Re: WARNING: at arch/x86/kernel/smp.c:119 native_smp_send_reschedule+0x25/0x43()

[Don Zickus <dzickus@redhat.com>]

On Fri, Feb 10, 2012 at 09:18:41PM +0100, Peter Zijlstra wrote:
> On Fri, 2012-02-10 at 15:02 -0500, Don Zickus wrote:
> > I also ran into the same problem you did and hacked up another patch that
> > checked a global atomic variable that let the system know we were shutting
> > down and not to do the WARN_ON (the global is already created for the NMI
> > case now). 
> 
> system_state seems like that thing.. 

except it doesn't seem to have a PANIC state, though we could add one I
suppose.

The thing is even if you reverted my changes:

e58d429 x86, reboot: Fix typo in nmi reboot path
bda6263 x86, NMI: Add knob to disable using NMI IPIs to stop cpus
3603a25 x86, reboot: Use NMI instead of REBOOT_VECTOR to stop cpus

I think you still run into the same problem because the reschedule code
changed.

So my second patch which I will eventually post will just skip the WARN_ON
if the system is going down.  Not sure if that is the proper way to address
this problem or change all of the stop_this_cpu code to use a different
bitmask than the cpu_online bitmask (but then you run the risk of a stuck
IPI I guess if the cpu is halted without notifying anyone).

Cheers,
Don