Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "Dixit, Ashutosh" <ashutosh.dixit@intel.com>
To: Raag Jadav <raag.jadav@intel.com>
Cc: lucas.demarchi@intel.com, John.C.Harrison@Intel.com,
	rodrigo.vivi@intel.com, matthew.d.roper@intel.com,
	andi.shyti@linux.intel.com, intel-xe@lists.freedesktop.org,
	 anshuman.gupta@intel.com, badal.nilawar@intel.com,
	riana.tauro@intel.com
Subject: Re: [PATCH v1] drm/xe: Rework throttle ABI
Date: Fri, 25 Oct 2024 12:58:45 -0700	[thread overview]
Message-ID: <857c9wt0ne.wl-ashutosh.dixit@intel.com> (raw)
In-Reply-To: <20241025092238.167042-1-raag.jadav@intel.com>

On Fri, 25 Oct 2024 02:22:38 -0700, Raag Jadav wrote:
>
> Current implementation adds multiple sysfs entries for getting GT
> throttle status and its reasons, which forces the user to read multiple
> entries for evaluating the result. Since output of each entry is based
> on the same underlying hardware register and considering the access type
> of this register is RO/v, the value of this register can change at any
> given point, even between subsequent sysfs reads. This makes current
> implementation fundamentally flawed which can produce inconsistent results.
>
> Rework throttle ABI and introduce throttle_status attribute which will
> provide throttle status through a oneshot register read, making it
> relatively less error prone. The new ABI will provide throttle reasons
> in a string based list based on the respective bits which are set in the
> hardware. Empty output means no bits are set and hence no throttling.
>
> $ cat /sys/devices/.../tile0/gt0/freq0/throttle_status
> prochot
> thermal
> ratl
> thermalert
> tdc
> pl4
> pl1
> pl2

Agree this seems to be a much better way of doing this, so I'd be open to
changing the ABI while we can :-) Not sure if there are any IGT's which use
the current ABI though. Are there any real applications using the old ABI?

Note that the top 16 bits are "latched" values of the conditions in the
lower 16 bits, so maybe we can add those too in throttle_status?

Ashutosh

  parent reply	other threads:[~2024-10-25 19:58 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-25  9:22 [PATCH v1] drm/xe: Rework throttle ABI Raag Jadav
2024-10-25 10:30 ` ✓ CI.Patch_applied: success for " Patchwork
2024-10-25 10:30 ` ✗ CI.checkpatch: warning " Patchwork
2024-10-25 10:31 ` ✓ CI.KUnit: success " Patchwork
2024-10-25 10:43 ` ✓ CI.Build: " Patchwork
2024-10-25 10:45 ` ✓ CI.Hooks: " Patchwork
2024-10-25 10:46 ` ✓ CI.checksparse: " Patchwork
2024-10-25 11:24 ` ✓ CI.BAT: " Patchwork
2024-10-25 17:03 ` [PATCH v1] " Matt Roper
2024-10-25 19:04   ` Raag Jadav
2024-10-25 20:45     ` Matt Roper
2024-10-25 23:07       ` Lucas De Marchi
2024-10-25 23:31         ` Matt Roper
2024-10-26 11:58         ` Raag Jadav
2024-10-28 20:48         ` Rodrigo Vivi
2024-10-25 19:58 ` Dixit, Ashutosh [this message]
2024-10-26 23:09 ` ✗ CI.FULL: failure for " Patchwork
2024-10-29 11:28 ` Patchwork

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=857c9wt0ne.wl-ashutosh.dixit@intel.com \
    --to=ashutosh.dixit@intel.com \
    --cc=John.C.Harrison@Intel.com \
    --cc=andi.shyti@linux.intel.com \
    --cc=anshuman.gupta@intel.com \
    --cc=badal.nilawar@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=lucas.demarchi@intel.com \
    --cc=matthew.d.roper@intel.com \
    --cc=raag.jadav@intel.com \
    --cc=riana.tauro@intel.com \
    --cc=rodrigo.vivi@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