Re: [patch] Real-Time Preemption, -RT-2.6.11-rc2-V0.7.36-04

[Ingo Molnar]

* Lee Revell <rlrevell@xxxxxxxxxxx> wrote:

> OK.  Rereading my old mail, it looks like there were some possibly
> unresolved false positives with the userspace atomicity debugger.
> 
> Here's one I get from alsaplayer.  Would more information be required
> to know if this is a false positive?

this is a false positive that only triggers if PREEMPT_RT is disabled. 
Does the patch below fix it? (i've also updated the -37-03 patch that
includes it.)

	Ingo

--- linux/lib/rwsem.c.orig
+++ linux/lib/rwsem.c
@@ -169,6 +169,8 @@ rwsem_down_failed_common(struct rw_semap
 
 	/* wait to be given the lock */
 	for (;;) {
+		unsigned long nosched_flag = current->flags & PF_NOSCHED;
+	
 		if ((sleep_state == TASK_INTERRUPTIBLE) &&
 						signal_pending(current)) {
 			spin_lock(&sem->wait_lock);
@@ -181,7 +183,10 @@ rwsem_down_failed_common(struct rw_semap
 		}
 		if (!waiter->task)
 			break;
+
+		current->flags &= ~PF_NOSCHED;
 		schedule();
+		current->flags |= nosched_flag;
 		set_task_state(tsk, sleep_state);
 	}
 
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/