With the ultimate goal of keeping rt_mutex wait_list and futex_q
waiters consistent we want to split 'rt_mutex_futex_lock()' into finer
parts, such that only the actual blocking can be done without hb->lock
held.

This means we need to split rt_mutex_finish_proxy_lock() into two
parts, one that does the blocking and one that does remove_waiter()
when we fail to acquire.

When we do acquire, we can safely remove ourselves, since there is no
concurrency on the lock owner.

This means that, except for futex_lock_pi(), all wait_list
modifications are done with both hb->lock and wait_lock held.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/futex.c                  |    5 +++-
 kernel/locking/rtmutex.c        |   47 ++++++++++++++++++++++++++++++++++------
 kernel/locking/rtmutex_common.h |    8 ++++--
 3 files changed, 49 insertions(+), 11 deletions(-)

--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -3012,10 +3012,13 @@ static int futex_wait_requeue_pi(u32 __u
 		 */
 		WARN_ON(!q.pi_state);
 		pi_mutex = &q.pi_state->pi_mutex;
-		ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter);
+		ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter);
 		debug_rt_mutex_free_waiter(&rt_waiter);
 
 		spin_lock(q.lock_ptr);
+		if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter))
+			ret = 0;
+
 		/*
 		 * Fixup the pi_state owner and possibly acquire the lock if we
 		 * haven't already.
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1747,21 +1747,23 @@ struct task_struct *rt_mutex_next_owner(
 }
 
 /**
- * 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)
 {
@@ -1774,9 +1776,6 @@ int rt_mutex_finish_proxy_lock(struct rt
 	/* sleep on the mutex */
 	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
 
-	if (unlikely(ret))
-		remove_waiter(lock, waiter);
-
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
 	 * have to fix that up.
@@ -1787,3 +1786,37 @@ int rt_mutex_finish_proxy_lock(struct rt
 
 	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
+ *
+ * Clean up the failed lock acquisition as per rt_mutex_wait_proxy_lock().
+ *
+ * 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);
+	/*
+	 * If we acquired the lock, no cleanup required.
+	 */
+	if (rt_mutex_owner(lock) != current) {
+		remove_waiter(lock, waiter);
+		fixup_rt_mutex_waiters(lock);
+		cleanup = true;
+	}
+	raw_spin_unlock_irq(&lock->wait_lock);
+
+	return cleanup;
+}
+
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -106,9 +106,11 @@ extern void rt_mutex_proxy_unlock(struct
 extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 				     struct rt_mutex_waiter *waiter,
 				     struct task_struct *task);
-extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
-				      struct hrtimer_sleeper *to,
-				      struct rt_mutex_waiter *waiter);
+extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
+			       struct hrtimer_sleeper *to,
+			       struct rt_mutex_waiter *waiter);
+extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+				 struct rt_mutex_waiter *waiter);
 
 extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to);
 extern int rt_mutex_futex_trylock(struct rt_mutex *l);