[PATCH 0/3] Disable dynamic load balancing and support fixed balancing

[PATCH 0/3] Disable dynamic load balancing and support fixed balancing

[Andi Shyti]

Hi,

This series aims to disable the CCS hardware load balancing, as recommended by
hardware directives in Wa_16016805146.

In the meantime, we need to define and support a fixed CCS mode of balancing
that can be configured by the user.

Thanks,
Andi

Cc: Chris Wilson <chris.p.wilson@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Cc: Tejas Upadhyay <tejas.upadhyay@intel.com>

Andi Shyti (3):
  drm/i915/gt: Support fixed CCS mode
  drm/i915/gt: Allow user to set up the CSS mode
  drm/i915/gt: Disable HW load balancing for CCS

 drivers/gpu/drm/i915/Makefile               |   1 +
 drivers/gpu/drm/i915/gt/intel_gt.c          |   6 +
 drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c | 149 ++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h |  17 +++
 drivers/gpu/drm/i915/gt/intel_gt_regs.h     |  14 ++
 drivers/gpu/drm/i915/gt/intel_gt_sysfs.c    |   2 +
 drivers/gpu/drm/i915/gt/intel_gt_types.h    |  20 +++
 drivers/gpu/drm/i915/gt/intel_workarounds.c |   6 +
 drivers/gpu/drm/i915/i915_drv.h             |   2 +
 9 files changed, 217 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

-- 
2.43.0

[PATCH 1/3] drm/i915/gt: Support fixed CCS mode

[Andi Shyti]

The CCS mode involves assigning CCS engines to slices depending
on the number of slices and the number of engines the user wishes
to set.

In this patch, the default CCS setting is established during the
initial GT settings. It involves assigning only one CCS to all
the slices.

Based on a patch by Chris Wilson <chris.p.wilson@linux.intel.com>
and Tejas Upadhyay <tejas.upadhyay@intel.com>.

Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Chris Wilson <chris.p.wilson@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Cc: Tejas Upadhyay <tejas.upadhyay@intel.com>
---
 drivers/gpu/drm/i915/Makefile               |  1 +
 drivers/gpu/drm/i915/gt/intel_gt.c          |  6 ++
 drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c | 81 +++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h | 16 ++++
 drivers/gpu/drm/i915/gt/intel_gt_regs.h     | 13 ++++
 drivers/gpu/drm/i915/gt/intel_gt_types.h    | 20 +++++
 drivers/gpu/drm/i915/i915_drv.h             |  2 +
 7 files changed, 139 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

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index e777686190ca..1dce15d6306b 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -119,6 +119,7 @@ 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 \
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index a425db5ed3a2..e83c7b80c07a 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -17,6 +17,7 @@
 #include "intel_engine_regs.h"
 #include "intel_ggtt_gmch.h"
 #include "intel_gt.h"
+#include "intel_gt_ccs_mode.h"
 #include "intel_gt_buffer_pool.h"
 #include "intel_gt_clock_utils.h"
 #include "intel_gt_debugfs.h"
@@ -47,6 +48,7 @@ void intel_gt_common_init_early(struct intel_gt *gt)
 	init_llist_head(&gt->watchdog.list);
 	INIT_WORK(&gt->watchdog.work, intel_gt_watchdog_work);
 
+	intel_gt_init_ccs_mode(gt);
 	intel_gt_init_buffer_pool(gt);
 	intel_gt_init_reset(gt);
 	intel_gt_init_requests(gt);
@@ -195,6 +197,9 @@ int intel_gt_init_hw(struct intel_gt *gt)
 
 	intel_gt_init_swizzling(gt);
 
+	/* Configure CCS mode */
+	intel_gt_apply_ccs_mode(gt);
+
 	/*
 	 * At least 830 can leave some of the unused rings
 	 * "active" (ie. head != tail) after resume which
@@ -860,6 +865,7 @@ void intel_gt_driver_late_release_all(struct drm_i915_private *i915)
 
 	for_each_gt(gt, i915, id) {
 		intel_uc_driver_late_release(&gt->uc);
+		intel_gt_fini_ccs_mode(gt);
 		intel_gt_fini_requests(gt);
 		intel_gt_fini_reset(gt);
 		intel_gt_fini_timelines(gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
new file mode 100644
index 000000000000..fab8a77bded2
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
@@ -0,0 +1,81 @@
+//SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2023 Intel Corporation
+ */
+
+#include "i915_drv.h"
+
+#include "intel_gt.h"
+#include "intel_gt_ccs_mode.h"
+#include "intel_gt_regs.h"
+#include "intel_gt_types.h"
+
+static void __intel_gt_apply_ccs_mode(struct intel_gt *gt)
+{
+	u32 mode = XEHP_CCS_MODE_CSLICE_0_3_MASK; /* disable all by default */
+	int num_slices = hweight32(CCS_MASK(gt));
+	int num_engines = gt->ccs.mode;
+	int slice = 0;
+	int i;
+
+	if (!num_engines)
+		return;
+
+	/*
+	 * Loop over all available slices and assign each a user engine.
+	 *
+	 * With 1 engine (ccs0):
+	 *   slice 0, 1, 2, 3: ccs0
+	 *
+	 * With 2 engines (ccs0, ccs1):
+	 *   slice 0, 2: ccs0
+	 *   slice 1, 3: ccs1
+	 *
+	 * With 4 engines (ccs0, ccs1, ccs2, ccs3):
+	 *   slice 0: ccs0
+	 *   slice 1: ccs1
+	 *   slice 2: ccs2
+	 *   slice 3: ccs3
+	 *
+	 * Since the number of slices and the number of engines is
+	 * known, and we ensure that there is an exact multiple of
+	 * engines for slices, the double loop becomes a loop over each
+	 * slice.
+	 */
+	for (i = num_slices / num_engines; i < num_slices; i++) {
+		struct intel_engine_cs *engine;
+		intel_engine_mask_t tmp;
+
+		for_each_engine_masked(engine, gt, ALL_CCS(gt), tmp) {
+			/* If a slice is fused off, leave disabled */
+			while (!(CCS_MASK(gt) & BIT(slice)))
+				slice++;
+
+			mode &= ~XEHP_CCS_MODE_CSLICE(slice, XEHP_CCS_MODE_CSLICE_MASK);
+			mode |= XEHP_CCS_MODE_CSLICE(slice, engine->instance);
+
+			/* assign the next slice */
+			slice++;
+		}
+	}
+
+	intel_uncore_write(gt->uncore, XEHP_CCS_MODE, mode);
+}
+
+void intel_gt_apply_ccs_mode(struct intel_gt *gt)
+{
+	mutex_lock(&gt->ccs.mutex);
+	__intel_gt_apply_ccs_mode(gt);
+	mutex_unlock(&gt->ccs.mutex);
+}
+
+void intel_gt_init_ccs_mode(struct intel_gt *gt)
+{
+	mutex_init(&gt->ccs.mutex);
+	gt->ccs.mode = 1;
+}
+
+void intel_gt_fini_ccs_mode(struct intel_gt *gt)
+{
+	mutex_destroy(&gt->ccs.mutex);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h
new file mode 100644
index 000000000000..751c5700944b
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2023 Intel Corporation
+ */
+
+#ifndef INTEL_GT_CCS_MODE_H
+#define INTEL_GT_CCS_MODE_H
+
+struct intel_gt;
+
+void intel_gt_init_ccs_mode(struct intel_gt *gt);
+void intel_gt_fini_ccs_mode(struct intel_gt *gt);
+
+void intel_gt_apply_ccs_mode(struct intel_gt *gt);
+
+#endif /* INTEL_GT_CCS_MODE_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index 50962cfd1353..3e558d6d5e89 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -1604,6 +1604,19 @@
 #define   GEN12_VOLTAGE_MASK			REG_GENMASK(10, 0)
 #define   GEN12_CAGF_MASK			REG_GENMASK(19, 11)
 
+/*
+ * Total of 4 cslices, where each cslice is in the form:
+ *   [0-3]     CCS ID
+ *   [4-6]     RSVD
+ *   [7]       Disabled
+ */
+#define XEHP_CCS_MODE				_MMIO(0x14804)
+#define   XEHP_CCS_MODE_CSLICE_0_3_MASK		REG_GENMASK(11, 0)
+#define   XEHP_CCS_MODE_CSLICE_MASK		0x7 /* 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 GEN11_GT_INTR_DW(x)			_MMIO(0x190018 + ((x) * 4))
 #define   GEN11_CSME				(31)
 #define   GEN12_HECI_2				(30)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index def7dd0eb6f1..6abd93c299c4 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -207,6 +207,26 @@ struct intel_gt {
 					    [MAX_ENGINE_INSTANCE + 1];
 	enum intel_submission_method submission_method;
 
+	/*
+	 * Track fixed mapping between CCS engines and compute slices.
+	 *
+	 * In order to w/a HW that has the inability to dynamically load
+	 * balance between CCS engines and EU in the compute slices, we have to
+	 * reconfigure a static mapping on the fly. We track the current CCS
+	 * configuration (determined by inspection of the user's engine
+	 * selection during execbuf) and compare it against the current
+	 * CCS_MODE (which maps CCS engines to compute slices).  If there is
+	 * only a single engine selected, we can map it to all available
+	 * compute slices for maximal single task performance (fast/narrow). If
+	 * there are more then one engine selected, we have to reduce the
+	 * number of slices allocated to each engine (wide/slow), fairly
+	 * distributing the EU between the equivalent engines.
+	 */
+	struct {
+		struct mutex mutex;
+		u32 mode;
+	} ccs;
+
 	/*
 	 * Default address space (either GGTT or ppGTT depending on arch).
 	 *
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e81b3b2858ac..cd85889ecfe4 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -659,6 +659,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define CCS_MASK(gt) \
 	ENGINE_INSTANCES_MASK(gt, CCS0, I915_MAX_CCS)
 
+#define ALL_CCS(gt) (CCS_MASK(gt) << CCS0)
+
 #define HAS_MEDIA_RATIO_MODE(i915) (INTEL_INFO(i915)->has_media_ratio_mode)
 
 /*
-- 
2.43.0

Re: [PATCH 1/3] drm/i915/gt: Support fixed CCS mode

[Joonas Lahtinen]

Quoting Andi Shyti (2023-12-21 19:08:22)
> The CCS mode involves assigning CCS engines to slices depending
> on the number of slices and the number of engines the user wishes
> to set.
> 
> In this patch, the default CCS setting is established during the
> initial GT settings. It involves assigning only one CCS to all
> the slices.
> 
> Based on a patch by Chris Wilson <chris.p.wilson@linux.intel.com>
> and Tejas Upadhyay <tejas.upadhyay@intel.com>.
> 
> Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
> Cc: Chris Wilson <chris.p.wilson@linux.intel.com>
> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> Cc: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
> Cc: Tejas Upadhyay <tejas.upadhyay@intel.com>

<SNIP>

> +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
> @@ -207,6 +207,26 @@ struct intel_gt {
>                                             [MAX_ENGINE_INSTANCE + 1];
>         enum intel_submission_method submission_method;
>  
> +       /*
> +        * Track fixed mapping between CCS engines and compute slices.
> +        *
> +        * In order to w/a HW that has the inability to dynamically load
> +        * balance between CCS engines and EU in the compute slices, we have to
> +        * reconfigure a static mapping on the fly. We track the current CCS
> +        * configuration (determined by inspection of the user's engine
> +        * selection during execbuf) and compare it against the current
> +        * CCS_MODE (which maps CCS engines to compute slices).  If there is
> +        * only a single engine selected, we can map it to all available
> +        * compute slices for maximal single task performance (fast/narrow). If
> +        * there are more then one engine selected, we have to reduce the
> +        * number of slices allocated to each engine (wide/slow), fairly
> +        * distributing the EU between the equivalent engines.
> +        */

This comment is outdated as we don't consider execbuf but the sysfs
configuration.

Regards, Joonas

> +       struct {
> +               struct mutex mutex;
> +               u32 mode;
> +       } ccs;
> +
>         /*
>          * Default address space (either GGTT or ppGTT depending on arch).
>          *

Re: [PATCH 1/3] drm/i915/gt: Support fixed CCS mode

[Andi Shyti]

Hi Joonas,

> > +       /*
> > +        * Track fixed mapping between CCS engines and compute slices.
> > +        *
> > +        * In order to w/a HW that has the inability to dynamically load
> > +        * balance between CCS engines and EU in the compute slices, we have to
> > +        * reconfigure a static mapping on the fly. We track the current CCS
> > +        * configuration (determined by inspection of the user's engine
> > +        * selection during execbuf) and compare it against the current
> > +        * CCS_MODE (which maps CCS engines to compute slices).  If there is
> > +        * only a single engine selected, we can map it to all available
> > +        * compute slices for maximal single task performance (fast/narrow). If
> > +        * there are more then one engine selected, we have to reduce the
> > +        * number of slices allocated to each engine (wide/slow), fairly
> > +        * distributing the EU between the equivalent engines.
> > +        */
> 
> This comment is outdated as we don't consider execbuf but the sysfs
> configuration.

yes, I removed some parts of the original comment already, but
yes, I agree it can be improved.

Thanks,
Andi

[PATCH 2/3] drm/i915/gt: Allow user to set up the CSS mode

[Andi Shyti]

Now that the CCS mode is configurable, an interface has been
exposed in the GT's sysfs set of files, allowing users to set the
mode.

Additionally, another interface has been added to display the
number of available slices, named 'num_slices.'

Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Chris Wilson <chris.p.wilson@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Cc: Tejas Upadhyay <tejas.upadhyay@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c | 68 +++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h |  1 +
 drivers/gpu/drm/i915/gt/intel_gt_sysfs.c    |  2 +
 3 files changed, 71 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
index fab8a77bded2..88663698eb1f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
@@ -7,6 +7,7 @@
 
 #include "intel_gt.h"
 #include "intel_gt_ccs_mode.h"
+#include "intel_gt_print.h"
 #include "intel_gt_regs.h"
 #include "intel_gt_types.h"
 
@@ -79,3 +80,70 @@ void intel_gt_fini_ccs_mode(struct intel_gt *gt)
 {
 	mutex_destroy(&gt->ccs.mutex);
 }
+
+static ssize_t
+ccs_mode_show(struct kobject *kobj, struct kobj_attribute *attr, char *buff)
+{
+	struct intel_gt *gt = container_of(kobj, struct intel_gt, sysfs_gt);
+
+	return sysfs_emit(buff, "%u\n", gt->ccs.mode);
+}
+
+static ssize_t
+ccs_mode_store(struct kobject *kobj, struct kobj_attribute *attr,
+	       const char *buff, size_t count)
+{
+	struct intel_gt *gt = container_of(kobj, struct intel_gt, sysfs_gt);
+	int num_slices = hweight32(CCS_MASK(gt));
+	int err;
+	u32 val;
+
+	err = kstrtou32(buff, 0, &val);
+	if (err)
+		return err;
+
+	if ((!val) || (val > num_slices) || (val % num_slices))
+		return -EINVAL;
+
+	mutex_lock(&gt->ccs.mutex);
+
+	if (val == gt->ccs.mode)
+		goto out;
+
+	gt->ccs.mode = val;
+	intel_gt_apply_ccs_mode(gt);
+
+out:
+	mutex_unlock(&gt->ccs.mutex);
+
+	return count;
+}
+
+static ssize_t
+num_slices_show(struct kobject *kobj, struct kobj_attribute *attr, char *buff)
+{
+	struct intel_gt *gt = container_of(kobj, struct intel_gt, sysfs_gt);
+	u32 num_slices;
+
+	num_slices = hweight32(CCS_MASK(gt));
+
+	return sysfs_emit(buff, "%u\n", num_slices);
+}
+
+static struct kobj_attribute ccs_mode = __ATTR_RW(ccs_mode);
+static struct kobj_attribute num_slices = __ATTR_RO(num_slices);
+
+static const struct attribute * const ccs_mode_attrs[] = {
+	&ccs_mode.attr,
+	&num_slices.attr,
+	NULL
+};
+
+void intel_gt_sysfs_ccs_mode(struct intel_gt *gt)
+{
+	int ret;
+
+	ret = sysfs_create_files(&gt->sysfs_gt, ccs_mode_attrs);
+	if (ret)
+		gt_warn(gt, "Failed to create ccs mode sysfs files");
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h
index 751c5700944b..ae96de1b36c5 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h
@@ -12,5 +12,6 @@ void intel_gt_init_ccs_mode(struct intel_gt *gt);
 void intel_gt_fini_ccs_mode(struct intel_gt *gt);
 
 void intel_gt_apply_ccs_mode(struct intel_gt *gt);
+void intel_gt_sysfs_ccs_mode(struct intel_gt *gt);
 
 #endif /* INTEL_GT_CCS_MODE_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c
index 33cba406b569..a0290347938d 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c
@@ -12,6 +12,7 @@
 #include "i915_drv.h"
 #include "i915_sysfs.h"
 #include "intel_gt.h"
+#include "intel_gt_ccs_mode.h"
 #include "intel_gt_print.h"
 #include "intel_gt_sysfs.h"
 #include "intel_gt_sysfs_pm.h"
@@ -101,6 +102,7 @@ void intel_gt_sysfs_register(struct intel_gt *gt)
 		goto exit_fail;
 
 	intel_gt_sysfs_pm_init(gt, &gt->sysfs_gt);
+	intel_gt_sysfs_ccs_mode(gt);
 
 	return;
 
-- 
2.43.0

[PATCH 3/3] drm/i915/gt: Disable HW load balancing for CCS

[Andi Shyti]

The hardware is not able to dynamically balance the load between
CCS engines. Wa_16016805146 suggests disabling it for all
platforms.

Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Chris Wilson <chris.p.wilson@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Cc: Tejas Upadhyay <tejas.upadhyay@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_gt_regs.h     | 1 +
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 6 ++++++
 2 files changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index 3e558d6d5e89..edaa446abd91 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -1478,6 +1478,7 @@
 
 #define GEN12_RCU_MODE				_MMIO(0x14800)
 #define   GEN12_RCU_MODE_CCS_ENABLE		REG_BIT(0)
+#define   XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE	REG_BIT(1)
 
 #define CHV_FUSE_GT				_MMIO(VLV_GUNIT_BASE + 0x2168)
 #define   CHV_FGT_DISABLE_SS0			(1 << 10)
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 3eacbc50caf8..a7718f7d2925 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -2978,6 +2978,12 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li
 		wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN1,
 				 GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE);
 	}
+
+	/*
+	 * Wa_16016805146: disable the CCS load balancing
+	 * indiscriminately for all the platforms
+	 */
+	wa_masked_en(wal, GEN12_RCU_MODE, XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE);
 }
 
 static void
-- 
2.43.0