This is a note to let you know that I've just added the patch titled
drm/i915/gt: Enable only one CCS for compute workload
to the 6.8-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
drm-i915-gt-enable-only-one-ccs-for-compute-workload.patch
and it can be found in the queue-6.8 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 6db31251bb265813994bfb104eb4b4d0f44d64fb Mon Sep 17 00:00:00 2001
From: Andi Shyti <andi.shyti@xxxxxxxxxxxxxxx>
Date: Thu, 28 Mar 2024 08:34:05 +0100
Subject: drm/i915/gt: Enable only one CCS for compute workload
From: Andi Shyti <andi.shyti@xxxxxxxxxxxxxxx>
commit 6db31251bb265813994bfb104eb4b4d0f44d64fb upstream.
Enable only one CCS engine by default with all the compute sices
allocated to it.
While generating the list of UABI engines to be exposed to the
user, exclude any additional CCS engines beyond the first
instance.
This change can be tested with igt i915_query.
Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement")
Signed-off-by: Andi Shyti <andi.shyti@xxxxxxxxxxxxxxx>
Cc: Chris Wilson <chris.p.wilson@xxxxxxxxxxxxxxx>
Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
Cc: Matt Roper <matthew.d.roper@xxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> # v6.2+
Reviewed-by: Matt Roper <matthew.d.roper@xxxxxxxxx>
Acked-by: Michal Mrozek <michal.mrozek@xxxxxxxxx>
Link: https://patchwork.freedesktop.org/patch/msgid/20240328073409.674098-4-andi.shyti@xxxxxxxxxxxxxxx
(cherry picked from commit 2bebae0112b117de7e8a7289277a4bd2403b9e17)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/Makefile | 1
drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c | 39 ++++++++++++++++++++++++++++
drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h | 13 +++++++++
drivers/gpu/drm/i915/gt/intel_gt_regs.h | 5 +++
drivers/gpu/drm/i915/gt/intel_workarounds.c | 7 +++++
5 files changed, 65 insertions(+)
create mode 100644 drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
create mode 100644 drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -118,6 +118,7 @@ gt-y += \
gt/intel_ggtt_fencing.o \
gt/intel_gt.o \
gt/intel_gt_buffer_pool.o \
+ gt/intel_gt_ccs_mode.o \
gt/intel_gt_clock_utils.o \
gt/intel_gt_debugfs.o \
gt/intel_gt_engines_debugfs.o \
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2024 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "intel_gt.h"
+#include "intel_gt_ccs_mode.h"
+#include "intel_gt_regs.h"
+
+void intel_gt_apply_ccs_mode(struct intel_gt *gt)
+{
+ int cslice;
+ u32 mode = 0;
+ int first_ccs = __ffs(CCS_MASK(gt));
+
+ if (!IS_DG2(gt->i915))
+ return;
+
+ /* Build the value for the fixed CCS load balancing */
+ for (cslice = 0; cslice < I915_MAX_CCS; cslice++) {
+ if (CCS_MASK(gt) & BIT(cslice))
+ /*
+ * If available, assign the cslice
+ * to the first available engine...
+ */
+ mode |= XEHP_CCS_MODE_CSLICE(cslice, first_ccs);
+
+ else
+ /*
+ * ... otherwise, mark the cslice as
+ * unavailable if no CCS dispatches here
+ */
+ mode |= XEHP_CCS_MODE_CSLICE(cslice,
+ XEHP_CCS_MODE_CSLICE_MASK);
+ }
+
+ intel_uncore_write(gt->uncore, XEHP_CCS_MODE, mode);
+}
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2024 Intel Corporation
+ */
+
+#ifndef __INTEL_GT_CCS_MODE_H__
+#define __INTEL_GT_CCS_MODE_H__
+
+struct intel_gt;
+
+void intel_gt_apply_ccs_mode(struct intel_gt *gt);
+
+#endif /* __INTEL_GT_CCS_MODE_H__ */
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -1480,6 +1480,11 @@
#define XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE REG_BIT(1)
#define GEN12_RCU_MODE_CCS_ENABLE REG_BIT(0)
+#define XEHP_CCS_MODE _MMIO(0x14804)
+#define XEHP_CCS_MODE_CSLICE_MASK REG_GENMASK(2, 0) /* CCS0-3 + rsvd */
+#define XEHP_CCS_MODE_CSLICE_WIDTH ilog2(XEHP_CCS_MODE_CSLICE_MASK + 1)
+#define XEHP_CCS_MODE_CSLICE(cslice, ccs) (ccs << (cslice * XEHP_CCS_MODE_CSLICE_WIDTH))
+
#define CHV_FUSE_GT _MMIO(VLV_GUNIT_BASE + 0x2168)
#define CHV_FGT_DISABLE_SS0 (1 << 10)
#define CHV_FGT_DISABLE_SS1 (1 << 11)
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -10,6 +10,7 @@
#include "intel_engine_regs.h"
#include "intel_gpu_commands.h"
#include "intel_gt.h"
+#include "intel_gt_ccs_mode.h"
#include "intel_gt_mcr.h"
#include "intel_gt_print.h"
#include "intel_gt_regs.h"
@@ -2865,6 +2866,12 @@ static void ccs_engine_wa_mode(struct in
* made to completely disable automatic CCS load balancing.
*/
wa_masked_en(wal, GEN12_RCU_MODE, XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE);
+
+ /*
+ * After having disabled automatic load balancing we need to
+ * assign all slices to a single CCS. We will call it CCS mode 1
+ */
+ intel_gt_apply_ccs_mode(gt);
}
/*
Patches currently in stable-queue which might be from andi.shyti@xxxxxxxxxxxxxxx are
queue-6.8/drm-i915-gt-limit-the-reserved-vm-space-to-only-the-.patch
queue-6.8/drm-i915-gt-enable-only-one-ccs-for-compute-workload.patch
queue-6.8/drm-i915-gt-disable-hw-load-balancing-for-ccs.patch
queue-6.8/drm-i915-mtl-update-workaround-14018575942.patch
queue-6.8/drm-i915-gt-do-not-generate-the-command-streamer-for-all-the-ccs.patch
