From: Gustavo Sousa <gustavo.sousa@intel.com>
To: intel-xe@lists.freedesktop.org, intel-gfx@lists.freedesktop.org
Cc: Gustavo Sousa <gustavo.sousa@intel.com>
Subject: [PATCH 10/16] drm/xe/xe3p_lpg: Update LRC sizes
Date: Mon, 02 Feb 2026 18:43:16 -0300 [thread overview]
Message-ID: <20260202-nvl-p-upstreaming-v1-10-653e4ff105dc@intel.com> (raw)
In-Reply-To: <20260202-nvl-p-upstreaming-v1-0-653e4ff105dc@intel.com>
Like with previous generations, the engine context images for of both
RCS and CCS in Xe3p_LPG contain a common layout at the end for the
context related to the "Compute Pipeline".
The size of the memory area written to such section varies; it depends
on the type of preemption has taken place during the execution and type
of command streamer instruction that was used on the pipeline. For
Xe3p_LPG, the maximum possible size, including NOOPs for cache line
alignment, is 4368 dwords, which would be the case of a mid-thread
preemption during the execution of a COMPUTE_WALKER_2 instruction.
The maximum size has increased in such a way that we need to update
xe_gt_lrc_size() to match the new sizing requirement. When we add that
to the engine-specific parts, we have:
- RCS context image: 6672 dwords = 26688 bytes -> 7 pages
- CCS context image: 5024 dwords = 20096 bytes -> 5 pages
Bspec: 65182, 55793, 73590
Signed-off-by: Gustavo Sousa <gustavo.sousa@intel.com>
---
drivers/gpu/drm/xe/xe_lrc.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index e58eb8b9db78..38f648b98868 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -113,13 +113,17 @@ size_t xe_gt_lrc_hang_replay_size(struct xe_gt *gt, enum xe_engine_class class)
/* Engine context image */
switch (class) {
case XE_ENGINE_CLASS_RENDER:
- if (GRAPHICS_VER(xe) >= 20)
+ if (GRAPHICS_VERx100(xe) >= 3510)
+ size += 7 * SZ_4K;
+ else if (GRAPHICS_VER(xe) >= 20)
size += 3 * SZ_4K;
else
size += 13 * SZ_4K;
break;
case XE_ENGINE_CLASS_COMPUTE:
- if (GRAPHICS_VER(xe) >= 20)
+ if (GRAPHICS_VERx100(xe) >= 3510)
+ size += 5 * SZ_4K;
+ else if (GRAPHICS_VER(xe) >= 20)
size += 2 * SZ_4K;
else
size += 13 * SZ_4K;
--
2.52.0
next prev parent reply other threads:[~2026-02-02 21:44 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-02 21:43 [PATCH 00/16] Basic enabling patches for Xe3p_LPG and NVL-P Gustavo Sousa
2026-02-02 21:43 ` [PATCH 01/16] drm/xe/xe3p_lpg: Add support for graphics IP 35.10 Gustavo Sousa
2026-02-02 22:11 ` Matt Roper
2026-02-02 23:36 ` Matt Roper
2026-02-03 23:53 ` Gustavo Sousa
2026-02-02 21:43 ` [PATCH 02/16] drm/xe/xe3p_lpg: Add initial workarounds for graphics version 35.10 Gustavo Sousa
2026-02-02 22:47 ` Matt Roper
2026-02-04 0:25 ` Gustavo Sousa
2026-02-02 21:43 ` [PATCH 03/16] drm/xe/pat: Differentiate between primary and media for PTA Gustavo Sousa
2026-02-02 22:51 ` Matt Roper
2026-02-02 21:43 ` [PATCH 04/16] drm/xe/xe3p_lpg: Add new PAT table Gustavo Sousa
2026-02-05 17:05 ` Matt Atwood
2026-02-02 21:43 ` [PATCH 05/16] drm/xe/xe3p_lpg: Add MCR steering Gustavo Sousa
2026-02-03 10:32 ` Bhadane, Dnyaneshwar
2026-02-04 0:33 ` Gustavo Sousa
2026-02-06 8:29 ` Bhadane, Dnyaneshwar
2026-02-06 12:38 ` Gustavo Sousa
2026-02-02 21:43 ` [PATCH 06/16] drm/xe/xe3p_lpg: Add LRC parsing for additional RCS engine state Gustavo Sousa
2026-02-05 22:12 ` Matt Atwood
2026-02-02 21:43 ` [PATCH 07/16] drm/xe/xe3p_lpg: Disable reporting of context switch status to GHWSP Gustavo Sousa
2026-02-05 17:31 ` Matt Atwood
2026-02-02 21:43 ` [PATCH 08/16] drm/xe/xe3p_lpg: Drop unnecessary tuning settings Gustavo Sousa
2026-02-05 17:28 ` Matt Atwood
2026-02-02 21:43 ` [PATCH 09/16] drm/xe/xe3p_lpg: Extend 'group ID' mask size Gustavo Sousa
2026-02-04 12:18 ` Bhadane, Dnyaneshwar
2026-02-02 21:43 ` Gustavo Sousa [this message]
2026-02-02 23:29 ` [PATCH 10/16] drm/xe/xe3p_lpg: Update LRC sizes Matt Roper
2026-02-02 21:43 ` [PATCH 11/16] drm/xe/xe3p_lpg: Set STLB bank hash mode to 4KB Gustavo Sousa
2026-02-02 23:34 ` Matt Roper
2026-02-02 21:43 ` [PATCH 12/16] drm/xe/xe3p_lpg: Enable multi-queue feature Gustavo Sousa
2026-02-02 23:35 ` Matt Roper
2026-02-02 21:43 ` [PATCH 13/16] drm/xe/nvlp: Add NVL-P platform definition Gustavo Sousa
2026-02-02 23:48 ` Matt Roper
2026-02-04 12:59 ` Gustavo Sousa
2026-02-04 18:08 ` Matt Roper
2026-02-04 18:36 ` Gustavo Sousa
2026-02-02 21:43 ` [PATCH 14/16] drm/xe/nvlp: Attach MOCS table for nvlp Gustavo Sousa
2026-02-02 23:48 ` Matt Roper
2026-02-02 21:43 ` [PATCH 15/16] drm/i915/nvlp: Hook up display support Gustavo Sousa
2026-02-03 4:19 ` Kandpal, Suraj
2026-02-02 21:43 ` [PATCH 16/16] drm/xe/nvlp: Define GuC firmware for NVL-P Gustavo Sousa
2026-02-02 23:52 ` Matt Roper
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=20260202-nvl-p-upstreaming-v1-10-653e4ff105dc@intel.com \
--to=gustavo.sousa@intel.com \
--cc=intel-gfx@lists.freedesktop.org \
--cc=intel-xe@lists.freedesktop.org \
/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