diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 2f7b94e98317..3fe274b84f1c 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -102,9 +102,9 @@ struct hwlat_sample {
 /* keep the global state somewhere. */
 static struct hwlat_data {
 
-	struct mutex lock;		/* protect changes */
+	struct mutex	lock;		/* protect changes */
 
-	u64	count;			/* total since reset */
+	atomic64_t	count;		/* total since reset */
 
 	u64	sample_window;		/* total sampling window (on+off) */
 	u64	sample_width;		/* active sampling portion of window */
@@ -193,8 +193,7 @@ void trace_hwlat_callback(bool enter)
  * get_sample - sample the CPU TSC and look for likely hardware latencies
  *
  * Used to repeatedly capture the CPU TSC (or similar), looking for potential
- * hardware-induced latency. Called with interrupts disabled and with
- * hwlat_data.lock held.
+ * hardware-induced latency. Called with interrupts disabled.
  */
 static int get_sample(void)
 {
@@ -204,6 +203,7 @@ static int get_sample(void)
 	time_type start, t1, t2, last_t2;
 	s64 diff, outer_diff, total, last_total = 0;
 	u64 sample = 0;
+	u64 sample_width = READ_ONCE(hwlat_data.sample_width);
 	u64 thresh = tracing_thresh;
 	u64 outer_sample = 0;
 	int ret = -1;
@@ -267,7 +267,7 @@ static int get_sample(void)
 		if (diff > sample)
 			sample = diff; /* only want highest value */
 
-	} while (total <= hwlat_data.sample_width);
+	} while (total <= sample_width);
 
 	barrier(); /* finish the above in the view for NMIs */
 	trace_hwlat_callback_enabled = false;
@@ -285,8 +285,7 @@ static int get_sample(void)
 		if (kdata->nmi_total_ts)
 			do_div(kdata->nmi_total_ts, NSEC_PER_USEC);
 
-		hwlat_data.count++;
-		s.seqnum = hwlat_data.count;
+		s.seqnum = atomic64_inc_return(&hwlat_data.count);
 		s.duration = sample;
 		s.outer_duration = outer_sample;
 		s.nmi_total_ts = kdata->nmi_total_ts;
@@ -832,7 +831,7 @@ static int hwlat_tracer_init(struct trace_array *tr)
 
 	hwlat_trace = tr;
 
-	hwlat_data.count = 0;
+	atomic64_set(&hwlat_data.count, 0);
 	tr->max_latency = 0;
 	save_tracing_thresh = tracing_thresh;