Re: 2.6.29 boot hang

From: Rusty Russell
Date: Wed Apr 01 2009 - 02:34:20 EST


On Wednesday 01 April 2009 15:21:32 Randy Dunlap wrote:
> Rusty Russell wrote:
> > On Wednesday 01 April 2009 07:15:35 Randy Dunlap wrote:
> >> On a 4-proc x86_64 (HP BladeCenter, AMD CPUs) system, booting 2.6.29
> >> (or earlier, back to 2.6.28-6921-g873392c) hangs during boot.
> >>
> >> git bisect says:
> >> 873392ca514f87eae39f53b6944caf85b1a047cb is first bad commit
> >> commit 873392ca514f87eae39f53b6944caf85b1a047cb
> >> Author: Rusty Russell <rusty@xxxxxxxxxxxxxxx>
> >> Date: Wed Dec 31 23:54:56 2008 +1030
> >>
> >> PCI: work_on_cpu: use in drivers/pci/pci-driver.c
> >
> > ...
> >
> >> If I change CONFIG_MICROCODE_AMD=y to CONFIG_MICROCODE_AMD=n & rebuild,
> >> the kernel boots successfully.
> >
> > How very very odd. My first thought was a deadlock with keventd used
> > by work_on_cpu (changed in latest Linus tree), but the microcode code at
> > that version doesn't use work_on_cpu.
>
> Yep, I thought it a bit odd also.
>
> > So I don't think that's it, but this patch should canonically eliminate it:
> >
> > Subject: work_on_cpu(): rewrite it to create a kernel thread on demand
> > From: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
>
> This patch doesn't apply to 2.6.29-final, but it does apply to 2.6.29-git8,

Err, it has 14 line offset. But here's an adjusted one.

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 1f0c509..08bd795 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -971,20 +971,20 @@ undo:
}

#ifdef CONFIG_SMP
-static struct workqueue_struct *work_on_cpu_wq __read_mostly;

struct work_for_cpu {
- struct work_struct work;
+ struct completion completion;
long (*fn)(void *);
void *arg;
long ret;
};

-static void do_work_for_cpu(struct work_struct *w)
+static int do_work_for_cpu(void *_wfc)
{
- struct work_for_cpu *wfc = container_of(w, struct work_for_cpu, work);
-
+ struct work_for_cpu *wfc = _wfc;
wfc->ret = wfc->fn(wfc->arg);
+ complete(&wfc->completion);
+ return 0;
}

/**
@@ -995,17 +995,23 @@ static void do_work_for_cpu(struct work_struct *w)
*
* This will return the value @fn returns.
* It is up to the caller to ensure that the cpu doesn't go offline.
+ * The caller must not hold any locks which would prevent @fn from completing.
*/
long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
{
- struct work_for_cpu wfc;
-
- INIT_WORK(&wfc.work, do_work_for_cpu);
- wfc.fn = fn;
- wfc.arg = arg;
- queue_work_on(cpu, work_on_cpu_wq, &wfc.work);
- flush_work(&wfc.work);
-
+ struct task_struct *sub_thread;
+ struct work_for_cpu wfc = {
+ .completion = COMPLETION_INITIALIZER_ONSTACK(wfc.completion),
+ .fn = fn,
+ .arg = arg,
+ };
+
+ sub_thread = kthread_create(do_work_for_cpu, &wfc, "work_for_cpu");
+ if (IS_ERR(sub_thread))
+ return PTR_ERR(sub_thread);
+ kthread_bind(sub_thread, cpu);
+ wake_up_process(sub_thread);
+ wait_for_completion(&wfc.completion);
return wfc.ret;
}
EXPORT_SYMBOL_GPL(work_on_cpu);
@@ -1021,8 +1027,4 @@ void __init init_workqueues(void)
hotcpu_notifier(workqueue_cpu_callback, 0);
keventd_wq = create_workqueue("events");
BUG_ON(!keventd_wq);
-#ifdef CONFIG_SMP
- work_on_cpu_wq = create_workqueue("work_on_cpu");
- BUG_ON(!work_on_cpu_wq);
-#endif
}
--
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/