linux/kernel/panic.c
Andrew Morton dd287796d6 [PATCH] pause_on_oops command line option
Attempt to fix the problem wherein people's oops reports scroll off the screen
due to repeated oopsing or to oopses on other CPUs.

If this happens the user can reboot with the `pause_on_oops=<seconds>' option.
It will allow the first oopsing CPU to print an oops record just a single
time.  Second oopsing attempts, or oopses on other CPUs will cause those CPUs
to enter a tight loop until the specified number of seconds have elapsed.

The patch implements the infrastructure generically in the expectation that
architectures other than x86 will find it useful.

Cc: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-23 07:38:16 -08:00

271 lines
6.2 KiB
C

/*
* linux/kernel/panic.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
/*
* This function is used through-out the kernel (including mm and fs)
* to indicate a major problem.
*/
#include <linux/config.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/delay.h>
#include <linux/reboot.h>
#include <linux/notifier.h>
#include <linux/init.h>
#include <linux/sysrq.h>
#include <linux/interrupt.h>
#include <linux/nmi.h>
#include <linux/kexec.h>
int panic_on_oops;
int tainted;
static int pause_on_oops;
static int pause_on_oops_flag;
static DEFINE_SPINLOCK(pause_on_oops_lock);
int panic_timeout;
EXPORT_SYMBOL(panic_timeout);
struct notifier_block *panic_notifier_list;
EXPORT_SYMBOL(panic_notifier_list);
static int __init panic_setup(char *str)
{
panic_timeout = simple_strtoul(str, NULL, 0);
return 1;
}
__setup("panic=", panic_setup);
static long no_blink(long time)
{
return 0;
}
/* Returns how long it waited in ms */
long (*panic_blink)(long time);
EXPORT_SYMBOL(panic_blink);
/**
* panic - halt the system
* @fmt: The text string to print
*
* Display a message, then perform cleanups.
*
* This function never returns.
*/
NORET_TYPE void panic(const char * fmt, ...)
{
long i;
static char buf[1024];
va_list args;
#if defined(CONFIG_S390)
unsigned long caller = (unsigned long) __builtin_return_address(0);
#endif
/*
* It's possible to come here directly from a panic-assertion and not
* have preempt disabled. Some functions called from here want
* preempt to be disabled. No point enabling it later though...
*/
preempt_disable();
bust_spinlocks(1);
va_start(args, fmt);
vsnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf);
bust_spinlocks(0);
/*
* If we have crashed and we have a crash kernel loaded let it handle
* everything else.
* Do we want to call this before we try to display a message?
*/
crash_kexec(NULL);
#ifdef CONFIG_SMP
/*
* Note smp_send_stop is the usual smp shutdown function, which
* unfortunately means it may not be hardened to work in a panic
* situation.
*/
smp_send_stop();
#endif
notifier_call_chain(&panic_notifier_list, 0, buf);
if (!panic_blink)
panic_blink = no_blink;
if (panic_timeout > 0) {
/*
* Delay timeout seconds before rebooting the machine.
* We can't use the "normal" timers since we just panicked..
*/
printk(KERN_EMERG "Rebooting in %d seconds..",panic_timeout);
for (i = 0; i < panic_timeout*1000; ) {
touch_nmi_watchdog();
i += panic_blink(i);
mdelay(1);
i++;
}
/* This will not be a clean reboot, with everything
* shutting down. But if there is a chance of
* rebooting the system it will be rebooted.
*/
emergency_restart();
}
#ifdef __sparc__
{
extern int stop_a_enabled;
/* Make sure the user can actually press Stop-A (L1-A) */
stop_a_enabled = 1;
printk(KERN_EMERG "Press Stop-A (L1-A) to return to the boot prom\n");
}
#endif
#if defined(CONFIG_S390)
disabled_wait(caller);
#endif
local_irq_enable();
for (i = 0;;) {
touch_softlockup_watchdog();
i += panic_blink(i);
mdelay(1);
i++;
}
}
EXPORT_SYMBOL(panic);
/**
* print_tainted - return a string to represent the kernel taint state.
*
* 'P' - Proprietary module has been loaded.
* 'F' - Module has been forcibly loaded.
* 'S' - SMP with CPUs not designed for SMP.
* 'R' - User forced a module unload.
* 'M' - Machine had a machine check experience.
* 'B' - System has hit bad_page.
*
* The string is overwritten by the next call to print_taint().
*/
const char *print_tainted(void)
{
static char buf[20];
if (tainted) {
snprintf(buf, sizeof(buf), "Tainted: %c%c%c%c%c%c",
tainted & TAINT_PROPRIETARY_MODULE ? 'P' : 'G',
tainted & TAINT_FORCED_MODULE ? 'F' : ' ',
tainted & TAINT_UNSAFE_SMP ? 'S' : ' ',
tainted & TAINT_FORCED_RMMOD ? 'R' : ' ',
tainted & TAINT_MACHINE_CHECK ? 'M' : ' ',
tainted & TAINT_BAD_PAGE ? 'B' : ' ');
}
else
snprintf(buf, sizeof(buf), "Not tainted");
return(buf);
}
void add_taint(unsigned flag)
{
tainted |= flag;
}
EXPORT_SYMBOL(add_taint);
static int __init pause_on_oops_setup(char *str)
{
pause_on_oops = simple_strtoul(str, NULL, 0);
return 1;
}
__setup("pause_on_oops=", pause_on_oops_setup);
static void spin_msec(int msecs)
{
int i;
for (i = 0; i < msecs; i++) {
touch_nmi_watchdog();
mdelay(1);
}
}
/*
* It just happens that oops_enter() and oops_exit() are identically
* implemented...
*/
static void do_oops_enter_exit(void)
{
unsigned long flags;
static int spin_counter;
if (!pause_on_oops)
return;
spin_lock_irqsave(&pause_on_oops_lock, flags);
if (pause_on_oops_flag == 0) {
/* This CPU may now print the oops message */
pause_on_oops_flag = 1;
} else {
/* We need to stall this CPU */
if (!spin_counter) {
/* This CPU gets to do the counting */
spin_counter = pause_on_oops;
do {
spin_unlock(&pause_on_oops_lock);
spin_msec(MSEC_PER_SEC);
spin_lock(&pause_on_oops_lock);
} while (--spin_counter);
pause_on_oops_flag = 0;
} else {
/* This CPU waits for a different one */
while (spin_counter) {
spin_unlock(&pause_on_oops_lock);
spin_msec(1);
spin_lock(&pause_on_oops_lock);
}
}
}
spin_unlock_irqrestore(&pause_on_oops_lock, flags);
}
/*
* Return true if the calling CPU is allowed to print oops-related info. This
* is a bit racy..
*/
int oops_may_print(void)
{
return pause_on_oops_flag == 0;
}
/*
* Called when the architecture enters its oops handler, before it prints
* anything. If this is the first CPU to oops, and it's oopsing the first time
* then let it proceed.
*
* This is all enabled by the pause_on_oops kernel boot option. We do all this
* to ensure that oopses don't scroll off the screen. It has the side-effect
* of preventing later-oopsing CPUs from mucking up the display, too.
*
* It turns out that the CPU which is allowed to print ends up pausing for the
* right duration, whereas all the other CPUs pause for twice as long: once in
* oops_enter(), once in oops_exit().
*/
void oops_enter(void)
{
do_oops_enter_exit();
}
/*
* Called when the architecture exits its oops handler, after printing
* everything.
*/
void oops_exit(void)
{
do_oops_enter_exit();
}