[Intel-gfx] [PATCH 2/2] drm/i915/execlists: Ensure the context is reloaded after a GPU reset

[Chris Wilson]

Quoting Mika Kuoppala (2019-09-12 12:53:01)
> Chris Wilson <chris at chris-wilson.co.uk> writes:
> 
> > After we manipulate the context to allow replay after a GPU reset, force
> > that context to be reloaded. This should be a layer of paranoia, for if
> > the GPU was reset, the context will no longer be resident!
> >
> > Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> > Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
> > ---
> >  drivers/gpu/drm/i915/gt/intel_lrc.c | 1 +
> >  1 file changed, 1 insertion(+)
> >
> > diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
> > index dbc90da2341a..47d766ccea71 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_lrc.c
> > +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
> > @@ -2445,6 +2445,7 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
> >       intel_ring_update_space(ce->ring);
> >       __execlists_reset_reg_state(ce, engine);
> >       __execlists_update_reg_state(ce, engine);
> > +     ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was
> > reset! */
> 
> The CCID should be reset also, but I see no harm to be explicit.

Yeah, I think it's developing into a healthy enough pattern. If we ever
manipulate anything inside the image itself, we should probably force
the restore. A bit more mulling over that, I like the current comment :)
-Chris