kdump: crash_kexec()-smp_send_stop() race in panic

[Michael Holzheu]

Hello Seiji,

On Mon, 2011-10-24 at 18:24 -0400, Seiji Aguchi wrote:
> Hi,
> 
> >> >>> 1st CPU:
> >> >>> panic()->crash_kexec()->mutex_trylock(&kexec_mutex)-> do kdump
> >> >>>
> >> >>> 2nd CPU:
> >> >>> panic()->crash_kexec()->kexec_mutex already held by 1st CPU
> >> >>>        ->smp_send_stop()-> stop CPU 1 (stop kdump)
> >> >>>
> >> >>> How should we fix this problem? One possibility could be to do
> >> >>> smp_send_stop() before we call crash_kexec().
> 
> http://lkml.org/lkml/2010/9/16/353
> 
> I developed a patch solving this issue one year ago.
> (Just adding local_irq_disable in kexec path.)

This won't work (at least on s390) because smp_send_stop() will also
stop CPUs that have interrupts disabled.

Michael