[PATCH] kthread_bind new worker threads when onlining cpu

[Nathan Lynch <ntl@pobox.com>]

Hi Andrew-

On Tue, Feb 15, 2005 at 08:02:17AM +0100, Ingo Molnar wrote:
> 
> * Nathan Lynch <ntl@pobox.com> wrote:
> 
> > 
> > It looks as if we need to explicitly bind worker threads to a newly
> > onlined cpu.  This gets rid of the smp_processor_id warnings from
> > cache_reap.  Adding a little more instrumentation to the debug
> > smp_processor_id showed that new worker threads were actually running
> > on the wrong cpu...
> > 
> > Does this look ok?
> 
> indeed - looks much better than the 'turn off the warning' solution.
> 
> Acked-by: Ingo Molnar <mingo@elte.hu>

We weren't binding new worker threads to their cpu when onlining.
Using preempt and the debug version of smp_processor_id found this.

Signed-off-by: Nathan Lynch <ntl@pobox.com>

Index: linux-2.6.11-rc4-bk2/kernel/workqueue.c
===================================================================
--- linux-2.6.11-rc4-bk2.orig/kernel/workqueue.c	2005-02-14 11:13:08.000000000 -0600
+++ linux-2.6.11-rc4-bk2/kernel/workqueue.c	2005-02-14 15:18:35.000000000 -0600
@@ -485,8 +485,10 @@
 
 	case CPU_ONLINE:
 		/* Kick off worker threads. */
-		list_for_each_entry(wq, &workqueues, list)
+		list_for_each_entry(wq, &workqueues, list) {
+			kthread_bind(wq->cpu_wq[hotcpu].thread, hotcpu);
 			wake_up_process(wq->cpu_wq[hotcpu].thread);
+		}
 		break;
 
 	case CPU_UP_CANCELED: