Re: [PATCH v5 9/9] x86/nmi: Include NMI-source information in tracepoint and debug prints

[Sohil Mehta <sohil.mehta@intel.com>]

On 5/7/2025 2:48 PM, Steven Rostedt wrote:
> On Tue,  6 May 2025 18:21:45 -0700
> Sohil Mehta <sohil.mehta@intel.com> wrote:
> 
>> diff --git a/include/trace/events/nmi.h b/include/trace/events/nmi.h
>> index 18e0411398ba..6e4a1ff70a44 100644
>> --- a/include/trace/events/nmi.h
>> +++ b/include/trace/events/nmi.h
>> @@ -10,29 +10,32 @@
>>  
>>  TRACE_EVENT(nmi_handler,
>>  
>> -	TP_PROTO(void *handler, s64 delta_ns, int handled),
>> +	TP_PROTO(void *handler, s64 delta_ns, int handled, unsigned long source_bitmap),
> 
> Even though x86 is currently the only architecture using the nmi
> tracepoint, this "source_bitmap" makes it become very x86 specific.
> 

Sure. Will move it into x86.

> This file should be moved into arch/x86/include/asm/trace/
> 
> And that would require adding to the Makefile:
> 
> CFLAGS_nmi.o := -I $(src)/../include/asm/trace
> 

Thank you for the detailed instructions. It makes it a lot easier.


> diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
> index 183e3e717326..b9ece0b63ca7 100644
> --- a/arch/x86/kernel/nmi.c
> +++ b/arch/x86/kernel/nmi.c
> @@ -202,7 +202,7 @@ static int nmi_handle(unsigned int type, struct pt_regs *regs)
>  		thishandled = a->handler(type, regs);
>  		handled += thishandled;
>  		delta = sched_clock() - delta;
> -		trace_nmi_handler(a->handler, (int)delta, thishandled);
> +		trace_nmi_handler(a->handler, (int)delta, thishandled, source_bitmap);
>  
>  		nmi_check_duration(a, delta);
>  	}

Also, I just realized that the source_bitmap information might be
incorrect for !NMI_LOCAL. With the new changes suggested by PeterZ in
patch 5, the source_bitmap would be significantly different from the
original one received from fred_event_data().

I need to figure out a solution to print it accurately in all situations.

Sohil