On ke, 2016-06-08 at 08:04 +0100, Chris Wilson wrote:
> On Tue, Jun 07, 2016 at 11:18:46AM -0400, Zhi Wang wrote:
> >
> > This patch introduces the support of LRC context single submission.
> > As GVT context may come from different guests, which require different
> > configuration of render registers. It can't be combined into a dual ELSP
> > submission combo.
> >
> > Only GVT-g will create this kinds of GEM context currently.
> >
> > v7:
> >
> > - Fix typos in commit message. (Joonas)
> >
> > v6:
> > - Make GVT code as dead code when !CONFIG_DRM_I915_GVT. (Chris)
> >
> > v5:
> >
> > - Only compile this feature when CONFIG_DRM_I915_GVT=y. (Tvrtko)
> >
> > Signed-off-by: Zhi Wang <zhi.a.w...@intel.com>
> > ---
> > drivers/gpu/drm/i915/i915_drv.h | 1 +
> > drivers/gpu/drm/i915/intel_lrc.c | 15 +++++++++++++++
> > 2 files changed, 16 insertions(+)
> >
> > diff --git a/drivers/gpu/drm/i915/i915_drv.h
> > b/drivers/gpu/drm/i915/i915_drv.h
> > index 4ab4cf7..8f8a5bc 100644
> > --- a/drivers/gpu/drm/i915/i915_drv.h
> > +++ b/drivers/gpu/drm/i915/i915_drv.h
> > @@ -882,6 +882,7 @@ struct i915_gem_context {
> > u32 lrc_addressing_mode_bits;
> > struct atomic_notifier_head status_notifier;
> > bool enable_lrc_status_change_notification;
> > + bool enable_lrc_single_submission;
> >
> > struct list_head link;
> >
> > diff --git a/drivers/gpu/drm/i915/intel_lrc.c
> > b/drivers/gpu/drm/i915/intel_lrc.c
> > index 956585d..e3cab06 100644
> > --- a/drivers/gpu/drm/i915/intel_lrc.c
> > +++ b/drivers/gpu/drm/i915/intel_lrc.c
> > @@ -447,6 +447,21 @@ static void execlists_context_unqueue(struct
> > intel_engine_cs *engine)
> > i915_gem_request_unreference(req0);
> > req0 = cursor;
> > } else {
> > + /* Compiler will do the dead-code elimination */
> > + if (IS_ENABLED(CONFIG_DRM_I915_GVT)) {
> > + /*
> > + * req0 (after merged) ctx requires single
> > + * submission, stop picking
> > + */
> > + if (req0->ctx->enable_lrc_single_submission)
> enable_ is a bad verb here, force_ would be more apt.
>
> s/lrc/execlists/
>
> ctx->execlists_force_single_submission
> -Chris
Also CCing Kevin here, who commented on the previous patch. I still
think it would be good to do the req0->{vgpu,vmid} != cursor-
>{vgpu,vmid} test. That way, we get better results if there's one
dominating VM submitting workloads, right?
Regards, Joonas
>
--
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
