diff --git a/include/linux/futex.h b/include/linux/futex.h
index 063a5cd00d770b66660ed54d42367bc26798cbdf..805508373fcea2cc1f94cceb955aef6d0591ae40 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -57,6 +57,7 @@ union futex_key {
 #ifdef CONFIG_FUTEX
 enum {
 	FUTEX_STATE_OK,
+	FUTEX_STATE_EXITING,
 	FUTEX_STATE_DEAD,
 };
 
@@ -71,33 +72,7 @@ static inline void futex_init_task(struct task_struct *tsk)
 	tsk->futex_state = FUTEX_STATE_OK;
 }
 
-/**
- * futex_exit_done - Sets the tasks futex state to FUTEX_STATE_DEAD
- * @tsk:	task to set the state on
- *
- * Set the futex exit state of the task lockless. The futex waiter code
- * observes that state when a task is exiting and loops until the task has
- * actually finished the futex cleanup. The worst case for this is that the
- * waiter runs through the wait loop until the state becomes visible.
- *
- * This has two callers:
- *
- * - futex_mm_release() after the futex exit cleanup has been done
- *
- * - do_exit() from the recursive fault handling path.
- *
- * In case of a recursive fault this is best effort. Either the futex exit
- * code has run already or not. If the OWNER_DIED bit has been set on the
- * futex then the waiter can take it over. If not, the problem is pushed
- * back to user space. If the futex exit code did not run yet, then an
- * already queued waiter might block forever, but there is nothing which
- * can be done about that.
- */
-static inline void futex_exit_done(struct task_struct *tsk)
-{
-	tsk->futex_state = FUTEX_STATE_DEAD;
-}
-
+void futex_exit_recursive(struct task_struct *tsk);
 void futex_exit_release(struct task_struct *tsk);
 void futex_exec_release(struct task_struct *tsk);
 
@@ -105,7 +80,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 	      u32 __user *uaddr2, u32 val2, u32 val3);
 #else
 static inline void futex_init_task(struct task_struct *tsk) { }
-static inline void futex_exit_done(struct task_struct *tsk) { }
+static inline void futex_exit_recursive(struct task_struct *tsk) { }
 static inline void futex_exit_release(struct task_struct *tsk) { }
 static inline void futex_exec_release(struct task_struct *tsk) { }
 #endif
diff --git a/kernel/exit.c b/kernel/exit.c
index b39f4b3c0f37cbf850c656db0e1dae22451be607..8d3c268fb1b8dc2c779df4981ba6348c7458c6e2 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -695,18 +695,12 @@ void do_exit(long code)
 	 */
 	if (unlikely(tsk->flags & PF_EXITING)) {
 		pr_alert("Fixing recursive fault but reboot is needed!\n");
-		futex_exit_done(tsk);
+		futex_exit_recursive(tsk);
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		schedule();
 	}
 
 	exit_signals(tsk);  /* sets PF_EXITING */
-	/*
-	 * tsk->flags are checked in the futex code to protect against
-	 * an exiting task cleaning up the robust pi futexes.
-	 */
-	smp_mb();
-	raw_spin_unlock_wait(&tsk->pi_lock);
 
 	if (unlikely(in_atomic())) {
 		pr_info("note: %s[%d] exited with preempt_count %d\n",
diff --git a/kernel/futex.c b/kernel/futex.c
index f85635ff2fce1aed50b92c1ed300468ca6b4b9e5..5bd3afee4e13981fde41460d3a02346f5c141606 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -3252,10 +3252,45 @@ void futex_exec_release(struct task_struct *tsk)
 		exit_pi_state_list(tsk);
 }
 
+/**
+ * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD
+ * @tsk:	task to set the state on
+ *
+ * Set the futex exit state of the task lockless. The futex waiter code
+ * observes that state when a task is exiting and loops until the task has
+ * actually finished the futex cleanup. The worst case for this is that the
+ * waiter runs through the wait loop until the state becomes visible.
+ *
+ * This is called from the recursive fault handling path in do_exit().
+ *
+ * This is best effort. Either the futex exit code has run already or
+ * not. If the OWNER_DIED bit has been set on the futex then the waiter can
+ * take it over. If not, the problem is pushed back to user space. If the
+ * futex exit code did not run yet, then an already queued waiter might
+ * block forever, but there is nothing which can be done about that.
+ */
+void futex_exit_recursive(struct task_struct *tsk)
+{
+	tsk->futex_state = FUTEX_STATE_DEAD;
+}
+
 void futex_exit_release(struct task_struct *tsk)
 {
+	tsk->futex_state = FUTEX_STATE_EXITING;
+	/*
+	 * Ensure that all new tsk->pi_lock acquisitions must observe
+	 * FUTEX_STATE_EXITING. Serializes against attach_to_pi_owner().
+	 */
+	smp_mb();
+	/*
+	 * Ensure that we must observe the pi_state in exit_pi_state_list().
+	 */
+	raw_spin_lock_irq(&tsk->pi_lock);
+	raw_spin_unlock_irq(&tsk->pi_lock);
+
 	futex_exec_release(tsk);
-	futex_exit_done(tsk);
+
+	tsk->futex_state = FUTEX_STATE_DEAD;
 }
 
 long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,