diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 7c467c5b048e9fc431bbb0c1c29af07fb81d0f9b..b26361355daeb39b61c238333c20dd2d68ec4a61 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -749,6 +749,15 @@ core_initcall(register_cpufreq_notifier);
 
 static void raise_nmi(cpumask_t *mask)
 {
+	/*
+	 * Generate the backtrace directly if we are running in a calling
+	 * context that is not preemptible by the backtrace IPI. Note
+	 * that nmi_cpu_backtrace() automatically removes the current cpu
+	 * from mask.
+	 */
+	if (cpumask_test_cpu(smp_processor_id(), mask) && irqs_disabled())
+		nmi_cpu_backtrace(NULL);
+
 	smp_cross_call(mask, IPI_CPU_BACKTRACE);
 }
 
diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c
index 88d3d32e59236bc1127d88c781bc014d70920652..6019c53c669e176bcf36cf3e8bffb35c9b893432 100644
--- a/lib/nmi_backtrace.c
+++ b/lib/nmi_backtrace.c
@@ -43,6 +43,12 @@ static void print_seq_line(struct nmi_seq_buf *s, int start, int end)
 	printk("%.*s", (end - start) + 1, buf);
 }
 
+/*
+ * When raise() is called it will be is passed a pointer to the
+ * backtrace_mask. Architectures that call nmi_cpu_backtrace()
+ * directly from their raise() functions may rely on the mask
+ * they are passed being updated as a side effect of this call.
+ */
 void nmi_trigger_all_cpu_backtrace(bool include_self,
 				   void (*raise)(cpumask_t *mask))
 {
@@ -149,7 +155,10 @@ bool nmi_cpu_backtrace(struct pt_regs *regs)
 		/* Replace printk to write into the NMI seq */
 		this_cpu_write(printk_func, nmi_vprintk);
 		pr_warn("NMI backtrace for cpu %d\n", cpu);
-		show_regs(regs);
+		if (regs)
+			show_regs(regs);
+		else
+			dump_stack();
 		this_cpu_write(printk_func, printk_func_save);
 
 		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));