From: Matt Roper <matthew.d.roper@intel.com>
To: Matthew Brost <matthew.brost@intel.com>
Cc: <intel-xe@lists.freedesktop.org>, <michal.mrozek@intel.com>,
<balasubramani.vivekanandan@intel.com>, <jose.souza@intel.com>,
<paulo.r.zanoni@intel.com>
Subject: Re: [PATCH v2] drm/xe: Mark ComputeCS read mode as UC on iGPU
Date: Tue, 14 Jan 2025 13:33:19 -0800 [thread overview]
Message-ID: <20250114213319.GD5109@mdroper-desk1.amr.corp.intel.com> (raw)
In-Reply-To: <20250114002507.114087-1-matthew.brost@intel.com>
On Mon, Jan 13, 2025 at 04:25:07PM -0800, Matthew Brost wrote:
> RING_CMD_CCTL read index should be UC on iGPU parts due to L3 caching
> structure. Having this as WB blocks ULLS from being enabled. Change to
> UC to unblock ULLS on iGPU.
>
> v2:
> - Drop internal communications commnet, bspec is updated
>
> Cc: Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com>
> Cc: Michal Mrozek <michal.mrozek@intel.com>
> Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
> Cc: José Roberto de Souza <jose.souza@intel.com>
> Cc: stable@vger.kernel.org
> Fixes: 328e089bfb37 ("drm/xe: Leverage ComputeCS read L3 caching")
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> Acked-by: Michal Mrozek <michal.mrozek@intel.com>
> Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Matches the bspec update that landed last month.
Bspec: 72161
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Matt
> ---
> drivers/gpu/drm/xe/xe_hw_engine.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c
> index ac9c666a9652..fc447751fe78 100644
> --- a/drivers/gpu/drm/xe/xe_hw_engine.c
> +++ b/drivers/gpu/drm/xe/xe_hw_engine.c
> @@ -422,7 +422,7 @@ hw_engine_setup_default_state(struct xe_hw_engine *hwe)
> * Bspec: 72161
> */
> const u8 mocs_write_idx = gt->mocs.uc_index;
> - const u8 mocs_read_idx = hwe->class == XE_ENGINE_CLASS_COMPUTE &&
> + const u8 mocs_read_idx = hwe->class == XE_ENGINE_CLASS_COMPUTE && IS_DGFX(xe) &&
> (GRAPHICS_VER(xe) >= 20 || xe->info.platform == XE_PVC) ?
> gt->mocs.wb_index : gt->mocs.uc_index;
> u32 ring_cmd_cctl_val = REG_FIELD_PREP(CMD_CCTL_WRITE_OVERRIDE_MASK, mocs_write_idx) |
> --
> 2.34.1
>
--
Matt Roper
Graphics Software Engineer
Linux GPU Platform Enablement
Intel Corporation
next prev parent reply other threads:[~2025-01-14 21:33 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-01-14 0:25 [PATCH v2] drm/xe: Mark ComputeCS read mode as UC on iGPU Matthew Brost
2025-01-14 0:33 ` ✓ CI.Patch_applied: success for drm/xe: Mark ComputeCS read mode as UC on iGPU (rev2) Patchwork
2025-01-14 0:33 ` ✓ CI.checkpatch: " Patchwork
2025-01-14 0:35 ` ✓ CI.KUnit: " Patchwork
2025-01-14 0:43 ` ✗ CI.Build: failure " Patchwork
2025-01-14 18:24 ` ✓ CI.Patch_applied: success for drm/xe: Mark ComputeCS read mode as UC on iGPU (rev3) Patchwork
2025-01-14 18:25 ` ✓ CI.checkpatch: " Patchwork
2025-01-14 18:26 ` ✓ CI.KUnit: " Patchwork
2025-01-14 18:56 ` ✓ CI.Build: " Patchwork
2025-01-14 19:00 ` ✓ CI.Hooks: " Patchwork
2025-01-14 19:01 ` ✓ CI.checksparse: " Patchwork
2025-01-14 19:30 ` ✓ Xe.CI.BAT: " Patchwork
2025-01-14 21:33 ` Matt Roper [this message]
2025-01-14 21:46 ` ✗ Xe.CI.Full: failure " 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=20250114213319.GD5109@mdroper-desk1.amr.corp.intel.com \
--to=matthew.d.roper@intel.com \
--cc=balasubramani.vivekanandan@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=jose.souza@intel.com \
--cc=matthew.brost@intel.com \
--cc=michal.mrozek@intel.com \
--cc=paulo.r.zanoni@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