linux/drivers/char/hangcheck-timer.c

176 lines
5.1 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* hangcheck-timer.c
*
* Driver for a little io fencing timer.
*
* Copyright (C) 2002, 2003 Oracle. All rights reserved.
*
* Author: Joel Becker <joel.becker@oracle.com>
*/
/*
* The hangcheck-timer driver uses the TSC to catch delays that
* jiffies does not notice. A timer is set. When the timer fires, it
* checks whether it was delayed and if that delay exceeds a given
* margin of error. The hangcheck_tick module parameter takes the timer
* duration in seconds. The hangcheck_margin parameter defines the
* margin of error, in seconds. The defaults are 60 seconds for the
* timer and 180 seconds for the margin of error. IOW, a timer is set
* for 60 seconds. When the timer fires, the callback checks the
* actual duration that the timer waited. If the duration exceeds the
* allotted time and margin (here 60 + 180, or 240 seconds), the machine
* is restarted. A healthy machine will have the duration match the
* expected timeout very closely.
*/
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/reboot.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/uaccess.h>
#include <linux/sysrq.h>
#include <linux/timer.h>
#include <linux/hrtimer.h>
#define VERSION_STR "0.9.1"
#define DEFAULT_IOFENCE_MARGIN 60 /* Default fudge factor, in seconds */
#define DEFAULT_IOFENCE_TICK 180 /* Default timer timeout, in seconds */
static int hangcheck_tick = DEFAULT_IOFENCE_TICK;
static int hangcheck_margin = DEFAULT_IOFENCE_MARGIN;
static int hangcheck_reboot; /* Defaults to not reboot */
static int hangcheck_dump_tasks; /* Defaults to not dumping SysRQ T */
/* options - modular */
module_param(hangcheck_tick, int, 0);
MODULE_PARM_DESC(hangcheck_tick, "Timer delay.");
module_param(hangcheck_margin, int, 0);
MODULE_PARM_DESC(hangcheck_margin, "If the hangcheck timer has been delayed more than hangcheck_margin seconds, the driver will fire.");
module_param(hangcheck_reboot, int, 0);
MODULE_PARM_DESC(hangcheck_reboot, "If nonzero, the machine will reboot when the timer margin is exceeded.");
module_param(hangcheck_dump_tasks, int, 0);
MODULE_PARM_DESC(hangcheck_dump_tasks, "If nonzero, the machine will dump the system task state when the timer margin is exceeded.");
MODULE_AUTHOR("Oracle");
MODULE_DESCRIPTION("Hangcheck-timer detects when the system has gone out to lunch past a certain margin.");
MODULE_LICENSE("GPL");
MODULE_VERSION(VERSION_STR);
/* options - nonmodular */
#ifndef MODULE
static int __init hangcheck_parse_tick(char *str)
{
int par;
if (get_option(&str,&par))
hangcheck_tick = par;
return 1;
}
static int __init hangcheck_parse_margin(char *str)
{
int par;
if (get_option(&str,&par))
hangcheck_margin = par;
return 1;
}
static int __init hangcheck_parse_reboot(char *str)
{
int par;
if (get_option(&str,&par))
hangcheck_reboot = par;
return 1;
}
static int __init hangcheck_parse_dump_tasks(char *str)
{
int par;
if (get_option(&str,&par))
hangcheck_dump_tasks = par;
return 1;
}
__setup("hcheck_tick", hangcheck_parse_tick);
__setup("hcheck_margin", hangcheck_parse_margin);
__setup("hcheck_reboot", hangcheck_parse_reboot);
__setup("hcheck_dump_tasks", hangcheck_parse_dump_tasks);
#endif /* not MODULE */
#define TIMER_FREQ 1000000000ULL
/* Last time scheduled */
static unsigned long long hangcheck_tsc, hangcheck_tsc_margin;
static void hangcheck_fire(struct timer_list *);
timer: Remove expires and data arguments from DEFINE_TIMER Drop the arguments from the macro and adjust all callers with the following script: perl -pi -e 's/DEFINE_TIMER\((.*), 0, 0\);/DEFINE_TIMER($1);/g;' \ $(git grep DEFINE_TIMER | cut -d: -f1 | sort -u | grep -v timer.h) Signed-off-by: Kees Cook <keescook@chromium.org> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> # for m68k parts Acked-by: Guenter Roeck <linux@roeck-us.net> # for watchdog parts Acked-by: David S. Miller <davem@davemloft.net> # for networking parts Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Kalle Valo <kvalo@codeaurora.org> # for wireless parts Acked-by: Arnd Bergmann <arnd@arndb.de> Cc: linux-mips@linux-mips.org Cc: Petr Mladek <pmladek@suse.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Lai Jiangshan <jiangshanlai@gmail.com> Cc: Sebastian Reichel <sre@kernel.org> Cc: Kalle Valo <kvalo@qca.qualcomm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: linux1394-devel@lists.sourceforge.net Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: linux-s390@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: "James E.J. Bottomley" <jejb@linux.vnet.ibm.com> Cc: Wim Van Sebroeck <wim@iguana.be> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Ursula Braun <ubraun@linux.vnet.ibm.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: Harish Patil <harish.patil@cavium.com> Cc: Stephen Boyd <sboyd@codeaurora.org> Cc: Michael Reed <mdr@sgi.com> Cc: Manish Chopra <manish.chopra@cavium.com> Cc: Len Brown <len.brown@intel.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: linux-pm@vger.kernel.org Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Julian Wiedmann <jwi@linux.vnet.ibm.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Mark Gross <mark.gross@intel.com> Cc: linux-watchdog@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Stefan Richter <stefanr@s5r6.in-berlin.de> Cc: Guenter Roeck <linux@roeck-us.net> Cc: netdev@vger.kernel.org Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: linuxppc-dev@lists.ozlabs.org Cc: Sudip Mukherjee <sudipm.mukherjee@gmail.com> Link: https://lkml.kernel.org/r/1507159627-127660-11-git-send-email-keescook@chromium.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2017-10-04 23:27:04 +00:00
static DEFINE_TIMER(hangcheck_ticktock, hangcheck_fire);
static void hangcheck_fire(struct timer_list *unused)
{
unsigned long long cur_tsc, tsc_diff;
cur_tsc = ktime_get_ns();
if (cur_tsc > hangcheck_tsc)
tsc_diff = cur_tsc - hangcheck_tsc;
else
tsc_diff = (cur_tsc + (~0ULL - hangcheck_tsc)); /* or something */
if (tsc_diff > hangcheck_tsc_margin) {
if (hangcheck_dump_tasks) {
printk(KERN_CRIT "Hangcheck: Task state:\n");
#ifdef CONFIG_MAGIC_SYSRQ
handle_sysrq('t');
#endif /* CONFIG_MAGIC_SYSRQ */
}
if (hangcheck_reboot) {
printk(KERN_CRIT "Hangcheck: hangcheck is restarting the machine.\n");
emergency_restart();
} else {
printk(KERN_CRIT "Hangcheck: hangcheck value past margin!\n");
}
}
#if 0
/*
* Enable to investigate delays in detail
*/
printk("Hangcheck: called %Ld ns since last time (%Ld ns overshoot)\n",
tsc_diff, tsc_diff - hangcheck_tick*TIMER_FREQ);
#endif
mod_timer(&hangcheck_ticktock, jiffies + (hangcheck_tick*HZ));
hangcheck_tsc = ktime_get_ns();
}
static int __init hangcheck_init(void)
{
printk("Hangcheck: starting hangcheck timer %s (tick is %d seconds, margin is %d seconds).\n",
VERSION_STR, hangcheck_tick, hangcheck_margin);
hangcheck_tsc_margin =
(unsigned long long)hangcheck_margin + hangcheck_tick;
hangcheck_tsc_margin *= TIMER_FREQ;
hangcheck_tsc = ktime_get_ns();
mod_timer(&hangcheck_ticktock, jiffies + (hangcheck_tick*HZ));
return 0;
}
static void __exit hangcheck_exit(void)
{
del_timer_sync(&hangcheck_ticktock);
printk("Hangcheck: Stopped hangcheck timer.\n");
}
module_init(hangcheck_init);
module_exit(hangcheck_exit);