Messages in this thread | | | Date | Fri, 03 May 2013 11:31:39 +0200 | From | Sebastian Andrzej Siewior <> | Subject | Re: [PATCH RT v2] x86/mce: Defer mce wakeups to threads for PREEMPT_RT |
| |
On 05/02/2013 04:33 PM, Steven Rostedt wrote: >> mce_notify_irq() can use simple_waitqueue, no? > > Yeah, and I went down that path. > > But it also schedules work, which has the issue.
Hmm, okay.
>> The other issue is that mce_report_event() is scheduling a per-cpu >> workqueue (mce_schedule_work) in case of a memory fault. This has the >> same issue. > > Yeah, that looks like it can be an issue too. I wonder if we can use the > same thread and use flags check what to do. Atomically set the flag for > the function to perform, and then have the thread clear it before doing > the function and only go to sleep when all flags are cleared.
This should work. It uses per-cpu workthreads, not sure why. Maybe to avoid locking issues when invoked from NMI.
> > -- Steve
Sebastian
| |