[PATCH v5 1/2] xe/oa: Fix query mode of operation for OAR/OAC

[Cavitt, Jonathan]

-----Original Message-----
From: Dixit, Ashutosh <ashutosh.dixit at intel.com> 
Sent: Friday, December 20, 2024 10:25 AM
To: Cavitt, Jonathan <jonathan.cavitt at intel.com>
Cc: Nerlige Ramappa, Umesh <umesh.nerlige.ramappa at intel.com>; intel-xe at lists.freedesktop.org; Souza, Jose <jose.souza at intel.com>
Subject: Re: [PATCH v5 1/2] xe/oa: Fix query mode of operation for OAR/OAC
> 
> On Fri, 20 Dec 2024 10:08:41 -0800, Cavitt, Jonathan wrote:
> >
> > > diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
> > > index 3a75a08b6be9..c8ab37fa0d19 100644
> > > --- a/drivers/gpu/drm/xe/xe_ring_ops.c
> > > +++ b/drivers/gpu/drm/xe/xe_ring_ops.c
> > > @@ -223,7 +223,10 @@ static int emit_pipe_imm_ggtt(u32 addr, u32 value, bool stall_only, u32 *dw,
> > >
> > >  static u32 get_ppgtt_flag(struct xe_sched_job *job)
> > >  {
> > > -	return job->q->vm ? BIT(8) : 0;
> > > +	if (job->q->vm && !job->ggtt)
> > > +		return BIT(8);
> >
> > Non-blocking question:
> > I'm assuming that xe_oa_submit_bb isn't the only function that can submit
> > jobs for get_ppgtt_flag to decode, because otherwise job->ggtt would always
> > return true?
> 
> Look at callers of xe_sched_job_push.

Okay, I see where emit_job (which calls one of __emit_job_gen12_[render_compute|video|copy|gsc]
internally, thus also calling get_ppgtt_flag) is being called in xe_exec_ioctl on a job where ggtt == false.
-Jonathan Cavitt

>