I'll follow that approach.

On Fri, Mar 10, 2023, at 12:02 PM, Steven Rostedt wrote:
> On Fri, 10 Mar 2023 11:22:54 -0800
> Stefan Roesch <shr@devkernel.io> wrote:
> 
> > >> + trace_ksm_remove_rmap_item(stable_node->kpfn, rmap_item, rmap_item->mm);  
> > >
> > > Instead of dereferencing the stable_node here, where the work could
> > > possibly happen outside the trace event and in the hot path, could you pass
> > > in the stable_node instead, and then in the TP_fast_assign() do:
> > >
> > > __entry->pfn = stable_node->kpfn;
> > >
> > >  
> > 
> > To do this, the structure would need to be exposed. Currently the
> > structure is defined in ksm.c. This is an internal structure that we
> > most likely don't want to expose. We can get by not printing the pfn
> > and use the rmap_item to refer back to it, but exposing it directly
> > here is more convenient for debugging.
> > 
> > Any thoughts?
> 
> Sounds like the include/trace/events/ksm.h should be local too.
> 
> See my reply about include/trace/events/thermal.h
> 
>   https://lore.kernel.org/all/20230227100715.7d896836@gandalf.local.home/
> 
> And their solution.
> 
>   https://lore.kernel.org/all/20230307133735.90772-2-daniel.lezcano@linaro.org/
> 
> I suggest you do the same.
> 
> -- Steve
>