Merge "futex: Rework inconsistent rt_mutex/futex_q state"

6 files changed, 90 insertions, 108 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index d24d164e9bdb..6dba4ebfdcfd 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -910,7 +910,7 @@ void exit_pi_state_list(struct task_struct *curr)
 		pi_state->owner = NULL;
 		raw_spin_unlock_irq(&curr->pi_lock);
 
-		rt_mutex_unlock(&pi_state->pi_mutex);
+		rt_mutex_futex_unlock(&pi_state->pi_mutex);
 
 		spin_unlock(&hb->lock);
 
@@ -1312,12 +1312,19 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
 
 	/*
-	 * It is possible that the next waiter (the one that brought
-	 * this owner to the kernel) timed out and is no longer
-	 * waiting on the lock.
+	 * When we interleave with futex_lock_pi() where it does
+	 * rt_mutex_timed_futex_lock(), we might observe @this futex_q waiter,
+	 * but the rt_mutex's wait_list can be empty (either still, or again,
+	 * depending on which side we land).
+	 *
+	 * When this happens, give up our locks and try again, giving the
+	 * futex_lock_pi() instance time to complete, either by waiting on the
+	 * rtmutex or removing itself from the futex queue.
 	 */
-	if (!new_owner)
-		new_owner = this->task;
+	if (!new_owner) {
+		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+		return -EAGAIN;
+	}
 
 	/*
 	 * We pass it to the next owner. The WAITERS bit is always
@@ -1359,20 +1366,18 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 	pi_state->owner = new_owner;
 	raw_spin_unlock_irq(&new_owner->pi_lock);
 
-	raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
-
-	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.
+	 * We've updated the uservalue, this unlock cannot fail.
 	 */
+	deboost = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
+
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	spin_unlock(&hb->lock);
-	wake_up_q(&wake_q);
-	if (deboost)
+
+	if (deboost) {
+		wake_up_q(&wake_q);
 		rt_mutex_adjust_prio(current);
+	}
 
 	return 0;
 }
@@ -2237,7 +2242,6 @@ static long futex_wait_restart(struct restart_block *restart);
  */
 static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 {
-	struct task_struct *owner;
 	int ret = 0;
 
 	if (locked) {
@@ -2251,43 +2255,15 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 	}
 
 	/*
-	 * Catch the rare case, where the lock was released when we were on the
-	 * way back before we locked the hash bucket.
-	 */
-	if (q->pi_state->owner == current) {
-		/*
-		 * Try to get the rt_mutex now. This might fail as some other
-		 * task acquired the rt_mutex after we removed ourself from the
-		 * rt_mutex waiters list.
-		 */
-		if (rt_mutex_trylock(&q->pi_state->pi_mutex)) {
-			locked = 1;
-			goto out;
-		}
-
-		/*
-		 * pi_state is incorrect, some other task did a lock steal and
-		 * we returned due to timeout or signal without taking the
-		 * rt_mutex. Too late.
-		 */
-		raw_spin_lock(&q->pi_state->pi_mutex.wait_lock);
-		owner = rt_mutex_owner(&q->pi_state->pi_mutex);
-		if (!owner)
-			owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
-		raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock);
-		ret = fixup_pi_state_owner(uaddr, q, owner);
-		goto out;
-	}
-
-	/*
 	 * Paranoia check. If we did not take the lock, then we should not be
 	 * the owner of the rt_mutex.
 	 */
-	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
+	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) {
 		printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
 				"pi-state %p\n", ret,
 				q->pi_state->pi_mutex.owner,
 				q->pi_state->owner);
+	}
 
 out:
 	return ret ? ret : locked;
@@ -2575,7 +2551,7 @@ retry_private:
 	if (!trylock) {
 		ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to);
 	} else {
-		ret = rt_mutex_trylock(&q.pi_state->pi_mutex);
+		ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex);
 		/* Fixup the trylock return value: */
 		ret = ret ? 0 : -EWOULDBLOCK;
 	}
@@ -2598,7 +2574,7 @@ retry_private:
 	 * it and return the fault to userspace.
 	 */
 	if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current))
-		rt_mutex_unlock(&q.pi_state->pi_mutex);
+		rt_mutex_futex_unlock(&q.pi_state->pi_mutex);
 
 	/* Unqueue and drop the lock */
 	unqueue_me_pi(&q);
@@ -2905,7 +2881,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 			spin_lock(q.lock_ptr);
 			ret = fixup_pi_state_owner(uaddr2, &q, current);
 			if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current)
-				rt_mutex_unlock(&q.pi_state->pi_mutex);
+				rt_mutex_futex_unlock(&q.pi_state->pi_mutex);
 			/*
 			 * Drop the reference to the pi state which
 			 * the requeue_pi() code acquired for us.
@@ -2948,7 +2924,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		 * userspace.
 		 */
 		if (ret && rt_mutex_owner(pi_mutex) == current)
-			rt_mutex_unlock(pi_mutex);
+			rt_mutex_futex_unlock(pi_mutex);
 
 		/* Unqueue and drop the lock. */
 		unqueue_me_pi(&q);
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index 62b6cee8ea7f..0613c4b1d059 100644
--- a/kernel/locking/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -173,12 +173,3 @@ void debug_rt_mutex_init(struct rt_mutex *lock, const char *name)
 	lock->name = name;
 }
 
-void
-rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task)
-{
-}
-
-void rt_mutex_deadlock_account_unlock(struct task_struct *task)
-{
-}
-
diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h
index d0519c3432b6..b585af9a1b50 100644
--- a/kernel/locking/rtmutex-debug.h
+++ b/kernel/locking/rtmutex-debug.h
@@ -9,9 +9,6 @@
  * This file contains macros used solely by rtmutex.c. Debug version.
  */
 
-extern void
-rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task);
-extern void rt_mutex_deadlock_account_unlock(struct task_struct *task);
 extern void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter);
 extern void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter);
 extern void debug_rt_mutex_init(struct rt_mutex *lock, const char *name);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index dd173df9ee5e..e3dd1642423f 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -937,8 +937,6 @@ takeit:
 	 */
 	rt_mutex_set_owner(lock, task);
 
-	rt_mutex_deadlock_account_lock(lock, task);
-
 	return 1;
 }
 
@@ -1331,8 +1329,6 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
 
 	debug_rt_mutex_unlock(lock);
 
-	rt_mutex_deadlock_account_unlock(current);
-
 	/*
 	 * We must be careful here if the fast path is enabled. If we
 	 * have no waiters queued we cannot set owner to NULL here
@@ -1398,11 +1394,10 @@ rt_mutex_fastlock(struct rt_mutex *lock, int state,
 				struct hrtimer_sleeper *timeout,
 				enum rtmutex_chainwalk chwalk))
 {
-	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
-		rt_mutex_deadlock_account_lock(lock, current);
+	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		return 0;
-	} else
-		return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
+
+	return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
 }
 
 static inline int
@@ -1414,21 +1409,19 @@ rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
 				      enum rtmutex_chainwalk chwalk))
 {
 	if (chwalk == RT_MUTEX_MIN_CHAINWALK &&
-	    likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
-		rt_mutex_deadlock_account_lock(lock, current);
+	    likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		return 0;
-	} else
-		return slowfn(lock, state, timeout, chwalk);
+
+	return slowfn(lock, state, timeout, chwalk);
 }
 
 static inline int
 rt_mutex_fasttrylock(struct rt_mutex *lock,
 		     int (*slowfn)(struct rt_mutex *lock))
 {
-	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
-		rt_mutex_deadlock_account_lock(lock, current);
+	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		return 1;
-	}
+
 	return slowfn(lock);
 }
 
@@ -1438,19 +1431,18 @@ rt_mutex_fastunlock(struct rt_mutex *lock,
 				   struct wake_q_head *wqh))
 {
 	WAKE_Q(wake_q);
+	bool deboost;
 
-	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) {
-		rt_mutex_deadlock_account_unlock(current);
+	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL)))
+		return;
 
-	} else {
-		bool deboost = slowfn(lock, &wake_q);
+	deboost = slowfn(lock, &wake_q);
 
-		wake_up_q(&wake_q);
+	wake_up_q(&wake_q);
 
-		/* Undo pi boosting if necessary: */
-		if (deboost)
-			rt_mutex_adjust_prio(current);
-	}
+	/* Undo pi boosting if necessary: */
+	if (deboost)
+		rt_mutex_adjust_prio(current);
 }
 
 /**
@@ -1485,15 +1477,23 @@ 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);
 }
 
 /**
@@ -1552,20 +1552,38 @@ 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))) {
-		rt_mutex_deadlock_account_unlock(current);
-		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 */
+}
+
+void __sched rt_mutex_futex_unlock(struct rt_mutex *lock)
+{
+	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);
 	}
-	return rt_mutex_slowunlock(lock, wqh);
 }
 
 /**
@@ -1622,7 +1640,6 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 	__rt_mutex_init(lock, NULL);
 	debug_rt_mutex_proxy_lock(lock, proxy_owner);
 	rt_mutex_set_owner(lock, proxy_owner);
-	rt_mutex_deadlock_account_lock(lock, proxy_owner);
 }
 
 /**
@@ -1638,7 +1655,6 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 {
 	debug_rt_mutex_proxy_unlock(lock);
 	rt_mutex_set_owner(lock, NULL);
-	rt_mutex_deadlock_account_unlock(proxy_owner);
 }
 
 /**
diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h
index c4060584c407..6607802efa8b 100644
--- a/kernel/locking/rtmutex.h
+++ b/kernel/locking/rtmutex.h
@@ -11,8 +11,6 @@
  */
 
 #define rt_mutex_deadlock_check(l)			(0)
-#define rt_mutex_deadlock_account_lock(m, t)		do { } while (0)
-#define rt_mutex_deadlock_account_unlock(l)		do { } while (0)
 #define debug_rt_mutex_init_waiter(w)			do { } while (0)
 #define debug_rt_mutex_free_waiter(w)			do { } while (0)
 #define debug_rt_mutex_lock(l)				do { } while (0)
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 6f8f68edb700..cdcaccfb7443 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -112,8 +112,12 @@ 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 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