From: Matt Atwood <matthew.s.atwood@intel.com>
To: Matt Roper <matthew.d.roper@intel.com>,
<lucas.demarchi@intel.com>, <intel-xe@lists.freedesktop.org>
Cc: lucas.demarchi@intel.com, intel-xe@lists.freedesktop.org
Subject: Re: [Intel-xe] [PATCH 1/2 v3] drm/xe: Add infrastructure for per engine tuning
Date: Wed, 6 Sep 2023 14:40:57 -0700 [thread overview]
Message-ID: <ZPjx6XGFVTvY3RTr@msatwood-mobl> (raw)
In-Reply-To: <20230824200538.GZ1529860@mdroper-desk1.amr.corp.intel.com>
On Thu, Aug 24, 2023 at 01:05:38PM -0700, Matt Roper wrote:
> On Wed, Aug 23, 2023 at 12:55:32PM -0700, Matt Atwood wrote:
> > Add the infrastructure that allows for per engine tuning preparation for
> > disable indirect state.
>
> I don't think we need this patch; there's nothing terribly complicated
> here so we might as well just squash it directly into the next patch
> that starts adding some entries.
originally was, however lucas asked for it to be split out.
>
> >
> > v3: rebase
> >
> > Signed-off-by: Matt Atwood <matthew.s.atwood@intel.com>
> > ---
> > drivers/gpu/drm/xe/xe_hw_engine.c | 2 ++
> > drivers/gpu/drm/xe/xe_tuning.c | 12 ++++++++++++
> > drivers/gpu/drm/xe/xe_tuning.h | 1 +
> > 3 files changed, 15 insertions(+)
> >
> > diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c
> > index dd673a684b70..9dafc56d5fe8 100644
> > --- a/drivers/gpu/drm/xe/xe_hw_engine.c
> > +++ b/drivers/gpu/drm/xe/xe_hw_engine.c
> > @@ -24,6 +24,7 @@
> > #include "xe_reg_sr.h"
> > #include "xe_rtp.h"
> > #include "xe_sched_job.h"
> > +#include "xe_tuning.h"
> > #include "xe_wa.h"
> >
> > #define MAX_MMIO_BASES 3
> > @@ -401,6 +402,7 @@ static void hw_engine_init_early(struct xe_gt *gt, struct xe_hw_engine *hwe,
> > }
> >
> > xe_reg_sr_init(&hwe->reg_sr, hwe->name, gt_to_xe(gt));
> > + xe_tuning_process_engine(gt);
> > xe_wa_process_engine(hwe);
> > hw_engine_setup_default_state(hwe);
> >
> > diff --git a/drivers/gpu/drm/xe/xe_tuning.c b/drivers/gpu/drm/xe/xe_tuning.c
> > index 412e59de9842..702cb41dab53 100644
> > --- a/drivers/gpu/drm/xe/xe_tuning.c
> > +++ b/drivers/gpu/drm/xe/xe_tuning.c
> > @@ -27,6 +27,10 @@ static const struct xe_rtp_entry_sr gt_tunings[] = {
> > {}
> > };
> >
> > +static const struct xe_rtp_entry_sr engine_tunings[] = {
> > + {}
> > +};
> > +
> > static const struct xe_rtp_entry_sr lrc_tunings[] = {
> > { XE_RTP_NAME("Tuning: ganged timer, also known as 16011163337"),
> > XE_RTP_RULES(GRAPHICS_VERSION_RANGE(1200, 1210)),
> > @@ -65,6 +69,14 @@ void xe_tuning_process_gt(struct xe_gt *gt)
> > }
> > EXPORT_SYMBOL_IF_KUNIT(xe_tuning_process_gt);
> >
> > +void xe_tuning_process_engine(struct xe_gt *gt)
> > +{
> > + struct xe_rtp_process_ctx ctx = XE_RTP_PROCESS_CTX_INITIALIZER(gt);
> > +
> > + xe_rtp_process_to_sr(&ctx, engine_tunings, >->reg_sr);
> > +}
>
> It looks like you may have copied the GT function but forgot to update
> it for engine usage?
yes, seem to have copy pasted the wrong block, ack.
>
>
> Matt
>
> > +EXPORT_SYMBOL_IF_KUNIT(xe_tuning_process_engine);
> > +
> > /**
> > * xe_tuning_process_lrc - process lrc tunings
> > * @hwe: engine instance to process tunings for
> > diff --git a/drivers/gpu/drm/xe/xe_tuning.h b/drivers/gpu/drm/xe/xe_tuning.h
> > index 2b95b0c8effc..740cb1bd2f0a 100644
> > --- a/drivers/gpu/drm/xe/xe_tuning.h
> > +++ b/drivers/gpu/drm/xe/xe_tuning.h
> > @@ -10,6 +10,7 @@ struct xe_gt;
> > struct xe_hw_engine;
> >
> > void xe_tuning_process_gt(struct xe_gt *gt);
> > +void xe_tuning_process_engine(struct xe_gt *gt);
> > void xe_tuning_process_lrc(struct xe_hw_engine *hwe);
> >
> > #endif
> > --
> > 2.40.1
> >
>
> --
> Matt Roper
> Graphics Software Engineer
> Linux GPU Platform Enablement
> Intel Corporation
prev parent reply other threads:[~2023-09-06 21:41 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-23 19:55 [Intel-xe] [PATCH 1/2 v3] drm/xe: Add infrastructure for per engine tuning Matt Atwood
2023-08-23 19:55 ` [Intel-xe] [PATCH 2/2 v3] drm/xe: add gt tuning for indirect state Matt Atwood
2023-08-24 20:35 ` Matt Roper
2023-09-06 21:39 ` Matt Atwood
2023-08-23 19:58 ` [Intel-xe] ✓ CI.Patch_applied: success for series starting with [1/2,v3] drm/xe: Add infrastructure for per engine tuning Patchwork
2023-08-23 19:58 ` [Intel-xe] ✗ CI.checkpatch: warning " Patchwork
2023-08-23 19:59 ` [Intel-xe] ✓ CI.KUnit: success " Patchwork
2023-08-23 20:03 ` [Intel-xe] ✓ CI.Build: " Patchwork
2023-08-23 20:04 ` [Intel-xe] ✓ CI.Hooks: " Patchwork
2023-08-23 20:04 ` [Intel-xe] ✗ CI.checksparse: warning " Patchwork
2023-08-23 20:31 ` [Intel-xe] ✗ CI.BAT: failure " Patchwork
2023-08-24 20:05 ` [Intel-xe] [PATCH 1/2 v3] " Matt Roper
2023-09-06 21:40 ` Matt Atwood [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=ZPjx6XGFVTvY3RTr@msatwood-mobl \
--to=matthew.s.atwood@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=lucas.demarchi@intel.com \
--cc=matthew.d.roper@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox