1 files changed, 48 insertions, 24 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index 2579e407ff67..c4a182f5357e 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1090,9 +1090,11 @@ static void __unqueue_futex(struct futex_q *q)
 
 /*
  * The hash bucket lock must be held when this is called.
- * Afterwards, the futex_q must not be accessed.
+ * Afterwards, the futex_q must not be accessed. Callers
+ * must ensure to later call wake_up_q() for the actual
+ * wakeups to occur.
  */
-static void wake_futex(struct futex_q *q)
+static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
 {
 	struct task_struct *p = q->task;
 
@@ -1100,14 +1102,10 @@ static void wake_futex(struct futex_q *q)
 		return;
 
 	/*
-	 * We set q->lock_ptr = NULL _before_ we wake up the task. If
-	 * a non-futex wake up happens on another CPU then the task
-	 * might exit and p would dereference a non-existing task
-	 * struct. Prevent this by holding a reference on p across the
-	 * wake up.
+	 * Queue the task for later wakeup for after we've released
+	 * the hb->lock. wake_q_add() grabs reference to p.
 	 */
-	get_task_struct(p);
-
+	wake_q_add(wake_q, p);
 	__unqueue_futex(q);
 	/*
 	 * The waiting task can free the futex_q as soon as
@@ -1117,16 +1115,16 @@ static void wake_futex(struct futex_q *q)
 	 */
 	smp_wmb();
 	q->lock_ptr = NULL;
-
-	wake_up_state(p, TASK_NORMAL);
-	put_task_struct(p);
 }
 
-static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
+static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
+			 struct futex_hash_bucket *hb)
 {
 	struct task_struct *new_owner;
 	struct futex_pi_state *pi_state = this->pi_state;
 	u32 uninitialized_var(curval), newval;
+	WAKE_Q(wake_q);
+	bool deboost;
 	int ret = 0;
 
 	if (!pi_state)
@@ -1178,7 +1176,19 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 	raw_spin_unlock_irq(&new_owner->pi_lock);
 
 	raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
-	rt_mutex_unlock(&pi_state->pi_mutex);
+
+	deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
+
+	/*
+	 * First unlock HB so the waiter does not spin on it once he got woken
+	 * up. Second wake up the waiter before the priority is adjusted. If we
+	 * deboost first (and lose our higher priority), then the task might get
+	 * scheduled away before the wake up can take place.
+	 */
+	spin_unlock(&hb->lock);
+	wake_up_q(&wake_q);
+	if (deboost)
+		rt_mutex_adjust_prio(current);
 
 	return 0;
 }
@@ -1217,6 +1227,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 	struct futex_q *this, *next;
 	union futex_key key = FUTEX_KEY_INIT;
 	int ret;
+	WAKE_Q(wake_q);
 
 	if (!bitset)
 		return -EINVAL;
@@ -1244,13 +1255,14 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 			if (!(this->bitset & bitset))
 				continue;
 
-			wake_futex(this);
+			mark_wake_futex(&wake_q, this);
 			if (++ret >= nr_wake)
 				break;
 		}
 	}
 
 	spin_unlock(&hb->lock);
+	wake_up_q(&wake_q);
 out_put_key:
 	put_futex_key(&key);
 out:
@@ -1269,6 +1281,7 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
 	struct futex_hash_bucket *hb1, *hb2;
 	struct futex_q *this, *next;
 	int ret, op_ret;
+	WAKE_Q(wake_q);
 
 retry:
 	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
@@ -1320,7 +1333,7 @@ retry_private:
 				ret = -EINVAL;
 				goto out_unlock;
 			}
-			wake_futex(this);
+			mark_wake_futex(&wake_q, this);
 			if (++ret >= nr_wake)
 				break;
 		}
@@ -1334,7 +1347,7 @@ retry_private:
 					ret = -EINVAL;
 					goto out_unlock;
 				}
-				wake_futex(this);
+				mark_wake_futex(&wake_q, this);
 				if (++op_ret >= nr_wake2)
 					break;
 			}
@@ -1344,6 +1357,7 @@ retry_private:
 
 out_unlock:
 	double_unlock_hb(hb1, hb2);
+	wake_up_q(&wake_q);
 out_put_keys:
 	put_futex_key(&key2);
 out_put_key1:
@@ -1503,6 +1517,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct futex_q *this, *next;
+	WAKE_Q(wake_q);
 
 	if (requeue_pi) {
 		/*
@@ -1679,7 +1694,7 @@ retry_private:
 		 * woken by futex_unlock_pi().
 		 */
 		if (++task_count <= nr_wake && !requeue_pi) {
-			wake_futex(this);
+			mark_wake_futex(&wake_q, this);
 			continue;
 		}
 
@@ -1719,6 +1734,7 @@ retry_private:
 out_unlock:
 	free_pi_state(pi_state);
 	double_unlock_hb(hb1, hb2);
+	wake_up_q(&wake_q);
 	hb_waiters_dec(hb2);
 
 	/*
@@ -2055,7 +2071,7 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
 {
 	/*
 	 * The task state is guaranteed to be set before another task can
-	 * wake it. set_current_state() is implemented using set_mb() and
+	 * wake it. set_current_state() is implemented using smp_store_mb() and
 	 * queue_me() calls spin_unlock() upon completion, both serializing
 	 * access to the hash list and forcing another memory barrier.
 	 */
@@ -2063,11 +2079,8 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
 	queue_me(q, hb);
 
 	/* Arm the timer */
-	if (timeout) {
+	if (timeout)
 		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
-		if (!hrtimer_active(&timeout->timer))
-			timeout->task = NULL;
-	}
 
 	/*
 	 * If we have been removed from the hash list, then another task
@@ -2412,13 +2425,23 @@ retry:
 	 */
 	match = futex_top_waiter(hb, &key);
 	if (match) {
-		ret = wake_futex_pi(uaddr, uval, match);
+		ret = wake_futex_pi(uaddr, uval, match, hb);
+		/*
+		 * In case of success wake_futex_pi dropped the hash
+		 * bucket lock.
+		 */
+		if (!ret)
+			goto out_putkey;
 		/*
 		 * The atomic access to the futex value generated a
 		 * pagefault, so retry the user-access and the wakeup:
 		 */
 		if (ret == -EFAULT)
 			goto pi_faulted;
+		/*
+		 * wake_futex_pi has detected invalid state. Tell user
+		 * space.
+		 */
 		goto out_unlock;
 	}
 
@@ -2439,6 +2462,7 @@ retry:
 
 out_unlock:
 	spin_unlock(&hb->lock);
+out_putkey:
 	put_futex_key(&key);
 	return ret;