Bug with futex requeue piv3.2.2-rt10

I found the problem:

The bug comes from a timed out condition.

	TASK 1				TASK 2
	------				------
    futex_wait_requeue_pi()
	futex_wait_queue_me()
	<timed out>

					double_lock_hb();

	raw_spin_lock(pi_lock);
	if (current->pi_blocked_on) {
	} else {
	    current->pi_blocked_on = PI_WAKE_INPROGRESS;
	    run_spin_unlock(pi_lock);
	    spin_lock(hb->lock); <-- blocked!

					plist_for_each_entry_safe(this) {
					    rt_mutex_start_proxy_lock();
						task_blocks_on_rt_mutex();
						BUG_ON(task->pi_blocked_on)!!!!

The BUG_ON() actually has a check for PI_WAKE_INPROGRESS, but the
problem is that, after TASK 1 sets PI_WAKE_INPROGRESS, it then tries to
grab the hb->lock, which it fails to do so. As the hb->lock is a mutex,
it will block and set the "pi_blocked_on" to the hb->lock.

When TASK 2 goes to requeue it, the check for PI_WAKE_INPROGESS fails
because the task1's pi_blocked_on is no longer set to that, but instead,
set to the hb->lock.

We need a way in rt_mutex_start_proxy_lock() to prevent this.

I just added the below patch, which makes the bug go away. It's a little
ugly (but no more ugly than the pi futex_requeue already is ;-)

-- Steve

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

1 files changed, 1 insertions, 0 deletions

diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h
index a688a299b36b..6ec3dc1eab10 100644
--- a/kernel/rtmutex_common.h
+++ b/kernel/rtmutex_common.h
@@ -105,6 +105,7 @@ static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
  * PI-futex support (proxy locking functions, etc.):
  */
 #define PI_WAKEUP_INPROGRESS	((struct rt_mutex_waiter *) 1)
+#define PI_REQUEUE_INPROGRESS	((struct rt_mutex_waiter *) 2)
 
 extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
 extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,