Now upon failure kdump script might not be called at all and it might not be able to execute default action. It results in a hang.
Because we disable emergency shell and rely on kdump.sh being invoked through dracut-pre-pivot hook. But it might happen that we never call into dracut-pre-pivot hook because certain systemd targets could not reach due to failure in their dependencies. In those cases error handling code does not run and system hangs.
To solve this problem, we need to separate the error handling code from dracut-pre-pivot hook, and every time when a failure shows up, the separated code can be called by the emergency service.
By default systemd provides an emergency service which will drop us into shell every time upon a critical failure. It's very convenient for us to re-use the framework of systemd emergency, because we don't have to touch the other parts of systemd. We can use our own script instead of the default one.
This new scheme will overwrite emergency shell and replace with kdump error handling code. And this code will do the error handling as needed. Now, we will not rely on dracut-pre-pivot hook running always. Instead whenever error happens and it is serious enough that emergency shell needed to run, now kdump error handler will run.
Signed-off-by: WANG Chao chaowang@redhat.com --- dracut-kdump-emergency.service | 30 ++++++++++++++++++++++++++++++ dracut-kdump-error-handler.sh | 10 ++++++++++ dracut-kdump.sh | 4 ---- dracut-module-setup.sh | 3 +++ kdump-lib-initramfs.sh | 34 ++++++++++++++++++++++++++++++---- kexec-tools.spec | 5 ++++- 6 files changed, 77 insertions(+), 9 deletions(-) create mode 100644 dracut-kdump-emergency.service create mode 100755 dracut-kdump-error-handler.sh
diff --git a/dracut-kdump-emergency.service b/dracut-kdump-emergency.service new file mode 100644 index 0000000..4434b9e --- /dev/null +++ b/dracut-kdump-emergency.service @@ -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 Error Handler +DefaultDependencies=no +After=systemd-vconsole-setup.service +Wants=systemd-vconsole-setup.service + +[Service] +Environment=HOME=/ +Environment=DRACUT_SYSTEMD=1 +Environment=NEWROOT=/sysroot +WorkingDirectory=/ +ExecStart=/bin/kdump-error-handler.sh +ExecStopPost=-/usr/bin/systemctl --fail --no-block default +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 diff --git a/dracut-kdump-error-handler.sh b/dracut-kdump-error-handler.sh new file mode 100755 index 0000000..2f0f1d1 --- /dev/null +++ b/dracut-kdump-error-handler.sh @@ -0,0 +1,10 @@ +#!/bin/sh + +. /lib/kdump-lib-initramfs.sh + +set -o pipefail +export PATH=$PATH:$KDUMP_SCRIPT_DIR + +get_kdump_confs +do_default_action +do_final_action diff --git a/dracut-kdump.sh b/dracut-kdump.sh index 08f4322..1fe91ab 100755 --- a/dracut-kdump.sh +++ b/dracut-kdump.sh @@ -4,10 +4,6 @@ exec &> /dev/console . /lib/dracut-lib.sh . /lib/kdump-lib-initramfs.sh
-if [ -f "$initdir/lib/dracut/no-emergency-shell" ]; then - rm -f -- $initdir/lib/dracut/no-emergency-shell -fi - set -o pipefail DUMP_RETVAL=0
diff --git a/dracut-module-setup.sh b/dracut-module-setup.sh index 84bf975..4799219 100755 --- a/dracut-module-setup.sh +++ b/dracut-module-setup.sh @@ -556,6 +556,9 @@ install() { inst_hook pre-pivot 9999 "$moddir/kdump.sh" inst "/lib/kdump/kdump-lib.sh" "/lib/kdump-lib.sh" inst "/lib/kdump/kdump-lib-initramfs.sh" "/lib/kdump-lib-initramfs.sh" + inst "$moddir/kdump-error-handler.sh" "/usr/bin/kdump-error-handler.sh" + # Replace existing emergency service + cp "$moddir/kdump-emergency.service" "$initdir/$systemdsystemunitdir/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 diff --git a/kdump-lib-initramfs.sh b/kdump-lib-initramfs.sh index b7f0e61..d8cae5c 100755 --- a/kdump-lib-initramfs.sh +++ b/kdump-lib-initramfs.sh @@ -1,6 +1,5 @@ # These variables and functions are useful in 2nd kernel
-. /lib/dracut-lib.sh . /lib/kdump-lib.sh
KDUMP_PATH="/var/crash" @@ -23,6 +22,7 @@ NEWROOT="/sysroot" get_kdump_confs() { local config_opt config_val + local user_specified_cc
while read config_opt config_val; do @@ -34,6 +34,7 @@ get_kdump_confs() ;; core_collector) [ -n "$config_val" ] && CORE_COLLECTOR="$config_val" + user_specified_cc=yes ;; sshkey) if [ -f "$config_val" ]; then @@ -55,7 +56,7 @@ get_kdump_confs() default) case $config_val in shell) - DEFAULT_ACTION="_emergency_shell kdump" + DEFAULT_ACTION="kdump_emergency_shell" ;; reboot) DEFAULT_ACTION="do_umount; reboot -f" @@ -67,12 +68,19 @@ get_kdump_confs() DEFAULT_ACTION="do_umount; poweroff -f" ;; dump_to_rootfs) - DEFAULT_ACTION="dump_fs $NEWROOT" + DEFAULT_ACTION="dump_to_rootfs" ;; esac ;; esac done < $KDUMP_CONF + + if is_ssh_dump_target || is_raw_dump_target; then + if [ -z "$user_specified_cc" ]; then + CORE_COLLECTOR="$CORE_COLLECTOR -F" + fi + fi + }
# dump_fs <mount point| device> @@ -122,6 +130,24 @@ save_vmcore_dmesg_fs() { fi }
+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_umount() { umount -Rf $NEWROOT @@ -129,7 +155,7 @@ do_umount()
do_default_action() { - wait_for_loginit + echo "Kdump: Error Occured, doing default action" eval $DEFAULT_ACTION }
diff --git a/kexec-tools.spec b/kexec-tools.spec index a613b43..b3081bb 100644 --- a/kexec-tools.spec +++ b/kexec-tools.spec @@ -36,6 +36,8 @@ Source24: kdump-lib-initramfs.sh Source100: dracut-kdump.sh Source101: dracut-module-setup.sh Source102: dracut-monitor_dd_progress +Source103: dracut-kdump-error-handler.sh +Source104: dracut-kdump-emergency.service
Requires(post): systemd-units Requires(preun): systemd-units @@ -210,7 +212,8 @@ mkdir -p -m755 $RPM_BUILD_ROOT/etc/kdump-adv-conf/kdump_dracut_modules/99kdumpba cp %{SOURCE100} $RPM_BUILD_ROOT/etc/kdump-adv-conf/kdump_dracut_modules/99kdumpbase/%{remove_dracut_prefix %{SOURCE100}} cp %{SOURCE101} $RPM_BUILD_ROOT/etc/kdump-adv-conf/kdump_dracut_modules/99kdumpbase/%{remove_dracut_prefix %{SOURCE101}} cp %{SOURCE102} $RPM_BUILD_ROOT/etc/kdump-adv-conf/kdump_dracut_modules/99kdumpbase/%{remove_dracut_prefix %{SOURCE102}} - +cp %{SOURCE103} $RPM_BUILD_ROOT/etc/kdump-adv-conf/kdump_dracut_modules/99kdumpbase/%{remove_dracut_prefix %{SOURCE103}} +cp %{SOURCE104} $RPM_BUILD_ROOT/etc/kdump-adv-conf/kdump_dracut_modules/99kdumpbase/%{remove_dracut_prefix %{SOURCE104}} chmod 755 $RPM_BUILD_ROOT/etc/kdump-adv-conf/kdump_dracut_modules/99kdumpbase/%{remove_dracut_prefix %{SOURCE100}} chmod 755 $RPM_BUILD_ROOT/etc/kdump-adv-conf/kdump_dracut_modules/99kdumpbase/%{remove_dracut_prefix %{SOURCE101}}