rpms/kexec-tools
7
0
Fork 0
Code Issues Pull Requests Releases Activity

import kexec-tools-2.0.20-34.el8_3.1

Browse Source
This commit is contained in:
CentOS Sources 2020-12-15 10:59:59 -05:00 committed by Andrew Lukoshko
commit 89a2b3181d
58 changed files with 10805 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.gitignore vendored Normal file
View File

@ -0,0 +1,3 @@
SOURCES/eppic_050615.tar.gz
SOURCES/kexec-tools-2.0.20.tar.xz
SOURCES/makedumpfile-1.6.7.tar.gz

3
.kexec-tools.metadata Normal file
View File

@ -0,0 +1,3 @@
a096c8e0892b559f40b01916aae240652f75b68a SOURCES/eppic_050615.tar.gz
5d9acd2e741d356d4a48fe4f2d63f66ba431051d SOURCES/kexec-tools-2.0.20.tar.xz
42941a0219d57d99909616778835e5d9ba890711 SOURCES/makedumpfile-1.6.7.tar.gz

16
SOURCES/98-kexec.rules Normal file
View File

@ -0,0 +1,16 @@
SUBSYSTEM=="cpu", ACTION=="add", GOTO="kdump_reload"
SUBSYSTEM=="cpu", ACTION=="remove", GOTO="kdump_reload"
SUBSYSTEM=="memory", ACTION=="online", GOTO="kdump_reload"
SUBSYSTEM=="memory", ACTION=="offline", GOTO="kdump_reload"
GOTO="kdump_reload_end"
LABEL="kdump_reload"
# If kdump is not loaded, calling kdump-udev-throttle will end up
# doing nothing, but systemd-run will always generate extra logs for
# each call, so trigger the kdump-udev-throttler only if kdump
# service is active to avoid unnecessary logs
RUN+="/bin/sh -c '/usr/bin/systemctl is-active kdump.service || exit 0; /usr/bin/systemd-run --quiet --no-block /usr/lib/udev/kdump-udev-throttler'"
LABEL="kdump_reload_end"

15
SOURCES/98-kexec.rules.ppc64 Normal file
View File

@ -0,0 +1,15 @@
SUBSYSTEM=="cpu", ACTION=="online", GOTO="kdump_reload"
SUBSYSTEM=="memory", ACTION=="online", GOTO="kdump_reload"
SUBSYSTEM=="memory", ACTION=="offline", GOTO="kdump_reload"
GOTO="kdump_reload_end"
LABEL="kdump_reload"
# If kdump is not loaded, calling kdump-udev-throttle will end up
# doing nothing, but systemd-run will always generate extra logs for
# each call, so trigger the kdump-udev-throttler only if kdump
# service is active to avoid unnecessary logs
RUN+="/bin/sh -c '/usr/bin/systemctl is-active kdump.service || exit 0; /usr/bin/systemd-run --quiet --no-block /usr/lib/udev/kdump-udev-throttler'"
LABEL="kdump_reload_end"

65
SOURCES/dracut-early-kdump-module-setup.sh Executable file
View File

@ -0,0 +1,65 @@
#!/bin/bash
. /etc/sysconfig/kdump
. /lib/kdump/kdump-lib.sh
KDUMP_KERNEL=""
KDUMP_INITRD=""
check() {
if [ ! -f /etc/sysconfig/kdump ] || [ ! -f /lib/kdump/kdump-lib.sh ]\
|| [ -n "${IN_KDUMP}" ]
then
return 1
fi
return 255
}
depends() {
echo "base shutdown"
return 0
}
prepare_kernel_initrd() {
KDUMP_BOOTDIR=$(check_boot_dir "${KDUMP_BOOTDIR}")
if [ -z "$KDUMP_KERNELVER" ]; then
kdump_kver=`uname -r`
if [ "$kernel" != "$kdump_kver" ]; then
dwarn "Using current kernel version '$kdump_kver' for early kdump," \
"but the initramfs is generated for kernel version '$kernel'"
fi
else
kdump_kver=$KDUMP_KERNELVER
fi
KDUMP_KERNEL="${KDUMP_BOOTDIR}/${KDUMP_IMG}-${kdump_kver}${KDUMP_IMG_EXT}"
KDUMP_INITRD="${KDUMP_BOOTDIR}/initramfs-${kdump_kver}kdump.img"
}
install() {
prepare_kernel_initrd
if [ ! -f "$KDUMP_KERNEL" ]; then
derror "Could not find required kernel for earlykdump," \
"earlykdump will not work!"
return 1
fi
if [ ! -f "$KDUMP_INITRD" ]; then
derror "Could not find required kdump initramfs for earlykdump," \
"please ensure kdump initramfs is generated first," \
"earlykdump will not work!"
return 1
fi
inst_multiple tail find cut dirname hexdump
inst_simple "/etc/sysconfig/kdump"
inst_binary "/usr/sbin/kexec"
inst_binary "/usr/bin/gawk" "/usr/bin/awk"
inst_script "/lib/kdump/kdump-lib.sh" "/lib/kdump-lib.sh"
inst_hook cmdline 00 "$moddir/early-kdump.sh"
inst_binary "$KDUMP_KERNEL"
inst_binary "$KDUMP_INITRD"
ln_r "$KDUMP_KERNEL" "${KDUMP_BOOTDIR}/${KDUMP_IMG}-earlykdump${KDUMP_IMG_EXT}"
ln_r "$KDUMP_INITRD" "${KDUMP_BOOTDIR}/initramfs-earlykdump.img"
chmod -x "${initdir}/$KDUMP_KERNEL"
}

75
SOURCES/dracut-early-kdump.sh Executable file
View File

@ -0,0 +1,75 @@
#! /bin/sh
KEXEC=/sbin/kexec
standard_kexec_args="-p"
EARLY_KDUMP_INITRD=""
EARLY_KDUMP_KERNEL=""
EARLY_KDUMP_CMDLINE=""
EARLY_KDUMP_KERNELVER=""
EARLY_KEXEC_ARGS=""
. /etc/sysconfig/kdump
. /lib/dracut-lib.sh
. /lib/kdump-lib.sh
prepare_parameters()
{
EARLY_KDUMP_CMDLINE=$(prepare_cmdline "${KDUMP_COMMANDLINE}" "${KDUMP_COMMANDLINE_REMOVE}" "${KDUMP_COMMANDLINE_APPEND}")
KDUMP_BOOTDIR=$(check_boot_dir "${KDUMP_BOOTDIR}")
EARLY_KDUMP_KERNEL="${KDUMP_BOOTDIR}/${KDUMP_IMG}-earlykdump${KDUMP_IMG_EXT}"
EARLY_KDUMP_INITRD="${KDUMP_BOOTDIR}/initramfs-earlykdump.img"
}
early_kdump_load()
{
check_kdump_feasibility
if [ $? -ne 0 ]; then
return 1
fi
if is_fadump_capable; then
echo "WARNING: early kdump doesn't support fadump."
return 1
fi
check_current_kdump_status
if [ $? == 0 ]; then
return 1
fi
prepare_parameters
EARLY_KEXEC_ARGS=$(prepare_kexec_args "${KEXEC_ARGS}")
if is_secure_boot_enforced; then
echo "Secure Boot is enabled. Using kexec file based syscall."
EARLY_KEXEC_ARGS="$EARLY_KEXEC_ARGS -s"
fi
$KEXEC ${EARLY_KEXEC_ARGS} $standard_kexec_args \
--command-line="$EARLY_KDUMP_CMDLINE" \
--initrd=$EARLY_KDUMP_INITRD $EARLY_KDUMP_KERNEL
if [ $? == 0 ]; then
echo "kexec: loaded early-kdump kernel"
return 0
else
echo "kexec: failed to load early-kdump kernel"
return 1
fi
}
set_early_kdump()
{
if getargbool 0 rd.earlykdump; then
echo "early-kdump is enabled."
early_kdump_load
else
echo "early-kdump is disabled."
fi
return 0
}
set_early_kdump

30
SOURCES/dracut-kdump-capture.service Normal file
View File

@ -0,0 +1,30 @@
# This file is part of systemd.
#
# systemd is free software; you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published by
# the Free Software Foundation; either version 2.1 of the License, or
# (at your option) any later version.
[Unit]
Description=Kdump Vmcore Save Service
After=initrd.target initrd-parse-etc.service sysroot.mount
After=dracut-initqueue.service dracut-pre-mount.service dracut-mount.service dracut-pre-pivot.service
Before=initrd-cleanup.service
ConditionPathExists=/etc/initrd-release
OnFailure=emergency.target
OnFailureJobMode=isolate
[Service]
Environment=DRACUT_SYSTEMD=1
Environment=NEWROOT=/sysroot
Type=oneshot
ExecStart=/bin/kdump.sh
StandardInput=null
StandardOutput=syslog
StandardError=syslog+console
KillMode=process
RemainAfterExit=yes
# Bash ignores SIGTERM, so we send SIGHUP instead, to ensure that bash
# terminates cleanly.
KillSignal=SIGHUP

28
SOURCES/dracut-kdump-emergency.service Normal file
View File

@ -0,0 +1,28 @@
# This file is part of systemd.
#
# systemd is free software; you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published by
# the Free Software Foundation; either version 2.1 of the License, or
# (at your option) any later version.
# This service will be placed in kdump initramfs and replace both the systemd
# emergency service and dracut emergency shell. IOW, any emergency will be
# kick this service and in turn isolating to kdump error handler.
[Unit]
Description=Kdump Emergency
DefaultDependencies=no
IgnoreOnIsolate=yes
[Service]
ExecStart=/usr/bin/systemctl --no-block isolate kdump-error-handler.service
Type=oneshot
StandardInput=tty-force
StandardOutput=inherit
StandardError=inherit
KillMode=process
IgnoreSIGPIPE=no
# Bash ignores SIGTERM, so we send SIGHUP instead, to ensure that bash
# terminates cleanly.
KillSignal=SIGHUP

14
SOURCES/dracut-kdump-emergency.target Normal file
View File

@ -0,0 +1,14 @@
# This file is part of systemd.
#
# systemd is free software; you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published by
# the Free Software Foundation; either version 2.1 of the License, or
# (at your option) any later version.
[Unit]
Description=Emergency Mode
Documentation=man:systemd.special(7)
Requires=emergency.service
After=emergency.service
AllowIsolate=yes
IgnoreOnIsolate=yes

33
SOURCES/dracut-kdump-error-handler.service Normal file
View File

@ -0,0 +1,33 @@
# This file is part of systemd.
#
# systemd is free software; you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published by
# the Free Software Foundation; either version 2.1 of the License, or
# (at your option) any later version.
# This service will run the real kdump error handler code. Executing the
# failure action configured in kdump.conf
[Unit]
Description=Kdump Error Handler
DefaultDependencies=no
After=systemd-vconsole-setup.service
Wants=systemd-vconsole-setup.service
AllowIsolate=yes
[Service]
Environment=HOME=/
Environment=DRACUT_SYSTEMD=1
Environment=NEWROOT=/sysroot
WorkingDirectory=/
ExecStart=/bin/kdump-error-handler.sh
Type=oneshot
StandardInput=tty-force
StandardOutput=inherit
StandardError=inherit
KillMode=process
IgnoreSIGPIPE=no
# Bash ignores SIGTERM, so we send SIGHUP instead, to ensure that bash
# terminates cleanly.
KillSignal=SIGHUP

10
SOURCES/dracut-kdump-error-handler.sh Executable file
View File

@ -0,0 +1,10 @@
#!/bin/sh
. /lib/kdump-lib-initramfs.sh
set -o pipefail
export PATH=$PATH:$KDUMP_SCRIPT_DIR
get_kdump_confs
do_failure_action
do_final_action

271
SOURCES/dracut-kdump.sh Executable file
View File

@ -0,0 +1,271 @@
#!/bin/sh
# continue here only if we have to save dump.
if [ -f /etc/fadump.initramfs ] && [ ! -f /proc/device-tree/rtas/ibm,kernel-dump ] && [ ! -f /proc/device-tree/ibm,opal/dump/mpipl-boot ]; then
exit 0
fi
exec &> /dev/console
. /lib/dracut-lib.sh
. /lib/kdump-lib-initramfs.sh
set -o pipefail
DUMP_RETVAL=0
export PATH=$PATH:$KDUMP_SCRIPT_DIR
do_dump()
{
local _ret
eval $DUMP_INSTRUCTION
_ret=$?
if [ $_ret -ne 0 ]; then
echo "kdump: saving vmcore failed"
fi
return $_ret
}
do_kdump_pre()
{
local _ret
if [ -n "$KDUMP_PRE" ]; then
"$KDUMP_PRE"
_ret=$?
if [ $_ret -ne 0 ]; then
echo "kdump: $KDUMP_PRE exited with $_ret status"
return $_ret
fi
fi
# if any script fails, it just raises warning and continues
if [ -d /etc/kdump/pre.d ]; then
for file in /etc/kdump/pre.d/*; do
"$file"
_ret=$?
if [ $_ret -ne 0 ]; then
echo "kdump: $file exited with $_ret status"
fi
done
fi
return 0
}
do_kdump_post()
{
local _ret
if [ -d /etc/kdump/post.d ]; then
for file in /etc/kdump/post.d/*; do
"$file" "$1"
_ret=$?
if [ $_ret -ne 0 ]; then
echo "kdump: $file exited with $_ret status"
fi
done
fi
if [ -n "$KDUMP_POST" ]; then
"$KDUMP_POST" "$1"
_ret=$?
if [ $_ret -ne 0 ]; then
echo "kdump: $KDUMP_POST exited with $_ret status"
fi
fi
}
add_dump_code()
{
DUMP_INSTRUCTION=$1
}
dump_raw()
{
local _raw=$1
[ -b "$_raw" ] || return 1
echo "kdump: saving to raw disk $_raw"
if ! $(echo -n $CORE_COLLECTOR|grep -q makedumpfile); then
_src_size=`ls -l /proc/vmcore | cut -d' ' -f5`
_src_size_mb=$(($_src_size / 1048576))
monitor_dd_progress $_src_size_mb &
fi
echo "kdump: saving vmcore"
$CORE_COLLECTOR /proc/vmcore | dd of=$_raw bs=$DD_BLKSIZE >> /tmp/dd_progress_file 2>&1 || return 1
sync
echo "kdump: saving vmcore complete"
return 0
}
dump_ssh()
{
local _opt="-i $1 -o BatchMode=yes -o StrictHostKeyChecking=yes"
local _dir="$KDUMP_PATH/$HOST_IP-$DATEDIR"
local _host=$2
echo "kdump: saving to $_host:$_dir"
cat /var/lib/random-seed > /dev/urandom
ssh -q $_opt $_host mkdir -p $_dir || return 1
save_vmcore_dmesg_ssh ${DMESG_COLLECTOR} ${_dir} "${_opt}" $_host
save_opalcore_ssh ${_dir} "${_opt}" $_host
echo "kdump: saving vmcore"
if [ "${CORE_COLLECTOR%%[[:blank:]]*}" = "scp" ]; then
scp -q $_opt /proc/vmcore "$_host:$_dir/vmcore-incomplete" || return 1
ssh $_opt $_host "mv $_dir/vmcore-incomplete $_dir/vmcore" || return 1
else
$CORE_COLLECTOR /proc/vmcore | ssh $_opt $_host "dd bs=512 of=$_dir/vmcore-incomplete" || return 1
ssh $_opt $_host "mv $_dir/vmcore-incomplete $_dir/vmcore.flat" || return 1
fi
echo "kdump: saving vmcore complete"
return 0
}
save_opalcore_ssh() {
local _path=$1
local _opts="$2"
local _location=$3
if [ ! -f $OPALCORE ]; then
# Check if we are on an old kernel that uses a different path
if [ -f /sys/firmware/opal/core ]; then
OPALCORE="/sys/firmware/opal/core"
else
return 0
fi
fi
echo "kdump: saving opalcore"
scp $_opts $OPALCORE $_location:$_path/opalcore-incomplete
if [ $? -ne 0 ]; then
echo "kdump: saving opalcore failed"
return 1
fi
ssh $_opts $_location mv $_path/opalcore-incomplete $_path/opalcore
echo "kdump: saving opalcore complete"
return 0
}
save_vmcore_dmesg_ssh() {
local _dmesg_collector=$1
local _path=$2
local _opts="$3"
local _location=$4
echo "kdump: saving vmcore-dmesg.txt"
$_dmesg_collector /proc/vmcore | ssh $_opts $_location "dd of=$_path/vmcore-dmesg-incomplete.txt"
_exitcode=$?
if [ $_exitcode -eq 0 ]; then
ssh -q $_opts $_location mv $_path/vmcore-dmesg-incomplete.txt $_path/vmcore-dmesg.txt
echo "kdump: saving vmcore-dmesg.txt complete"
else
echo "kdump: saving vmcore-dmesg.txt failed"
fi
}
get_host_ip()
{
local _host
if is_nfs_dump_target || is_ssh_dump_target
then
kdumpnic=$(getarg kdumpnic=)
[ -z "$kdumpnic" ] && echo "kdump: failed to get kdumpnic!" && return 1
_host=`ip addr show dev $kdumpnic|grep '[ ]*inet'`
[ $? -ne 0 ] && echo "kdump: wrong kdumpnic: $kdumpnic" && return 1
_host=`echo $_host | head -n 1 | cut -d' ' -f2`
_host="${_host%%/*}"
[ -z "$_host" ] && echo "kdump: wrong kdumpnic: $kdumpnic" && return 1
HOST_IP=$_host
fi
return 0
}
read_kdump_conf()
{
if [ ! -f "$KDUMP_CONF" ]; then
echo "kdump: $KDUMP_CONF not found"
return
fi
get_kdump_confs
# rescan for add code for dump target
while read config_opt config_val;
do
# remove inline comments after the end of a directive.
case "$config_opt" in
dracut_args)
config_val=$(get_dracut_args_target "$config_val")
if [ -n "$config_val" ]; then
config_val=$(get_mntpoint_from_target "$config_val")
add_dump_code "dump_fs $config_val"
fi
;;
ext[234]|xfs|btrfs|minix|nfs)
config_val=$(get_mntpoint_from_target "$config_val")
add_dump_code "dump_fs $config_val"
;;
raw)
add_dump_code "dump_raw $config_val"
;;
ssh)
add_dump_code "dump_ssh $SSH_KEY_LOCATION $config_val"
;;
esac
done <<< "$(read_strip_comments $KDUMP_CONF)"
}
fence_kdump_notify()
{
if [ -n "$FENCE_KDUMP_NODES" ]; then
$FENCE_KDUMP_SEND $FENCE_KDUMP_ARGS $FENCE_KDUMP_NODES &
fi
}
read_kdump_conf
fence_kdump_notify
get_host_ip
if [ $? -ne 0 ]; then
echo "kdump: get_host_ip exited with non-zero status!"
exit 1
fi
if [ -z "$DUMP_INSTRUCTION" ]; then
add_dump_code "dump_fs $NEWROOT"
fi
do_kdump_pre
if [ $? -ne 0 ]; then
echo "kdump: kdump_pre script exited with non-zero status!"
do_final_action
# During systemd service to reboot the machine, stop this shell script running
exit 1
fi
make_trace_mem "kdump saving vmcore" '1:shortmem' '2+:mem' '3+:slab'
do_dump
DUMP_RETVAL=$?
do_kdump_post $DUMP_RETVAL
if [ $? -ne 0 ]; then
echo "kdump: kdump_post script exited with non-zero status!"
fi
if [ $DUMP_RETVAL -ne 0 ]; then
exit 1
fi
do_final_action

840
SOURCES/dracut-module-setup.sh Executable file
View File

@ -0,0 +1,840 @@
#!/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 || is_pcs_fence_kdump; then
_dep="$_dep network"
fi
echo $_dep
return 0
}
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 " |\
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_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
# 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=$(kdump_setup_ifname $_netdev):$_phydev" > ${initdir}/etc/cmdline.d/43vlan.conf
else
_kdumpdev="$(kdump_setup_ifname $_phydev)"
echo " vlan=$(kdump_setup_ifname $_netdev):$_kdumpdev ifname=$_kdumpdev:$_netmac" > ${initdir}/etc/cmdline.d/43vlan.conf
fi
}
# setup s390 znet cmdline
# $1: netdev name
kdump_setup_znet() {
local _options=""
local _netdev=$1
source_ifcfg_file $_netdev
for i in $OPTIONS; do
_options=${_options},$i
done
echo rd.znet=${NETTYPE},${SUBCHANNELS}${_options} rd.znet_ifname=$_netdev:${SUBCHANNELS} > ${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"
if [ ! -f ${initdir}/etc/cmdline.d/50neednet.conf ]; then
# network-manager module needs this parameter
echo "rd.neednet" >> ${initdir}/etc/cmdline.d/50neednet.conf
fi
}
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
}
# install etc/kdump/pre.d and /etc/kdump/post.d
kdump_install_pre_post_conf() {
if [ -d /etc/kdump/pre.d ]; then
for file in /etc/kdump/pre.d/*; do
if [ -x "$file" ]; then
dracut_install $file
elif [ $file != "/etc/kdump/pre.d/*" ]; then
echo "$file is not executable"
fi
done
fi
if [ -d /etc/kdump/post.d ]; then
for file in /etc/kdump/post.d/*; do
if [ -x "$file" ]; then
dracut_install $file
elif [ $file != "/etc/kdump/post.d/*" ]; then
echo "$file is not executable"
fi
done
fi
}
default_dump_target_install_conf()
{
local _target _fstype
local _mntpoint _save_path
is_user_configured_dump_target && return
_save_path=$(get_bind_mount_source $(get_save_path))
_target=$(get_target_from_path $_save_path)
_mntpoint=$(get_mntpoint_from_target $_target)
_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
# 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
}
#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/$$-kdump.conf
;;
ssh|nfs)
kdump_install_net "$_val"
;;
dracut_args)
if [[ $(get_dracut_args_fstype "$_val") = nfs* ]] ; then
kdump_install_net "$(get_dracut_args_target "$_val")"
fi
;;
kdump_pre|kdump_post|extra_bins)
dracut_install $_val
;;
core_collector)
dracut_install "${_val%%[[:blank:]]*}"
;;
esac
done <<< "$(read_strip_comments /etc/kdump.conf)"
kdump_install_pre_post_conf
default_dump_target_install_conf
kdump_configure_fence_kdump "${initdir}/tmp/$$-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"
# 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 $ips
do
# in /etc/hosts, alias can come at the 2nd column
entries=$(grep $ip /etc/hosts | awk '{ $1=""; 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 [ "$nodename" = `hostname` -o "$nodename" = `hostname -s` ]; 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=$poolsize count=1 2> /dev/null
}
remove_cpu_online_rule() {
local file=${initdir}/usr/lib/udev/rules.d/40-redhat.rules
sed -i '/SUBSYSTEM=="cpu"/d' $file
}
install() {
local arch
kdump_install_conf
remove_sysctl_conf
# Onlining secondary cpus breaks kdump completely on KVM on Power hosts
# Though we use maxcpus=1 by default but 40-redhat.rules will bring up all
# possible cpus by default. (rhbz1270174 rhbz1266322)
# Thus before we get the kernel fix and the systemd rule fix let's remove
# the cpu online rule in kdump initramfs.
arch=$(uname -m)
if [[ "$arch" = "ppc64le" ]] || [[ "$arch" = "ppc64" ]]; then
remove_cpu_online_rule
fi
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"
inst "$moddir/kdump-error-handler.sh" "/usr/bin/kdump-error-handler.sh"
inst "$moddir/kdump-error-handler.service" "$systemdsystemunitdir/kdump-error-handler.service"
# Replace existing emergency service and emergency target
cp "$moddir/kdump-emergency.service" "$initdir/$systemdsystemunitdir/emergency.service"
cp "$moddir/kdump-emergency.target" "$initdir/$systemdsystemunitdir/emergency.target"
# Also redirect dracut-emergency to kdump error handler
ln_r "$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
if ! is_fadump_capable; then
# Forward logs to console directly, this avoids unneccessary memory
# consumption and make console output more useful.
# Only do so for non fadump image.
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
# Save more memory by dropping switch root capability
dracut_no_switch_root
fi
}

28
SOURCES/dracut-monitor_dd_progress Normal file
View File

@ -0,0 +1,28 @@
#!/bin/sh
SRC_FILE_MB=$1
while true
do
DD_PID=`pidof dd`
if [ -n "$DD_PID" ]; then
break
fi
done
while true
do
sleep 5
if [ ! -d /proc/$DD_PID ]; then
break
fi
kill -s USR1 $DD_PID
CURRENT_SIZE=`tail -n 1 /tmp/dd_progress_file | sed "s/[^0-9].*//g"`
[ -n "$CURRENT_SIZE" ] && {
CURRENT_MB=$(($CURRENT_SIZE / 1048576))
echo -e "Copied $CURRENT_MB MB / $SRC_FILE_MB MB\r"
}
done
rm -f /tmp/dd_progress_file

95
SOURCES/early-kdump-howto.txt Normal file
View File

@ -0,0 +1,95 @@
Early Kdump HOWTO
Introduction
------------
Early kdump is a mechanism to make kdump operational earlier than normal kdump
service. The kdump service starts early enough for general crash cases, but
there are some cases where it has no chance to make kdump operational in boot
sequence, such as detecting devices and starting early services. If you hit
such a case, early kdump may allow you to get more information of it.
Early kdump is implemented as a dracut module. It adds a kernel (vmlinuz) and
initramfs for kdump to your system's initramfs in order to load them as early
as possible. After that, if you provide "rd.earlykdump" in kernel command line,
then in the initramfs, early kdump will load those files like the normal kdump
service. This is disabled by default.
For the normal kdump service, it can check whether the early kdump has loaded
the crash kernel and initramfs. It has no conflict with the early kdump.
How to configure early kdump
----------------------------
We assume if you're reading this document, you should already have kexec-tools
installed.
You can rebuild the initramfs with earlykdump support with below steps:
1. start kdump service to make sure kdump initramfs is created.
# systemctl start kdump
NOTE: If a crash occurs during boot process, early kdump captures a vmcore
and reboot the system by default, so the system might go into crash loop.
You can avoid such a crash loop by adding the following settings, which
power off the system after dump capturing, to kdump.conf in advance:
final_action poweroff
failure_action poweroff
For the failure_action, you can choose anything other than "reboot".
2. rebuild system initramfs with earlykdump support.
# dracut --force --add earlykdump
NOTE: Recommend to backup the original system initramfs before performing
this step to put it back if something happens during boot-up.
3. add rd.earlykdump in grub kernel command line.
After making said changes, reboot your system to take effect. Of course, if you
want to disable early kdump, you can simply remove "rd.earlykdump" from kernel
boot parameters in grub, and reboot system like above.
Once the boot is completed, you can check the status of the early kdump support
on the command prompt:
# journalctl -b | grep early-kdump
Then, you will see some useful logs, for example:
- if early kdump is successful.
Mar 09 09:57:56 localhost dracut-cmdline[190]: early-kdump is enabled.
Mar 09 09:57:56 localhost dracut-cmdline[190]: kexec: loaded early-kdump kernel
- if early kdump is disabled.
Mar 09 10:02:47 localhost dracut-cmdline[189]: early-kdump is disabled.
Notes
-----
- The size of early kdump initramfs will be large because it includes vmlinuz
and kdump initramfs.
- Early kdump inherits the settings of normal kdump, so any changes that
caused normal kdump rebuilding also require rebuilding the system initramfs
to make sure that the changes take effect for early kdump. Therefore, after
the rebuilding of kdump initramfs is completed, provide a prompt message to
tell the fact.
- If you install an updated kernel and reboot the system with it, the early
kdump will be disabled by default. To enable it with the new kernel, you
need to take the above steps again.
Limitation
----------
- At present, early kdump doesn't support fadump.
- Early kdump loads a crash kernel and initramfs at the beginning of the
process in system's initramfs, so a crash at earlier than that (e.g. in
kernel initialization) cannot be captured even with the early kdump.

338
SOURCES/fadump-howto.txt Normal file
View File

@ -0,0 +1,338 @@
Firmware assisted dump (fadump) HOWTO
Introduction
Firmware assisted dump is a new feature in the 3.4 mainline kernel supported
only on powerpc architecture. The goal of firmware-assisted dump is to enable
the dump of a crashed system, and to do so from a fully-reset system, and to
minimize the total elapsed time until the system is back in production use. A
complete documentation on implementation can be found at
Documentation/powerpc/firmware-assisted-dump.txt in upstream linux kernel tree
from 3.4 version and above.
Please note that the firmware-assisted dump feature is only available on Power6
and above systems with recent firmware versions.
Overview
Fadump
Fadump is a robust kernel crash dumping mechanism to get reliable kernel crash
dump with assistance from firmware. This approach does not use kexec, instead
firmware assists in booting the kdump kernel while preserving memory contents.
Unlike kdump, the system is fully reset, and loaded with a fresh copy of the
kernel. In particular, PCI and I/O devices are reinitialized and are in a
clean, consistent state. This second kernel, often called a capture kernel,
boots with very little memory and captures the dump image.
The first kernel registers the sections of memory with the Power firmware for
dump preservation during OS initialization. These registered sections of memory
are reserved by the first kernel during early boot. When a system crashes, the
Power firmware fully resets the system, preserves all the system memory
contents, save the low memory (boot memory of size larger of 5% of system
RAM or 256MB) of RAM to the previous registered region. It will also save
system registers, and hardware PTE's.
Fadump is supported only on ppc64 platform. The standard kernel and capture
kernel are one and the same on ppc64.
If you're reading this document, you should already have kexec-tools
installed. If not, you install it via the following command:
# yum install kexec-tools
Fadump Operational Flow:
Like kdump, fadump also exports the ELF formatted kernel crash dump through
/proc/vmcore. Hence existing kdump infrastructure can be used to capture fadump
vmcore. The idea is to keep the functionality transparent to end user. From
user perspective there is no change in the way kdump init script works.
However, unlike kdump, fadump does not pre-load kdump kernel and initrd into
reserved memory, instead it always uses default OS initrd during second boot
after crash. Hence, for fadump, we rebuild the new kdump initrd and replace it
with default initrd. Before replacing existing default initrd we take a backup
of original default initrd for user's reference. The dracut package has been
enhanced to rebuild the default initrd with vmcore capture steps. The initrd
image is rebuilt as per the configuration in /etc/kdump.conf file.
The control flow of fadump works as follows:
01. System panics.
02. At the crash, kernel informs power firmware that kernel has crashed.
03. Firmware takes the control and reboots the entire system preserving
only the memory (resets all other devices).
04. The reboot follows the normal booting process (non-kexec).
05. The boot loader loads the default kernel and initrd from /boot
06. The default initrd loads and runs /init
07. dracut-kdump.sh script present in fadump aware default initrd checks if
'/proc/device-tree/rtas/ibm,kernel-dump' file exists before executing
steps to capture vmcore.
(This check will help to bypass the vmcore capture steps during normal boot
process.)
09. Captures dump according to /etc/kdump.conf
10. Is dump capture successful (yes goto 12, no goto 11)
11. Perform the failure action specified in /etc/kdump.conf
(The default failure action is reboot, if unspecified)
12. Perform the final action specified in /etc/kdump.conf
(The default final action is reboot, if unspecified)
How to configure fadump:
Again, we assume if you're reading this document, you should already have
kexec-tools installed. If not, you install it via the following command:
# yum install kexec-tools
Make the kernel to be configured with FADump as the default boot entry, if
it isn't already:
# grubby --set-default=/boot/vmlinuz-<kver>
Boot into the kernel to be configured for FADump. To be able to do much of
anything interesting in the way of debug analysis, you'll also need to install
the kernel-debuginfo package, of the same arch as your running kernel, and the
crash utility:
# yum --enablerepo=\*debuginfo install kernel-debuginfo.$(uname -m) crash
Next up, we need to modify some boot parameters to enable firmware assisted
dump. With the help of grubby, it's very easy to append "fadump=on" to the end
of your kernel boot parameters. To reserve the appropriate amount of memory
for boot memory preservation, pass 'crashkernel=X' kernel cmdline parameter.
For the recommended value of X, see 'FADump Memory Requirements' section.
# grubby --args="fadump=on crashkernel=6G" --update-kernel=/boot/vmlinuz-`uname -r`
The term 'boot memory' means size of the low memory chunk that is required for
a kernel to boot successfully when booted with restricted memory. By default,
the boot memory size will be the larger of 5% of system RAM or 256MB.
Alternatively, user can also specify boot memory size through boot parameter
'fadump_reserve_mem=' which will override the default calculated size. Use this
option if default boot memory size is not sufficient for second kernel to boot
successfully.
After making said changes, reboot your system, so that the specified memory is
reserved and left untouched by the normal system. Take note that the output of
'free -m' will show X MB less memory than without this parameter, which is
expected. If you see OOM (Out Of Memory) error messages while loading capture
kernel, then you should bump up the memory reservation size.
Now that you've got that reserved memory region set up, you want to turn on
the kdump init script:
# systemctl enable kdump.service
Then, start up kdump as well:
# systemctl start kdump.service
This should turn on the firmware assisted functionality in kernel by
echo'ing 1 to /sys/kernel/fadump_registered, leaving the system ready
to capture a vmcore upon crashing. For journaling filesystems like XFS an
additional step is required to ensure bootloader does not pick the
older initrd (without vmcore capture scripts):
* If /boot is a separate partition, run the below commands as the root user,
or as a user with CAP_SYS_ADMIN rights:
# fsfreeze -f
# fsfreeze -u
* If /boot is not a separate partition, reboot the system.
After reboot check if the kdump service is up and running with:
# systemctl status kdump.service
To test out whether FADump is configured properly, you can force-crash your
system by echo'ing a 'c' into /proc/sysrq-trigger:
# echo c > /proc/sysrq-trigger
You should see some panic output, followed by the system reset and booting into
fresh copy of kernel. When default initrd loads and runs /init, vmcore should
be copied out to disk (by default, in /var/crash/<YYYY.MM.DD-HH:MM:SS>/vmcore),
then the system rebooted back into your normal kernel.
Once back to your normal kernel, you can use the previously installed crash
kernel in conjunction with the previously installed kernel-debuginfo to
perform postmortem analysis:
# crash /usr/lib/debug/lib/modules/2.6.17-1.2621.el5/vmlinux
/var/crash/2006-08-23-15:34/vmcore
crash> bt
and so on...
Saving vmcore-dmesg.txt
-----------------------
Kernel log bufferes are one of the most important information available
in vmcore. Now before saving vmcore, kernel log bufferes are extracted
from /proc/vmcore and saved into a file vmcore-dmesg.txt. After
vmcore-dmesg.txt, vmcore is saved. Destination disk and directory for
vmcore-dmesg.txt is same as vmcore. Note that kernel log buffers will
not be available if dump target is raw device.
FADump Memory Requirements:
System Memory Recommended memory
--------------------- ----------------------
4 GB - 16 GB : 768 MB
16 GB - 64 GB : 1024 MB
64 GB - 128 GB : 2 GB
128 GB - 1 TB : 4 GB
1 TB - 2 TB : 6 GB
2 TB - 4 TB : 12 GB
4 TB - 8 TB : 20 GB
8 TB - 16 TB : 36 GB
16 TB - 32 TB : 64 GB
32 TB - 64 TB : 128 GB
64 TB & above : 180 GB
Things to remember:
1) The memory required to boot capture Kernel is a moving target that depends
on many factors like hardware attached to the system, kernel and modules in
use, packages installed and services enabled, there is no one-size-fits-all.
But the above recommendations are based on system memory. So, the above
recommendations for FADump come with a few assumptions, based on available
system memory, about the resources the system could have. So, please take
the recommendations with a pinch of salt and remember to try capturing dump
a few times to confirm that the system is configured successfully with dump
capturing support.
2) Though the memory requirements for FADump seem high, this memory is not
completely set aside but made available for userspace applications to use,
through the CMA allocator.
3) As the same initrd is used for booting production kernel as well as capture
kernel and with dump being captured in a restricted memory environment, few
optimizations (like not inclding network dracut module, disabling multipath
and such) are applied while building the initrd. In case, the production
environment needs these optimizations to be avoided, dracut_args option in
/etc/kdump.conf file could be leveraged. For example, if a user wishes for
network module to be included in the initrd, adding the below entry in
/etc/kdump.conf file and restarting kdump service would take care of it.
dracut_args --add "network"
4) If FADump is configured to capture vmcore to a remote dump target using SSH
or NFS protocol, the network interface is renamed to kdump-<interface-name>
if <interface-name> is generic, for example, *eth#, or net#. This problem
occurs because the vmcore capture scripts in the initial RAM disk (initrd)
add the kdump- prefix to the network interface name to secure persistent
naming. As the same initrd is used for production kernel boot, the interface
name is changed for the production kernel too.
Dump Triggering methods:
This section talks about the various ways, other than a Kernel Panic, in which
fadump can be triggered. The following methods assume that fadump is configured
on your system, with the scripts enabled as described in the section above.
1) AltSysRq C
FAdump can be triggered with the combination of the 'Alt','SysRq' and 'C'
keyboard keys. Please refer to the following link for more details:
https://fedoraproject.org/wiki/QA/Sysrq
In addition, on PowerPC boxes, fadump can also be triggered via Hardware
Management Console(HMC) using 'Ctrl', 'O' and 'C' keyboard keys.
2) Kernel OOPs
If we want to generate a dump everytime the Kernel OOPses, we can achieve this
by setting the 'Panic On OOPs' option as follows:
# echo 1 > /proc/sys/kernel/panic_on_oops
3) PowerPC specific methods:
On IBM PowerPC machines, issuing a soft reset invokes the XMON debugger(if
XMON is configured). To configure XMON one needs to compile the kernel with
the CONFIG_XMON and CONFIG_XMON_DEFAULT options, or by compiling with
CONFIG_XMON and booting the kernel with xmon=on option.
Following are the ways to remotely issue a soft reset on PowerPC boxes, which
would drop you to XMON. Pressing a 'X' (capital alphabet X) followed by an
'Enter' here will trigger the dump.
3.1) HMC
Hardware Management Console(HMC) available on Power4 and Power5 machines allow
partitions to be reset remotely. This is specially useful in hang situations
where the system is not accepting any keyboard inputs.
Once you have HMC configured, the following steps will enable you to trigger
fadump via a soft reset:
On Power4
Using GUI
* In the right pane, right click on the partition you wish to dump.
* Select "Operating System->Reset".
* Select "Soft Reset".
* Select "Yes".
Using HMC Commandline
# reset_partition -m <machine> -p <partition> -t soft
On Power5
Using GUI
* In the right pane, right click on the partition you wish to dump.
* Select "Restart Partition".
* Select "Dump".
* Select "OK".
Using HMC Commandline
# chsysstate -m <managed system name> -n <lpar name> -o dumprestart -r lpar
3.2) Blade Management Console for Blade Center
To initiate a dump operation, go to Power/Restart option under "Blade Tasks" in
the Blade Management Console. Select the corresponding blade for which you want
to initate the dump and then click "Restart blade with NMI". This issues a
system reset and invokes xmon debugger.
Advanced Setups & Failure action:
Kdump and fadump exhibit similar behavior in terms of setup & failure action.
For fadump advanced setup related information see section "Advanced Setups" in
"kexec-kdump-howto.txt" document. Refer to "Failure action" section in "kexec-
kdump-howto.txt" document for fadump failure action related information.
Compression and filtering
Refer "Compression and filtering" section in "kexec-kdump-howto.txt" document.
Compression and filtering are same for kdump & fadump.
Notes on rootfs mount:
Dracut is designed to mount rootfs by default. If rootfs mounting fails it
will refuse to go on. So fadump leaves rootfs mounting to dracut currently.
We make the assumtion that proper root= cmdline is being passed to dracut
initramfs for the time being. If you need modify "KDUMP_COMMANDLINE=" in
/etc/sysconfig/kdump, you will need to make sure that appropriate root=
options are copied from /proc/cmdline. In general it is best to append
command line options using "KDUMP_COMMANDLINE_APPEND=" instead of replacing
the original command line completely.
How to disable FADump:
Remove "fadump=on" from kernel cmdline parameters:
# grubby --update-kernel=/boot/vmlinuz-`uname -r` --remove-args="fadump=on"
If KDump is to be used as the dump capturing mechanism, update the crashkernel
parameter (Else, remove "crashkernel=" parameter too, using grubby):
# grubby --update-kernel=/boot/vmlinuz-$kver --args="crashkernl=auto"
Reboot the system for the settings to take effect.

22
SOURCES/kdump-dep-generator.sh Normal file
View File

@ -0,0 +1,22 @@
#!/bin/sh
# More details about systemd generator:
# http://www.freedesktop.org/wiki/Software/systemd/Generators/
. /usr/lib/kdump/kdump-lib.sh
# If invokded with no arguments for testing purpose, output to /tmp to
# avoid overriding the existing.
dest_dir="/tmp"
if [ -n "$1" ]; then
dest_dir=$1
fi
systemd_dir=/usr/lib/systemd/system
kdump_wants=$dest_dir/kdump.service.wants
if is_ssh_dump_target; then
mkdir -p $kdump_wants
ln -sf $systemd_dir/network-online.target $kdump_wants/
fi

91
SOURCES/kdump-in-cluster-environment.txt Normal file
View File

@ -0,0 +1,91 @@
Kdump-in-cluster-environment HOWTO
Introduction
Kdump is a kexec based crash dumping mechansim for Linux. This docuement
illustrate how to configure kdump in cluster environment to allow the kdump
crash recovery service complete without being preempted by traditional power
fencing methods.
Overview
Kexec/Kdump
Details about Kexec/Kdump are available in Kexec-Kdump-howto file and will not
be described here.
fence_kdump
fence_kdump is an I/O fencing agent to be used with the kdump crash recovery
service. When the fence_kdump agent is invoked, it will listen for a message
from the failed node that acknowledges that the failed node is executing the
kdump crash kernel. Note that fence_kdump is not a replacement for traditional
fencing methods. The fence_kdump agent can only detect that a node has entered
the kdump crash recovery service. This allows the kdump crash recovery service
complete without being preempted by traditional power fencing methods.
fence_kdump_send
fence_kdump_send is a utility used to send messages that acknowledge that the
node itself has entered the kdump crash recovery service. The fence_kdump_send
utility is typically run in the kdump kernel after a cluster node has
encountered a kernel panic. Once the cluster node has entered the kdump crash
recovery service, fence_kdump_send will periodically send messages to all
cluster nodes. When the fence_kdump agent receives a valid message from the
failed nodes, fencing is complete.
How to configure Pacemaker cluster environment:
If we want to use kdump in Pacemaker cluster environment, fence-agents-kdump
should be installed in every nodes in the cluster. You can achieve this via
the following command:
# yum install -y fence-agents-kdump
Next is to add kdump_fence to the cluster. Assuming that the cluster consists
of three nodes, they are node1, node2 and node3, and use Pacemaker to perform
resource management and pcs as cli configuration tool.
With pcs it is easy to add a stonith resource to the cluster. For example, add
a stonith resource named mykdumpfence with fence type of fence_kdump via the
following commands:
# pcs stonith create mykdumpfence fence_kdump \
pcmk_host_check=static-list pcmk_host_list="node1 node2 node3"
# pcs stonith update mykdumpfence pcmk_monitor_action=metadata --force
# pcs stonith update mykdumpfence pcmk_status_action=metadata --force
# pcs stonith update mykdumpfence pcmk_reboot_action=off --force
Then enable stonith
# pcs property set stonith-enabled=true
How to configure kdump:
Actually there are two ways how to configure fence_kdump support:
1) Pacemaker based clusters
If you have successfully configured fence_kdump in Pacemaker, there is
no need to add some special configuration in kdump. So please refer to
Kexec-Kdump-howto file for more information.
2) Generic clusters
For other types of clusters there are two configuration options in
kdump.conf which enables fence_kdump support:
fence_kdump_nodes <node(s)>
Contains list of cluster node(s) separated by space to send
fence_kdump notification to (this option is mandatory to enable
fence_kdump)
fence_kdump_args <arg(s)>
Command line arguments for fence_kdump_send (it can contain
all valid arguments except hosts to send notification to)
These options will most probably be configured by your cluster software,
so please refer to your cluster documentation how to enable fence_kdump
support.
Please be aware that these two ways cannot be combined and 2) has precedence
over 1). It means that if fence_kdump is configured using fence_kdump_nodes
and fence_kdump_args options in kdump.conf, Pacemaker configuration is not
used even if it exists.

214
SOURCES/kdump-lib-initramfs.sh Executable file
View File

@ -0,0 +1,214 @@
# These variables and functions are useful in 2nd kernel
. /lib/kdump-lib.sh
KDUMP_PATH="/var/crash"
CORE_COLLECTOR=""
DEFAULT_CORE_COLLECTOR="makedumpfile -l --message-level 1 -d 31"
DMESG_COLLECTOR="/sbin/vmcore-dmesg"
FAILURE_ACTION="systemctl reboot -f"
DATEDIR=`date +%Y-%m-%d-%T`
HOST_IP='127.0.0.1'
DUMP_INSTRUCTION=""
SSH_KEY_LOCATION="/root/.ssh/kdump_id_rsa"
KDUMP_SCRIPT_DIR="/kdumpscripts"
DD_BLKSIZE=512
FINAL_ACTION="systemctl reboot -f"
KDUMP_CONF="/etc/kdump.conf"
KDUMP_PRE=""
KDUMP_POST=""
NEWROOT="/sysroot"
OPALCORE="/sys/firmware/opal/mpipl/core"
get_kdump_confs()
{
local config_opt config_val
while read config_opt config_val;
do
# remove inline comments after the end of a directive.
case "$config_opt" in
path)
KDUMP_PATH="$config_val"
;;
core_collector)
[ -n "$config_val" ] && CORE_COLLECTOR="$config_val"
;;
sshkey)
if [ -f "$config_val" ]; then
SSH_KEY_LOCATION=$config_val
fi
;;
kdump_pre)
KDUMP_PRE="$config_val"
;;
kdump_post)
KDUMP_POST="$config_val"
;;
fence_kdump_args)
FENCE_KDUMP_ARGS="$config_val"
;;
fence_kdump_nodes)
FENCE_KDUMP_NODES="$config_val"
;;
failure_action|default)
case $config_val in
shell)
FAILURE_ACTION="kdump_emergency_shell"
;;
reboot)
FAILURE_ACTION="systemctl reboot -f && exit"
;;
halt)
FAILURE_ACTION="halt && exit"
;;
poweroff)
FAILURE_ACTION="systemctl poweroff -f && exit"
;;
dump_to_rootfs)
FAILURE_ACTION="dump_to_rootfs"
;;
esac
;;
final_action)
case $config_val in
reboot)
FINAL_ACTION="systemctl reboot -f"
;;
halt)
FINAL_ACTION="halt"
;;
poweroff)
FINAL_ACTION="systemctl poweroff -f"
;;
esac
;;
esac
done <<< "$(read_strip_comments $KDUMP_CONF)"
if [ -z "$CORE_COLLECTOR" ]; then
CORE_COLLECTOR="$DEFAULT_CORE_COLLECTOR"
if is_ssh_dump_target || is_raw_dump_target; then
CORE_COLLECTOR="$CORE_COLLECTOR -F"
fi
fi
}
# dump_fs <mount point>
dump_fs()
{
local _mp=$1
local _dev=$(get_mount_info SOURCE target $_mp -f)
local _op=$(get_mount_info OPTIONS target $_mp -f)
# If dump path have a corresponding device entry but not mounted, mount it.
if [ -n "$_dev" ] || [ "$_dev" == "rootfs" ]; then
if ! is_mounted "$_mp"; then
echo "kdump: dump target $_dev is not mounted, trying to mount..."
mkdir -p $_mp
mount -o $_op $_dev $_mp
if [ $? -ne 0 ]; then
echo "kdump: mounting failed (mount point: $_mp, option: $_op)"
return 1
fi
fi
else
echo "kdump: failed to dump to \"$_mp\", it's not a mount point!"
return 1
fi
# Remove -F in makedumpfile case. We don't want a flat format dump here.
[[ $CORE_COLLECTOR = *makedumpfile* ]] && CORE_COLLECTOR=`echo $CORE_COLLECTOR | sed -e "s/-F//g"`
echo "kdump: saving to $_mp/$KDUMP_PATH/$HOST_IP-$DATEDIR/"
mount -o remount,rw $_mp || return 1
mkdir -p $_mp/$KDUMP_PATH/$HOST_IP-$DATEDIR || return 1
save_vmcore_dmesg_fs ${DMESG_COLLECTOR} "$_mp/$KDUMP_PATH/$HOST_IP-$DATEDIR/"
save_opalcore_fs "$_mp/$KDUMP_PATH/$HOST_IP-$DATEDIR/"
echo "kdump: saving vmcore"
$CORE_COLLECTOR /proc/vmcore $_mp/$KDUMP_PATH/$HOST_IP-$DATEDIR/vmcore-incomplete || return 1
mv $_mp/$KDUMP_PATH/$HOST_IP-$DATEDIR/vmcore-incomplete $_mp/$KDUMP_PATH/$HOST_IP-$DATEDIR/vmcore
sync
echo "kdump: saving vmcore complete"
# improper kernel cmdline can cause the failure of echo, we can ignore this kind of failure
return 0
}
save_vmcore_dmesg_fs() {
local _dmesg_collector=$1
local _path=$2
echo "kdump: saving vmcore-dmesg.txt"
$_dmesg_collector /proc/vmcore > ${_path}/vmcore-dmesg-incomplete.txt
_exitcode=$?
if [ $_exitcode -eq 0 ]; then
mv ${_path}/vmcore-dmesg-incomplete.txt ${_path}/vmcore-dmesg.txt
# Make sure file is on disk. There have been instances where later
# saving vmcore failed and system rebooted without sync and there
# was no vmcore-dmesg.txt available.
sync
echo "kdump: saving vmcore-dmesg.txt complete"
else
echo "kdump: saving vmcore-dmesg.txt failed"
fi
}
save_opalcore_fs() {
local _path=$1
if [ ! -f $OPALCORE ]; then
# Check if we are on an old kernel that uses a different path
if [ -f /sys/firmware/opal/core ]; then
OPALCORE="/sys/firmware/opal/core"
else
return 0
fi
fi
echo "kdump: saving opalcore"
cp $OPALCORE ${_path}/opalcore
if [ $? -ne 0 ]; then
echo "kdump: saving opalcore failed"
return 1
fi
sync
echo "kdump: saving opalcore complete"
return 0
}
dump_to_rootfs()
{
echo "Kdump: trying to bring up rootfs device"
systemctl start dracut-initqueue
echo "Kdump: waiting for rootfs mount, will timeout after 90 seconds"
systemctl start sysroot.mount
dump_fs $NEWROOT
}
kdump_emergency_shell()
{
echo "PS1=\"kdump:\\\${PWD}# \"" >/etc/profile
/bin/dracut-emergency
rm -f /etc/profile
}
do_failure_action()
{
echo "Kdump: Executing failure action $FAILURE_ACTION"
eval $FAILURE_ACTION
}
do_final_action()
{
eval $FINAL_ACTION
}

745
SOURCES/kdump-lib.sh Executable file
View File

@ -0,0 +1,745 @@
#!/bin/sh
#
# Kdump common variables and functions
#
DEFAULT_PATH="/var/crash/"
FENCE_KDUMP_CONFIG_FILE="/etc/sysconfig/fence_kdump"
FENCE_KDUMP_SEND="/usr/libexec/fence_kdump_send"
FADUMP_ENABLED_SYS_NODE="/sys/kernel/fadump_enabled"
is_fadump_capable()
{
# Check if firmware-assisted dump is enabled
# if no, fallback to kdump check
if [ -f $FADUMP_ENABLED_SYS_NODE ]; then
rc=`cat $FADUMP_ENABLED_SYS_NODE`
[ $rc -eq 1 ] && return 0
fi
return 1
}
perror_exit() {
echo $@ >&2
exit 1
}
perror() {
echo $@ >&2
}
is_ssh_dump_target()
{
grep -q "^ssh[[:blank:]].*@" /etc/kdump.conf
}
is_nfs_dump_target()
{
grep -q "^nfs" /etc/kdump.conf || \
[[ $(get_dracut_args_fstype "$(grep "^dracut_args .*\-\-mount" /etc/kdump.conf)") = nfs* ]]
}
is_raw_dump_target()
{
grep -q "^raw" /etc/kdump.conf
}
is_fs_type_nfs()
{
local _fstype=$1
[ $_fstype = "nfs" ] || [ $_fstype = "nfs4" ] && return 0
return 1
}
is_fs_dump_target()
{
egrep -q "^ext[234]|^xfs|^btrfs|^minix" /etc/kdump.conf
}
strip_comments()
{
echo $@ | sed -e 's/\(.*\)#.*/\1/'
}
# Read from kdump config file stripping all comments
read_strip_comments()
{
# strip heading spaces, and print any content starting with
# neither space or #, and strip everything after #
sed -n -e "s/^\s*\([^# \t][^#]\+\).*/\1/gp" $1
}
# Check if fence kdump is configured in Pacemaker cluster
is_pcs_fence_kdump()
{
# no pcs or fence_kdump_send executables installed?
type -P pcs > /dev/null || return 1
[ -x $FENCE_KDUMP_SEND ] || return 1
# fence kdump not configured?
(pcs cluster cib | grep 'type="fence_kdump"') &> /dev/null || return 1
}
# Check if fence_kdump is configured using kdump options
is_generic_fence_kdump()
{
[ -x $FENCE_KDUMP_SEND ] || return 1
grep -q "^fence_kdump_nodes" /etc/kdump.conf
}
to_dev_name() {
local dev="${1//\"/}"
case "$dev" in
UUID=*)
dev=`blkid -U "${dev#UUID=}"`
;;
LABEL=*)
dev=`blkid -L "${dev#LABEL=}"`
;;
esac
echo $dev
}
is_user_configured_dump_target()
{
return $(is_mount_in_dracut_args || is_ssh_dump_target || is_nfs_dump_target || \
is_raw_dump_target || is_fs_dump_target)
}
get_user_configured_dump_disk()
{
local _target
_target=$(egrep "^ext[234]|^xfs|^btrfs|^minix|^raw" /etc/kdump.conf 2>/dev/null |awk '{print $2}')
[ -n "$_target" ] && echo $_target && return
_target=$(get_dracut_args_target "$(grep "^dracut_args .*\-\-mount" /etc/kdump.conf)")
[ -b "$_target" ] && echo $_target
}
get_root_fs_device()
{
findmnt -k -f -n -o SOURCE /
}
get_save_path()
{
local _save_path=$(awk '$1 == "path" {print $2}' /etc/kdump.conf)
[ -z "$_save_path" ] && _save_path=$DEFAULT_PATH
# strip the duplicated "/"
echo $_save_path | tr -s /
}
get_block_dump_target()
{
local _target _path
if is_ssh_dump_target || is_nfs_dump_target; then
return
fi
_target=$(get_user_configured_dump_disk)
[ -n "$_target" ] && echo $(to_dev_name $_target) && return
# Get block device name from local save path
_path=$(get_save_path)
_target=$(get_target_from_path $_path)
[ -b "$_target" ] && echo $(to_dev_name $_target)
}
is_dump_to_rootfs()
{
grep -E "^(failure_action|default)[[:space:]]dump_to_rootfs" /etc/kdump.conf >/dev/null
}
get_failure_action_target()
{
local _target
if is_dump_to_rootfs; then
# Get rootfs device name
_target=$(get_root_fs_device)
[ -b "$_target" ] && echo $(to_dev_name $_target) && return
# Then, must be nfs root
echo "nfs"
fi
}
# Get kdump targets(including root in case of dump_to_rootfs).
get_kdump_targets()
{
local _target _root
local kdump_targets
_target=$(get_block_dump_target)
if [ -n "$_target" ]; then
kdump_targets=$_target
elif is_ssh_dump_target; then
kdump_targets="ssh"
else
kdump_targets="nfs"
fi
# Add the root device if dump_to_rootfs is specified.
_root=$(get_failure_action_target)
if [ -n "$_root" -a "$kdump_targets" != "$_root" ]; then
kdump_targets="$kdump_targets $_root"
fi
echo "$kdump_targets"
}
# Return the bind mount source path, return the path itself if it's not bind mounted
# Eg. if /path/to/src is bind mounted to /mnt/bind, then:
# /mnt/bind -> /path/to/src, /mnt/bind/dump -> /path/to/src/dump
#
# findmnt uses the option "-v, --nofsroot" to exclusive the [/dir]
# in the SOURCE column for bind-mounts, then if $_mntpoint equals to
# $_mntpoint_nofsroot, the mountpoint is not bind mounted directory.
#
# Below is just an example for mount info
# /dev/mapper/atomicos-root[/ostree/deploy/rhel-atomic-host/var], if the
# directory is bind mounted. The former part represents the device path, rest
# part is the bind mounted directory which quotes by bracket "[]".
get_bind_mount_source()
{
local _path=$1
# In case it's a sub path in a mount point, get the mount point first
local _mnt_top=$(df $_path | tail -1 | awk '{print $NF}')
local _mntpoint=$(findmnt $_mnt_top | tail -n 1 | awk '{print $2}')
local _mntpoint_nofsroot=$(findmnt -v $_mnt_top | tail -n 1 | awk '{print $2}')
if [[ "$_mntpoint" = $_mntpoint_nofsroot ]]; then
echo $_path && return
fi
_mntpoint=${_mntpoint#*$_mntpoint_nofsroot}
_mntpoint=${_mntpoint#[}
_mntpoint=${_mntpoint%]}
_path=${_path#$_mnt_top}
echo $_mntpoint$_path
}
# Return the current underlaying device of a path, ignore bind mounts
get_target_from_path()
{
local _target
_target=$(df $1 2>/dev/null | tail -1 | awk '{print $1}')
[[ "$_target" == "/dev/root" ]] && [[ ! -e /dev/root ]] && _target=$(get_root_fs_device)
echo $_target
}
is_mounted()
{
findmnt -k -n $1 &>/dev/null
}
get_mount_info()
{
local _info_type=$1 _src_type=$2 _src=$3; shift 3
local _info=$(findmnt -k -n -r -o $_info_type --$_src_type $_src $@)
[ -z "$_info" ] && [ -e "/etc/fstab" ] && _info=$(findmnt -s -n -r -o $_info_type --$_src_type $_src $@)
echo $_info
}
get_fs_type_from_target()
{
get_mount_info FSTYPE source $1 -f
}
get_mntopt_from_target()
{
get_mount_info OPTIONS source $1 -f
}
# Find the general mount point of a dump target, not the bind mount point
get_mntpoint_from_target()
{
# Expcilitly specify --source to findmnt could ensure non-bind mount is returned
get_mount_info TARGET source $1 -f
}
# Get the path where the target will be mounted in kdump kernel
# $1: kdump target device
get_kdump_mntpoint_from_target()
{
local _mntpoint=$(get_mntpoint_from_target $1)
# mount under /sysroot if dump to root disk or mount under
# mount under /kdumproot if dump target is not mounted in first kernel
# mount under /kdumproot/$_mntpoint in other cases in 2nd kernel.
# systemd will be in charge to umount it.
if [ -z "$_mntpoint" ];then
_mntpoint="/kdumproot"
else
if [ "$_mntpoint" = "/" ];then
_mntpoint="/sysroot"
else
_mntpoint="/kdumproot/$_mntpoint"
fi
fi
# strip duplicated "/"
echo $_mntpoint | tr -s "/"
}
# get_option_value <option_name>
# retrieves value of option defined in kdump.conf
get_option_value() {
strip_comments `grep "^$1[[:space:]]\+" /etc/kdump.conf | tail -1 | cut -d\ -f2-`
}
kdump_get_persistent_dev() {
local dev="${1//\"/}"
case "$dev" in
UUID=*)
dev=`blkid -U "${dev#UUID=}"`
;;
LABEL=*)
dev=`blkid -L "${dev#LABEL=}"`
;;
esac
echo $(get_persistent_dev "$dev")
}
is_atomic()
{
grep -q "ostree" /proc/cmdline
}
# fixme, try the best to decide whether the ipv6 addr is allocated by slaac or dhcp6
is_ipv6_auto()
{
local _netdev=$1
local _auto=$(cat /proc/sys/net/ipv6/conf/$_netdev/autoconf)
if [ $_auto -eq 1 ]; then
return 0
else
return 1
fi
}
is_ipv6_address()
{
echo $1 | grep -q ":"
}
# get ip address or hostname from nfs/ssh config value
get_remote_host()
{
local _config_val=$1
# ipv6 address in kdump.conf is around with "[]",
# factor out the ipv6 address
_config_val=${_config_val#*@}
_config_val=${_config_val%:/*}
_config_val=${_config_val#[}
_config_val=${_config_val%]}
echo $_config_val
}
is_hostname()
{
local _hostname=`echo $1 | grep ":"`
if [ -n "$_hostname" ]; then
return 1
fi
echo $1 | grep -q "[a-zA-Z]"
}
# Copied from "/etc/sysconfig/network-scripts/network-functions"
get_hwaddr()
{
if [ -f "/sys/class/net/${1}/address" ]; then
awk '{ print toupper($0) }' < /sys/class/net/${1}/address
elif [ -d "/sys/class/net/${1}" ]; then
LC_ALL= LANG= ip -o link show ${1} 2>/dev/null | \
awk '{ print toupper(gensub(/.*link\/[^ ]* ([[:alnum:]:]*).*/,
"\\1", 1)); }'
fi
}
get_ifcfg_by_device()
{
grep -E -i -l "^[[:space:]]*DEVICE=\"*${1}\"*[[:space:]]*$" \
/etc/sysconfig/network-scripts/ifcfg-* 2>/dev/null | head -1
}
get_ifcfg_by_hwaddr()
{
grep -E -i -l "^[[:space:]]*HWADDR=\"*${1}\"*[[:space:]]*$" \
/etc/sysconfig/network-scripts/ifcfg-* 2>/dev/null | head -1
}
get_ifcfg_by_uuid()
{
grep -E -i -l "^[[:space:]]*UUID=\"*${1}\"*[[:space:]]*$" \
/etc/sysconfig/network-scripts/ifcfg-* 2>/dev/null | head -1
}
get_ifcfg_by_name()
{
grep -E -i -l "^[[:space:]]*NAME=\"*${1}\"*[[:space:]]*$" \
/etc/sysconfig/network-scripts/ifcfg-* 2>/dev/null | head -1
}
is_nm_running()
{
[ "$(LANG=C nmcli -t --fields running general status 2>/dev/null)" = "running" ]
}
is_nm_handling()
{
LANG=C nmcli -t --fields device,state dev status 2>/dev/null \
| grep -q "^\(${1}:connected\)\|\(${1}:connecting.*\)$"
}
# $1: netdev name
get_ifcfg_nmcli()
{
local nm_uuid nm_name
local ifcfg_file
# Get the active nmcli config name of $1
if is_nm_running && is_nm_handling "${1}" ; then
# The configuration "uuid" and "name" generated by nm is wrote to
# the ifcfg file as "UUID=<nm_uuid>" and "NAME=<nm_name>".
nm_uuid=$(LANG=C nmcli -t --fields uuid,device c show --active 2>/dev/null \
| grep "${1}" | head -1 | cut -d':' -f1)
nm_name=$(LANG=C nmcli -t --fields name,device c show --active 2>/dev/null \
| grep "${1}" | head -1 | cut -d':' -f1)
ifcfg_file=$(get_ifcfg_by_uuid "${nm_uuid}")
[ -z "${ifcfg_file}" ] && ifcfg_file=$(get_ifcfg_by_name "${nm_name}")
fi
echo -n "${ifcfg_file}"
}
# $1: netdev name
get_ifcfg_legacy()
{
local ifcfg_file
ifcfg_file="/etc/sysconfig/network-scripts/ifcfg-${1}"
[ -f "${ifcfg_file}" ] && echo -n "${ifcfg_file}" && return
ifcfg_file=$(get_ifcfg_by_name "${1}")
[ -f "${ifcfg_file}" ] && echo -n "${ifcfg_file}" && return
local hwaddr=$(get_hwaddr "${1}")
if [ -n "$hwaddr" ]; then
ifcfg_file=$(get_ifcfg_by_hwaddr "${hwaddr}")
[ -f "${ifcfg_file}" ] && echo -n "${ifcfg_file}" && return
fi
ifcfg_file=$(get_ifcfg_by_device "${1}")
echo -n "${ifcfg_file}"
}
# $1: netdev name
# Return the ifcfg file whole name(including the path) of $1 if any.
get_ifcfg_filename() {
local ifcfg_file
ifcfg_file=$(get_ifcfg_nmcli "${1}")
if [ -z "${ifcfg_file}" ]; then
ifcfg_file=$(get_ifcfg_legacy "${1}")
fi
echo -n "${ifcfg_file}"
}
# returns 0 when omission of watchdog module is desired in dracut_args
# returns 1 otherwise
is_wdt_mod_omitted() {
local dracut_args
local ret=1
dracut_args=$(grep "^dracut_args" /etc/kdump.conf)
[[ -z $dracut_args ]] && return $ret
eval set -- $dracut_args
while :; do
[[ -z $1 ]] && break
case $1 in
-o|--omit)
echo $2 | grep -qw "watchdog"
[[ $? == 0 ]] && ret=0
break
esac
shift
done
return $ret
}
# If "dracut_args" contains "--mount" information, use it
# directly without any check(users are expected to ensure
# its correctness).
is_mount_in_dracut_args()
{
grep -q "^dracut_args .*\-\-mount" /etc/kdump.conf
}
# If $1 contains dracut_args "--mount", return <filesystem type>
get_dracut_args_fstype()
{
echo $1 | grep "\-\-mount" | sed "s/.*--mount .\(.*\)/\1/" | cut -d' ' -f3
}
# If $1 contains dracut_args "--mount", return <device>
get_dracut_args_target()
{
echo $1 | grep "\-\-mount" | sed "s/.*--mount .\(.*\)/\1/" | cut -d' ' -f1
}
check_crash_mem_reserved()
{
local mem_reserved
mem_reserved=$(cat /sys/kernel/kexec_crash_size)
if [ $mem_reserved -eq 0 ]; then
echo "No memory reserved for crash kernel"
return 1
fi
return 0
}
check_kdump_feasibility()
{
if [ ! -e /sys/kernel/kexec_crash_loaded ]; then
echo "Kdump is not supported on this kernel"
return 1
fi
check_crash_mem_reserved
return $?
}
check_current_kdump_status()
{
if [ ! -f /sys/kernel/kexec_crash_loaded ];then
echo "Perhaps CONFIG_CRASH_DUMP is not enabled in kernel"
return 1
fi
rc=`cat /sys/kernel/kexec_crash_loaded`
if [ $rc == 1 ]; then
return 0
else
return 1
fi
}
# remove_cmdline_param <kernel cmdline> <param1> [<param2>] ... [<paramN>]
# Remove a list of kernel parameters from a given kernel cmdline and print the result.
# For each "arg" in the removing params list, "arg" and "arg=xxx" will be removed if exists.
remove_cmdline_param()
{
local cmdline=$1
shift
for arg in $@; do
cmdline=`echo $cmdline | \
sed -e "s/\b$arg=[^ ]*//g" \
-e "s/^$arg\b//g" \
-e "s/[[:space:]]$arg\b//g" \
-e "s/\s\+/ /g"`
done
echo $cmdline
}
#
# This function returns the "apicid" of the boot
# cpu (cpu 0) if present.
#
get_bootcpu_apicid()
{
awk ' \
BEGIN { CPU = "-1"; } \
$1=="processor" && $2==":" { CPU = $NF; } \
CPU=="0" && /^apicid/ { print $NF; } \
' \
/proc/cpuinfo
}
#
# append_cmdline <kernel cmdline> <parameter name> <parameter value>
# This function appends argument "$2=$3" to string ($1) if not already present.
#
append_cmdline()
{
local cmdline=$1
local newstr=${cmdline/$2/""}
# unchanged str implies argument wasn't there
if [ "$cmdline" == "$newstr" ]; then
cmdline="${cmdline} ${2}=${3}"
fi
echo $cmdline
}
# This function check iomem and determines if we have more than
# 4GB of ram available. Returns 1 if we do, 0 if we dont
need_64bit_headers()
{
return `tail -n 1 /proc/iomem | awk '{ split ($1, r, "-"); \
print (strtonum("0x" r[2]) > strtonum("0xffffffff")); }'`
}
# Check if secure boot is being enforced.
#
# Per Peter Jones, we need check efivar SecureBoot-$(the UUID) and
# SetupMode-$(the UUID), they are both 5 bytes binary data. The first four
# bytes are the attributes associated with the variable and can safely be
# ignored, the last bytes are one-byte true-or-false variables. If SecureBoot
# is 1 and SetupMode is 0, then secure boot is being enforced.
#
# Assume efivars is mounted at /sys/firmware/efi/efivars.
is_secure_boot_enforced()
{
local secure_boot_file setup_mode_file
local secure_boot_byte setup_mode_byte
# On powerpc, os-secureboot-enforcing DT property indicates whether secureboot
# is enforced. Return success, if it is found.
if [ -f /proc/device-tree/ibm,secureboot/os-secureboot-enforcing ]; then
return 0
fi
# Detect secure boot on x86 and arm64
secure_boot_file=$(find /sys/firmware/efi/efivars -name SecureBoot-* 2>/dev/null)
setup_mode_file=$(find /sys/firmware/efi/efivars -name SetupMode-* 2>/dev/null)
if [ -f "$secure_boot_file" ] && [ -f "$setup_mode_file" ]; then
secure_boot_byte=$(hexdump -v -e '/1 "%d\ "' $secure_boot_file|cut -d' ' -f 5)
setup_mode_byte=$(hexdump -v -e '/1 "%d\ "' $setup_mode_file|cut -d' ' -f 5)
if [ "$secure_boot_byte" = "1" ] && [ "$setup_mode_byte" = "0" ]; then
return 0
fi
fi
# Detect secure boot on s390x
if [[ -e "/sys/firmware/ipl/secure" && "$(cat /sys/firmware/ipl/secure)" == "1" ]]; then
return 0
fi
return 1
}
#
# prepare_kexec_args <kexec args>
# This function prepares kexec argument.
#
prepare_kexec_args()
{
local kexec_args=$1
local found_elf_args
ARCH=`uname -m`
if [ "$ARCH" == "i686" -o "$ARCH" == "i386" ]
then
need_64bit_headers
if [ $? == 1 ]
then
found_elf_args=`echo $kexec_args | grep elf32-core-headers`
if [ -n "$found_elf_args" ]
then
echo -n "Warning: elf32-core-headers overrides correct elf64 setting"
echo
else
kexec_args="$kexec_args --elf64-core-headers"
fi
else
found_elf_args=`echo $kexec_args | grep elf64-core-headers`
if [ -z "$found_elf_args" ]
then
kexec_args="$kexec_args --elf32-core-headers"
fi
fi
fi
echo $kexec_args
}
check_boot_dir()
{
local kdump_bootdir=$1
#If user specify a boot dir for kdump kernel, let's use it. Otherwise
#check whether it's a atomic host. If yes parse the subdirectory under
#/boot; If not just find it under /boot.
if [ -n "$kdump_bootdir" ]; then
echo "$kdump_bootdir"
return
fi
if ! is_atomic || [ "$(uname -m)" = "s390x" ]; then
kdump_bootdir="/boot"
else
eval $(cat /proc/cmdline| grep "BOOT_IMAGE" | cut -d' ' -f1)
kdump_bootdir="/boot"$(dirname $BOOT_IMAGE)
fi
echo $kdump_bootdir
}
#
# prepare_cmdline <commandline> <commandline remove> <commandline append>
# This function performs a series of edits on the command line.
# Store the final result in global $KDUMP_COMMANDLINE.
prepare_cmdline()
{
local cmdline id
if [ -z "$1" ]; then
cmdline=$(cat /proc/cmdline)
else
cmdline="$1"
fi
# These params should always be removed
cmdline=$(remove_cmdline_param "$cmdline" crashkernel panic_on_warn)
# These params can be removed configurably
cmdline=$(remove_cmdline_param "$cmdline" "$2")
# Always remove "root=X", as we now explicitly generate all kinds
# of dump target mount information including root fs.
#
# We do this before KDUMP_COMMANDLINE_APPEND, if one really cares
# about it(e.g. for debug purpose), then can pass "root=X" using
# KDUMP_COMMANDLINE_APPEND.
cmdline=$(remove_cmdline_param "$cmdline" root)
# With the help of "--hostonly-cmdline", we can avoid some interitage.
cmdline=$(remove_cmdline_param "$cmdline" rd.lvm.lv rd.luks.uuid rd.dm.uuid rd.md.uuid fcoe)
# Remove netroot, rd.iscsi.initiator and iscsi_initiator since
# we get duplicate entries for the same in case iscsi code adds
# it as well.
cmdline=$(remove_cmdline_param "$cmdline" netroot rd.iscsi.initiator iscsi_initiator)
cmdline="${cmdline} $3"
id=$(get_bootcpu_apicid)
if [ ! -z ${id} ] ; then
cmdline=$(append_cmdline "${cmdline}" disable_cpu_apicid ${id})
fi
# Disable efifb if hyperv_fb is in use, hyperv_fb will relocate the framebuffer
# but kexec_file_load always use original screen_info and in second kernel efifb
# will try to access an invalid framebuffer address
if [ -d /sys/module/hyperv_fb ]; then
cmdline=$(append_cmdline "$cmdline" "video=efifb:off")
fi
echo ${cmdline}
}

42
SOURCES/kdump-udev-throttler Executable file
View File

@ -0,0 +1,42 @@
#!/bin/bash
# This util helps to reduce the workload of kdump service restarting
# on udev event. When hotplugging memory / CPU, multiple udev
# events may be triggered concurrently, and obviously, we don't want
# to restart kdump service for each event.
# This script will be called by udev, and make sure kdump service is
# restart after all events we are watching are settled.
# On each call, this script will update try to aquire the $throttle_lock
# The first instance acquired the file lock will keep waiting for events
# to settle and then reload kdump. Other instances will just exit
# In this way, we can make sure kdump service is restarted immediately
# and for exactly once after udev events are settled.
throttle_lock="/var/lock/kdump-udev-throttle"
exec 9>$throttle_lock
if [ $? -ne 0 ]; then
echo "Failed to create the lock file! Fallback to non-throttled kdump service restart"
/bin/kdumpctl reload
exit 1
fi
flock -n 9
if [ $? -ne 0 ]; then
echo "Throttling kdump restart for concurrent udev event"
exit 0
fi
# Wait for at least 1 second, at most 4 seconds for udev to settle
# Idealy we will have a less than 1 second lag between udev events settle
# and kdump reload
sleep 1 && udevadm settle --timeout 3
# Release the lock, /bin/kdumpctl will block and make the process
# holding two locks at the same time and we might miss some events
exec 9>&-
/bin/kdumpctl reload
exit 0

183
SOURCES/kdump.conf Normal file
View File

@ -0,0 +1,183 @@
# This file contains a series of commands to perform (in order) in the kdump
# kernel after a kernel crash in the crash kernel(1st kernel) has happened.
#
# Directives in this file are only applicable to the kdump initramfs, and have
# no effect once the root filesystem is mounted and the normal init scripts are
# processed.
#
# Currently, only one dump target and path can be specified. If the dumping to
# the configured target fails, the failure action which can be configured via
# the "failure_action" directive will be performed.
#
# Supported options:
#
# raw <partition>
# - Will dd /proc/vmcore into <partition>.
# Use persistent device names for partition devices,
# such as /dev/vg/<devname>.
#
# nfs <nfs mount>
# - Will mount nfs to <mnt>, and copy /proc/vmcore to
# <mnt>/<path>/%HOST-%DATE/, supports DNS.
#
# ssh <user@server>
# - Will scp /proc/vmcore to <user@server>:<path>/%HOST-%DATE/,
# supports DNS.
# NOTE: make sure the user has write permissions on the server.
#
# sshkey <path>
# - Will use the sshkey to do ssh dump.
# Specify the path of the ssh key to use when dumping
# via ssh. The default value is /root/.ssh/kdump_id_rsa.
#
# <fs type> <partition>
# - Will mount -t <fs type> <partition> <mnt>, and copy
# /proc/vmcore to <mnt>/<path>/%DATE/.
# NOTE: <partition> can be a device node, label or uuid.
# It's recommended to use persistent device names
# such as /dev/vg/<devname>.
# Otherwise it's suggested to use label or uuid.
#
# path <path>
# - "path" represents the file system path in which vmcore
# will be saved. If a dump target is specified in
# kdump.conf, then "path" is relative to the specified
# dump target.
#
# Interpretation of "path" changes a bit if the user didn't
# specify any dump target explicitly in kdump.conf. In this
# case, "path" represents the absolute path from root. The
# dump target and adjusted path are arrived at automatically
# depending on what's mounted in the current system.
#
# Ignored for raw device dumps. If unset, will use the default
# "/var/crash".
#
# core_collector <command> <options>
# - This allows you to specify the command to copy
# the vmcore. The default is makedumpfile, which on
# some architectures can drastically reduce vmcore size.
# See /sbin/makedumpfile --help for a list of options.
# Note that the -i and -g options are not needed here,
# as the initrd will automatically be populated with a
# config file appropriate for the running kernel.
# The default core_collector for raw/ssh dump is:
# "makedumpfile -F -l --message-level 1 -d 31".
# The default core_collector for other targets is:
# "makedumpfile -l --message-level 1 -d 31".
#
# "makedumpfile -F" will create a flattened vmcore.
# You need to use "makedumpfile -R" to rearrange the dump data to
# a normal dumpfile readable with analysis tools. For example:
# "makedumpfile -R vmcore < vmcore.flat".
#
# For core_collector format details, you can refer to
# kexec-kdump-howto.txt or kdump.conf manpage.
#
# kdump_post <binary | script>
# - This directive allows you to run a executable binary
# or script after the vmcore dump process terminates.
# The exit status of the current dump process is fed to
# the executable binary or script as its first argument.
# All files under /etc/kdump/post.d are collectively sorted
# and executed in lexical order, before binary or script
# specified kdump_post parameter is executed.
#
# kdump_pre <binary | script>
# - Works like the "kdump_post" directive, but instead of running
# after the dump process, runs immediately before it.
# Exit status of this binary is interpreted as follows:
# 0 - continue with dump process as usual
# non 0 - run the final action (reboot/poweroff/halt)
# All files under /etc/kdump/pre.d are collectively sorted and
# executed in lexical order, after binary or script specified
# kdump_pre parameter is executed.
# Even if the binary or script in /etc/kdump/pre.d directory
# returns non 0 exit status, the processing is continued.
#
# extra_bins <binaries | shell scripts>
# - This directive allows you to specify additional binaries or
# shell scripts to be included in the kdump initrd.
# Generally they are useful in conjunction with a kdump_post
# or kdump_pre binary or script which depends on these extra_bins.
#
# extra_modules <module(s)>
# - This directive allows you to specify extra kernel modules
# that you want to be loaded in the kdump initrd.
# Multiple modules can be listed, separated by spaces, and any
# dependent modules will automatically be included.
#
# failure_action <reboot | halt | poweroff | shell | dump_to_rootfs>
# - Action to perform in case dumping fails.
# reboot: Reboot the system.
# halt: Halt the system.
# poweroff: Power down the system.
# shell: Drop to a bash shell.
# Exiting the shell reboots the system by default,
# or perform "final_action".
# dump_to_rootfs: Dump vmcore to rootfs from initramfs context and
# reboot by default or perform "final_action".
# Useful when non-root dump target is specified.
# The default option is "reboot".
#
# default <reboot | halt | poweroff | shell | dump_to_rootfs>
# - Same as the "failure_action" directive above, but this directive
# is obsolete and will be removed in the future.
#
# final_action <reboot | halt | poweroff>
# - Action to perform in case dumping succeeds. Also performed
# when "shell" or "dump_to_rootfs" failure action finishes.
# Each action is same as the "failure_action" directive above.
# The default is "reboot".
#
# force_rebuild <0 | 1>
# - By default, kdump initrd will only be rebuilt when necessary.
# Specify 1 to force rebuilding kdump initrd every time when kdump
# service starts.
#
# force_no_rebuild <0 | 1>
# - By default, kdump initrd will be rebuilt when necessary.
# Specify 1 to bypass rebuilding of kdump initrd.
#
# force_no_rebuild and force_rebuild options are mutually
# exclusive and they should not be set to 1 simultaneously.
#
# override_resettable <0 | 1>
# - Usually an unresettable block device can't be a dump target.
# Specifying 1 when you want to dump even though the block
# target is unresettable
# By default, it is 0, which will not try dumping destined to fail.
#
# dracut_args <arg(s)>
# - Pass extra dracut options when rebuilding kdump initrd.
#
# fence_kdump_args <arg(s)>
# - Command line arguments for fence_kdump_send (it can contain
# all valid arguments except hosts to send notification to).
#
# fence_kdump_nodes <node(s)>
# - List of cluster node(s) except localhost, separated by spaces,
# to send fence_kdump notifications to.
# (this option is mandatory to enable fence_kdump).
#
#raw /dev/vg/lv_kdump
#ext4 /dev/vg/lv_kdump
#ext4 LABEL=/boot
#ext4 UUID=03138356-5e61-4ab3-b58e-27507ac41937
#nfs my.server.com:/export/tmp
#ssh user@my.server.com
#sshkey /root/.ssh/kdump_id_rsa
path /var/crash
core_collector makedumpfile -l --message-level 1 -d 31
#core_collector scp
#kdump_post /var/crash/scripts/kdump-post.sh
#kdump_pre /var/crash/scripts/kdump-pre.sh
#extra_bins /usr/bin/lftp
#extra_modules gfs2
#failure_action shell
#force_rebuild 1
#force_no_rebuild 1
#dracut_args --omit-drivers "cfg80211 snd" --add-drivers "ext2 ext3"
#fence_kdump_args -p 7410 -f auto -c 0 -i 10
#fence_kdump_nodes node1 node2

370
SOURCES/kdump.conf.5 Normal file
View File

@ -0,0 +1,370 @@
.TH KDUMP.CONF 5 "07/23/2008" "kexec-tools"
.SH NAME
kdump.conf \- configuration file for kdump kernel.
.SH DESCRIPTION
kdump.conf is a configuration file for the kdump kernel crash
collection service.
kdump.conf provides post-kexec instructions to the kdump kernel. It is
stored in the initrd file managed by the kdump service. If you change
this file and do not want to reboot in order for the changes to take
effect, restart the kdump service to rebuild the initrd.
For most configurations, you can simply review the examples provided
in the stock /etc/kdump.conf.
.B NOTE:
For filesystem dumps the dump target must be mounted before building
kdump initramfs.
kdump.conf only affects the behavior of the initramfs. Please read the
kdump operational flow section of kexec-kdump-howto.txt in the docs to better
understand how this configuration file affects the behavior of kdump.
.SH OPTIONS
.B raw <partition>
.RS
Will dd /proc/vmcore into <partition>. Use persistent device names for
partition devices, such as /dev/vg/<devname>.
.RE
.B nfs <nfs mount>
.RS
Will mount nfs to <mnt>, and copy /proc/vmcore to <mnt>/<path>/%HOST-%DATE/,
supports DNS. Note that a fqdn should be used as the server name in the
mount point.
.RE
.B ssh <user@server>
.RS
Will scp /proc/vmcore to <user@server>:<path>/%HOST-%DATE/,
supports DNS. NOTE: make sure user has necessary write permissions on
server and that a fqdn is used as the server name.
.RE
.B sshkey <path>
.RS
Specify the path of the ssh key to use when dumping via ssh.
The default value is /root/.ssh/kdump_id_rsa.
.RE
.B <fs type> <partition>
.RS
Will mount -t <fs type> <partition> <mnt>, and copy /proc/vmcore to
<mnt>/<path>/%DATE/. NOTE: <partition> can be a device node, label
or uuid. It's recommended to use persistent device names such as
/dev/vg/<devname>. Otherwise it's suggested to use label or uuid.
.RE
.B path <path>
.RS
"path" represents the file system path in which vmcore will be saved.
If a dump target is specified in kdump.conf, then "path" is relative to the
specified dump target.
.PP
Interpretation of "path" changes a bit if the user didn't specify any dump
target explicitly in kdump.conf. In this case, "path" represents the
absolute path from root. The dump target and adjusted path are arrived
at automatically depending on what's mounted in the current system.
.PP
Ignored for raw device dumps. If unset, will use the default "/var/crash".
.RE
.B core_collector <command> <options>
.RS
This allows you to specify the command to copy the vmcore.
The default is makedumpfile, which on some architectures can drastically reduce
core file size. See /sbin/makedumpfile --help for a list of options.
Note that the -i and -g options are not needed here, as the initrd
will automatically be populated with a config file appropriate
for the running kernel.
.PP
Note 1: About default core collector:
The default core_collector for raw/ssh dump is:
"makedumpfile -F -l --message-level 1 -d 31".
The default core_collector for other targets is:
"makedumpfile -l --message-level 1 -d 31".
Even if core_collector option is commented out in kdump.conf, makedumpfile
is the default core collector and kdump uses it internally.
If one does not want makedumpfile as default core_collector, then they
need to specify one using core_collector option to change the behavior.
.PP
Note 2: If "makedumpfile -F" is used then you will get a flattened format
vmcore.flat, you will need to use "makedumpfile -R" to rearrange the
dump data from standard input to a normal dumpfile (readable with analysis
tools).
ie. "makedumpfile -R vmcore < vmcore.flat"
.RE
.B kdump_post <binary | script>
.RS
This directive allows you to run a specified executable
just after the vmcore dump process terminates. The exit
status of the current dump process is fed to the kdump_post
executable as its first argument($1). Executable can modify
it to indicate the new exit status of succeeding dump process,
.PP
All files under /etc/kdump/post.d are collectively sorted
and executed in lexical order, before binary or script
specified kdump_post parameter is executed.
.PP
Note that scripts written for use with this directive must use
the /bin/bash interpreter.
.RE
.B kdump_pre <binary | script>
.RS
Works just like the "kdump_post" directive, but instead
of running after the dump process, runs immediately
before. Exit status of this binary is interpreted
as follows:
.PP
0 - continue with dump process as usual
.PP
non 0 - run the final action (reboot/poweroff/halt)
.PP
All files under /etc/kdump/pre.d are collectively sorted and
executed in lexical order, after binary or script specified
kdump_pre parameter is executed.
Even if the binary or script in /etc/kdump/pre.d directory
returns non 0 exit status, the processing is continued.
.PP
Note that scripts written for this directive must use
the /bin/bash interpreter.
.RE
.B extra_bins <binaries | shell scripts>
.RS
This directive allows you to specify additional
binaries or shell scripts you'd like to include in
your kdump initrd. Generally only useful in
conjunction with a kdump_post binary or script that
relies on other binaries or scripts.
.RE
.B extra_modules <module(s)>
.RS
This directive allows you to specify extra kernel
modules that you want to be loaded in the kdump
initrd, typically used to set up access to
non-boot-path dump targets that might otherwise
not be accessible in the kdump environment. Multiple
modules can be listed, separated by spaces, and any
dependent modules will automatically be included.
.RE
.B failure_action <reboot | halt | poweroff | shell | dump_to_rootfs>
.RS
Action to perform in case dumping to the intended target fails. The default is "reboot".
reboot: Reboot the system (this is what most people will want, as it returns the system
to a normal state). halt: Halt the system and lose the vmcore. poweroff: The system
will be powered down. shell: Drop to a shell session inside the initramfs, from which
you can manually perform additional recovery actions. Exiting this shell reboots the
system by default or performs "final_action".
Note: kdump uses bash as the default shell. dump_to_rootfs: If non-root dump
target is specified, the failure action can be set as dump_to_rootfs. That means when
dumping to target fails, dump vmcore to rootfs from initramfs context and reboot
by default or perform "final_action".
.RE
.B default <reboot | halt | poweroff | shell | dump_to_rootfs>
.RS
Same as the "failure_action" directive above, but this directive is obsolete
and will be removed in the future.
.RE
.B final_action <reboot | halt | poweroff>
.RS
Action to perform in case dumping to the intended target succeeds.
Also performed when "shell" or "dump_to_rootfs" failure action finishes.
Each action is same as the "failure_action" directive above.
The default is "reboot".
.RE
.B force_rebuild <0 | 1>
.RS
By default, kdump initrd will only be rebuilt when necessary.
Specify 1 to force rebuilding kdump initrd every time when kdump service starts.
.RE
.B force_no_rebuild <0 | 1>
.RS
By default, kdump initrd will be rebuilt when necessary.
Specify 1 to bypass rebuilding of kdump initrd.
.PP
force_no_rebuild and force_rebuild options are mutually exclusive and
they should not be set to 1 simultaneously.
.RE
.B override_resettable <0 | 1>
.RS
Usually an unresettable block device can't be a dump target. Specifying 1 means
that even though the block target is unresettable, the user wants to try dumping anyway.
By default, it's set to 0, which will not try something destined to fail.
.RE
.B dracut_args <arg(s)>
.RS
Kdump uses dracut to generate initramfs for second kernel. This option
allows a user to pass arguments to dracut directly.
.RE
.B fence_kdump_args <arg(s)>
.RS
Command line arguments for fence_kdump_send (it can contain all valid
arguments except hosts to send notification to).
.RE
.B fence_kdump_nodes <node(s)>
.RS
List of cluster node(s) except localhost, separated by spaces, to send fence_kdump notification
to (this option is mandatory to enable fence_kdump).
.RE
.SH DEPRECATED OPTIONS
.B net <nfs mount>|<user@server>
.RS
net option is replaced by nfs and ssh options. Use nfs or ssh options
directly.
.RE
.B options <module> <option list>
.RS
Use KDUMP_COMMANDLINE_APPEND in /etc/sysconfig/kdump to add module options as
kernel command line parameters. For example, specify 'loop.max_loop=1' to limit
maximum loop devices to 1.
.RE
.B link_delay <seconds>
.RS
link_delay was used to wait for a network device to initialize before using it.
Now dracut network module takes care of this issue automatically.
.RE
.B disk_timeout <seconds>
.RS
Similar to link_delay, dracut ensures disks are ready before kdump uses them.
.RE
.B debug_mem_level <0-3>
.RS
Turn on verbose debug output of kdump scripts regarding free/used memory at
various points of execution. This feature has been
moved to dracut now.
Use KDUMP_COMMANDLINE_APPEND in /etc/sysconfig/kdump and
append dracut cmdline param rd.memdebug=[0-3] to enable the debug output.
Higher level means more debugging output.
.PP
0 - no output
.PP
1 - partial /proc/meminfo
.PP
2 - /proc/meminfo
.PP
3 - /proc/meminfo + /proc/slabinfo
.RE
.B blacklist <list of kernel modules>
.RS
blacklist option was recently being used to prevent loading modules in
initramfs. General terminology for blacklist has been that module is
present in initramfs but it is not actually loaded in kernel. Hence
retaining blacklist option creates more confusing behavior. It has been
deprecated.
.PP
Instead, use rd.driver.blacklist option on second kernel to blacklist
a certain module. One can edit /etc/sysconfig/kdump and edit
KDUMP_COMMANDLINE_APPEND to pass kernel command line options. Refer
to dracut.cmdline man page for more details on module blacklist option.
.RE
.RE
.SH EXAMPLES
Here are some examples for core_collector option:
.PP
Core collector command format depends on dump target type. Typically for
filesystem (local/remote), core_collector should accept two arguments.
First one is source file and second one is target file. For ex.
.TP
ex1.
core_collector "cp --sparse=always"
Above will effectively be translated to:
cp --sparse=always /proc/vmcore <dest-path>/vmcore
.TP
ex2.
core_collector "makedumpfile -l --message-level 1 -d 31"
Above will effectively be translated to:
makedumpfile -l --message-level 1 -d 31 /proc/vmcore <dest-path>/vmcore
.PP
For dump targets like raw and ssh, in general, core collector should expect
one argument (source file) and should output the processed core on standard
output (There is one exception of "scp", discussed later). This standard
output will be saved to destination using appropriate commands.
raw dumps examples:
.TP
ex3.
core_collector "cat"
Above will effectively be translated to.
cat /proc/vmcore | dd of=<target-device>
.TP
ex4.
core_collector "makedumpfile -F -l --message-level 1 -d 31"
Above will effectively be translated to.
makedumpfile -F -l --message-level 1 -d 31 | dd of=<target-device>
.PP
ssh dumps examples
.TP
ex5.
core_collector "cat"
Above will effectively be translated to.
cat /proc/vmcore | ssh <options> <remote-location> "dd of=path/vmcore"
.TP
ex6.
core_collector "makedumpfile -F -l --message-level 1 -d 31"
Above will effectively be translated to.
makedumpfile -F -l --message-level 1 -d 31 | ssh <options> <remote-location> "dd of=path/vmcore"
There is one exception to standard output rule for ssh dumps. And that is
scp. As scp can handle ssh destinations for file transfers, one can
specify "scp" as core collector for ssh targets (no output on stdout).
.TP
ex7.
core_collector "scp"
Above will effectively be translated to.
scp /proc/vmcore <user@host>:path/vmcore
.PP
examples for other options please see
.I /etc/kdump.conf
.SH SEE ALSO
kexec(8) mkdumprd(8) dracut.cmdline(7)

15
SOURCES/kdump.service Normal file
View File

@ -0,0 +1,15 @@
[Unit]
Description=Crash recovery kernel arming
After=network.target network-online.target remote-fs.target basic.target
DefaultDependencies=no
[Service]
Type=oneshot
ExecStart=/usr/bin/kdumpctl start
ExecStop=/usr/bin/kdumpctl stop
ExecReload=/usr/bin/kdumpctl reload
RemainAfterExit=yes
StartLimitInterval=0
[Install]
WantedBy=multi-user.target

37
SOURCES/kdump.sysconfig Normal file
View File

@ -0,0 +1,37 @@
# Kernel Version string for the -kdump kernel, such as 2.6.13-1544.FC5kdump
# If no version is specified, then the init script will try to find a
# kdump kernel with the same version number as the running kernel.
KDUMP_KERNELVER=""
# The kdump commandline is the command line that needs to be passed off to
# the kdump kernel. This will likely match the contents of the grub kernel
# line. For example:
# KDUMP_COMMANDLINE="ro root=LABEL=/"
# Dracut depends on proper root= options, so please make sure that appropriate
# root= options are copied from /proc/cmdline. In general it is best to append
# command line options using "KDUMP_COMMANDLINE_APPEND=".
# If a command line is not specified, the default will be taken from
# /proc/cmdline
KDUMP_COMMANDLINE=""
# This variable lets us remove arguments from the current kdump commandline
# as taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline
# NOTE: some arguments such as crashkernel will always be removed
KDUMP_COMMANDLINE_REMOVE="hugepages hugepagesz slub_debug quiet log_buf_len"
# This variable lets us append arguments to the current kdump commandline
# after processed by KDUMP_COMMANDLINE_REMOVE
KDUMP_COMMANDLINE_APPEND="irqpoll maxcpus=1 reset_devices novmcoredd"
# Any additional kexec arguments required. In most situations, this should
# be left empty
#
# Example:
# KEXEC_ARGS="--elf32-core-headers"
KEXEC_ARGS=""
#Where to find the boot image
#KDUMP_BOOTDIR="/boot"
#What is the image type used for kdump
KDUMP_IMG="vmlinuz"

37
SOURCES/kdump.sysconfig.aarch64 Normal file
View File

@ -0,0 +1,37 @@
# Kernel Version string for the -kdump kernel, such as 2.6.13-1544.FC5kdump
# If no version is specified, then the init script will try to find a
# kdump kernel with the same version number as the running kernel.
KDUMP_KERNELVER=""
# The kdump commandline is the command line that needs to be passed off to
# the kdump kernel. This will likely match the contents of the grub kernel
# line. For example:
# KDUMP_COMMANDLINE="ro root=LABEL=/"
# Dracut depends on proper root= options, so please make sure that appropriate
# root= options are copied from /proc/cmdline. In general it is best to append
# command line options using "KDUMP_COMMANDLINE_APPEND=".
# If a command line is not specified, the default will be taken from
# /proc/cmdline
KDUMP_COMMANDLINE=""
# This variable lets us remove arguments from the current kdump commandline
# as taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline
# NOTE: some arguments such as crashkernel will always be removed
KDUMP_COMMANDLINE_REMOVE="hugepages hugepagesz slub_debug quiet log_buf_len swiotlb"
# This variable lets us append arguments to the current kdump commandline
# after processed by KDUMP_COMMANDLINE_REMOVE
KDUMP_COMMANDLINE_APPEND="irqpoll nr_cpus=1 reset_devices cgroup_disable=memory udev.children-max=2 panic=10 swiotlb=noforce novmcoredd"
# Any additional kexec arguments required. In most situations, this should
# be left empty
#
# Example:
# KEXEC_ARGS="--elf32-core-headers"
KEXEC_ARGS=""
#Where to find the boot image
#KDUMP_BOOTDIR="/boot"
#What is the image type used for kdump
KDUMP_IMG="vmlinuz"

40
SOURCES/kdump.sysconfig.i386 Normal file
View File

@ -0,0 +1,40 @@
# Kernel Version string for the -kdump kernel, such as 2.6.13-1544.FC5kdump
# If no version is specified, then the init script will try to find a
# kdump kernel with the same version number as the running kernel.
KDUMP_KERNELVER=""
# The kdump commandline is the command line that needs to be passed off to
# the kdump kernel. This will likely match the contents of the grub kernel
# line. For example:
# KDUMP_COMMANDLINE="ro root=LABEL=/"
# Dracut depends on proper root= options, so please make sure that appropriate
# root= options are copied from /proc/cmdline. In general it is best to append
# command line options using "KDUMP_COMMANDLINE_APPEND=".
# If a command line is not specified, the default will be taken from
# /proc/cmdline
KDUMP_COMMANDLINE=""
# This variable lets us remove arguments from the current kdump commandline
# as taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline
# NOTE: some arguments such as crashkernel will always be removed
KDUMP_COMMANDLINE_REMOVE="hugepages hugepagesz slub_debug quiet log_buf_len swiotlb"
# This variable lets us append arguments to the current kdump commandline
# after processed by KDUMP_COMMANDLINE_REMOVE
KDUMP_COMMANDLINE_APPEND="irqpoll nr_cpus=1 reset_devices numa=off udev.children-max=2 panic=10 rootflags=nofail transparent_hugepage=never novmcoredd"
# Any additional kexec arguments required. In most situations, this should
# be left empty
#
# Example:
# KEXEC_ARGS="--elf32-core-headers"
KEXEC_ARGS=""
#Where to find the boot image
#KDUMP_BOOTDIR="/boot"
#What is the image type used for kdump
KDUMP_IMG="vmlinuz"
#What is the images extension. Relocatable kernels don't have one
KDUMP_IMG_EXT=""

42
SOURCES/kdump.sysconfig.ppc64 Normal file
View File

@ -0,0 +1,42 @@
# Kernel Version string for the -kdump kernel, such as 2.6.13-1544.FC5kdump
# If no version is specified, then the init script will try to find a
# kdump kernel with the same version number as the running kernel.
KDUMP_KERNELVER=""
# The kdump commandline is the command line that needs to be passed off to
# the kdump kernel. This will likely match the contents of the grub kernel
# line. For example:
# KDUMP_COMMANDLINE="ro root=LABEL=/"
# Dracut depends on proper root= options, so please make sure that appropriate
# root= options are copied from /proc/cmdline. In general it is best to append
# command line options using "KDUMP_COMMANDLINE_APPEND=".
# If a command line is not specified, the default will be taken from
# /proc/cmdline
KDUMP_COMMANDLINE=""
# This variable lets us remove arguments from the current kdump commandline
# as taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline
# NOTE: some arguments such as crashkernel will always be removed
KDUMP_COMMANDLINE_REMOVE="hugepages hugepagesz slub_debug quiet log_buf_len swiotlb"
# This variable lets us append arguments to the current kdump commandline
# after processed by KDUMP_COMMANDLINE_REMOVE
KDUMP_COMMANDLINE_APPEND="irqpoll maxcpus=1 noirqdistrib reset_devices cgroup_disable=memory numa=off udev.children-max=2 ehea.use_mcs=0 panic=10 rootflags=nofail kvm_cma_resv_ratio=0 transparent_hugepage=never novmcoredd"
# Any additional kexec arguments required. In most situations, this should
# be left empty
#
# Example:
# KEXEC_ARGS="--elf32-core-headers"
KEXEC_ARGS="--dt-no-old-root"
#Where to find the boot image
#KDUMP_BOOTDIR="/boot"
#What is the image type used for kdump
KDUMP_IMG="vmlinuz"
#What is the images extension. Relocatable kernels don't have one
KDUMP_IMG_EXT=""
#Specify the action after failure

42
SOURCES/kdump.sysconfig.ppc64le Normal file
View File

@ -0,0 +1,42 @@
# Kernel Version string for the -kdump kernel, such as 2.6.13-1544.FC5kdump
# If no version is specified, then the init script will try to find a
# kdump kernel with the same version number as the running kernel.
KDUMP_KERNELVER=""
# The kdump commandline is the command line that needs to be passed off to
# the kdump kernel. This will likely match the contents of the grub kernel
# line. For example:
# KDUMP_COMMANDLINE="ro root=LABEL=/"
# Dracut depends on proper root= options, so please make sure that appropriate
# root= options are copied from /proc/cmdline. In general it is best to append
# command line options using "KDUMP_COMMANDLINE_APPEND=".
# If a command line is not specified, the default will be taken from
# /proc/cmdline
KDUMP_COMMANDLINE=""
# This variable lets us remove arguments from the current kdump commandline
# as taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline
# NOTE: some arguments such as crashkernel will always be removed
KDUMP_COMMANDLINE_REMOVE="hugepages hugepagesz slub_debug quiet log_buf_len swiotlb"
# This variable lets us append arguments to the current kdump commandline
# after processed by KDUMP_COMMANDLINE_REMOVE
KDUMP_COMMANDLINE_APPEND="irqpoll maxcpus=1 noirqdistrib reset_devices cgroup_disable=memory numa=off udev.children-max=2 ehea.use_mcs=0 panic=10 rootflags=nofail kvm_cma_resv_ratio=0 transparent_hugepage=never novmcoredd"
# Any additional kexec arguments required. In most situations, this should
# be left empty
#
# Example:
# KEXEC_ARGS="--elf32-core-headers"
KEXEC_ARGS="--dt-no-old-root"
#Where to find the boot image
#KDUMP_BOOTDIR="/boot"
#What is the image type used for kdump
KDUMP_IMG="vmlinuz"
#What is the images extension. Relocatable kernels don't have one
KDUMP_IMG_EXT=""
#Specify the action after failure

43
SOURCES/kdump.sysconfig.s390x Normal file
View File

@ -0,0 +1,43 @@
# Kernel Version string for the -kdump kernel, such as 2.6.13-1544.FC5kdump
# If no version is specified, then the init script will try to find a
# kdump kernel with the same version number as the running kernel.
KDUMP_KERNELVER=""
# The kdump commandline is the command line that needs to be passed off to
# the kdump kernel. This will likely match the contents of the grub kernel
# line. For example:
# KDUMP_COMMANDLINE="ro root=LABEL=/"
# Dracut depends on proper root= options, so please make sure that appropriate
# root= options are copied from /proc/cmdline. In general it is best to append
# command line options using "KDUMP_COMMANDLINE_APPEND=".
# If a command line is not specified, the default will be taken from
# /proc/cmdline
KDUMP_COMMANDLINE=""
# This variable lets us remove arguments from the current kdump commandline
# as taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline
# NOTE: some arguments such as crashkernel will always be removed
KDUMP_COMMANDLINE_REMOVE="hugepages hugepagesz slub_debug quiet log_buf_len swiotlb"
# This variable lets us append arguments to the current kdump commandline
# after processed by KDUMP_COMMANDLINE_REMOVE
KDUMP_COMMANDLINE_APPEND="nr_cpus=1 cgroup_disable=memory numa=off udev.children-max=2 panic=10 rootflags=nofail transparent_hugepage=never novmcoredd"
# Any additional /sbin/mkdumprd arguments required.
MKDUMPRD_ARGS=""
# Any additional kexec arguments required. In most situations, this should
# be left empty
#
# Example:
# KEXEC_ARGS="--elf32-core-headers"
KEXEC_ARGS=""
#Where to find the boot image
#KDUMP_BOOTDIR="/boot"
#What is the image type used for kdump
KDUMP_IMG="vmlinuz"
#What is the images extension. Relocatable kernels don't have one
KDUMP_IMG_EXT=""

40
SOURCES/kdump.sysconfig.x86_64 Normal file
View File

@ -0,0 +1,40 @@
# Kernel Version string for the -kdump kernel, such as 2.6.13-1544.FC5kdump
# If no version is specified, then the init script will try to find a
# kdump kernel with the same version number as the running kernel.
KDUMP_KERNELVER=""
# The kdump commandline is the command line that needs to be passed off to
# the kdump kernel. This will likely match the contents of the grub kernel
# line. For example:
# KDUMP_COMMANDLINE="ro root=LABEL=/"
# Dracut depends on proper root= options, so please make sure that appropriate
# root= options are copied from /proc/cmdline. In general it is best to append
# command line options using "KDUMP_COMMANDLINE_APPEND=".
# If a command line is not specified, the default will be taken from
# /proc/cmdline
KDUMP_COMMANDLINE=""
# This variable lets us remove arguments from the current kdump commandline
# as taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline
# NOTE: some arguments such as crashkernel will always be removed
KDUMP_COMMANDLINE_REMOVE="hugepages hugepagesz slub_debug quiet log_buf_len swiotlb"
# This variable lets us append arguments to the current kdump commandline
# after processed by KDUMP_COMMANDLINE_REMOVE
KDUMP_COMMANDLINE_APPEND="irqpoll nr_cpus=1 reset_devices cgroup_disable=memory mce=off numa=off udev.children-max=2 panic=10 rootflags=nofail acpi_no_memhotplug transparent_hugepage=never nokaslr novmcoredd hest_disable"
# Any additional kexec arguments required. In most situations, this should
# be left empty
#
# Example:
# KEXEC_ARGS="--elf32-core-headers"
KEXEC_ARGS="-s"
#Where to find the boot image
#KDUMP_BOOTDIR="/boot"
#What is the image type used for kdump
KDUMP_IMG="vmlinuz"
#What is the images extension. Relocatable kernels don't have one
KDUMP_IMG_EXT=""

1303
SOURCES/kdumpctl Executable file
View File

File diff suppressed because it is too large Load Diff

50
SOURCES/kdumpctl.8 Normal file
View File

@ -0,0 +1,50 @@
.TH KDUMPCTL 8 2015-07-13 kexec-tools
.SH NAME
kdumpctl \- control interface for kdump
.SH SYNOPSIS
.B kdumpctl
.I COMMAND
.SH DESCRIPTION
.B kdumpctl
is used to check or control the kdump service.
In most cases, you should use
.B systemctl
to start / stop / enable kdump service instead. However,
.B kdumpctl
provides more details for debug and a helper to setup ssh key authentication.
.SH COMMANDS
.TP
.I start
Start the service.
.TP
.I stop
Stop the service.
.TP
.I status
Prints the current status of kdump service.
It returns non-zero value if kdump is not operational.
.TP
.I restart
Is equal to
.I start; stop
.TP
.I reload
reload crash kernel image and initramfs without triggering a rebuild.
.TP
.I rebuild
rebuild the crash kernel initramfs.
.TP
.I propagate
Helps to setup key authentication for ssh storage since it's
impossible to use password authentication during kdump.
.TP
.I showmem
Prints the size of reserved memory for crash kernel in megabytes.
.SH "SEE ALSO"
.BR kdump.conf (5),
.BR mkdumprd (8)

887
SOURCES/kexec-kdump-howto.txt Normal file
View File

@ -0,0 +1,887 @@
=================
Kexec/Kdump HOWTO
=================
Introduction
============
Kexec and kdump are new features in the 2.6 mainstream kernel. These features
are included in Red Hat Enterprise Linux 5. The purpose of these features
is to ensure faster boot up and creation of reliable kernel vmcores for
diagnostic purposes.
Overview
========
Kexec
-----
Kexec is a fastboot mechanism which allows booting a Linux kernel from the
context of already running kernel without going through BIOS. BIOS can be very
time consuming especially on the big servers with lots of peripherals. This can
save a lot of time for developers who end up booting a machine numerous times.
Kdump
-----
Kdump is a new kernel crash dumping mechanism and is very reliable because
the crash dump is captured from the context of a freshly booted kernel and
not from the context of the crashed kernel. Kdump uses kexec to boot into
a second kernel whenever system crashes. This second kernel, often called
a capture kernel, boots with very little memory and captures the dump image.
The first kernel reserves a section of memory that the second kernel uses
to boot. Kexec enables booting the capture kernel without going through BIOS
hence contents of first kernel's memory are preserved, which is essentially
the kernel crash dump.
Kdump is supported on the i686, x86_64, ia64 and ppc64 platforms. The
standard kernel and capture kernel are one in the same on i686, x86_64,
ia64 and ppc64.
If you're reading this document, you should already have kexec-tools
installed. If not, you install it via the following command:
# yum install kexec-tools
Now load a kernel with kexec:
# kver=`uname -r` # kexec -l /boot/vmlinuz-$kver
--initrd=/boot/initrd-$kver.img \
--command-line="`cat /proc/cmdline`"
NOTE: The above will boot you back into the kernel you're currently running,
if you want to load a different kernel, substitute it in place of `uname -r`.
Now reboot your system, taking note that it should bypass the BIOS:
# reboot
How to configure kdump
======================
Again, we assume if you're reading this document, you should already have
kexec-tools installed. If not, you install it via the following command:
# yum install kexec-tools
To be able to do much of anything interesting in the way of debug analysis,
you'll also need to install the kernel-debuginfo package, of the same arch
as your running kernel, and the crash utility:
# yum --enablerepo=\*debuginfo install kernel-debuginfo.$(uname -m) crash
Next up, we need to modify some boot parameters to reserve a chunk of memory for
the capture kernel. With the help of grubby, it's very easy to append
"crashkernel=128M" to the end of your kernel boot parameters. Note that the X
values are such that X = the amount of memory to reserve for the capture kernel.
And based on arch and system configuration, one might require more than 128M to
be reserved for kdump. One need to experiment and test kdump, if 128M is not
sufficient, try reserving more memory.
# grubby --args="crashkernel=128M" --update-kernel=/boot/vmlinuz-`uname -r`
Note that there is an alternative form in which to specify a crashkernel
memory reservation, in the event that more control is needed over the size and
placement of the reserved memory. The format is:
crashkernel=range1:size1[,range2:size2,...][@offset]
Where range<n> specifies a range of values that are matched against the amount
of physical RAM present in the system, and the corresponding size<n> value
specifies the amount of kexec memory to reserve. For example:
crashkernel=512M-2G:64M,2G-:128M
This line tells kexec to reserve 64M of ram if the system contains between
512M and 2G of physical memory. If the system contains 2G or more of physical
memory, 128M should be reserved.
Besides, since kdump needs to access /proc/kallsyms during a kernel
loading if KASLR is enabled, check /proc/sys/kernel/kptr_restrict to
make sure that the content of /proc/kallsyms is exposed correctly.
We recommend to set the value of kptr_restrict to '1'. Otherwise
capture kernel loading could fail.
After making said changes, reboot your system, so that the X MB of memory is
left untouched by the normal system, reserved for the capture kernel. Take note
that the output of 'free -m' will show X MB less memory than without this
parameter, which is expected. You may be able to get by with less than 128M, but
testing with only 64M has proven unreliable of late. On ia64, as much as 512M
may be required.
Now that you've got that reserved memory region set up, you want to turn on
the kdump init script:
# chkconfig kdump on
Then, start up kdump as well:
# systemctl start kdump.service
This should load your kernel-kdump image via kexec, leaving the system ready
to capture a vmcore upon crashing. To test this out, you can force-crash
your system by echo'ing a c into /proc/sysrq-trigger:
# echo c > /proc/sysrq-trigger
You should see some panic output, followed by the system restarting into
the kdump kernel. When the boot process gets to the point where it starts
the kdump service, your vmcore should be copied out to disk (by default,
in /var/crash/<YYYY-MM-DD-HH:MM>/vmcore), then the system rebooted back into
your normal kernel.
Once back to your normal kernel, you can use the previously installed crash
kernel in conjunction with the previously installed kernel-debuginfo to
perform postmortem analysis:
# crash /usr/lib/debug/lib/modules/2.6.17-1.2621.el5/vmlinux
/var/crash/2006-08-23-15:34/vmcore
crash> bt
and so on...
Notes on kdump
==============
When kdump starts, the kdump kernel is loaded together with the kdump
initramfs. To save memory usage and disk space, the kdump initramfs is
generated strictly against the system it will run on, and contains the
minimum set of kernel modules and utilities to boot the machine to a stage
where the dump target could be mounted.
With kdump service enabled, kdumpctl will try to detect possible system
change and rebuild the kdump initramfs if needed. But it can not guarantee
to cover every possible case. So after a hardware change, disk migration,
storage setup update or any similar system level changes, it's highly
recommended to rebuild the initramfs manually with following command:
# kdumpctl rebuild
Saving vmcore-dmesg.txt
=======================
Kernel log bufferes are one of the most important information available
in vmcore. Now before saving vmcore, kernel log bufferes are extracted
from /proc/vmcore and saved into a file vmcore-dmesg.txt. After
vmcore-dmesg.txt, vmcore is saved. Destination disk and directory for
vmcore-dmesg.txt is same as vmcore. Note that kernel log buffers will
not be available if dump target is raw device.
Dump Triggering methods
=======================
This section talks about the various ways, other than a Kernel Panic, in which
Kdump can be triggered. The following methods assume that Kdump is configured
on your system, with the scripts enabled as described in the section above.
1) AltSysRq C
Kdump can be triggered with the combination of the 'Alt','SysRq' and 'C'
keyboard keys. Please refer to the following link for more details:
https://access.redhat.com/solutions/2023
In addition, on PowerPC boxes, Kdump can also be triggered via Hardware
Management Console(HMC) using 'Ctrl', 'O' and 'C' keyboard keys.
2) NMI_WATCHDOG
In case a machine has a hard hang, it is quite possible that it does not
respond to keyboard interrupts. As a result 'Alt-SysRq' keys will not help
trigger a dump. In such scenarios Nmi Watchdog feature can prove to be useful.
The following link has more details on configuring Nmi watchdog option.
https://access.redhat.com/solutions/125103
Once this feature has been enabled in the kernel, any lockups will result in an
OOPs message to be generated, followed by Kdump being triggered.
3) Kernel OOPs
If we want to generate a dump everytime the Kernel OOPses, we can achieve this
by setting the 'Panic On OOPs' option as follows:
# echo 1 > /proc/sys/kernel/panic_on_oops
This is enabled by default on RHEL5.
4) NMI(Non maskable interrupt) button
In cases where the system is in a hung state, and is not accepting keyboard
interrupts, using NMI button for triggering Kdump can be very useful. NMI
button is present on most of the newer x86 and x86_64 machines. Please refer
to the User guides/manuals to locate the button, though in most occasions it
is not very well documented. In most cases it is hidden behind a small hole
on the front or back panel of the machine. You could use a toothpick or some
other non-conducting probe to press the button.
For example, on the IBM X series 366 machine, the NMI button is located behind
a small hole on the bottom center of the rear panel.
To enable this method of dump triggering using NMI button, you will need to set
the 'unknown_nmi_panic' option as follows:
# echo 1 > /proc/sys/kernel/unknown_nmi_panic
5) PowerPC specific methods:
On IBM PowerPC machines, issuing a soft reset invokes the XMON debugger(if
XMON is configured). To configure XMON one needs to compile the kernel with
the CONFIG_XMON and CONFIG_XMON_DEFAULT options, or by compiling with
CONFIG_XMON and booting the kernel with xmon=on option.
Following are the ways to remotely issue a soft reset on PowerPC boxes, which
would drop you to XMON. Pressing a 'X' (capital alphabet X) followed by an
'Enter' here will trigger the dump.
5.1) HMC
Hardware Management Console(HMC) available on Power4 and Power5 machines allow
partitions to be reset remotely. This is specially useful in hang situations
where the system is not accepting any keyboard inputs.
Once you have HMC configured, the following steps will enable you to trigger
Kdump via a soft reset:
On Power4
Using GUI
* In the right pane, right click on the partition you wish to dump.
* Select "Operating System->Reset".
* Select "Soft Reset".
* Select "Yes".
Using HMC Commandline
# reset_partition -m <machine> -p <partition> -t soft
On Power5
Using GUI
* In the right pane, right click on the partition you wish to dump.
* Select "Restart Partition".
* Select "Dump".
* Select "OK".
Using HMC Commandline
# chsysstate -m <managed system name> -n <lpar name> -o dumprestart -r lpar
5.2) Blade Management Console for Blade Center
To initiate a dump operation, go to Power/Restart option under "Blade Tasks" in
the Blade Management Console. Select the corresponding blade for which you want
to initate the dump and then click "Restart blade with NMI". This issues a
system reset and invokes xmon debugger.
Dump targets
============
In addition to being able to capture a vmcore to your system's local file
system, kdump can be configured to capture a vmcore to a number of other
locations, including a raw disk partition, a dedicated file system, an NFS
mounted file system, or a remote system via ssh/scp. Additional options
exist for specifying the relative path under which the dump is captured,
what to do if the capture fails, and for compressing and filtering the dump
(so as to produce smaller, more manageable, vmcore files, see "Advanced Setups"
for more detail on these options).
In theory, dumping to a location other than the local file system should be
safer than kdump's default setup, as its possible the default setup will try
dumping to a file system that has become corrupted. The raw disk partition and
dedicated file system options allow you to still dump to the local system,
but without having to remount your possibly corrupted file system(s),
thereby decreasing the chance a vmcore won't be captured. Dumping to an
NFS server or remote system via ssh/scp also has this advantage, as well
as allowing for the centralization of vmcore files, should you have several
systems from which you'd like to obtain vmcore files. Of course, note that
these configurations could present problems if your network is unreliable.
Kdump target and advanced setups are configured via modifications to
/etc/kdump.conf, which out of the box, is fairly well documented itself.
Any alterations to /etc/kdump.conf should be followed by a restart of the
kdump service, so the changes can be incorporated in the kdump initrd.
Restarting the kdump service is as simple as '/sbin/systemctl restart kdump.service'.
There are two ways to config the dump target, config dump target only
using "path", and config dump target explicitly. Interpretation of "path"
also differs in two config styles.
Config dump target only using "path"
------------------------------------
You can change the dump target by setting "path" to a mount point where
dump target is mounted. When there is no explicitly configured dump target,
"path" in kdump.conf represents the current file system path in which vmcore
will be saved. Kdump will automatically detect the underlying device of
"path" and use that as the dump target.
In fact, upon dump, kdump creates a directory $hostip-$date with-in "path"
and saves vmcore there. So practically dump is saved in $path/$hostip-$date/.
Kdump will only check current mount status for mount entry corresponding to
"path". So please ensure the dump target is mounted on "path" before kdump
service starts.
NOTES:
- It's strongly recommanded to put an mount entry for "path" in /etc/fstab
and have it auto mounted on boot. This make sure the dump target is
reachable from the machine and kdump's configuration is stable.
EXAMPLES:
- path /var/crash/
This is the default configuration. Assuming there is no disk mounted
on /var/ or on /var/crash, dump will be saved on disk backing rootfs
in directory /var/crash.
- path /var/crash/ (A separate disk mounted on /var/crash)
Say a disk /dev/sdb is mounted on /var. In this case dump target will
become /dev/sdb and path will become "/" and dump will be saved
on "sdb:/var/crash/" directory.
- path /var/crash/ (NFS mounted on /var)
Say foo.com:/export/tmp is mounted on /var. In this case dump target is
nfs server and path will be adjusted to "/crash" and dump will be saved to
foo.com:/export/tmp/crash/ directory.
Config dump target explicitely
------------------------------
You can set the dump target explicitly in kdump.conf, and "path" will be
the relative path in the specified dump target. For example, if dump
target is "ext4 /dev/sda", then dump will be saved in "path" directory
on /dev/sda.
Same is the case for nfs dump. If user specified "nfs foo.com:/export/tmp/"
as dump target, then dump will effectively be saved in
"foo.com:/export/tmp/var/crash/" directory.
If the dump target is "raw", then "path" is ignored.
If it's a filesystem target, kdump will need to know the right mount option.
Kdump will check current mount status, and then /etc/fstab for mount options
corresponding to the specified dump target and use it. If there are
special mount option required for the dump target, it could be set by put
an entry in fstab.
If there are no related mount entry, mount option is set to "defaults".
NOTES:
- It's recommended to put an entry for the dump target in /etc/fstab
and have it auto mounted on boot. This make sure the dump target is
reachable from the machine and kdump won't fail.
- Kdump ignores some mount options, including "noauto", "ro". This
make it possible to keep the dump target unmounted or read-only
when not used.
EXAMPLES:
- ext4 /dev/sda (mounted)
path /var/crash/
In this case dump target is set to /dev/sdb, path is the absolute path
"/var/crash" in /dev/sda, vmcore path will saved on
"sda:/var/crash" directory.
- nfs foo.com:/export/tmp (mounted)
path /var/crash/
In this case dump target is nfs server, path is the absolute path
"/var/crash", vmcore path will saved on "foo.com:/export/tmp/crash/" directory.
- nfs foo.com:/export/tmp (not mounted)
path /var/crash/
Same with above case, kdump will use "defaults" as the mount option
for the dump target.
- nfs foo.com:/export/tmp (not mounted, entry with option "noauto,nolock" exists in /etc/fstab)
path /var/crash/
In this case dump target is nfs server, vmcore path will saved on
"foo.com:/export/tmp/crash/" directory, and kdump will inherit "nolock" option.
Dump target and mkdumprd
------------------------
MKdumprd is the tool used to create kdump initramfs, and it may change
the mount status of the dump target in some condition.
Usually the dump target should be used only for kdump. If you worry about
someone uses the filesystem for something else other than dumping vmcore
you can mount it as read-only or make it a noauto mount. Mkdumprd will
mount/remount it as read-write for creating dump directory and will
move it back to it's original state afterwards.
Supported dump target types and requirements
--------------------------------------------
1) Raw partition
Raw partition dumping requires that a disk partition in the system, at least
as large as the amount of memory in the system, be left unformatted. Assuming
/dev/vg/lv_kdump is left unformatted, kdump.conf can be configured with
'raw /dev/vg/lv_kdump', and the vmcore file will be copied via dd directly
onto partition /dev/vg/lv_kdump. Restart the kdump service via
'/sbin/systemctl restart kdump.service' to commit this change to your kdump
initrd. Dump target should be persistent device name, such as lvm or device
mapper canonical name.
2) Dedicated file system
Similar to raw partition dumping, you can format a partition with the file
system of your choice, Again, it should be at least as large as the amount
of memory in the system. Assuming it should be at least as large as the
amount of memory in the system. Assuming /dev/vg/lv_kdump has been
formatted ext4, specify 'ext4 /dev/vg/lv_kdump' in kdump.conf, and a
vmcore file will be copied onto the file system after it has been mounted.
Dumping to a dedicated partition has the advantage that you can dump multiple
vmcores to the file system, space permitting, without overwriting previous ones,
as would be the case in a raw partition setup. Restart the kdump service via
'/sbin/systemctl restart kdump.service' to commit this change to
your kdump initrd. Note that for local file systems ext4 and ext2 are
supported as dumpable targets. Kdump will not prevent you from specifying
other filesystems, and they will most likely work, but their operation
cannot be guaranteed. for instance specifying a vfat filesystem or msdos
filesystem will result in a successful load of the kdump service, but during
crash recovery, the dump will fail if the system has more than 2GB of memory
(since vfat and msdos filesystems do not support more than 2GB files).
Be careful of your filesystem selection when using this target.
It is recommended to use persistent device names or UUID/LABEL for file system
dumps. One example of persistent device is /dev/vg/<devname>.
3) NFS mount
Dumping over NFS requires an NFS server configured to export a file system
with full read/write access for the root user. All operations done within
the kdump initial ramdisk are done as root, and to write out a vmcore file,
we obviously must be able to write to the NFS mount. Configuring an NFS
server is outside the scope of this document, but either the no_root_squash
or anonuid options on the NFS server side are likely of interest to permit
the kdump initrd operations write to the NFS mount as root.
Assuming your're exporting /dump on the machine nfs-server.example.com,
once the mount is properly configured, specify it in kdump.conf, via
'nfs nfs-server.example.com:/dump'. The server portion can be specified either
by host name or IP address. Following a system crash, the kdump initrd will
mount the NFS mount and copy out the vmcore to your NFS server. Restart the
kdump service via '/sbin/systemctl restart kdump.service' to commit this change
to your kdump initrd.
4) Special mount via "dracut_args"
You can utilize "dracut_args" to pass "--mount" to kdump, see dracut manpage
about the format of "--mount" for details. If there is any "--mount" specified
via "dracut_args", kdump will build it as the mount target without doing any
validation (mounting or checking like mount options, fs size, save path, etc),
so you must test it to ensure all the correctness. You cannot use other targets
in /etc/kdump.conf if you use "--mount" in "dracut_args". You also cannot specify
mutliple "--mount" targets via "dracut_args".
One use case of "--mount" in "dracut_args" is you do not want to mount dump target
before kdump service startup, for example, to reduce the burden of the shared nfs
server. Such as the example below:
dracut_args --mount "192.168.1.1:/share /mnt/test nfs4 defaults"
NOTE:
- <mountpoint> must be specified as an absolute path.
5) Remote system via ssh/scp
Dumping over ssh/scp requires setting up passwordless ssh keys for every
machine you wish to have dump via this method. First up, configure kdump.conf
for ssh/scp dumping, adding a config line of 'ssh user@server', where 'user'
can be any user on the target system you choose, and 'server' is the host
name or IP address of the target system. Using a dedicated, restricted user
account on the target system is recommended, as there will be keyless ssh
access to this account.
Once kdump.conf is appropriately configured, issue the command
'kdumpctl propagate' to automatically set up the ssh host keys and transmit
the necessary bits to the target server. You'll have to type in 'yes'
to accept the host key for your targer server if this is the first time
you've connected to it, and then input the target system user's password
to send over the necessary ssh key file. Restart the kdump service via
'/sbin/systemctl restart kdump.service' to commit this change to your kdump initrd.
Advanced Setups
===============
Kdump boot directory
--------------------
Usually kdump kernel is the same as 1st kernel. So kdump will try to find
kdump kernel under /boot according to /proc/cmdline. E.g we execute below
command and get an output:
cat /proc/cmdline
BOOT_IMAGE=/xxx/vmlinuz-3.yyy.zzz root=xxxx .....
Then kdump kernel will be /boot/xxx/vmlinuz-3.yyy.zzz.
However a variable KDUMP_BOOTDIR in /etc/sysconfig/kdump is provided to
user if kdump kernel is put in a different directory.
Kdump Post-Capture Executable
-----------------------------
It is possible to specify a custom script or binary you wish to run following
an attempt to capture a vmcore. The executable is passed an exit code from
the capture process, which can be used to trigger different actions from
within your post-capture executable.
If /etc/kdump/post.d directory exist, All files in the directory are
collectively sorted and executed in lexical order, before binary or script
specified kdump_post parameter is executed.
Kdump Pre-Capture Executable
----------------------------
It is possible to specify a custom script or binary you wish to run before
capturing a vmcore. Exit status of this binary is interpreted:
0 - continue with dump process as usual
non 0 - run the final action (reboot/poweroff/halt)
If /etc/kdump/pre.d directory exists, all files in the directory are collectively
sorted and executed in lexical order, after binary or script specified
kdump_pre parameter is executed.
Even if the binary or script in /etc/kdump/pre.d directory returns non 0
exit status, the processing is continued.
Extra Binaries
--------------
If you have specific binaries or scripts you want to have made available
within your kdump initrd, you can specify them by their full path, and they
will be included in your kdump initrd, along with all dependent libraries.
This may be particularly useful for those running post-capture scripts that
rely on other binaries.
Extra Modules
-------------
By default, only the bare minimum of kernel modules will be included in your
kdump initrd. Should you wish to capture your vmcore files to a non-boot-path
storage device, such as an iscsi target disk or clustered file system, you may
need to manually specify additional kernel modules to load into your kdump
initrd.
Failure action
--------------
Failure action specifies what to do when dump to configured dump target
fails. By default, failure action is "reboot" and that is system reboots
if attempt to save dump to dump target fails.
There are other failure actions available though.
- dump_to_rootfs
This option tries to mount root and save dump on root filesystem
in a path specified by "path". This option will generally make
sense when dump target is not root filesystem. For example, if
dump is being saved over network using "ssh" then one can specify
failure action to "dump_to_rootfs" to try saving dump to root
filesystem if dump over network fails.
- shell
Drop into a shell session inside initramfs.
- halt
Halt system after failure
- poweroff
Poweroff system after failure.
Compression and filtering
-------------------------
The 'core_collector' parameter in kdump.conf allows you to specify a custom
dump capture method. The most common alternate method is makedumpfile, which
is a dump filtering and compression utility provided with kexec-tools. On
some architectures, it can drastically reduce the size of your vmcore files,
which becomes very useful on systems with large amounts of memory.
A typical setup is 'core_collector makedumpfile -F -l --message-level 1 -d 31',
but check the output of '/sbin/makedumpfile --help' for a list of all available
options (-i and -g don't need to be specified, they're automatically taken care
of). Note that use of makedumpfile requires that the kernel-debuginfo package
corresponding with your running kernel be installed.
Core collector command format depends on dump target type. Typically for
filesystem (local/remote), core_collector should accept two arguments.
First one is source file and second one is target file. For ex.
- ex1.
core_collector "cp --sparse=always"
Above will effectively be translated to:
cp --sparse=always /proc/vmcore <dest-path>/vmcore
- ex2.
core_collector "makedumpfile -l --message-level 1 -d 31"
Above will effectively be translated to:
makedumpfile -l --message-level 1 -d 31 /proc/vmcore <dest-path>/vmcore
For dump targets like raw and ssh, in general, core collector should expect
one argument (source file) and should output the processed core on standard
output (There is one exception of "scp", discussed later). This standard
output will be saved to destination using appropriate commands.
raw dumps core_collector examples:
- ex3.
core_collector "cat"
Above will effectively be translated to.
cat /proc/vmcore | dd of=<target-device>
- ex4.
core_collector "makedumpfile -F -l --message-level 1 -d 31"
Above will effectively be translated to.
makedumpfile -F -l --message-level 1 -d 31 | dd of=<target-device>
ssh dumps core_collector examples:
- ex5.
core_collector "cat"
Above will effectively be translated to.
cat /proc/vmcore | ssh <options> <remote-location> "dd of=path/vmcore"
- ex6.
core_collector "makedumpfile -F -l --message-level 1 -d 31"
Above will effectively be translated to.
makedumpfile -F -l --message-level 1 -d 31 | ssh <options> <remote-location> "dd of=path/vmcore"
There is one exception to standard output rule for ssh dumps. And that is
scp. As scp can handle ssh destinations for file transfers, one can
specify "scp" as core collector for ssh targets (no output on stdout).
- ex7.
core_collector "scp"
Above will effectively be translated to.
scp /proc/vmcore <user@host>:path/vmcore
About default core collector
----------------------------
Default core_collector for ssh/raw dump is:
"makedumpfile -F -l --message-level 1 -d 31".
Default core_collector for other targets is:
"makedumpfile -l --message-level 1 -d 31".
Even if core_collector option is commented out in kdump.conf, makedumpfile
is default core collector and kdump uses it internally.
If one does not want makedumpfile as default core_collector, then they
need to specify one using core_collector option to change the behavior.
Note: If "makedumpfile -F" is used then you will get a flattened format
vmcore.flat, you will need to use "makedumpfile -R" to rearrange the
dump data from stdard input to a normal dumpfile (readable with analysis
tools).
For example: "makedumpfile -R vmcore < vmcore.flat"
Caveats
=======
Console frame-buffers and X are not properly supported. If you typically run
with something along the lines of "vga=791" in your kernel config line or
have X running, console video will be garbled when a kernel is booted via
kexec. Note that the kdump kernel should still be able to create a dump,
and when the system reboots, video should be restored to normal.
Notes
=====
Notes on resetting video:
-------------------------
Video is a notoriously difficult issue with kexec. Video cards contain ROM code
that controls their initial configuration and setup. This code is nominally
accessed and executed from the Bios, and otherwise not safely executable. Since
the purpose of kexec is to reboot the system without re-executing the Bios, it
is rather difficult if not impossible to reset video cards with kexec. The
result is, that if a system crashes while running in a graphical mode (i.e.
running X), the screen may appear to become 'frozen' while the dump capture is
taking place. A serial console will of course reveal that the system is
operating and capturing a vmcore image, but a casual observer will see the
system as hung until the dump completes and a true reboot is executed.
There are two possiblilties to work around this issue. One is by adding
--reset-vga to the kexec command line options in /etc/sysconfig/kdump. This
tells kdump to write some reasonable default values to the video card register
file, in the hopes of returning it to a text mode such that boot messages are
visible on the screen. It does not work with all video cards however.
Secondly, it may be worth trying to add vga15fb.ko to the extra_modules list in
/etc/kdump.conf. This will attempt to use the video card in framebuffer mode,
which can blank the screen prior to the start of a dump capture.
Notes on rootfs mount
---------------------
Dracut is designed to mount rootfs by default. If rootfs mounting fails it
will refuse to go on. So kdump leaves rootfs mounting to dracut currently.
We make the assumtion that proper root= cmdline is being passed to dracut
initramfs for the time being. If you need modify "KDUMP_COMMANDLINE=" in
/etc/sysconfig/kdump, you will need to make sure that appropriate root=
options are copied from /proc/cmdline. In general it is best to append
command line options using "KDUMP_COMMANDLINE_APPEND=" instead of replacing
the original command line completely.
Notes on watchdog module handling
---------------------------------
If a watchdog is active in first kernel then, we must have it's module
loaded in crash kernel, so that either watchdog is deactivated or started
being kicked in second kernel. Otherwise, we might face watchdog reboot
when vmcore is being saved. When dracut watchdog module is enabled, it
installs kernel watchdog module of active watchdog device in initrd.
kexec-tools always add "-a watchdog" to the dracut_args if there exists at
least one active watchdog and user has not added specifically "-o watchdog"
in dracut_args of kdump.conf. If a watchdog module (such as hp_wdt) has
not been written in watchdog-core framework then this option will not have
any effect and module will not be added. Please note that only systemd
watchdog daemon is supported as watchdog kick application.
Notes for disk images
---------------------
Kdump initramfs is a critical component for capturing the crash dump.
But it's strictly generated for the machine it will run on, and have
no generality. If you install a new machine with a previous disk image
(eg. VMs created with disk image or snapshot), kdump could be broken
easily due to hardware changes or disk ID changes. So it's strongly
recommended to not include the kdump initramfs in the disk image in the
first place, this helps to save space, and kdumpctl will build the
initramfs automatically if it's missing. If you have already installed
a machine with a disk image which have kdump initramfs embedded, you
should rebuild the initramfs using "kdumpctl rebuild" command manually,
or else kdump may not work as expeceted.
Notes on encrypted dump target
------------------------------
Currently, kdump is not working well with encrypted dump target.
First, user have to give the password manually in capture kernel,
so a working interactive terminal is required in the capture kernel.
And another major issue is that an OOM problem will occur with certain
encryption setup. For example, the default setup for LUKS2 will use a
memory hard key derivation function to mitigate brute force attach,
it's impossible to reduce the memory usage for mounting the encrypted
target. In such case, you have to either reserved enough memory for
crash kernel according, or update your encryption setup.
It's recommanded to use a non-encrypted target (eg. remote target)
instead.
Notes on device dump
--------------------
Device dump allows drivers to append dump data to vmcore, so you can
collect driver specified debug info. The drivers could append the
data without any limit, and the data is stored in memory, this may
bring a significant memory stress. So device dump is disabled by default
by passing "novmcoredd" command line option to the kdump capture kernel.
If you want to collect debug data with device dump, you need to modify
"KDUMP_COMMANDLINE_APPEND=" value in /etc/sysconfig/kdump and remove the
"novmcoredd" option. You also need to increase the "crashkernel=" value
accordingly in case of OOM issue.
Besides, kdump initramfs won't automatically include the device drivers
which support device dump, only device drivers that are required for
the dump target setup will be included. To ensure the device dump data
will be included in the vmcore, you need to force include related
device drivers by using "extra_modules" option in /etc/kdump.conf
Parallel Dumping Operation
==========================
Kexec allows kdump using multiple cpus. So parallel feature can accelerate
dumping substantially, especially in executing compression and filter.
For example:
1."makedumpfile -c --num-threads [THREAD_NUM] /proc/vmcore dumpfile"
2."makedumpfile -c /proc/vmcore dumpfile",
1 has better performance than 2, if THREAD_NUM is larger than two
and the usable cpus number is larger than THREAD_NUM.
Notes on how to use multiple cpus on a capture kernel on x86 system:
Make sure that you are using a kernel that supports disable_cpu_apicid
kernel option as a capture kernel, which is needed to avoid x86 specific
hardware issue (*). The disable_cpu_apicid kernel option is automatically
appended by kdumpctl script and is ignored if the kernel doesn't support it.
You need to specify how many cpus to be used in a capture kernel by specifying
the number of cpus in nr_cpus kernel option in /etc/sysconfig/kdump. nr_cpus
is 1 at default.
You should use necessary and sufficient number of cpus on a capture kernel.
Warning: Don't use too many cpus on a capture kernel, or the capture kernel
may lead to panic due to Out Of Memory.
(*) Without disable_cpu_apicid kernel option, capture kernel may lead to
hang, system reset or power-off at boot, depending on your system and runtime
situation at the time of crash.
Debugging Tips
==============
- One can drop into a shell before/after saving vmcore with the help of
using kdump_pre/kdump_post hooks. Use following in one of the pre/post
scripts to drop into a shell.
#!/bin/bash
_ctty=/dev/ttyS0
setsid /bin/sh -i -l 0<>$_ctty 1<>$_ctty 2<>$_ctty
One might have to change the terminal depending on what they are using.
- Serial console logging for virtual machines
I generally use "virsh console <domain-name>" to get to serial console.
I noticed after dump saving system reboots and when grub menu shows up
some of the previously logged messages are no more there. That means
any important debugging info at the end will be lost.
One can log serial console as follows to make sure messages are not lost.
virsh ttyconsole <domain-name>
ln -s <name-of-tty> /dev/modem
minicom -C /tmp/console-logs
Now minicom should be logging serial console in file console-logs.

181
SOURCES/kexec-tools-2.0.20-Cleanup-move-it-back-from-util_lib-elf_info.c.patch Normal file
View File

@ -0,0 +1,181 @@
From a7c4cb8e998571cb3dd62e907935a1e052b15d6c Mon Sep 17 00:00:00 2001
From: Lianbo Jiang <lijiang@redhat.com>
Date: Fri, 23 Aug 2019 20:05:38 +0800
Subject: [PATCH 3/5] Cleanup: move it back from util_lib/elf_info.c
Some code related to vmcore-dmesg.c is put into the util_lib, which
is not very reasonable, so lets move it back and tidy up those code.
In addition, that will also help to limit the size of vmcore-dmesg.txt
in vmcore-dmesg.c instead of elf_info.c.
Signed-off-by: Lianbo Jiang <lijiang@redhat.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
util_lib/elf_info.c | 48 +++++++++----------------------------
util_lib/include/elf_info.h | 2 +-
vmcore-dmesg/vmcore-dmesg.c | 30 ++++++++++++++++++++++-
3 files changed, 41 insertions(+), 39 deletions(-)
diff --git a/util_lib/elf_info.c b/util_lib/elf_info.c
index 5d0efaafab53..2bce5cb1713c 100644
--- a/util_lib/elf_info.c
+++ b/util_lib/elf_info.c
@@ -531,19 +531,7 @@ static int32_t read_file_s32(int fd, uint64_t addr)
return read_file_u32(fd, addr);
}
-static void write_to_stdout(char *buf, unsigned int nr)
-{
- ssize_t ret;
-
- ret = write(STDOUT_FILENO, buf, nr);
- if (ret != nr) {
- fprintf(stderr, "Failed to write out the dmesg log buffer!:"
- " %s\n", strerror(errno));
- exit(54);
- }
-}
-
-static void dump_dmesg_legacy(int fd)
+static void dump_dmesg_legacy(int fd, void (*handler)(char*, unsigned int))
{
uint64_t log_buf, log_buf_offset;
unsigned log_end, logged_chars, log_end_wrapped;
@@ -604,7 +592,8 @@ static void dump_dmesg_legacy(int fd)
*/
logged_chars = log_end < log_buf_len ? log_end : log_buf_len;
- write_to_stdout(buf + (log_buf_len - logged_chars), logged_chars);
+ if (handler)
+ handler(buf + (log_buf_len - logged_chars), logged_chars);
}
static inline uint16_t struct_val_u16(char *ptr, unsigned int offset)
@@ -623,7 +612,7 @@ static inline uint64_t struct_val_u64(char *ptr, unsigned int offset)
}
/* Read headers of log records and dump accordingly */
-static void dump_dmesg_structured(int fd)
+static void dump_dmesg_structured(int fd, void (*handler)(char*, unsigned int))
{
#define OUT_BUF_SIZE 4096
uint64_t log_buf, log_buf_offset, ts_nsec;
@@ -733,7 +722,8 @@ static void dump_dmesg_structured(int fd)
out_buf[len++] = c;
if (len >= OUT_BUF_SIZE - 64) {
- write_to_stdout(out_buf, len);
+ if (handler)
+ handler(out_buf, len);
len = 0;
}
}
@@ -752,16 +742,16 @@ static void dump_dmesg_structured(int fd)
current_idx += loglen;
}
free(buf);
- if (len)
- write_to_stdout(out_buf, len);
+ if (len && handler)
+ handler(out_buf, len);
}
-static void dump_dmesg(int fd)
+void dump_dmesg(int fd, void (*handler)(char*, unsigned int))
{
if (log_first_idx_vaddr)
- dump_dmesg_structured(fd);
+ dump_dmesg_structured(fd, handler);
else
- dump_dmesg_legacy(fd);
+ dump_dmesg_legacy(fd, handler);
}
int read_elf(int fd)
@@ -808,22 +798,6 @@ int read_elf(int fd)
return 0;
}
-int read_elf_vmcore(int fd)
-{
- int ret;
-
- ret = read_elf(fd);
- if (ret > 0) {
- fprintf(stderr, "Unable to read ELF information"
- " from vmcore\n");
- return ret;
- }
-
- dump_dmesg(fd);
-
- return 0;
-}
-
int read_phys_offset_elf_kcore(int fd, unsigned long *phys_off)
{
int ret;
diff --git a/util_lib/include/elf_info.h b/util_lib/include/elf_info.h
index c328a1b0ecf2..4bc9279ba603 100644
--- a/util_lib/include/elf_info.h
+++ b/util_lib/include/elf_info.h
@@ -30,6 +30,6 @@ int get_pt_load(int idx,
unsigned long long *virt_end);
int read_phys_offset_elf_kcore(int fd, unsigned long *phys_off);
int read_elf(int fd);
-int read_elf_vmcore(int fd);
+void dump_dmesg(int fd, void (*handler)(char*, unsigned int));
#endif /* ELF_INFO_H */
diff --git a/vmcore-dmesg/vmcore-dmesg.c b/vmcore-dmesg/vmcore-dmesg.c
index bebc348a657e..fe7df8ec372c 100644
--- a/vmcore-dmesg/vmcore-dmesg.c
+++ b/vmcore-dmesg/vmcore-dmesg.c
@@ -5,6 +5,34 @@ typedef Elf32_Nhdr Elf_Nhdr;
extern const char *fname;
+static void write_to_stdout(char *buf, unsigned int nr)
+{
+ ssize_t ret;
+
+ ret = write(STDOUT_FILENO, buf, nr);
+ if (ret != nr) {
+ fprintf(stderr, "Failed to write out the dmesg log buffer!:"
+ " %s\n", strerror(errno));
+ exit(54);
+ }
+}
+
+static int read_vmcore_dmesg(int fd, void (*handler)(char*, unsigned int))
+{
+ int ret;
+
+ ret = read_elf(fd);
+ if (ret > 0) {
+ fprintf(stderr, "Unable to read ELF information"
+ " from vmcore\n");
+ return ret;
+ }
+
+ dump_dmesg(fd, handler);
+
+ return 0;
+}
+
int main(int argc, char **argv)
{
ssize_t ret;
@@ -23,7 +51,7 @@ int main(int argc, char **argv)
return 2;
}
- ret = read_elf_vmcore(fd);
+ ret = read_vmcore_dmesg(fd, write_to_stdout);
close(fd);
--
2.17.1

84
SOURCES/kexec-tools-2.0.20-Cleanup-remove-the-read_elf_kcore.patch Normal file
View File

@ -0,0 +1,84 @@
From 545c811050a375f79e0fa0e107cb35b9ae3a1599 Mon Sep 17 00:00:00 2001
From: Lianbo Jiang <lijiang@redhat.com>
Date: Fri, 23 Aug 2019 20:05:36 +0800
Subject: [PATCH 1/5] Cleanup: remove the read_elf_kcore()
Here, no need to wrap the read_elf() again, lets invoke it directly.
So remove the read_elf_kcore() and clean up redundant code.
Signed-off-by: Lianbo Jiang <lijiang@redhat.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
kexec/arch/arm64/kexec-arm64.c | 2 +-
util_lib/elf_info.c | 15 ++-------------
util_lib/include/elf_info.h | 2 +-
3 files changed, 4 insertions(+), 15 deletions(-)
diff --git a/kexec/arch/arm64/kexec-arm64.c b/kexec/arch/arm64/kexec-arm64.c
index eb3a3a37307c..6ad3b0a134b3 100644
--- a/kexec/arch/arm64/kexec-arm64.c
+++ b/kexec/arch/arm64/kexec-arm64.c
@@ -889,7 +889,7 @@ int get_phys_base_from_pt_load(unsigned long *phys_offset)
return EFAILED;
}
- read_elf_kcore(fd);
+ read_elf(fd);
for (i = 0; get_pt_load(i,
&phys_start, NULL, &virt_start, NULL);
diff --git a/util_lib/elf_info.c b/util_lib/elf_info.c
index 90a3b21662e7..d9397ecd8626 100644
--- a/util_lib/elf_info.c
+++ b/util_lib/elf_info.c
@@ -764,7 +764,7 @@ static void dump_dmesg(int fd)
dump_dmesg_legacy(fd);
}
-static int read_elf(int fd)
+int read_elf(int fd)
{
int ret;
@@ -824,24 +824,13 @@ int read_elf_vmcore(int fd)
return 0;
}
-int read_elf_kcore(int fd)
-{
- int ret;
-
- ret = read_elf(fd);
- if (ret != 0)
- return ret;
-
- return 0;
-}
-
int read_phys_offset_elf_kcore(int fd, unsigned long *phys_off)
{
int ret;
*phys_off = UINT64_MAX;
- ret = read_elf_kcore(fd);
+ ret = read_elf(fd);
if (!ret) {
/* If we have a valid 'PHYS_OFFSET' by now,
* return it to the caller now.
diff --git a/util_lib/include/elf_info.h b/util_lib/include/elf_info.h
index 1a4debd2d4ba..c328a1b0ecf2 100644
--- a/util_lib/include/elf_info.h
+++ b/util_lib/include/elf_info.h
@@ -29,7 +29,7 @@ int get_pt_load(int idx,
unsigned long long *virt_start,
unsigned long long *virt_end);
int read_phys_offset_elf_kcore(int fd, unsigned long *phys_off);
-int read_elf_kcore(int fd);
+int read_elf(int fd);
int read_elf_vmcore(int fd);
#endif /* ELF_INFO_H */
--
2.17.1

47
SOURCES/kexec-tools-2.0.20-Fix-an-error-definition-about-the-variable-fname.patch Normal file
View File

@ -0,0 +1,47 @@
From 14ad054e7baa788a6629385ffe5e0f1996b7de02 Mon Sep 17 00:00:00 2001
From: Lianbo Jiang <lijiang@redhat.com>
Date: Fri, 23 Aug 2019 20:05:37 +0800
Subject: [PATCH 2/5] Fix an error definition about the variable 'fname'
The variable 'fname' is mistakenly defined two twice, the first definition
is in the vmcore-dmesg.c, and the second definition is in the elf_info.c.
That is confused and incorrect although it's a static type, because the
value of variable 'fname' is not assigned(set) in elf_info.c. Anyway, its
value will be always 'null' when printing an error information.
Signed-off-by: Lianbo Jiang <lijiang@redhat.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
util_lib/elf_info.c | 2 +-
vmcore-dmesg/vmcore-dmesg.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/util_lib/elf_info.c b/util_lib/elf_info.c
index d9397ecd8626..5d0efaafab53 100644
--- a/util_lib/elf_info.c
+++ b/util_lib/elf_info.c
@@ -20,7 +20,7 @@
/* The 32bit and 64bit note headers make it clear we don't care */
typedef Elf32_Nhdr Elf_Nhdr;
-static const char *fname;
+const char *fname;
static Elf64_Ehdr ehdr;
static Elf64_Phdr *phdr;
static int num_pt_loads;
diff --git a/vmcore-dmesg/vmcore-dmesg.c b/vmcore-dmesg/vmcore-dmesg.c
index 7a386b380291..bebc348a657e 100644
--- a/vmcore-dmesg/vmcore-dmesg.c
+++ b/vmcore-dmesg/vmcore-dmesg.c
@@ -3,7 +3,7 @@
/* The 32bit and 64bit note headers make it clear we don't care */
typedef Elf32_Nhdr Elf_Nhdr;
-static const char *fname;
+extern const char *fname;
int main(int argc, char **argv)
{
--
2.17.1

55
SOURCES/kexec-tools-2.0.20-Limit-the-size-of-vmcore-dmesg.txt-to-2G.patch Normal file
View File

@ -0,0 +1,55 @@
From fa3f0ed47f3e6dbee485722d13713ad495571b7e Mon Sep 17 00:00:00 2001
From: Lianbo Jiang <lijiang@redhat.com>
Date: Fri, 23 Aug 2019 20:05:39 +0800
Subject: [PATCH 4/5] Limit the size of vmcore-dmesg.txt to 2G
With some corrupted vmcore files, the vmcore-dmesg.txt file may grow
forever till the kdump disk becomes full, and also probably causes
the disk error messages as follow:
...
sd 0:0:0:0: [sda] tag#6 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK
sd 0:0:0:0: [sda] tag#6 CDB: Read(10) 28 00 08 06 4c 98 00 00 08 00
blk_update_request: I/O error, dev sda, sector 134630552
sd 0:0:0:0: [sda] tag#7 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK
sd 0:0:0:0: [sda] tag#7 CDB: Read(10) 28 00 08 06 4c 98 00 00 08 00
blk_update_request: I/O error, dev sda, sector 134630552
...
If vmcore-dmesg.txt occupies the whole disk, the vmcore can not be
saved, this is also a problem.
Lets limit the size of vmcore-dmesg.txt to avoid such problems.
Signed-off-by: Lianbo Jiang <lijiang@redhat.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
vmcore-dmesg/vmcore-dmesg.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/vmcore-dmesg/vmcore-dmesg.c b/vmcore-dmesg/vmcore-dmesg.c
index fe7df8ec372c..81c2a58c9d86 100644
--- a/vmcore-dmesg/vmcore-dmesg.c
+++ b/vmcore-dmesg/vmcore-dmesg.c
@@ -5,9 +5,19 @@ typedef Elf32_Nhdr Elf_Nhdr;
extern const char *fname;
+/* stole this macro from kernel printk.c */
+#define LOG_BUF_LEN_MAX (uint32_t)(1 << 31)
+
static void write_to_stdout(char *buf, unsigned int nr)
{
ssize_t ret;
+ static uint32_t n_bytes = 0;
+
+ n_bytes += nr;
+ if (n_bytes > LOG_BUF_LEN_MAX) {
+ fprintf(stderr, "The vmcore-dmesg.txt over 2G in size is not supported.\n");
+ exit(53);
+ }
ret = write(STDOUT_FILENO, buf, nr);
if (ret != nr) {
--
2.17.1

82
SOURCES/kexec-tools-2.0.20-arm64-kdump-deal-with-a-lot-of-resource-entries-in-p.patch Normal file
View File

@ -0,0 +1,82 @@
From 2572b8d702e452624bdb8d7b7c39f458e7dcf2ce Mon Sep 17 00:00:00 2001
From: AKASHI Takahiro <takahiro.akashi@linaro.org>
Date: Wed, 18 Dec 2019 11:42:32 -0500
Subject: [PATCH 3/3] arm64: kdump: deal with a lot of resource entries in
/proc/iomem
As described in the commit ("arm64: kexec: allocate memory space avoiding
reserved regions"), /proc/iomem now has a lot of "reserved" entries, and
it's not just enough to have a fixed size of memory range array.
With this patch, kdump is allowed to handle arbitrary number of memory
ranges, using mem_regions_alloc_and_xxx() functions.
Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Tested-by: Bhupesh Sharma <bhsharma@redhat.com>
Tested-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
kexec/arch/arm64/crashdump-arm64.c | 25 ++++++++++---------------
1 file changed, 10 insertions(+), 15 deletions(-)
diff --git a/kexec/arch/arm64/crashdump-arm64.c b/kexec/arch/arm64/crashdump-arm64.c
index 4fd7aa8fd43c..38d1a0f3000d 100644
--- a/kexec/arch/arm64/crashdump-arm64.c
+++ b/kexec/arch/arm64/crashdump-arm64.c
@@ -23,13 +23,8 @@
#include "kexec-elf.h"
#include "mem_regions.h"
-/* memory ranges on crashed kernel */
-static struct memory_range system_memory_ranges[CRASH_MAX_MEMORY_RANGES];
-static struct memory_ranges system_memory_rgns = {
- .size = 0,
- .max_size = CRASH_MAX_MEMORY_RANGES,
- .ranges = system_memory_ranges,
-};
+/* memory ranges of crashed kernel */
+static struct memory_ranges system_memory_rgns;
/* memory range reserved for crashkernel */
struct memory_range crash_reserved_mem;
@@ -82,7 +77,7 @@ static uint64_t get_kernel_page_offset(void)
*
* This function is called once for each memory region found in /proc/iomem.
* It locates system RAM and crashkernel reserved memory and places these to
- * variables, respectively, system_memory_ranges and crash_reserved_mem.
+ * variables, respectively, system_memory_rgns and usablemem_rgns.
*/
static int iomem_range_callback(void *UNUSED(data), int UNUSED(nr),
@@ -90,11 +85,11 @@ static int iomem_range_callback(void *UNUSED(data), int UNUSED(nr),
unsigned long long length)
{
if (strncmp(str, CRASH_KERNEL, strlen(CRASH_KERNEL)) == 0)
- return mem_regions_add(&usablemem_rgns,
- base, length, RANGE_RAM);
+ return mem_regions_alloc_and_add(&usablemem_rgns,
+ base, length, RANGE_RAM);
else if (strncmp(str, SYSTEM_RAM, strlen(SYSTEM_RAM)) == 0)
- return mem_regions_add(&system_memory_rgns,
- base, length, RANGE_RAM);
+ return mem_regions_alloc_and_add(&system_memory_rgns,
+ base, length, RANGE_RAM);
else if (strncmp(str, KERNEL_CODE, strlen(KERNEL_CODE)) == 0)
elf_info.kern_paddr_start = base;
else if (strncmp(str, KERNEL_DATA, strlen(KERNEL_DATA)) == 0)
@@ -135,9 +130,9 @@ static int crash_get_memory_ranges(void)
dbgprint_mem_range("Reserved memory range", &crash_reserved_mem, 1);
- if (mem_regions_exclude(&system_memory_rgns, &crash_reserved_mem)) {
- fprintf(stderr,
- "Error: Number of crash memory ranges excedeed the max limit\n");
+ if (mem_regions_alloc_and_exclude(&system_memory_rgns,
+ &crash_reserved_mem)) {
+ fprintf(stderr, "Cannot allocate memory for ranges\n");
return -ENOMEM;
}
--
2.7.4

248
SOURCES/kexec-tools-2.0.20-arm64-kexec-allocate-memory-space-avoiding-reserved-.patch Normal file
View File

@ -0,0 +1,248 @@
From f736104f533290b4ce6fbfbca74abde9ffd3888c Mon Sep 17 00:00:00 2001
From: AKASHI Takahiro <takahiro.akashi@linaro.org>
Date: Wed, 18 Dec 2019 11:42:31 -0500
Subject: [PATCH 2/3] arm64: kexec: allocate memory space avoiding reserved
regions
On UEFI/ACPI-only system, some memory regions, including but not limited
to UEFI memory map and ACPI tables, must be preserved across kexec'ing.
Otherwise, they can be corrupted and result in early failure in booting
a new kernel.
In recent kernels, /proc/iomem now has an extended file format like:
40000000-5871ffff : System RAM
41800000-426affff : Kernel code
426b0000-42aaffff : reserved
42ab0000-42c64fff : Kernel data
54400000-583fffff : Crash kernel
58590000-585effff : reserved
58700000-5871ffff : reserved
58720000-58b5ffff : reserved
58b60000-5be3ffff : System RAM
58b61000-58b61fff : reserved
where the "reserved" entries at the top level or under System RAM (and
its descendant resources) are ones of such kind and should not be regarded
as usable memory ranges where several free spaces for loading kexec data
will be allocated.
With this patch, get_memory_ranges() will handle this format of file
correctly. Note that, for safety, unknown regions, in addition to
"reserved" ones, will also be excluded.
Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Tested-by: Bhupesh Sharma <bhsharma@redhat.com>
Tested-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
kexec/arch/arm64/kexec-arm64.c | 153 +++++++++++++++++++++++++----------------
1 file changed, 94 insertions(+), 59 deletions(-)
diff --git a/kexec/arch/arm64/kexec-arm64.c b/kexec/arch/arm64/kexec-arm64.c
index 6ad3b0a134b3..45ebc54a9b6f 100644
--- a/kexec/arch/arm64/kexec-arm64.c
+++ b/kexec/arch/arm64/kexec-arm64.c
@@ -10,7 +10,9 @@
#include <inttypes.h>
#include <libfdt.h>
#include <limits.h>
+#include <stdio.h>
#include <stdlib.h>
+#include <string.h>
#include <sys/stat.h>
#include <linux/elf-em.h>
#include <elf.h>
@@ -29,6 +31,7 @@
#include "fs2dt.h"
#include "iomem.h"
#include "kexec-syscall.h"
+#include "mem_regions.h"
#include "arch/options.h"
#define ROOT_NODE_ADDR_CELLS_DEFAULT 1
@@ -905,19 +908,33 @@ int get_phys_base_from_pt_load(unsigned long *phys_offset)
return 0;
}
+static bool to_be_excluded(char *str)
+{
+ if (!strncmp(str, SYSTEM_RAM, strlen(SYSTEM_RAM)) ||
+ !strncmp(str, KERNEL_CODE, strlen(KERNEL_CODE)) ||
+ !strncmp(str, KERNEL_DATA, strlen(KERNEL_DATA)) ||
+ !strncmp(str, CRASH_KERNEL, strlen(CRASH_KERNEL)))
+ return false;
+ else
+ return true;
+}
+
/**
- * get_memory_ranges_iomem_cb - Helper for get_memory_ranges_iomem.
+ * get_memory_ranges - Try to get the memory ranges from
+ * /proc/iomem.
*/
-
-static int get_memory_ranges_iomem_cb(void *data, int nr, char *str,
- unsigned long long base, unsigned long long length)
+int get_memory_ranges(struct memory_range **range, int *ranges,
+ unsigned long kexec_flags)
{
- int ret;
unsigned long phys_offset = UINT64_MAX;
- struct memory_range *r;
-
- if (nr >= KEXEC_SEGMENT_MAX)
- return -1;
+ FILE *fp;
+ const char *iomem = proc_iomem();
+ char line[MAX_LINE], *str;
+ unsigned long long start, end;
+ int n, consumed;
+ struct memory_ranges memranges;
+ struct memory_range *last, excl_range;
+ int ret;
if (!try_read_phys_offset_from_kcore) {
/* Since kernel version 4.19, 'kcore' contains
@@ -951,17 +968,72 @@ static int get_memory_ranges_iomem_cb(void *data, int nr, char *str,
try_read_phys_offset_from_kcore = true;
}
- r = (struct memory_range *)data + nr;
+ fp = fopen(iomem, "r");
+ if (!fp)
+ die("Cannot open %s\n", iomem);
+
+ memranges.ranges = NULL;
+ memranges.size = memranges.max_size = 0;
+
+ while (fgets(line, sizeof(line), fp) != 0) {
+ n = sscanf(line, "%llx-%llx : %n", &start, &end, &consumed);
+ if (n != 2)
+ continue;
+ str = line + consumed;
+
+ if (!strncmp(str, SYSTEM_RAM, strlen(SYSTEM_RAM))) {
+ ret = mem_regions_alloc_and_add(&memranges,
+ start, end - start + 1, RANGE_RAM);
+ if (ret) {
+ fprintf(stderr,
+ "Cannot allocate memory for ranges\n");
+ fclose(fp);
+ return -ENOMEM;
+ }
- if (!strncmp(str, SYSTEM_RAM, strlen(SYSTEM_RAM)))
- r->type = RANGE_RAM;
- else if (!strncmp(str, IOMEM_RESERVED, strlen(IOMEM_RESERVED)))
- r->type = RANGE_RESERVED;
- else
- return 1;
+ dbgprintf("%s:+[%d] %016llx - %016llx\n", __func__,
+ memranges.size - 1,
+ memranges.ranges[memranges.size - 1].start,
+ memranges.ranges[memranges.size - 1].end);
+ } else if (to_be_excluded(str)) {
+ if (!memranges.size)
+ continue;
+
+ /*
+ * Note: mem_regions_exclude() doesn't guarantee
+ * that the ranges are sorted out, but as long as
+ * we cope with /proc/iomem, we only operate on
+ * the last entry and so it is safe.
+ */
- r->start = base;
- r->end = base + length - 1;
+ /* The last System RAM range */
+ last = &memranges.ranges[memranges.size - 1];
+
+ if (last->end < start)
+ /* New resource outside of System RAM */
+ continue;
+ if (end < last->start)
+ /* Already excluded by parent resource */
+ continue;
+
+ excl_range.start = start;
+ excl_range.end = end;
+ ret = mem_regions_alloc_and_exclude(&memranges, &excl_range);
+ if (ret) {
+ fprintf(stderr,
+ "Cannot allocate memory for ranges (exclude)\n");
+ fclose(fp);
+ return -ENOMEM;
+ }
+ dbgprintf("%s:- %016llx - %016llx\n",
+ __func__, start, end);
+ }
+ }
+
+ fclose(fp);
+
+ *range = memranges.ranges;
+ *ranges = memranges.size;
/* As a fallback option, we can try determining the PHYS_OFFSET
* value from the '/proc/iomem' entries as well.
@@ -982,52 +1054,15 @@ static int get_memory_ranges_iomem_cb(void *data, int nr, char *str,
* between the user-space and kernel space 'PHYS_OFFSET'
* value.
*/
- set_phys_offset(r->start, "iomem");
-
- dbgprintf("%s: %016llx - %016llx : %s", __func__, r->start,
- r->end, str);
-
- return 0;
-}
-
-/**
- * get_memory_ranges_iomem - Try to get the memory ranges from
- * /proc/iomem.
- */
+ if (memranges.size)
+ set_phys_offset(memranges.ranges[0].start, "iomem");
-static int get_memory_ranges_iomem(struct memory_range *array,
- unsigned int *count)
-{
- *count = kexec_iomem_for_each_line(NULL,
- get_memory_ranges_iomem_cb, array);
-
- if (!*count) {
- dbgprintf("%s: failed: No RAM found.\n", __func__);
- return EFAILED;
- }
+ dbgprint_mem_range("System RAM ranges;",
+ memranges.ranges, memranges.size);
return 0;
}
-/**
- * get_memory_ranges - Try to get the memory ranges some how.
- */
-
-int get_memory_ranges(struct memory_range **range, int *ranges,
- unsigned long kexec_flags)
-{
- static struct memory_range array[KEXEC_SEGMENT_MAX];
- unsigned int count;
- int result;
-
- result = get_memory_ranges_iomem(array, &count);
-
- *range = result ? NULL : array;
- *ranges = result ? 0 : count;
-
- return result;
-}
-
int arch_compat_trampoline(struct kexec_info *info)
{
return 0;
--
2.7.4

89
SOURCES/kexec-tools-2.0.20-kexec-add-variant-helper-functions-for-handling-memo.patch Normal file
View File

@ -0,0 +1,89 @@
From cf977b1af9ec67fabcc6a625589c49c52d07b11d Mon Sep 17 00:00:00 2001
From: AKASHI Takahiro <takahiro.akashi@linaro.org>
Date: Wed, 18 Dec 2019 11:42:30 -0500
Subject: [PATCH 1/3] kexec: add variant helper functions for handling memory
regions
mem_regions_alloc_and_add() and mem_regions_alloc_and_exclude() are
functionally equivalent to, respectively, mem_regions_add() and
mem_regions_exclude() except the formers will re-allocate memory
dynamically when no more entries are available in 'ranges' array.
Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Tested-by: Bhupesh Sharma <bhsharma@redhat.com>
Tested-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
kexec/mem_regions.c | 42 ++++++++++++++++++++++++++++++++++++++++++
kexec/mem_regions.h | 7 +++++++
2 files changed, 49 insertions(+)
diff --git a/kexec/mem_regions.c b/kexec/mem_regions.c
index 50c8abccb93a..ad7d3f13fd84 100644
--- a/kexec/mem_regions.c
+++ b/kexec/mem_regions.c
@@ -125,3 +125,45 @@ int mem_regions_exclude(struct memory_ranges *ranges,
}
return 0;
}
+
+#define KEXEC_MEMORY_RANGES 16
+
+int mem_regions_alloc_and_add(struct memory_ranges *ranges,
+ unsigned long long base,
+ unsigned long long length, int type)
+{
+ void *new_ranges;
+
+ if (ranges->size >= ranges->max_size) {
+ new_ranges = realloc(ranges->ranges,
+ sizeof(struct memory_range) *
+ (ranges->max_size + KEXEC_MEMORY_RANGES));
+ if (!new_ranges)
+ return -1;
+
+ ranges->ranges = new_ranges;
+ ranges->max_size += KEXEC_MEMORY_RANGES;
+ }
+
+ return mem_regions_add(ranges, base, length, type);
+}
+
+int mem_regions_alloc_and_exclude(struct memory_ranges *ranges,
+ const struct memory_range *range)
+{
+ void *new_ranges;
+
+ /* for safety, we should have at least one free entry in ranges */
+ if (ranges->size >= ranges->max_size) {
+ new_ranges = realloc(ranges->ranges,
+ sizeof(struct memory_range) *
+ (ranges->max_size + KEXEC_MEMORY_RANGES));
+ if (!new_ranges)
+ return -1;
+
+ ranges->ranges = new_ranges;
+ ranges->max_size += KEXEC_MEMORY_RANGES;
+ }
+
+ return mem_regions_exclude(ranges, range);
+}
diff --git a/kexec/mem_regions.h b/kexec/mem_regions.h
index ae9e972b0206..e306d67e3261 100644
--- a/kexec/mem_regions.h
+++ b/kexec/mem_regions.h
@@ -12,4 +12,11 @@ int mem_regions_exclude(struct memory_ranges *ranges,
int mem_regions_add(struct memory_ranges *ranges, unsigned long long base,
unsigned long long length, int type);
+int mem_regions_alloc_and_exclude(struct memory_ranges *ranges,
+ const struct memory_range *range);
+
+int mem_regions_alloc_and_add(struct memory_ranges *ranges,
+ unsigned long long base,
+ unsigned long long length, int type);
+
#endif
--
2.7.4

36
SOURCES/kexec-tools-2.0.20-makedumpfile-PATCH-Align-PMD_SECTION_MASK-with-PHYS_MASK.patch Normal file
View File

@ -0,0 +1,36 @@
From 7242ae4cb5288df626f464ced0a8b60fd669100b Mon Sep 17 00:00:00 2001
From: Michal Suchanek <msuchanek@suse.de>
Date: Mon, 16 Mar 2020 19:39:58 +0100
Subject: [PATCH 6/7] [PATCH] Align PMD_SECTION_MASK with PHYS_MASK
Reportedly on some arm64 systems makedumpfile loops forever exhausting
all memory when filtering kernel core. It turns out the reason is it
cannot resolve some addresses because the PMD mask is wrong. When
physical address mask allows up to 48bits pmd mask should allow the
same.
I suppose you would need a system that needs physical addresses over 1TB
to be able to reproduce this. This may be either because you have a lot
of memory or because the firmware mapped some memory above 1TB for some
reason.
Signed-off-by: Michal Suchanek <msuchanek@suse.de>
---
arch/arm64.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/makedumpfile-1.6.7/arch/arm64.c b/makedumpfile-1.6.7/arch/arm64.c
index 43164cc..54d60b4 100644
--- a/makedumpfile-1.6.7/arch/arm64.c
+++ b/makedumpfile-1.6.7/arch/arm64.c
@@ -81,7 +81,7 @@ static unsigned long kimage_voffset;
* Remove the highest order bits that are not a part of the
* physical address in a section
*/
-#define PMD_SECTION_MASK ((1UL << 40) - 1)
+#define PMD_SECTION_MASK ((1UL << PHYS_MASK_SHIFT) - 1)
#define PMD_TYPE_MASK 3
#define PMD_TYPE_SECT 1
--
2.7.5

80
SOURCES/kexec-tools-2.0.20-makedumpfile-PATCH-Avoid-false-positive-failure-in-mem_seciton-va.patch Normal file
View File

@ -0,0 +1,80 @@
From 81b79c514ff6fc881f1df4cb04ecb2d7cb22badc Mon Sep 17 00:00:00 2001
From: Kazuhito Hagio <k-hagio-ab@nec.com>
Date: Wed, 19 Feb 2020 12:48:13 -0500
Subject: [PATCH] [PATCH] Avoid false-positive failure in mem_seciton
validation
Currently in get_mem_section(), we check whether SYMBOL(mem_section)
is a pointer to the array or a pointer to the pointer to the array
for some cases.
However, with commit e113f1c974c8 ("[PATCH] cope with not-present
mem section") relaxing the check, there was a report that the function
failed because both of two validate_mem_section() calls return TRUE.
Avoid the false-positive failure by not calling the second one if the
first one returns TRUE.
Reported-by: Pingfan Liu <piliu@redhat.com>
Acked-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Signed-off-by: Kazuhito Hagio <k-hagio-ab@nec.com>
---
makedumpfile.c | 29 ++++++-----------------------
1 file changed, 6 insertions(+), 23 deletions(-)
diff --git a/makedumpfile-1.6.7/makedumpfile.c b/makedumpfile-1.6.7/makedumpfile.c
index f5860a1..4c4251e 100644
--- a/makedumpfile-1.6.7/makedumpfile.c
+++ b/makedumpfile-1.6.7/makedumpfile.c
@@ -3472,7 +3472,6 @@ static int
get_mem_section(unsigned int mem_section_size, unsigned long *mem_maps,
unsigned int num_section)
{
- unsigned long mem_section_ptr;
int ret = FALSE;
unsigned long *mem_sec = NULL;
@@ -3484,34 +3483,18 @@ get_mem_section(unsigned int mem_section_size, unsigned long *mem_maps,
ret = validate_mem_section(mem_sec, SYMBOL(mem_section),
mem_section_size, mem_maps, num_section);
- if (is_sparsemem_extreme()) {
- int symbol_valid = ret;
- int pointer_valid;
- int mem_maps_size = sizeof(*mem_maps) * num_section;
- unsigned long *mem_maps_ex = NULL;
+ if (!ret && is_sparsemem_extreme()) {
+ unsigned long mem_section_ptr;
+
if (!readmem(VADDR, SYMBOL(mem_section), &mem_section_ptr,
sizeof(mem_section_ptr)))
goto out;
- if ((mem_maps_ex = malloc(mem_maps_size)) == NULL) {
- ERRMSG("Can't allocate memory for the mem_maps. %s\n",
- strerror(errno));
- goto out;
- }
+ ret = validate_mem_section(mem_sec, mem_section_ptr,
+ mem_section_size, mem_maps, num_section);
- pointer_valid = validate_mem_section(mem_sec,
- mem_section_ptr,
- mem_section_size,
- mem_maps_ex,
- num_section);
- if (pointer_valid)
- memcpy(mem_maps, mem_maps_ex, mem_maps_size);
- if (mem_maps_ex)
- free(mem_maps_ex);
- ret = symbol_valid ^ pointer_valid;
- if (!ret) {
+ if (!ret)
ERRMSG("Could not validate mem_section.\n");
- }
}
out:
if (mem_sec != NULL)
--
2.7.5

42
SOURCES/kexec-tools-2.0.20-makedumpfile-PATCH-Fix-cd_header-offset-overflow-with-large-pfn.patch Normal file
View File

@ -0,0 +1,42 @@
From 6e4b2dfaed5e5e5c617e0e45f969c1f571c13e27 Mon Sep 17 00:00:00 2001
From: Jialong Chen <chenjialong@huawei.com>
Date: Mon, 23 Mar 2020 16:42:01 -0400
Subject: [PATCH 7/7] [PATCH] Fix cd_header offset overflow with large pfn
In function write_kdump_pages_and_bitmap_cyclic(), cd_header->offset is
calculated by the following formula:
cd_header->offset
= (DISKDUMP_HEADER_BLOCKS + dh->sub_hdr_size + dh->bitmap_blocks)
* dh->block_size;
However, the variables of the right side are only int and unsigned int,
so if dh->bitmap_blocks is very large, it causes an interger overflow.
As a result, makedumpfile created a broken vmcore in a system with a
physical address range from 0x602770ecf000 to 0x6027ffffffff, and the
crash utility failed during session initialization, ending with the
error message "crash: vmlinux and vmcore do not match!".
Signed-off-by: Jialong Chen <chenjialong@huawei.com>
Signed-off-by: Kazuhito Hagio <k-hagio-ab@nec.com>
---
diskdump_mod.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/makedumpfile-1.6.7/diskdump_mod.h b/makedumpfile-1.6.7/diskdump_mod.h
index 2676817..3733953 100644
--- a/makedumpfile-1.6.7/diskdump_mod.h
+++ b/makedumpfile-1.6.7/diskdump_mod.h
@@ -22,7 +22,7 @@
#define DISK_DUMP_SIGNATURE "DISKDUMP"
#define KDUMP_SIGNATURE "KDUMP "
#define SIG_LEN (sizeof(DUMP_PARTITION_SIGNATURE) - 1)
-#define DISKDUMP_HEADER_BLOCKS (1)
+#define DISKDUMP_HEADER_BLOCKS (1UL)
/*
* These are all remnants of the old "diskdump" facility,
--
2.7.5

255
SOURCES/kexec-tools-2.0.20-makedumpfile-PATCH-Introduce-check-params-option.patch Normal file
View File

@ -0,0 +1,255 @@
From 989152e113bfcb4fbfbad6f3aed6f43be4455919 Mon Sep 17 00:00:00 2001
From: Kazuhito Hagio <k-hagio-ab@nec.com>
Date: Tue, 25 Feb 2020 16:04:55 -0500
Subject: [PATCH 4/7] [PATCH] Introduce --check-params option
Currently it's difficult to check whether a makedumpfile command-line
is valid or not without an actual panic. This is inefficient and if
a wrong configuration is not tested, you will miss the vmcore when an
actual panic occurs.
In order for kdump facilities like kexec-tools to be able to check
the specified command-line parameters in advance, introduce the
--check-params option that only checks them and exits immediately.
Signed-off-by: Kazuhito Hagio <k-hagio-ab@nec.com>
---
makedumpfile.8 | 5 ++++
makedumpfile.c | 75 +++++++++++++++++++++++++++++++++++++++++++++-------------
makedumpfile.h | 2 ++
print_info.c | 4 ++++
4 files changed, 69 insertions(+), 17 deletions(-)
diff --git a/makedumpfile-1.6.7/makedumpfile.8 b/makedumpfile-1.6.7/makedumpfile.8
index bf156a8..c5d4806 100644
--- a/makedumpfile-1.6.7/makedumpfile.8
+++ b/makedumpfile-1.6.7/makedumpfile.8
@@ -632,6 +632,11 @@ Show help message and LZO/snappy support status (enabled/disabled).
\fB\-v\fR
Show the version of makedumpfile.
+.TP
+\fB\-\-check-params\fR
+Only check whether the command-line parameters are valid or not, and exit.
+Preferable to be given as the first parameter.
+
.SH ENVIRONMENT VARIABLES
.TP 8
diff --git a/makedumpfile-1.6.7/makedumpfile.c b/makedumpfile-1.6.7/makedumpfile.c
index 607e07f..f5860a1 100644
--- a/makedumpfile-1.6.7/makedumpfile.c
+++ b/makedumpfile-1.6.7/makedumpfile.c
@@ -10972,12 +10972,6 @@ check_param_for_creating_dumpfile(int argc, char *argv[])
if (info->flag_generate_vmcoreinfo || info->flag_rearrange)
return FALSE;
- if ((message_level < MIN_MSG_LEVEL)
- || (MAX_MSG_LEVEL < message_level)) {
- message_level = DEFAULT_MSG_LEVEL;
- MSG("Message_level is invalid.\n");
- return FALSE;
- }
if ((info->flag_compress && info->flag_elf_dumpfile)
|| (info->flag_read_vmcoreinfo && info->name_vmlinux)
|| (info->flag_read_vmcoreinfo && info->name_xen_syms))
@@ -11007,6 +11001,11 @@ check_param_for_creating_dumpfile(int argc, char *argv[])
if (info->flag_partial_dmesg && !info->flag_dmesg)
return FALSE;
+ if (info->flag_excludevm && !info->working_dir) {
+ MSG("-%c requires --work-dir\n", OPT_EXCLUDE_UNUSED_VM);
+ return FALSE;
+ }
+
if ((argc == optind + 2) && !info->flag_flatten
&& !info->flag_split
&& !info->flag_sadump_diskset) {
@@ -11402,6 +11401,23 @@ int show_mem_usage(void)
return TRUE;
}
+static int set_message_level(char *str_ml)
+{
+ int ml;
+
+ ml = atoi(str_ml);
+ if ((ml < MIN_MSG_LEVEL) || (MAX_MSG_LEVEL < ml)) {
+ message_level = DEFAULT_MSG_LEVEL;
+ MSG("Message_level(%d) is invalid.\n", ml);
+ return FALSE;
+ }
+
+ if (info->flag_check_params)
+ return TRUE;
+
+ message_level = ml;
+ return TRUE;
+}
static struct option longopts[] = {
{"split", no_argument, NULL, OPT_SPLIT},
@@ -11423,6 +11439,7 @@ static struct option longopts[] = {
{"splitblock-size", required_argument, NULL, OPT_SPLITBLOCK_SIZE},
{"work-dir", required_argument, NULL, OPT_WORKING_DIR},
{"num-threads", required_argument, NULL, OPT_NUM_THREADS},
+ {"check-params", no_argument, NULL, OPT_CHECK_PARAMS},
{0, 0, 0, 0}
};
@@ -11521,7 +11538,8 @@ main(int argc, char *argv[])
info->flag_compress = DUMP_DH_COMPRESSED_LZO;
break;
case OPT_MESSAGE_LEVEL:
- message_level = atoi(optarg);
+ if (!set_message_level(optarg))
+ goto out;
break;
case OPT_DUMP_DMESG:
info->flag_dmesg = 1;
@@ -11584,6 +11602,10 @@ main(int argc, char *argv[])
case OPT_NUM_THREADS:
info->num_threads = MAX(atoi(optarg), 0);
break;
+ case OPT_CHECK_PARAMS:
+ info->flag_check_params = TRUE;
+ message_level = DEFAULT_MSG_LEVEL;
+ break;
case '?':
MSG("Commandline parameter is invalid.\n");
MSG("Try `makedumpfile --help' for more information.\n");
@@ -11593,11 +11615,9 @@ main(int argc, char *argv[])
if (flag_debug)
message_level |= ML_PRINT_DEBUG_MSG;
- if (info->flag_excludevm && !info->working_dir) {
- ERRMSG("Error: -%c requires --work-dir\n", OPT_EXCLUDE_UNUSED_VM);
- ERRMSG("Try `makedumpfile --help' for more information\n");
- return COMPLETED;
- }
+ if (info->flag_check_params)
+ /* suppress debugging messages */
+ message_level = DEFAULT_MSG_LEVEL;
if (info->flag_show_usage) {
print_usage();
@@ -11628,6 +11648,9 @@ main(int argc, char *argv[])
MSG("Try `makedumpfile --help' for more information.\n");
goto out;
}
+ if (info->flag_check_params)
+ goto check_ok;
+
if (!open_files_for_generating_vmcoreinfo())
goto out;
@@ -11651,6 +11674,9 @@ main(int argc, char *argv[])
MSG("Try `makedumpfile --help' for more information.\n");
goto out;
}
+ if (info->flag_check_params)
+ goto check_ok;
+
if (!check_dump_file(info->name_dumpfile))
goto out;
@@ -11671,6 +11697,9 @@ main(int argc, char *argv[])
MSG("Try `makedumpfile --help' for more information.\n");
goto out;
}
+ if (info->flag_check_params)
+ goto check_ok;
+
if (!check_dump_file(info->name_dumpfile))
goto out;
@@ -11684,6 +11713,9 @@ main(int argc, char *argv[])
MSG("Try `makedumpfile --help' for more information.\n");
goto out;
}
+ if (info->flag_check_params)
+ goto check_ok;
+
if (!check_dump_file(info->name_dumpfile))
goto out;
if (!dump_dmesg())
@@ -11697,6 +11729,9 @@ main(int argc, char *argv[])
MSG("Try `makedumpfile --help' for more information.\n");
goto out;
}
+ if (info->flag_check_params)
+ goto check_ok;
+
if (!populate_kernel_version())
goto out;
@@ -11715,6 +11750,9 @@ main(int argc, char *argv[])
MSG("Try `makedumpfile --help' for more information.\n");
goto out;
}
+ if (info->flag_check_params)
+ goto check_ok;
+
if (info->flag_split) {
for (i = 0; i < info->num_dumpfile; i++) {
SPLITTING_FD_BITMAP(i) = -1;
@@ -11742,13 +11780,16 @@ main(int argc, char *argv[])
MSG("The dumpfile is saved to %s.\n", info->name_dumpfile);
}
}
+check_ok:
retcd = COMPLETED;
out:
- MSG("\n");
- if (retcd != COMPLETED)
- MSG("makedumpfile Failed.\n");
- else if (!info->flag_mem_usage)
- MSG("makedumpfile Completed.\n");
+ if (!info->flag_check_params) {
+ MSG("\n");
+ if (retcd != COMPLETED)
+ MSG("makedumpfile Failed.\n");
+ else if (!info->flag_mem_usage)
+ MSG("makedumpfile Completed.\n");
+ }
free_for_parallel();
diff --git a/makedumpfile-1.6.7/makedumpfile.h b/makedumpfile-1.6.7/makedumpfile.h
index 7217407..03fb4ce 100644
--- a/makedumpfile-1.6.7/makedumpfile.h
+++ b/makedumpfile-1.6.7/makedumpfile.h
@@ -1301,6 +1301,7 @@ struct DumpInfo {
int flag_read_vmcoreinfo; /* flag of reading vmcoreinfo file */
int flag_show_usage; /* flag of showing usage */
int flag_show_version; /* flag of showing version */
+ int flag_check_params; /* only check parameters */
int flag_flatten; /* flag of outputting flattened
format to a standard out */
int flag_rearrange; /* flag of creating dumpfile from
@@ -2362,6 +2363,7 @@ struct elf_prstatus {
#define OPT_WORKING_DIR OPT_START+15
#define OPT_NUM_THREADS OPT_START+16
#define OPT_PARTIAL_DMESG OPT_START+17
+#define OPT_CHECK_PARAMS OPT_START+18
/*
* Function Prototype.
diff --git a/makedumpfile-1.6.7/print_info.c b/makedumpfile-1.6.7/print_info.c
index 0be12ea..e0c38b4 100644
--- a/makedumpfile-1.6.7/print_info.c
+++ b/makedumpfile-1.6.7/print_info.c
@@ -321,6 +321,10 @@ print_usage(void)
MSG(" [-v]:\n");
MSG(" Show the version of makedumpfile.\n");
MSG("\n");
+ MSG(" [--check-params]:\n");
+ MSG(" Only check whether the command-line parameters are valid or not, and exit.\n");
+ MSG(" Preferable to be given as the first parameter.\n");
+ MSG("\n");
MSG(" VMLINUX:\n");
MSG(" This is a pathname to the first kernel's vmlinux.\n");
MSG(" This file must have the debug information of the first kernel to analyze\n");
--
2.7.5

65
SOURCES/kexec-tools-2.0.20-makedumpfile-PATCH-Makefile-Fix-build-errors-in-static-build.patch Normal file
View File

@ -0,0 +1,65 @@
From 12250baa02584dc713cdb1a12fb366f643fdc8b3 Mon Sep 17 00:00:00 2001
From: Kazuhito Hagio <k-hagio-ab@nec.com>
Date: Mon, 9 Mar 2020 17:17:31 -0400
Subject: [PATCH 5/7] [PATCH] Makefile: Fix build errors in static build
When building makedumpfile statically (without LINKTYPE=dynamic),
the following error is observed:
/usr/bin/ld: /usr/lib/makedumpfile-1.6.7/gcc/x86_64-redhat-linux/9/../../../../lib64/libdw.a(lzma.o): in function `__libdw_unlzma':
(.text+0xbd): undefined reference to `lzma_auto_decoder'
/usr/bin/ld: (.text+0x23a): undefined reference to `lzma_code'
/usr/bin/ld: (.text+0x269): undefined reference to `lzma_end'
/usr/bin/ld: (.text+0x2aa): undefined reference to `lzma_end'
/usr/bin/ld: (.text+0x3ac): undefined reference to `lzma_end'
/usr/bin/ld: (.text+0x427): undefined reference to `lzma_end'
/usr/bin/ld: (.text+0x62b): undefined reference to `lzma_end'
collect2: error: ld returned 1 exit status
make: *** [Makefile:97: makedumpfile] Error 1
Also, when doing it with USESNAPPY=on:
/usr/bin/ld: /usr/local/lib64/libsnappy.a(snappy.cc.o): in function `snappy::internal::WorkingMemory::WorkingMemory(unsigned long)':
snappy.cc:(.text+0x7d4): undefined reference to `std::allocator<char>::allocator()'
/usr/bin/ld: snappy.cc:(.text+0x803): undefined reference to `std::allocator<char>::~allocator()'
/usr/bin/ld: snappy.cc:(.text+0x853): undefined reference to `std::allocator<char>::~allocator()'
/usr/bin/ld: /usr/local/lib64/libsnappy.a(snappy.cc.o): in function `snappy::internal::WorkingMemory::~WorkingMemory()':
snappy.cc:(.text+0x87e): undefined reference to `std::allocator<char>::allocator()'
/usr/bin/ld: snappy.cc:(.text+0x8a8): undefined reference to `std::allocator<char>::~allocator()'
...
Fix these errors by adding -llzma and -lstd++ to LIBS respectively
if LINKTYPE=dynamic is not specified.
Reported-by: Prabhakar Kushwaha <prabhakar.pkin@gmail.com>
Signed-off-by: Kazuhito Hagio <k-hagio-ab@nec.com>
---
Makefile | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/makedumpfile-1.6.7/Makefile b/makedumpfile-1.6.7/Makefile
index 868eea6..ef20672 100644
--- a/makedumpfile-1.6.7/Makefile
+++ b/makedumpfile-1.6.7/Makefile
@@ -52,7 +52,7 @@ OBJ_ARCH=$(patsubst %.c,%.o,$(SRC_ARCH))
LIBS = -ldw -lbz2 -ldl -lelf -lz
ifneq ($(LINKTYPE), dynamic)
-LIBS := -static $(LIBS)
+LIBS := -static $(LIBS) -llzma
endif
ifeq ($(USELZO), on)
@@ -62,6 +62,9 @@ endif
ifeq ($(USESNAPPY), on)
LIBS := -lsnappy $(LIBS)
+ifneq ($(LINKTYPE), dynamic)
+LIBS := $(LIBS) -lstdc++
+endif
CFLAGS += -DUSESNAPPY
endif
--
2.7.5

103
SOURCES/kexec-tools-2.0.20-makedumpfile-PATCH-Remove-duplicated-variable-definitions.patch Normal file
View File

@ -0,0 +1,103 @@
From 399f2c9a3acd5bd913e50a4dde52dee6527b297e Mon Sep 17 00:00:00 2001
From: Kairui Song <kasong@redhat.com>
Date: Wed, 29 Jan 2020 13:37:13 +0800
Subject: [PATCH 2/7] [PATCH] Remove duplicated variable definitions
When building on Fedora 32 (with GCC 10), following error is observed:
/usr/bin/ld: erase_info.o:/tmp/makedumpfile/makedumpfile.h:2010: multiple definition of
`crash_reserved_mem_nr'; elf_info.o:/tmp/makedumpfile/makedumpfile.h:2010: first defined here
/usr/bin/ld: erase_info.o:/tmp/makedumpfile/makedumpfile.h:2009: multiple definition of
`crash_reserved_mem'; elf_info.o:/tmp/makedumpfile/makedumpfile.h:2009: first defined here
/usr/bin/ld: erase_info.o:/tmp/makedumpfile/makedumpfile.h:1278: multiple definition of
`parallel_info_t'; elf_info.o:/tmp/makedumpfile/makedumpfile.h:1278: first defined here
/usr/bin/ld: erase_info.o:/tmp/makedumpfile/makedumpfile.h:1265: multiple definition of
`splitting_info_t'; elf_info.o:/tmp/makedumpfile/makedumpfile.h:1265: first defined here
...
collect2: error: ld returned 1 exit status
make: *** [Makefile:97: makedumpfile] Error 1
These variables are wrongly defined multiple times. So remove the
duplicated definitions.
Signed-off-by: Kairui Song <kasong@redhat.com>
Signed-off-by: Kazuhito Hagio <k-hagio-ab@nec.com>
---
makedumpfile.c | 8 ++++----
makedumpfile.h | 8 ++++----
2 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/makedumpfile-1.6.7/makedumpfile.c b/makedumpfile-1.6.7/makedumpfile.c
index e290fbd..ae7336a 100644
--- a/makedumpfile-1.6.7/makedumpfile.c
+++ b/makedumpfile-1.6.7/makedumpfile.c
@@ -10954,7 +10954,7 @@ check_param_for_reassembling_dumpfile(int argc, char *argv[])
return FALSE;
if ((info->splitting_info
- = malloc(sizeof(splitting_info_t) * info->num_dumpfile))
+ = malloc(sizeof(struct splitting_info) * info->num_dumpfile))
== NULL) {
MSG("Can't allocate memory for splitting_info.\n");
return FALSE;
@@ -11042,7 +11042,7 @@ check_param_for_creating_dumpfile(int argc, char *argv[])
return FALSE;
}
if ((info->splitting_info
- = malloc(sizeof(splitting_info_t) * info->num_dumpfile))
+ = malloc(sizeof(struct splitting_info) * info->num_dumpfile))
== NULL) {
MSG("Can't allocate memory for splitting_info.\n");
return FALSE;
@@ -11077,13 +11077,13 @@ check_param_for_creating_dumpfile(int argc, char *argv[])
if (info->num_threads) {
if ((info->parallel_info =
- malloc(sizeof(parallel_info_t) * info->num_threads))
+ malloc(sizeof(struct parallel_info) * info->num_threads))
== NULL) {
MSG("Can't allocate memory for parallel_info.\n");
return FALSE;
}
- memset(info->parallel_info, 0, sizeof(parallel_info_t)
+ memset(info->parallel_info, 0, sizeof(struct parallel_info)
* info->num_threads);
}
diff --git a/makedumpfile-1.6.7/makedumpfile.h b/makedumpfile-1.6.7/makedumpfile.h
index 68d9691..7217407 100644
--- a/makedumpfile-1.6.7/makedumpfile.h
+++ b/makedumpfile-1.6.7/makedumpfile.h
@@ -1262,7 +1262,7 @@ struct splitting_info {
mdf_pfn_t end_pfn;
off_t offset_eraseinfo;
unsigned long size_eraseinfo;
-} splitting_info_t;
+};
struct parallel_info {
int fd_memory;
@@ -1275,7 +1275,7 @@ struct parallel_info {
#ifdef USELZO
lzo_bytep wrkmem;
#endif
-} parallel_info_t;
+};
struct ppc64_vmemmap {
unsigned long phys;
@@ -2006,8 +2006,8 @@ struct memory_range {
};
#define CRASH_RESERVED_MEM_NR 8
-struct memory_range crash_reserved_mem[CRASH_RESERVED_MEM_NR];
-int crash_reserved_mem_nr;
+extern struct memory_range crash_reserved_mem[CRASH_RESERVED_MEM_NR];
+extern int crash_reserved_mem_nr;
unsigned long read_vmcoreinfo_symbol(char *str_symbol);
int readmem(int type_addr, unsigned long long addr, void *bufptr, size_t size);
--
2.7.5

65
SOURCES/kexec-tools-2.0.20-makedumpfile-PATCH-cope-with-not-present-mem-section.patch Normal file
View File

@ -0,0 +1,65 @@
From e113f1c974c820f9633dc0073eda525d7575f365 Mon Sep 17 00:00:00 2001
From: Pingfan Liu <piliu@redhat.com>
Date: Mon, 20 Jan 2020 10:25:24 +0800
Subject: [PATCH 3/7] [PATCH] cope with not-present mem section
After kernel commit ba72b4c8cf60 ("mm/sparsemem: support sub-section
hotplug"), when hot-removed, section_mem_map is still encoded with section
start pfn, not NULL. This break the current makedumpfile.
# makedumpfile -x vmlinux -l -d 31 vmcore vmcore.dump
get_mem_section: Could not validate mem_section.
get_mm_sparsemem: Can't get the address of mem_section.
makedumpfile Failed.
Whatever section_mem_map coding info after hot-removed, it is reliable
just to work on SECTION_MARKED_PRESENT bit. Fixing makedumpfile by this
way.
[ This issue occurs on kernel 5.3 through 5.5, and should be fixed by
commit 1f503443e7df ("mm/sparse.c: reset section's mem_map when fully
deactivated") in 5.6-rc1, 5.5.3 and 5.4.19. ]
Signed-off-by: Pingfan Liu <piliu@redhat.com>
To: kexec@lists.infradead.org
Cc: Kazuhito Hagio <k-hagio@ab.jp.nec.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Qian Cai <cai@lca.pw>
---
makedumpfile.c | 6 +-----
1 file changed, 1 insertion(+), 5 deletions(-)
diff --git a/makedumpfile-1.6.7/makedumpfile.c b/makedumpfile-1.6.7/makedumpfile.c
index ae7336a..607e07f 100644
--- a/makedumpfile-1.6.7/makedumpfile.c
+++ b/makedumpfile-1.6.7/makedumpfile.c
@@ -3406,8 +3406,6 @@ section_mem_map_addr(unsigned long addr, unsigned long *map_mask)
map = ULONG(mem_section + OFFSET(mem_section.section_mem_map));
mask = SECTION_MAP_MASK;
*map_mask = map & ~mask;
- if (map == 0x0)
- *map_mask |= SECTION_MARKED_PRESENT;
map &= mask;
free(mem_section);
@@ -3453,10 +3451,8 @@ validate_mem_section(unsigned long *mem_sec,
mem_map = NOT_MEMMAP_ADDR;
} else {
mem_map = section_mem_map_addr(section, &map_mask);
+ /* for either no mem_map or hot-removed */
if (!(map_mask & SECTION_MARKED_PRESENT)) {
- return FALSE;
- }
- if (mem_map == 0) {
mem_map = NOT_MEMMAP_ADDR;
} else {
mem_map = sparse_decode_mem_map(mem_map,
--
2.7.5

213
SOURCES/kexec-tools-2.0.20-makedumpfile-PATCH-sadump-kaslr-fix-failure-of-calculating-kaslr.patch Normal file
View File

@ -0,0 +1,213 @@
From 3c0cf7a93cff83f1e711e241eb47fcb096a451c5 Mon Sep 17 00:00:00 2001
From: HATAYAMA Daisuke <d.hatayama@fujitsu.com>
Date: Thu, 9 Jul 2020 18:27:49 +0900
Subject: [PATCH] [PATCH] sadump, kaslr: fix failure of calculating
kaslr_offset due to an sadump format restriction
We faced recently a memory dump collected by sadump where unused part
of register values are non-zero. For the crash dump, calculating
kaslr_offset fails because it is based on the assumption that unused
part of register values in the sadump format are always zero cleared.
The problem is that used and unused part of register values are
rigorously indistinguishable in the sadump format. Although there is
kernel data structure that represents a map between logical cpu
numbers and lapic ids, they cannot be used in order to calculate
kaslr_offset.
To fix this, we have no choice but use a trial-and-error approach: try
to use each entry of register values in order until we find a good
pair of cr3 and idtr by which we can refer to linux_banner symbol as
expected.
Signed-off-by: HATAYAMA Daisuke <d.hatayama@fujitsu.com>
---
sadump_info.c | 129 +++++++++++++++++++++++++++++++++++++++++-----------------
1 file changed, 91 insertions(+), 38 deletions(-)
diff --git a/makedumpfile-1.6.7/sadump_info.c b/makedumpfile-1.6.7/sadump_info.c
index 72a077b4f408..410c6bc2a909 100644
--- a/makedumpfile-1.6.7/sadump_info.c
+++ b/makedumpfile-1.6.7/sadump_info.c
@@ -101,6 +101,7 @@ static int lookup_diskset(unsigned long long whole_offset, int *diskid,
unsigned long long *disk_offset);
static int max_mask_cpu(void);
static int cpu_online_mask_init(void);
+static int linux_banner_sanity_check(ulong cr3);
static int per_cpu_init(void);
static int get_data_from_elf_note_desc(const char *note_buf, uint32_t n_descsz,
char *name, uint32_t n_type, char **data);
@@ -1293,6 +1294,30 @@ finish:
return ret;
}
+static int linux_banner_sanity_check(ulong cr3)
+{
+ unsigned long linux_banner_paddr;
+ char buf[sizeof("Linux version")];
+
+ linux_banner_paddr = vtop4_x86_64_pagetable(SYMBOL(linux_banner), cr3);
+ if (linux_banner_paddr == NOT_PADDR) {
+ DEBUG_MSG("sadump: linux_banner address translation failed\n");
+ return FALSE;
+ }
+
+ if (!readmem(PADDR, linux_banner_paddr, &buf, sizeof(buf))) {
+ DEBUG_MSG("sadump: reading linux_banner failed\n");
+ return FALSE;
+ }
+
+ if (!STRNEQ(buf, "Linux version")) {
+ DEBUG_MSG("sadump: linux_banner sanity check failed\n");
+ return FALSE;
+ }
+
+ return TRUE;
+}
+
/*
* Calculate kaslr_offset and phys_base
*
@@ -1370,59 +1395,85 @@ calc_kaslr_offset(void)
{
struct sadump_header *sh = si->sh_memory;
uint64_t idtr = 0, cr3 = 0, idtr_paddr;
- struct sadump_smram_cpu_state smram, zero;
+ struct sadump_smram_cpu_state smram;
int apicid;
unsigned long divide_error_vmcore, divide_error_vmlinux;
unsigned long kaslr_offset, phys_base;
unsigned long kaslr_offset_kdump, phys_base_kdump;
+ int sanity_check_passed = FALSE;
- memset(&zero, 0, sizeof(zero));
for (apicid = 0; apicid < sh->nr_cpus; ++apicid) {
+
+ DEBUG_MSG("sadump: apicid: %d\n", apicid);
+
if (!get_smram_cpu_state(apicid, &smram)) {
ERRMSG("get_smram_cpu_state error\n");
return FALSE;
}
- if (memcmp(&smram, &zero, sizeof(smram)) != 0)
- break;
- }
- if (apicid >= sh->nr_cpus) {
- ERRMSG("Can't get smram state\n");
- return FALSE;
- }
+ idtr = ((uint64_t)smram.IdtUpper)<<32|(uint64_t)smram.IdtLower;
- idtr = ((uint64_t)smram.IdtUpper)<<32 | (uint64_t)smram.IdtLower;
- if ((SYMBOL(pti_init) != NOT_FOUND_SYMBOL) ||
- (SYMBOL(kaiser_init) != NOT_FOUND_SYMBOL))
- cr3 = smram.Cr3 & ~(CR3_PCID_MASK|PTI_USER_PGTABLE_MASK);
- else
- cr3 = smram.Cr3 & ~CR3_PCID_MASK;
+ if (!smram.Cr3 || !idtr) {
+ DEBUG_MSG("sadump: cr3: %lx idt: %lx, skipped\n",
+ smram.Cr3, idtr);
+ continue;
+ }
- /* Convert virtual address of IDT table to physical address */
- if ((idtr_paddr = vtop4_x86_64_pagetable(idtr, cr3)) == NOT_PADDR)
- return FALSE;
+ if ((SYMBOL(pti_init) != NOT_FOUND_SYMBOL) ||
+ (SYMBOL(kaiser_init) != NOT_FOUND_SYMBOL))
+ cr3 = smram.Cr3 & ~(CR3_PCID_MASK|PTI_USER_PGTABLE_MASK);
+ else
+ cr3 = smram.Cr3 & ~CR3_PCID_MASK;
- /* Now we can calculate kaslr_offset and phys_base */
- divide_error_vmlinux = SYMBOL(divide_error);
- divide_error_vmcore = get_vec0_addr(idtr_paddr);
- kaslr_offset = divide_error_vmcore - divide_error_vmlinux;
- phys_base = idtr_paddr -
- (SYMBOL(idt_table) + kaslr_offset - __START_KERNEL_map);
+ /* Convert virtual address of IDT table to physical address */
+ idtr_paddr = vtop4_x86_64_pagetable(idtr, cr3);
+ if (idtr_paddr == NOT_PADDR) {
+ DEBUG_MSG("sadump: converting IDT physical address "
+ "failed.\n");
+ continue;
+ }
- info->kaslr_offset = kaslr_offset;
- info->phys_base = phys_base;
+ /* Now we can calculate kaslr_offset and phys_base */
+ divide_error_vmlinux = SYMBOL(divide_error);
+ divide_error_vmcore = get_vec0_addr(idtr_paddr);
+ kaslr_offset = divide_error_vmcore - divide_error_vmlinux;
+ phys_base = idtr_paddr -
+ (SYMBOL(idt_table)+kaslr_offset-__START_KERNEL_map);
- DEBUG_MSG("sadump: idtr=%" PRIx64 "\n", idtr);
- DEBUG_MSG("sadump: cr3=%" PRIx64 "\n", cr3);
- DEBUG_MSG("sadump: idtr(phys)=%" PRIx64 "\n", idtr_paddr);
- DEBUG_MSG("sadump: devide_error(vmlinux)=%lx\n",
- divide_error_vmlinux);
- DEBUG_MSG("sadump: devide_error(vmcore)=%lx\n",
- divide_error_vmcore);
+ info->kaslr_offset = kaslr_offset;
+ info->phys_base = phys_base;
- /* Reload symbol */
- if (!get_symbol_info())
- return FALSE;
+ DEBUG_MSG("sadump: idtr=%" PRIx64 "\n", idtr);
+ DEBUG_MSG("sadump: cr3=%" PRIx64 "\n", cr3);
+ DEBUG_MSG("sadump: idtr(phys)=%" PRIx64 "\n", idtr_paddr);
+ DEBUG_MSG("sadump: devide_error(vmlinux)=%lx\n",
+ divide_error_vmlinux);
+ DEBUG_MSG("sadump: devide_error(vmcore)=%lx\n",
+ divide_error_vmcore);
+
+ /* Reload symbol */
+ if (!get_symbol_info()) {
+ ERRMSG("Reading symbol table failed\n");
+ return FALSE;
+ }
+
+ /* Sanity check */
+ if (linux_banner_sanity_check(cr3)) {
+ sanity_check_passed = TRUE;
+ break;
+ }
+
+ info->kaslr_offset = 0;
+ info->phys_base = 0;
+ }
+
+ if (!sanity_check_passed) {
+ ERRMSG("failed to calculate kaslr_offset and phys_base; "
+ "default to 0\n");
+ info->kaslr_offset = 0;
+ info->phys_base = 0;
+ return TRUE;
+ }
/*
* Check if current kaslr_offset/phys_base is for 1st kernel or 2nd
@@ -1430,13 +1481,15 @@ calc_kaslr_offset(void)
* from vmcoreinfo
*/
if (get_kaslr_offset_from_vmcoreinfo(cr3, &kaslr_offset_kdump,
- &phys_base_kdump)) {
+ &phys_base_kdump)) {
info->kaslr_offset = kaslr_offset_kdump;
info->phys_base = phys_base_kdump;
/* Reload symbol */
- if (!get_symbol_info())
+ if (!get_symbol_info()) {
+ ERRMSG("Reading symbol table failed\n");
return FALSE;
+ }
}
DEBUG_MSG("sadump: kaslr_offset=%lx\n", info->kaslr_offset);
--
2.7.4

38
SOURCES/kexec-tools-2.0.20-vmcore-dmesg-vmcore-dmesg.c-Fix-shifting-error-repor.patch Normal file
View File

@ -0,0 +1,38 @@
From a46c686f615a86933134c0924c3391ba598a02b8 Mon Sep 17 00:00:00 2001
From: Bhupesh Sharma <bhsharma@redhat.com>
Date: Tue, 10 Sep 2019 15:51:49 +0530
Subject: [PATCH 5/5] vmcore-dmesg/vmcore-dmesg.c: Fix shifting error reported
by cppcheck
Running 'cppcheck' static code analyzer (see cppcheck(1))
on 'vmcore-dmesg/vmcore-dmesg.c' shows the following
shifting error:
$ cppcheck --enable=all vmcore-dmesg/vmcore-dmesg.c
Checking vmcore-dmesg/vmcore-dmesg.c ...
[vmcore-dmesg/vmcore-dmesg.c:17]: (error) Shifting signed 32-bit value by 31 bits is undefined behaviour
Fix the same via this patch.
Signed-off-by: Bhupesh Sharma <bhsharma@redhat.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
vmcore-dmesg/vmcore-dmesg.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/vmcore-dmesg/vmcore-dmesg.c b/vmcore-dmesg/vmcore-dmesg.c
index 81c2a58c9d86..122e53672e01 100644
--- a/vmcore-dmesg/vmcore-dmesg.c
+++ b/vmcore-dmesg/vmcore-dmesg.c
@@ -6,7 +6,7 @@ typedef Elf32_Nhdr Elf_Nhdr;
extern const char *fname;
/* stole this macro from kernel printk.c */
-#define LOG_BUF_LEN_MAX (uint32_t)(1 << 31)
+#define LOG_BUF_LEN_MAX (uint32_t)(1U << 31)
static void write_to_stdout(char *buf, unsigned int nr)
{
--
2.17.1

25
SOURCES/live-image-kdump-howto.txt Normal file
View File

@ -0,0 +1,25 @@
Kdump now works on live images with some manual configurations. Here is the step
by step guide.
1. Enable crashkernel reservation
Since there isn't any config file that can be used to configure kernel
parameters for live images before booting them, we have to append 'crashkernel'
argument in boot menu every time we boot a live image.
2. Change dump target in /etc/kdump.conf
When kdump kernel boots in a live environment, the default target /var/crash is
in RAM so you need to change the dump target to an external disk or a network
dump target.
Besides, make sure that "default dump_to_rootfs" is not specified.
3. Start kdump service
$ kdumpctl start
4. Trigger a kdump test
$ echo 1 > /proc/sys/kernel/sysrq
$ echo c > /proc/sysrq-trigger

482
SOURCES/mkdumprd Normal file
View File

@ -0,0 +1,482 @@
#!/bin/bash --norc
# New mkdumprd
#
# Copyright 2011 Red Hat, Inc.
#
# Written by Cong Wang <amwang@redhat.com>
#
[[ $dracutbasedir ]] || dracutbasedir=/usr/lib/dracut
. $dracutbasedir/dracut-functions.sh
. /lib/kdump/kdump-lib.sh
export IN_KDUMP=1
conf_file="/etc/kdump.conf"
SSH_KEY_LOCATION="/root/.ssh/kdump_id_rsa"
SAVE_PATH=$(get_save_path)
OVERRIDE_RESETTABLE=0
extra_modules=""
dracut_args="--quiet --hostonly --hostonly-cmdline --hostonly-i18n --hostonly-mode strict -o \"plymouth dash resume ifcfg earlykdump\""
readonly MKDUMPRD_TMPDIR="$(mktemp -d -t mkdumprd.XXXXXX)"
[ -d "$MKDUMPRD_TMPDIR" ] || perror_exit "dracut: mktemp -p -d -t dracut.XXXXXX failed."
readonly MKDUMPRD_TMPMNT="$MKDUMPRD_TMPDIR/target"
trap '
ret=$?;
is_mounted $MKDUMPRD_TMPMNT && umount -f $MKDUMPRD_TMPMNT;
[[ -d $MKDUMPRD_TMPDIR ]] && rm --one-file-system -rf -- "$MKDUMPRD_TMPDIR";
exit $ret;
' EXIT
# clean up after ourselves no matter how we die.
trap 'exit 1;' SIGINT
is_wdt_addition_needed() {
local active
is_wdt_mod_omitted
[[ $? -eq 0 ]] && return 1
[[ -d /sys/class/watchdog/ ]] || return 1
for dir in /sys/class/watchdog/*; do
[[ -f "$dir/state" ]] || continue
active=$(< "$dir/state")
[[ "$active" = "active" ]] && return 0
done
return 1
}
add_dracut_arg() {
dracut_args="$dracut_args $@"
}
add_dracut_module() {
add_dracut_arg "--add" "\"$1\""
}
add_dracut_mount() {
add_dracut_arg "--mount" "\"$1\""
}
add_dracut_sshkey() {
add_dracut_arg "--sshkey" "\"$1\""
}
# caller should ensure $1 is valid and mounted in 1st kernel
to_mount() {
local _target=$1 _fstype=$2 _options=$3 _new_mntpoint _pdev
_new_mntpoint=$(get_kdump_mntpoint_from_target $_target)
_fstype="${_fstype:-$(get_fs_type_from_target $_target)}"
_options="${_options:-$(get_mntopt_from_target $_target)}"
_options="${_options:-defaults}"
if [[ "$_fstype" == "nfs"* ]]; then
_pdev=$_target
_options=$(echo $_options | sed 's/,addr=[^,]*//')
_options=$(echo $_options | sed 's/,proto=[^,]*//')
_options=$(echo $_options | sed 's/,clientaddr=[^,]*//')
else
# for non-nfs _target converting to use udev persistent name
_pdev="$(kdump_get_persistent_dev $_target)"
if [ -z "$_pdev" ]; then
return 1
fi
fi
#mount fs target as rw in 2nd kernel
_options=$(echo $_options | sed 's/\(^\|,\)ro\($\|,\)/\1rw\2/g')
# with 'noauto' in fstab nfs and non-root disk mount will fail in 2nd
# kernel, filter it out here.
_options=$(echo $_options | sed 's/\(^\|,\)noauto\($\|,\)/\1/g')
# use both nofail and x-systemd.before to ensure systemd will try best to
# mount it before kdump starts, this is an attempt to improve robustness
_options="$_options,nofail,x-systemd.before=initrd-fs.target"
echo "$_pdev $_new_mntpoint $_fstype $_options"
}
#Function: get_ssh_size
#$1=dump target
#called from while loop and shouldn't read from stdin, so we're using "ssh -n"
get_ssh_size() {
local _opt _out _size
_opt="-i $SSH_KEY_LOCATION -o BatchMode=yes -o StrictHostKeyChecking=yes"
_out=$(ssh -q -n $_opt $1 "df -P $SAVE_PATH")
[ $? -ne 0 ] && {
perror_exit "checking remote ssh server available size failed."
}
#ssh output removed the line break, so print field NF-2
_size=$(echo -n $_out| awk '{avail=NF-2; print $avail}')
echo -n $_size
}
#mkdir if save path does not exist on ssh dump target
#$1=ssh dump target
#caller should ensure write permission on $1:$SAVE_PATH
#called from while loop and shouldn't read from stdin, so we're using "ssh -n"
mkdir_save_path_ssh()
{
local _opt _dir
_opt="-i $SSH_KEY_LOCATION -o BatchMode=yes -o StrictHostKeyChecking=yes"
ssh -qn $_opt $1 mkdir -p $SAVE_PATH 2>&1 > /dev/null
_ret=$?
if [ $_ret -ne 0 ]; then
perror_exit "mkdir failed on $1:$SAVE_PATH"
fi
#check whether user has write permission on $1:$SAVE_PATH
_dir=$(ssh -qn $_opt $1 mktemp -dqp $SAVE_PATH 2>/dev/null)
_ret=$?
if [ $_ret -ne 0 ]; then
perror_exit "Could not create temporary directory on $1:$SAVE_PATH. Make sure user has write permission on destination"
fi
ssh -qn $_opt $1 rmdir $_dir
return 0
}
#Function: get_fs_size
#$1=dump target
get_fs_size() {
local _mnt=$(get_mntpoint_from_target $1)
echo -n $(df -P "${_mnt}/$SAVE_PATH"|tail -1|awk '{print $4}')
}
#Function: get_raw_size
#$1=dump target
get_raw_size() {
echo -n $(fdisk -s "$1")
}
#Function: check_size
#$1: dump type string ('raw', 'fs', 'ssh')
#$2: dump target
check_size() {
local avail memtotal
memtotal=$(awk '/MemTotal/{print $2}' /proc/meminfo)
case "$1" in
raw)
avail=$(get_raw_size "$2")
;;
ssh)
avail=$(get_ssh_size "$2")
;;
fs)
avail=$(get_fs_size "$2")
;;
*)
return
esac
if [ $? -ne 0 ]; then
perror_exit "Check dump target size failed"
fi
if [ $avail -lt $memtotal ]; then
echo "Warning: There might not be enough space to save a vmcore."
echo " The size of $2 should be greater than $memtotal kilo bytes."
fi
}
check_save_path_fs()
{
local _path=$1
if [ ! -d $_path ]; then
perror_exit "Dump path $_path does not exist."
fi
}
check_user_configured_target()
{
local _target=$1 _cfg_fs_type=$2 _mounted
local _mnt=$(get_mntpoint_from_target $_target)
local _opt=$(get_mntopt_from_target $_target)
local _fstype=$(get_fs_type_from_target $_target)
if [ -n "$_fstype" ]; then
# In case of nfs4, nfs should be used instead, nfs* options is deprecated in kdump.conf
[[ $_fstype = "nfs"* ]] && _fstype=nfs
if [ -n "$_cfg_fs_type" ] && [ "$_fstype" != "$_cfg_fs_type" ]; then
perror_exit "\"$_target\" have a wrong type config \"$_cfg_fs_type\", expected \"$_fstype\""
fi
else
_fstype="$_cfg_fs_type"
_fstype="$_cfg_fs_type"
fi
# For noauto mount, mount it inplace with default value.
# Else use the temporary target directory
if [ -n "$_mnt" ]; then
if ! is_mounted "$_mnt"; then
if [[ $_opt = *",noauto"* ]]; then
mount $_mnt
[ $? -ne 0 ] && perror_exit "Failed to mount $_target on $_mnt for kdump preflight check."
_mounted=$_mnt
else
perror_exit "Dump target \"$_target\" is neither mounted nor configured as \"noauto\""
fi
fi
else
_mnt=$MKDUMPRD_TMPMNT
mkdir -p $_mnt
mount $_target $_mnt -t $_fstype -o defaults
[ $? -ne 0 ] && perror_exit "Failed to mount $_target for kdump preflight check."
_mounted=$_mnt
fi
# For user configured target, use $SAVE_PATH as the dump path within the target
if [ ! -d "$_mnt/$SAVE_PATH" ]; then
perror_exit "Dump path \"$SAVE_PATH\" does not exist in dump target \"$_target\""
fi
check_size fs "$_target"
# Unmount it early, if function is interrupted and didn't reach here, the shell trap will clear it up anyway
if [ -n "$_mounted" ]; then
umount -f -- $_mounted
fi
}
# $1: core_collector config value
verify_core_collector() {
local _cmd="${1%% *}"
local _params="${1#* }"
if [ "$_cmd" != "makedumpfile" ]; then
if is_raw_dump_target; then
echo "Warning: specifying a non-makedumpfile core collector, you will have to recover the vmcore manually."
fi
return
fi
if is_ssh_dump_target || is_raw_dump_target; then
if ! strstr "$_params" "-F"; then
perror_exit "The specified dump target needs makedumpfile \"-F\" option."
fi
_params="$_params vmcore"
else
_params="$_params vmcore dumpfile"
fi
if ! $_cmd --check-params $_params; then
perror_exit "makedumpfile parameter check failed."
fi
}
add_mount() {
local _mnt=$(to_mount $@)
if [ $? -ne 0 ]; then
exit 1
fi
add_dracut_mount "$_mnt"
}
#handle the case user does not specify the dump target explicitly
handle_default_dump_target()
{
local _target
local _mntpoint
is_user_configured_dump_target && return
check_save_path_fs $SAVE_PATH
_save_path=$(get_bind_mount_source $SAVE_PATH)
_target=$(get_target_from_path $_save_path)
_mntpoint=$(get_mntpoint_from_target $_target)
SAVE_PATH=${_save_path##"$_mntpoint"}
add_mount "$_target"
check_size fs $_target
}
get_override_resettable()
{
local override_resettable
override_resettable=$(grep "^override_resettable" $conf_file)
if [ -n "$override_resettable" ]; then
OVERRIDE_RESETTABLE=$(echo $override_resettable | cut -d' ' -f2)
if [ "$OVERRIDE_RESETTABLE" != "0" ] && [ "$OVERRIDE_RESETTABLE" != "1" ];then
perror_exit "override_resettable value $OVERRIDE_RESETTABLE is invalid"
fi
fi
}
# $1: function name
for_each_block_target()
{
local dev majmin
for dev in $(get_kdump_targets); do
[ -b "$dev" ] || continue
majmin=$(get_maj_min $dev)
check_block_and_slaves $1 $majmin && return 1
done
return 0
}
#judge if a specific device with $1 is unresettable
#return false if unresettable.
is_unresettable()
{
local path="/sys/$(udevadm info --query=all --path=/sys/dev/block/$1 | awk '/^P:/ {print $2}' | sed -e 's/\(cciss[0-9]\+\/\).*/\1/g' -e 's/\/block\/.*$//')/resettable"
local resettable=1
if [ -f "$path" ]
then
resettable="$(cat $path)"
[ $resettable -eq 0 -a "$OVERRIDE_RESETTABLE" -eq 0 ] && {
local device=$(udevadm info --query=all --path=/sys/dev/block/$1 | awk -F= '/DEVNAME/{print $2}')
echo "Error: Can not save vmcore because device $device is unresettable"
return 0
}
fi
return 1
}
#check if machine is resettable.
#return true if resettable
check_resettable()
{
local _ret _target
get_override_resettable
for_each_block_target is_unresettable
_ret=$?
[ $_ret -eq 0 ] && return
return 1
}
# $1: maj:min
is_crypt()
{
local majmin=$1 dev line ID_FS_TYPE=""
line=$(udevadm info --query=property --path=/sys/dev/block/$majmin \
| grep "^ID_FS_TYPE")
eval "$line"
[[ "$ID_FS_TYPE" = "crypto_LUKS" ]] && {
dev=$(udevadm info --query=all --path=/sys/dev/block/$majmin | awk -F= '/DEVNAME/{print $2}')
echo "Device $dev is encrypted."
return 0
}
return 1
}
check_crypt()
{
local _ret _target
for_each_block_target is_crypt
_ret=$?
[ $_ret -eq 0 ] && return
return 1
}
if ! check_resettable; then
exit 1
fi
if ! check_crypt; then
echo "Warning: Encrypted device is in dump path. User will prompted for password during second kernel boot."
fi
# firstly get right SSH_KEY_LOCATION
keyfile=$(awk '/^sshkey/ {print $2}' $conf_file)
if [ -f "$keyfile" ]; then
# canonicalize the path
SSH_KEY_LOCATION=$(/usr/bin/readlink -m $keyfile)
fi
if [ "$(uname -m)" = "s390x" ]; then
add_dracut_module "znet"
fi
if is_wdt_addition_needed; then
add_dracut_arg "-a" "watchdog"
fi
while read config_opt config_val;
do
# remove inline comments after the end of a directive.
case "$config_opt" in
extra_modules)
extra_modules="$extra_modules $config_val"
;;
ext[234]|xfs|btrfs|minix|nfs)
check_user_configured_target "$config_val" "$config_opt"
add_mount "$config_val" "$config_opt"
;;
raw)
# checking raw disk writable
dd if=$config_val count=1 of=/dev/null > /dev/null 2>&1 || {
perror_exit "Bad raw disk $config_val"
}
_praw=$(persistent_policy="by-id" kdump_get_persistent_dev $config_val)
if [ -z "$_praw" ]; then
exit 1
fi
add_dracut_arg "--device" "$_praw"
check_size raw $config_val
;;
ssh)
if strstr "$config_val" "@";
then
mkdir_save_path_ssh $config_val
check_size ssh $config_val
add_dracut_module "ssh-client"
add_dracut_sshkey "$SSH_KEY_LOCATION"
else
perror_exit "Bad ssh dump target $config_val"
fi
;;
core_collector)
verify_core_collector "$config_val"
;;
dracut_args)
add_dracut_arg $config_val
;;
*)
;;
esac
done <<< "$(read_strip_comments $conf_file)"
handle_default_dump_target
if [ -n "$extra_modules" ]
then
add_dracut_arg "--add-drivers" \"$extra_modules\"
fi
if ! is_fadump_capable; then
# The 2nd rootfs mount stays behind the normal dump target mount,
# so it doesn't affect the logic of check_dump_fs_modified().
is_dump_to_rootfs && add_mount "$(to_dev_name $(get_root_fs_device))"
add_dracut_arg "--no-hostonly-default-device"
fi
echo "$dracut_args $@" | xargs dracut
_rc=$?
sync
exit $_rc

33
SOURCES/mkdumprd.8 Normal file
View File

@ -0,0 +1,33 @@
.TH MKDUMRD 8 "Fri Feb 9 2007"
.SH NAME
mkdumprd \- creates initial ramdisk images for kdump crash recovery
.SH SYNOPSIS
\fBmkdumprd\fR [OPTION]
.SH DESCRIPTION
\fBmkdumprd\fR creates an initial ram file system for use in conjunction with
the booting of a kernel within the kdump framework for crash recovery.
\fBmkdumprds\fR purpose is to create an initial ram filesystem capable of copying
the crashed systems vmcore image to a location specified in \fI/etc/kdump.conf
\fBmkdumprd\fR interrogates the running system to understand what modules need to
be loaded in the initramfs (based on configuration retrieved from
\fI/etc/kdump.conf)\fR
\fBmkdumprd\fR add a new \fBdracut\fR module 99kdumpbase and use \fBdracut\fR
utility to generate the initramfs.
\fBmkdumprd\fR was not intended for casual use outside of the service
initialization script for the kdump utility, and should not be run manually. If
you require a custom kdump initramfs image, it is suggested that you use the
kdump service infrastructure to create one, and then manually unpack, modify and
repack the image.
.SH OPTIONS
.TP
All options here are passed to dracut directly, please refer \fBdracut\fR docs
for the info.
.SH "SEE ALSO"
.BR dracut (8)

13
SOURCES/rhelonly-kexec-tools-2.0.16-koji-build-fail-workaround.patch Normal file
View File

@ -0,0 +1,13 @@
diff --git a/purgatory/Makefile b/purgatory/Makefile
index 49ce80a..97b7a03 100644
--- a/purgatory/Makefile
+++ b/purgatory/Makefile
@@ -67,7 +67,7 @@ $(PURGATORY): $(PURGATORY_OBJS)
$(MKDIR) -p $(@D)
$(CC) $(CFLAGS) $(LDFLAGS) -o $@.sym $^
# $(LD) $(LDFLAGS) $(EXTRA_LDFLAGS) --no-undefined -e purgatory_start -r -o $@ $(PURGATORY_OBJS) $(UTIL_LIB)
- $(STRIP) --strip-debug -o $@ $@.sym
+ $(STRIP) --strip-debug --no-merge-notes -o $@ $@.sym
echo::
@echo "PURGATORY_SRCS $(PURGATORY_SRCS)"

51
SOURCES/rhelonly-kexec-tools-2.0.18-eppic-fix-issues-with-hardening-flags.patch Normal file
View File

@ -0,0 +1,51 @@
From ce720608d5933e62f77f2c2f216859cf4f06adf8 Mon Sep 17 00:00:00 2001
From: Kairui Song <kasong@redhat.com>
Date: Wed, 13 Feb 2019 00:03:51 +0800
Subject: [PATCH] Fix eppic issue with hardening flags
This is stash of two commits:
commit f98cf5fe07f390554696755f0a5843f6bb9c4716
Author: ryncsn <ryncsn@gmail.com>
Date: Tue Mar 19 13:39:25 2019 +0800
Tell gcc not to omit frame pointer
After commit 0209874, it's now possible to enable optimization above O0.
But eppic might call __builtin_return_address(1). With O1,
-fomit-frame-pointer is enabled gcc may omit frame pointer.
__builtin_return_address(1) relies on callee preserves RBP as the stack
base, which is untrue if optimization is usded. In this case it may return
wrong value or crash.
In case of any potential failure, use -fno-omit-frame-pointer globally.
Signed-off-by: Kairui Song <ryncsn@gmail.com>
commit 0209874f4b46b8af5a2d42662ba6775cf5a1dc44
Author: Kairui Song <kasong@redhat.com>
Date: Wed Feb 13 00:03:51 2019 +0800
Drop O0 CFLAGS override in Makefile
Signed-off-by: Kairui Song <kasong@redhat.com>
---
libeppic/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/libeppic/Makefile b/libeppic/Makefile
index bcf2edf..8b97c87 100644
--- a/eppic/libeppic/Makefile
+++ b/eppic/libeppic/Makefile
@@ -24,7 +24,7 @@ LDIRT = lex.eppic.c lex.eppicpp.c eppic.tab.c eppic.tab.h eppicpp.tab.c \
LIBDIR = /usr/lib
TARGETS = libeppic.a
-CFLAGS += -O0 -g -fPIC
+CFLAGS += -g -fno-omit-frame-pointer -fPIC
ifeq ($(TARGET), PPC64)
CFLAGS += -m64
endif
--
2.20.1

235
SOURCES/rhonly-kexec-tools-2.0.18-makedumpfile-arm64-Add-support-for-ARMv8.2-LVA-52-bi.patch Normal file
View File

@ -0,0 +1,235 @@
From: Bhupesh Sharma <bhsharma@redhat.com>
Date: Wed, 6 Feb 2019 12:31:29 +0530
Subject: [PATCH] makedumpfile/arm64: Add support for ARMv8.2-LVA (52-bit
user-space VA support)
With ARMv8.2-LVA architecture extension availability, arm64 hardware
which supports this extension can support upto 52-bit virtual
addresses. It is specially useful for having a 52-bit user-space virtual
address space while the kernel can still retain 48-bit virtual
addresses.
Since at the moment we enable the support of this extension in the
kernel via a CONFIG flag (CONFIG_ARM64_USER_VA_BITS_52), so there are
no clear mechanisms in user-space to determine this CONFIG
flag value and use it to determine the user-space VA address range
values.
'makedumpfile' can instead use 'MAX_USER_VA_BITS' value to
determine the maximum virtual physical address supported by user-space.
If 'MAX_USER_VA_BITS' value is greater than 'VA_BITS' than we are
running a use-case where user-space is 52-bit and underlying kernel is
still 48-bit. The increased 'PTRS_PER_PGD' value for such cases can then
be calculated as is done by the underlying kernel (see kernel file
'arch/arm64/include/asm/pgtable-hwdef.h' for details):
#define PTRS_PER_PGD (1 << (MAX_USER_VA_BITS - PGDIR_SHIFT))
I have sent a kernel patch upstream to add 'MAX_USER_VA_BITS' to
vmcoreinfo for arm64 (see [0]).
This patch is in accordance with ARMv8 Architecture Reference Manual
version D.a
[0].
http://lists.infradead.org/pipermail/kexec/2019-February/022411.html
Signed-off-by: Bhupesh Sharma <bhsharma@redhat.com>
---
arch/arm64.c | 109 ++++++++++++++++++++++++++++++++++++++++++---------------
makedumpfile.c | 2 ++
makedumpfile.h | 1 +
3 files changed, 83 insertions(+), 29 deletions(-)
diff --git a/makedumpfile-1.6.7/arch/arm64.c b/makedumpfile-1.6.7/arch/arm64.c
index 0535193..5fcf59d 100644
--- a/makedumpfile-1.6.7/arch/arm64.c
+++ b/makedumpfile-1.6.7/arch/arm64.c
@@ -41,6 +41,7 @@ typedef struct {
static int pgtable_level;
static int va_bits;
+static int max_user_va_bits;
static unsigned long kimage_voffset;
#define SZ_4K (4 * 1024)
@@ -61,7 +62,7 @@ static unsigned long kimage_voffset;
#define PAGE_MASK (~(PAGESIZE() - 1))
#define PGDIR_SHIFT ((PAGESHIFT() - 3) * pgtable_level + 3)
-#define PTRS_PER_PGD (1 << (va_bits - PGDIR_SHIFT))
+#define PTRS_PER_PGD (1 << ((max_user_va_bits) - PGDIR_SHIFT))
#define PUD_SHIFT get_pud_shift_arm64()
#define PUD_SIZE (1UL << PUD_SHIFT)
#define PUD_MASK (~(PUD_SIZE - 1))
@@ -73,6 +74,10 @@ static unsigned long kimage_voffset;
#define PTRS_PER_PMD PTRS_PER_PTE
#define PAGE_PRESENT (1 << 0)
+
+/*
+ * Section address mask and size definitions.
+ */
#define SECTIONS_SIZE_BITS 30
/* Highest possible physical address supported */
#define PHYS_MASK_SHIFT 48
@@ -284,14 +289,83 @@ get_stext_symbol(void)
return(found ? kallsym : FALSE);
}
+static int
+get_va_bits_from_stext_arm64(void)
+{
+ ulong _stext;
+
+ _stext = get_stext_symbol();
+ if (!_stext) {
+ ERRMSG("Can't get the symbol of _stext.\n");
+ return FALSE;
+ }
+
+ /* Derive va_bits as per arch/arm64/Kconfig */
+ if ((_stext & PAGE_OFFSET_36) == PAGE_OFFSET_36) {
+ va_bits = 36;
+ } else if ((_stext & PAGE_OFFSET_39) == PAGE_OFFSET_39) {
+ va_bits = 39;
+ } else if ((_stext & PAGE_OFFSET_42) == PAGE_OFFSET_42) {
+ va_bits = 42;
+ } else if ((_stext & PAGE_OFFSET_47) == PAGE_OFFSET_47) {
+ va_bits = 47;
+ } else if ((_stext & PAGE_OFFSET_48) == PAGE_OFFSET_48) {
+ va_bits = 48;
+ } else {
+ ERRMSG("Cannot find a proper _stext for calculating VA_BITS\n");
+ return FALSE;
+ }
+
+ DEBUG_MSG("va_bits : %d\n", va_bits);
+
+ return TRUE;
+}
+
+static void
+get_page_offset_arm64(void)
+{
+ info->page_offset = (0xffffffffffffffffUL) << (va_bits - 1);
+
+ DEBUG_MSG("page_offset : %lx\n", info->page_offset);
+}
+
int
get_machdep_info_arm64(void)
{
/* Check if va_bits is still not initialized. If still 0, call
* get_versiondep_info() to initialize the same.
*/
+ if (NUMBER(VA_BITS) != NOT_FOUND_NUMBER) {
+ va_bits = NUMBER(VA_BITS);
+ DEBUG_MSG("va_bits : %d (vmcoreinfo)\n",
+ va_bits);
+ }
+
+ /* Check if va_bits is still not initialized. If still 0, call
+ * get_versiondep_info() to initialize the same from _stext
+ * symbol.
+ */
if (!va_bits)
- get_versiondep_info_arm64();
+ if (get_va_bits_from_stext_arm64() == ERROR)
+ return ERROR;
+
+ get_page_offset_arm64();
+
+ if (NUMBER(MAX_USER_VA_BITS) != NOT_FOUND_NUMBER) {
+ max_user_va_bits = NUMBER(MAX_USER_VA_BITS);
+ DEBUG_MSG("max_user_va_bits : %d (vmcoreinfo)\n",
+ max_user_va_bits);
+ }
+
+ /* Check if max_user_va_bits is still not initialized.
+ * If still 0, its not available in vmcoreinfo and its
+ * safe to initialize it with va_bits.
+ */
+ if (!max_user_va_bits) {
+ max_user_va_bits = va_bits;
+ DEBUG_MSG("max_user_va_bits : %d (default = va_bits)\n",
+ max_user_va_bits);
+ }
if (!calculate_plat_config()) {
ERRMSG("Can't determine platform config values\n");
@@ -330,34 +404,11 @@ get_xen_info_arm64(void)
int
get_versiondep_info_arm64(void)
{
- ulong _stext;
-
- _stext = get_stext_symbol();
- if (!_stext) {
- ERRMSG("Can't get the symbol of _stext.\n");
- return FALSE;
- }
-
- /* Derive va_bits as per arch/arm64/Kconfig */
- if ((_stext & PAGE_OFFSET_36) == PAGE_OFFSET_36) {
- va_bits = 36;
- } else if ((_stext & PAGE_OFFSET_39) == PAGE_OFFSET_39) {
- va_bits = 39;
- } else if ((_stext & PAGE_OFFSET_42) == PAGE_OFFSET_42) {
- va_bits = 42;
- } else if ((_stext & PAGE_OFFSET_47) == PAGE_OFFSET_47) {
- va_bits = 47;
- } else if ((_stext & PAGE_OFFSET_48) == PAGE_OFFSET_48) {
- va_bits = 48;
- } else {
- ERRMSG("Cannot find a proper _stext for calculating VA_BITS\n");
- return FALSE;
- }
-
- info->page_offset = (0xffffffffffffffffUL) << (va_bits - 1);
+ if (!va_bits)
+ if (get_va_bits_from_stext_arm64() == ERROR)
+ return ERROR;
- DEBUG_MSG("va_bits : %d\n", va_bits);
- DEBUG_MSG("page_offset : %lx\n", info->page_offset);
+ get_page_offset_arm64();
return TRUE;
}
diff --git a/makedumpfile-1.6.7/makedumpfile.c b/makedumpfile-1.6.7/makedumpfile.c
index d76a435..c8906b5 100644
--- a/makedumpfile-1.6.7/makedumpfile.c
+++ b/makedumpfile-1.6.7/makedumpfile.c
@@ -2313,6 +2313,7 @@ write_vmcoreinfo_data(void)
WRITE_NUMBER("HUGETLB_PAGE_DTOR", HUGETLB_PAGE_DTOR);
#ifdef __aarch64__
+ WRITE_NUMBER("MAX_USER_VA_BITS", MAX_USER_VA_BITS);
WRITE_NUMBER("VA_BITS", VA_BITS);
WRITE_NUMBER_UNSIGNED("PHYS_OFFSET", PHYS_OFFSET);
WRITE_NUMBER_UNSIGNED("kimage_voffset", kimage_voffset);
@@ -2719,6 +2720,7 @@ read_vmcoreinfo(void)
READ_NUMBER("phys_base", phys_base);
READ_NUMBER("KERNEL_IMAGE_SIZE", KERNEL_IMAGE_SIZE);
#ifdef __aarch64__
+ READ_NUMBER("MAX_USER_VA_BITS", MAX_USER_VA_BITS);
READ_NUMBER("VA_BITS", VA_BITS);
READ_NUMBER_UNSIGNED("PHYS_OFFSET", PHYS_OFFSET);
READ_NUMBER_UNSIGNED("kimage_voffset", kimage_voffset);
diff --git a/makedumpfile-1.6.7/makedumpfile.h b/makedumpfile-1.6.7/makedumpfile.h
index 24b2f69..cccb52a 100644
--- a/makedumpfile-1.6.7/makedumpfile.h
+++ b/makedumpfile-1.6.7/makedumpfile.h
@@ -1937,6 +1937,7 @@ struct number_table {
long phys_base;
long KERNEL_IMAGE_SIZE;
#ifdef __aarch64__
+ long MAX_USER_VA_BITS;
long VA_BITS;
unsigned long PHYS_OFFSET;
unsigned long kimage_voffset;
--
2.7.5

128
SOURCES/supported-kdump-targets.txt Normal file
View File

@ -0,0 +1,128 @@
Supported Kdump Targets
This document try to list all supported kdump targets, and those supported
or unknown/tech-preview targets, this can help users to decide whether a dump
solution is available.
Dump Target support status
==========================
This section tries to come up with some kind of guidelines in terms of
what dump targets are supported/not supported. Whatever is listed here
is not binding in any manner. It is just sharing of current understanding
and if something is not right, this section needs to be edited.
Following are 3 lists. First one contains supported targets. These are
generic configurations which should work and some configuration most
likely has worked in testing. Second list is known unsupported targets.
These targets we know either don't work or we don't support. And third
list is unknown/tech-preview. We either don't yet know the status of kdump
on these targets or these are under tech-preview.
Note, these lists are not set in stone and can be changed at any point of
time. Also these lists might not be complete. We will add/remove items to
it as we get more testing information. Also, there are many corner cases
which can't possibly be listed. For example in general we might be
supporting software iscsi but there might be some configurations of it
which don't work.
So if any target is listed in supported section, it does not mean it works
in all possible configurations. It just means that in common configurations
it should work but there can be issues with particular configurations which
are not supported. As we come to know of particular issues, we will keep on
updating lists accordingly.
Supported Dump targets
----------------------
storage:
LVM volume (no thinp)
FC disks (qla2xxx, lpfc, bnx2fc, bfa)
software initiator based iSCSI
software RAID (mdraid)
hardware RAID (cciss, hpsa, megaraid_sas, mpt2sas, aacraid)
SCSI/SATA disks
iSCSI HBA (all offload)
hardware FCoE (qla2xxx, lpfc)
software FCoE (bnx2fc) (Extra configuration required,
please read "Note on FCoE" section below)
network:
Hardware using kernel modules: (tg3, igb, ixgbe, sfc, e1000e, bna,
cnic, netxen_nic, qlge, bnx2x, bnx, qlcnic, be2net, enic,
virtio-net, ixgbevf, igbvf)
protocol: ipv4
bonding
vlan
bridge
team
vlan tagged bonding
bridge over bond/team/vlan
hypervisor:
kvm
xen (Supported in select configurations only)
filesystem:
ext[234]
xfs
nfs
firmware:
BIOS
UEFI
hypervisor:
VMWare ESXi 4.1 and 5.1
Hyper-V 2012 R2 (RHEL Gen1 UP Guest only)
Unsupported Dump targets
------------------------
storage:
BIOS RAID
Thin provisioning volume
Software iSCSI with iBFT (bnx2i, cxgb3i, cxgb4i)
Software iSCSI with hybrid (be2iscsi)
FCoE
legacy IDE
glusterfs
gfs2/clvm/halvm
network:
hardware using kernel modules: (sfc SRIOV, cxgb4vf, pch_gbe)
protocol: ipv6
wireless
Infiniband (IB)
vlan over bridge/team
filesystem:
btrfs
Unknown/tech-preview
--------------------
storage:
PCI Express based SSDs
hypervisor:
Hyper-V 2008
Hyper-V 2012
Note on FCoE
=====================
If you are trying to dump to a software FCoE target, you may encounter OOM
issue, because some software FCoE requires more memory to work. In such case,
you may need to increase the kdump reserved memory size in "crashkernel="
kernel parameter.
By default, RHEL systems have "crashkernel=auto" in kernel boot arguments.
The auto reserved memory size is designed to balance the coverage of use cases
and an acceptable memory overhead, so not every use case could fit in, software
FCoE is one of the case.
For hardware FCoE, kdump should work naturally as firmware will do the
initialization job. The capture kernel and kdump tools will run just fine.
Useful Links
============
[1] RHEL6: Enabling kdump for full-virt (HVM) Xen DomU
(https://access.redhat.com/knowledge/solutions/92943)

2088
SPECS/kexec-tools.spec Normal file
View File

File diff suppressed because it is too large Load Diff