Re: [PATCH] 2.6.17-rt1 : fix x86_64 oops

[Ingo Molnar <mingo@elte.hu>]

* Ingo Molnar <mingo@elte.hu> wrote:

> > Ingo, do you have a suspect ?
> 
> I suspect it's the patch below. That patch (from John) relaxes the 
> affinities of IRQ threads: if there are /proc/irq/*/smp_affinity 
> entries that have multiple bits set an IRQ thread is allowed to jump 
> from one CPU to another while it is executing a IRQ-handler. It 
> _should_ be fine but i'd not be surprised if that caused breakage ...

the patch below is against 2.6.17-rt5, does this solve the crashes?

	Ingo

Index: linux-rt.q/kernel/irq/manage.c
===================================================================
--- linux-rt.q.orig/kernel/irq/manage.c
+++ linux-rt.q/kernel/irq/manage.c
@@ -645,17 +645,24 @@ extern asmlinkage void __do_softirq(void
 
 static int curr_irq_prio = 49;
 
-static int do_irqd(void * __desc)
+static void follow_irq_affinity(struct irq_desc *desc)
 {
-	struct sched_param param = { 0, };
-	struct irq_desc *desc = __desc;
 #ifdef CONFIG_SMP
-	int irq = desc - irq_desc;
 	cpumask_t mask;
 
-	mask = cpumask_of_cpu(any_online_cpu(irq_desc[irq].affinity));
+	if (cpus_equal(current->cpus_allowed, desc->affinity))
+		return;
+	mask = cpumask_of_cpu(any_online_cpu(desc->affinity));
 	set_cpus_allowed(current, mask);
 #endif
+}
+
+static int do_irqd(void * __desc)
+{
+	struct sched_param param = { 0, };
+	struct irq_desc *desc = __desc;
+
+	follow_irq_affinity(desc);
 	current->flags |= PF_NOFREEZE | PF_HARDIRQ;
 
 	/*
@@ -674,13 +681,7 @@ static int do_irqd(void * __desc)
 		local_irq_disable();
 		__do_softirq();
 		local_irq_enable();
-#ifdef CONFIG_SMP
-		/*
-		 * Did IRQ affinities change?
-		 */
-		if (!cpus_equal(current->cpus_allowed, irq_desc[irq].affinity))
-			set_cpus_allowed(current, irq_desc[irq].affinity);
-#endif
+		follow_irq_affinity(desc);
 		schedule();
 	}
 	__set_current_state(TASK_RUNNING);