2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-23 12:43:55 +08:00
linux-next/kernel/softlockup.c
Colin Ian King 8c2eb4805d softlockup: Stop spurious softlockup messages due to overflow
Ensure additions on touch_ts do not overflow.  This can occur
when the top 32 bits of the TSC reach 0xffffffff causing
additions to touch_ts to overflow and this in turn generates
spurious softlockup warnings.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: <stable@kernel.org>
LKML-Reference: <1268994482.1798.6.camel@lenovo>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-21 19:30:13 +01:00

294 lines
7.1 KiB
C

/*
* Detect Soft Lockups
*
* started by Ingo Molnar, Copyright (C) 2005, 2006 Red Hat, Inc.
*
* this code detects soft lockups: incidents in where on a CPU
* the kernel does not reschedule for 10 seconds or more.
*/
#include <linux/mm.h>
#include <linux/cpu.h>
#include <linux/nmi.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/lockdep.h>
#include <linux/notifier.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <asm/irq_regs.h>
static DEFINE_SPINLOCK(print_lock);
static DEFINE_PER_CPU(unsigned long, softlockup_touch_ts); /* touch timestamp */
static DEFINE_PER_CPU(unsigned long, softlockup_print_ts); /* print timestamp */
static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
static DEFINE_PER_CPU(bool, softlock_touch_sync);
static int __read_mostly did_panic;
int __read_mostly softlockup_thresh = 60;
/*
* Should we panic (and reboot, if panic_timeout= is set) when a
* soft-lockup occurs:
*/
unsigned int __read_mostly softlockup_panic =
CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
static int __init softlockup_panic_setup(char *str)
{
softlockup_panic = simple_strtoul(str, NULL, 0);
return 1;
}
__setup("softlockup_panic=", softlockup_panic_setup);
static int
softlock_panic(struct notifier_block *this, unsigned long event, void *ptr)
{
did_panic = 1;
return NOTIFY_DONE;
}
static struct notifier_block panic_block = {
.notifier_call = softlock_panic,
};
/*
* Returns seconds, approximately. We don't need nanosecond
* resolution, and we don't need to waste time with a big divide when
* 2^30ns == 1.074s.
*/
static unsigned long get_timestamp(int this_cpu)
{
return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */
}
static void __touch_softlockup_watchdog(void)
{
int this_cpu = raw_smp_processor_id();
__raw_get_cpu_var(softlockup_touch_ts) = get_timestamp(this_cpu);
}
void touch_softlockup_watchdog(void)
{
__raw_get_cpu_var(softlockup_touch_ts) = 0;
}
EXPORT_SYMBOL(touch_softlockup_watchdog);
void touch_softlockup_watchdog_sync(void)
{
__raw_get_cpu_var(softlock_touch_sync) = true;
__raw_get_cpu_var(softlockup_touch_ts) = 0;
}
void touch_all_softlockup_watchdogs(void)
{
int cpu;
/* Cause each CPU to re-update its timestamp rather than complain */
for_each_online_cpu(cpu)
per_cpu(softlockup_touch_ts, cpu) = 0;
}
EXPORT_SYMBOL(touch_all_softlockup_watchdogs);
int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
touch_all_softlockup_watchdogs();
return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
}
/*
* This callback runs from the timer interrupt, and checks
* whether the watchdog thread has hung or not:
*/
void softlockup_tick(void)
{
int this_cpu = smp_processor_id();
unsigned long touch_ts = per_cpu(softlockup_touch_ts, this_cpu);
unsigned long print_ts;
struct pt_regs *regs = get_irq_regs();
unsigned long now;
/* Is detection switched off? */
if (!per_cpu(softlockup_watchdog, this_cpu) || softlockup_thresh <= 0) {
/* Be sure we don't false trigger if switched back on */
if (touch_ts)
per_cpu(softlockup_touch_ts, this_cpu) = 0;
return;
}
if (touch_ts == 0) {
if (unlikely(per_cpu(softlock_touch_sync, this_cpu))) {
/*
* If the time stamp was touched atomically
* make sure the scheduler tick is up to date.
*/
per_cpu(softlock_touch_sync, this_cpu) = false;
sched_clock_tick();
}
__touch_softlockup_watchdog();
return;
}
print_ts = per_cpu(softlockup_print_ts, this_cpu);
/* report at most once a second */
if (print_ts == touch_ts || did_panic)
return;
/* do not print during early bootup: */
if (unlikely(system_state != SYSTEM_RUNNING)) {
__touch_softlockup_watchdog();
return;
}
now = get_timestamp(this_cpu);
/*
* Wake up the high-prio watchdog task twice per
* threshold timespan.
*/
if (time_after(now - softlockup_thresh/2, touch_ts))
wake_up_process(per_cpu(softlockup_watchdog, this_cpu));
/* Warn about unreasonable delays: */
if (time_before_eq(now - softlockup_thresh, touch_ts))
return;
per_cpu(softlockup_print_ts, this_cpu) = touch_ts;
spin_lock(&print_lock);
printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %lus! [%s:%d]\n",
this_cpu, now - touch_ts,
current->comm, task_pid_nr(current));
print_modules();
print_irqtrace_events(current);
if (regs)
show_regs(regs);
else
dump_stack();
spin_unlock(&print_lock);
if (softlockup_panic)
panic("softlockup: hung tasks");
}
/*
* The watchdog thread - runs every second and touches the timestamp.
*/
static int watchdog(void *__bind_cpu)
{
struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
sched_setscheduler(current, SCHED_FIFO, &param);
/* initialize timestamp */
__touch_softlockup_watchdog();
set_current_state(TASK_INTERRUPTIBLE);
/*
* Run briefly once per second to reset the softlockup timestamp.
* If this gets delayed for more than 60 seconds then the
* debug-printout triggers in softlockup_tick().
*/
while (!kthread_should_stop()) {
__touch_softlockup_watchdog();
schedule();
if (kthread_should_stop())
break;
set_current_state(TASK_INTERRUPTIBLE);
}
__set_current_state(TASK_RUNNING);
return 0;
}
/*
* Create/destroy watchdog threads as CPUs come and go:
*/
static int __cpuinit
cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
int hotcpu = (unsigned long)hcpu;
struct task_struct *p;
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
BUG_ON(per_cpu(softlockup_watchdog, hotcpu));
p = kthread_create(watchdog, hcpu, "watchdog/%d", hotcpu);
if (IS_ERR(p)) {
printk(KERN_ERR "watchdog for %i failed\n", hotcpu);
return NOTIFY_BAD;
}
per_cpu(softlockup_touch_ts, hotcpu) = 0;
per_cpu(softlockup_watchdog, hotcpu) = p;
kthread_bind(p, hotcpu);
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
wake_up_process(per_cpu(softlockup_watchdog, hotcpu));
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
if (!per_cpu(softlockup_watchdog, hotcpu))
break;
/* Unbind so it can run. Fall thru. */
kthread_bind(per_cpu(softlockup_watchdog, hotcpu),
cpumask_any(cpu_online_mask));
case CPU_DEAD:
case CPU_DEAD_FROZEN:
p = per_cpu(softlockup_watchdog, hotcpu);
per_cpu(softlockup_watchdog, hotcpu) = NULL;
kthread_stop(p);
break;
#endif /* CONFIG_HOTPLUG_CPU */
}
return NOTIFY_OK;
}
static struct notifier_block __cpuinitdata cpu_nfb = {
.notifier_call = cpu_callback
};
static int __initdata nosoftlockup;
static int __init nosoftlockup_setup(char *str)
{
nosoftlockup = 1;
return 1;
}
__setup("nosoftlockup", nosoftlockup_setup);
static int __init spawn_softlockup_task(void)
{
void *cpu = (void *)(long)smp_processor_id();
int err;
if (nosoftlockup)
return 0;
err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
if (err == NOTIFY_BAD) {
BUG();
return 1;
}
cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
register_cpu_notifier(&cpu_nfb);
atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
return 0;
}
early_initcall(spawn_softlockup_task);