diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index 53bad099ebd6..c03154173cc7 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -6,15 +6,58 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/atomic.h>
+
+static void __dump_stack(void)
+{
+	dump_stack_print_info(KERN_DEFAULT);
+	show_stack(NULL, NULL);
+}
 
 /**
  * dump_stack - dump the current task information and its stack trace
  *
  * Architectures can override this implementation by implementing its own.
  */
+#ifdef CONFIG_SMP
+static atomic_t dump_lock = ATOMIC_INIT(-1);
+
 void dump_stack(void)
 {
-	dump_stack_print_info(KERN_DEFAULT);
-	show_stack(NULL, NULL);
+	int was_locked;
+	int old;
+	int cpu;
+
+	/*
+	 * Permit this cpu to perform nested stack dumps while serialising
+	 * against other CPUs
+	 */
+	preempt_disable();
+
+retry:
+	cpu = smp_processor_id();
+	old = atomic_cmpxchg(&dump_lock, -1, cpu);
+	if (old == -1) {
+		was_locked = 0;
+	} else if (old == cpu) {
+		was_locked = 1;
+	} else {
+		cpu_relax();
+		goto retry;
+	}
+
+	__dump_stack();
+
+	if (!was_locked)
+		atomic_set(&dump_lock, -1);
+
+	preempt_enable();
 }
+#else
+void dump_stack(void)
+{
+	__dump_stack();
+}
+#endif
 EXPORT_SYMBOL(dump_stack);