diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index 8740297dac77..1473fc2f7ab7 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -20,7 +20,7 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
-#define NR_IPI	6
+#define NR_IPI	7
 
 typedef struct {
 	unsigned int __softirq_pending;
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index b77197d941fc..96fbe7a7c69e 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -56,5 +56,8 @@ static inline bool on_irq_stack(unsigned long sp, int cpu)
 	return (low <= sp && sp <= high);
 }
 
+void arch_trigger_all_cpu_backtrace(void);
+#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
+
 #endif /* !__ASSEMBLER__ */
 #endif
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 6a4348b1b962..0f627090bedf 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -73,7 +73,8 @@ enum ipi_msg_type {
 	IPI_CPU_STOP,
 	IPI_TIMER,
 	IPI_IRQ_WORK,
-	IPI_WAKEUP
+	IPI_WAKEUP,
+	IPI_CPU_BACKTRACE,
 };
 
 #ifdef CONFIG_ARM64_VHE
@@ -760,6 +761,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
 	S(IPI_TIMER, "Timer broadcast interrupts"),
 	S(IPI_IRQ_WORK, "IRQ work interrupts"),
 	S(IPI_WAKEUP, "CPU wake-up interrupts"),
+	S(IPI_CPU_BACKTRACE, "CPU backtrace"),
 };
 
 static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
@@ -846,6 +848,72 @@ static void ipi_cpu_stop(unsigned int cpu, struct pt_regs *regs)
 		cpu_relax();
 }
 
+static cpumask_t backtrace_mask;
+static DEFINE_RAW_SPINLOCK(backtrace_lock);
+
+/* "in progress" flag of arch_trigger_all_cpu_backtrace */
+static unsigned long backtrace_flag;
+
+static void smp_send_all_cpu_backtrace(void)
+{
+	unsigned int this_cpu = smp_processor_id();
+	int i;
+
+	if (test_and_set_bit(0, &backtrace_flag))
+		/*
+		 * If there is already a trigger_all_cpu_backtrace() in progress
+		 * (backtrace_flag == 1), don't output double cpu dump infos.
+		 */
+		return;
+
+	cpumask_copy(&backtrace_mask, cpu_online_mask);
+	cpumask_clear_cpu(this_cpu, &backtrace_mask);
+
+	pr_info("Backtrace for cpu %d (current):\n", this_cpu);
+	dump_stack();
+
+	pr_info("\nsending IPI to all other CPUs:\n");
+	if (!cpumask_empty(&backtrace_mask))
+		smp_cross_call(&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++) {
+		if (cpumask_empty(&backtrace_mask))
+			break;
+		mdelay(1);
+	}
+
+	clear_bit(0, &backtrace_flag);
+	smp_mb__after_atomic();
+}
+
+/*
+ * ipi_cpu_backtrace - handle IPI from smp_send_all_cpu_backtrace()
+ */
+static void ipi_cpu_backtrace(unsigned int cpu, struct pt_regs *regs)
+{
+	if (cpumask_test_cpu(cpu, &backtrace_mask)) {
+		raw_spin_lock(&backtrace_lock);
+		pr_warn("IPI backtrace for cpu %d\n", cpu);
+		show_regs(regs);
+		raw_spin_unlock(&backtrace_lock);
+		cpumask_clear_cpu(cpu, &backtrace_mask);
+	}
+}
+
+#ifdef CONFIG_SMP
+void arch_trigger_all_cpu_backtrace(void)
+{
+	smp_send_all_cpu_backtrace();
+}
+#else
+void arch_trigger_all_cpu_backtrace(void)
+{
+	dump_stack();
+}
+#endif
+
+
 /*
  * Main handler for inter-processor interrupts
  */
@@ -900,6 +968,10 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		break;
 #endif
 
+	case IPI_CPU_BACKTRACE:
+		ipi_cpu_backtrace(cpu, regs);
+		break;
+
 	default:
 		pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr);
 		break;
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 780949dff0ed..e062ebe00c09 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -41,25 +41,37 @@ static inline void hardlockup_detector_disable(void) {}
 #ifdef arch_trigger_cpumask_backtrace
 static inline bool trigger_all_cpu_backtrace(void)
 {
-	arch_trigger_cpumask_backtrace(cpu_online_mask, false);
+	#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+		arch_trigger_all_cpu_backtrace();
+	else
+		arch_trigger_cpumask_backtrace(cpu_online_mask, false);
+	#endif
+
 	return true;
 }
 
 static inline bool trigger_allbutself_cpu_backtrace(void)
 {
-	arch_trigger_cpumask_backtrace(cpu_online_mask, true);
+	#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+		arch_trigger_all_cpu_backtrace();
+	else
+		arch_trigger_cpumask_backtrace(cpu_online_mask, true);
+	#endif
+
 	return true;
 }
 
 static inline bool trigger_cpumask_backtrace(struct cpumask *mask)
 {
 	arch_trigger_cpumask_backtrace(mask, false);
+
 	return true;
 }
 
 static inline bool trigger_single_cpu_backtrace(int cpu)
 {
 	arch_trigger_cpumask_backtrace(cpumask_of(cpu), false);
+
 	return true;
 }