path: root/kernel/watchdog.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Detect hard and soft lockups on a system
 *
 * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
 *
 * Note: Most of this code is borrowed heavily from the original softlockup
 * detector, so thanks to Ingo for the initial implementation.
 * Some chunks also taken from the old x86-specific nmi watchdog code, thanks
 * to those contributors as well.
 */

#define pr_fmt(fmt) "watchdog: " fmt

#include <linux/mm.h>
#include <linux/cpu.h>
#include <linux/nmi.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <linux/tick.h>
#include <linux/sched/clock.h>
#include <linux/sched/debug.h>
#include <linux/sched/isolation.h>
#include <linux/stop_machine.h>

#include <asm/irq_regs.h>
#include <linux/kvm_para.h>

static DEFINE_MUTEX(watchdog_mutex);

#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HARDLOCKUP_DETECTOR_SPARC64)
# define WATCHDOG_HARDLOCKUP_DEFAULT	1
#else
# define WATCHDOG_HARDLOCKUP_DEFAULT	0
#endif

unsigned long __read_mostly watchdog_enabled;
int __read_mostly watchdog_user_enabled = 1;
static int __read_mostly watchdog_hardlockup_user_enabled = WATCHDOG_HARDLOCKUP_DEFAULT;
static int __read_mostly watchdog_softlockup_user_enabled = 1;
int __read_mostly watchdog_thresh = 10;
static int __read_mostly watchdog_hardlockup_available;

struct cpumask watchdog_cpumask __read_mostly;
unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);

#ifdef CONFIG_HARDLOCKUP_DETECTOR

# ifdef CONFIG_SMP
int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
# endif /* CONFIG_SMP */

/*
 * Should we panic when a soft-lockup or hard-lockup occurs:
 */
unsigned int __read_mostly hardlockup_panic =
			IS_ENABLED(CONFIG_BOOTPARAM_HARDLOCKUP_PANIC);
/*
 * We may not want to enable hard lockup detection by default in all cases,
 * for example when running the kernel as a guest on a hypervisor. In these
 * cases this function can be called to disable hard lockup detection. This
 * function should only be executed once by the boot processor before the
 * kernel command line parameters are parsed, because otherwise it is not
 * possible to override this in hardlockup_panic_setup().
 */
void __init hardlockup_detector_disable(void)
{
	watchdog_hardlockup_user_enabled = 0;
}

static int __init hardlockup_panic_setup(char *str)
{
	if (!strncmp(str, "panic", 5))
		hardlockup_panic = 1;
	else if (!strncmp(str, "nopanic", 7))
		hardlockup_panic = 0;
	else if (!strncmp(str, "0", 1))
		watchdog_hardlockup_user_enabled = 0;
	else if (!strncmp(str, "1", 1))
		watchdog_hardlockup_user_enabled = 1;
	return 1;
}
__setup("nmi_watchdog=", hardlockup_panic_setup);

#endif /* CONFIG_HARDLOCKUP_DETECTOR */

#if defined(CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER)

static DEFINE_PER_CPU(atomic_t, hrtimer_interrupts);
static DEFINE_PER_CPU(int, hrtimer_interrupts_saved);
static DEFINE_PER_CPU(bool, watchdog_hardlockup_warned);
static DEFINE_PER_CPU(bool, watchdog_hardlockup_touched);
static unsigned long hard_lockup_nmi_warn;

notrace void arch_touch_nmi_watchdog(void)
{
	/*
	 * Using __raw here because some code paths have
	 * preemption enabled.  If preemption is enabled
	 * then interrupts should be enabled too, in which
	 * case we shouldn't have to worry about the watchdog
	 * going off.
	 */
	raw_cpu_write(watchdog_hardlockup_touched, true);
}
EXPORT_SYMBOL(arch_touch_nmi_watchdog);

void watchdog_hardlockup_touch_cpu(unsigned int cpu)
{
	per_cpu(watchdog_hardlockup_touched, cpu) = true;
}

static bool is_hardlockup(unsigned int cpu)
{
	int hrint = atomic_read(&per_cpu(hrtimer_interrupts, cpu));

	if (per_cpu(hrtimer_interrupts_saved, cpu) == hrint)
		return true;

	/*
	 * NOTE: we don't need any fancy atomic_t or READ_ONCE/WRITE_ONCE
	 * for hrtimer_interrupts_saved. hrtimer_interrupts_saved is
	 * written/read by a single CPU.
	 */
	per_cpu(hrtimer_interrupts_saved, cpu) = hrint;

	return false;
}

static void watchdog_hardlockup_kick(void)
{
	int new_interrupts;

	new_interrupts = atomic_inc_return(this_cpu_ptr(&hrtimer_interrupts));
	watchdog_buddy_check_hardlockup(new_interrupts);
}

void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
{
	if (per_cpu(watchdog_hardlockup_touched, cpu)) {
		per_cpu(watchdog_hardlockup_touched, cpu) = false;
		return;
	}

	/*
	 * Check for a hardlockup by making sure the CPU's timer
	 * interrupt is incrementing. The timer interrupt should have
	 * fired multiple times before we overflow'd. If it hasn't
	 * then this is a good indication the cpu is stuck
	 */
	if (is_hardlockup(cpu)) {
		unsigned int this_cpu = smp_processor_id();
		unsigned long flags;

		/* Only print hardlockups once. */
		if (per_cpu(watchdog_hardlockup_warned, cpu))
			return;

		/*
		 * Prevent multiple hard-lockup reports if one cpu is already
		 * engaged in dumping all cpu back traces.
		 */
		if (sysctl_hardlockup_all_cpu_backtrace) {
			if (test_and_set_bit_lock(0, &hard_lockup_nmi_warn))
				return;