1 files changed, 246 insertions, 164 deletions

diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 6edc32ecd9c5..28cd09e635ed 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -224,6 +224,12 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
 }
 #endif
 
+/*
+ * Only use with rt_mutex_waiter_{less,equal}()
+ */
+#define task_to_waiter(p)	\
+	&(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline }
+
 static inline int
 rt_mutex_waiter_less(struct rt_mutex_waiter *left,
 		     struct rt_mutex_waiter *right)
@@ -238,12 +244,30 @@ rt_mutex_waiter_less(struct rt_mutex_waiter *left,
 	 * then right waiter has a dl_prio() too.
 	 */
 	if (dl_prio(left->prio))
-		return dl_time_before(left->task->dl.deadline,
-				      right->task->dl.deadline);
+		return dl_time_before(left->deadline, right->deadline);
 
 	return 0;
 }
 
+static inline int
+rt_mutex_waiter_equal(struct rt_mutex_waiter *left,
+		      struct rt_mutex_waiter *right)
+{
+	if (left->prio != right->prio)
+		return 0;
+
+	/*
+	 * If both waiters have dl_prio(), we check the deadlines of the
+	 * associated tasks.
+	 * If left waiter has a dl_prio(), and we didn't return 0 above,
+	 * then right waiter has a dl_prio() too.
+	 */
+	if (dl_prio(left->prio))
+		return left->deadline == right->deadline;
+
+	return 1;
+}
+
 static void
 rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
 {
@@ -322,72 +346,16 @@ rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
 	RB_CLEAR_NODE(&waiter->pi_tree_entry);
 }
 
-/*
- * Calculate task priority from the waiter tree priority
- *
- * Return task->normal_prio when the waiter tree is empty or when
- * the waiter is not allowed to do priority boosting
- */
-int rt_mutex_getprio(struct task_struct *task)
+static void rt_mutex_adjust_prio(struct task_struct *p)
 {
-	if (likely(!task_has_pi_waiters(task)))
-		return task->normal_prio;
+	struct task_struct *pi_task = NULL;
 
-	return min(task_top_pi_waiter(task)->prio,
-		   task->normal_prio);
-}
+	lockdep_assert_held(&p->pi_lock);
 
-struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
-{
-	if (likely(!task_has_pi_waiters(task)))
-		return NULL;
+	if (task_has_pi_waiters(p))
+		pi_task = task_top_pi_waiter(p)->task;
 
-	return task_top_pi_waiter(task)->task;
-}
-
-/*
- * Called by sched_setscheduler() to get the priority which will be
- * effective after the change.
- */
-int rt_mutex_get_effective_prio(struct task_struct *task, int newprio)
-{
-	if (!task_has_pi_waiters(task))
-		return newprio;
-
-	if (task_top_pi_waiter(task)->task->prio <= newprio)
-		return task_top_pi_waiter(task)->task->prio;
-	return newprio;
-}
-
-/*
- * Adjust the priority of a task, after its pi_waiters got modified.
- *
- * This can be both boosting and unboosting. task->pi_lock must be held.
- */
-static void __rt_mutex_adjust_prio(struct task_struct *task)
-{
-	int prio = rt_mutex_getprio(task);
-
-	if (task->prio != prio || dl_prio(prio))
-		rt_mutex_setprio(task, prio);
-}
-
-/*
- * Adjust task priority (undo boosting). Called from the exit path of
- * rt_mutex_slowunlock() and rt_mutex_slowlock().
- *
- * (Note: We do this outside of the protection of lock->wait_lock to
- * allow the lock to be taken while or before we readjust the priority
- * of task. We do not use the spin_xx_mutex() variants here as we are
- * outside of the debug path.)
- */
-void rt_mutex_adjust_prio(struct task_struct *task)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&task->pi_lock, flags);
-	__rt_mutex_adjust_prio(task);
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	rt_mutex_setprio(p, pi_task);
 }
 
 /*
@@ -610,7 +578,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * enabled we continue, but stop the requeueing in the chain
 	 * walk.
 	 */
-	if (waiter->prio == task->prio) {
+	if (rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
 		if (!detect_deadlock)
 			goto out_unlock_pi;
 		else
@@ -706,7 +674,26 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 
 	/* [7] Requeue the waiter in the lock waiter tree. */
 	rt_mutex_dequeue(lock, waiter);
+
+	/*
+	 * Update the waiter prio fields now that we're dequeued.
+	 *
+	 * These values can have changed through either:
+	 *
+	 *   sys_sched_set_scheduler() / sys_sched_setattr()
+	 *
+	 * or
+	 *
+	 *   DL CBS enforcement advancing the effective deadline.
+	 *
+	 * Even though pi_waiters also uses these fields, and that tree is only
+	 * updated in [11], we can do this here, since we hold [L], which
+	 * serializes all pi_waiters access and rb_erase() does not care about
+	 * the values of the node being removed.
+	 */
 	waiter->prio = task->prio;
+	waiter->deadline = task->dl.deadline;
+
 	rt_mutex_enqueue(lock, waiter);
 
 	/* [8] Release the task */
@@ -747,7 +734,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		 */
 		rt_mutex_dequeue_pi(task, prerequeue_top_waiter);
 		rt_mutex_enqueue_pi(task, waiter);
-		__rt_mutex_adjust_prio(task);
+		rt_mutex_adjust_prio(task);
 
 	} else if (prerequeue_top_waiter == waiter) {
 		/*
@@ -763,7 +750,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		rt_mutex_dequeue_pi(task, waiter);
 		waiter = rt_mutex_top_waiter(lock);
 		rt_mutex_enqueue_pi(task, waiter);
-		__rt_mutex_adjust_prio(task);
+		rt_mutex_adjust_prio(task);
 	} else {
 		/*
 		 * Nothing changed. No need to do any priority
@@ -833,6 +820,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 				struct rt_mutex_waiter *waiter)
 {
+	lockdep_assert_held(&lock->wait_lock);
+
 	/*
 	 * Before testing whether we can acquire @lock, we set the
 	 * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all
@@ -892,7 +881,8 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 			 * the top waiter priority (kernel view),
 			 * @task lost.
 			 */
-			if (task->prio >= rt_mutex_top_waiter(lock)->prio)
+			if (!rt_mutex_waiter_less(task_to_waiter(task),
+						  rt_mutex_top_waiter(lock)))
 				return 0;
 
 			/*
@@ -938,8 +928,6 @@ takeit:
 	 */
 	rt_mutex_set_owner(lock, task);
 
-	rt_mutex_deadlock_account_lock(lock, task);
-
 	return 1;
 }
 
@@ -960,6 +948,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	struct rt_mutex *next_lock;
 	int chain_walk = 0, res;
 
+	lockdep_assert_held(&lock->wait_lock);
+
 	/*
 	 * Early deadlock detection. We really don't want the task to
 	 * enqueue on itself just to untangle the mess later. It's not
@@ -973,10 +963,11 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 		return -EDEADLK;
 
 	raw_spin_lock(&task->pi_lock);
-	__rt_mutex_adjust_prio(task);
+	rt_mutex_adjust_prio(task);
 	waiter->task = task;
 	waiter->lock = lock;
 	waiter->prio = task->prio;
+	waiter->deadline = task->dl.deadline;
 
 	/* Get the top priority waiter on the lock */
 	if (rt_mutex_has_waiters(lock))
@@ -995,7 +986,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 		rt_mutex_dequeue_pi(owner, top_waiter);
 		rt_mutex_enqueue_pi(owner, waiter);
 
-		__rt_mutex_adjust_prio(owner);
+		rt_mutex_adjust_prio(owner);
 		if (owner->pi_blocked_on)
 			chain_walk = 1;
 	} else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
@@ -1047,12 +1038,14 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
 	waiter = rt_mutex_top_waiter(lock);
 
 	/*
-	 * Remove it from current->pi_waiters. We do not adjust a
-	 * possible priority boost right now. We execute wakeup in the
-	 * boosted mode and go back to normal after releasing
-	 * lock->wait_lock.
+	 * Remove it from current->pi_waiters and deboost.
+	 *
+	 * We must in fact deboost here in order to ensure we call
+	 * rt_mutex_setprio() to update p->pi_top_task before the
+	 * task unblocks.
 	 */
 	rt_mutex_dequeue_pi(current, waiter);
+	rt_mutex_adjust_prio(current);
 
 	/*
 	 * As we are waking up the top waiter, and the waiter stays
@@ -1064,9 +1057,19 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
 	 */
 	lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
 
-	raw_spin_unlock(&current->pi_lock);
-
+	/*
+	 * We deboosted before waking the top waiter task such that we don't
+	 * run two tasks with the 'same' priority (and ensure the
+	 * p->pi_top_task pointer points to a blocked task). This however can
+	 * lead to priority inversion if we would get preempted after the
+	 * deboost but before waking our donor task, hence the preempt_disable()
+	 * before unlock.
+	 *
+	 * Pairs with preempt_enable() in rt_mutex_postunlock();
+	 */
+	preempt_disable();
 	wake_q_add(wake_q, waiter->task);
+	raw_spin_unlock(&current->pi_lock);
 }
 
 /*
@@ -1082,6 +1085,8 @@ static void remove_waiter(struct rt_mutex *lock,
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex *next_lock;
 
+	lockdep_assert_held(&lock->wait_lock);
+
 	raw_spin_lock(&current->pi_lock);
 	rt_mutex_dequeue(lock, waiter);
 	current->pi_blocked_on = NULL;
@@ -1101,7 +1106,7 @@ static void remove_waiter(struct rt_mutex *lock,
 	if (rt_mutex_has_waiters(lock))
 		rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock));
 
-	__rt_mutex_adjust_prio(owner);
+	rt_mutex_adjust_prio(owner);
 
 	/* Store the lock on which owner is blocked or NULL */
 	next_lock = task_blocked_on_lock(owner);
@@ -1140,8 +1145,7 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
 	waiter = task->pi_blocked_on;
-	if (!waiter || (waiter->prio == task->prio &&
-			!dl_prio(task->prio))) {
+	if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
@@ -1155,6 +1159,14 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 				   next_lock, NULL, task);
 }
 
+void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
+{
+	debug_rt_mutex_init_waiter(waiter);
+	RB_CLEAR_NODE(&waiter->pi_tree_entry);
+	RB_CLEAR_NODE(&waiter->tree_entry);
+	waiter->task = NULL;
+}
+
 /**
  * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
  * @lock:		 the rt_mutex to take
@@ -1237,9 +1249,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	unsigned long flags;
 	int ret = 0;
 
-	debug_rt_mutex_init_waiter(&waiter);
-	RB_CLEAR_NODE(&waiter.pi_tree_entry);
-	RB_CLEAR_NODE(&waiter.tree_entry);
+	rt_mutex_init_waiter(&waiter);
 
 	/*
 	 * Technically we could use raw_spin_[un]lock_irq() here, but this can
@@ -1330,7 +1340,8 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
 
 /*
  * Slow path to release a rt-mutex.
- * Return whether the current task needs to undo a potential priority boosting.
+ *
+ * Return whether the current task needs to call rt_mutex_postunlock().
  */
 static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
 					struct wake_q_head *wake_q)
@@ -1342,8 +1353,6 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
 
 	debug_rt_mutex_unlock(lock);
 
-	rt_mutex_deadlock_account_unlock(current);
-
 	/*
 	 * We must be careful here if the fast path is enabled. If we
 	 * have no waiters queued we cannot set owner to NULL here
@@ -1390,11 +1399,9 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
 	 * Queue the next waiter for wakeup once we release the wait_lock.
 	 */
 	mark_wakeup_next_waiter(wake_q, lock);
-
 	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
-	/* check PI boosting */
-	return true;
+	return true; /* call rt_mutex_postunlock() */
 }
 
 /*
@@ -1409,11 +1416,10 @@ rt_mutex_fastlock(struct rt_mutex *lock, int state,
 				struct hrtimer_sleeper *timeout,
 				enum rtmutex_chainwalk chwalk))
 {
-	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
-		rt_mutex_deadlock_account_lock(lock, current);
+	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		return 0;
-	} else
-		return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
+
+	return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
 }
 
 static inline int
@@ -1425,24 +1431,33 @@ rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
 				      enum rtmutex_chainwalk chwalk))
 {
 	if (chwalk == RT_MUTEX_MIN_CHAINWALK &&
-	    likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
-		rt_mutex_deadlock_account_lock(lock, current);
+	    likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		return 0;
-	} else
-		return slowfn(lock, state, timeout, chwalk);
+
+	return slowfn(lock, state, timeout, chwalk);
 }
 
 static inline int
 rt_mutex_fasttrylock(struct rt_mutex *lock,
 		     int (*slowfn)(struct rt_mutex *lock))
 {
-	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
-		rt_mutex_deadlock_account_lock(lock, current);
+	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		return 1;
-	}
+
 	return slowfn(lock);
 }
 
+/*
+ * Performs the wakeup of the the top-waiter and re-enables preemption.
+ */
+void rt_mutex_postunlock(struct wake_q_head *wake_q)
+{
+	wake_up_q(wake_q);
+
+	/* Pairs with preempt_disable() in rt_mutex_slowunlock() */
+	preempt_enable();
+}
+
 static inline void
 rt_mutex_fastunlock(struct rt_mutex *lock,
 		    bool (*slowfn)(struct rt_mutex *lock,
@@ -1450,18 +1465,11 @@ rt_mutex_fastunlock(struct rt_mutex *lock,
 {
 	DEFINE_WAKE_Q(wake_q);
 
-	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) {
-		rt_mutex_deadlock_account_unlock(current);
-
-	} else {
-		bool deboost = slowfn(lock, &wake_q);
-
-		wake_up_q(&wake_q);
+	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL)))
+		return;
 
-		/* Undo pi boosting if necessary: */
-		if (deboost)
-			rt_mutex_adjust_prio(current);
-	}
+	if (slowfn(lock, &wake_q))
+		rt_mutex_postunlock(&wake_q);
 }
 
 /**
@@ -1495,16 +1503,11 @@ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
 EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
 
 /*
- * Futex variant with full deadlock detection.
+ * Futex variant, must not use fastpath.
  */
-int rt_mutex_timed_futex_lock(struct rt_mutex *lock,
-			      struct hrtimer_sleeper *timeout)
+int __sched rt_mutex_futex_trylock(struct rt_mutex *lock)
 {
-	might_sleep();
-
-	return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
-				       RT_MUTEX_FULL_CHAINWALK,
-				       rt_mutex_slowlock);
+	return rt_mutex_slowtrylock(lock);
 }
 
 /**
@@ -1563,20 +1566,43 @@ void __sched rt_mutex_unlock(struct rt_mutex *lock)
 EXPORT_SYMBOL_GPL(rt_mutex_unlock);
 
 /**
- * rt_mutex_futex_unlock - Futex variant of rt_mutex_unlock
- * @lock: the rt_mutex to be unlocked
- *
- * Returns: true/false indicating whether priority adjustment is
- * required or not.
+ * Futex variant, that since futex variants do not use the fast-path, can be
+ * simple and will not need to retry.
  */
-bool __sched rt_mutex_futex_unlock(struct rt_mutex *lock,
-				   struct wake_q_head *wqh)
+bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock,
+				    struct wake_q_head *wake_q)
 {
-	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) {
-		rt_mutex_deadlock_account_unlock(current);
-		return false;
+	lockdep_assert_held(&lock->wait_lock);
+
+	debug_rt_mutex_unlock(lock);
+
+	if (!rt_mutex_has_waiters(lock)) {
+		lock->owner = NULL;
+		return false; /* done */
 	}
-	return rt_mutex_slowunlock(lock, wqh);
+
+	/*
+	 * We've already deboosted, mark_wakeup_next_waiter() will
+	 * retain preempt_disabled when we drop the wait_lock, to
+	 * avoid inversion prior to the wakeup.  preempt_disable()
+	 * therein pairs with rt_mutex_postunlock().
+	 */
+	mark_wakeup_next_waiter(wake_q, lock);
+
+	return true; /* call postunlock() */
+}
+
+void __sched rt_mutex_futex_unlock(struct rt_mutex *lock)
+{
+	DEFINE_WAKE_Q(wake_q);
+	bool postunlock;
+
+	raw_spin_lock_irq(&lock->wait_lock);
+	postunlock = __rt_mutex_futex_unlock(lock, &wake_q);
+	raw_spin_unlock_irq(&lock->wait_lock);
+
+	if (postunlock)
+		rt_mutex_postunlock(&wake_q);
 }
 
 /**
@@ -1637,7 +1663,6 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 	__rt_mutex_init(lock, NULL);
 	debug_rt_mutex_proxy_lock(lock, proxy_owner);
 	rt_mutex_set_owner(lock, proxy_owner);
-	rt_mutex_deadlock_account_lock(lock, proxy_owner);
 }
 
 /**
@@ -1657,34 +1682,16 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 {
 	debug_rt_mutex_proxy_unlock(lock);
 	rt_mutex_set_owner(lock, NULL);
-	rt_mutex_deadlock_account_unlock(proxy_owner);
 }
 
-/**
- * rt_mutex_start_proxy_lock() - Start lock acquisition for another task
- * @lock:		the rt_mutex to take
- * @waiter:		the pre-initialized rt_mutex_waiter
- * @task:		the task to prepare
- *
- * Returns:
- *  0 - task blocked on lock
- *  1 - acquired the lock for task, caller should wake it up
- * <0 - error
- *
- * Special API call for FUTEX_REQUEUE_PI support.
- */
-int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 			      struct rt_mutex_waiter *waiter,
 			      struct task_struct *task)
 {
 	int ret;
 
-	raw_spin_lock_irq(&lock->wait_lock);
-
-	if (try_to_take_rt_mutex(lock, task, NULL)) {
-		raw_spin_unlock_irq(&lock->wait_lock);
+	if (try_to_take_rt_mutex(lock, task, NULL))
 		return 1;
-	}
 
 	/* We enforce deadlock detection for futexes */
 	ret = task_blocks_on_rt_mutex(lock, waiter, task,
@@ -1703,14 +1710,38 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 	if (unlikely(ret))
 		remove_waiter(lock, waiter);
 
-	raw_spin_unlock_irq(&lock->wait_lock);
-
 	debug_rt_mutex_print_deadlock(waiter);
 
 	return ret;
 }
 
 /**
+ * rt_mutex_start_proxy_lock() - Start lock acquisition for another task
+ * @lock:		the rt_mutex to take
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ * @task:		the task to prepare
+ *
+ * Returns:
+ *  0 - task blocked on lock
+ *  1 - acquired the lock for task, caller should wake it up
+ * <0 - error
+ *
+ * Special API call for FUTEX_REQUEUE_PI support.
+ */
+int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+			      struct rt_mutex_waiter *waiter,
+			      struct task_struct *task)
+{
+	int ret;
+
+	raw_spin_lock_irq(&lock->wait_lock);
+	ret = __rt_mutex_start_proxy_lock(lock, waiter, task);
+	raw_spin_unlock_irq(&lock->wait_lock);
+
+	return ret;
+}
+
+/**
  * rt_mutex_next_owner - return the next owner of the lock
  *
  * @lock: the rt lock query
@@ -1731,36 +1762,87 @@ struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock)
 }
 
 /**
- * rt_mutex_finish_proxy_lock() - Complete lock acquisition
+ * rt_mutex_wait_proxy_lock() - Wait for lock acquisition
  * @lock:		the rt_mutex we were woken on
  * @to:			the timeout, null if none. hrtimer should already have
  *			been started.
  * @waiter:		the pre-initialized rt_mutex_waiter
  *
- * Complete the lock acquisition started our behalf by another thread.
+ * Wait for the the lock acquisition started on our behalf by
+ * rt_mutex_start_proxy_lock(). Upon failure, the caller must call
+ * rt_mutex_cleanup_proxy_lock().
  *
  * Returns:
  *  0 - success
  * <0 - error, one of -EINTR, -ETIMEDOUT
  *
- * Special API call for PI-futex requeue support
+ * Special API call for PI-futex support
  */
-int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
+int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
 			       struct hrtimer_sleeper *to,
 			       struct rt_mutex_waiter *waiter)
 {
 	int ret;
 
 	raw_spin_lock_irq(&lock->wait_lock);
-
-	set_current_state(TASK_INTERRUPTIBLE);
-
 	/* sleep on the mutex */
+	set_current_state(TASK_INTERRUPTIBLE);
 	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
+	/*
+	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
+	 * have to fix that up.
+	 */
+	fixup_rt_mutex_waiters(lock);
+	raw_spin_unlock_irq(&lock->wait_lock);
 
-	if (unlikely(ret))
-		remove_waiter(lock, waiter);
+	return ret;
+}
+
+/**
+ * rt_mutex_cleanup_proxy_lock() - Cleanup failed lock acquisition
+ * @lock:		the rt_mutex we were woken on
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ *
+ * Attempt to clean up after a failed rt_mutex_wait_proxy_lock().
+ *
+ * Unless we acquired the lock; we're still enqueued on the wait-list and can
+ * in fact still be granted ownership until we're removed. Therefore we can
+ * find we are in fact the owner and must disregard the
+ * rt_mutex_wait_proxy_lock() failure.
+ *
+ * Returns:
+ *  true  - did the cleanup, we done.
+ *  false - we acquired the lock after rt_mutex_wait_proxy_lock() returned,
+ *          caller should disregards its return value.
+ *
+ * Special API call for PI-futex support
+ */
+bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+				 struct rt_mutex_waiter *waiter)
+{
+	bool cleanup = false;
 
+	raw_spin_lock_irq(&lock->wait_lock);
+	/*
+	 * Do an unconditional try-lock, this deals with the lock stealing
+	 * state where __rt_mutex_futex_unlock() -> mark_wakeup_next_waiter()
+	 * sets a NULL owner.
+	 *
+	 * We're not interested in the return value, because the subsequent
+	 * test on rt_mutex_owner() will infer that. If the trylock succeeded,
+	 * we will own the lock and it will have removed the waiter. If we
+	 * failed the trylock, we're still not owner and we need to remove
+	 * ourselves.
+	 */
+	try_to_take_rt_mutex(lock, current, waiter);
+	/*
+	 * Unless we're the owner; we're still enqueued on the wait_list.
+	 * So check if we became owner, if not, take us off the wait_list.
+	 */
+	if (rt_mutex_owner(lock) != current) {
+		remove_waiter(lock, waiter);
+		cleanup = true;
+	}
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
 	 * have to fix that up.
@@ -1769,5 +1851,5 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 
 	raw_spin_unlock_irq(&lock->wait_lock);
 
-	return ret;
+	return cleanup;
 }