[PATCH 0/2] Disable automatic load CCS load balancing

[PATCH 0/2] Disable automatic load CCS load balancing

[Andi Shyti]

Hi,

this series does basically two things:

1. Disables automatic load balancing as adviced by the hardware
   workaround.

2. Forces the sharing of the load submitted to CCS among all the
   CCS available (as of now only DG2 has more than one CCS). This
   way the user, when sending a query, will see only one CCS
   available.

Andi

Andi Shyti (2):
  drm/i915/gt: Disable HW load balancing for CCS
  drm/i915/gt: Set default CCS mode '1'

 drivers/gpu/drm/i915/gt/intel_gt.c          | 11 +++++++++++
 drivers/gpu/drm/i915/gt/intel_gt_regs.h     |  3 +++
 drivers/gpu/drm/i915/gt/intel_workarounds.c |  6 ++++++
 drivers/gpu/drm/i915/i915_drv.h             | 17 +++++++++++++++++
 drivers/gpu/drm/i915/i915_query.c           |  5 +++--
 5 files changed, 40 insertions(+), 2 deletions(-)

-- 
2.43.0

[PATCH 1/2] drm/i915/gt: Disable HW load balancing for CCS

[Andi Shyti]

The hardware should not dynamically balance the load between CCS
engines. Wa_16016805146 recommends disabling it across all
platforms.

Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement")
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: Matt Roper <matthew.d.roper@intel.com>
Cc: <stable@vger.kernel.org> # v6.2+
---
 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 50962cfd1353..cf709f6c05ae 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 d67d44611c28..7f42c8015f71 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -2988,6 +2988,12 @@ 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

[PATCH 2/2] drm/i915/gt: Set default CCS mode '1'

[Andi Shyti]

Since CCS automatic load balancing is disabled, we will impose a
fixed balancing policy that involves setting all the CCS engines
to work together on the same load.

Simultaneously, the user will see only 1 CCS rather than the
actual number. As of now, this change affects only DG2.

Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement")
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: Matt Roper <matthew.d.roper@intel.com>
Cc: <stable@vger.kernel.org> # v6.2+
---
 drivers/gpu/drm/i915/gt/intel_gt.c      | 11 +++++++++++
 drivers/gpu/drm/i915/gt/intel_gt_regs.h |  2 ++
 drivers/gpu/drm/i915/i915_drv.h         | 17 +++++++++++++++++
 drivers/gpu/drm/i915/i915_query.c       |  5 +++--
 4 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index a425db5ed3a2..e19df4ef47f6 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -168,6 +168,14 @@ static void init_unused_rings(struct intel_gt *gt)
 	}
 }
 
+static void intel_gt_apply_ccs_mode(struct intel_gt *gt)
+{
+	if (!IS_DG2(gt->i915))
+		return;
+
+	intel_uncore_write(gt->uncore, XEHP_CCS_MODE, 0);
+}
+
 int intel_gt_init_hw(struct intel_gt *gt)
 {
 	struct drm_i915_private *i915 = gt->i915;
@@ -195,6 +203,9 @@ 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
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index cf709f6c05ae..c148113770ea 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -1605,6 +1605,8 @@
 #define   GEN12_VOLTAGE_MASK			REG_GENMASK(10, 0)
 #define   GEN12_CAGF_MASK			REG_GENMASK(19, 11)
 
+#define XEHP_CCS_MODE                          _MMIO(0x14804)
+
 #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/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e81b3b2858ac..0853ffd3cb8d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -396,6 +396,23 @@ static inline struct intel_gt *to_gt(const struct drm_i915_private *i915)
 	     (engine__); \
 	     (engine__) = rb_to_uabi_engine(rb_next(&(engine__)->uabi_node)))
 
+/*
+ * Exclude unavailable engines.
+ *
+ * Only the first CCS engine is utilized due to the disabling of CCS auto load
+ * balancing. As a result, all CCS engines operate collectively, functioning
+ * essentially as a single CCS engine, hence the count of active CCS engines is
+ * considered '1'.
+ * Currently, this applies to platforms with more than one CCS engine,
+ * specifically DG2.
+ */
+#define for_each_available_uabi_engine(engine__, i915__) \
+	for_each_uabi_engine(engine__, i915__) \
+		if ((IS_DG2(i915__)) && \
+		    ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
+		    ((engine__)->uabi_instance)) { } \
+		else
+
 #define INTEL_INFO(i915)	((i915)->__info)
 #define RUNTIME_INFO(i915)	(&(i915)->__runtime)
 #define DRIVER_CAPS(i915)	(&(i915)->caps)
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index fa3e937ed3f5..2d41bda626a6 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -124,6 +124,7 @@ static int query_geometry_subslices(struct drm_i915_private *i915,
 	return fill_topology_info(sseu, query_item, sseu->geometry_subslice_mask);
 }
 
+
 static int
 query_engine_info(struct drm_i915_private *i915,
 		  struct drm_i915_query_item *query_item)
@@ -140,7 +141,7 @@ query_engine_info(struct drm_i915_private *i915,
 	if (query_item->flags)
 		return -EINVAL;
 
-	for_each_uabi_engine(engine, i915)
+	for_each_available_uabi_engine(engine, i915)
 		num_uabi_engines++;
 
 	len = struct_size(query_ptr, engines, num_uabi_engines);
@@ -155,7 +156,7 @@ query_engine_info(struct drm_i915_private *i915,
 
 	info_ptr = &query_ptr->engines[0];
 
-	for_each_uabi_engine(engine, i915) {
+	for_each_available_uabi_engine(engine, i915) {
 		info.engine.engine_class = engine->uabi_class;
 		info.engine.engine_instance = engine->uabi_instance;
 		info.flags = I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE;
-- 
2.43.0

✗ Fi.CI.CHECKPATCH: warning for Disable automatic load CCS load balancing

[Patchwork]

== Series Details ==

Series: Disable automatic load CCS load balancing
URL   : https://patchwork.freedesktop.org/series/129951/
State : warning

== Summary ==

Error: dim checkpatch failed
36e5f8a455e7 drm/i915/gt: Disable HW load balancing for CCS
f1bfa29b3219 drm/i915/gt: Set default CCS mode '1'
-:80: ERROR:COMPLEX_MACRO: Macros with complex values should be enclosed in parentheses
#80: FILE: drivers/gpu/drm/i915/i915_drv.h:409:
+#define for_each_available_uabi_engine(engine__, i915__) \
+	for_each_uabi_engine(engine__, i915__) \
+		if ((IS_DG2(i915__)) && \
+		    ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
+		    ((engine__)->uabi_instance)) { } \
+		else

-:80: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'engine__' - possible side-effects?
#80: FILE: drivers/gpu/drm/i915/i915_drv.h:409:
+#define for_each_available_uabi_engine(engine__, i915__) \
+	for_each_uabi_engine(engine__, i915__) \
+		if ((IS_DG2(i915__)) && \
+		    ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
+		    ((engine__)->uabi_instance)) { } \
+		else

-:80: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'i915__' - possible side-effects?
#80: FILE: drivers/gpu/drm/i915/i915_drv.h:409:
+#define for_each_available_uabi_engine(engine__, i915__) \
+	for_each_uabi_engine(engine__, i915__) \
+		if ((IS_DG2(i915__)) && \
+		    ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
+		    ((engine__)->uabi_instance)) { } \
+		else

-:82: ERROR:TRAILING_STATEMENTS: trailing statements should be on next line
#82: FILE: drivers/gpu/drm/i915/i915_drv.h:411:
+		if ((IS_DG2(i915__)) && \
[...]
+		    ((engine__)->uabi_instance)) { } \

-:98: CHECK:LINE_SPACING: Please don't use multiple blank lines
#98: FILE: drivers/gpu/drm/i915/i915_query.c:127:
 
+

total: 2 errors, 0 warnings, 3 checks, 77 lines checked

✗ Fi.CI.SPARSE: warning for Disable automatic load CCS load balancing

[Patchwork]

== Series Details ==

Series: Disable automatic load CCS load balancing
URL   : https://patchwork.freedesktop.org/series/129951/
State : warning

== Summary ==

Error: dim sparse failed
Sparse version: v0.6.2
Fast mode used, each commit won't be checked separately.

✗ Fi.CI.BAT: failure for Disable automatic load CCS load balancing

[Patchwork]

[-- Attachment #1: Type: text/plain, Size: 12317 bytes --]

== Series Details ==

Series: Disable automatic load CCS load balancing
URL   : https://patchwork.freedesktop.org/series/129951/
State : failure

== Summary ==

CI Bug Log - changes from CI_DRM_14278 -> Patchwork_129951v1
====================================================

Summary
-------

  **FAILURE**

  Serious unknown changes coming with Patchwork_129951v1 absolutely need to be
  verified manually.
  
  If you think the reported changes have nothing to do with the changes
  introduced in Patchwork_129951v1, please notify your bug team (I915-ci-infra@lists.freedesktop.org) to allow them
  to document this new failure mode, which will reduce false positives in CI.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/index.html

Participating hosts (36 -> 35)
------------------------------

  Additional (1): bat-mtlp-8 
  Missing    (2): bat-kbl-2 fi-snb-2520m 

Possible new issues
-------------------

  Here are the unknown changes that may have been introduced in Patchwork_129951v1:

### IGT changes ###

#### Possible regressions ####

  * igt@i915_module_load@load:
    - fi-skl-6600u:       [PASS][1] -> [ABORT][2]
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/fi-skl-6600u/igt@i915_module_load@load.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/fi-skl-6600u/igt@i915_module_load@load.html
    - fi-glk-j4005:       [PASS][3] -> [ABORT][4]
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/fi-glk-j4005/igt@i915_module_load@load.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/fi-glk-j4005/igt@i915_module_load@load.html
    - fi-skl-guc:         [PASS][5] -> [ABORT][6]
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/fi-skl-guc/igt@i915_module_load@load.html
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/fi-skl-guc/igt@i915_module_load@load.html
    - fi-kbl-7567u:       [PASS][7] -> [ABORT][8]
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/fi-kbl-7567u/igt@i915_module_load@load.html
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/fi-kbl-7567u/igt@i915_module_load@load.html
    - fi-cfl-8700k:       [PASS][9] -> [ABORT][10]
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/fi-cfl-8700k/igt@i915_module_load@load.html
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/fi-cfl-8700k/igt@i915_module_load@load.html
    - fi-bsw-nick:        [PASS][11] -> [ABORT][12]
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/fi-bsw-nick/igt@i915_module_load@load.html
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/fi-bsw-nick/igt@i915_module_load@load.html
    - fi-cfl-guc:         [PASS][13] -> [ABORT][14]
   [13]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/fi-cfl-guc/igt@i915_module_load@load.html
   [14]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/fi-cfl-guc/igt@i915_module_load@load.html
    - fi-kbl-x1275:       [PASS][15] -> [ABORT][16]
   [15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/fi-kbl-x1275/igt@i915_module_load@load.html
   [16]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/fi-kbl-x1275/igt@i915_module_load@load.html
    - fi-cfl-8109u:       [PASS][17] -> [ABORT][18]
   [17]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/fi-cfl-8109u/igt@i915_module_load@load.html
   [18]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/fi-cfl-8109u/igt@i915_module_load@load.html
    - fi-ivb-3770:        [PASS][19] -> [ABORT][20]
   [19]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/fi-ivb-3770/igt@i915_module_load@load.html
   [20]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/fi-ivb-3770/igt@i915_module_load@load.html
    - fi-kbl-guc:         [PASS][21] -> [ABORT][22]
   [21]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/fi-kbl-guc/igt@i915_module_load@load.html
   [22]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/fi-kbl-guc/igt@i915_module_load@load.html

  * igt@i915_selftest@live@client:
    - fi-elk-e7500:       [PASS][23] -> [DMESG-WARN][24] +42 other tests dmesg-warn
   [23]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/fi-elk-e7500/igt@i915_selftest@live@client.html
   [24]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/fi-elk-e7500/igt@i915_selftest@live@client.html

  * igt@i915_selftest@live@coherency:
    - bat-jsl-3:          [PASS][25] -> [DMESG-WARN][26] +41 other tests dmesg-warn
   [25]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/bat-jsl-3/igt@i915_selftest@live@coherency.html
   [26]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-jsl-3/igt@i915_selftest@live@coherency.html

  * igt@i915_selftest@live@gt_contexts:
    - fi-ilk-650:         [PASS][27] -> [DMESG-WARN][28] +42 other tests dmesg-warn
   [27]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/fi-ilk-650/igt@i915_selftest@live@gt_contexts.html
   [28]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/fi-ilk-650/igt@i915_selftest@live@gt_contexts.html

  * igt@i915_selftest@live@gt_pm:
    - bat-jsl-1:          [PASS][29] -> [DMESG-WARN][30] +41 other tests dmesg-warn
   [29]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/bat-jsl-1/igt@i915_selftest@live@gt_pm.html
   [30]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-jsl-1/igt@i915_selftest@live@gt_pm.html

  
#### Suppressed ####

  The following results come from untrusted machines, tests, or statuses.
  They do not affect the overall result.

  * igt@gem_exec_fence@basic-busy@rcs0:
    - {bat-arls-1}:       [PASS][31] -> [DMESG-WARN][32]
   [31]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/bat-arls-1/igt@gem_exec_fence@basic-busy@rcs0.html
   [32]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-arls-1/igt@gem_exec_fence@basic-busy@rcs0.html

  
Known issues
------------

  Here are the changes found in Patchwork_129951v1 that come from known issues:

### CI changes ###

#### Issues hit ####

  * boot:
    - fi-apl-guc:         [PASS][33] -> [FAIL][34] ([i915#8293])
   [33]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/fi-apl-guc/boot.html
   [34]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/fi-apl-guc/boot.html

  

### IGT changes ###

#### Issues hit ####

  * igt@debugfs_test@basic-hwmon:
    - bat-mtlp-8:         NOTRUN -> [SKIP][35] ([i915#9318])
   [35]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-mtlp-8/igt@debugfs_test@basic-hwmon.html

  * igt@gem_lmem_swapping@verify-random:
    - bat-mtlp-8:         NOTRUN -> [SKIP][36] ([i915#4613]) +3 other tests skip
   [36]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-mtlp-8/igt@gem_lmem_swapping@verify-random.html

  * igt@gem_mmap@basic:
    - bat-mtlp-8:         NOTRUN -> [SKIP][37] ([i915#4083])
   [37]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-mtlp-8/igt@gem_mmap@basic.html

  * igt@gem_mmap_gtt@basic:
    - bat-mtlp-8:         NOTRUN -> [SKIP][38] ([i915#4077]) +2 other tests skip
   [38]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-mtlp-8/igt@gem_mmap_gtt@basic.html

  * igt@gem_render_tiled_blits@basic:
    - bat-mtlp-8:         NOTRUN -> [SKIP][39] ([i915#4079]) +1 other test skip
   [39]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-mtlp-8/igt@gem_render_tiled_blits@basic.html

  * igt@i915_pm_rps@basic-api:
    - bat-mtlp-8:         NOTRUN -> [SKIP][40] ([i915#6621])
   [40]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-mtlp-8/igt@i915_pm_rps@basic-api.html

  * igt@kms_addfb_basic@addfb25-y-tiled-small-legacy:
    - bat-mtlp-8:         NOTRUN -> [SKIP][41] ([i915#5190])
   [41]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-mtlp-8/igt@kms_addfb_basic@addfb25-y-tiled-small-legacy.html

  * igt@kms_addfb_basic@basic-y-tiled-legacy:
    - bat-mtlp-8:         NOTRUN -> [SKIP][42] ([i915#4212]) +8 other tests skip
   [42]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-mtlp-8/igt@kms_addfb_basic@basic-y-tiled-legacy.html

  * igt@kms_cursor_legacy@basic-busy-flip-before-cursor-legacy:
    - bat-mtlp-8:         NOTRUN -> [SKIP][43] ([i915#4213]) +1 other test skip
   [43]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-mtlp-8/igt@kms_cursor_legacy@basic-busy-flip-before-cursor-legacy.html

  * igt@kms_dsc@dsc-basic:
    - bat-mtlp-8:         NOTRUN -> [SKIP][44] ([i915#3555] / [i915#3840] / [i915#9159])
   [44]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-mtlp-8/igt@kms_dsc@dsc-basic.html

  * igt@kms_force_connector_basic@force-load-detect:
    - bat-mtlp-8:         NOTRUN -> [SKIP][45] ([fdo#109285])
   [45]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-mtlp-8/igt@kms_force_connector_basic@force-load-detect.html

  * igt@kms_force_connector_basic@prune-stale-modes:
    - bat-mtlp-8:         NOTRUN -> [SKIP][46] ([i915#5274])
   [46]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-mtlp-8/igt@kms_force_connector_basic@prune-stale-modes.html

  * igt@kms_setmode@basic-clone-single-crtc:
    - bat-mtlp-8:         NOTRUN -> [SKIP][47] ([i915#3555] / [i915#8809])
   [47]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-mtlp-8/igt@kms_setmode@basic-clone-single-crtc.html

  * igt@prime_vgem@basic-fence-mmap:
    - bat-mtlp-8:         NOTRUN -> [SKIP][48] ([i915#3708] / [i915#4077]) +1 other test skip
   [48]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-mtlp-8/igt@prime_vgem@basic-fence-mmap.html

  * igt@prime_vgem@basic-fence-read:
    - bat-mtlp-8:         NOTRUN -> [SKIP][49] ([i915#3708]) +2 other tests skip
   [49]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-mtlp-8/igt@prime_vgem@basic-fence-read.html

  
#### Possible fixes ####

  * igt@gem_exec_create@basic@smem:
    - {bat-arls-1}:       [DMESG-WARN][50] ([i915#10194]) -> [PASS][51]
   [50]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_14278/bat-arls-1/igt@gem_exec_create@basic@smem.html
   [51]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/bat-arls-1/igt@gem_exec_create@basic@smem.html

  
  {name}: This element is suppressed. This means it is ignored when computing
          the status of the difference (SUCCESS, WARNING, or FAILURE).

  [fdo#109285]: https://bugs.freedesktop.org/show_bug.cgi?id=109285
  [i915#10194]: https://gitlab.freedesktop.org/drm/intel/issues/10194
  [i915#3555]: https://gitlab.freedesktop.org/drm/intel/issues/3555
  [i915#3708]: https://gitlab.freedesktop.org/drm/intel/issues/3708
  [i915#3840]: https://gitlab.freedesktop.org/drm/intel/issues/3840
  [i915#4077]: https://gitlab.freedesktop.org/drm/intel/issues/4077
  [i915#4079]: https://gitlab.freedesktop.org/drm/intel/issues/4079
  [i915#4083]: https://gitlab.freedesktop.org/drm/intel/issues/4083
  [i915#4212]: https://gitlab.freedesktop.org/drm/intel/issues/4212
  [i915#4213]: https://gitlab.freedesktop.org/drm/intel/issues/4213
  [i915#4613]: https://gitlab.freedesktop.org/drm/intel/issues/4613
  [i915#5190]: https://gitlab.freedesktop.org/drm/intel/issues/5190
  [i915#5274]: https://gitlab.freedesktop.org/drm/intel/issues/5274
  [i915#6621]: https://gitlab.freedesktop.org/drm/intel/issues/6621
  [i915#8293]: https://gitlab.freedesktop.org/drm/intel/issues/8293
  [i915#8809]: https://gitlab.freedesktop.org/drm/intel/issues/8809
  [i915#9159]: https://gitlab.freedesktop.org/drm/intel/issues/9159
  [i915#9318]: https://gitlab.freedesktop.org/drm/intel/issues/9318
  [i915#9688]: https://gitlab.freedesktop.org/drm/intel/issues/9688


Build changes
-------------

  * Linux: CI_DRM_14278 -> Patchwork_129951v1

  CI-20190529: 20190529
  CI_DRM_14278: 000df4b23820dc3866d8c92c228c778ef33bf396 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_7714: 7714
  Patchwork_129951v1: 000df4b23820dc3866d8c92c228c778ef33bf396 @ git://anongit.freedesktop.org/gfx-ci/linux


### Linux commits

08e0f187cab5 drm/i915/gt: Set default CCS mode '1'
c21b8eb46264 drm/i915/gt: Disable HW load balancing for CCS

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_129951v1/index.html

[-- Attachment #2: Type: text/html, Size: 13720 bytes --]

Re: [PATCH 1/2] drm/i915/gt: Disable HW load balancing for CCS

[Matt Roper]

On Thu, Feb 15, 2024 at 02:59:23PM +0100, Andi Shyti wrote:
> The hardware should not dynamically balance the load between CCS
> engines. Wa_16016805146 recommends disabling it across all

Is this the right workaround number?  When I check the database, this
workaround was rejected on both DG2-G10 and DG2-G11, and doesn't even
have an entry for DG2-G12.

There are other workarounds that sound somewhat related to load
balancing (e.g., part 3 of Wa_14019159160), but what's asked there is
more involved than just setting one register bit and conflicts a bit
with the second patch of this series.


Matt

> platforms.
> 
> Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement")
> 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: Matt Roper <matthew.d.roper@intel.com>
> Cc: <stable@vger.kernel.org> # v6.2+
> ---
>  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 50962cfd1353..cf709f6c05ae 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 d67d44611c28..7f42c8015f71 100644
> --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
> +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
> @@ -2988,6 +2988,12 @@ 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
> 

-- 
Matt Roper
Graphics Software Engineer
Linux GPU Platform Enablement
Intel Corporation

Re: [PATCH 2/2] drm/i915/gt: Set default CCS mode '1'

[John Harrison]

On 2/15/2024 05:59, Andi Shyti wrote:
> Since CCS automatic load balancing is disabled, we will impose a
> fixed balancing policy that involves setting all the CCS engines
> to work together on the same load.
>
> Simultaneously, the user will see only 1 CCS rather than the
> actual number. As of now, this change affects only DG2.
These two paragraphs are mutually exclusive. You can't have four CCS 
engines 'working together' if only one engine exists. I think you are 
meaning that we only export 1 CCS engine and that single engine is 
configured to control all the EUs. As opposed to running in 4 CCS engine 
mode where the EUs are (dynamically or statically) divided amongst those 
four engines.

John.

>
> Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement")
> 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: Matt Roper <matthew.d.roper@intel.com>
> Cc: <stable@vger.kernel.org> # v6.2+
> ---
>   drivers/gpu/drm/i915/gt/intel_gt.c      | 11 +++++++++++
>   drivers/gpu/drm/i915/gt/intel_gt_regs.h |  2 ++
>   drivers/gpu/drm/i915/i915_drv.h         | 17 +++++++++++++++++
>   drivers/gpu/drm/i915/i915_query.c       |  5 +++--
>   4 files changed, 33 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
> index a425db5ed3a2..e19df4ef47f6 100644
> --- a/drivers/gpu/drm/i915/gt/intel_gt.c
> +++ b/drivers/gpu/drm/i915/gt/intel_gt.c
> @@ -168,6 +168,14 @@ static void init_unused_rings(struct intel_gt *gt)
>   	}
>   }
>   
> +static void intel_gt_apply_ccs_mode(struct intel_gt *gt)
> +{
> +	if (!IS_DG2(gt->i915))
> +		return;
> +
> +	intel_uncore_write(gt->uncore, XEHP_CCS_MODE, 0);
> +}
> +
>   int intel_gt_init_hw(struct intel_gt *gt)
>   {
>   	struct drm_i915_private *i915 = gt->i915;
> @@ -195,6 +203,9 @@ 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
> diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> index cf709f6c05ae..c148113770ea 100644
> --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> @@ -1605,6 +1605,8 @@
>   #define   GEN12_VOLTAGE_MASK			REG_GENMASK(10, 0)
>   #define   GEN12_CAGF_MASK			REG_GENMASK(19, 11)
>   
> +#define XEHP_CCS_MODE                          _MMIO(0x14804)
> +
>   #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/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index e81b3b2858ac..0853ffd3cb8d 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -396,6 +396,23 @@ static inline struct intel_gt *to_gt(const struct drm_i915_private *i915)
>   	     (engine__); \
>   	     (engine__) = rb_to_uabi_engine(rb_next(&(engine__)->uabi_node)))
>   
> +/*
> + * Exclude unavailable engines.
> + *
> + * Only the first CCS engine is utilized due to the disabling of CCS auto load
> + * balancing. As a result, all CCS engines operate collectively, functioning
> + * essentially as a single CCS engine, hence the count of active CCS engines is
> + * considered '1'.
> + * Currently, this applies to platforms with more than one CCS engine,
> + * specifically DG2.
> + */
> +#define for_each_available_uabi_engine(engine__, i915__) \
> +	for_each_uabi_engine(engine__, i915__) \
> +		if ((IS_DG2(i915__)) && \
> +		    ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
> +		    ((engine__)->uabi_instance)) { } \
> +		else
> +
>   #define INTEL_INFO(i915)	((i915)->__info)
>   #define RUNTIME_INFO(i915)	(&(i915)->__runtime)
>   #define DRIVER_CAPS(i915)	(&(i915)->caps)
> diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
> index fa3e937ed3f5..2d41bda626a6 100644
> --- a/drivers/gpu/drm/i915/i915_query.c
> +++ b/drivers/gpu/drm/i915/i915_query.c
> @@ -124,6 +124,7 @@ static int query_geometry_subslices(struct drm_i915_private *i915,
>   	return fill_topology_info(sseu, query_item, sseu->geometry_subslice_mask);
>   }
>   
> +
>   static int
>   query_engine_info(struct drm_i915_private *i915,
>   		  struct drm_i915_query_item *query_item)
> @@ -140,7 +141,7 @@ query_engine_info(struct drm_i915_private *i915,
>   	if (query_item->flags)
>   		return -EINVAL;
>   
> -	for_each_uabi_engine(engine, i915)
> +	for_each_available_uabi_engine(engine, i915)
>   		num_uabi_engines++;
>   
>   	len = struct_size(query_ptr, engines, num_uabi_engines);
> @@ -155,7 +156,7 @@ query_engine_info(struct drm_i915_private *i915,
>   
>   	info_ptr = &query_ptr->engines[0];
>   
> -	for_each_uabi_engine(engine, i915) {
> +	for_each_available_uabi_engine(engine, i915) {
>   		info.engine.engine_class = engine->uabi_class;
>   		info.engine.engine_instance = engine->uabi_instance;
>   		info.flags = I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE;

Re: [PATCH 2/2] drm/i915/gt: Set default CCS mode '1'

[Andi Shyti]

Hi John,

On Thu, Feb 15, 2024 at 01:23:24PM -0800, John Harrison wrote:
> On 2/15/2024 05:59, Andi Shyti wrote:
> > Since CCS automatic load balancing is disabled, we will impose a
> > fixed balancing policy that involves setting all the CCS engines
> > to work together on the same load.
> > 
> > Simultaneously, the user will see only 1 CCS rather than the
> > actual number. As of now, this change affects only DG2.
> These two paragraphs are mutually exclusive. You can't have four CCS engines
> 'working together' if only one engine exists. I think you are meaning that
> we only export 1 CCS engine and that single engine is configured to control
> all the EUs. As opposed to running in 4 CCS engine mode where the EUs are
> (dynamically or statically) divided amongst those four engines.

The balancing is done statically. The dynamic balancing is
disabled in patch 1.

The 2 or 4 CCS engines will share the same workload.

Because the user won't be able anymore to select the CCS engine
he wants to use, he will see only one CCS.

I think we are saying the same thing using different words :)
I can try in v2 to reword the commit better.

Thanks for looking into this.
Andi

> John.
> 
> > 
> > Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement")
> > 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: Matt Roper <matthew.d.roper@intel.com>
> > Cc: <stable@vger.kernel.org> # v6.2+
> > ---
> >   drivers/gpu/drm/i915/gt/intel_gt.c      | 11 +++++++++++
> >   drivers/gpu/drm/i915/gt/intel_gt_regs.h |  2 ++
> >   drivers/gpu/drm/i915/i915_drv.h         | 17 +++++++++++++++++
> >   drivers/gpu/drm/i915/i915_query.c       |  5 +++--
> >   4 files changed, 33 insertions(+), 2 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
> > index a425db5ed3a2..e19df4ef47f6 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_gt.c
> > +++ b/drivers/gpu/drm/i915/gt/intel_gt.c
> > @@ -168,6 +168,14 @@ static void init_unused_rings(struct intel_gt *gt)
> >   	}
> >   }
> > +static void intel_gt_apply_ccs_mode(struct intel_gt *gt)
> > +{
> > +	if (!IS_DG2(gt->i915))
> > +		return;
> > +
> > +	intel_uncore_write(gt->uncore, XEHP_CCS_MODE, 0);
> > +}
> > +
> >   int intel_gt_init_hw(struct intel_gt *gt)
> >   {
> >   	struct drm_i915_private *i915 = gt->i915;
> > @@ -195,6 +203,9 @@ 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
> > diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> > index cf709f6c05ae..c148113770ea 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> > +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> > @@ -1605,6 +1605,8 @@
> >   #define   GEN12_VOLTAGE_MASK			REG_GENMASK(10, 0)
> >   #define   GEN12_CAGF_MASK			REG_GENMASK(19, 11)
> > +#define XEHP_CCS_MODE                          _MMIO(0x14804)
> > +
> >   #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/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> > index e81b3b2858ac..0853ffd3cb8d 100644
> > --- a/drivers/gpu/drm/i915/i915_drv.h
> > +++ b/drivers/gpu/drm/i915/i915_drv.h
> > @@ -396,6 +396,23 @@ static inline struct intel_gt *to_gt(const struct drm_i915_private *i915)
> >   	     (engine__); \
> >   	     (engine__) = rb_to_uabi_engine(rb_next(&(engine__)->uabi_node)))
> > +/*
> > + * Exclude unavailable engines.
> > + *
> > + * Only the first CCS engine is utilized due to the disabling of CCS auto load
> > + * balancing. As a result, all CCS engines operate collectively, functioning
> > + * essentially as a single CCS engine, hence the count of active CCS engines is
> > + * considered '1'.
> > + * Currently, this applies to platforms with more than one CCS engine,
> > + * specifically DG2.
> > + */
> > +#define for_each_available_uabi_engine(engine__, i915__) \
> > +	for_each_uabi_engine(engine__, i915__) \
> > +		if ((IS_DG2(i915__)) && \
> > +		    ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
> > +		    ((engine__)->uabi_instance)) { } \
> > +		else
> > +
> >   #define INTEL_INFO(i915)	((i915)->__info)
> >   #define RUNTIME_INFO(i915)	(&(i915)->__runtime)
> >   #define DRIVER_CAPS(i915)	(&(i915)->caps)
> > diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
> > index fa3e937ed3f5..2d41bda626a6 100644
> > --- a/drivers/gpu/drm/i915/i915_query.c
> > +++ b/drivers/gpu/drm/i915/i915_query.c
> > @@ -124,6 +124,7 @@ static int query_geometry_subslices(struct drm_i915_private *i915,
> >   	return fill_topology_info(sseu, query_item, sseu->geometry_subslice_mask);
> >   }
> > +
> >   static int
> >   query_engine_info(struct drm_i915_private *i915,
> >   		  struct drm_i915_query_item *query_item)
> > @@ -140,7 +141,7 @@ query_engine_info(struct drm_i915_private *i915,
> >   	if (query_item->flags)
> >   		return -EINVAL;
> > -	for_each_uabi_engine(engine, i915)
> > +	for_each_available_uabi_engine(engine, i915)
> >   		num_uabi_engines++;
> >   	len = struct_size(query_ptr, engines, num_uabi_engines);
> > @@ -155,7 +156,7 @@ query_engine_info(struct drm_i915_private *i915,
> >   	info_ptr = &query_ptr->engines[0];
> > -	for_each_uabi_engine(engine, i915) {
> > +	for_each_available_uabi_engine(engine, i915) {
> >   		info.engine.engine_class = engine->uabi_class;
> >   		info.engine.engine_instance = engine->uabi_instance;
> >   		info.flags = I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE;

Re: [PATCH 2/2] drm/i915/gt: Set default CCS mode '1'

[John Harrison]

On 2/15/2024 14:34, Andi Shyti wrote:
> Hi John,
>
> On Thu, Feb 15, 2024 at 01:23:24PM -0800, John Harrison wrote:
>> On 2/15/2024 05:59, Andi Shyti wrote:
>>> Since CCS automatic load balancing is disabled, we will impose a
>>> fixed balancing policy that involves setting all the CCS engines
>>> to work together on the same load.
>>>
>>> Simultaneously, the user will see only 1 CCS rather than the
>>> actual number. As of now, this change affects only DG2.
>> These two paragraphs are mutually exclusive. You can't have four CCS engines
>> 'working together' if only one engine exists. I think you are meaning that
>> we only export 1 CCS engine and that single engine is configured to control
>> all the EUs. As opposed to running in 4 CCS engine mode where the EUs are
>> (dynamically or statically) divided amongst those four engines.
> The balancing is done statically. The dynamic balancing is
> disabled in patch 1.
>
> The 2 or 4 CCS engines will share the same workload.
But they don't.

In i915, we use 'engine' to refer to a command streamer and all the 
associated hardware. This is distinct from the EUs which sit behind and 
can be driven by one or more command streamers. Saying that multiple 
engines are sharing a workload implies that you are submitting the 
context to multiple command streamers in parallel. I.e. a similar 
process to media frame split where they have a set of LRCA contexts 
bound together which are submitted in parallel to two or more video 
decode engines (VCS0, VCS1, etc.). That is not what is happening here.

Here, you are submitting a single context with a singe ring buffer to a 
single engine - CCS0. That engine is configured to own all EUs. Which 
actually means that submitting a compute task to another CCS engine will 
achieve nothing because there are no EUs available to those other 
engines. They will simply hang when waiting for the walker instruction 
to complete.

>
> Because the user won't be able anymore to select the CCS engine
> he wants to use, he will see only one CCS.
>
> I think we are saying the same thing using different words :)
But words are important.

John.

> I can try in v2 to reword the commit better.
>
> Thanks for looking into this.
> Andi
>
>> John.
>>
>>> Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement")
>>> 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: Matt Roper <matthew.d.roper@intel.com>
>>> Cc: <stable@vger.kernel.org> # v6.2+
>>> ---
>>>    drivers/gpu/drm/i915/gt/intel_gt.c      | 11 +++++++++++
>>>    drivers/gpu/drm/i915/gt/intel_gt_regs.h |  2 ++
>>>    drivers/gpu/drm/i915/i915_drv.h         | 17 +++++++++++++++++
>>>    drivers/gpu/drm/i915/i915_query.c       |  5 +++--
>>>    4 files changed, 33 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
>>> index a425db5ed3a2..e19df4ef47f6 100644
>>> --- a/drivers/gpu/drm/i915/gt/intel_gt.c
>>> +++ b/drivers/gpu/drm/i915/gt/intel_gt.c
>>> @@ -168,6 +168,14 @@ static void init_unused_rings(struct intel_gt *gt)
>>>    	}
>>>    }
>>> +static void intel_gt_apply_ccs_mode(struct intel_gt *gt)
>>> +{
>>> +	if (!IS_DG2(gt->i915))
>>> +		return;
>>> +
>>> +	intel_uncore_write(gt->uncore, XEHP_CCS_MODE, 0);
>>> +}
>>> +
>>>    int intel_gt_init_hw(struct intel_gt *gt)
>>>    {
>>>    	struct drm_i915_private *i915 = gt->i915;
>>> @@ -195,6 +203,9 @@ 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
>>> diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
>>> index cf709f6c05ae..c148113770ea 100644
>>> --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
>>> +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
>>> @@ -1605,6 +1605,8 @@
>>>    #define   GEN12_VOLTAGE_MASK			REG_GENMASK(10, 0)
>>>    #define   GEN12_CAGF_MASK			REG_GENMASK(19, 11)
>>> +#define XEHP_CCS_MODE                          _MMIO(0x14804)
>>> +
>>>    #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/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
>>> index e81b3b2858ac..0853ffd3cb8d 100644
>>> --- a/drivers/gpu/drm/i915/i915_drv.h
>>> +++ b/drivers/gpu/drm/i915/i915_drv.h
>>> @@ -396,6 +396,23 @@ static inline struct intel_gt *to_gt(const struct drm_i915_private *i915)
>>>    	     (engine__); \
>>>    	     (engine__) = rb_to_uabi_engine(rb_next(&(engine__)->uabi_node)))
>>> +/*
>>> + * Exclude unavailable engines.
>>> + *
>>> + * Only the first CCS engine is utilized due to the disabling of CCS auto load
>>> + * balancing. As a result, all CCS engines operate collectively, functioning
>>> + * essentially as a single CCS engine, hence the count of active CCS engines is
>>> + * considered '1'.
>>> + * Currently, this applies to platforms with more than one CCS engine,
>>> + * specifically DG2.
>>> + */
>>> +#define for_each_available_uabi_engine(engine__, i915__) \
>>> +	for_each_uabi_engine(engine__, i915__) \
>>> +		if ((IS_DG2(i915__)) && \
>>> +		    ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
>>> +		    ((engine__)->uabi_instance)) { } \
>>> +		else
>>> +
>>>    #define INTEL_INFO(i915)	((i915)->__info)
>>>    #define RUNTIME_INFO(i915)	(&(i915)->__runtime)
>>>    #define DRIVER_CAPS(i915)	(&(i915)->caps)
>>> diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
>>> index fa3e937ed3f5..2d41bda626a6 100644
>>> --- a/drivers/gpu/drm/i915/i915_query.c
>>> +++ b/drivers/gpu/drm/i915/i915_query.c
>>> @@ -124,6 +124,7 @@ static int query_geometry_subslices(struct drm_i915_private *i915,
>>>    	return fill_topology_info(sseu, query_item, sseu->geometry_subslice_mask);
>>>    }
>>> +
>>>    static int
>>>    query_engine_info(struct drm_i915_private *i915,
>>>    		  struct drm_i915_query_item *query_item)
>>> @@ -140,7 +141,7 @@ query_engine_info(struct drm_i915_private *i915,
>>>    	if (query_item->flags)
>>>    		return -EINVAL;
>>> -	for_each_uabi_engine(engine, i915)
>>> +	for_each_available_uabi_engine(engine, i915)
>>>    		num_uabi_engines++;
>>>    	len = struct_size(query_ptr, engines, num_uabi_engines);
>>> @@ -155,7 +156,7 @@ query_engine_info(struct drm_i915_private *i915,
>>>    	info_ptr = &query_ptr->engines[0];
>>> -	for_each_uabi_engine(engine, i915) {
>>> +	for_each_available_uabi_engine(engine, i915) {
>>>    		info.engine.engine_class = engine->uabi_class;
>>>    		info.engine.engine_instance = engine->uabi_instance;
>>>    		info.flags = I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE;

Re: [PATCH 1/2] drm/i915/gt: Disable HW load balancing for CCS

[Andi Shyti]

Hi Matt,

On Thu, Feb 15, 2024 at 08:55:41AM -0800, Matt Roper wrote:
> On Thu, Feb 15, 2024 at 02:59:23PM +0100, Andi Shyti wrote:
> > The hardware should not dynamically balance the load between CCS
> > engines. Wa_16016805146 recommends disabling it across all
> 
> Is this the right workaround number?  When I check the database, this
> workaround was rejected on both DG2-G10 and DG2-G11, and doesn't even
> have an entry for DG2-G12.
> 
> There are other workarounds that sound somewhat related to load
> balancing (e.g., part 3 of Wa_14019159160), but what's asked there is
> more involved than just setting one register bit and conflicts a bit
> with the second patch of this series.

thanks for checking it. Indeed the WA I mentioned is limited to
a specific platform. This recommendation comes in different WA,
e.g. this one: Wa_14019186972 (3rd point). Will start using that
as a reference.

Thank you.
Andi

> 
> 
> Matt
> 
> > platforms.
> > 
> > Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement")
> > 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: Matt Roper <matthew.d.roper@intel.com>
> > Cc: <stable@vger.kernel.org> # v6.2+
> > ---
> >  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 50962cfd1353..cf709f6c05ae 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 d67d44611c28..7f42c8015f71 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
> > +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
> > @@ -2988,6 +2988,12 @@ 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
> > 
> 
> -- 
> Matt Roper
> Graphics Software Engineer
> Linux GPU Platform Enablement
> Intel Corporation

Re: [PATCH 1/2] drm/i915/gt: Disable HW load balancing for CCS

[Andi Shyti]

On Mon, Feb 19, 2024 at 11:17:33AM +0100, Andi Shyti wrote:
> On Thu, Feb 15, 2024 at 08:55:41AM -0800, Matt Roper wrote:
> > On Thu, Feb 15, 2024 at 02:59:23PM +0100, Andi Shyti wrote:
> > > The hardware should not dynamically balance the load between CCS
> > > engines. Wa_16016805146 recommends disabling it across all
> > 
> > Is this the right workaround number?  When I check the database, this
> > workaround was rejected on both DG2-G10 and DG2-G11, and doesn't even
> > have an entry for DG2-G12.
> > 
> > There are other workarounds that sound somewhat related to load
> > balancing (e.g., part 3 of Wa_14019159160), but what's asked there is
> > more involved than just setting one register bit and conflicts a bit
> > with the second patch of this series.
> 
> thanks for checking it. Indeed the WA I mentioned is limited to
> a specific platform. This recommendation comes in different WA,
> e.g. this one: Wa_14019186972 (3rd point). Will start using that
> as a reference.

actually you are right, I checked with Joonas and I will use
Wa_14019159160.

Thanks,
Andi

Re: [PATCH 2/2] drm/i915/gt: Set default CCS mode '1'

[Tvrtko Ursulin]

On 15/02/2024 13:59, Andi Shyti wrote:
> Since CCS automatic load balancing is disabled, we will impose a
> fixed balancing policy that involves setting all the CCS engines
> to work together on the same load.
> 
> Simultaneously, the user will see only 1 CCS rather than the
> actual number. As of now, this change affects only DG2.
> 
> Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement")
> 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: Matt Roper <matthew.d.roper@intel.com>
> Cc: <stable@vger.kernel.org> # v6.2+
> ---
>   drivers/gpu/drm/i915/gt/intel_gt.c      | 11 +++++++++++
>   drivers/gpu/drm/i915/gt/intel_gt_regs.h |  2 ++
>   drivers/gpu/drm/i915/i915_drv.h         | 17 +++++++++++++++++
>   drivers/gpu/drm/i915/i915_query.c       |  5 +++--
>   4 files changed, 33 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
> index a425db5ed3a2..e19df4ef47f6 100644
> --- a/drivers/gpu/drm/i915/gt/intel_gt.c
> +++ b/drivers/gpu/drm/i915/gt/intel_gt.c
> @@ -168,6 +168,14 @@ static void init_unused_rings(struct intel_gt *gt)
>   	}
>   }
>   
> +static void intel_gt_apply_ccs_mode(struct intel_gt *gt)
> +{
> +	if (!IS_DG2(gt->i915))
> +		return;
> +
> +	intel_uncore_write(gt->uncore, XEHP_CCS_MODE, 0);
> +}
> +
>   int intel_gt_init_hw(struct intel_gt *gt)
>   {
>   	struct drm_i915_private *i915 = gt->i915;
> @@ -195,6 +203,9 @@ 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
> diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> index cf709f6c05ae..c148113770ea 100644
> --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> @@ -1605,6 +1605,8 @@
>   #define   GEN12_VOLTAGE_MASK			REG_GENMASK(10, 0)
>   #define   GEN12_CAGF_MASK			REG_GENMASK(19, 11)
>   
> +#define XEHP_CCS_MODE                          _MMIO(0x14804)
> +
>   #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/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index e81b3b2858ac..0853ffd3cb8d 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -396,6 +396,23 @@ static inline struct intel_gt *to_gt(const struct drm_i915_private *i915)
>   	     (engine__); \
>   	     (engine__) = rb_to_uabi_engine(rb_next(&(engine__)->uabi_node)))
>   
> +/*
> + * Exclude unavailable engines.
> + *
> + * Only the first CCS engine is utilized due to the disabling of CCS auto load
> + * balancing. As a result, all CCS engines operate collectively, functioning
> + * essentially as a single CCS engine, hence the count of active CCS engines is
> + * considered '1'.
> + * Currently, this applies to platforms with more than one CCS engine,
> + * specifically DG2.
> + */
> +#define for_each_available_uabi_engine(engine__, i915__) \
> +	for_each_uabi_engine(engine__, i915__) \
> +		if ((IS_DG2(i915__)) && \
> +		    ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
> +		    ((engine__)->uabi_instance)) { } \
> +		else
> +

If you don't want userspace to see some engines, just don't add them to 
the uabi list in intel_engines_driver_register or thereabouts?

Similar as we do for gsc which uses I915_NO_UABI_CLASS, although for ccs 
you can choose a different approach, whatever is more elegant.

That is also needed for i915->engine_uabi_class_count to be right, so 
userspace stats which rely on it are correct.

Regards,

Tvrtko

>   #define INTEL_INFO(i915)	((i915)->__info)
>   #define RUNTIME_INFO(i915)	(&(i915)->__runtime)
>   #define DRIVER_CAPS(i915)	(&(i915)->caps)
> diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
> index fa3e937ed3f5..2d41bda626a6 100644
> --- a/drivers/gpu/drm/i915/i915_query.c
> +++ b/drivers/gpu/drm/i915/i915_query.c
> @@ -124,6 +124,7 @@ static int query_geometry_subslices(struct drm_i915_private *i915,
>   	return fill_topology_info(sseu, query_item, sseu->geometry_subslice_mask);
>   }
>   
> +
>   static int
>   query_engine_info(struct drm_i915_private *i915,
>   		  struct drm_i915_query_item *query_item)
> @@ -140,7 +141,7 @@ query_engine_info(struct drm_i915_private *i915,
>   	if (query_item->flags)
>   		return -EINVAL;
>   
> -	for_each_uabi_engine(engine, i915)
> +	for_each_available_uabi_engine(engine, i915)
>   		num_uabi_engines++;
>   
>   	len = struct_size(query_ptr, engines, num_uabi_engines);
> @@ -155,7 +156,7 @@ query_engine_info(struct drm_i915_private *i915,
>   
>   	info_ptr = &query_ptr->engines[0];
>   
> -	for_each_uabi_engine(engine, i915) {
> +	for_each_available_uabi_engine(engine, i915) {
>   		info.engine.engine_class = engine->uabi_class;
>   		info.engine.engine_instance = engine->uabi_instance;
>   		info.flags = I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE;

Re: [PATCH 2/2] drm/i915/gt: Set default CCS mode '1'

[Tvrtko Ursulin]

On 19/02/2024 11:16, Tvrtko Ursulin wrote:
> 
> On 15/02/2024 13:59, Andi Shyti wrote:
>> Since CCS automatic load balancing is disabled, we will impose a
>> fixed balancing policy that involves setting all the CCS engines
>> to work together on the same load.
>>
>> Simultaneously, the user will see only 1 CCS rather than the
>> actual number. As of now, this change affects only DG2.
>>
>> Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement")
>> 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: Matt Roper <matthew.d.roper@intel.com>
>> Cc: <stable@vger.kernel.org> # v6.2+
>> ---
>>   drivers/gpu/drm/i915/gt/intel_gt.c      | 11 +++++++++++
>>   drivers/gpu/drm/i915/gt/intel_gt_regs.h |  2 ++
>>   drivers/gpu/drm/i915/i915_drv.h         | 17 +++++++++++++++++
>>   drivers/gpu/drm/i915/i915_query.c       |  5 +++--
>>   4 files changed, 33 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c 
>> b/drivers/gpu/drm/i915/gt/intel_gt.c
>> index a425db5ed3a2..e19df4ef47f6 100644
>> --- a/drivers/gpu/drm/i915/gt/intel_gt.c
>> +++ b/drivers/gpu/drm/i915/gt/intel_gt.c
>> @@ -168,6 +168,14 @@ static void init_unused_rings(struct intel_gt *gt)
>>       }
>>   }
>> +static void intel_gt_apply_ccs_mode(struct intel_gt *gt)
>> +{
>> +    if (!IS_DG2(gt->i915))
>> +        return;
>> +
>> +    intel_uncore_write(gt->uncore, XEHP_CCS_MODE, 0);
>> +}
>> +
>>   int intel_gt_init_hw(struct intel_gt *gt)
>>   {
>>       struct drm_i915_private *i915 = gt->i915;
>> @@ -195,6 +203,9 @@ 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
>> diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h 
>> b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
>> index cf709f6c05ae..c148113770ea 100644
>> --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
>> +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
>> @@ -1605,6 +1605,8 @@
>>   #define   GEN12_VOLTAGE_MASK            REG_GENMASK(10, 0)
>>   #define   GEN12_CAGF_MASK            REG_GENMASK(19, 11)
>> +#define XEHP_CCS_MODE                          _MMIO(0x14804)
>> +
>>   #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/i915_drv.h 
>> b/drivers/gpu/drm/i915/i915_drv.h
>> index e81b3b2858ac..0853ffd3cb8d 100644
>> --- a/drivers/gpu/drm/i915/i915_drv.h
>> +++ b/drivers/gpu/drm/i915/i915_drv.h
>> @@ -396,6 +396,23 @@ static inline struct intel_gt *to_gt(const struct 
>> drm_i915_private *i915)
>>            (engine__); \
>>            (engine__) = 
>> rb_to_uabi_engine(rb_next(&(engine__)->uabi_node)))
>> +/*
>> + * Exclude unavailable engines.
>> + *
>> + * Only the first CCS engine is utilized due to the disabling of CCS 
>> auto load
>> + * balancing. As a result, all CCS engines operate collectively, 
>> functioning
>> + * essentially as a single CCS engine, hence the count of active CCS 
>> engines is
>> + * considered '1'.
>> + * Currently, this applies to platforms with more than one CCS engine,
>> + * specifically DG2.
>> + */
>> +#define for_each_available_uabi_engine(engine__, i915__) \
>> +    for_each_uabi_engine(engine__, i915__) \
>> +        if ((IS_DG2(i915__)) && \
>> +            ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
>> +            ((engine__)->uabi_instance)) { } \
>> +        else
>> +
> 
> If you don't want userspace to see some engines, just don't add them to 
> the uabi list in intel_engines_driver_register or thereabouts?
> 
> Similar as we do for gsc which uses I915_NO_UABI_CLASS, although for ccs 
> you can choose a different approach, whatever is more elegant.
> 
> That is also needed for i915->engine_uabi_class_count to be right, so 
> userspace stats which rely on it are correct.

I later realized it is more than that - everything that uses 
intel_engine_lookup_user to look up class instance passed in from 
userspace relies on the engine not being on the user list otherwise 
userspace could bypass the fact engine query does not list it. Like PMU, 
Perf/POA, context engine map and SSEU context query.

Regards,

Tvrtko

> 
> Regards,
> 
> Tvrtko
> 
>>   #define INTEL_INFO(i915)    ((i915)->__info)
>>   #define RUNTIME_INFO(i915)    (&(i915)->__runtime)
>>   #define DRIVER_CAPS(i915)    (&(i915)->caps)
>> diff --git a/drivers/gpu/drm/i915/i915_query.c 
>> b/drivers/gpu/drm/i915/i915_query.c
>> index fa3e937ed3f5..2d41bda626a6 100644
>> --- a/drivers/gpu/drm/i915/i915_query.c
>> +++ b/drivers/gpu/drm/i915/i915_query.c
>> @@ -124,6 +124,7 @@ static int query_geometry_subslices(struct 
>> drm_i915_private *i915,
>>       return fill_topology_info(sseu, query_item, 
>> sseu->geometry_subslice_mask);
>>   }
>> +
>>   static int
>>   query_engine_info(struct drm_i915_private *i915,
>>             struct drm_i915_query_item *query_item)
>> @@ -140,7 +141,7 @@ query_engine_info(struct drm_i915_private *i915,
>>       if (query_item->flags)
>>           return -EINVAL;
>> -    for_each_uabi_engine(engine, i915)
>> +    for_each_available_uabi_engine(engine, i915)
>>           num_uabi_engines++;
>>       len = struct_size(query_ptr, engines, num_uabi_engines);
>> @@ -155,7 +156,7 @@ query_engine_info(struct drm_i915_private *i915,
>>       info_ptr = &query_ptr->engines[0];
>> -    for_each_uabi_engine(engine, i915) {
>> +    for_each_available_uabi_engine(engine, i915) {
>>           info.engine.engine_class = engine->uabi_class;
>>           info.engine.engine_instance = engine->uabi_instance;
>>           info.flags = I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE;

Re: [PATCH 2/2] drm/i915/gt: Set default CCS mode '1'

[Andi Shyti]

Hi Tvrtko,

On Mon, Feb 19, 2024 at 12:51:44PM +0000, Tvrtko Ursulin wrote:
> On 19/02/2024 11:16, Tvrtko Ursulin wrote:
> > On 15/02/2024 13:59, Andi Shyti wrote:

...

> > > +/*
> > > + * Exclude unavailable engines.
> > > + *
> > > + * Only the first CCS engine is utilized due to the disabling of
> > > CCS auto load
> > > + * balancing. As a result, all CCS engines operate collectively,
> > > functioning
> > > + * essentially as a single CCS engine, hence the count of active
> > > CCS engines is
> > > + * considered '1'.
> > > + * Currently, this applies to platforms with more than one CCS engine,
> > > + * specifically DG2.
> > > + */
> > > +#define for_each_available_uabi_engine(engine__, i915__) \
> > > +    for_each_uabi_engine(engine__, i915__) \
> > > +        if ((IS_DG2(i915__)) && \
> > > +            ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
> > > +            ((engine__)->uabi_instance)) { } \
> > > +        else
> > > +
> > 
> > If you don't want userspace to see some engines, just don't add them to
> > the uabi list in intel_engines_driver_register or thereabouts?

It will be dynamic. In next series I am preparing the user will
be able to increase the number of CCS engines he wants to use.

> > Similar as we do for gsc which uses I915_NO_UABI_CLASS, although for ccs
> > you can choose a different approach, whatever is more elegant.
> > 
> > That is also needed for i915->engine_uabi_class_count to be right, so
> > userspace stats which rely on it are correct.

Oh yes. Will update it.

> I later realized it is more than that - everything that uses
> intel_engine_lookup_user to look up class instance passed in from userspace
> relies on the engine not being on the user list otherwise userspace could
> bypass the fact engine query does not list it. Like PMU, Perf/POA, context
> engine map and SSEU context query.

Correct, will look into that, thank you!

Andi

Re: [PATCH 2/2] drm/i915/gt: Set default CCS mode '1'

[Tvrtko Ursulin]

On 20/02/2024 10:11, Andi Shyti wrote:
> Hi Tvrtko,
> 
> On Mon, Feb 19, 2024 at 12:51:44PM +0000, Tvrtko Ursulin wrote:
>> On 19/02/2024 11:16, Tvrtko Ursulin wrote:
>>> On 15/02/2024 13:59, Andi Shyti wrote:
> 
> ...
> 
>>>> +/*
>>>> + * Exclude unavailable engines.
>>>> + *
>>>> + * Only the first CCS engine is utilized due to the disabling of
>>>> CCS auto load
>>>> + * balancing. As a result, all CCS engines operate collectively,
>>>> functioning
>>>> + * essentially as a single CCS engine, hence the count of active
>>>> CCS engines is
>>>> + * considered '1'.
>>>> + * Currently, this applies to platforms with more than one CCS engine,
>>>> + * specifically DG2.
>>>> + */
>>>> +#define for_each_available_uabi_engine(engine__, i915__) \
>>>> +    for_each_uabi_engine(engine__, i915__) \
>>>> +        if ((IS_DG2(i915__)) && \
>>>> +            ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
>>>> +            ((engine__)->uabi_instance)) { } \
>>>> +        else
>>>> +
>>>
>>> If you don't want userspace to see some engines, just don't add them to
>>> the uabi list in intel_engines_driver_register or thereabouts?
> 
> It will be dynamic. In next series I am preparing the user will
> be able to increase the number of CCS engines he wants to use.

Oh tricky and new. Does it need to be at runtime or could be boot time?

If you are aiming to make the static single CCS only into the 6.9 
release, and you feel running out of time, you could always do a simple 
solution for now. The one I mentioned of simply not registering on the 
uabi list. Then you can refine more leisurely for the next release.

Regards,

Tvrtko

> 
>>> Similar as we do for gsc which uses I915_NO_UABI_CLASS, although for ccs
>>> you can choose a different approach, whatever is more elegant.
>>>
>>> That is also needed for i915->engine_uabi_class_count to be right, so
>>> userspace stats which rely on it are correct.
> 
> Oh yes. Will update it.
> 
>> I later realized it is more than that - everything that uses
>> intel_engine_lookup_user to look up class instance passed in from userspace
>> relies on the engine not being on the user list otherwise userspace could
>> bypass the fact engine query does not list it. Like PMU, Perf/POA, context
>> engine map and SSEU context query.
> 
> Correct, will look into that, thank you!
> 
> Andi

Re: [PATCH 2/2] drm/i915/gt: Set default CCS mode '1'

[Andi Shyti]

On Tue, Feb 20, 2024 at 11:15:05AM +0000, Tvrtko Ursulin wrote:
> On 20/02/2024 10:11, Andi Shyti wrote:
> > On Mon, Feb 19, 2024 at 12:51:44PM +0000, Tvrtko Ursulin wrote:
> > > On 19/02/2024 11:16, Tvrtko Ursulin wrote:
> > > > On 15/02/2024 13:59, Andi Shyti wrote:
> > 
> > ...
> > 
> > > > > +/*
> > > > > + * Exclude unavailable engines.
> > > > > + *
> > > > > + * Only the first CCS engine is utilized due to the disabling of
> > > > > CCS auto load
> > > > > + * balancing. As a result, all CCS engines operate collectively,
> > > > > functioning
> > > > > + * essentially as a single CCS engine, hence the count of active
> > > > > CCS engines is
> > > > > + * considered '1'.
> > > > > + * Currently, this applies to platforms with more than one CCS engine,
> > > > > + * specifically DG2.
> > > > > + */
> > > > > +#define for_each_available_uabi_engine(engine__, i915__) \
> > > > > +    for_each_uabi_engine(engine__, i915__) \
> > > > > +        if ((IS_DG2(i915__)) && \
> > > > > +            ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
> > > > > +            ((engine__)->uabi_instance)) { } \
> > > > > +        else
> > > > > +
> > > > 
> > > > If you don't want userspace to see some engines, just don't add them to
> > > > the uabi list in intel_engines_driver_register or thereabouts?
> > 
> > It will be dynamic. In next series I am preparing the user will
> > be able to increase the number of CCS engines he wants to use.
> 
> Oh tricky and new. Does it need to be at runtime or could be boot time?

At boot time the CCS mode has to be set to '1', i.e. only one CCS
will be visible to the user. Then, during the normal execution of
the driver, the user can decide to change the mode and therefore
we would need to expose more than one CCS engine.

> If you are aiming to make the static single CCS only into the 6.9 release,
> and you feel running out of time, you could always do a simple solution for
> now. The one I mentioned of simply not registering on the uabi list. Then
> you can refine more leisurely for the next release.

Thanks. I started working on a dynamic rebuilt of the
uabi_engines, but in this series it wouldn't fit.

I will add the limitation during the list creation.

Thanks a lot,
Andi

Re: [PATCH 2/2] drm/i915/gt: Set default CCS mode '1'

[Andi Shyti]

Hi Jani,

thanks, there has been a v2 after this and your comments have
been addressed somehow.

There will be a v3, as well.

Thanks,
Andi

On Tue, Feb 27, 2024 at 02:18:01PM +0200, Jani Nikula wrote:
> On Tue, 20 Feb 2024, Andi Shyti <andi.shyti@linux.intel.com> wrote:
> > Since CCS automatic load balancing is disabled, we will impose a
> > fixed balancing policy that involves setting all the CCS engines
> > to work together on the same load.
> >
> > Simultaneously, the user will see only 1 CCS rather than the
> > actual number. As of now, this change affects only DG2.
> >
> > Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement")
> > 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: Matt Roper <matthew.d.roper@intel.com>
> > Cc: <stable@vger.kernel.org> # v6.2+
> > ---
> >  drivers/gpu/drm/i915/gt/intel_gt.c      | 11 +++++++++++
> >  drivers/gpu/drm/i915/gt/intel_gt_regs.h |  2 ++
> >  drivers/gpu/drm/i915/i915_drv.h         | 17 +++++++++++++++++
> >  drivers/gpu/drm/i915/i915_query.c       |  5 +++--
> >  4 files changed, 33 insertions(+), 2 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
> > index a425db5ed3a2..e19df4ef47f6 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_gt.c
> > +++ b/drivers/gpu/drm/i915/gt/intel_gt.c
> > @@ -168,6 +168,14 @@ static void init_unused_rings(struct intel_gt *gt)
> >  	}
> >  }
> >  
> > +static void intel_gt_apply_ccs_mode(struct intel_gt *gt)
> > +{
> > +	if (!IS_DG2(gt->i915))
> > +		return;
> > +
> > +	intel_uncore_write(gt->uncore, XEHP_CCS_MODE, 0);
> > +}
> > +
> >  int intel_gt_init_hw(struct intel_gt *gt)
> >  {
> >  	struct drm_i915_private *i915 = gt->i915;
> > @@ -195,6 +203,9 @@ 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
> > diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> > index cf709f6c05ae..c148113770ea 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> > +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> > @@ -1605,6 +1605,8 @@
> >  #define   GEN12_VOLTAGE_MASK			REG_GENMASK(10, 0)
> >  #define   GEN12_CAGF_MASK			REG_GENMASK(19, 11)
> >  
> > +#define XEHP_CCS_MODE                          _MMIO(0x14804)
> > +
> >  #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/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> > index e81b3b2858ac..0853ffd3cb8d 100644
> > --- a/drivers/gpu/drm/i915/i915_drv.h
> > +++ b/drivers/gpu/drm/i915/i915_drv.h
> > @@ -396,6 +396,23 @@ static inline struct intel_gt *to_gt(const struct drm_i915_private *i915)
> >  	     (engine__); \
> >  	     (engine__) = rb_to_uabi_engine(rb_next(&(engine__)->uabi_node)))
> >  
> > +/*
> > + * Exclude unavailable engines.
> > + *
> > + * Only the first CCS engine is utilized due to the disabling of CCS auto load
> > + * balancing. As a result, all CCS engines operate collectively, functioning
> > + * essentially as a single CCS engine, hence the count of active CCS engines is
> > + * considered '1'.
> > + * Currently, this applies to platforms with more than one CCS engine,
> > + * specifically DG2.
> > + */
> > +#define for_each_available_uabi_engine(engine__, i915__) \
> 
> Hrmh, I've been trying to pester folks to move the existing engine
> iterator macros away from i915_drv.h, so not happy to see more.
> 
> But since this is Cc: stable, better do that in a follow-up. Please?
> 
> > +	for_each_uabi_engine(engine__, i915__) \
> > +		if ((IS_DG2(i915__)) && \
> > +		    ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
> > +		    ((engine__)->uabi_instance)) { } \
> > +		else
> 
> We have for_each_if for this.
> 
> > +
> >  #define INTEL_INFO(i915)	((i915)->__info)
> >  #define RUNTIME_INFO(i915)	(&(i915)->__runtime)
> >  #define DRIVER_CAPS(i915)	(&(i915)->caps)
> > diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
> > index fa3e937ed3f5..2d41bda626a6 100644
> > --- a/drivers/gpu/drm/i915/i915_query.c
> > +++ b/drivers/gpu/drm/i915/i915_query.c
> > @@ -124,6 +124,7 @@ static int query_geometry_subslices(struct drm_i915_private *i915,
> >  	return fill_topology_info(sseu, query_item, sseu->geometry_subslice_mask);
> >  }
> >  
> > +
> 
> Superfluous newline change.
> 
> >  static int
> >  query_engine_info(struct drm_i915_private *i915,
> >  		  struct drm_i915_query_item *query_item)
> > @@ -140,7 +141,7 @@ query_engine_info(struct drm_i915_private *i915,
> >  	if (query_item->flags)
> >  		return -EINVAL;
> >  
> > -	for_each_uabi_engine(engine, i915)
> > +	for_each_available_uabi_engine(engine, i915)
> >  		num_uabi_engines++;
> >  
> >  	len = struct_size(query_ptr, engines, num_uabi_engines);
> > @@ -155,7 +156,7 @@ query_engine_info(struct drm_i915_private *i915,
> >  
> >  	info_ptr = &query_ptr->engines[0];
> >  
> > -	for_each_uabi_engine(engine, i915) {
> > +	for_each_available_uabi_engine(engine, i915) {
> >  		info.engine.engine_class = engine->uabi_class;
> >  		info.engine.engine_instance = engine->uabi_instance;
> >  		info.flags = I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE;
> 
> -- 
> Jani Nikula, Intel

Re: [PATCH 2/2] drm/i915/gt: Set default CCS mode '1'

[Jani Nikula]

On Tue, 20 Feb 2024, Andi Shyti <andi.shyti@linux.intel.com> wrote:
> Since CCS automatic load balancing is disabled, we will impose a
> fixed balancing policy that involves setting all the CCS engines
> to work together on the same load.
>
> Simultaneously, the user will see only 1 CCS rather than the
> actual number. As of now, this change affects only DG2.
>
> Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement")
> 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: Matt Roper <matthew.d.roper@intel.com>
> Cc: <stable@vger.kernel.org> # v6.2+
> ---
>  drivers/gpu/drm/i915/gt/intel_gt.c      | 11 +++++++++++
>  drivers/gpu/drm/i915/gt/intel_gt_regs.h |  2 ++
>  drivers/gpu/drm/i915/i915_drv.h         | 17 +++++++++++++++++
>  drivers/gpu/drm/i915/i915_query.c       |  5 +++--
>  4 files changed, 33 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
> index a425db5ed3a2..e19df4ef47f6 100644
> --- a/drivers/gpu/drm/i915/gt/intel_gt.c
> +++ b/drivers/gpu/drm/i915/gt/intel_gt.c
> @@ -168,6 +168,14 @@ static void init_unused_rings(struct intel_gt *gt)
>  	}
>  }
>  
> +static void intel_gt_apply_ccs_mode(struct intel_gt *gt)
> +{
> +	if (!IS_DG2(gt->i915))
> +		return;
> +
> +	intel_uncore_write(gt->uncore, XEHP_CCS_MODE, 0);
> +}
> +
>  int intel_gt_init_hw(struct intel_gt *gt)
>  {
>  	struct drm_i915_private *i915 = gt->i915;
> @@ -195,6 +203,9 @@ 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
> diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> index cf709f6c05ae..c148113770ea 100644
> --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> @@ -1605,6 +1605,8 @@
>  #define   GEN12_VOLTAGE_MASK			REG_GENMASK(10, 0)
>  #define   GEN12_CAGF_MASK			REG_GENMASK(19, 11)
>  
> +#define XEHP_CCS_MODE                          _MMIO(0x14804)
> +
>  #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/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index e81b3b2858ac..0853ffd3cb8d 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -396,6 +396,23 @@ static inline struct intel_gt *to_gt(const struct drm_i915_private *i915)
>  	     (engine__); \
>  	     (engine__) = rb_to_uabi_engine(rb_next(&(engine__)->uabi_node)))
>  
> +/*
> + * Exclude unavailable engines.
> + *
> + * Only the first CCS engine is utilized due to the disabling of CCS auto load
> + * balancing. As a result, all CCS engines operate collectively, functioning
> + * essentially as a single CCS engine, hence the count of active CCS engines is
> + * considered '1'.
> + * Currently, this applies to platforms with more than one CCS engine,
> + * specifically DG2.
> + */
> +#define for_each_available_uabi_engine(engine__, i915__) \

Hrmh, I've been trying to pester folks to move the existing engine
iterator macros away from i915_drv.h, so not happy to see more.

But since this is Cc: stable, better do that in a follow-up. Please?

> +	for_each_uabi_engine(engine__, i915__) \
> +		if ((IS_DG2(i915__)) && \
> +		    ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
> +		    ((engine__)->uabi_instance)) { } \
> +		else

We have for_each_if for this.

> +
>  #define INTEL_INFO(i915)	((i915)->__info)
>  #define RUNTIME_INFO(i915)	(&(i915)->__runtime)
>  #define DRIVER_CAPS(i915)	(&(i915)->caps)
> diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
> index fa3e937ed3f5..2d41bda626a6 100644
> --- a/drivers/gpu/drm/i915/i915_query.c
> +++ b/drivers/gpu/drm/i915/i915_query.c
> @@ -124,6 +124,7 @@ static int query_geometry_subslices(struct drm_i915_private *i915,
>  	return fill_topology_info(sseu, query_item, sseu->geometry_subslice_mask);
>  }
>  
> +

Superfluous newline change.

>  static int
>  query_engine_info(struct drm_i915_private *i915,
>  		  struct drm_i915_query_item *query_item)
> @@ -140,7 +141,7 @@ query_engine_info(struct drm_i915_private *i915,
>  	if (query_item->flags)
>  		return -EINVAL;
>  
> -	for_each_uabi_engine(engine, i915)
> +	for_each_available_uabi_engine(engine, i915)
>  		num_uabi_engines++;
>  
>  	len = struct_size(query_ptr, engines, num_uabi_engines);
> @@ -155,7 +156,7 @@ query_engine_info(struct drm_i915_private *i915,
>  
>  	info_ptr = &query_ptr->engines[0];
>  
> -	for_each_uabi_engine(engine, i915) {
> +	for_each_available_uabi_engine(engine, i915) {
>  		info.engine.engine_class = engine->uabi_class;
>  		info.engine.engine_instance = engine->uabi_instance;
>  		info.flags = I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE;

-- 
Jani Nikula, Intel

Re: [PATCH 2/2] drm/i915/gt: Set default CCS mode '1'

[Andi Shyti]

On Tue, Feb 20, 2024 at 02:27:07PM +0000, Tvrtko Ursulin wrote:
> 
> On 20/02/2024 14:20, Andi Shyti wrote:
> > Since CCS automatic load balancing is disabled, we will impose a
> > fixed balancing policy that involves setting all the CCS engines
> > to work together on the same load.
> 
> Erm *all* CSS engines work together..
> 
> > Simultaneously, the user will see only 1 CCS rather than the
> > actual number. As of now, this change affects only DG2.
> 
> ... *one* CCS engine.

ops... I sent V1 again!

Sorry, I will send v2 now

Thanks!

Andi

Re: [PATCH 2/2] drm/i915/gt: Set default CCS mode '1'

[Tvrtko Ursulin]

On 20/02/2024 14:20, Andi Shyti wrote:
> Since CCS automatic load balancing is disabled, we will impose a
> fixed balancing policy that involves setting all the CCS engines
> to work together on the same load.

Erm *all* CSS engines work together..

> Simultaneously, the user will see only 1 CCS rather than the
> actual number. As of now, this change affects only DG2.

... *one* CCS engine.

> 
> Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement")
> 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: Matt Roper <matthew.d.roper@intel.com>
> Cc: <stable@vger.kernel.org> # v6.2+
> ---
>   drivers/gpu/drm/i915/gt/intel_gt.c      | 11 +++++++++++
>   drivers/gpu/drm/i915/gt/intel_gt_regs.h |  2 ++
>   drivers/gpu/drm/i915/i915_drv.h         | 17 +++++++++++++++++
>   drivers/gpu/drm/i915/i915_query.c       |  5 +++--
>   4 files changed, 33 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
> index a425db5ed3a2..e19df4ef47f6 100644
> --- a/drivers/gpu/drm/i915/gt/intel_gt.c
> +++ b/drivers/gpu/drm/i915/gt/intel_gt.c
> @@ -168,6 +168,14 @@ static void init_unused_rings(struct intel_gt *gt)
>   	}
>   }
>   
> +static void intel_gt_apply_ccs_mode(struct intel_gt *gt)
> +{
> +	if (!IS_DG2(gt->i915))
> +		return;
> +
> +	intel_uncore_write(gt->uncore, XEHP_CCS_MODE, 0);
> +}
> +
>   int intel_gt_init_hw(struct intel_gt *gt)
>   {
>   	struct drm_i915_private *i915 = gt->i915;
> @@ -195,6 +203,9 @@ 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
> diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> index cf709f6c05ae..c148113770ea 100644
> --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
> @@ -1605,6 +1605,8 @@
>   #define   GEN12_VOLTAGE_MASK			REG_GENMASK(10, 0)
>   #define   GEN12_CAGF_MASK			REG_GENMASK(19, 11)
>   
> +#define XEHP_CCS_MODE                          _MMIO(0x14804)
> +
>   #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/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index e81b3b2858ac..0853ffd3cb8d 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -396,6 +396,23 @@ static inline struct intel_gt *to_gt(const struct drm_i915_private *i915)
>   	     (engine__); \
>   	     (engine__) = rb_to_uabi_engine(rb_next(&(engine__)->uabi_node)))
>   
> +/*
> + * Exclude unavailable engines.
> + *
> + * Only the first CCS engine is utilized due to the disabling of CCS auto load
> + * balancing. As a result, all CCS engines operate collectively, functioning
> + * essentially as a single CCS engine, hence the count of active CCS engines is
> + * considered '1'.
> + * Currently, this applies to platforms with more than one CCS engine,
> + * specifically DG2.
> + */
> +#define for_each_available_uabi_engine(engine__, i915__) \
> +	for_each_uabi_engine(engine__, i915__) \
> +		if ((IS_DG2(i915__)) && \
> +		    ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
> +		    ((engine__)->uabi_instance)) { } \
> +		else
> +

I thought the plan was to simply not register the engine. Like that it 
would be a simpler patch.

>   #define INTEL_INFO(i915)	((i915)->__info)
>   #define RUNTIME_INFO(i915)	(&(i915)->__runtime)
>   #define DRIVER_CAPS(i915)	(&(i915)->caps)
> diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
> index fa3e937ed3f5..2d41bda626a6 100644
> --- a/drivers/gpu/drm/i915/i915_query.c
> +++ b/drivers/gpu/drm/i915/i915_query.c
> @@ -124,6 +124,7 @@ static int query_geometry_subslices(struct drm_i915_private *i915,
>   	return fill_topology_info(sseu, query_item, sseu->geometry_subslice_mask);
>   }
>   
> +

!

>   static int
>   query_engine_info(struct drm_i915_private *i915,
>   		  struct drm_i915_query_item *query_item)
> @@ -140,7 +141,7 @@ query_engine_info(struct drm_i915_private *i915,
>   	if (query_item->flags)
>   		return -EINVAL;
>   
> -	for_each_uabi_engine(engine, i915)
> +	for_each_available_uabi_engine(engine, i915)
>   		num_uabi_engines++;
>   
>   	len = struct_size(query_ptr, engines, num_uabi_engines);
> @@ -155,7 +156,7 @@ query_engine_info(struct drm_i915_private *i915,
>   
>   	info_ptr = &query_ptr->engines[0];
>   
> -	for_each_uabi_engine(engine, i915) {
> +	for_each_available_uabi_engine(engine, i915) {
>   		info.engine.engine_class = engine->uabi_class;
>   		info.engine.engine_instance = engine->uabi_instance;
>   		info.flags = I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE;

I thought you agreed that this still misses to hide the engine on direct 
lookup from userspace such as context map, PMU, SSEU. All of those would 
automatically be handled by not registering the engine.

Regards,

Tvrtko

[PATCH 2/2] drm/i915/gt: Set default CCS mode '1'

[Andi Shyti]

Since CCS automatic load balancing is disabled, we will impose a
fixed balancing policy that involves setting all the CCS engines
to work together on the same load.

Simultaneously, the user will see only 1 CCS rather than the
actual number. As of now, this change affects only DG2.

Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement")
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: Matt Roper <matthew.d.roper@intel.com>
Cc: <stable@vger.kernel.org> # v6.2+
---
 drivers/gpu/drm/i915/gt/intel_gt.c      | 11 +++++++++++
 drivers/gpu/drm/i915/gt/intel_gt_regs.h |  2 ++
 drivers/gpu/drm/i915/i915_drv.h         | 17 +++++++++++++++++
 drivers/gpu/drm/i915/i915_query.c       |  5 +++--
 4 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index a425db5ed3a2..e19df4ef47f6 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -168,6 +168,14 @@ static void init_unused_rings(struct intel_gt *gt)
 	}
 }
 
+static void intel_gt_apply_ccs_mode(struct intel_gt *gt)
+{
+	if (!IS_DG2(gt->i915))
+		return;
+
+	intel_uncore_write(gt->uncore, XEHP_CCS_MODE, 0);
+}
+
 int intel_gt_init_hw(struct intel_gt *gt)
 {
 	struct drm_i915_private *i915 = gt->i915;
@@ -195,6 +203,9 @@ 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
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index cf709f6c05ae..c148113770ea 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -1605,6 +1605,8 @@
 #define   GEN12_VOLTAGE_MASK			REG_GENMASK(10, 0)
 #define   GEN12_CAGF_MASK			REG_GENMASK(19, 11)
 
+#define XEHP_CCS_MODE                          _MMIO(0x14804)
+
 #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/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e81b3b2858ac..0853ffd3cb8d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -396,6 +396,23 @@ static inline struct intel_gt *to_gt(const struct drm_i915_private *i915)
 	     (engine__); \
 	     (engine__) = rb_to_uabi_engine(rb_next(&(engine__)->uabi_node)))
 
+/*
+ * Exclude unavailable engines.
+ *
+ * Only the first CCS engine is utilized due to the disabling of CCS auto load
+ * balancing. As a result, all CCS engines operate collectively, functioning
+ * essentially as a single CCS engine, hence the count of active CCS engines is
+ * considered '1'.
+ * Currently, this applies to platforms with more than one CCS engine,
+ * specifically DG2.
+ */
+#define for_each_available_uabi_engine(engine__, i915__) \
+	for_each_uabi_engine(engine__, i915__) \
+		if ((IS_DG2(i915__)) && \
+		    ((engine__)->uabi_class == I915_ENGINE_CLASS_COMPUTE) && \
+		    ((engine__)->uabi_instance)) { } \
+		else
+
 #define INTEL_INFO(i915)	((i915)->__info)
 #define RUNTIME_INFO(i915)	(&(i915)->__runtime)
 #define DRIVER_CAPS(i915)	(&(i915)->caps)
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index fa3e937ed3f5..2d41bda626a6 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -124,6 +124,7 @@ static int query_geometry_subslices(struct drm_i915_private *i915,
 	return fill_topology_info(sseu, query_item, sseu->geometry_subslice_mask);
 }
 
+
 static int
 query_engine_info(struct drm_i915_private *i915,
 		  struct drm_i915_query_item *query_item)
@@ -140,7 +141,7 @@ query_engine_info(struct drm_i915_private *i915,
 	if (query_item->flags)
 		return -EINVAL;
 
-	for_each_uabi_engine(engine, i915)
+	for_each_available_uabi_engine(engine, i915)
 		num_uabi_engines++;
 
 	len = struct_size(query_ptr, engines, num_uabi_engines);
@@ -155,7 +156,7 @@ query_engine_info(struct drm_i915_private *i915,
 
 	info_ptr = &query_ptr->engines[0];
 
-	for_each_uabi_engine(engine, i915) {
+	for_each_available_uabi_engine(engine, i915) {
 		info.engine.engine_class = engine->uabi_class;
 		info.engine.engine_instance = engine->uabi_instance;
 		info.flags = I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE;
-- 
2.43.0