futex,rt_mutex: Provide futex specific rt_mutex API

Part of what makes futex_unlock_pi() intricate is that
rt_mutex_futex_unlock() -> rt_mutex_slowunlock() can drop
rt_mutex::wait_lock.

This means it cannot rely on the atomicy of wait_lock, which would be
preferred in order to not rely on hb->lock so much.

The reason rt_mutex_slowunlock() needs to drop wait_lock is because it can
race with the rt_mutex fastpath, however futexes have their own fast path.

Since futexes already have a bunch of separate rt_mutex accessors, complete
that set and implement a rt_mutex variant without fastpath for them.

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/20170322104151.702962446@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

2 files changed, 48 insertions, 16 deletions

diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index bab66cbe3b37..7d63bc5dd9b2 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1488,15 +1488,23 @@ 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 rt_mutex_timed_futex_lock(struct rt_mutex *lock,
+int __sched rt_mutex_timed_futex_lock(struct rt_mutex *lock,
 			      struct hrtimer_sleeper *timeout)
 {
 	might_sleep();
 
-	return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
-				       RT_MUTEX_FULL_CHAINWALK,
-				       rt_mutex_slowlock);
+	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)
+{
+	return rt_mutex_slowtrylock(lock);
 }
 
 /**
@@ -1555,19 +1563,38 @@ 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)))
-		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 */
+	}
+
+	mark_wakeup_next_waiter(wake_q, lock);
+	return true; /* deboost and wakeups */
+}
 
-	return rt_mutex_slowunlock(lock, wqh);
+void __sched rt_mutex_futex_unlock(struct rt_mutex *lock)
+{
+	DEFINE_WAKE_Q(wake_q);
+	bool deboost;
+
+	raw_spin_lock_irq(&lock->wait_lock);
+	deboost = __rt_mutex_futex_unlock(lock, &wake_q);
+	raw_spin_unlock_irq(&lock->wait_lock);
+
+	if (deboost) {
+		wake_up_q(&wake_q);
+		rt_mutex_adjust_prio(current);
+	}
 }
 
 /**
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 856dfff5c33a..af667f61ebcb 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -109,9 +109,14 @@ extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 				      struct hrtimer_sleeper *to,
 				      struct rt_mutex_waiter *waiter);
+
 extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to);
-extern bool rt_mutex_futex_unlock(struct rt_mutex *lock,
-				  struct wake_q_head *wqh);
+extern int rt_mutex_futex_trylock(struct rt_mutex *l);
+
+extern void rt_mutex_futex_unlock(struct rt_mutex *lock);
+extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock,
+				 struct wake_q_head *wqh);
+
 extern void rt_mutex_adjust_prio(struct task_struct *task);
 
 #ifdef CONFIG_DEBUG_RT_MUTEXES