Merge branch 'core-watchdog-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull watchddog clean-up and fixes from Thomas Gleixner:
 "The watchdog (hard/softlockup detector) code is pretty much broken in
  its current state. The patch series addresses this by removing all
  duct tape and refactoring it into a workable state.

  The reasons why I ask for inclusion that late in the cycle are:

   1) The code causes lockdep splats vs. hotplug locking which get
      reported over and over. Unfortunately there is no easy fix.

   2) The risk of breakage is minimal because it's already broken

   3) As 4.14 is a long term stable kernel, I prefer to have working
      watchdog code in that and the lockdep issues resolved. I wouldn't
      ask you to pull if 4.14 wouldn't be a LTS kernel or if the
      solution would be easy to backport.

   4) The series was around before the merge window opened, but then got
      delayed due to the UP failure caused by the for_each_cpu()
      surprise which we discussed recently.

  Changes vs. V1:

   - Addressed your review points

   - Addressed the warning in the powerpc code which was discovered late

   - Changed two function names which made sense up to a certain point
     in the series. Now they match what they do in the end.

   - Fixed a 'unused variable' warning, which got not detected by the
     intel robot. I triggered it when trying all possible related config
     combinations manually. Randconfig testing seems not random enough.

  The changes have been tested by and reviewed by Don Zickus and tested
  and acked by Micheal Ellerman for powerpc"

* 'core-watchdog-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
  watchdog/core: Put softlockup_threads_initialized under ifdef guard
  watchdog/core: Rename some softlockup_* functions
  powerpc/watchdog: Make use of watchdog_nmi_probe()
  watchdog/core, powerpc: Lock cpus across reconfiguration
  watchdog/core, powerpc: Replace watchdog_nmi_reconfigure()
  watchdog/hardlockup/perf: Fix spelling mistake: "permanetely" -> "permanently"
  watchdog/hardlockup/perf: Cure UP damage
  watchdog/hardlockup: Clean up hotplug locking mess
  watchdog/hardlockup/perf: Simplify deferred event destroy
  watchdog/hardlockup/perf: Use new perf CPU enable mechanism
  watchdog/hardlockup/perf: Implement CPU enable replacement
  watchdog/hardlockup/perf: Implement init time detection of perf
  watchdog/hardlockup/perf: Implement init time perf validation
  watchdog/core: Get rid of the racy update loop
  watchdog/core, powerpc: Make watchdog_nmi_reconfigure() two stage
  watchdog/sysctl: Clean up sysctl variable name space
  watchdog/sysctl: Get rid of the #ifdeffery
  watchdog/core: Clean up header mess
  watchdog/core: Further simplify sysctl handling
  watchdog/core: Get rid of the thread teardown/setup dance
  ...

5 files changed, 372 insertions, 520 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 8de11a29e495..d851df22f5c5 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -24,6 +24,7 @@
 #include <linux/lockdep.h>
 #include <linux/tick.h>
 #include <linux/irq.h>
+#include <linux/nmi.h>
 #include <linux/smpboot.h>
 #include <linux/relay.h>
 #include <linux/slab.h>
@@ -897,6 +898,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 
 out:
 	cpus_write_unlock();
+	/*
+	 * Do post unplug cleanup. This is still protected against
+	 * concurrent CPU hotplug via cpu_add_remove_lock.
+	 */
+	lockup_detector_cleanup();
 	return ret;
 }
 
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 1d71c051a951..5043e7433f4b 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -344,39 +344,30 @@ EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread);
  * by the client, but only by calling this function.
  * This function can only be called on a registered smp_hotplug_thread.
  */
-int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
-					 const struct cpumask *new)
+void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
+					  const struct cpumask *new)
 {
 	struct cpumask *old = plug_thread->cpumask;
-	cpumask_var_t tmp;
+	static struct cpumask tmp;
 	unsigned int cpu;
 
-	if (!alloc_cpumask_var(&tmp, GFP_KERNEL))
-		return -ENOMEM;
-
-	get_online_cpus();
+	lockdep_assert_cpus_held();
 	mutex_lock(&smpboot_threads_lock);
 
 	/* Park threads that were exclusively enabled on the old mask. */
-	cpumask_andnot(tmp, old, new);
-	for_each_cpu_and(cpu, tmp, cpu_online_mask)
+	cpumask_andnot(&tmp, old, new);
+	for_each_cpu_and(cpu, &tmp, cpu_online_mask)
 		smpboot_park_thread(plug_thread, cpu);
 
 	/* Unpark threads that are exclusively enabled on the new mask. */
-	cpumask_andnot(tmp, new, old);
-	for_each_cpu_and(cpu, tmp, cpu_online_mask)
+	cpumask_andnot(&tmp, new, old);
+	for_each_cpu_and(cpu, &tmp, cpu_online_mask)
 		smpboot_unpark_thread(plug_thread, cpu);
 
 	cpumask_copy(old, new);
 
 	mutex_unlock(&smpboot_threads_lock);
-	put_online_cpus();
-
-	free_cpumask_var(tmp);
-
-	return 0;
 }
-EXPORT_SYMBOL_GPL(smpboot_update_cpumask_percpu_thread);
 
 static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD);
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4da9e622471f..d9c31bc2eaea 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -872,9 +872,9 @@ static struct ctl_table kern_table[] = {
 #if defined(CONFIG_LOCKUP_DETECTOR)
 	{
 		.procname       = "watchdog",
-		.data           = &watchdog_user_enabled,
-		.maxlen         = sizeof (int),
-		.mode           = 0644,
+		.data		= &watchdog_user_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
 		.proc_handler   = proc_watchdog,
 		.extra1		= &zero,
 		.extra2		= &one,
@@ -890,16 +890,12 @@ static struct ctl_table kern_table[] = {
 	},
 	{
 		.procname       = "nmi_watchdog",
-		.data           = &nmi_watchdog_enabled,
-		.maxlen         = sizeof (int),
-		.mode           = 0644,
+		.data		= &nmi_watchdog_user_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= NMI_WATCHDOG_SYSCTL_PERM,
 		.proc_handler   = proc_nmi_watchdog,
 		.extra1		= &zero,
-#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
 		.extra2		= &one,
-#else
-		.extra2		= &zero,
-#endif
 	},
 	{
 		.procname	= "watchdog_cpumask",
@@ -911,9 +907,9 @@ static struct ctl_table kern_table[] = {
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
 	{
 		.procname       = "soft_watchdog",
-		.data           = &soft_watchdog_enabled,
-		.maxlen         = sizeof (int),
-		.mode           = 0644,
+		.data		= &soft_watchdog_user_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
 		.proc_handler   = proc_soft_watchdog,
 		.extra1		= &zero,
 		.extra2		= &one,
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index f5d52024f6b7..6bcb854909c0 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -29,20 +29,29 @@
 #include <linux/kvm_para.h>
 #include <linux/kthread.h>
 
-/* Watchdog configuration */
-static DEFINE_MUTEX(watchdog_proc_mutex);
-
-int __read_mostly nmi_watchdog_enabled;
+static DEFINE_MUTEX(watchdog_mutex);
 
 #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG)
-unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED |
-						NMI_WATCHDOG_ENABLED;
+# define WATCHDOG_DEFAULT	(SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED)
+# define NMI_WATCHDOG_DEFAULT	1
 #else
-unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED;
+# define WATCHDOG_DEFAULT	(SOFT_WATCHDOG_ENABLED)
+# define NMI_WATCHDOG_DEFAULT	0
 #endif
 
+unsigned long __read_mostly watchdog_enabled;
+int __read_mostly watchdog_user_enabled = 1;
+int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT;
+int __read_mostly soft_watchdog_user_enabled = 1;
+int __read_mostly watchdog_thresh = 10;
+int __read_mostly nmi_watchdog_available;
+
+struct cpumask watchdog_allowed_mask __read_mostly;
+
+struct cpumask watchdog_cpumask __read_mostly;
+unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
+
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
-/* boot commands */
 /*
  * Should we panic when a soft-lockup or hard-lockup occurs:
  */
@@ -56,9 +65,9 @@ unsigned int __read_mostly hardlockup_panic =
  * kernel command line parameters are parsed, because otherwise it is not
  * possible to override this in hardlockup_panic_setup().
  */
-void hardlockup_detector_disable(void)
+void __init hardlockup_detector_disable(void)
 {
-	watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+	nmi_watchdog_user_enabled = 0;
 }
 
 static int __init hardlockup_panic_setup(char *str)
@@ -68,48 +77,24 @@ static int __init hardlockup_panic_setup(char *str)
 	else if (!strncmp(str, "nopanic", 7))
 		hardlockup_panic = 0;
 	else if (!strncmp(str, "0", 1))
-		watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+		nmi_watchdog_user_enabled = 0;
 	else if (!strncmp(str, "1", 1))
-		watchdog_enabled |= NMI_WATCHDOG_ENABLED;
+		nmi_watchdog_user_enabled = 1;
 	return 1;
 }
 __setup("nmi_watchdog=", hardlockup_panic_setup);
 
-#endif
-
-#ifdef CONFIG_SOFTLOCKUP_DETECTOR
-int __read_mostly soft_watchdog_enabled;
-#endif
-
-int __read_mostly watchdog_user_enabled;
-int __read_mostly watchdog_thresh = 10;
-
-#ifdef CONFIG_SMP
-int __read_mostly sysctl_softlockup_all_cpu_backtrace;
+# ifdef CONFIG_SMP
 int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
-#endif
-struct cpumask watchdog_cpumask __read_mostly;
-unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
 
-/*
- * The 'watchdog_running' variable is set to 1 when the watchdog threads
- * are registered/started and is set to 0 when the watchdog threads are
- * unregistered/stopped, so it is an indicator whether the threads exist.
- */
-static int __read_mostly watchdog_running;
-/*
- * If a subsystem has a need to deactivate the watchdog temporarily, it
- * can use the suspend/resume interface to achieve this. The content of
- * the 'watchdog_suspended' variable reflects this state. Existing threads
- * are parked/unparked by the lockup_detector_{suspend|resume} functions
- * (see comment blocks pertaining to those functions for further details).
- *
- * 'watchdog_suspended' also prevents threads from being registered/started
- * or unregistered/stopped via parameters in /proc/sys/kernel, so the state
- * of 'watchdog_running' cannot change while the watchdog is deactivated
- * temporarily (see related code in 'proc' handlers).
- */
-int __read_mostly watchdog_suspended;
+static int __init hardlockup_all_cpu_backtrace_setup(char *str)
+{
+	sysctl_hardlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0);
+	return 1;
+}
+__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup);
+# endif /* CONFIG_SMP */
+#endif /* CONFIG_HARDLOCKUP_DETECTOR */
 
 /*
  * These functions can be overridden if an architecture implements its
@@ -121,36 +106,68 @@ int __read_mostly watchdog_suspended;
  */
 int __weak watchdog_nmi_enable(unsigned int cpu)
 {
+	hardlockup_detector_perf_enable();
 	return 0;
 }
+
 void __weak watchdog_nmi_disable(unsigned int cpu)
 {
+	hardlockup_detector_perf_disable();
 }
 
-/*
- * watchdog_nmi_reconfigure can be implemented to be notified after any
- * watchdog configuration change. The arch hardlockup watchdog should
- * respond to the following variables:
- * - nmi_watchdog_enabled
+/* Return 0, if a NMI watchdog is available. Error code otherwise */
+int __weak __init watchdog_nmi_probe(void)
+{
+	return hardlockup_detector_perf_init();
+}
+
+/**
+ * watchdog_nmi_stop - Stop the watchdog for reconfiguration
+ *
+ * The reconfiguration steps are:
+ * watchdog_nmi_stop();
+ * update_variables();
+ * watchdog_nmi_start();
+ */
+void __weak watchdog_nmi_stop(void) { }
+
+/**
+ * watchdog_nmi_start - Start the watchdog after reconfiguration
+ *
+ * Counterpart to watchdog_nmi_stop().
+ *
+ * The following variables have been updated in update_variables() and
+ * contain the currently valid configuration:
+ * - watchdog_enabled
  * - watchdog_thresh
  * - watchdog_cpumask
- * - sysctl_hardlockup_all_cpu_backtrace
- * - hardlockup_panic
- * - watchdog_suspended
  */
-void __weak watchdog_nmi_reconfigure(void)
+void __weak watchdog_nmi_start(void) { }
+
+/**
+ * lockup_detector_update_enable - Update the sysctl enable bit
+ *
+ * Caller needs to make sure that the NMI/perf watchdogs are off, so this
+ * can't race with watchdog_nmi_disable().
+ */
+static void lockup_detector_update_enable(void)
 {
+	watchdog_enabled = 0;
+	if (!watchdog_user_enabled)
+		return;
+	if (nmi_watchdog_available && nmi_watchdog_user_enabled)
+		watchdog_enabled |= NMI_WATCHDOG_ENABLED;
+	if (soft_watchdog_user_enabled)
+		watchdog_enabled |= SOFT_WATCHDOG_ENABLED;
 }
 
-
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
 
-/* Helper for online, unparked cpus. */
-#define for_each_watchdog_cpu(cpu) \
-	for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
-
-atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);
+/* Global variables, exported for sysctl */
+unsigned int __read_mostly softlockup_panic =
+			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
 
+static bool softlockup_threads_initialized __read_mostly;
 static u64 __read_mostly sample_period;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
@@ -164,50 +181,40 @@ static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static unsigned long soft_lockup_nmi_warn;
 
-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 __init nowatchdog_setup(char *str)
 {
-	watchdog_enabled = 0;
+	watchdog_user_enabled = 0;
 	return 1;
 }
 __setup("nowatchdog", nowatchdog_setup);
 
 static int __init nosoftlockup_setup(char *str)
 {
-	watchdog_enabled &= ~SOFT_WATCHDOG_ENABLED;
+	soft_watchdog_user_enabled = 0;
 	return 1;
 }
 __setup("nosoftlockup", nosoftlockup_setup);
 
 #ifdef CONFIG_SMP
+int __read_mostly sysctl_softlockup_all_cpu_backtrace;
+
 static int __init softlockup_all_cpu_backtrace_setup(char *str)
 {
-	sysctl_softlockup_all_cpu_backtrace =
-		!!simple_strtol(str, NULL, 0);
+	sysctl_softlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0);
 	return 1;
 }
 __setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup);
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-static int __init hardlockup_all_cpu_backtrace_setup(char *str)
-{
-	sysctl_hardlockup_all_cpu_backtrace =
-		!!simple_strtol(str, NULL, 0);
-	return 1;
-}
-__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup);
-#endif
 #endif
 
+static void __lockup_detector_cleanup(void);
+
 /*
  * Hard-lockup warnings should be triggered after just a few seconds. Soft-
  * lockups can have false positives under extreme conditions. So we generally
@@ -278,11 +285,15 @@ void touch_all_softlockup_watchdogs(void)
 	int cpu;
 
 	/*
-	 * this is done lockless
-	 * do we care if a 0 races with a timestamp?
-	 * all it means is the softlock check starts one cycle later
+	 * watchdog_mutex cannpt be taken here, as this might be called
+	 * from (soft)interrupt context, so the access to
+	 * watchdog_allowed_cpumask might race with a concurrent update.
+	 *
+	 * The watchdog time stamp can race against a concurrent real
+	 * update as well, the only side effect might be a cycle delay for
+	 * the softlockup check.
 	 */
-	for_each_watchdog_cpu(cpu)
+	for_each_cpu(cpu, &watchdog_allowed_mask)
 		per_cpu(watchdog_touch_ts, cpu) = 0;
 	wq_watchdog_touch(-1);
 }
@@ -322,9 +333,6 @@ static void watchdog_interrupt_count(void)
 	__this_cpu_inc(hrtimer_interrupts);
 }
 
-static int watchdog_enable_all_cpus(void);
-static void watchdog_disable_all_cpus(void);
-
 /* watchdog kicker functions */
 static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
@@ -333,7 +341,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	int duration;
 	int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
 
-	if (atomic_read(&watchdog_park_in_progress) != 0)
+	if (!watchdog_enabled)
 		return HRTIMER_NORESTART;
 
 	/* kick the hardlockup detector */
@@ -447,32 +455,38 @@ static void watchdog_set_prio(unsigned int policy, unsigned int prio)
 
 static void watchdog_enable(unsigned int cpu)
 {
-	struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer);
+	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
 
-	/* kick off the timer for the hardlockup detector */
+	/*
+	 * Start the timer first to prevent the NMI watchdog triggering
+	 * before the timer has a chance to fire.
+	 */
 	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer->function = watchdog_timer_fn;
-
-	/* Enable the perf event */
-	watchdog_nmi_enable(cpu);
-
-	/* done here because hrtimer_start can only pin to smp_processor_id() */
 	hrtimer_start(hrtimer, ns_to_ktime(sample_period),
 		      HRTIMER_MODE_REL_PINNED);
 
-	/* initialize timestamp */
-	watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
+	/* Initialize timestamp */
 	__touch_watchdog();
+	/* Enable the perf event */
+	if (watchdog_enabled & NMI_WATCHDOG_ENABLED)
+		watchdog_nmi_enable(cpu);
+
+	watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
 }
 
 static void watchdog_disable(unsigned int cpu)
 {
-	struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer);
+	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
 
 	watchdog_set_prio(SCHED_NORMAL, 0);
-	hrtimer_cancel(hrtimer);
-	/* disable the perf event */
+	/*
+	 * Disable the perf event first. That prevents that a large delay
+	 * between disabling the timer and disabling the perf event causes
+	 * the perf NMI to detect a false positive.
+	 */
 	watchdog_nmi_disable(cpu);
+	hrtimer_cancel(hrtimer);
 }
 
 static void watchdog_cleanup(unsigned int cpu, bool online)
@@ -499,21 +513,6 @@ static void watchdog(unsigned int cpu)
 	__this_cpu_write(soft_lockup_hrtimer_cnt,
 			 __this_cpu_read(hrtimer_interrupts));
 	__touch_watchdog();
-
-	/*
-	 * watchdog_nmi_enable() clears the NMI_WATCHDOG_ENABLED bit in the
-	 * failure path. Check for failures that can occur asynchronously -
-	 * for example, when CPUs are on-lined - and shut down the hardware
-	 * perf event on each CPU accordingly.
-	 *
-	 * The only non-obvious place this bit can be cleared is through
-	 * watchdog_nmi_enable(), so a pr_info() is placed there.  Placing a
-	 * pr_info here would be too noisy as it would result in a message
-	 * every few seconds if the hardlockup was disabled but the softlockup
-	 * enabled.
-	 */
-	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
-		watchdog_nmi_disable(cpu);
 }
 
 static struct smp_hotplug_thread watchdog_threads = {
@@ -527,295 +526,174 @@ static struct smp_hotplug_thread watchdog_threads = {
 	.unpark			= watchdog_enable,
 };
 
-/*
- * park all watchdog threads that are specified in 'watchdog_cpumask'
- *
- * This function returns an error if kthread_park() of a watchdog thread
- * fails. In this situation, the watchdog threads of some CPUs can already
- * be parked and the watchdog threads of other CPUs can still be runnable.
- * Callers are expected to handle this special condition as appropriate in
- * their context.
- *
- * This function may only be called in a context that is protected against
- * races with CPU hotplug - for example, via get_online_cpus().
- */
-static int watchdog_park_threads(void)
+static void softlockup_update_smpboot_threads(void)
 {
-	int cpu, ret = 0;
+	lockdep_assert_held(&watchdog_mutex);
 
-	atomic_set(&watchdog_park_in_progress, 1);
+	if (!softlockup_threads_initialized)
+		return;
 
-	for_each_watchdog_cpu(cpu) {
-		ret = kthread_park(per_cpu(softlockup_watchdog, cpu));
-		if (ret)
-			break;
-	}
-
-	atomic_set(&watchdog_park_in_progress, 0);
-
-	return ret;
+	smpboot_update_cpumask_percpu_thread(&watchdog_threads,
+					     &watchdog_allowed_mask);
 }
 
-/*
- * unpark all watchdog threads that are specified in 'watchdog_cpumask'
- *
- * This function may only be called in a context that is protected against
- * races with CPU hotplug - for example, via get_online_cpus().
- */
-static void watchdog_unpark_threads(void)
+/* Temporarily park all watchdog threads */
+static void softlockup_park_all_threads(void)
 {
-	int cpu;
-
-	for_each_watchdog_cpu(cpu)
-		kthread_unpark(per_cpu(softlockup_watchdog, cpu));
+	cpumask_clear(&watchdog_allowed_mask);
+	softlockup_update_smpboot_threads();
 }
 
-static int update_watchdog_all_cpus(void)
+/* Unpark enabled threads */
+static void softlockup_unpark_threads(void)
 {
-	int ret;
-
-	ret = watchdog_park_threads();
-	if (ret)
-		return ret;
-
-	watchdog_unpark_threads();
-
-	return 0;
+	cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
+	softlockup_update_smpboot_threads();
 }
 
-static int watchdog_enable_all_cpus(void)
+static void lockup_detector_reconfigure(void)
 {
-	int err = 0;
-
-	if (!watchdog_running) {
-		err = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
-							     &watchdog_cpumask);
-		if (err)
-			pr_err("Failed to create watchdog threads, disabled\n");
-		else
-			watchdog_running = 1;
-	} else {
-		/*
-		 * Enable/disable the lockup detectors or
-		 * change the sample period 'on the fly'.
-		 */
-		err = update_watchdog_all_cpus();
-
-		if (err) {
-			watchdog_disable_all_cpus();
-			pr_err("Failed to update lockup detectors, disabled\n");
-		}
-	}
-
-	if (err)
-		watchdog_enabled = 0;
-
-	return err;
+	cpus_read_lock();
+	watchdog_nmi_stop();
+	softlockup_park_all_threads();
+	set_sample_period();
+	lockup_detector_update_enable();
+	if (watchdog_enabled && watchdog_thresh)
+		softlockup_unpark_threads();
+	watchdog_nmi_start();
+	cpus_read_unlock();
+	/*
+	 * Must be called outside the cpus locked section to prevent
+	 * recursive locking in the perf code.
+	 */
+	__lockup_detector_cleanup();
 }
 
-static void watchdog_disable_all_cpus(void)
+/*
+ * Create the watchdog thread infrastructure and configure the detector(s).
+ *
+ * The threads are not unparked as watchdog_allowed_mask is empty.  When
+ * the threads are sucessfully initialized, take the proper locks and
+ * unpark the threads in the watchdog_cpumask if the watchdog is enabled.
+ */
+static __init void lockup_detector_setup(void)
 {
-	if (watchdog_running) {
-		watchdog_running = 0;
-		smpboot_unregister_percpu_thread(&watchdog_threads);
-	}
-}
+	int ret;
 
-#ifdef CONFIG_SYSCTL
-static int watchdog_update_cpus(void)
-{
-	return smpboot_update_cpumask_percpu_thread(
-		    &watchdog_threads, &watchdog_cpumask);
-}
-#endif
+	/*
+	 * If sysctl is off and watchdog got disabled on the command line,
+	 * nothing to do here.
+	 */
+	lockup_detector_update_enable();
 
-#else /* SOFTLOCKUP */
-static int watchdog_park_threads(void)
-{
-	return 0;
-}
+	if (!IS_ENABLED(CONFIG_SYSCTL) &&
+	    !(watchdog_enabled && watchdog_thresh))
+		return;
 
-static void watchdog_unpark_threads(void)
-{
-}
+	ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
+						     &watchdog_allowed_mask);
+	if (ret) {
+		pr_err("Failed to initialize soft lockup detector threads\n");
+		return;
+	}
 
-static int watchdog_enable_all_cpus(void)
-{
-	return 0;
+	mutex_lock(&watchdog_mutex);
+	softlockup_threads_initialized = true;
+	lockup_detector_reconfigure();
+	mutex_unlock(&watchdog_mutex);
 }
 
-static void watchdog_disable_all_cpus(void)
+#else /* CONFIG_SOFTLOCKUP_DETECTOR */
+static inline int watchdog_park_threads(void) { return 0; }
+static inline void watchdog_unpark_threads(void) { }
+static inline int watchdog_enable_all_cpus(void) { return 0; }
+static inline void watchdog_disable_all_cpus(void) { }
+static void lockup_detector_reconfigure(void)
 {
+	cpus_read_lock();
+	watchdog_nmi_stop();
+	lockup_detector_update_enable();
+	watchdog_nmi_start();
+	cpus_read_unlock();
 }
-
-#ifdef CONFIG_SYSCTL
-static int watchdog_update_cpus(void)
+static inline void lockup_detector_setup(void)
 {
-	return 0;
+	lockup_detector_reconfigure();
 }
-#endif
+#endif /* !CONFIG_SOFTLOCKUP_DETECTOR */
 
-static void set_sample_period(void)
+static void __lockup_detector_cleanup(void)
 {
+	lockdep_assert_held(&watchdog_mutex);
+	hardlockup_detector_perf_cleanup();
 }
-#endif /* SOFTLOCKUP */
 
-/*
- * Suspend the hard and soft lockup detector by parking the watchdog threads.
+/**
+ * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes
+ *
+ * Caller must not hold the cpu hotplug rwsem.
  */
-int lockup_detector_suspend(void)
+void lockup_detector_cleanup(void)
 {
-	int ret = 0;
-
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
-	/*
-	 * Multiple suspend requests can be active in parallel (counted by
-	 * the 'watchdog_suspended' variable). If the watchdog threads are
-	 * running, the first caller takes care that they will be parked.
-	 * The state of 'watchdog_running' cannot change while a suspend
-	 * request is active (see related code in 'proc' handlers).
-	 */
-	if (watchdog_running && !watchdog_suspended)
-		ret = watchdog_park_threads();
-
-	if (ret == 0)
-		watchdog_suspended++;
-	else {
-		watchdog_disable_all_cpus();
-		pr_err("Failed to suspend lockup detectors, disabled\n");
-		watchdog_enabled = 0;
-	}
-
-	watchdog_nmi_reconfigure();
-
-	mutex_unlock(&watchdog_proc_mutex);
-
-	return ret;
+	mutex_lock(&watchdog_mutex);
+	__lockup_detector_cleanup();
+	mutex_unlock(&watchdog_mutex);
 }
 
-/*
- * Resume the hard and soft lockup detector by unparking the watchdog threads.
+/**
+ * lockup_detector_soft_poweroff - Interface to stop lockup detector(s)
+ *
+ * Special interface for parisc. It prevents lockup detector warnings from
+ * the default pm_poweroff() function which busy loops forever.
  */
-void lockup_detector_resume(void)
+void lockup_detector_soft_poweroff(void)
 {
-	mutex_lock(&watchdog_proc_mutex);
-
-	watchdog_suspended--;
-	/*
-	 * The watchdog threads are unparked if they were previously running
-	 * and if there is no more active suspend request.
-	 */
-	if (watchdog_running && !watchdog_suspended)
-		watchdog_unpark_threads();
-
-	watchdog_nmi_reconfigure();
-
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	watchdog_enabled = 0;
 }
 
 #ifdef CONFIG_SYSCTL
 
-/*
- * Update the run state of the lockup detectors.
- */
-static int proc_watchdog_update(void)
+/* Propagate any changes to the watchdog threads */
+static void proc_watchdog_update(void)
 {
-	int err = 0;
-
-	/*
-	 * Watchdog threads won't be started if they are already active.
-	 * The 'watchdog_running' variable in watchdog_*_all_cpus() takes
-	 * care of this. If those threads are already active, the sample
-	 * period will be updated and the lockup detectors will be enabled
-	 * or disabled 'on the fly'.
-	 */
-	if (watchdog_enabled && watchdog_thresh)
-		err = watchdog_enable_all_cpus();
-	else
-		watchdog_disable_all_cpus();
-
-	watchdog_nmi_reconfigure();
-
-	return err;
-
+	/* Remove impossible cpus to keep sysctl output clean. */
+	cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask);
+	lockup_detector_reconfigure();
 }
 
 /*
  * common function for watchdog, nmi_watchdog and soft_watchdog parameter
  *
- * caller             | table->data points to | 'which' contains the flag(s)
- * -------------------|-----------------------|-----------------------------
- * proc_watchdog      | watchdog_user_enabled | NMI_WATCHDOG_ENABLED or'ed
- *                    |                       | with SOFT_WATCHDOG_ENABLED
- * -------------------|-----------------------|-----------------------------
- * proc_nmi_watchdog  | nmi_watchdog_enabled  | NMI_WATCHDOG_ENABLED
- * -------------------|-----------------------|-----------------------------
- * proc_soft_watchdog | soft_watchdog_enabled | SOFT_WATCHDOG_ENABLED
+ * caller             | table->data points to      | 'which'
+ * -------------------|----------------------------|--------------------------
+ * proc_watchdog      | watchdog_user_enabled      | NMI_WATCHDOG_ENABLED |
+ *                    |                            | SOFT_WATCHDOG_ENABLED
+ * -------------------|----------------------------|--------------------------
+ * proc_nmi_watchdog  | nmi_watchdog_user_enabled  | NMI_WATCHDOG_ENABLED
+ * -------------------|----------------------------|--------------------------
+ * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED
  */
 static int proc_watchdog_common(int which, struct ctl_table *table, int write,
 				void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	int err, old, new;
-	int *watchdog_param = (int *)table->data;
+	int err, old, *param = table->data;
 
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
+	mutex_lock(&watchdog_mutex);
 
-	if (watchdog_suspended) {
-		/* no parameter changes allowed while watchdog is suspended */
-		err = -EAGAIN;
-		goto out;
-	}
-
-	/*
-	 * If the parameter is being read return the state of the corresponding
-	 * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the
-	 * run state of the lockup detectors.
-	 */
 	if (!write) {
-		*watchdog_param = (watchdog_enabled & which) != 0;
+		/*
+		 * On read synchronize the userspace interface. This is a
+		 * racy snapshot.
+		 */
+		*param = (watchdog_enabled & which) != 0;
 		err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	} else {
+		old = READ_ONCE(*param);
 		err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-		if (err)
-			goto out;
-
-		/*
-		 * There is a race window between fetching the current value
-		 * from 'watchdog_enabled' and storing the new value. During
-		 * this race window, watchdog_nmi_enable() can sneak in and
-		 * clear the NMI_WATCHDOG_ENABLED bit in 'watchdog_enabled'.
-		 * The 'cmpxchg' detects this race and the loop retries.
-		 */
-		do {
-			old = watchdog_enabled;
-			/*
-			 * If the parameter value is not zero set the
-			 * corresponding bit(s), else clear it(them).
-			 */
-			if (*watchdog_param)
-				new = old | which;
-			else
-				new = old & ~which;
-		} while (cmpxchg(&watchdog_enabled, old, new) != old);
-
-		/*
-		 * Update the run state of the lockup detectors. There is _no_
-		 * need to check the value returned by proc_watchdog_update()
-		 * and to restore the previous value of 'watchdog_enabled' as
-		 * both lockup detectors are disabled if proc_watchdog_update()
-		 * returns an error.
-		 */
-		if (old == new)
-			goto out;
-
-		err = proc_watchdog_update();
+		if (!err && old != READ_ONCE(*param))
+			proc_watchdog_update();
 	}
-out:
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	mutex_unlock(&watchdog_mutex);
 	return err;
 }
 
@@ -835,6 +713,8 @@ int proc_watchdog(struct ctl_table *table, int write,
 int proc_nmi_watchdog(struct ctl_table *table, int write,
 		      void __user *buffer, size_t *lenp, loff_t *ppos)
 {
+	if (!nmi_watchdog_available && write)
+		return -ENOTSUPP;
 	return proc_watchdog_common(NMI_WATCHDOG_ENABLED,
 				    table, write, buffer, lenp, ppos);
 }
@@ -855,39 +735,17 @@ int proc_soft_watchdog(struct ctl_table *table, int write,
 int proc_watchdog_thresh(struct ctl_table *table, int write,
 			 void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	int err, old, new;
-
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
+	int err, old;
 
-	if (watchdog_suspended) {
-		/* no parameter changes allowed while watchdog is suspended */
-		err = -EAGAIN;
-		goto out;
-	}
+	mutex_lock(&watchdog_mutex);
 
-	old = ACCESS_ONCE(watchdog_thresh);
+	old = READ_ONCE(watchdog_thresh);
 	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
-	if (err || !write)
-		goto out;
-
-	/*
-	 * Update the sample period. Restore on failure.
-	 */
-	new = ACCESS_ONCE(watchdog_thresh);
-	if (old == new)
-		goto out;
+	if (!err && write && old != READ_ONCE(watchdog_thresh))
+		proc_watchdog_update();
 
-	set_sample_period();
-	err = proc_watchdog_update();
-	if (err) {
-		watchdog_thresh = old;
-		set_sample_period();
-	}
-out:
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	mutex_unlock(&watchdog_mutex);
 	return err;
 }
 
@@ -902,45 +760,19 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,
 {
 	int err;
 
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
-
-	if (watchdog_suspended) {
-		/* no parameter changes allowed while watchdog is suspended */
-		err = -EAGAIN;
-		goto out;
-	}
+	mutex_lock(&watchdog_mutex);
 
 	err = proc_do_large_bitmap(table, write, buffer, lenp, ppos);
-	if (!err && write) {
-		/* Remove impossible cpus to keep sysctl output cleaner. */
-		cpumask_and(&watchdog_cpumask, &watchdog_cpumask,
-			    cpu_possible_mask);
-
-		if (watchdog_running) {
-			/*
-			 * Failure would be due to being unable to allocate
-			 * a temporary cpumask, so we are likely not in a
-			 * position to do much else to make things better.
-			 */
-			if (watchdog_update_cpus() != 0)
-				pr_err("cpumask update failed\n");
-		}
+	if (!err && write)
+		proc_watchdog_update();
 
-		watchdog_nmi_reconfigure();
-	}
-out:
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	mutex_unlock(&watchdog_mutex);
 	return err;
 }
-
 #endif /* CONFIG_SYSCTL */
 
 void __init lockup_detector_init(void)
 {
-	set_sample_period();
-
 #ifdef CONFIG_NO_HZ_FULL
 	if (tick_nohz_full_enabled()) {
 		pr_info("Disabling watchdog on nohz_full cores by default\n");
@@ -951,6 +783,7 @@ void __init lockup_detector_init(void)
 	cpumask_copy(&watchdog_cpumask, cpu_possible_mask);
 #endif
 
-	if (watchdog_enabled)
-		watchdog_enable_all_cpus();
+	if (!watchdog_nmi_probe())
+		nmi_watchdog_available = true;
+	lockup_detector_setup();
 }
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 3a09ea1b1d3d..71a62ceacdc8 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -21,8 +21,10 @@
 static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
+static struct cpumask dead_events_mask;
 
 static unsigned long hardlockup_allcpu_dumped;
+static unsigned int watchdog_cpus;
 
 void arch_touch_nmi_watchdog(void)
 {
@@ -103,15 +105,12 @@ static struct perf_event_attr wd_hw_attr = {
 
 /* Callback function for perf event subsystem */
 static void watchdog_overflow_callback(struct perf_event *event,
-		 struct perf_sample_data *data,
-		 struct pt_regs *regs)
+				       struct perf_sample_data *data,
+				       struct pt_regs *regs)
 {
 	/* Ensure the watchdog never gets throttled */
 	event->hw.interrupts = 0;
 
-	if (atomic_read(&watchdog_park_in_progress) != 0)
-		return;
-
 	if (__this_cpu_read(watchdog_nmi_touch) == true) {
 		__this_cpu_write(watchdog_nmi_touch, false);
 		return;
@@ -160,104 +159,131 @@ static void watchdog_overflow_callback(struct perf_event *event,
 	return;
 }
 
-/*
- * People like the simple clean cpu node info on boot.
- * Reduce the watchdog noise by only printing messages
- * that are different from what cpu0 displayed.
- */
-static unsigned long firstcpu_err;
-static atomic_t watchdog_cpus;
-
-int watchdog_nmi_enable(unsigned int cpu)
+static int hardlockup_detector_event_create(void)
 {
+	unsigned int cpu = smp_processor_id();
 	struct perf_event_attr *wd_attr;
-	struct perf_event *event = per_cpu(watchdog_ev, cpu);
-	int firstcpu = 0;
-
-	/* nothing to do if the hard lockup detector is disabled */
-	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
-		goto out;
-
-	/* is it already setup and enabled? */
-	if (event && event->state > PERF_EVENT_STATE_OFF)
-		goto out;
-
-	/* it is setup but not enabled */
-	if (event != NULL)
-		goto out_enable;
-
-	if (atomic_inc_return(&watchdog_cpus) == 1)
-		firstcpu = 1;
+	struct perf_event *evt;
 
 	wd_attr = &wd_hw_attr;
 	wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh);
 
 	/* Try to register using hardware perf events */
-	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
+	evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL,
+					       watchdog_overflow_callback, NULL);
+	if (IS_ERR(evt)) {
+		pr_info("Perf event create on CPU %d failed with %ld\n", cpu,
+			PTR_ERR(evt));
+		return PTR_ERR(evt);
+	}
+	this_cpu_write(watchdog_ev, evt);
+	return 0;
+}
 
-	/* save the first cpu's error for future comparision */
-	if (firstcpu && IS_ERR(event))
-		firstcpu_err = PTR_ERR(event);
+/**
+ * hardlockup_detector_perf_enable - Enable the local event
+ */
+void hardlockup_detector_perf_enable(void)
+{
+	if (hardlockup_detector_event_create())
+		return;
 
-	if (!IS_ERR(event)) {
-		/* only print for the first cpu initialized */
-		if (firstcpu || firstcpu_err)
-			pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n");
-		goto out_save;
-	}
+	if (!watchdog_cpus++)
+		pr_info("Enabled. Permanently consumes one hw-PMU counter.\n");
 
-	/*
-	 * Disable the hard lockup detector if _any_ CPU fails to set up
-	 * set up the hardware perf event. The watchdog() function checks
-	 * the NMI_WATCHDOG_ENABLED bit periodically.
-	 *
-	 * The barriers are for syncing up watchdog_enabled across all the
-	 * cpus, as clear_bit() does not use barriers.
-	 */
-	smp_mb__before_atomic();
-	clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled);
-	smp_mb__after_atomic();
-
-	/* skip displaying the same error again */
-	if (!firstcpu && (PTR_ERR(event) == firstcpu_err))
-		return PTR_ERR(event);
-
-	/* vary the KERN level based on the returned errno */
-	if (PTR_ERR(event) == -EOPNOTSUPP)
-		pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu);
-	else if (PTR_ERR(event) == -ENOENT)
-		pr_warn("disabled (cpu%i): hardware events not enabled\n",
-			 cpu);
-	else
-		pr_err("disabled (cpu%i): unable to create perf event: %ld\n",
-			cpu, PTR_ERR(event));
-
-	pr_info("Shutting down hard lockup detector on all cpus\n");
-
-	return PTR_ERR(event);
-
-	/* success path */
-out_save:
-	per_cpu(watchdog_ev, cpu) = event;
-out_enable:
-	perf_event_enable(per_cpu(watchdog_ev, cpu));
-out:
-	return 0;
+	perf_event_enable(this_cpu_read(watchdog_ev));
 }
 
-void watchdog_nmi_disable(unsigned int cpu)
+/**
+ * hardlockup_detector_perf_disable - Disable the local event
+ */
+void hardlockup_detector_perf_disable(void)
 {
-	struct perf_event *event = per_cpu(watchdog_ev, cpu);
+	struct perf_event *event = this_cpu_read(watchdog_ev);
 
 	if (event) {
 		perf_event_disable(event);
+		cpumask_set_cpu(smp_processor_id(), &dead_events_mask);
+		watchdog_cpus--;
+	}
+}
+
+/**
+ * hardlockup_detector_perf_cleanup - Cleanup disabled events and destroy them
+ *
+ * Called from lockup_detector_cleanup(). Serialized by the caller.
+ */
+void hardlockup_detector_perf_cleanup(void)
+{
+	int cpu;
+
+	for_each_cpu(cpu, &dead_events_mask) {
+		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+		/*
+		 * Required because for_each_cpu() reports  unconditionally
+		 * CPU0 as set on UP kernels. Sigh.
+		 */
+		if (event)
+			perf_event_release_kernel(event);
 		per_cpu(watchdog_ev, cpu) = NULL;
+	}
+	cpumask_clear(&dead_events_mask);
+}
+
+/**
+ * hardlockup_detector_perf_stop - Globally stop watchdog events
+ *
+ * Special interface for x86 to handle the perf HT bug.
+ */
+void __init hardlockup_detector_perf_stop(void)
+{
+	int cpu;
+
+	lockdep_assert_cpus_held();
+
+	for_each_online_cpu(cpu) {
+		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+		if (event)
+			perf_event_disable(event);
+	}
+}
 
-		/* should be in cleanup, but blocks oprofile */
-		perf_event_release_kernel(event);
+/**
+ * hardlockup_detector_perf_restart - Globally restart watchdog events
+ *
+ * Special interface for x86 to handle the perf HT bug.
+ */
+void __init hardlockup_detector_perf_restart(void)
+{
+	int cpu;
+
+	lockdep_assert_cpus_held();
+
+	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+		return;
+
+	for_each_online_cpu(cpu) {
+		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+		if (event)
+			perf_event_enable(event);
+	}
+}
+
+/**
+ * hardlockup_detector_perf_init - Probe whether NMI event is available at all
+ */
+int __init hardlockup_detector_perf_init(void)
+{
+	int ret = hardlockup_detector_event_create();
 
-		/* watchdog_nmi_enable() expects this to be zero initially. */
-		if (atomic_dec_and_test(&watchdog_cpus))
-			firstcpu_err = 0;
+	if (ret) {
+		pr_info("Perf NMI watchdog permanently disabled\n");
+	} else {
+		perf_event_release_kernel(this_cpu_read(watchdog_ev));
+		this_cpu_write(watchdog_ev, NULL);
 	}
+	return ret;
 }