Re: [RFC RESEND v10 03/14] irq & spin_lock: Add counted interrupt disabling/enabling

[Steven Rostedt]

On Mon, 16 Jun 2025 14:37:49 -0400
Joel Fernandes <joelagnelf@xxxxxxxxxx> wrote:

> At first glance that makes sense. Was there some concern about overhead? Me and
> Steve did some experiments back in the day where we found local_irq_disable()
> can be performance-sensitive, but we were adding tracers/tracing which
> presumably can be higher overhead than what this series is doing.
> 

The performance overhead was because, I believe, we added a function call
to the local_irq_disable, which can add quite a bit of overhead.

> thanks,
> 
>  - Hiek

I like the new sig! (Right hand off by one?) You should keep it ;-)

-- Steve