diff --git a/kernel/futex.c b/kernel/futex.c
index 0d638f0..76ed592 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -903,11 +903,27 @@
 	 */
 	raw_spin_lock_irq(&curr->pi_lock);
 	while (!list_empty(head)) {
-
 		next = head->next;
 		pi_state = list_entry(next, struct futex_pi_state, list);
 		key = pi_state->key;
 		hb = hash_futex(&key);
+
+		/*
+		 * We can race against put_pi_state() removing itself from the
+		 * list (a waiter going away). put_pi_state() will first
+		 * decrement the reference count and then modify the list, so
+		 * its possible to see the list entry but fail this reference
+		 * acquire.
+		 *
+		 * In that case; drop the locks to let put_pi_state() make
+		 * progress and retry the loop.
+		 */
+		if (!atomic_inc_not_zero(&pi_state->refcount)) {
+			raw_spin_unlock_irq(&curr->pi_lock);
+			cpu_relax();
+			raw_spin_lock_irq(&curr->pi_lock);
+			continue;
+		}
 		raw_spin_unlock_irq(&curr->pi_lock);
 
 		spin_lock(&hb->lock);
@@ -918,8 +934,10 @@
 		 * task still owns the PI-state:
 		 */
 		if (head->next != next) {
+			/* retain curr->pi_lock for the loop invariant */
 			raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
 			spin_unlock(&hb->lock);
+			put_pi_state(pi_state);
 			continue;
 		}
 
@@ -927,9 +945,8 @@
 		WARN_ON(list_empty(&pi_state->list));
 		list_del_init(&pi_state->list);
 		pi_state->owner = NULL;
-		raw_spin_unlock(&curr->pi_lock);
 
-		get_pi_state(pi_state);
+		raw_spin_unlock(&curr->pi_lock);
 		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 		spin_unlock(&hb->lock);
 
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 4583feb..e449a23 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -13,6 +13,7 @@
 #define pr_fmt(fmt) "NMI watchdog: " fmt
 
 #include <linux/nmi.h>
+#include <linux/atomic.h>
 #include <linux/module.h>
 #include <linux/sched/debug.h>
 
@@ -22,10 +23,11 @@
 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 unsigned int watchdog_cpus;
+static atomic_t watchdog_cpus = ATOMIC_INIT(0);
 
 void arch_touch_nmi_watchdog(void)
 {
@@ -189,7 +191,8 @@
 	if (hardlockup_detector_event_create())
 		return;
 
-	if (!watchdog_cpus++)
+	/* use original value for check */
+	if (!atomic_fetch_inc(&watchdog_cpus))
 		pr_info("Enabled. Permanently consumes one hw-PMU counter.\n");
 
 	perf_event_enable(this_cpu_read(watchdog_ev));
@@ -204,8 +207,10 @@
 
 	if (event) {
 		perf_event_disable(event);
+		this_cpu_write(watchdog_ev, NULL);
+		this_cpu_write(dead_event, event);
 		cpumask_set_cpu(smp_processor_id(), &dead_events_mask);
-		watchdog_cpus--;
+		atomic_dec(&watchdog_cpus);
 	}
 }
 
@@ -219,7 +224,7 @@
 	int cpu;
 
 	for_each_cpu(cpu, &dead_events_mask) {
-		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+		struct perf_event *event = per_cpu(dead_event, cpu);
 
 		/*
 		 * Required because for_each_cpu() reports  unconditionally
@@ -227,7 +232,7 @@
 		 */
 		if (event)
 			perf_event_release_kernel(event);
-		per_cpu(watchdog_ev, cpu) = NULL;
+		per_cpu(dead_event, cpu) = NULL;
 	}
 	cpumask_clear(&dead_events_mask);
 }