Merge branch 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  rtmutex: tester: Remove the remaining BKL leftovers
  lockdep/timers: Explain in detail the locking problems del_timer_sync() may cause
  rtmutex: Simplify PI algorithm and make highest prio task get lock
  rwsem: Remove redundant asmregparm annotation
  rwsem: Move duplicate function prototypes to linux/rwsem.h
  rwsem: Unify the duplicate rwsem_is_locked() inlines
  rwsem: Move duplicate init macros and functions to linux/rwsem.h
  rwsem: Move duplicate struct rwsem declaration to linux/rwsem.h
  x86: Cleanup rwsem_count_t typedef
  rwsem: Cleanup includes
  locking: Remove deprecated lock initializers
  cred: Replace deprecated spinlock initialization
  kthread: Replace deprecated spinlock initialization
  xtensa: Replace deprecated spinlock initialization
  um: Replace deprecated spinlock initialization
  sparc: Replace deprecated spinlock initialization
  mips: Replace deprecated spinlock initialization
  cris: Replace deprecated spinlock initialization
  alpha: Replace deprecated spinlock initialization
  rtmutex-tester: Remove BKL tests

1 files changed, 12 insertions, 10 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index e9251d9..bda4157 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1555,10 +1555,10 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 
 	/*
 	 * We are here either because we stole the rtmutex from the
-	 * pending owner or we are the pending owner which failed to
-	 * get the rtmutex. We have to replace the pending owner TID
-	 * in the user space variable. This must be atomic as we have
-	 * to preserve the owner died bit here.
+	 * previous highest priority waiter or we are the highest priority
+	 * waiter but failed to get the rtmutex the first time.
+	 * We have to replace the newowner TID in the user space variable.
+	 * This must be atomic as we have to preserve the owner died bit here.
 	 *
 	 * Note: We write the user space value _before_ changing the pi_state
 	 * because we can fault here. Imagine swapped out pages or a fork
@@ -1605,8 +1605,8 @@ retry:
 
 	/*
 	 * To handle the page fault we need to drop the hash bucket
-	 * lock here. That gives the other task (either the pending
-	 * owner itself or the task which stole the rtmutex) the
+	 * lock here. That gives the other task (either the highest priority
+	 * waiter itself or the task which stole the rtmutex) the
 	 * chance to try the fixup of the pi_state. So once we are
 	 * back from handling the fault we need to check the pi_state
 	 * after reacquiring the hash bucket lock and before trying to
@@ -1682,18 +1682,20 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 		/*
 		 * 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. We can access the rt_mutex_owner without
-		 * locking, as the other task is now blocked on the hash bucket
-		 * lock. Fix the state up.
+		 * 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, nor the pending owner, of the rt_mutex.
+	 * the owner of the rt_mutex.
 	 */
 	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
 		printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "