Intel-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Uma Shankar <uma.shankar@intel.com>
To: intel-gfx@lists.freedesktop.org, intel-xe@lists.freedesktop.org
Cc: vinod.govindapillai@intel.com, suraj.kandpal@intel.com,
	Uma Shankar <uma.shankar@intel.com>
Subject: [v3 1/2] drm/i915/xe3p/dram: Interpret 0xF populated-channel count as 16
Date: Wed, 15 Jul 2026 20:02:42 +0530	[thread overview]
Message-ID: <20260715143243.4141208-2-uma.shankar@intel.com> (raw)
In-Reply-To: <20260715143243.4141208-1-uma.shankar@intel.com>

Wa_16030862157:
Interpret 0xF populated-channel count as 16
The register MEM_SS_INFO_GLOBAL [Number of populated channels] field
definition is updated with an encoding for 16 channels.

For 16-channel configuration, program 1111b. A programmed value of 1111b
must be interpreted as 16 channels for memory bandwidth calculations.

The MEM_SS_INFO_GLOBAL populated-channel field is only 4 bits and cannot
encode 16, so on Xe3p the BIOS programs the saturated field value (0xf)
to indicate the fully-populated 16-channel config (4 memory controllers
x 4 channels). Interpret it as 16 and let the bandwidth math handle the
larger channel count.

v2: Limit the WA only till NVL (Suraj)
    Logical separation of WA (Vinod)

WA: 16030862157, 16030875223
Bspec: 69131, 79482

Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Uma Shankar <uma.shankar@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display_wa.c |  2 ++
 drivers/gpu/drm/i915/display/intel_display_wa.h |  1 +
 drivers/gpu/drm/i915/display/intel_dram.c       | 14 +++++++++++++-
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_wa.c b/drivers/gpu/drm/i915/display/intel_display_wa.c
index b4c49816f7eb..3662e0f17c69 100644
--- a/drivers/gpu/drm/i915/display/intel_display_wa.c
+++ b/drivers/gpu/drm/i915/display/intel_display_wa.c
@@ -140,6 +140,8 @@ bool __intel_display_wa(struct intel_display *display, enum intel_display_wa wa,
 						STEP_A0, STEP_B0);
 	case INTEL_DISPLAY_WA_16029024088:
 		return DISPLAY_VER(display) >= 35;
+	case INTEL_DISPLAY_WA_16030862157:
+		return DISPLAY_VER(display) == 35;
 	case INTEL_DISPLAY_WA_18034343758:
 		return DISPLAY_VER(display) == 20 ||
 			(display->platform.pantherlake &&
diff --git a/drivers/gpu/drm/i915/display/intel_display_wa.h b/drivers/gpu/drm/i915/display/intel_display_wa.h
index 92b3980bea84..338b32e4162d 100644
--- a/drivers/gpu/drm/i915/display/intel_display_wa.h
+++ b/drivers/gpu/drm/i915/display/intel_display_wa.h
@@ -54,6 +54,7 @@ enum intel_display_wa {
 	INTEL_DISPLAY_WA_16025573575,
 	INTEL_DISPLAY_WA_16025596647,
 	INTEL_DISPLAY_WA_16029024088,
+	INTEL_DISPLAY_WA_16030862157,
 	INTEL_DISPLAY_WA_18034343758,
 	INTEL_DISPLAY_WA_22010178259,
 	INTEL_DISPLAY_WA_22010947358,
diff --git a/drivers/gpu/drm/i915/display/intel_dram.c b/drivers/gpu/drm/i915/display/intel_dram.c
index f103f7cba018..0763d0bfd98e 100644
--- a/drivers/gpu/drm/i915/display/intel_dram.c
+++ b/drivers/gpu/drm/i915/display/intel_dram.c
@@ -13,6 +13,7 @@
 #include "intel_display_core.h"
 #include "intel_display_utils.h"
 #include "intel_display_regs.h"
+#include "intel_display_wa.h"
 #include "intel_dram.h"
 #include "intel_mchbar.h"
 #include "intel_parent.h"
@@ -794,7 +795,18 @@ static int xelpdp_get_dram_info(struct intel_display *display, struct dram_info
 
 	dram_info->num_channels = REG_FIELD_GET(MTL_N_OF_POPULATED_CH_MASK, val);
 	dram_info->num_qgv_points = REG_FIELD_GET(MTL_N_OF_ENABLED_QGV_POINTS_MASK, val);
-	/* PSF GV points not supported in D14+ */
+
+	/*
+	 * Wa_16030862157
+	 * MEM_SS_INFO_GLOBAL populated-channel field is only 4 bits and
+	 * cannot encode 16, so on Xe3p the BIOS programs the saturated field
+	 * value (0xf) to indicate the fully-populated 16-channel config (4
+	 * memory controllers x 4 channels). Interpret it as 16.
+	 */
+
+	if (intel_display_wa(display, INTEL_DISPLAY_WA_16030862157) &&
+	    dram_info->num_channels == REG_FIELD_MAX(MTL_N_OF_POPULATED_CH_MASK))
+		dram_info->num_channels = 16;
 
 	if (DISPLAY_VER(display) >= 35)
 		dram_info->ecc_impacting_de_bw = REG_FIELD_GET(XE3P_ECC_IMPACTING_DE, val);
-- 
2.50.1


  reply	other threads:[~2026-07-15 14:13 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-15 14:32 [v3 0/2] drm/i915/display: Implement Display Wa_16030862157 Uma Shankar
2026-07-15 14:32 ` Uma Shankar [this message]
2026-07-16  2:40   ` [v3 1/2] drm/i915/xe3p/dram: Interpret 0xF populated-channel count as 16 Kandpal, Suraj
2026-07-16  9:47   ` Govindapillai, Vinod
2026-07-15 14:32 ` [v3 2/2] drm/i915/xe3p/bw: Update bw calculation to account for 16 channels Uma Shankar
2026-07-16  2:41   ` Kandpal, Suraj
2026-07-16  9:49   ` Govindapillai, Vinod
2026-07-15 16:42 ` ✓ i915.CI.BAT: success for drm/i915/display: Implement Display Wa_16030862157 (rev2) Patchwork
2026-07-15 21:59 ` ✗ i915.CI.Full: failure " Patchwork
2026-07-17 15:47 ` ✓ i915.CI.Full: success " 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=20260715143243.4141208-2-uma.shankar@intel.com \
    --to=uma.shankar@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=suraj.kandpal@intel.com \
    --cc=vinod.govindapillai@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