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.orgSigned-off-by: Thomas Gleixner <tglx@linutronix.de>

kernel/futex.c

@@ -2099,20 +2099,7 @@ queue_unlock(struct futex_hash_bucket *hb)
 	hb_waiters_dec(hb);
 }
 
-/**
- * queue_me() - Enqueue the futex_q on the futex_hash_bucket
- * @q:	The futex_q to enqueue
- * @hb:	The destination hash bucket
- *
- * The hb->lock must be held by the caller, and is released here. A call to
- * queue_me() is typically paired with exactly one call to unqueue_me().  The
- * exceptions involve the PI related operations, which may use unqueue_me_pi()
- * or nothing if the unqueue is done as part of the wake process and the unqueue
- * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
- * an example).
- */
-static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
-	__releases(&hb->lock)
+static inline void __queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
 {
 	int prio;
 
@@ -2129,6 +2116,24 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
 	plist_node_init(&q->list, prio);
 	plist_add(&q->list, &hb->chain);
 	q->task = current;
+}
+
+/**
+ * queue_me() - Enqueue the futex_q on the futex_hash_bucket
+ * @q:	The futex_q to enqueue
+ * @hb:	The destination hash bucket
+ *
+ * The hb->lock must be held by the caller, and is released here. A call to
+ * queue_me() is typically paired with exactly one call to unqueue_me().  The
+ * exceptions involve the PI related operations, which may use unqueue_me_pi()
+ * or nothing if the unqueue is done as part of the wake process and the unqueue
+ * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
+ * an example).
+ */
+static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
+	__releases(&hb->lock)
+{
+	__queue_me(q, hb);
 	spin_unlock(&hb->lock);
 }
 
@@ -2587,6 +2592,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
 	struct futex_pi_state *pi_state = NULL;
+	struct rt_mutex_waiter rt_waiter;
 	struct futex_hash_bucket *hb;
 	struct futex_q q = futex_q_init;
 	int res, ret;
@@ -2639,24 +2645,51 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 		}
 	}
 
+	WARN_ON(!q.pi_state);
+
 	/*
 	 * Only actually queue now that the atomic ops are done:
 	 */
-	queue_me(&q, hb);
+	__queue_me(&q, hb);
 
-	WARN_ON(!q.pi_state);
-	/*
-	 * Block on the PI mutex:
-	 */
-	if (!trylock) {
-		ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to);
-	} else {
+	if (trylock) {
 		ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex);
 		/* Fixup the trylock return value: */
 		ret = ret ? 0 : -EWOULDBLOCK;
+		goto no_block;
+	}
+
+	/*
+	 * We must add ourselves to the rt_mutex waitlist while holding hb->lock
+	 * such that the hb and rt_mutex wait lists match.
+	 */
+	rt_mutex_init_waiter(&rt_waiter);
+	ret = rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
+	if (ret) {
+		if (ret == 1)
+			ret = 0;
+
+		goto no_block;
 	}
 
+	spin_unlock(q.lock_ptr);
+
+	if (unlikely(to))
+		hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS);
+
+	ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);
+
 	spin_lock(q.lock_ptr);
+	/*
+	 * If we failed to acquire the lock (signal/timeout), we must
+	 * first acquire the hb->lock before removing the lock from the
+	 * rt_mutex waitqueue, such that we can keep the hb and rt_mutex
+	 * wait lists consistent.
+	 */
+	if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter))
+		ret = 0;
+
+no_block:
 	/*
 	 * Fixup the pi_state owner and possibly acquire the lock if we
 	 * haven't already.

kernel/locking/rtmutex.c

@@ -1492,19 +1492,6 @@ 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.
  */
@@ -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;

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);