[Intel-gfx] [PATCH] drm/i915: Take reference for signaling the request from hardirq

[Chris Wilson]

On Fri, Mar 03, 2017 at 05:00:50PM +0200, Mika Kuoppala wrote:
> Mika Kuoppala <mika.kuoppala at linux.intel.com> writes:
> 
> > Chris Wilson <chris at chris-wilson.co.uk> writes:
> >
> >> Being inside a spinlock signaling that the hardware just completed a
> >> request doesn't prevent a second thread already spotting that the
> >> request is complete, freeing it and reallocating it! The code currently
> >> tries to prevent this using RCU -- but that only prevents the request
> >> from being freed, it doesn't prevent us from reallocating it - that
> >> requires us to take a reference.
> >
> > How can it be reallocated if it was never freed in the first place?
> 
> Oh request backing storage from being freed?

Yes. "prevents the request slab from being freed, it doesn't prevent us
from reallocating an individual request".
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre