Re: [RFC PATCH 0/7] Early task context tracking

[Daniel Bristot de Oliveira <bristot@redhat.com>]

On 4/4/19 7:40 PM, Joel Fernandes wrote:
>> Currently, recursion control uses the preempt_counter to
>> identify the current context. The NMI/HARD/SOFT IRQ counters
>> are set in the preempt_counter in the irq_enter/exit functions.
> Just started looking.
> 
> Thinking out loud... can we not just update the preempt_count as early on
> entry and as late on exit, as possible, and fix it that way? (Haven't fully
> yet looked into what could break if we did that.)
> 
> I also feel the context tracking should be unified, right now we already have
> two methods AFAIK - preempt_count and lockdep. Now this is yet another third.
> Granted lockdep cannot be enabled in production, but still. It will be nice
> to unify these tracking methods and if there is a single point of all such
> context tracking that works well, and even better if we can just fix
> preempt_count and use that for non-debugging usecases.
> 
> Also I feel in_interrupt() etc should be updated to rely on such tracking
> methods if something other than preempt_count is used..

Hi Joel,

I agree with you that it is important to have a single method to identify the
context.

I did the RFC using a specific percpu variable to make things simpler. Also
because I tried to move set/unset of the preempt_counter and my dev VM stopped
booting. So it looked, somehow, risky to move the preempt_counter.

Still, if people believe it is better to use the preempt_counter... I am not
against...

-- Daniel


> thanks,
> 
>  - Joel
> 
>