futex: Fix bug on when a requeued RT task times out

Requeue with timeout causes a bug with PREEMPT_RT_FULL.

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.

The fix:

When calling rt_mutex_start_proxy_lock() a check is made to see
if the proxy tasks pi_blocked_on is set. If so, exit out early.
Otherwise set it to a new flag PI_REQUEUE_INPROGRESS, which notifies
the proxy task that it is being requeued, and will handle things
appropriately.

Cc: stable-rt@vger.kernel.org
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 13b3c9270fc2b66f57f4d909663d25d10bff3785..f8dcb7baec7a63ff19aba543f030c74fbef5bff1 100644 (file)
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -69,7 +69,8 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
 
 static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter)
 {
-       return waiter && waiter != PI_WAKEUP_INPROGRESS;
+       return waiter && waiter != PI_WAKEUP_INPROGRESS &&
+               waiter != PI_REQUEUE_INPROGRESS;
 }
 
 /*
@@ -1010,6 +1011,35 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
                return 1;
        }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+       /*
+        * In PREEMPT_RT there's an added race.
+        * If the task, that we are about to requeue, times out,
+        * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue
+        * to skip this task. But right after the task sets
+        * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then
+        * block on the spin_lock(&hb->lock), which in RT is an rtmutex.
+        * This will replace the PI_WAKEUP_INPROGRESS with the actual
+        * lock that it blocks on. We *must not* place this task
+        * on this proxy lock in that case.
+        *
+        * To prevent this race, we first take the task's pi_lock
+        * and check if it has updated its pi_blocked_on. If it has,
+        * we assume that it woke up and we return -EAGAIN.
+        * Otherwise, we set the task's pi_blocked_on to
+        * PI_REQUEUE_INPROGRESS, so that if the task is waking up
+        * it will know that we are in the process of requeuing it.
+        */
+       raw_spin_lock(&task->pi_lock);
+       if (task->pi_blocked_on) {
+               raw_spin_unlock(&task->pi_lock);
+               raw_spin_unlock(&lock->wait_lock);
+               return -EAGAIN;
+       }
+       task->pi_blocked_on = PI_REQUEUE_INPROGRESS;
+       raw_spin_unlock(&task->pi_lock);
+#endif
+
        ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
 
        if (ret && !rt_mutex_owner(lock)) {

diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h
index b43d832f4f6f503894d788b392bcc4b209933ca7..47290eca692ae465ffd193bdc4393d799510be39 100644 (file)
--- a/kernel/rtmutex_common.h
+++ b/kernel/rtmutex_common.h
@@ -104,6 +104,7 @@ 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,