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>,
Aradhya Bhatia <aradhya.bhatia@intel.com>
Subject: [PATCH 11/16] drm/xe/xe3p_lpg: Set STLB bank hash mode to 4KB
Date: Mon, 02 Feb 2026 18:43:17 -0300 [thread overview]
Message-ID: <20260202-nvl-p-upstreaming-v1-11-653e4ff105dc@intel.com> (raw)
In-Reply-To: <20260202-nvl-p-upstreaming-v1-0-653e4ff105dc@intel.com>
From: Aradhya Bhatia <aradhya.bhatia@intel.com>
Since the dominant size of the pages referred in an i-gpu, such as
Xe3p_LPG, will be 4KB, the HW default of mix of 64K and 2M for STLB bank
hash mode does not make sense.
Allow the SW to change it to 4KB Mode, for Xe3p_LPG.
Signed-off-by: Aradhya Bhatia <aradhya.bhatia@intel.com>
Signed-off-by: Gustavo Sousa <gustavo.sousa@intel.com>
---
drivers/gpu/drm/xe/regs/xe_gt_regs.h | 2 ++
drivers/gpu/drm/xe/xe_tuning.c | 9 +++++++++
2 files changed, 11 insertions(+)
diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
index 19f053a7f9be..cd84b8945a5d 100644
--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
@@ -473,6 +473,8 @@
#define FORCE_MISS_FTLB REG_BIT(3)
#define XEHP_GAMSTLB_CTRL XE_REG_MCR(0xcf4c)
+#define BANK_HASH_MODE REG_GENMASK(27, 26)
+#define BANK_HASH_4KB_MODE REG_FIELD_PREP(BANK_HASH_MODE, 0x3)
#define CONTROL_BLOCK_CLKGATE_DIS REG_BIT(12)
#define EGRESS_BLOCK_CLKGATE_DIS REG_BIT(11)
#define TAG_BLOCK_CLKGATE_DIS REG_BIT(7)
diff --git a/drivers/gpu/drm/xe/xe_tuning.c b/drivers/gpu/drm/xe/xe_tuning.c
index 694385ae75f1..316f5e2b2e48 100644
--- a/drivers/gpu/drm/xe/xe_tuning.c
+++ b/drivers/gpu/drm/xe/xe_tuning.c
@@ -90,6 +90,15 @@ static const struct xe_rtp_entry_sr gt_tunings[] = {
XE_RTP_RULES(MEDIA_VERSION(2000)),
XE_RTP_ACTIONS(SET(XE2LPM_SCRATCH3_LBCF, RWFLUSHALLEN))
},
+
+ /* Xe3p */
+
+ { XE_RTP_NAME("Tuning: Set STLB Bank Hash Mode to 4KB"),
+ XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3510, XE_RTP_END_VERSION_UNDEFINED),
+ IS_INTEGRATED),
+ XE_RTP_ACTIONS(FIELD_SET(XEHP_GAMSTLB_CTRL, BANK_HASH_MODE,
+ BANK_HASH_4KB_MODE))
+ },
};
static const struct xe_rtp_entry_sr engine_tunings[] = {
--
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 ` [PATCH 10/16] drm/xe/xe3p_lpg: Update LRC sizes Gustavo Sousa
2026-02-02 23:29 ` Matt Roper
2026-02-02 21:43 ` Gustavo Sousa [this message]
2026-02-02 23:34 ` [PATCH 11/16] drm/xe/xe3p_lpg: Set STLB bank hash mode to 4KB 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-v1-11-653e4ff105dc@intel.com \
--to=gustavo.sousa@intel.com \
--cc=aradhya.bhatia@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