Re: 2.6.17-rc6-rt3

[Thomas Gleixner <tglx@linutronix.de>]

On Sun, 2006-06-11 at 14:38 +0200, Mike Galbraith wrote:

> OK, it's dying on the very first call, with absolutely nothing between
> spin_lock_irq() and BUG_ON(!irqs_disabled()), but the spin_lock_irq()
> has become rt_lock().  Is the BUG_ON() check bogus for the rt kernel?

Yes. The patch below should help.

	tglx

Index: linux-2.6.17-rc6/kernel/posix-cpu-timers.c
===================================================================
--- linux-2.6.17-rc6.orig/kernel/posix-cpu-timers.c	2006-06-10 09:45:45.000000000 +0200
+++ linux-2.6.17-rc6/kernel/posix-cpu-timers.c	2006-06-10 14:47:10.000000000 +0200
@@ -564,7 +564,7 @@
 		p->cpu_timers : p->signal->cpu_timers);
 	head += CPUCLOCK_WHICH(timer->it_clock);
 
-	BUG_ON(!irqs_disabled());
+	BUG_ON_NONRT(!irqs_disabled());
 	spin_lock(&p->sighand->siglock);
 
 	listpos = head;
@@ -721,7 +721,7 @@
 	/*
 	 * Disarm any old timer after extracting its expiry time.
 	 */
-	BUG_ON(!irqs_disabled());
+	BUG_ON_NONRT(!irqs_disabled());
 
 	ret = 0;
 	spin_lock(&p->sighand->siglock);