Re: [PATCH 0/8] tracing vs rcu vs nmi

[Peter Zijlstra]

On Wed, Feb 12, 2020 at 10:32:10AM +0100, Peter Zijlstra wrote:
> Hi all,
> 
> These here patches are the result of Mathieu and Steve trying to get commit
> 865e63b04e9b2 ("tracing: Add back in rcu_irq_enter/exit_irqson() for rcuidle
> tracepoints") reverted again.
> 
> One of the things discovered is that tracing MUST NOT happen before nmi_enter()
> or after nmi_exit(). I've only fixed x86, but quickly gone through other
> architectures and there is definitely more stuff to be fixed (simply grep for
> nmi_enter in your arch).

For Power:

 - system_reset_exception()
 - machine_check_exception()
 - soft_nmi_interrupt()
 - __perf_event_interrupt() (book3s)
 - perf_event_interrupt() (fsl)

will want looking at.