intel-gfx.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: Dave Gordon <david.s.gordon@intel.com>
To: sourab.gupta@intel.com, "Dai, Yu" <yu.dai@intel.com>,
	"O'Rourke, Tom" <Tom.O'Rourke@intel.com>
Cc: Intel Graphics Development <intel-gfx@lists.freedesktop.org>,
	jabin.wu@intel.com
Subject: Re: [PATCH 03/11] drm/i915: return ctx->global_id from intel_execlists_ctx_id()
Date: Tue, 16 Feb 2016 09:34:29 +0000	[thread overview]
Message-ID: <56C2ED25.8080600@intel.com> (raw)
In-Reply-To: <1455600439-18480-4-git-send-email-sourab.gupta@intel.com>

On 16/02/16 05:27, sourab.gupta@intel.com wrote:
> From: Robert Bragg <robert@sixbynine.org>
>
> The newly added intel_context::global_id is suitable (a globally unique
> 20 bit ID) for giving to the hardware as a unique context identifier.
>
> Compared to using the pinned address of a logical ring context these IDs
> are constant for the lifetime of a context whereas a context could be
> repinned at different addresses during its lifetime.
>
> Having a stable ID is useful when we need to buffer information
> associated with a context based on this ID so the association can't be
> lost. For example the OA unit writes out counter reports to a circular
> buffer tagged with this ID and we want to be able to accurately filter
> reports for a specific context, ideally without the added complexity of
> tracking context re-pinning while the OA buffer may contain reports with
> older IDs.

Unfortunately, I suspect that the GuC firmware has conflated the context 
ID (which ought to be a purely software-defined tag) with the (hardware) 
GTT page address of the LRC. So this will probably break GuC submission.

But it looks like a good idea otherwise; maybe we can get the GuC 
firmware updated so it doesn't make this assumption ...

.Dave.

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  reply	other threads:[~2016-02-16  9:34 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-02-16  5:27 [PATCH 00/11] Framework to collect gpu metrics using i915 perf infrastructure sourab.gupta
2016-02-16  5:27 ` [PATCH 01/11] drm/i915: Introduce global id for contexts sourab.gupta
2016-02-16  5:27 ` [PATCH 02/11] drm/i915: Constrain intel_context::global_id to 20 bits sourab.gupta
2016-02-16  5:27 ` [PATCH 03/11] drm/i915: return ctx->global_id from intel_execlists_ctx_id() sourab.gupta
2016-02-16  9:34   ` Dave Gordon [this message]
2016-02-16  5:27 ` [PATCH 04/11] drm/i915: Add ctx getparam ioctl parameter to retrieve ctx global id sourab.gupta
2016-02-16  5:27 ` [PATCH 05/11] drm/i915: Expose OA sample source to userspace sourab.gupta
2016-02-16  5:27 ` [PATCH 06/11] drm/i915: Framework for capturing command stream based OA reports sourab.gupta
2016-02-17 17:30   ` Robert Bragg
2016-02-19  6:51     ` sourab gupta
2016-02-16  5:27 ` [PATCH 07/11] drm/i915: Add support for having pid output with OA report sourab.gupta
2016-02-16  5:27 ` [PATCH 08/11] drm/i915: Add support to add execbuffer tags to OA counter reports sourab.gupta
2016-02-16  5:27 ` [PATCH 09/11] drm/i915: Extend i915 perf framework for collecting timestamps on all gpu engines sourab.gupta
2016-02-16  5:27 ` [PATCH 10/11] drm/i915: Support opening multiple concurrent perf streams sourab.gupta
2016-02-16  5:27 ` [PATCH 11/11] drm/i915: Support for capturing MMIO register values sourab.gupta

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=56C2ED25.8080600@intel.com \
    --to=david.s.gordon@intel.com \
    --cc=Tom.O'Rourke@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=jabin.wu@intel.com \
    --cc=sourab.gupta@intel.com \
    --cc=yu.dai@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;
as well as URLs for NNTP newsgroup(s).