diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index f567032a09c0..6d1938d1b4df 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -92,16 +92,28 @@ void machine_crash_nonpanic_core(void *unused)
 	}
 }
 
+static DEFINE_PER_CPU(call_single_data_t, cpu_stop_csd) =
+	CSD_INIT(machine_crash_nonpanic_core, NULL);
+
 void crash_smp_send_stop(void)
 {
 	static int cpus_stopped;
 	unsigned long msecs;
+	call_single_data_t *csd;
+	int cpu, this_cpu = raw_smp_processor_id();
 
 	if (cpus_stopped)
 		return;
 
 	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
-	smp_call_function(machine_crash_nonpanic_core, NULL, false);
+	for_each_online_cpu(cpu) {
+		if (cpu == this_cpu)
+			continue;
+
+		csd = &per_cpu(cpu_stop_csd, cpu);
+		smp_call_function_single_async(cpu, csd);
+	}
+
 	msecs = 1000; /* Wait at most a second for the other cpus to stop */
 	while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
 		mdelay(1);