1 files changed, 35 insertions, 70 deletions

diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_perf.c
index 247bf0b1582c..8ea00c4a24b2 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_perf.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Detect hard lockups on a system
+ * Detect hard lockups on a system using perf
  *
  * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
  *
@@ -20,28 +20,12 @@
 #include <asm/irq_regs.h>
 #include <linux/perf_event.h>
 
-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 DEFINE_PER_CPU(struct perf_event *, dead_event);
 static struct cpumask dead_events_mask;
 
-static unsigned long hardlockup_allcpu_dumped;
 static atomic_t watchdog_cpus = ATOMIC_INIT(0);
 
-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_nmi_touch, true);
-}
-EXPORT_SYMBOL(arch_touch_nmi_watchdog);
-
 #ifdef CONFIG_HARDLOCKUP_CHECK_TIMESTAMP
 static DEFINE_PER_CPU(ktime_t, last_timestamp);
 static DEFINE_PER_CPU(unsigned int, nmi_rearmed);
@@ -114,61 +98,24 @@ static void watchdog_overflow_callback(struct perf_event *event,
 	/* Ensure the watchdog never gets throttled */
 	event->hw.interrupts = 0;
 
-	if (__this_cpu_read(watchdog_nmi_touch) == true) {
-		__this_cpu_write(watchdog_nmi_touch, false);
-		return;
-	}
-
 	if (!watchdog_check_timestamp())
 		return;
 
-	/* check for a hardlockup
-	 * This is done by making sure our 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()) {
-		int this_cpu = smp_processor_id();
-
-		/* only print hardlockups once */
-		if (__this_cpu_read(hard_watchdog_warn) == true)
-			return;
-
-		pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n",
-			 this_cpu);
-		print_modules();
-		print_irqtrace_events(current);
-		if (regs)
-			show_regs(regs);
-		else
-			dump_stack();
-
-		/*
-		 * Perform all-CPU dump only once to avoid multiple hardlockups
-		 * generating interleaving traces
-		 */
-		if (sysctl_hardlockup_all_cpu_backtrace &&
-				!test_and_set_bit(0, &hardlockup_allcpu_dumped))
-			trigger_allbutself_cpu_backtrace();
-
-		if (hardlockup_panic)
-			nmi_panic(regs, "Hard LOCKUP");
-
-		__this_cpu_write(hard_watchdog_warn, true);
-		return;
-	}
-
-	__this_cpu_write(hard_watchdog_warn, false);
-	return;
+	watchdog_hardlockup_check(smp_processor_id(), regs);
 }
 
 static int hardlockup_detector_event_create(void)
 {
-	unsigned int cpu = smp_processor_id();
+	unsigned int cpu;
 	struct perf_event_attr *wd_attr;
 	struct perf_event *evt;
 
+	/*
+	 * Preemption is not disabled because memory will be allocated.
+	 * Ensure CPU-locality by calling this in per-CPU kthread.
+	 */
+	WARN_ON(!is_percpu_thread());
+	cpu = raw_smp_processor_id();
 	wd_attr = &wd_hw_attr;
 	wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh);
 
@@ -185,10 +132,14 @@ static int hardlockup_detector_event_create(void)
 }
 
 /**
- * hardlockup_detector_perf_enable - Enable the local event
+ * watchdog_hardlockup_enable - Enable the local event
+ *
+ * @cpu: The CPU to enable hard lockup on.
  */
-void hardlockup_detector_perf_enable(void)
+void watchdog_hardlockup_enable(unsigned int cpu)
 {
+	WARN_ON_ONCE(cpu != smp_processor_id());
+
 	if (hardlockup_detector_event_create())
 		return;
 
@@ -200,12 +151,16 @@ void hardlockup_detector_perf_enable(void)
 }
 
 /**
- * hardlockup_detector_perf_disable - Disable the local event
+ * watchdog_hardlockup_disable - Disable the local event
+ *
+ * @cpu: The CPU to enable hard lockup on.
  */
-void hardlockup_detector_perf_disable(void)
+void watchdog_hardlockup_disable(unsigned int cpu)
 {
 	struct perf_event *event = this_cpu_read(watchdog_ev);
 
+	WARN_ON_ONCE(cpu != smp_processor_id());
+
 	if (event) {
 		perf_event_disable(event);
 		this_cpu_write(watchdog_ev, NULL);
@@ -268,7 +223,7 @@ void __init hardlockup_detector_perf_restart(void)
 
 	lockdep_assert_cpus_held();
 
-	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+	if (!(watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED))
 		return;
 
 	for_each_online_cpu(cpu) {
@@ -279,12 +234,22 @@ void __init hardlockup_detector_perf_restart(void)
 	}
 }
 
+bool __weak __init arch_perf_nmi_is_available(void)
+{
+	return true;
+}
+
 /**
- * hardlockup_detector_perf_init - Probe whether NMI event is available at all
+ * watchdog_hardlockup_probe - Probe whether NMI event is available at all
  */
-int __init hardlockup_detector_perf_init(void)
+int __init watchdog_hardlockup_probe(void)
 {
-	int ret = hardlockup_detector_event_create();
+	int ret;
+
+	if (!arch_perf_nmi_is_available())
+		return -ENODEV;
+
+	ret = hardlockup_detector_event_create();
 
 	if (ret) {
 		pr_info("Perf NMI watchdog permanently disabled\n");