diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index f76d6f77dd5e..70e86b4b4932 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -441,6 +441,37 @@ int dbg_remove_all_break(void)
 	return 0;
 }
 
+#ifdef CONFIG_KGDB_KDB
+void kdb_dump_stack_on_cpu(int cpu)
+{
+	if (cpu == raw_smp_processor_id()) {
+		dump_stack();
+		return;
+	}
+
+	if (!(kgdb_info[cpu].exception_state & DCPU_IS_SLAVE)) {
+		kdb_printf("ERROR: Task on cpu %d didn't stop in the debugger\n",
+			   cpu);
+		return;
+	}
+
+	/*
+	 * In general, architectures don't support dumping the stack of a
+	 * "running" process that's not the current one.  From the point of
+	 * view of the Linux, kernel processes that are looping in the kgdb
+	 * slave loop are still "running".  There's also no API (that actually
+	 * works across all architectures) that can do a stack crawl based
+	 * on registers passed as a parameter.
+	 *
+	 * Solve this conundrum by asking slave CPUs to do the backtrace
+	 * themselves.
+	 */
+	kgdb_info[cpu].exception_state |= DCPU_WANT_BT;
+	while (kgdb_info[cpu].exception_state & DCPU_WANT_BT)
+		cpu_relax();
+}
+#endif
+
 /*
  * Return true if there is a valid kgdb I/O module.  Also if no
  * debugger is attached a message can be printed to the console about
@@ -580,6 +611,9 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
 				atomic_xchg(&kgdb_active, cpu);
 				break;
 			}
+		} else if (kgdb_info[cpu].exception_state & DCPU_WANT_BT) {
+			dump_stack();
+			kgdb_info[cpu].exception_state &= ~DCPU_WANT_BT;
 		} else if (kgdb_info[cpu].exception_state & DCPU_IS_SLAVE) {
 			if (!raw_spin_is_locked(&dbg_slave_lock))
 				goto return_normal;
diff --git a/kernel/debug/debug_core.h b/kernel/debug/debug_core.h
index 804b0fe5a0ba..cd22b5f68831 100644
--- a/kernel/debug/debug_core.h
+++ b/kernel/debug/debug_core.h
@@ -33,6 +33,7 @@ struct kgdb_state {
 #define DCPU_WANT_MASTER 0x1 /* Waiting to become a master kgdb cpu */
 #define DCPU_NEXT_MASTER 0x2 /* Transition from one master cpu to another */
 #define DCPU_IS_SLAVE    0x4 /* Slave cpu enter exception */
+#define DCPU_WANT_BT     0x8 /* Slave cpu should backtrace then clear flag */
 
 struct debuggerinfo_struct {
 	void			*debuggerinfo;
@@ -75,6 +76,7 @@ extern int kdb_stub(struct kgdb_state *ks);
 extern int kdb_parse(const char *cmdstr);
 extern int kdb_common_init_state(struct kgdb_state *ks);
 extern int kdb_common_deinit_state(void);
+extern void kdb_dump_stack_on_cpu(int cpu);
 #else /* ! CONFIG_KGDB_KDB */
 static inline int kdb_stub(struct kgdb_state *ks)
 {
diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c
index d9af139f9a31..0e94efe07b72 100644
--- a/kernel/debug/kdb/kdb_bt.c
+++ b/kernel/debug/kdb/kdb_bt.c
@@ -22,20 +22,15 @@
 static void kdb_show_stack(struct task_struct *p, void *addr)
 {
 	int old_lvl = console_loglevel;
+
 	console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH;
 	kdb_trap_printk++;
-	kdb_set_current_task(p);
-	if (addr) {
-		show_stack((struct task_struct *)p, addr);
-	} else if (kdb_current_regs) {
-#ifdef CONFIG_X86
-		show_stack(p, &kdb_current_regs->sp);
-#else
-		show_stack(p, NULL);
-#endif
-	} else {
-		show_stack(p, NULL);
-	}
+
+	if (!addr && kdb_task_has_cpu(p))
+		kdb_dump_stack_on_cpu(kdb_process_cpu(p));
+	else
+		show_stack(p, addr);
+
 	console_loglevel = old_lvl;
 	kdb_trap_printk--;
 }