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")
Requires: 075e003a9e22 ("drm/i915/gt: Refactor uabi engine class/instance list creation")
Requires: 58b935268238 ("drm/i915/gt: Disable tests for CCS engines beyond the first")
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+
---
drivers/gpu/drm/i915/Makefile | 1 +
drivers/gpu/drm/i915/gt/intel_engine_user.c | 11 ++++++
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 ++++
6 files changed, 76 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 3ef6ed41e62b..a6885a1d41a1 100644
--- 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 \
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c
index 11cc06c0c785..9ef1c4ce252d 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_user.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c
@@ -208,6 +208,7 @@ void intel_engines_driver_register(struct drm_i915_private *i915)
struct list_head *it, *next;
struct rb_node **p, *prev;
LIST_HEAD(engines);
+ u16 uabi_ccs = 0;
sort_engines(i915, &engines);
@@ -244,6 +245,16 @@ void intel_engines_driver_register(struct drm_i915_private *i915)
if (uabi_class > I915_LAST_UABI_ENGINE_CLASS)
continue;
+ /*
+ * The load is balanced among all the available compute
+ * slices. Expose only the first instance of the compute
+ * engine.
+ */
+ if (IS_DG2(i915) &&
+ uabi_class == I915_ENGINE_CLASS_COMPUTE &&
+ uabi_ccs++)
+ continue;
+
GEM_BUG_ON(uabi_class >=
ARRAY_SIZE(i915->engine_uabi_class_count));
i915->engine_uabi_class_count[uabi_class]++;
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..044219c5960a
--- /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);
+}
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..9e5549caeb26
--- /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__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index cf709f6c05ae..8224dd99c7d7 100644
--- 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 GEN12_RCU_MODE_CCS_ENABLE REG_BIT(0)
#define XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE REG_BIT(1)
+#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)
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 4865eb5ca9c9..6ec3582c9735 100644
--- 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"
@@ -2869,6 +2870,12 @@ static void ccs_engine_wa_mode(struct intel_engine_cs *engine, struct i915_wa_li
* 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);
}
/*
--
2.43.0
