futex: Rework futex_lock_pi() to use rt_mutex_*_proxy_lock()

By changing futex_lock_pi() to use rt_mutex_*_proxy_lock() all wait_list
modifications are done under both hb->lock and wait_lock.

This closes the obvious interleave pattern between futex_lock_pi() and
futex_unlock_pi(), but not entirely so. See below:

Before:

futex_lock_pi()			futex_unlock_pi()
  unlock hb->lock

				  lock hb->lock
				  unlock hb->lock

				  lock rt_mutex->wait_lock
				  unlock rt_mutex_wait_lock
				    -EAGAIN

  lock rt_mutex->wait_lock
  list_add
  unlock rt_mutex->wait_lock

  schedule()

  lock rt_mutex->wait_lock
  list_del
  unlock rt_mutex->wait_lock

				  <idem>
				    -EAGAIN

  lock hb->lock


After:

futex_lock_pi()			futex_unlock_pi()

  lock hb->lock
  lock rt_mutex->wait_lock
  list_add
  unlock rt_mutex->wait_lock
  unlock hb->lock

  schedule()
				  lock hb->lock
				  unlock hb->lock
  lock hb->lock
  lock rt_mutex->wait_lock
  list_del
  unlock rt_mutex->wait_lock

				  lock rt_mutex->wait_lock
				  unlock rt_mutex_wait_lock
				    -EAGAIN

  unlock hb->lock


It does however solve the earlier starvation/live-lock scenario which got
introduced with the -EAGAIN since unlike the before scenario; where the
-EAGAIN happens while futex_unlock_pi() doesn't hold any locks; in the
after scenario it happens while futex_unlock_pi() actually holds a lock,
and then it is serialized on that lock.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: juri.lelli@arm.com
Cc: bigeasy@linutronix.de
Cc: xlpang@redhat.com
Cc: rostedt@goodmis.org
Cc: mathieu.desnoyers@efficios.com
Cc: jdesfossez@efficios.com
Cc: dvhart@infradead.org
Cc: bristot@redhat.com
Link: http://lkml.kernel.org/r/20170322104152.062785528@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

2 files changed, 7 insertions, 20 deletions

diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 1e8368db276e..48418a1733b8 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1493,19 +1493,6 @@ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
 EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
 
 /*
- * Futex variant with full deadlock detection.
- * Futex variants must not use the fast-path, see __rt_mutex_futex_unlock().
- */
-int __sched rt_mutex_timed_futex_lock(struct rt_mutex *lock,
-			      struct hrtimer_sleeper *timeout)
-{
-	might_sleep();
-
-	return rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE,
-				 timeout, RT_MUTEX_FULL_CHAINWALK);
-}
-
-/*
  * Futex variant, must not use fastpath.
  */
 int __sched rt_mutex_futex_trylock(struct rt_mutex *lock)
@@ -1782,12 +1769,6 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
 	/* sleep on the mutex */
 	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);
 
 	return ret;
@@ -1827,6 +1808,13 @@ bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
 		fixup_rt_mutex_waiters(lock);
 		cleanup = true;
 	}
+
+	/*
+	 * 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);
 
 	return cleanup;
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 35361e4dc773..1e93e15a0e45 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -113,7 +113,6 @@ extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
 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);
 
 extern void rt_mutex_futex_unlock(struct rt_mutex *lock);