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

[Michael Holzheu]

On Tue, 2011-10-25 at 11:08 -0400, Vivek Goyal wrote:
> On Tue, Oct 25, 2011 at 04:58:19PM +0200, Michael Holzheu wrote:
> > On Tue, 2011-10-25 at 05:04 -0700, Eric W. Biederman wrote:
> > > Michael Holzheu <holzheu at linux.vnet.ibm.com> writes:
[snip]
> > 
> > Is the following patch ok for you?
> > ---
> >  kernel/panic.c |    8 ++++++++
> >  1 file changed, 8 insertions(+)
> > 
> > --- a/kernel/panic.c
> > +++ b/kernel/panic.c
> > @@ -59,6 +59,7 @@ EXPORT_SYMBOL(panic_blink);
> >   */
> >  NORET_TYPE void panic(const char * fmt, ...)
> >  {
> > +	static DEFINE_SPINLOCK(panic_lock);
> >  	static char buf[1024];
> >  	va_list args;
> >  	long i, i_next = 0;
> > @@ -82,6 +83,13 @@ NORET_TYPE void panic(const char * fmt,
> >  #endif
> >  
> >  	/*
> > +	 * Only one CPU is allowed to execute the panic code from here. For
> > +	 * multiple parallel invocations of panic all other CPUs will wait on
> > +	 * the panic_lock. They are stopped afterwards by smp_send_stop().
> > +	 */
> > +	spin_lock(&panic_lock);
> 
> Why leave irqs enabled?
>
> Atleast for x86, Don Zickus had a patch to use NMI in smp_send_stop(). So
> that should work even if interrupts are disabled. (I think that patch is
> not merged yet).
> 
> So are other architectures a concern? If yes, then may be in future we
> can make it an arch call which can also choose to disable interrupts.

For s390 we could disable the interrupts here. smp_send_stop() works
also when IRQs are disabled. But as you said - who knows if that is true
on all architectures...

Michael