diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index e31119a4a05c..a90c2e5673f7 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -464,6 +464,17 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 static void (*__smp_cross_call)(const struct cpumask *, unsigned int);
 DEFINE_PER_CPU(bool, pending_ipi);
 
+static void smp_cross_call_common(const struct cpumask *cpumask,
+						unsigned int func)
+{
+	unsigned int cpu;
+
+	for_each_cpu(cpu, cpumask)
+		per_cpu(pending_ipi, cpu) = true;
+
+	__smp_cross_call(cpumask, func);
+}
+
 void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
 {
 	if (!__smp_cross_call)
@@ -472,17 +483,17 @@ void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
 
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
-	smp_cross_call(mask, IPI_CALL_FUNC);
+	smp_cross_call_common(mask, IPI_CALL_FUNC);
 }
 
 void arch_send_wakeup_ipi_mask(const struct cpumask *mask)
 {
-	smp_cross_call(mask, IPI_WAKEUP);
+	smp_cross_call_common(mask, IPI_WAKEUP);
 }
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
+	smp_cross_call_common(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
 }
 
 static const char *ipi_types[NR_IPI] __tracepoint_string = {
@@ -675,7 +686,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 void smp_send_reschedule(int cpu)
 {
 	BUG_ON(cpu_is_offline(cpu));
-	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
+	smp_cross_call_common(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
 void smp_send_stop(void)
@@ -686,7 +697,7 @@ void smp_send_stop(void)
 	cpumask_copy(&mask, cpu_online_mask);
 	cpumask_clear_cpu(smp_processor_id(), &mask);
 	if (!cpumask_empty(&mask))
-		smp_cross_call(&mask, IPI_CPU_STOP);
+		smp_cross_call_common(&mask, IPI_CPU_STOP);
 
 	/* Wait up to one second for other CPUs to stop */
 	timeout = USEC_PER_SEC;
@@ -768,7 +779,7 @@ static void raise_nmi(cpumask_t *mask)
 	if (cpumask_test_cpu(smp_processor_id(), mask) && irqs_disabled())
 		nmi_cpu_backtrace(NULL);
 
-	smp_cross_call(mask, IPI_CPU_BACKTRACE);
+	smp_cross_call_common(mask, IPI_CPU_BACKTRACE);
 }
 
 void arch_trigger_all_cpu_backtrace(bool include_self)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 6afe10641a93..08e78e47be95 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -484,6 +484,16 @@ acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header,
 void (*__smp_cross_call)(const struct cpumask *, unsigned int);
 DEFINE_PER_CPU(bool, pending_ipi);
 
+void smp_cross_call_common(const struct cpumask *cpumask, unsigned int func)
+{
+	unsigned int cpu;
+
+	for_each_cpu(cpu, cpumask)
+		per_cpu(pending_ipi, cpu) = true;
+
+	__smp_cross_call(cpumask, func);
+}
+
 /*
  * Enumerate the possible CPU set from the device tree and build the
  * cpu logical map array containing MPIDR values related to logical
@@ -683,17 +693,17 @@ u64 smp_irq_stat_cpu(unsigned int cpu)
 
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
-	smp_cross_call(mask, IPI_CALL_FUNC);
+	smp_cross_call_common(mask, IPI_CALL_FUNC);
 }
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC);
+	smp_cross_call_common(cpumask_of(cpu), IPI_CALL_FUNC);
 }
 
 void arch_send_wakeup_ipi_mask(const struct cpumask *mask)
 {
-	smp_cross_call(mask, IPI_WAKEUP);
+	smp_cross_call_common(mask, IPI_WAKEUP);
 }
 
 #ifdef CONFIG_IRQ_WORK
@@ -759,7 +769,7 @@ static void smp_send_all_cpu_backtrace(void)
 
 	pr_info("\nsending IPI to all other CPUs:\n");
 	if (!cpumask_empty(&backtrace_mask))
-		smp_cross_call(&backtrace_mask, IPI_CPU_BACKTRACE);
+		smp_cross_call_common(&backtrace_mask, IPI_CPU_BACKTRACE);
 
 	/* Wait for up to 10 seconds for all other CPUs to do the backtrace */
 	for (i = 0; i < 10 * 1000; i++) {
@@ -867,13 +877,13 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 void smp_send_reschedule(int cpu)
 {
 	BUG_ON(cpu_is_offline(cpu));
-	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
+	smp_cross_call_common(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 void tick_broadcast(const struct cpumask *mask)
 {
-	smp_cross_call(mask, IPI_TIMER);
+	smp_cross_call_common(mask, IPI_TIMER);
 }
 #endif
 
@@ -887,7 +897,7 @@ void smp_send_stop(void)
 		cpumask_copy(&mask, cpu_online_mask);
 		cpumask_clear_cpu(smp_processor_id(), &mask);
 
-		smp_cross_call(&mask, IPI_CPU_STOP);
+		smp_cross_call_common(&mask, IPI_CPU_STOP);
 	}
 
 	/* Wait up to one second for other CPUs to stop */