Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Lucas De Marchi <lucas.demarchi@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: Lucas De Marchi <lucas.demarchi@intel.com>,
	Matt Roper <matthew.d.roper@intel.com>
Subject: [PATCH 03/12] drm/xe/cri: Setup MOCS table
Date: Tue, 21 Oct 2025 22:17:35 -0700	[thread overview]
Message-ID: <20251021-cri-v1-3-bf11e61d9f49@intel.com> (raw)
In-Reply-To: <20251021-cri-v1-0-bf11e61d9f49@intel.com>

From: Matt Roper <matthew.d.roper@intel.com>

CRI has a new MOCS table, but uses the same general ops as other Xe2/Xe3
platforms.

Bspec: 71582
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_mocs.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_mocs.c b/drivers/gpu/drm/xe/xe_mocs.c
index e8ec4114302e5..6613d3b48a844 100644
--- a/drivers/gpu/drm/xe/xe_mocs.c
+++ b/drivers/gpu/drm/xe/xe_mocs.c
@@ -568,6 +568,23 @@ static const struct xe_mocs_ops xe2_mocs_ops = {
 	.dump = xe2_mocs_dump,
 };
 
+/*
+ * Note that the "L3" and "L4" register fields actually control the L2 and L3
+ * caches respectively on this platform.
+ */
+static const struct xe_mocs_entry xe3p_xpc_mocs_table[] = {
+	/* Defer to PAT */
+	MOCS_ENTRY(0, XE2_L3_0_WB | L4_3_UC, 0),
+	/* UC */
+	MOCS_ENTRY(1, IG_PAT | XE2_L3_3_UC | L4_3_UC, 0),
+	/* L2 */
+	MOCS_ENTRY(2, IG_PAT | XE2_L3_0_WB | L4_3_UC, 0),
+	/* L3 */
+	MOCS_ENTRY(3, IG_PAT | XE2_L3_3_UC | L4_0_WB, 0),
+	/* L2 + L3 */
+	MOCS_ENTRY(4, IG_PAT | XE2_L3_0_WB | L4_0_WB, 0),
+};
+
 static unsigned int get_mocs_settings(struct xe_device *xe,
 				      struct xe_mocs_info *info)
 {
@@ -576,6 +593,15 @@ static unsigned int get_mocs_settings(struct xe_device *xe,
 	memset(info, 0, sizeof(struct xe_mocs_info));
 
 	switch (xe->info.platform) {
+	case XE_CRESCENTISLAND:
+		info->ops = &xe2_mocs_ops;
+		info->table_size = ARRAY_SIZE(xe3p_xpc_mocs_table);
+		info->table = xe3p_xpc_mocs_table;
+		info->num_mocs_regs = XE2_NUM_MOCS_ENTRIES;
+		info->uc_index = 1;
+		info->wb_index = 4;
+		info->unused_entries_index = 4;
+		break;
 	case XE_NOVALAKE_S:
 	case XE_PANTHERLAKE:
 	case XE_LUNARLAKE:

-- 
2.51.0


  parent reply	other threads:[~2025-10-22  5:18 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-10-22  5:17 [PATCH 00/12] drm/xe: Add support for Crescent Island Lucas De Marchi
2025-10-22  5:17 ` [PATCH 01/12] drm/xe/cri: Add CRI platform definition Lucas De Marchi
2025-10-22 14:58   ` Shekhar Chauhan
2025-10-22 19:45     ` Lucas De Marchi
2025-10-23 10:57       ` Lucas De Marchi
2025-10-23 11:13         ` Lucas De Marchi
2025-10-22  5:17 ` [PATCH 02/12] topic/for-xe-CI: drm/xe/cri: Define GuC firmware for CRI Lucas De Marchi
2025-10-23 10:33   ` Lucas De Marchi
2025-10-22  5:17 ` Lucas De Marchi [this message]
2025-10-22  8:06   ` [PATCH 03/12] drm/xe/cri: Setup MOCS table Vivekanandan, Balasubramani
2025-10-22  5:17 ` [PATCH 04/12] drm/xe/cri: Add new performance limit reasons bits Lucas De Marchi
2025-10-22  6:31   ` [PATCH 4/12] " Raag Jadav
2025-10-22 21:22     ` Lucas De Marchi
2025-10-22  5:17 ` [PATCH 05/12] drm/xe/cri: Add check to verify if CSC is a PCIe endpoint Lucas De Marchi
2025-10-22  5:17 ` [PATCH 06/12] drm/xe/pm: Enable D3cold WAKE# support Lucas De Marchi
2025-10-22  6:35   ` [PATCH 6/12] " Raag Jadav
2025-10-22 19:53     ` Lucas De Marchi
2025-10-22  5:17 ` [PATCH 07/12] drm/xe: Add device flag to indicate standalone MERT Lucas De Marchi
2025-10-28 21:53   ` Dixit, Ashutosh
2025-10-22  5:17 ` [PATCH 08/12] drm/xe/oa/uapi: Expose MERT OA unit Lucas De Marchi
2025-10-22 23:09   ` Umesh Nerlige Ramappa
2025-11-24 21:34     ` Dixit, Ashutosh
2025-10-22  5:17 ` [PATCH 09/12] drm/xe/pf: Configure LMTT in MERT Lucas De Marchi
2025-10-22  5:17 ` [PATCH 10/12] drm/xe: Handle MERT interrupts Lucas De Marchi
2025-10-22 23:19   ` Matt Roper
2025-10-23 14:42     ` Lucas De Marchi
2025-10-28  9:30       ` Laguna, Lukasz
2025-10-22  5:17 ` [PATCH 11/12] drm/xe/pf: Add TLB invalidation support for MERT Lucas De Marchi
2025-10-22 18:28   ` Matthew Brost
2025-10-23 15:11     ` Lucas De Marchi
2025-10-28  9:33       ` Laguna, Lukasz
2025-10-22  5:17 ` [PATCH 12/12] drm/xe/pf: Handle MERT catastrophic errors Lucas De Marchi
2025-10-22  5:40 ` ✗ CI.checkpatch: warning for drm/xe: Add support for Crescent Island Patchwork
2025-10-22  5:41 ` ✓ CI.KUnit: success " Patchwork
2025-10-22  6:29 ` ✓ Xe.CI.BAT: " Patchwork
2025-10-22  7:56 ` ✗ 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=20251021-cri-v1-3-bf11e61d9f49@intel.com \
    --to=lucas.demarchi@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=matthew.d.roper@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