize=`cat /proc/sys/kernel/random/poolsize`
if [ ! -d ${initdir}/var/lib/ ]; then
mkdir -p ${initdir}/var/lib/
fi
dd if=/dev/urandom of=${initdir}/var/lib/random-seed \
bs=$poolsize count=1 2> /dev/null
}
install() {
kdump_install_conf
remove_sysctl_conf
if is_ssh_dump_target; then
kdump_install_random_seed
fi
dracut_install -o /etc/adjtime /etc/localtime
inst "$moddir/monitor_dd_progress" "/kdumpscripts/monitor_dd_progress"
chmod +x ${initdir}/kdumpscripts/monitor_dd_progress
inst "/bin/dd" "/bin/dd"
inst "/bin/tail" "/bin/tail"
inst "/bin/date" "/bin/date"
inst "/bin/sync" "/bin/sync"
inst "/bin/cut" "/bin/cut"
inst "/bin/head" "/bin/head"
inst "/sbin/makedumpfile" "/sbin/makedumpfile"
inst "/sbin/vmcore-dmesg" "/sbin/vmcore-dmesg"
inst "/lib/kdump/kdump-lib.sh" "/lib/kdump-lib.sh"
inst "/lib/kdump/kdump-lib-initramfs.sh" "/lib/kdump-lib-initramfs.sh"
inst "$moddir/kdump.sh" "/usr/bin/kdump.sh"
inst "$moddir/kdump-capture.service" "$systemdsystemunitdir/kdump-capture.service"
ln_r "$systemdsystemunitdir/kdump-capture.service" "$systemdsystemunitdir/initrd.target.wants/kdump-capture.service"
Introduce kdump error handling service Now upon failure kdump script might not be called at all and it might not be able to execute default action. It results in a hang. Because we disable emergency shell and rely on kdump.sh being invoked through dracut-pre-pivot hook. But it might happen that we never call into dracut-pre-pivot hook because certain systemd targets could not reach due to failure in their dependencies. In those cases error handling code does not run and system hangs. For example: sysroot-var-crash.mount --> initrd-root-fs.target --> initrd.target \ --> dracut-pre-pivot.service --> kdump.sh If /sysroot/var/crash mount fails, initrd-root-fs.target will not be reached. And then initrd.target will not be reached, dracut-pre-pivot.service wouldn't run. Finally kdump.sh wouldn't run. To solve this problem, we need to separate the error handling code from dracut-pre-pivot hook, and every time when a failure shows up, the separated code can be called by the emergency service. By default systemd provides an emergency service which will drop us into shell every time upon a critical failure. It's very convenient for us to re-use the framework of systemd emergency, because we don't have to touch the other parts of systemd. We can use our own script instead of the default one. This new scheme will overwrite emergency shell and replace with kdump error handling code. And this code will do the error handling as needed. Now, we will not rely on dracut-pre-pivot hook running always. Instead whenever error happens and it is serious enough that emergency shell needed to run, now kdump error handler will run. dracut-emergency is also replaced by kdump error handler and it's enabled again all the way down. So all the failure (including systemd and dracut) in 2nd kernel could be captured, and trigger kdump error handler. dracut-initqueue is a special case, which calls "systemctl start emergency" directly, not via "OnFailure=emergency". In case of failure, emergency is started, but not in a isolation mode, which means dracut-initqueue is still running. On the other hand, emergency will call dracut-initqueue again when default action is dump_to_rootfs. systemd would block on the last dracut-initqueue, waiting for the first instance to exit, which leaves us hang. It looks like the following: dracut-initqueue (running) --> call dracut-emergency: --> dracut-emergency (running) --> kdump-error-handler.sh (running) --> call dracut-initqueue: --> blocking and waiting for the original instance to exit. To fix this, I'd like to introduce a wrapper emergency service. This emegency service will replace both the systemd and dracut emergency. And this service does nothing but to isolate to real kdump error handler service: dracut-initqueue (running) --> call dracut-emergency: --> dracut-emergency isolate to kdump-error-handler.service --> dracut-emergency and dracut-initqueue will both be stopped and kdump-error-handler.service will run kdump-error-handler.sh. In a normal failure case, this still works: foo.service fails --> trigger emergency.service --> emergency.service isolates to kdump-error-handler.service --> kdump-error-handler.service will run kdump-error-handler.sh Signed-off-by: WANG Chao <chaowang@redhat.com> Acked-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Dave Young <dyoung@redhat.com>
2014-05-08 11:37:15 +00:00
inst "$moddir/kdump-error-handler.sh" "/usr/bin/kdump-error-handler.sh"
inst "$moddir/kdump-error-handler.service" "$systemdsystemunitdir/kdump-error-handler.service"
kdump-emergency: fix "Transaction is destructive" emergency failure We met a problem that the kdump emergency service failed to start when the target dump timeout(we passed "rd.timeout=30" to kdump), it reported "Transaction is destructive" messages: [ TIME ] Timed out waiting for device dev-mapper-fedora\x2droot.device. [DEPEND] Dependency failed for Initrd Root Device. [ SKIP ] Ordering cycle found, skipping System Initialization [DEPEND] Dependency failed for /sysroot. [DEPEND] Dependency failed for Initrd Root File System. [DEPEND] Dependency failed for Reload Configuration from the Real Root. [ SKIP ] Ordering cycle found, skipping System Initialization [ SKIP ] Ordering cycle found, skipping Initrd Default Target [DEPEND] Dependency failed for File System Check on /dev/mapper/fedora-root. [ OK ] Reached target Initrd File Systems. [ OK ] Stopped dracut pre-udev hook. [ OK ] Stopped dracut cmdline hook. Starting Setup Virtual Console... Starting Kdump Emergency... [ OK ] Reached target Initrd Default Target. [ OK ] Stopped dracut initqueue hook. Failed to start kdump-error-handler.service: Transaction is destructive. See system logs and 'systemctl status kdump-error-handler.service' for details. [FAILED] Failed to start Kdump Emergency. See 'systemctl status emergency.service' for details. [DEPEND] Dependency failed for Emergency Mode. This is because in case of root failure, initrd-root-fs.target will trigger systemd emergency target which requires the systemd emergency service actually is kdump-emergency.service, then our kdump-emergency.service starts kdump-error-handler.service with "systemctl isolate"(see 99kdumpbase/kdump-emergency.service, we replace systemd's with this one under kdump). This will lead to systemd two contradictable jobs queued as an atomic transaction: job 1) the emergency service gets started by initrd-root-fs.target job 2) the emergency service gets stopped due to "systemctl isolate" thereby throwing "Transaction is destructive". In order to solve it, we can utilize "IgnoreOnIsolate=yes" for both kdump-emergency.service and kdump-emergency.target. Unit with attribute "IgnoreOnIsolate=yes" won't be stopped when isolating another unit, they can keep going as expected in case be triggered by any failure. We add kdump-emergency.target dedicated to kdump the similar way as did for kdump-emergency.service(i.e. will replace systemd's emergency.target with kdump-emergency.target under kdump), and adds "IgnoreOnIsolate=yes" into both of them. Signed-off-by: Xunlei Pang <xlpang@redhat.com> Acked-by: Dave Young <dyoung@redhat.com> Acked-by: Pratyush Anand <panand@redhat.com> [bhe: improve the patch log about IgnoreOnIsolate="]
2017-03-27 04:07:32 +00:00
# Replace existing emergency service and emergency target
Introduce kdump error handling service Now upon failure kdump script might not be called at all and it might not be able to execute default action. It results in a hang. Because we disable emergency shell and rely on kdump.sh being invoked through dracut-pre-pivot hook. But it might happen that we never call into dracut-pre-pivot hook because certain systemd targets could not reach due to failure in their dependencies. In those cases error handling code does not run and system hangs. For example: sysroot-var-crash.mount --> initrd-root-fs.target --> initrd.target \ --> dracut-pre-pivot.service --> kdump.sh If /sysroot/var/crash mount fails, initrd-root-fs.target will not be reached. And then initrd.target will not be reached, dracut-pre-pivot.service wouldn't run. Finally kdump.sh wouldn't run. To solve this problem, we need to separate the error handling code from dracut-pre-pivot hook, and every time when a failure shows up, the separated code can be called by the emergency service. By default systemd provides an emergency service which will drop us into shell every time upon a critical failure. It's very convenient for us to re-use the framework of systemd emergency, because we don't have to touch the other parts of systemd. We can use our own script instead of the default one. This new scheme will overwrite emergency shell and replace with kdump error handling code. And this code will do the error handling as needed. Now, we will not rely on dracut-pre-pivot hook running always. Instead whenever error happens and it is serious enough that emergency shell needed to run, now kdump error handler will run. dracut-emergency is also replaced by kdump error handler and it's enabled again all the way down. So all the failure (including systemd and dracut) in 2nd kernel could be captured, and trigger kdump error handler. dracut-initqueue is a special case, which calls "systemctl start emergency" directly, not via "OnFailure=emergency". In case of failure, emergency is started, but not in a isolation mode, which means dracut-initqueue is still running. On the other hand, emergency will call dracut-initqueue again when default action is dump_to_rootfs. systemd would block on the last dracut-initqueue, waiting for the first instance to exit, which leaves us hang. It looks like the following: dracut-initqueue (running) --> call dracut-emergency: --> dracut-emergency (running) --> kdump-error-handler.sh (running) --> call dracut-initqueue: --> blocking and waiting for the original instance to exit. To fix this, I'd like to introduce a wrapper emergency service. This emegency service will replace both the systemd and dracut emergency. And this service does nothing but to isolate to real kdump error handler service: dracut-initqueue (running) --> call dracut-emergency: --> dracut-emergency isolate to kdump-error-handler.service --> dracut-emergency and dracut-initqueue will both be stopped and kdump-error-handler.service will run kdump-error-handler.sh. In a normal failure case, this still works: foo.service fails --> trigger emergency.service --> emergency.service isolates to kdump-error-handler.service --> kdump-error-handler.service will run kdump-error-handler.sh Signed-off-by: WANG Chao <chaowang@redhat.com> Acked-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Dave Young <dyoung@redhat.com>
2014-05-08 11:37:15 +00:00
cp "$moddir/kdump-emergency.service" "$initdir/$systemdsystemunitdir/emergency.service"
kdump-emergency: fix "Transaction is destructive" emergency failure We met a problem that the kdump emergency service failed to start when the target dump timeout(we passed "rd.timeout=30" to kdump), it reported "Transaction is destructive" messages: [ TIME ] Timed out waiting for device dev-mapper-fedora\x2droot.device. [DEPEND] Dependency failed for Initrd Root Device. [ SKIP ] Ordering cycle found, skipping System Initialization [DEPEND] Dependency failed for /sysroot. [DEPEND] Dependency failed for Initrd Root File System. [DEPEND] Dependency failed for Reload Configuration from the Real Root. [ SKIP ] Ordering cycle found, skipping System Initialization [ SKIP ] Ordering cycle found, skipping Initrd Default Target [DEPEND] Dependency failed for File System Check on /dev/mapper/fedora-root. [ OK ] Reached target Initrd File Systems. [ OK ] Stopped dracut pre-udev hook. [ OK ] Stopped dracut cmdline hook. Starting Setup Virtual Console... Starting Kdump Emergency... [ OK ] Reached target Initrd Default Target. [ OK ] Stopped dracut initqueue hook. Failed to start kdump-error-handler.service: Transaction is destructive. See system logs and 'systemctl status kdump-error-handler.service' for details. [FAILED] Failed to start Kdump Emergency. See 'systemctl status emergency.service' for details. [DEPEND] Dependency failed for Emergency Mode. This is because in case of root failure, initrd-root-fs.target will trigger systemd emergency target which requires the systemd emergency service actually is kdump-emergency.service, then our kdump-emergency.service starts kdump-error-handler.service with "systemctl isolate"(see 99kdumpbase/kdump-emergency.service, we replace systemd's with this one under kdump). This will lead to systemd two contradictable jobs queued as an atomic transaction: job 1) the emergency service gets started by initrd-root-fs.target job 2) the emergency service gets stopped due to "systemctl isolate" thereby throwing "Transaction is destructive". In order to solve it, we can utilize "IgnoreOnIsolate=yes" for both kdump-emergency.service and kdump-emergency.target. Unit with attribute "IgnoreOnIsolate=yes" won't be stopped when isolating another unit, they can keep going as expected in case be triggered by any failure. We add kdump-emergency.target dedicated to kdump the similar way as did for kdump-emergency.service(i.e. will replace systemd's emergency.target with kdump-emergency.target under kdump), and adds "IgnoreOnIsolate=yes" into both of them. Signed-off-by: Xunlei Pang <xlpang@redhat.com> Acked-by: Dave Young <dyoung@redhat.com> Acked-by: Pratyush Anand <panand@redhat.com> [bhe: improve the patch log about IgnoreOnIsolate="]
2017-03-27 04:07:32 +00:00
cp "$moddir/kdump-emergency.target" "$initdir/$systemdsystemunitdir/emergency.target"
Introduce kdump error handling service Now upon failure kdump script might not be called at all and it might not be able to execute default action. It results in a hang. Because we disable emergency shell and rely on kdump.sh being invoked through dracut-pre-pivot hook. But it might happen that we never call into dracut-pre-pivot hook because certain systemd targets could not reach due to failure in their dependencies. In those cases error handling code does not run and system hangs. For example: sysroot-var-crash.mount --> initrd-root-fs.target --> initrd.target \ --> dracut-pre-pivot.service --> kdump.sh If /sysroot/var/crash mount fails, initrd-root-fs.target will not be reached. And then initrd.target will not be reached, dracut-pre-pivot.service wouldn't run. Finally kdump.sh wouldn't run. To solve this problem, we need to separate the error handling code from dracut-pre-pivot hook, and every time when a failure shows up, the separated code can be called by the emergency service. By default systemd provides an emergency service which will drop us into shell every time upon a critical failure. It's very convenient for us to re-use the framework of systemd emergency, because we don't have to touch the other parts of systemd. We can use our own script instead of the default one. This new scheme will overwrite emergency shell and replace with kdump error handling code. And this code will do the error handling as needed. Now, we will not rely on dracut-pre-pivot hook running always. Instead whenever error happens and it is serious enough that emergency shell needed to run, now kdump error handler will run. dracut-emergency is also replaced by kdump error handler and it's enabled again all the way down. So all the failure (including systemd and dracut) in 2nd kernel could be captured, and trigger kdump error handler. dracut-initqueue is a special case, which calls "systemctl start emergency" directly, not via "OnFailure=emergency". In case of failure, emergency is started, but not in a isolation mode, which means dracut-initqueue is still running. On the other hand, emergency will call dracut-initqueue again when default action is dump_to_rootfs. systemd would block on the last dracut-initqueue, waiting for the first instance to exit, which leaves us hang. It looks like the following: dracut-initqueue (running) --> call dracut-emergency: --> dracut-emergency (running) --> kdump-error-handler.sh (running) --> call dracut-initqueue: --> blocking and waiting for the original instance to exit. To fix this, I'd like to introduce a wrapper emergency service. This emegency service will replace both the systemd and dracut emergency. And this service does nothing but to isolate to real kdump error handler service: dracut-initqueue (running) --> call dracut-emergency: --> dracut-emergency isolate to kdump-error-handler.service --> dracut-emergency and dracut-initqueue will both be stopped and kdump-error-handler.service will run kdump-error-handler.sh. In a normal failure case, this still works: foo.service fails --> trigger emergency.service --> emergency.service isolates to kdump-error-handler.service --> kdump-error-handler.service will run kdump-error-handler.sh Signed-off-by: WANG Chao <chaowang@redhat.com> Acked-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Dave Young <dyoung@redhat.com>
2014-05-08 11:37:15 +00:00
# Also redirect dracut-emergency to kdump error handler
ln_r "$systemdsystemunitdir/emergency.service" "$systemdsystemunitdir/dracut-emergency.service"
# Check for all the devices and if any device is iscsi, bring up iscsi
# target. Ideally all this should be pushed into dracut iscsi module
# at some point of time.
kdump_check_iscsi_targets
# For the lvm type target under kdump, in /etc/lvm/lvm.conf we can
# safely replace "reserved_memory=XXXX"(default value is 8192) with
# "reserved_memory=1024" to lower memory pressure under kdump. We do
# it unconditionally here, if "/etc/lvm/lvm.conf" doesn't exist, it
# actually does nothing.
sed -i -e \
's/\(^[[:space:]]*reserved_memory[[:space:]]*=\)[[:space:]]*[[:digit:]]*/\1 1024/' \
${initdir}/etc/lvm/lvm.conf &>/dev/null
# Kdump turns out to require longer default systemd mount timeout
# than 1st kernel(90s by default), we use default 300s for kdump.
grep -r "^[[:space:]]*DefaultTimeoutStartSec=" ${initdir}/etc/systemd/system.conf* &>/dev/null
if [ $? -ne 0 ]; then
mkdir -p ${initdir}/etc/systemd/system.conf.d
echo "[Manager]" > ${initdir}/etc/systemd/system.conf.d/kdump.conf
echo "DefaultTimeoutStartSec=300s" >> ${initdir}/etc/systemd/system.conf.d/kdump.conf
fi
# Forward logs to console directly, this avoids unneccessary memory
# consumption and make console output more useful.
# Only do so for non fadump image.
if ! is_fadump_capable; then
mkdir -p ${initdir}/etc/systemd/journald.conf.d
echo "[Journal]" > ${initdir}/etc/systemd/journald.conf.d/kdump.conf
echo "Storage=none" >> ${initdir}/etc/systemd/journald.conf.d/kdump.conf
echo "ForwardToConsole=yes" >> ${initdir}/etc/systemd/journald.conf.d/kdump.conf
fi
}