[PATCH 0/5] Refactor to expand subslice mask

[PATCH 0/5] Refactor to expand subslice mask

[Stuart Summers]

This patch series contains a few code clean-up patches, followed
by a patch which changes the storage of the subslice mask to better
match the userspace access through the I915_QUERY_TOPOLOGY_INFO
ioctl. The index into the subslice_mask array is then calculated:
  slice * subslice stride + subslice index / 8

v2: fix i915_pm_sseu test failure
v3: no changes to patches in the series, just resending to pick up
    in CI correctly
v4: rebase
v5: fix header test
v6: address review comments from Jari
    address minor checkpatch warning in existing code
    use eu_stride for EU div-by-8
v7: another rebase
v8: address review comments from Tvrtko and Daniele
v9: address review comments from Daniele

Stuart Summers (5):
  drm/i915: Use local variable for SSEU info in GETPARAM ioctl
  drm/i915: Add macro for SSEU stride calculation
  drm/i915: Move calculation of subslices per slice to new function
  drm/i915: Refactor sseu helper functions
  drm/i915: Expand subslice mask

 drivers/gpu/drm/i915/gt/intel_engine_cs.c    |  24 ++-
 drivers/gpu/drm/i915/gt/intel_engine_types.h |  30 ++--
 drivers/gpu/drm/i915/gt/intel_hangcheck.c    |   3 +-
 drivers/gpu/drm/i915/gt/intel_sseu.c         |  62 +++++++
 drivers/gpu/drm/i915/gt/intel_sseu.h         |  36 +++-
 drivers/gpu/drm/i915/gt/intel_workarounds.c  |   2 +-
 drivers/gpu/drm/i915/i915_debugfs.c          |  46 ++---
 drivers/gpu/drm/i915/i915_drv.c              |  15 +-
 drivers/gpu/drm/i915/i915_gpu_error.c        |   5 +-
 drivers/gpu/drm/i915/i915_query.c            |  15 +-
 drivers/gpu/drm/i915/intel_device_info.c     | 176 +++++++++++--------
 drivers/gpu/drm/i915/intel_device_info.h     |  47 -----
 12 files changed, 281 insertions(+), 180 deletions(-)

-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 1/5] drm/i915: Use local variable for SSEU info in GETPARAM ioctl

[Stuart Summers]

In the GETPARAM ioctl handler, use a local variable to consolidate
usage of SSEU runtime info.

v2: add const to sseu_dev_info variable

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 2c7a4318d13c..f16b535655ac 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -329,6 +329,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct pci_dev *pdev = dev_priv->drm.pdev;
+	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	drm_i915_getparam_t *param = data;
 	int value;
 
@@ -382,12 +383,12 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = i915_cmd_parser_get_version(dev_priv);
 		break;
 	case I915_PARAM_SUBSLICE_TOTAL:
-		value = sseu_subslice_total(&RUNTIME_INFO(dev_priv)->sseu);
+		value = sseu_subslice_total(sseu);
 		if (!value)
 			return -ENODEV;
 		break;
 	case I915_PARAM_EU_TOTAL:
-		value = RUNTIME_INFO(dev_priv)->sseu.eu_total;
+		value = sseu->eu_total;
 		if (!value)
 			return -ENODEV;
 		break;
@@ -404,7 +405,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = HAS_POOLED_EU(dev_priv);
 		break;
 	case I915_PARAM_MIN_EU_IN_POOL:
-		value = RUNTIME_INFO(dev_priv)->sseu.min_eu_in_pool;
+		value = sseu->min_eu_in_pool;
 		break;
 	case I915_PARAM_HUC_STATUS:
 		value = intel_huc_check_status(&dev_priv->huc);
@@ -454,12 +455,12 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = intel_engines_has_context_isolation(dev_priv);
 		break;
 	case I915_PARAM_SLICE_MASK:
-		value = RUNTIME_INFO(dev_priv)->sseu.slice_mask;
+		value = sseu->slice_mask;
 		if (!value)
 			return -ENODEV;
 		break;
 	case I915_PARAM_SUBSLICE_MASK:
-		value = RUNTIME_INFO(dev_priv)->sseu.subslice_mask[0];
+		value = sseu->subslice_mask[0];
 		if (!value)
 			return -ENODEV;
 		break;
-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 2/5] drm/i915: Add macro for SSEU stride calculation

[Stuart Summers]

Subslice stride and EU stride are calculated multiple times in
i915_query. Move this calculation to a macro to reduce code duplication.

v2: update headers in intel_sseu.h
v3: use GEN_SSEU_STRIDE for stride calculations in intel_sseu.h
    apply s/bits/max_entries/ to GEN_SSEU_STRIDE parameter

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_sseu.h     |  2 ++
 drivers/gpu/drm/i915/i915_query.c        | 17 ++++++++---------
 drivers/gpu/drm/i915/intel_device_info.h |  9 +++------
 3 files changed, 13 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 73bc824094e8..d20b7f96907d 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -8,11 +8,13 @@
 #define __INTEL_SSEU_H__
 
 #include <linux/types.h>
+#include <linux/kernel.h>
 
 struct drm_i915_private;
 
 #define GEN_MAX_SLICES		(6) /* CNL upper bound */
 #define GEN_MAX_SUBSLICES	(8) /* ICL upper bound */
+#define GEN_SSEU_STRIDE(max_entries) DIV_ROUND_UP(max_entries, BITS_PER_BYTE)
 
 struct sseu_dev_info {
 	u8 slice_mask;
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index 782183b78f49..7c1708c22811 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -37,6 +37,8 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
 	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	struct drm_i915_query_topology_info topo;
 	u32 slice_length, subslice_length, eu_length, total_length;
+	u8 subslice_stride = GEN_SSEU_STRIDE(sseu->max_subslices);
+	u8 eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
 	int ret;
 
 	if (query_item->flags != 0)
@@ -48,12 +50,10 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
 	BUILD_BUG_ON(sizeof(u8) != sizeof(sseu->slice_mask));
 
 	slice_length = sizeof(sseu->slice_mask);
-	subslice_length = sseu->max_slices *
-		DIV_ROUND_UP(sseu->max_subslices, BITS_PER_BYTE);
-	eu_length = sseu->max_slices * sseu->max_subslices *
-		DIV_ROUND_UP(sseu->max_eus_per_subslice, BITS_PER_BYTE);
-
-	total_length = sizeof(topo) + slice_length + subslice_length + eu_length;
+	subslice_length = sseu->max_slices * subslice_stride;
+	eu_length = sseu->max_slices * sseu->max_subslices * eu_stride;
+	total_length = sizeof(topo) + slice_length + subslice_length +
+		       eu_length;
 
 	ret = copy_query_item(&topo, sizeof(topo), total_length,
 			      query_item);
@@ -69,10 +69,9 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
 	topo.max_eus_per_subslice = sseu->max_eus_per_subslice;
 
 	topo.subslice_offset = slice_length;
-	topo.subslice_stride = DIV_ROUND_UP(sseu->max_subslices, BITS_PER_BYTE);
+	topo.subslice_stride = subslice_stride;
 	topo.eu_offset = slice_length + subslice_length;
-	topo.eu_stride =
-		DIV_ROUND_UP(sseu->max_eus_per_subslice, BITS_PER_BYTE);
+	topo.eu_stride = eu_stride;
 
 	if (__copy_to_user(u64_to_user_ptr(query_item->data_ptr),
 			   &topo, sizeof(topo)))
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 5a2e17d6146b..9d43f7edfd63 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -231,8 +231,7 @@ static inline unsigned int sseu_subslice_total(const struct sseu_dev_info *sseu)
 static inline int sseu_eu_idx(const struct sseu_dev_info *sseu,
 			      int slice, int subslice)
 {
-	int subslice_stride = DIV_ROUND_UP(sseu->max_eus_per_subslice,
-					   BITS_PER_BYTE);
+	int subslice_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
 	int slice_stride = sseu->max_subslices * subslice_stride;
 
 	return slice * slice_stride + subslice * subslice_stride;
@@ -244,8 +243,7 @@ static inline u16 sseu_get_eus(const struct sseu_dev_info *sseu,
 	int i, offset = sseu_eu_idx(sseu, slice, subslice);
 	u16 eu_mask = 0;
 
-	for (i = 0;
-	     i < DIV_ROUND_UP(sseu->max_eus_per_subslice, BITS_PER_BYTE); i++) {
+	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
 		eu_mask |= ((u16) sseu->eu_mask[offset + i]) <<
 			(i * BITS_PER_BYTE);
 	}
@@ -258,8 +256,7 @@ static inline void sseu_set_eus(struct sseu_dev_info *sseu,
 {
 	int i, offset = sseu_eu_idx(sseu, slice, subslice);
 
-	for (i = 0;
-	     i < DIV_ROUND_UP(sseu->max_eus_per_subslice, BITS_PER_BYTE); i++) {
+	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
 		sseu->eu_mask[offset + i] =
 			(eu_mask >> (BITS_PER_BYTE * i)) & 0xff;
 	}
-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 3/5] drm/i915: Move calculation of subslices per slice to new function

[Stuart Summers]

Add a new function to return the number of subslices per slice to
consolidate code usage.

v2: rebase on changes to move sseu struct to intel_sseu.h
v3: add intel_* prefix to sseu_subslices_per_slice

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_sseu.h     | 6 ++++++
 drivers/gpu/drm/i915/i915_debugfs.c      | 2 +-
 drivers/gpu/drm/i915/intel_device_info.c | 4 ++--
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index d20b7f96907d..9618dff46d83 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -63,6 +63,12 @@ intel_sseu_from_device_info(const struct sseu_dev_info *sseu)
 	return value;
 }
 
+static inline unsigned int
+intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice)
+{
+	return hweight8(sseu->subslice_mask[slice]);
+}
+
 u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
 			 const struct intel_sseu *req_sseu);
 
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 072464a18050..9b000ee3f982 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -4191,7 +4191,7 @@ static void i915_print_sseu_info(struct seq_file *m, bool is_available_info,
 		   sseu_subslice_total(sseu));
 	for (s = 0; s < fls(sseu->slice_mask); s++) {
 		seq_printf(m, "  %s Slice%i subslices: %u\n", type,
-			   s, hweight8(sseu->subslice_mask[s]));
+			   s, intel_sseu_subslices_per_slice(sseu, s));
 	}
 	seq_printf(m, "  %s EU Total: %u\n", type,
 		   sseu->eu_total);
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 6af480b95bc6..9d6b9c45bc5e 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -93,7 +93,7 @@ static void sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p)
 	drm_printf(p, "subslice total: %u\n", sseu_subslice_total(sseu));
 	for (s = 0; s < sseu->max_slices; s++) {
 		drm_printf(p, "slice%d: %u subslices, mask=%04x\n",
-			   s, hweight8(sseu->subslice_mask[s]),
+			   s, intel_sseu_subslices_per_slice(sseu, s),
 			   sseu->subslice_mask[s]);
 	}
 	drm_printf(p, "EU total: %u\n", sseu->eu_total);
@@ -126,7 +126,7 @@ void intel_device_info_dump_topology(const struct sseu_dev_info *sseu,
 
 	for (s = 0; s < sseu->max_slices; s++) {
 		drm_printf(p, "slice%d: %u subslice(s) (0x%hhx):\n",
-			   s, hweight8(sseu->subslice_mask[s]),
+			   s, intel_sseu_subslices_per_slice(sseu, s),
 			   sseu->subslice_mask[s]);
 
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 4/5] drm/i915: Refactor sseu helper functions

[Stuart Summers]

Move functions to intel_sseu.h and remove inline qualifier.
Additionally, ensure these are all prefixed with intel_sseu_*
to match the convention of other functions in i915.

v2: fix spacing from checkpatch warning
v3: squash helper function changes into a single patch
    break 80 character line to fix checkpatch warning
    move get/set_eus helpers to intel_device_info.c
v4: Remove intel_ prefix from static functions in
    intel_device_info.c and correctly copy changes
    to stride calculation in those functions.

Acked-by: Jani Nikula <jani.nikula@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_sseu.c     | 17 +++++++
 drivers/gpu/drm/i915/gt/intel_sseu.h     | 10 ++--
 drivers/gpu/drm/i915/i915_debugfs.c      |  4 +-
 drivers/gpu/drm/i915/i915_drv.c          |  2 +-
 drivers/gpu/drm/i915/intel_device_info.c | 60 +++++++++++++++++++-----
 drivers/gpu/drm/i915/intel_device_info.h | 44 -----------------
 6 files changed, 74 insertions(+), 63 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index 7f448f3bea0b..a0756f006f5f 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -8,6 +8,23 @@
 #include "intel_lrc_reg.h"
 #include "intel_sseu.h"
 
+unsigned int
+intel_sseu_subslice_total(const struct sseu_dev_info *sseu)
+{
+	unsigned int i, total = 0;
+
+	for (i = 0; i < ARRAY_SIZE(sseu->subslice_mask); i++)
+		total += hweight8(sseu->subslice_mask[i]);
+
+	return total;
+}
+
+unsigned int
+intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice)
+{
+	return hweight8(sseu->subslice_mask[slice]);
+}
+
 u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
 			 const struct intel_sseu *req_sseu)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 9618dff46d83..b50d0401a4e2 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -63,11 +63,11 @@ intel_sseu_from_device_info(const struct sseu_dev_info *sseu)
 	return value;
 }
 
-static inline unsigned int
-intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice)
-{
-	return hweight8(sseu->subslice_mask[slice]);
-}
+unsigned int
+intel_sseu_subslice_total(const struct sseu_dev_info *sseu);
+
+unsigned int
+intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice);
 
 u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
 			 const struct intel_sseu *req_sseu);
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 9b000ee3f982..a26015722405 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -4164,7 +4164,7 @@ static void broadwell_sseu_device_status(struct drm_i915_private *dev_priv,
 				RUNTIME_INFO(dev_priv)->sseu.subslice_mask[s];
 		}
 		sseu->eu_total = sseu->eu_per_subslice *
-				 sseu_subslice_total(sseu);
+				 intel_sseu_subslice_total(sseu);
 
 		/* subtract fused off EU(s) from enabled slice(s) */
 		for (s = 0; s < fls(sseu->slice_mask); s++) {
@@ -4188,7 +4188,7 @@ static void i915_print_sseu_info(struct seq_file *m, bool is_available_info,
 	seq_printf(m, "  %s Slice Total: %u\n", type,
 		   hweight8(sseu->slice_mask));
 	seq_printf(m, "  %s Subslice Total: %u\n", type,
-		   sseu_subslice_total(sseu));
+		   intel_sseu_subslice_total(sseu));
 	for (s = 0; s < fls(sseu->slice_mask); s++) {
 		seq_printf(m, "  %s Slice%i subslices: %u\n", type,
 			   s, intel_sseu_subslices_per_slice(sseu, s));
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index f16b535655ac..8a7d4dea8609 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -383,7 +383,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = i915_cmd_parser_get_version(dev_priv);
 		break;
 	case I915_PARAM_SUBSLICE_TOTAL:
-		value = sseu_subslice_total(sseu);
+		value = intel_sseu_subslice_total(sseu);
 		if (!value)
 			return -ENODEV;
 		break;
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 9d6b9c45bc5e..97f742530fa1 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -90,7 +90,7 @@ static void sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p)
 
 	drm_printf(p, "slice total: %u, mask=%04x\n",
 		   hweight8(sseu->slice_mask), sseu->slice_mask);
-	drm_printf(p, "subslice total: %u\n", sseu_subslice_total(sseu));
+	drm_printf(p, "subslice total: %u\n", intel_sseu_subslice_total(sseu));
 	for (s = 0; s < sseu->max_slices; s++) {
 		drm_printf(p, "slice%d: %u subslices, mask=%04x\n",
 			   s, intel_sseu_subslices_per_slice(sseu, s),
@@ -114,6 +114,40 @@ void intel_device_info_dump_runtime(const struct intel_runtime_info *info,
 		   info->cs_timestamp_frequency_khz);
 }
 
+static int sseu_eu_idx(const struct sseu_dev_info *sseu, int slice,
+		       int subslice)
+{
+	int subslice_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
+	int slice_stride = sseu->max_subslices * subslice_stride;
+
+	return slice * slice_stride + subslice * subslice_stride;
+}
+
+static u16 sseu_get_eus(const struct sseu_dev_info *sseu, int slice,
+			int subslice)
+{
+	int i, offset = sseu_eu_idx(sseu, slice, subslice);
+	u16 eu_mask = 0;
+
+	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
+		eu_mask |= ((u16)sseu->eu_mask[offset + i]) <<
+			(i * BITS_PER_BYTE);
+	}
+
+	return eu_mask;
+}
+
+static void sseu_set_eus(struct sseu_dev_info *sseu, int slice, int subslice,
+			 u16 eu_mask)
+{
+	int i, offset = sseu_eu_idx(sseu, slice, subslice);
+
+	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
+		sseu->eu_mask[offset + i] =
+			(eu_mask >> (BITS_PER_BYTE * i)) & 0xff;
+	}
+}
+
 void intel_device_info_dump_topology(const struct sseu_dev_info *sseu,
 				     struct drm_printer *p)
 {
@@ -260,9 +294,10 @@ static void gen10_sseu_info_init(struct drm_i915_private *dev_priv)
 	 * EU in any one subslice may be fused off for die
 	 * recovery.
 	 */
-	sseu->eu_per_subslice = sseu_subslice_total(sseu) ?
+	sseu->eu_per_subslice = intel_sseu_subslice_total(sseu) ?
 				DIV_ROUND_UP(sseu->eu_total,
-					     sseu_subslice_total(sseu)) : 0;
+					     intel_sseu_subslice_total(sseu)) :
+				0;
 
 	/* No restrictions on Power Gating */
 	sseu->has_slice_pg = 1;
@@ -310,8 +345,9 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
 	 * CHV expected to always have a uniform distribution of EU
 	 * across subslices.
 	*/
-	sseu->eu_per_subslice = sseu_subslice_total(sseu) ?
-				sseu->eu_total / sseu_subslice_total(sseu) :
+	sseu->eu_per_subslice = intel_sseu_subslice_total(sseu) ?
+				sseu->eu_total /
+					intel_sseu_subslice_total(sseu) :
 				0;
 	/*
 	 * CHV supports subslice power gating on devices with more than
@@ -319,7 +355,7 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
 	 * more than one EU pair per subslice.
 	*/
 	sseu->has_slice_pg = 0;
-	sseu->has_subslice_pg = sseu_subslice_total(sseu) > 1;
+	sseu->has_subslice_pg = intel_sseu_subslice_total(sseu) > 1;
 	sseu->has_eu_pg = (sseu->eu_per_subslice > 2);
 }
 
@@ -393,9 +429,10 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 	 * recovery. BXT is expected to be perfectly uniform in EU
 	 * distribution.
 	*/
-	sseu->eu_per_subslice = sseu_subslice_total(sseu) ?
+	sseu->eu_per_subslice = intel_sseu_subslice_total(sseu) ?
 				DIV_ROUND_UP(sseu->eu_total,
-					     sseu_subslice_total(sseu)) : 0;
+					     intel_sseu_subslice_total(sseu)) :
+				0;
 	/*
 	 * SKL+ supports slice power gating on devices with more than
 	 * one slice, and supports EU power gating on devices with
@@ -407,7 +444,7 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 	sseu->has_slice_pg =
 		!IS_GEN9_LP(dev_priv) && hweight8(sseu->slice_mask) > 1;
 	sseu->has_subslice_pg =
-		IS_GEN9_LP(dev_priv) && sseu_subslice_total(sseu) > 1;
+		IS_GEN9_LP(dev_priv) && intel_sseu_subslice_total(sseu) > 1;
 	sseu->has_eu_pg = sseu->eu_per_subslice > 2;
 
 	if (IS_GEN9_LP(dev_priv)) {
@@ -496,9 +533,10 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
 	 * subslices with the exception that any one EU in any one subslice may
 	 * be fused off for die recovery.
 	 */
-	sseu->eu_per_subslice = sseu_subslice_total(sseu) ?
+	sseu->eu_per_subslice = intel_sseu_subslice_total(sseu) ?
 				DIV_ROUND_UP(sseu->eu_total,
-					     sseu_subslice_total(sseu)) : 0;
+					     intel_sseu_subslice_total(sseu)) :
+				0;
 
 	/*
 	 * BDW supports slice power gating on devices with more than
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 9d43f7edfd63..6412a9c72898 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -218,50 +218,6 @@ struct intel_driver_caps {
 	bool has_logical_contexts:1;
 };
 
-static inline unsigned int sseu_subslice_total(const struct sseu_dev_info *sseu)
-{
-	unsigned int i, total = 0;
-
-	for (i = 0; i < ARRAY_SIZE(sseu->subslice_mask); i++)
-		total += hweight8(sseu->subslice_mask[i]);
-
-	return total;
-}
-
-static inline int sseu_eu_idx(const struct sseu_dev_info *sseu,
-			      int slice, int subslice)
-{
-	int subslice_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
-	int slice_stride = sseu->max_subslices * subslice_stride;
-
-	return slice * slice_stride + subslice * subslice_stride;
-}
-
-static inline u16 sseu_get_eus(const struct sseu_dev_info *sseu,
-			       int slice, int subslice)
-{
-	int i, offset = sseu_eu_idx(sseu, slice, subslice);
-	u16 eu_mask = 0;
-
-	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
-		eu_mask |= ((u16) sseu->eu_mask[offset + i]) <<
-			(i * BITS_PER_BYTE);
-	}
-
-	return eu_mask;
-}
-
-static inline void sseu_set_eus(struct sseu_dev_info *sseu,
-				int slice, int subslice, u16 eu_mask)
-{
-	int i, offset = sseu_eu_idx(sseu, slice, subslice);
-
-	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
-		sseu->eu_mask[offset + i] =
-			(eu_mask >> (BITS_PER_BYTE * i)) & 0xff;
-	}
-}
-
 const char *intel_platform_name(enum intel_platform platform);
 
 void intel_device_info_subplatform_init(struct drm_i915_private *dev_priv);
-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 5/5] drm/i915: Expand subslice mask

[Stuart Summers]

Currently, the subslice_mask runtime parameter is stored as an
array of subslices per slice. Expand the subslice mask array to
better match what is presented to userspace through the
I915_QUERY_TOPOLOGY_INFO ioctl. The index into this array is
then calculated:
  slice * subslice stride + subslice index / 8

v2: fix spacing in set_sseu_info args
    use set_sseu_info to initialize sseu data when building
    device status in debugfs
    rename variables in intel_engine_types.h to avoid checkpatch
    warnings
v3: update headers in intel_sseu.h
v4: add const to some sseu_dev_info variables
    use sseu->eu_stride for EU stride calculations
v5: address review comments from Tvrtko and Daniele
v6: remove extra space in intel_sseu_get_subslices
    return the correct subslice enable in for_each_instdone
    add GEM_BUG_ON to ensure user doesn't pass invalid ss_mask size
    use printk formatted string for subslice mask

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Acked-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c    |  24 +++-
 drivers/gpu/drm/i915/gt/intel_engine_types.h |  30 ++---
 drivers/gpu/drm/i915/gt/intel_hangcheck.c    |   3 +-
 drivers/gpu/drm/i915/gt/intel_sseu.c         |  47 ++++++-
 drivers/gpu/drm/i915/gt/intel_sseu.h         |  28 ++++-
 drivers/gpu/drm/i915/gt/intel_workarounds.c  |   2 +-
 drivers/gpu/drm/i915/i915_debugfs.c          |  40 +++---
 drivers/gpu/drm/i915/i915_drv.c              |   6 +-
 drivers/gpu/drm/i915/i915_gpu_error.c        |   5 +-
 drivers/gpu/drm/i915/i915_query.c            |  10 +-
 drivers/gpu/drm/i915/intel_device_info.c     | 122 +++++++++----------
 11 files changed, 201 insertions(+), 116 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 4c3753c1b573..3a5e0fefcab9 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -910,12 +910,30 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
 	}
 }
 
+static inline u32
+intel_sseu_fls_subslice(const struct sseu_dev_info *sseu, u32 slice)
+{
+	u32 subslice;
+	int i;
+
+	for (i = sseu->ss_stride - 1; i >= 0; i--) {
+		subslice = fls(sseu->subslice_mask[slice * sseu->ss_stride +
+						   i]);
+		if (subslice) {
+			subslice += i * BITS_PER_BYTE;
+			break;
+		}
+	}
+
+	return subslice;
+}
+
 u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv)
 {
 	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	u32 mcr_s_ss_select;
 	u32 slice = fls(sseu->slice_mask);
-	u32 subslice = fls(sseu->subslice_mask[slice]);
+	u32 subslice = intel_sseu_fls_subslice(sseu, slice);
 
 	if (IS_GEN(dev_priv, 10))
 		mcr_s_ss_select = GEN8_MCR_SLICE(slice) |
@@ -991,6 +1009,7 @@ void intel_engine_get_instdone(struct intel_engine_cs *engine,
 			       struct intel_instdone *instdone)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
+	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	struct intel_uncore *uncore = engine->uncore;
 	u32 mmio_base = engine->mmio_base;
 	int slice;
@@ -1008,7 +1027,8 @@ void intel_engine_get_instdone(struct intel_engine_cs *engine,
 
 		instdone->slice_common =
 			intel_uncore_read(uncore, GEN7_SC_INSTDONE);
-		for_each_instdone_slice_subslice(dev_priv, slice, subslice) {
+		for_each_instdone_slice_subslice(dev_priv, sseu, slice,
+						 subslice) {
 			instdone->sampler[slice][subslice] =
 				read_subslice_reg(dev_priv, slice, subslice,
 						  GEN7_SAMPLER_INSTDONE);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index e381c1c73902..cf79df8d4f32 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -534,20 +534,20 @@ intel_engine_needs_breadcrumb_tasklet(const struct intel_engine_cs *engine)
 	return engine->flags & I915_ENGINE_NEEDS_BREADCRUMB_TASKLET;
 }
 
-#define instdone_slice_mask(dev_priv__) \
-	(IS_GEN(dev_priv__, 7) ? \
-	 1 : RUNTIME_INFO(dev_priv__)->sseu.slice_mask)
-
-#define instdone_subslice_mask(dev_priv__) \
-	(IS_GEN(dev_priv__, 7) ? \
-	 1 : RUNTIME_INFO(dev_priv__)->sseu.subslice_mask[0])
-
-#define for_each_instdone_slice_subslice(dev_priv__, slice__, subslice__) \
-	for ((slice__) = 0, (subslice__) = 0; \
-	     (slice__) < I915_MAX_SLICES; \
-	     (subslice__) = ((subslice__) + 1) < I915_MAX_SUBSLICES ? (subslice__) + 1 : 0, \
-	       (slice__) += ((subslice__) == 0)) \
-		for_each_if((BIT(slice__) & instdone_slice_mask(dev_priv__)) && \
-			    (BIT(subslice__) & instdone_subslice_mask(dev_priv__)))
+#define instdone_has_slice(dev_priv___, sseu___, slice___) \
+	((IS_GEN(dev_priv___, 7) ? 1 : ((sseu___)->slice_mask)) & \
+	BIT(slice___))
+
+#define instdone_has_subslice(dev_priv__, sseu__, slice__, subslice__) \
+	(IS_GEN(dev_priv__, 7) ? (1 & BIT(subslice__)) : \
+	 intel_sseu_has_subslice(sseu__, slice__, subslice__))
+
+#define for_each_instdone_slice_subslice(dev_priv_, sseu_, slice_, subslice_) \
+	for ((slice_) = 0, (subslice_) = 0; (slice_) < I915_MAX_SLICES; \
+	     (subslice_) = ((subslice_) + 1) % I915_MAX_SUBSLICES, \
+	     (slice_) += ((subslice_) == 0)) \
+		for_each_if((instdone_has_slice(dev_priv_, sseu_, slice_)) && \
+			    (instdone_has_subslice(dev_priv_, sseu_, slice_, \
+						    subslice_)))
 
 #endif /* __INTEL_ENGINE_TYPES_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_hangcheck.c b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
index 3a4d09b80fa0..b19cd4cdcb5c 100644
--- a/drivers/gpu/drm/i915/gt/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
@@ -51,6 +51,7 @@ static bool instdone_unchanged(u32 current_instdone, u32 *old_instdone)
 static bool subunits_stuck(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
+	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	struct intel_instdone instdone;
 	struct intel_instdone *accu_instdone = &engine->hangcheck.instdone;
 	bool stuck;
@@ -72,7 +73,7 @@ static bool subunits_stuck(struct intel_engine_cs *engine)
 	stuck &= instdone_unchanged(instdone.slice_common,
 				    &accu_instdone->slice_common);
 
-	for_each_instdone_slice_subslice(dev_priv, slice, subslice) {
+	for_each_instdone_slice_subslice(dev_priv, sseu, slice, subslice) {
 		stuck &= instdone_unchanged(instdone.sampler[slice][subslice],
 					    &accu_instdone->sampler[slice][subslice]);
 		stuck &= instdone_unchanged(instdone.row[slice][subslice],
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index a0756f006f5f..763b811f2c9d 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -8,6 +8,17 @@
 #include "intel_lrc_reg.h"
 #include "intel_sseu.h"
 
+void intel_sseu_set_info(struct sseu_dev_info *sseu, u8 max_slices,
+			 u8 max_subslices, u8 max_eus_per_subslice)
+{
+	sseu->max_slices = max_slices;
+	sseu->max_subslices = max_subslices;
+	sseu->max_eus_per_subslice = max_eus_per_subslice;
+
+	sseu->ss_stride = GEN_SSEU_STRIDE(sseu->max_subslices);
+	sseu->eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
+}
+
 unsigned int
 intel_sseu_subslice_total(const struct sseu_dev_info *sseu)
 {
@@ -19,10 +30,44 @@ intel_sseu_subslice_total(const struct sseu_dev_info *sseu)
 	return total;
 }
 
+void intel_sseu_copy_subslices(const struct sseu_dev_info *sseu, int slice,
+			       u8 *to_mask)
+{
+	int offset = slice * sseu->ss_stride;
+
+	memcpy(&to_mask[offset], &sseu->subslice_mask[offset], sseu->ss_stride);
+}
+
+u32 intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice)
+{
+	int i, offset = slice * sseu->ss_stride;
+	u32 mask;
+
+	GEM_BUG_ON(slice >= sseu->max_slices);
+
+	GEM_BUG_ON(sseu->ss_stride > sizeof(mask));
+
+	for (i = 0; i < sseu->ss_stride; i++)
+		mask |= (u32)sseu->subslice_mask[offset + i] <<
+			i * BITS_PER_BYTE;
+
+	return mask;
+}
+
+void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
+			      u32 ss_mask)
+{
+	int i, offset = slice * sseu->ss_stride;
+
+	for (i = 0; i < sseu->ss_stride; i++)
+		sseu->subslice_mask[offset + i] =
+			(ss_mask >> (BITS_PER_BYTE * i)) & 0xff;
+}
+
 unsigned int
 intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice)
 {
-	return hweight8(sseu->subslice_mask[slice]);
+	return hweight32(intel_sseu_get_subslices(sseu, slice));
 }
 
 u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index b50d0401a4e2..3602ae54b937 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -9,16 +9,18 @@
 
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
 
 struct drm_i915_private;
 
 #define GEN_MAX_SLICES		(6) /* CNL upper bound */
 #define GEN_MAX_SUBSLICES	(8) /* ICL upper bound */
 #define GEN_SSEU_STRIDE(max_entries) DIV_ROUND_UP(max_entries, BITS_PER_BYTE)
+#define GEN_MAX_SUBSLICE_STRIDE GEN_SSEU_STRIDE(GEN_MAX_SUBSLICES)
 
 struct sseu_dev_info {
 	u8 slice_mask;
-	u8 subslice_mask[GEN_MAX_SLICES];
+	u8 subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
 	u16 eu_total;
 	u8 eu_per_subslice;
 	u8 min_eu_in_pool;
@@ -33,6 +35,9 @@ struct sseu_dev_info {
 	u8 max_subslices;
 	u8 max_eus_per_subslice;
 
+	u8 ss_stride;
+	u8 eu_stride;
+
 	/* We don't have more than 8 eus per subslice at the moment and as we
 	 * store eus enabled using bits, no need to multiply by eus per
 	 * subslice.
@@ -63,12 +68,33 @@ intel_sseu_from_device_info(const struct sseu_dev_info *sseu)
 	return value;
 }
 
+static inline bool
+intel_sseu_has_subslice(const struct sseu_dev_info *sseu, int slice,
+			int subslice)
+{
+	u8 mask = sseu->subslice_mask[slice * sseu->ss_stride +
+				      subslice / BITS_PER_BYTE];
+
+	return mask & BIT(subslice % BITS_PER_BYTE);
+}
+
+void intel_sseu_set_info(struct sseu_dev_info *sseu, u8 max_slices,
+			 u8 max_subslices, u8 max_eus_per_subslice);
+
 unsigned int
 intel_sseu_subslice_total(const struct sseu_dev_info *sseu);
 
 unsigned int
 intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice);
 
+void intel_sseu_copy_subslices(const struct sseu_dev_info *sseu, int slice,
+			       u8 *to_mask);
+
+u32  intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice);
+
+void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
+			      u32 ss_mask);
+
 u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
 			 const struct intel_sseu *req_sseu);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 43e290306551..8437f9d918ec 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -767,7 +767,7 @@ wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal)
 		u32 slice = fls(sseu->slice_mask);
 		u32 fuse3 =
 			intel_uncore_read(&i915->uncore, GEN10_MIRROR_FUSE3);
-		u8 ss_mask = sseu->subslice_mask[slice];
+		u32 ss_mask = intel_sseu_get_subslices(sseu, slice);
 
 		u8 enabled_mask = (ss_mask | ss_mask >>
 				   GEN10_L3BANK_PAIR_COUNT) & GEN10_L3BANK_MASK;
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index a26015722405..46365ab957e6 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1259,6 +1259,7 @@ static void i915_instdone_info(struct drm_i915_private *dev_priv,
 			       struct seq_file *m,
 			       struct intel_instdone *instdone)
 {
+	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	int slice;
 	int subslice;
 
@@ -1274,11 +1275,11 @@ static void i915_instdone_info(struct drm_i915_private *dev_priv,
 	if (INTEL_GEN(dev_priv) <= 6)
 		return;
 
-	for_each_instdone_slice_subslice(dev_priv, slice, subslice)
+	for_each_instdone_slice_subslice(dev_priv, sseu, slice, subslice)
 		seq_printf(m, "\t\tSAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
 			   slice, subslice, instdone->sampler[slice][subslice]);
 
-	for_each_instdone_slice_subslice(dev_priv, slice, subslice)
+	for_each_instdone_slice_subslice(dev_priv, sseu, slice, subslice)
 		seq_printf(m, "\t\tROW_INSTDONE[%d][%d]: 0x%08x\n",
 			   slice, subslice, instdone->row[slice][subslice]);
 }
@@ -4072,7 +4073,7 @@ static void gen10_sseu_device_status(struct drm_i915_private *dev_priv,
 			continue;
 
 		sseu->slice_mask |= BIT(s);
-		sseu->subslice_mask[s] = info->sseu.subslice_mask[s];
+		intel_sseu_copy_subslices(&info->sseu, s, sseu->subslice_mask);
 
 		for (ss = 0; ss < info->sseu.max_subslices; ss++) {
 			unsigned int eu_cnt;
@@ -4123,18 +4124,21 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
 		sseu->slice_mask |= BIT(s);
 
 		if (IS_GEN9_BC(dev_priv))
-			sseu->subslice_mask[s] =
-				RUNTIME_INFO(dev_priv)->sseu.subslice_mask[s];
+			intel_sseu_copy_subslices(&info->sseu, s,
+						  sseu->subslice_mask);
 
 		for (ss = 0; ss < info->sseu.max_subslices; ss++) {
 			unsigned int eu_cnt;
+			u8 ss_idx = s * info->sseu.ss_stride +
+				    ss / BITS_PER_BYTE;
 
 			if (IS_GEN9_LP(dev_priv)) {
 				if (!(s_reg[s] & (GEN9_PGCTL_SS_ACK(ss))))
 					/* skip disabled subslice */
 					continue;
 
-				sseu->subslice_mask[s] |= BIT(ss);
+				sseu->subslice_mask[ss_idx] |=
+					BIT(ss % BITS_PER_BYTE);
 			}
 
 			eu_cnt = 2 * hweight32(eu_reg[2*s + ss/2] &
@@ -4151,25 +4155,23 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
 static void broadwell_sseu_device_status(struct drm_i915_private *dev_priv,
 					 struct sseu_dev_info *sseu)
 {
+	struct intel_runtime_info *info = RUNTIME_INFO(dev_priv);
 	u32 slice_info = I915_READ(GEN8_GT_SLICE_INFO);
 	int s;
 
 	sseu->slice_mask = slice_info & GEN8_LSLICESTAT_MASK;
 
 	if (sseu->slice_mask) {
-		sseu->eu_per_subslice =
-			RUNTIME_INFO(dev_priv)->sseu.eu_per_subslice;
-		for (s = 0; s < fls(sseu->slice_mask); s++) {
-			sseu->subslice_mask[s] =
-				RUNTIME_INFO(dev_priv)->sseu.subslice_mask[s];
-		}
+		sseu->eu_per_subslice = info->sseu.eu_per_subslice;
+		for (s = 0; s < fls(sseu->slice_mask); s++)
+			intel_sseu_copy_subslices(&info->sseu, s,
+						  sseu->subslice_mask);
 		sseu->eu_total = sseu->eu_per_subslice *
 				 intel_sseu_subslice_total(sseu);
 
 		/* subtract fused off EU(s) from enabled slice(s) */
 		for (s = 0; s < fls(sseu->slice_mask); s++) {
-			u8 subslice_7eu =
-				RUNTIME_INFO(dev_priv)->sseu.subslice_7eu[s];
+			u8 subslice_7eu = info->sseu.subslice_7eu[s];
 
 			sseu->eu_total -= hweight8(subslice_7eu);
 		}
@@ -4216,6 +4218,7 @@ static void i915_print_sseu_info(struct seq_file *m, bool is_available_info,
 static int i915_sseu_status(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	const struct intel_runtime_info *info = RUNTIME_INFO(dev_priv);
 	struct sseu_dev_info sseu;
 	intel_wakeref_t wakeref;
 
@@ -4223,14 +4226,13 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
 		return -ENODEV;
 
 	seq_puts(m, "SSEU Device Info\n");
-	i915_print_sseu_info(m, true, &RUNTIME_INFO(dev_priv)->sseu);
+	i915_print_sseu_info(m, true, &info->sseu);
 
 	seq_puts(m, "SSEU Device Status\n");
 	memset(&sseu, 0, sizeof(sseu));
-	sseu.max_slices = RUNTIME_INFO(dev_priv)->sseu.max_slices;
-	sseu.max_subslices = RUNTIME_INFO(dev_priv)->sseu.max_subslices;
-	sseu.max_eus_per_subslice =
-		RUNTIME_INFO(dev_priv)->sseu.max_eus_per_subslice;
+	intel_sseu_set_info(&sseu, info->sseu.max_slices,
+			    info->sseu.max_subslices,
+			    info->sseu.max_eus_per_subslice);
 
 	with_intel_runtime_pm(dev_priv, wakeref) {
 		if (IS_CHERRYVIEW(dev_priv))
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 8a7d4dea8609..dc6bafc09b36 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -331,7 +331,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	drm_i915_getparam_t *param = data;
-	int value;
+	int value = 0;
 
 	switch (param->param) {
 	case I915_PARAM_IRQ_ACTIVE:
@@ -460,7 +460,9 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 			return -ENODEV;
 		break;
 	case I915_PARAM_SUBSLICE_MASK:
-		value = sseu->subslice_mask[0];
+		/* Only copy bits from the first slice */
+		memcpy(&value, sseu->subslice_mask,
+		       min(sseu->ss_stride, (u8)sizeof(value)));
 		if (!value)
 			return -ENODEV;
 		break;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 4f85cbdddb0d..c760cc5b3388 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -408,6 +408,7 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m,
 static void error_print_instdone(struct drm_i915_error_state_buf *m,
 				 const struct drm_i915_error_engine *ee)
 {
+	struct sseu_dev_info *sseu = &RUNTIME_INFO(m->i915)->sseu;
 	int slice;
 	int subslice;
 
@@ -423,12 +424,12 @@ static void error_print_instdone(struct drm_i915_error_state_buf *m,
 	if (INTEL_GEN(m->i915) <= 6)
 		return;
 
-	for_each_instdone_slice_subslice(m->i915, slice, subslice)
+	for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
 		err_printf(m, "  SAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
 			   slice, subslice,
 			   ee->instdone.sampler[slice][subslice]);
 
-	for_each_instdone_slice_subslice(m->i915, slice, subslice)
+	for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
 		err_printf(m, "  ROW_INSTDONE[%d][%d]: 0x%08x\n",
 			   slice, subslice,
 			   ee->instdone.row[slice][subslice]);
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index 7c1708c22811..000dcb145ce0 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -37,8 +37,6 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
 	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	struct drm_i915_query_topology_info topo;
 	u32 slice_length, subslice_length, eu_length, total_length;
-	u8 subslice_stride = GEN_SSEU_STRIDE(sseu->max_subslices);
-	u8 eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
 	int ret;
 
 	if (query_item->flags != 0)
@@ -50,8 +48,8 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
 	BUILD_BUG_ON(sizeof(u8) != sizeof(sseu->slice_mask));
 
 	slice_length = sizeof(sseu->slice_mask);
-	subslice_length = sseu->max_slices * subslice_stride;
-	eu_length = sseu->max_slices * sseu->max_subslices * eu_stride;
+	subslice_length = sseu->max_slices * sseu->ss_stride;
+	eu_length = sseu->max_slices * sseu->max_subslices * sseu->eu_stride;
 	total_length = sizeof(topo) + slice_length + subslice_length +
 		       eu_length;
 
@@ -69,9 +67,9 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
 	topo.max_eus_per_subslice = sseu->max_eus_per_subslice;
 
 	topo.subslice_offset = slice_length;
-	topo.subslice_stride = subslice_stride;
+	topo.subslice_stride = sseu->ss_stride;
 	topo.eu_offset = slice_length + subslice_length;
-	topo.eu_stride = eu_stride;
+	topo.eu_stride = sseu->eu_stride;
 
 	if (__copy_to_user(u64_to_user_ptr(query_item->data_ptr),
 			   &topo, sizeof(topo)))
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 97f742530fa1..3625f777f3a3 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -92,9 +92,9 @@ static void sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p)
 		   hweight8(sseu->slice_mask), sseu->slice_mask);
 	drm_printf(p, "subslice total: %u\n", intel_sseu_subslice_total(sseu));
 	for (s = 0; s < sseu->max_slices; s++) {
-		drm_printf(p, "slice%d: %u subslices, mask=%04x\n",
+		drm_printf(p, "slice%d: %u subslices, mask=%08x\n",
 			   s, intel_sseu_subslices_per_slice(sseu, s),
-			   sseu->subslice_mask[s]);
+			   intel_sseu_get_subslices(sseu, s));
 	}
 	drm_printf(p, "EU total: %u\n", sseu->eu_total);
 	drm_printf(p, "EU per subslice: %u\n", sseu->eu_per_subslice);
@@ -117,10 +117,9 @@ void intel_device_info_dump_runtime(const struct intel_runtime_info *info,
 static int sseu_eu_idx(const struct sseu_dev_info *sseu, int slice,
 		       int subslice)
 {
-	int subslice_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
-	int slice_stride = sseu->max_subslices * subslice_stride;
+	int slice_stride = sseu->max_subslices * sseu->eu_stride;
 
-	return slice * slice_stride + subslice * subslice_stride;
+	return slice * slice_stride + subslice * sseu->eu_stride;
 }
 
 static u16 sseu_get_eus(const struct sseu_dev_info *sseu, int slice,
@@ -129,7 +128,7 @@ static u16 sseu_get_eus(const struct sseu_dev_info *sseu, int slice,
 	int i, offset = sseu_eu_idx(sseu, slice, subslice);
 	u16 eu_mask = 0;
 
-	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
+	for (i = 0; i < sseu->eu_stride; i++) {
 		eu_mask |= ((u16)sseu->eu_mask[offset + i]) <<
 			(i * BITS_PER_BYTE);
 	}
@@ -142,7 +141,7 @@ static void sseu_set_eus(struct sseu_dev_info *sseu, int slice, int subslice,
 {
 	int i, offset = sseu_eu_idx(sseu, slice, subslice);
 
-	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
+	for (i = 0; i < sseu->eu_stride; i++) {
 		sseu->eu_mask[offset + i] =
 			(eu_mask >> (BITS_PER_BYTE * i)) & 0xff;
 	}
@@ -159,9 +158,9 @@ void intel_device_info_dump_topology(const struct sseu_dev_info *sseu,
 	}
 
 	for (s = 0; s < sseu->max_slices; s++) {
-		drm_printf(p, "slice%d: %u subslice(s) (0x%hhx):\n",
+		drm_printf(p, "slice%d: %u subslice(s) (0x%08x):\n",
 			   s, intel_sseu_subslices_per_slice(sseu, s),
-			   sseu->subslice_mask[s]);
+			   intel_sseu_get_subslices(sseu, s));
 
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			u16 enabled_eus = sseu_get_eus(sseu, s, ss);
@@ -190,15 +189,10 @@ static void gen11_sseu_info_init(struct drm_i915_private *dev_priv)
 	u8 eu_en;
 	int s;
 
-	if (IS_ELKHARTLAKE(dev_priv)) {
-		sseu->max_slices = 1;
-		sseu->max_subslices = 4;
-		sseu->max_eus_per_subslice = 8;
-	} else {
-		sseu->max_slices = 1;
-		sseu->max_subslices = 8;
-		sseu->max_eus_per_subslice = 8;
-	}
+	if (IS_ELKHARTLAKE(dev_priv))
+		intel_sseu_set_info(sseu, 1, 4, 8);
+	else
+		intel_sseu_set_info(sseu, 1, 8, 8);
 
 	s_en = I915_READ(GEN11_GT_SLICE_ENABLE) & GEN11_GT_S_ENA_MASK;
 	ss_en = ~I915_READ(GEN11_GT_SUBSLICE_DISABLE);
@@ -207,15 +201,15 @@ static void gen11_sseu_info_init(struct drm_i915_private *dev_priv)
 
 	for (s = 0; s < sseu->max_slices; s++) {
 		if (s_en & BIT(s)) {
-			int ss_idx = sseu->max_subslices * s;
 			int ss;
 
 			sseu->slice_mask |= BIT(s);
-			sseu->subslice_mask[s] = (ss_en >> ss_idx) & ss_en_mask;
-			for (ss = 0; ss < sseu->max_subslices; ss++) {
-				if (sseu->subslice_mask[s] & BIT(ss))
+
+			intel_sseu_set_subslices(sseu, s, ss_en_mask);
+
+			for (ss = 0; ss < sseu->max_subslices; ss++)
+				if (intel_sseu_has_subslice(sseu, s, ss))
 					sseu_set_eus(sseu, s, ss, eu_en);
-			}
 		}
 	}
 	sseu->eu_per_subslice = hweight8(eu_en);
@@ -235,23 +229,10 @@ static void gen10_sseu_info_init(struct drm_i915_private *dev_priv)
 	const int eu_mask = 0xff;
 	u32 subslice_mask, eu_en;
 
+	intel_sseu_set_info(sseu, 6, 4, 8);
+
 	sseu->slice_mask = (fuse2 & GEN10_F2_S_ENA_MASK) >>
 			    GEN10_F2_S_ENA_SHIFT;
-	sseu->max_slices = 6;
-	sseu->max_subslices = 4;
-	sseu->max_eus_per_subslice = 8;
-
-	subslice_mask = (1 << 4) - 1;
-	subslice_mask &= ~((fuse2 & GEN10_F2_SS_DIS_MASK) >>
-			   GEN10_F2_SS_DIS_SHIFT);
-
-	/*
-	 * Slice0 can have up to 3 subslices, but there are only 2 in
-	 * slice1/2.
-	 */
-	sseu->subslice_mask[0] = subslice_mask;
-	for (s = 1; s < sseu->max_slices; s++)
-		sseu->subslice_mask[s] = subslice_mask & 0x3;
 
 	/* Slice0 */
 	eu_en = ~I915_READ(GEN8_EU_DISABLE0);
@@ -276,14 +257,22 @@ static void gen10_sseu_info_init(struct drm_i915_private *dev_priv)
 	eu_en = ~I915_READ(GEN10_EU_DISABLE3);
 	sseu_set_eus(sseu, 5, 1, eu_en & eu_mask);
 
-	/* Do a second pass where we mark the subslices disabled if all their
-	 * eus are off.
-	 */
+	subslice_mask = (1 << 4) - 1;
+	subslice_mask &= ~((fuse2 & GEN10_F2_SS_DIS_MASK) >>
+			   GEN10_F2_SS_DIS_SHIFT);
+
 	for (s = 0; s < sseu->max_slices; s++) {
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			if (sseu_get_eus(sseu, s, ss) == 0)
-				sseu->subslice_mask[s] &= ~BIT(ss);
+				subslice_mask &= ~BIT(ss);
 		}
+
+		/*
+		 * Slice0 can have up to 3 subslices, but there are only 2 in
+		 * slice1/2.
+		 */
+		intel_sseu_set_subslices(sseu, s, s == 0 ? subslice_mask :
+							   subslice_mask & 0x3);
 	}
 
 	sseu->eu_total = compute_eu_total(sseu);
@@ -309,13 +298,12 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
 {
 	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	u32 fuse;
+	u8 subslice_mask;
 
 	fuse = I915_READ(CHV_FUSE_GT);
 
 	sseu->slice_mask = BIT(0);
-	sseu->max_slices = 1;
-	sseu->max_subslices = 2;
-	sseu->max_eus_per_subslice = 8;
+	intel_sseu_set_info(sseu, 1, 2, 8);
 
 	if (!(fuse & CHV_FGT_DISABLE_SS0)) {
 		u8 disabled_mask =
@@ -324,7 +312,7 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
 			(((fuse & CHV_FGT_EU_DIS_SS0_R1_MASK) >>
 			  CHV_FGT_EU_DIS_SS0_R1_SHIFT) << 4);
 
-		sseu->subslice_mask[0] |= BIT(0);
+		subslice_mask |= BIT(0);
 		sseu_set_eus(sseu, 0, 0, ~disabled_mask);
 	}
 
@@ -335,10 +323,12 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
 			(((fuse & CHV_FGT_EU_DIS_SS1_R1_MASK) >>
 			  CHV_FGT_EU_DIS_SS1_R1_SHIFT) << 4);
 
-		sseu->subslice_mask[0] |= BIT(1);
+		subslice_mask |= BIT(1);
 		sseu_set_eus(sseu, 0, 1, ~disabled_mask);
 	}
 
+	intel_sseu_set_subslices(sseu, 0, subslice_mask);
+
 	sseu->eu_total = compute_eu_total(sseu);
 
 	/*
@@ -371,9 +361,8 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
 
 	/* BXT has a single slice and at most 3 subslices. */
-	sseu->max_slices = IS_GEN9_LP(dev_priv) ? 1 : 3;
-	sseu->max_subslices = IS_GEN9_LP(dev_priv) ? 3 : 4;
-	sseu->max_eus_per_subslice = 8;
+	intel_sseu_set_info(sseu, IS_GEN9_LP(dev_priv) ? 1 : 3,
+			    IS_GEN9_LP(dev_priv) ? 3 : 4, 8);
 
 	/*
 	 * The subslice disable field is global, i.e. it applies
@@ -392,14 +381,14 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 			/* skip disabled slice */
 			continue;
 
-		sseu->subslice_mask[s] = subslice_mask;
+		intel_sseu_set_subslices(sseu, s, subslice_mask);
 
 		eu_disable = I915_READ(GEN9_EU_DISABLE(s));
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			int eu_per_ss;
 			u8 eu_disabled_mask;
 
-			if (!(sseu->subslice_mask[s] & BIT(ss)))
+			if (!intel_sseu_has_subslice(sseu, s, ss))
 				/* skip disabled subslice */
 				continue;
 
@@ -472,9 +461,7 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
 
 	fuse2 = I915_READ(GEN8_FUSE2);
 	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
-	sseu->max_slices = 3;
-	sseu->max_subslices = 3;
-	sseu->max_eus_per_subslice = 8;
+	intel_sseu_set_info(sseu, 3, 3, 8);
 
 	/*
 	 * The subslice disable field is global, i.e. it applies
@@ -501,18 +488,19 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
 			/* skip disabled slice */
 			continue;
 
-		sseu->subslice_mask[s] = subslice_mask;
+		intel_sseu_set_subslices(sseu, s, subslice_mask);
 
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			u8 eu_disabled_mask;
 			u32 n_disabled;
 
-			if (!(sseu->subslice_mask[s] & BIT(ss)))
+			if (!intel_sseu_has_subslice(sseu, s, ss))
 				/* skip disabled subslice */
 				continue;
 
 			eu_disabled_mask =
-				eu_disable[s] >> (ss * sseu->max_eus_per_subslice);
+				eu_disable[s] >>
+					(ss * sseu->max_eus_per_subslice);
 
 			sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
 
@@ -552,6 +540,7 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	u32 fuse1;
 	int s, ss;
+	u32 subslice_mask;
 
 	/*
 	 * There isn't a register to tell us how many slices/subslices. We
@@ -563,22 +552,18 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 		/* fall through */
 	case 1:
 		sseu->slice_mask = BIT(0);
-		sseu->subslice_mask[0] = BIT(0);
+		subslice_mask = BIT(0);
 		break;
 	case 2:
 		sseu->slice_mask = BIT(0);
-		sseu->subslice_mask[0] = BIT(0) | BIT(1);
+		subslice_mask = BIT(0) | BIT(1);
 		break;
 	case 3:
 		sseu->slice_mask = BIT(0) | BIT(1);
-		sseu->subslice_mask[0] = BIT(0) | BIT(1);
-		sseu->subslice_mask[1] = BIT(0) | BIT(1);
+		subslice_mask = BIT(0) | BIT(1);
 		break;
 	}
 
-	sseu->max_slices = hweight8(sseu->slice_mask);
-	sseu->max_subslices = hweight8(sseu->subslice_mask[0]);
-
 	fuse1 = I915_READ(HSW_PAVP_FUSE1);
 	switch ((fuse1 & HSW_F1_EU_DIS_MASK) >> HSW_F1_EU_DIS_SHIFT) {
 	default:
@@ -595,9 +580,14 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 		sseu->eu_per_subslice = 6;
 		break;
 	}
-	sseu->max_eus_per_subslice = sseu->eu_per_subslice;
+
+	intel_sseu_set_info(sseu, hweight8(sseu->slice_mask),
+			    hweight8(subslice_mask),
+			    sseu->eu_per_subslice);
 
 	for (s = 0; s < sseu->max_slices; s++) {
+		intel_sseu_set_subslices(sseu, s, subslice_mask);
+
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			sseu_set_eus(sseu, s, ss,
 				     (1UL << sseu->eu_per_subslice) - 1);
-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 5/5] drm/i915: Expand subslice mask

[Daniele Ceraolo Spurio]

<snip>

> --- a/drivers/gpu/drm/i915/gt/intel_sseu.h
> +++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
> @@ -9,16 +9,18 @@
>   
>   #include <linux/types.h>
>   #include <linux/kernel.h>
> +#include <linux/string.h>

AFAICS this header is not needed anymore. With it removed:

Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>

Daniele

>   
>   struct drm_i915_private;
>   
>   #define GEN_MAX_SLICES		(6) /* CNL upper bound */
>   #define GEN_MAX_SUBSLICES	(8) /* ICL upper bound */
>   #define GEN_SSEU_STRIDE(max_entries) DIV_ROUND_UP(max_entries, BITS_PER_BYTE)
> +#define GEN_MAX_SUBSLICE_STRIDE GEN_SSEU_STRIDE(GEN_MAX_SUBSLICES)
>   
>   struct sseu_dev_info {
>   	u8 slice_mask;
> -	u8 subslice_mask[GEN_MAX_SLICES];
> +	u8 subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
>   	u16 eu_total;
>   	u8 eu_per_subslice;
>   	u8 min_eu_in_pool;
> @@ -33,6 +35,9 @@ struct sseu_dev_info {
>   	u8 max_subslices;
>   	u8 max_eus_per_subslice;
>   
> +	u8 ss_stride;
> +	u8 eu_stride;
> +
>   	/* We don't have more than 8 eus per subslice at the moment and as we
>   	 * store eus enabled using bits, no need to multiply by eus per
>   	 * subslice.
> @@ -63,12 +68,33 @@ intel_sseu_from_device_info(const struct sseu_dev_info *sseu)
>   	return value;
>   }
>   
> +static inline bool
> +intel_sseu_has_subslice(const struct sseu_dev_info *sseu, int slice,
> +			int subslice)
> +{
> +	u8 mask = sseu->subslice_mask[slice * sseu->ss_stride +
> +				      subslice / BITS_PER_BYTE];
> +
> +	return mask & BIT(subslice % BITS_PER_BYTE);
> +}
> +
> +void intel_sseu_set_info(struct sseu_dev_info *sseu, u8 max_slices,
> +			 u8 max_subslices, u8 max_eus_per_subslice);
> +
>   unsigned int
>   intel_sseu_subslice_total(const struct sseu_dev_info *sseu);
>   
>   unsigned int
>   intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice);
>   
> +void intel_sseu_copy_subslices(const struct sseu_dev_info *sseu, int slice,
> +			       u8 *to_mask);
> +
> +u32  intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice);
> +
> +void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
> +			      u32 ss_mask);
> +
>   u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
>   			 const struct intel_sseu *req_sseu);
>   
> diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
> index 43e290306551..8437f9d918ec 100644
> --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
> +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
> @@ -767,7 +767,7 @@ wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal)
>   		u32 slice = fls(sseu->slice_mask);
>   		u32 fuse3 =
>   			intel_uncore_read(&i915->uncore, GEN10_MIRROR_FUSE3);
> -		u8 ss_mask = sseu->subslice_mask[slice];
> +		u32 ss_mask = intel_sseu_get_subslices(sseu, slice);
>   
>   		u8 enabled_mask = (ss_mask | ss_mask >>
>   				   GEN10_L3BANK_PAIR_COUNT) & GEN10_L3BANK_MASK;
> diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
> index a26015722405..46365ab957e6 100644
> --- a/drivers/gpu/drm/i915/i915_debugfs.c
> +++ b/drivers/gpu/drm/i915/i915_debugfs.c
> @@ -1259,6 +1259,7 @@ static void i915_instdone_info(struct drm_i915_private *dev_priv,
>   			       struct seq_file *m,
>   			       struct intel_instdone *instdone)
>   {
> +	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
>   	int slice;
>   	int subslice;
>   
> @@ -1274,11 +1275,11 @@ static void i915_instdone_info(struct drm_i915_private *dev_priv,
>   	if (INTEL_GEN(dev_priv) <= 6)
>   		return;
>   
> -	for_each_instdone_slice_subslice(dev_priv, slice, subslice)
> +	for_each_instdone_slice_subslice(dev_priv, sseu, slice, subslice)
>   		seq_printf(m, "\t\tSAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
>   			   slice, subslice, instdone->sampler[slice][subslice]);
>   
> -	for_each_instdone_slice_subslice(dev_priv, slice, subslice)
> +	for_each_instdone_slice_subslice(dev_priv, sseu, slice, subslice)
>   		seq_printf(m, "\t\tROW_INSTDONE[%d][%d]: 0x%08x\n",
>   			   slice, subslice, instdone->row[slice][subslice]);
>   }
> @@ -4072,7 +4073,7 @@ static void gen10_sseu_device_status(struct drm_i915_private *dev_priv,
>   			continue;
>   
>   		sseu->slice_mask |= BIT(s);
> -		sseu->subslice_mask[s] = info->sseu.subslice_mask[s];
> +		intel_sseu_copy_subslices(&info->sseu, s, sseu->subslice_mask);
>   
>   		for (ss = 0; ss < info->sseu.max_subslices; ss++) {
>   			unsigned int eu_cnt;
> @@ -4123,18 +4124,21 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
>   		sseu->slice_mask |= BIT(s);
>   
>   		if (IS_GEN9_BC(dev_priv))
> -			sseu->subslice_mask[s] =
> -				RUNTIME_INFO(dev_priv)->sseu.subslice_mask[s];
> +			intel_sseu_copy_subslices(&info->sseu, s,
> +						  sseu->subslice_mask);
>   
>   		for (ss = 0; ss < info->sseu.max_subslices; ss++) {
>   			unsigned int eu_cnt;
> +			u8 ss_idx = s * info->sseu.ss_stride +
> +				    ss / BITS_PER_BYTE;
>   
>   			if (IS_GEN9_LP(dev_priv)) {
>   				if (!(s_reg[s] & (GEN9_PGCTL_SS_ACK(ss))))
>   					/* skip disabled subslice */
>   					continue;
>   
> -				sseu->subslice_mask[s] |= BIT(ss);
> +				sseu->subslice_mask[ss_idx] |=
> +					BIT(ss % BITS_PER_BYTE);
>   			}
>   
>   			eu_cnt = 2 * hweight32(eu_reg[2*s + ss/2] &
> @@ -4151,25 +4155,23 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
>   static void broadwell_sseu_device_status(struct drm_i915_private *dev_priv,
>   					 struct sseu_dev_info *sseu)
>   {
> +	struct intel_runtime_info *info = RUNTIME_INFO(dev_priv);
>   	u32 slice_info = I915_READ(GEN8_GT_SLICE_INFO);
>   	int s;
>   
>   	sseu->slice_mask = slice_info & GEN8_LSLICESTAT_MASK;
>   
>   	if (sseu->slice_mask) {
> -		sseu->eu_per_subslice =
> -			RUNTIME_INFO(dev_priv)->sseu.eu_per_subslice;
> -		for (s = 0; s < fls(sseu->slice_mask); s++) {
> -			sseu->subslice_mask[s] =
> -				RUNTIME_INFO(dev_priv)->sseu.subslice_mask[s];
> -		}
> +		sseu->eu_per_subslice = info->sseu.eu_per_subslice;
> +		for (s = 0; s < fls(sseu->slice_mask); s++)
> +			intel_sseu_copy_subslices(&info->sseu, s,
> +						  sseu->subslice_mask);
>   		sseu->eu_total = sseu->eu_per_subslice *
>   				 intel_sseu_subslice_total(sseu);
>   
>   		/* subtract fused off EU(s) from enabled slice(s) */
>   		for (s = 0; s < fls(sseu->slice_mask); s++) {
> -			u8 subslice_7eu =
> -				RUNTIME_INFO(dev_priv)->sseu.subslice_7eu[s];
> +			u8 subslice_7eu = info->sseu.subslice_7eu[s];
>   
>   			sseu->eu_total -= hweight8(subslice_7eu);
>   		}
> @@ -4216,6 +4218,7 @@ static void i915_print_sseu_info(struct seq_file *m, bool is_available_info,
>   static int i915_sseu_status(struct seq_file *m, void *unused)
>   {
>   	struct drm_i915_private *dev_priv = node_to_i915(m->private);
> +	const struct intel_runtime_info *info = RUNTIME_INFO(dev_priv);
>   	struct sseu_dev_info sseu;
>   	intel_wakeref_t wakeref;
>   
> @@ -4223,14 +4226,13 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
>   		return -ENODEV;
>   
>   	seq_puts(m, "SSEU Device Info\n");
> -	i915_print_sseu_info(m, true, &RUNTIME_INFO(dev_priv)->sseu);
> +	i915_print_sseu_info(m, true, &info->sseu);
>   
>   	seq_puts(m, "SSEU Device Status\n");
>   	memset(&sseu, 0, sizeof(sseu));
> -	sseu.max_slices = RUNTIME_INFO(dev_priv)->sseu.max_slices;
> -	sseu.max_subslices = RUNTIME_INFO(dev_priv)->sseu.max_subslices;
> -	sseu.max_eus_per_subslice =
> -		RUNTIME_INFO(dev_priv)->sseu.max_eus_per_subslice;
> +	intel_sseu_set_info(&sseu, info->sseu.max_slices,
> +			    info->sseu.max_subslices,
> +			    info->sseu.max_eus_per_subslice);
>   
>   	with_intel_runtime_pm(dev_priv, wakeref) {
>   		if (IS_CHERRYVIEW(dev_priv))
> diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
> index 8a7d4dea8609..dc6bafc09b36 100644
> --- a/drivers/gpu/drm/i915/i915_drv.c
> +++ b/drivers/gpu/drm/i915/i915_drv.c
> @@ -331,7 +331,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
>   	struct pci_dev *pdev = dev_priv->drm.pdev;
>   	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
>   	drm_i915_getparam_t *param = data;
> -	int value;
> +	int value = 0;
>   
>   	switch (param->param) {
>   	case I915_PARAM_IRQ_ACTIVE:
> @@ -460,7 +460,9 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
>   			return -ENODEV;
>   		break;
>   	case I915_PARAM_SUBSLICE_MASK:
> -		value = sseu->subslice_mask[0];
> +		/* Only copy bits from the first slice */
> +		memcpy(&value, sseu->subslice_mask,
> +		       min(sseu->ss_stride, (u8)sizeof(value)));
>   		if (!value)
>   			return -ENODEV;
>   		break;
> diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
> index 4f85cbdddb0d..c760cc5b3388 100644
> --- a/drivers/gpu/drm/i915/i915_gpu_error.c
> +++ b/drivers/gpu/drm/i915/i915_gpu_error.c
> @@ -408,6 +408,7 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m,
>   static void error_print_instdone(struct drm_i915_error_state_buf *m,
>   				 const struct drm_i915_error_engine *ee)
>   {
> +	struct sseu_dev_info *sseu = &RUNTIME_INFO(m->i915)->sseu;
>   	int slice;
>   	int subslice;
>   
> @@ -423,12 +424,12 @@ static void error_print_instdone(struct drm_i915_error_state_buf *m,
>   	if (INTEL_GEN(m->i915) <= 6)
>   		return;
>   
> -	for_each_instdone_slice_subslice(m->i915, slice, subslice)
> +	for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
>   		err_printf(m, "  SAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
>   			   slice, subslice,
>   			   ee->instdone.sampler[slice][subslice]);
>   
> -	for_each_instdone_slice_subslice(m->i915, slice, subslice)
> +	for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
>   		err_printf(m, "  ROW_INSTDONE[%d][%d]: 0x%08x\n",
>   			   slice, subslice,
>   			   ee->instdone.row[slice][subslice]);
> diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
> index 7c1708c22811..000dcb145ce0 100644
> --- a/drivers/gpu/drm/i915/i915_query.c
> +++ b/drivers/gpu/drm/i915/i915_query.c
> @@ -37,8 +37,6 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
>   	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
>   	struct drm_i915_query_topology_info topo;
>   	u32 slice_length, subslice_length, eu_length, total_length;
> -	u8 subslice_stride = GEN_SSEU_STRIDE(sseu->max_subslices);
> -	u8 eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
>   	int ret;
>   
>   	if (query_item->flags != 0)
> @@ -50,8 +48,8 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
>   	BUILD_BUG_ON(sizeof(u8) != sizeof(sseu->slice_mask));
>   
>   	slice_length = sizeof(sseu->slice_mask);
> -	subslice_length = sseu->max_slices * subslice_stride;
> -	eu_length = sseu->max_slices * sseu->max_subslices * eu_stride;
> +	subslice_length = sseu->max_slices * sseu->ss_stride;
> +	eu_length = sseu->max_slices * sseu->max_subslices * sseu->eu_stride;
>   	total_length = sizeof(topo) + slice_length + subslice_length +
>   		       eu_length;
>   
> @@ -69,9 +67,9 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
>   	topo.max_eus_per_subslice = sseu->max_eus_per_subslice;
>   
>   	topo.subslice_offset = slice_length;
> -	topo.subslice_stride = subslice_stride;
> +	topo.subslice_stride = sseu->ss_stride;
>   	topo.eu_offset = slice_length + subslice_length;
> -	topo.eu_stride = eu_stride;
> +	topo.eu_stride = sseu->eu_stride;
>   
>   	if (__copy_to_user(u64_to_user_ptr(query_item->data_ptr),
>   			   &topo, sizeof(topo)))
> diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
> index 97f742530fa1..3625f777f3a3 100644
> --- a/drivers/gpu/drm/i915/intel_device_info.c
> +++ b/drivers/gpu/drm/i915/intel_device_info.c
> @@ -92,9 +92,9 @@ static void sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p)
>   		   hweight8(sseu->slice_mask), sseu->slice_mask);
>   	drm_printf(p, "subslice total: %u\n", intel_sseu_subslice_total(sseu));
>   	for (s = 0; s < sseu->max_slices; s++) {
> -		drm_printf(p, "slice%d: %u subslices, mask=%04x\n",
> +		drm_printf(p, "slice%d: %u subslices, mask=%08x\n",
>   			   s, intel_sseu_subslices_per_slice(sseu, s),
> -			   sseu->subslice_mask[s]);
> +			   intel_sseu_get_subslices(sseu, s));
>   	}
>   	drm_printf(p, "EU total: %u\n", sseu->eu_total);
>   	drm_printf(p, "EU per subslice: %u\n", sseu->eu_per_subslice);
> @@ -117,10 +117,9 @@ void intel_device_info_dump_runtime(const struct intel_runtime_info *info,
>   static int sseu_eu_idx(const struct sseu_dev_info *sseu, int slice,
>   		       int subslice)
>   {
> -	int subslice_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
> -	int slice_stride = sseu->max_subslices * subslice_stride;
> +	int slice_stride = sseu->max_subslices * sseu->eu_stride;
>   
> -	return slice * slice_stride + subslice * subslice_stride;
> +	return slice * slice_stride + subslice * sseu->eu_stride;
>   }
>   
>   static u16 sseu_get_eus(const struct sseu_dev_info *sseu, int slice,
> @@ -129,7 +128,7 @@ static u16 sseu_get_eus(const struct sseu_dev_info *sseu, int slice,
>   	int i, offset = sseu_eu_idx(sseu, slice, subslice);
>   	u16 eu_mask = 0;
>   
> -	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
> +	for (i = 0; i < sseu->eu_stride; i++) {
>   		eu_mask |= ((u16)sseu->eu_mask[offset + i]) <<
>   			(i * BITS_PER_BYTE);
>   	}
> @@ -142,7 +141,7 @@ static void sseu_set_eus(struct sseu_dev_info *sseu, int slice, int subslice,
>   {
>   	int i, offset = sseu_eu_idx(sseu, slice, subslice);
>   
> -	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
> +	for (i = 0; i < sseu->eu_stride; i++) {
>   		sseu->eu_mask[offset + i] =
>   			(eu_mask >> (BITS_PER_BYTE * i)) & 0xff;
>   	}
> @@ -159,9 +158,9 @@ void intel_device_info_dump_topology(const struct sseu_dev_info *sseu,
>   	}
>   
>   	for (s = 0; s < sseu->max_slices; s++) {
> -		drm_printf(p, "slice%d: %u subslice(s) (0x%hhx):\n",
> +		drm_printf(p, "slice%d: %u subslice(s) (0x%08x):\n",
>   			   s, intel_sseu_subslices_per_slice(sseu, s),
> -			   sseu->subslice_mask[s]);
> +			   intel_sseu_get_subslices(sseu, s));
>   
>   		for (ss = 0; ss < sseu->max_subslices; ss++) {
>   			u16 enabled_eus = sseu_get_eus(sseu, s, ss);
> @@ -190,15 +189,10 @@ static void gen11_sseu_info_init(struct drm_i915_private *dev_priv)
>   	u8 eu_en;
>   	int s;
>   
> -	if (IS_ELKHARTLAKE(dev_priv)) {
> -		sseu->max_slices = 1;
> -		sseu->max_subslices = 4;
> -		sseu->max_eus_per_subslice = 8;
> -	} else {
> -		sseu->max_slices = 1;
> -		sseu->max_subslices = 8;
> -		sseu->max_eus_per_subslice = 8;
> -	}
> +	if (IS_ELKHARTLAKE(dev_priv))
> +		intel_sseu_set_info(sseu, 1, 4, 8);
> +	else
> +		intel_sseu_set_info(sseu, 1, 8, 8);
>   
>   	s_en = I915_READ(GEN11_GT_SLICE_ENABLE) & GEN11_GT_S_ENA_MASK;
>   	ss_en = ~I915_READ(GEN11_GT_SUBSLICE_DISABLE);
> @@ -207,15 +201,15 @@ static void gen11_sseu_info_init(struct drm_i915_private *dev_priv)
>   
>   	for (s = 0; s < sseu->max_slices; s++) {
>   		if (s_en & BIT(s)) {
> -			int ss_idx = sseu->max_subslices * s;
>   			int ss;
>   
>   			sseu->slice_mask |= BIT(s);
> -			sseu->subslice_mask[s] = (ss_en >> ss_idx) & ss_en_mask;
> -			for (ss = 0; ss < sseu->max_subslices; ss++) {
> -				if (sseu->subslice_mask[s] & BIT(ss))
> +
> +			intel_sseu_set_subslices(sseu, s, ss_en_mask);
> +
> +			for (ss = 0; ss < sseu->max_subslices; ss++)
> +				if (intel_sseu_has_subslice(sseu, s, ss))
>   					sseu_set_eus(sseu, s, ss, eu_en);
> -			}
>   		}
>   	}
>   	sseu->eu_per_subslice = hweight8(eu_en);
> @@ -235,23 +229,10 @@ static void gen10_sseu_info_init(struct drm_i915_private *dev_priv)
>   	const int eu_mask = 0xff;
>   	u32 subslice_mask, eu_en;
>   
> +	intel_sseu_set_info(sseu, 6, 4, 8);
> +
>   	sseu->slice_mask = (fuse2 & GEN10_F2_S_ENA_MASK) >>
>   			    GEN10_F2_S_ENA_SHIFT;
> -	sseu->max_slices = 6;
> -	sseu->max_subslices = 4;
> -	sseu->max_eus_per_subslice = 8;
> -
> -	subslice_mask = (1 << 4) - 1;
> -	subslice_mask &= ~((fuse2 & GEN10_F2_SS_DIS_MASK) >>
> -			   GEN10_F2_SS_DIS_SHIFT);
> -
> -	/*
> -	 * Slice0 can have up to 3 subslices, but there are only 2 in
> -	 * slice1/2.
> -	 */
> -	sseu->subslice_mask[0] = subslice_mask;
> -	for (s = 1; s < sseu->max_slices; s++)
> -		sseu->subslice_mask[s] = subslice_mask & 0x3;
>   
>   	/* Slice0 */
>   	eu_en = ~I915_READ(GEN8_EU_DISABLE0);
> @@ -276,14 +257,22 @@ static void gen10_sseu_info_init(struct drm_i915_private *dev_priv)
>   	eu_en = ~I915_READ(GEN10_EU_DISABLE3);
>   	sseu_set_eus(sseu, 5, 1, eu_en & eu_mask);
>   
> -	/* Do a second pass where we mark the subslices disabled if all their
> -	 * eus are off.
> -	 */
> +	subslice_mask = (1 << 4) - 1;
> +	subslice_mask &= ~((fuse2 & GEN10_F2_SS_DIS_MASK) >>
> +			   GEN10_F2_SS_DIS_SHIFT);
> +
>   	for (s = 0; s < sseu->max_slices; s++) {
>   		for (ss = 0; ss < sseu->max_subslices; ss++) {
>   			if (sseu_get_eus(sseu, s, ss) == 0)
> -				sseu->subslice_mask[s] &= ~BIT(ss);
> +				subslice_mask &= ~BIT(ss);
>   		}
> +
> +		/*
> +		 * Slice0 can have up to 3 subslices, but there are only 2 in
> +		 * slice1/2.
> +		 */
> +		intel_sseu_set_subslices(sseu, s, s == 0 ? subslice_mask :
> +							   subslice_mask & 0x3);
>   	}
>   
>   	sseu->eu_total = compute_eu_total(sseu);
> @@ -309,13 +298,12 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
>   {
>   	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
>   	u32 fuse;
> +	u8 subslice_mask;
>   
>   	fuse = I915_READ(CHV_FUSE_GT);
>   
>   	sseu->slice_mask = BIT(0);
> -	sseu->max_slices = 1;
> -	sseu->max_subslices = 2;
> -	sseu->max_eus_per_subslice = 8;
> +	intel_sseu_set_info(sseu, 1, 2, 8);
>   
>   	if (!(fuse & CHV_FGT_DISABLE_SS0)) {
>   		u8 disabled_mask =
> @@ -324,7 +312,7 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
>   			(((fuse & CHV_FGT_EU_DIS_SS0_R1_MASK) >>
>   			  CHV_FGT_EU_DIS_SS0_R1_SHIFT) << 4);
>   
> -		sseu->subslice_mask[0] |= BIT(0);
> +		subslice_mask |= BIT(0);
>   		sseu_set_eus(sseu, 0, 0, ~disabled_mask);
>   	}
>   
> @@ -335,10 +323,12 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
>   			(((fuse & CHV_FGT_EU_DIS_SS1_R1_MASK) >>
>   			  CHV_FGT_EU_DIS_SS1_R1_SHIFT) << 4);
>   
> -		sseu->subslice_mask[0] |= BIT(1);
> +		subslice_mask |= BIT(1);
>   		sseu_set_eus(sseu, 0, 1, ~disabled_mask);
>   	}
>   
> +	intel_sseu_set_subslices(sseu, 0, subslice_mask);
> +
>   	sseu->eu_total = compute_eu_total(sseu);
>   
>   	/*
> @@ -371,9 +361,8 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
>   	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
>   
>   	/* BXT has a single slice and at most 3 subslices. */
> -	sseu->max_slices = IS_GEN9_LP(dev_priv) ? 1 : 3;
> -	sseu->max_subslices = IS_GEN9_LP(dev_priv) ? 3 : 4;
> -	sseu->max_eus_per_subslice = 8;
> +	intel_sseu_set_info(sseu, IS_GEN9_LP(dev_priv) ? 1 : 3,
> +			    IS_GEN9_LP(dev_priv) ? 3 : 4, 8);
>   
>   	/*
>   	 * The subslice disable field is global, i.e. it applies
> @@ -392,14 +381,14 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
>   			/* skip disabled slice */
>   			continue;
>   
> -		sseu->subslice_mask[s] = subslice_mask;
> +		intel_sseu_set_subslices(sseu, s, subslice_mask);
>   
>   		eu_disable = I915_READ(GEN9_EU_DISABLE(s));
>   		for (ss = 0; ss < sseu->max_subslices; ss++) {
>   			int eu_per_ss;
>   			u8 eu_disabled_mask;
>   
> -			if (!(sseu->subslice_mask[s] & BIT(ss)))
> +			if (!intel_sseu_has_subslice(sseu, s, ss))
>   				/* skip disabled subslice */
>   				continue;
>   
> @@ -472,9 +461,7 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
>   
>   	fuse2 = I915_READ(GEN8_FUSE2);
>   	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
> -	sseu->max_slices = 3;
> -	sseu->max_subslices = 3;
> -	sseu->max_eus_per_subslice = 8;
> +	intel_sseu_set_info(sseu, 3, 3, 8);
>   
>   	/*
>   	 * The subslice disable field is global, i.e. it applies
> @@ -501,18 +488,19 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
>   			/* skip disabled slice */
>   			continue;
>   
> -		sseu->subslice_mask[s] = subslice_mask;
> +		intel_sseu_set_subslices(sseu, s, subslice_mask);
>   
>   		for (ss = 0; ss < sseu->max_subslices; ss++) {
>   			u8 eu_disabled_mask;
>   			u32 n_disabled;
>   
> -			if (!(sseu->subslice_mask[s] & BIT(ss)))
> +			if (!intel_sseu_has_subslice(sseu, s, ss))
>   				/* skip disabled subslice */
>   				continue;
>   
>   			eu_disabled_mask =
> -				eu_disable[s] >> (ss * sseu->max_eus_per_subslice);
> +				eu_disable[s] >>
> +					(ss * sseu->max_eus_per_subslice);
>   
>   			sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
>   
> @@ -552,6 +540,7 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
>   	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
>   	u32 fuse1;
>   	int s, ss;
> +	u32 subslice_mask;
>   
>   	/*
>   	 * There isn't a register to tell us how many slices/subslices. We
> @@ -563,22 +552,18 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
>   		/* fall through */
>   	case 1:
>   		sseu->slice_mask = BIT(0);
> -		sseu->subslice_mask[0] = BIT(0);
> +		subslice_mask = BIT(0);
>   		break;
>   	case 2:
>   		sseu->slice_mask = BIT(0);
> -		sseu->subslice_mask[0] = BIT(0) | BIT(1);
> +		subslice_mask = BIT(0) | BIT(1);
>   		break;
>   	case 3:
>   		sseu->slice_mask = BIT(0) | BIT(1);
> -		sseu->subslice_mask[0] = BIT(0) | BIT(1);
> -		sseu->subslice_mask[1] = BIT(0) | BIT(1);
> +		subslice_mask = BIT(0) | BIT(1);
>   		break;
>   	}
>   
> -	sseu->max_slices = hweight8(sseu->slice_mask);
> -	sseu->max_subslices = hweight8(sseu->subslice_mask[0]);
> -
>   	fuse1 = I915_READ(HSW_PAVP_FUSE1);
>   	switch ((fuse1 & HSW_F1_EU_DIS_MASK) >> HSW_F1_EU_DIS_SHIFT) {
>   	default:
> @@ -595,9 +580,14 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
>   		sseu->eu_per_subslice = 6;
>   		break;
>   	}
> -	sseu->max_eus_per_subslice = sseu->eu_per_subslice;
> +
> +	intel_sseu_set_info(sseu, hweight8(sseu->slice_mask),
> +			    hweight8(subslice_mask),
> +			    sseu->eu_per_subslice);
>   
>   	for (s = 0; s < sseu->max_slices; s++) {
> +		intel_sseu_set_subslices(sseu, s, subslice_mask);
> +
>   		for (ss = 0; ss < sseu->max_subslices; ss++) {
>   			sseu_set_eus(sseu, s, ss,
>   				     (1UL << sseu->eu_per_subslice) - 1);
> 
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 5/5] drm/i915: Expand subslice mask

[Summers, Stuart]

[-- Attachment #1.1: Type: text/plain, Size: 25175 bytes --]

On Thu, 2019-05-16 at 15:40 -0700, Daniele Ceraolo Spurio wrote:
> <snip>
> 
> > --- a/drivers/gpu/drm/i915/gt/intel_sseu.h
> > +++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
> > @@ -9,16 +9,18 @@
> >   
> >   #include <linux/types.h>
> >   #include <linux/kernel.h>
> > +#include <linux/string.h>
> 
> AFAICS this header is not needed anymore. With it removed:
> 
> Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>

Thanks for the review!

I do not believe I have push rights to drm-tip at this point. Can you
help with merging this series?

Thanks,
Stuart

> 
> Daniele
> 
> >   
> >   struct drm_i915_private;
> >   
> >   #define GEN_MAX_SLICES		(6) /* CNL upper bound */
> >   #define GEN_MAX_SUBSLICES	(8) /* ICL upper bound */
> >   #define GEN_SSEU_STRIDE(max_entries) DIV_ROUND_UP(max_entries,
> > BITS_PER_BYTE)
> > +#define GEN_MAX_SUBSLICE_STRIDE GEN_SSEU_STRIDE(GEN_MAX_SUBSLICES)
> >   
> >   struct sseu_dev_info {
> >   	u8 slice_mask;
> > -	u8 subslice_mask[GEN_MAX_SLICES];
> > +	u8 subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
> >   	u16 eu_total;
> >   	u8 eu_per_subslice;
> >   	u8 min_eu_in_pool;
> > @@ -33,6 +35,9 @@ struct sseu_dev_info {
> >   	u8 max_subslices;
> >   	u8 max_eus_per_subslice;
> >   
> > +	u8 ss_stride;
> > +	u8 eu_stride;
> > +
> >   	/* We don't have more than 8 eus per subslice at the moment and
> > as we
> >   	 * store eus enabled using bits, no need to multiply by eus per
> >   	 * subslice.
> > @@ -63,12 +68,33 @@ intel_sseu_from_device_info(const struct
> > sseu_dev_info *sseu)
> >   	return value;
> >   }
> >   
> > +static inline bool
> > +intel_sseu_has_subslice(const struct sseu_dev_info *sseu, int
> > slice,
> > +			int subslice)
> > +{
> > +	u8 mask = sseu->subslice_mask[slice * sseu->ss_stride +
> > +				      subslice / BITS_PER_BYTE];
> > +
> > +	return mask & BIT(subslice % BITS_PER_BYTE);
> > +}
> > +
> > +void intel_sseu_set_info(struct sseu_dev_info *sseu, u8
> > max_slices,
> > +			 u8 max_subslices, u8 max_eus_per_subslice);
> > +
> >   unsigned int
> >   intel_sseu_subslice_total(const struct sseu_dev_info *sseu);
> >   
> >   unsigned int
> >   intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu,
> > u8 slice);
> >   
> > +void intel_sseu_copy_subslices(const struct sseu_dev_info *sseu,
> > int slice,
> > +			       u8 *to_mask);
> > +
> > +u32  intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8
> > slice);
> > +
> > +void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int
> > slice,
> > +			      u32 ss_mask);
> > +
> >   u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
> >   			 const struct intel_sseu *req_sseu);
> >   
> > diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c
> > b/drivers/gpu/drm/i915/gt/intel_workarounds.c
> > index 43e290306551..8437f9d918ec 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
> > +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
> > @@ -767,7 +767,7 @@ wa_init_mcr(struct drm_i915_private *i915,
> > struct i915_wa_list *wal)
> >   		u32 slice = fls(sseu->slice_mask);
> >   		u32 fuse3 =
> >   			intel_uncore_read(&i915->uncore,
> > GEN10_MIRROR_FUSE3);
> > -		u8 ss_mask = sseu->subslice_mask[slice];
> > +		u32 ss_mask = intel_sseu_get_subslices(sseu, slice);
> >   
> >   		u8 enabled_mask = (ss_mask | ss_mask >>
> >   				   GEN10_L3BANK_PAIR_COUNT) &
> > GEN10_L3BANK_MASK;
> > diff --git a/drivers/gpu/drm/i915/i915_debugfs.c
> > b/drivers/gpu/drm/i915/i915_debugfs.c
> > index a26015722405..46365ab957e6 100644
> > --- a/drivers/gpu/drm/i915/i915_debugfs.c
> > +++ b/drivers/gpu/drm/i915/i915_debugfs.c
> > @@ -1259,6 +1259,7 @@ static void i915_instdone_info(struct
> > drm_i915_private *dev_priv,
> >   			       struct seq_file *m,
> >   			       struct intel_instdone *instdone)
> >   {
> > +	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
> >   	int slice;
> >   	int subslice;
> >   
> > @@ -1274,11 +1275,11 @@ static void i915_instdone_info(struct
> > drm_i915_private *dev_priv,
> >   	if (INTEL_GEN(dev_priv) <= 6)
> >   		return;
> >   
> > -	for_each_instdone_slice_subslice(dev_priv, slice, subslice)
> > +	for_each_instdone_slice_subslice(dev_priv, sseu, slice,
> > subslice)
> >   		seq_printf(m, "\t\tSAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
> >   			   slice, subslice, instdone-
> > >sampler[slice][subslice]);
> >   
> > -	for_each_instdone_slice_subslice(dev_priv, slice, subslice)
> > +	for_each_instdone_slice_subslice(dev_priv, sseu, slice,
> > subslice)
> >   		seq_printf(m, "\t\tROW_INSTDONE[%d][%d]: 0x%08x\n",
> >   			   slice, subslice, instdone-
> > >row[slice][subslice]);
> >   }
> > @@ -4072,7 +4073,7 @@ static void gen10_sseu_device_status(struct
> > drm_i915_private *dev_priv,
> >   			continue;
> >   
> >   		sseu->slice_mask |= BIT(s);
> > -		sseu->subslice_mask[s] = info->sseu.subslice_mask[s];
> > +		intel_sseu_copy_subslices(&info->sseu, s, sseu-
> > >subslice_mask);
> >   
> >   		for (ss = 0; ss < info->sseu.max_subslices; ss++) {
> >   			unsigned int eu_cnt;
> > @@ -4123,18 +4124,21 @@ static void gen9_sseu_device_status(struct
> > drm_i915_private *dev_priv,
> >   		sseu->slice_mask |= BIT(s);
> >   
> >   		if (IS_GEN9_BC(dev_priv))
> > -			sseu->subslice_mask[s] =
> > -				RUNTIME_INFO(dev_priv)-
> > >sseu.subslice_mask[s];
> > +			intel_sseu_copy_subslices(&info->sseu, s,
> > +						  sseu->subslice_mask);
> >   
> >   		for (ss = 0; ss < info->sseu.max_subslices; ss++) {
> >   			unsigned int eu_cnt;
> > +			u8 ss_idx = s * info->sseu.ss_stride +
> > +				    ss / BITS_PER_BYTE;
> >   
> >   			if (IS_GEN9_LP(dev_priv)) {
> >   				if (!(s_reg[s] &
> > (GEN9_PGCTL_SS_ACK(ss))))
> >   					/* skip disabled subslice */
> >   					continue;
> >   
> > -				sseu->subslice_mask[s] |= BIT(ss);
> > +				sseu->subslice_mask[ss_idx] |=
> > +					BIT(ss % BITS_PER_BYTE);
> >   			}
> >   
> >   			eu_cnt = 2 * hweight32(eu_reg[2*s + ss/2] &
> > @@ -4151,25 +4155,23 @@ static void gen9_sseu_device_status(struct
> > drm_i915_private *dev_priv,
> >   static void broadwell_sseu_device_status(struct drm_i915_private
> > *dev_priv,
> >   					 struct sseu_dev_info *sseu)
> >   {
> > +	struct intel_runtime_info *info = RUNTIME_INFO(dev_priv);
> >   	u32 slice_info = I915_READ(GEN8_GT_SLICE_INFO);
> >   	int s;
> >   
> >   	sseu->slice_mask = slice_info & GEN8_LSLICESTAT_MASK;
> >   
> >   	if (sseu->slice_mask) {
> > -		sseu->eu_per_subslice =
> > -			RUNTIME_INFO(dev_priv)->sseu.eu_per_subslice;
> > -		for (s = 0; s < fls(sseu->slice_mask); s++) {
> > -			sseu->subslice_mask[s] =
> > -				RUNTIME_INFO(dev_priv)-
> > >sseu.subslice_mask[s];
> > -		}
> > +		sseu->eu_per_subslice = info->sseu.eu_per_subslice;
> > +		for (s = 0; s < fls(sseu->slice_mask); s++)
> > +			intel_sseu_copy_subslices(&info->sseu, s,
> > +						  sseu->subslice_mask);
> >   		sseu->eu_total = sseu->eu_per_subslice *
> >   				 intel_sseu_subslice_total(sseu);
> >   
> >   		/* subtract fused off EU(s) from enabled slice(s) */
> >   		for (s = 0; s < fls(sseu->slice_mask); s++) {
> > -			u8 subslice_7eu =
> > -				RUNTIME_INFO(dev_priv)-
> > >sseu.subslice_7eu[s];
> > +			u8 subslice_7eu = info->sseu.subslice_7eu[s];
> >   
> >   			sseu->eu_total -= hweight8(subslice_7eu);
> >   		}
> > @@ -4216,6 +4218,7 @@ static void i915_print_sseu_info(struct
> > seq_file *m, bool is_available_info,
> >   static int i915_sseu_status(struct seq_file *m, void *unused)
> >   {
> >   	struct drm_i915_private *dev_priv = node_to_i915(m->private);
> > +	const struct intel_runtime_info *info = RUNTIME_INFO(dev_priv);
> >   	struct sseu_dev_info sseu;
> >   	intel_wakeref_t wakeref;
> >   
> > @@ -4223,14 +4226,13 @@ static int i915_sseu_status(struct seq_file
> > *m, void *unused)
> >   		return -ENODEV;
> >   
> >   	seq_puts(m, "SSEU Device Info\n");
> > -	i915_print_sseu_info(m, true, &RUNTIME_INFO(dev_priv)->sseu);
> > +	i915_print_sseu_info(m, true, &info->sseu);
> >   
> >   	seq_puts(m, "SSEU Device Status\n");
> >   	memset(&sseu, 0, sizeof(sseu));
> > -	sseu.max_slices = RUNTIME_INFO(dev_priv)->sseu.max_slices;
> > -	sseu.max_subslices = RUNTIME_INFO(dev_priv)-
> > >sseu.max_subslices;
> > -	sseu.max_eus_per_subslice =
> > -		RUNTIME_INFO(dev_priv)->sseu.max_eus_per_subslice;
> > +	intel_sseu_set_info(&sseu, info->sseu.max_slices,
> > +			    info->sseu.max_subslices,
> > +			    info->sseu.max_eus_per_subslice);
> >   
> >   	with_intel_runtime_pm(dev_priv, wakeref) {
> >   		if (IS_CHERRYVIEW(dev_priv))
> > diff --git a/drivers/gpu/drm/i915/i915_drv.c
> > b/drivers/gpu/drm/i915/i915_drv.c
> > index 8a7d4dea8609..dc6bafc09b36 100644
> > --- a/drivers/gpu/drm/i915/i915_drv.c
> > +++ b/drivers/gpu/drm/i915/i915_drv.c
> > @@ -331,7 +331,7 @@ static int i915_getparam_ioctl(struct
> > drm_device *dev, void *data,
> >   	struct pci_dev *pdev = dev_priv->drm.pdev;
> >   	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)-
> > >sseu;
> >   	drm_i915_getparam_t *param = data;
> > -	int value;
> > +	int value = 0;
> >   
> >   	switch (param->param) {
> >   	case I915_PARAM_IRQ_ACTIVE:
> > @@ -460,7 +460,9 @@ static int i915_getparam_ioctl(struct
> > drm_device *dev, void *data,
> >   			return -ENODEV;
> >   		break;
> >   	case I915_PARAM_SUBSLICE_MASK:
> > -		value = sseu->subslice_mask[0];
> > +		/* Only copy bits from the first slice */
> > +		memcpy(&value, sseu->subslice_mask,
> > +		       min(sseu->ss_stride, (u8)sizeof(value)));
> >   		if (!value)
> >   			return -ENODEV;
> >   		break;
> > diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c
> > b/drivers/gpu/drm/i915/i915_gpu_error.c
> > index 4f85cbdddb0d..c760cc5b3388 100644
> > --- a/drivers/gpu/drm/i915/i915_gpu_error.c
> > +++ b/drivers/gpu/drm/i915/i915_gpu_error.c
> > @@ -408,6 +408,7 @@ static void print_error_buffers(struct
> > drm_i915_error_state_buf *m,
> >   static void error_print_instdone(struct drm_i915_error_state_buf
> > *m,
> >   				 const struct drm_i915_error_engine
> > *ee)
> >   {
> > +	struct sseu_dev_info *sseu = &RUNTIME_INFO(m->i915)->sseu;
> >   	int slice;
> >   	int subslice;
> >   
> > @@ -423,12 +424,12 @@ static void error_print_instdone(struct
> > drm_i915_error_state_buf *m,
> >   	if (INTEL_GEN(m->i915) <= 6)
> >   		return;
> >   
> > -	for_each_instdone_slice_subslice(m->i915, slice, subslice)
> > +	for_each_instdone_slice_subslice(m->i915, sseu, slice,
> > subslice)
> >   		err_printf(m, "  SAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
> >   			   slice, subslice,
> >   			   ee->instdone.sampler[slice][subslice]);
> >   
> > -	for_each_instdone_slice_subslice(m->i915, slice, subslice)
> > +	for_each_instdone_slice_subslice(m->i915, sseu, slice,
> > subslice)
> >   		err_printf(m, "  ROW_INSTDONE[%d][%d]: 0x%08x\n",
> >   			   slice, subslice,
> >   			   ee->instdone.row[slice][subslice]);
> > diff --git a/drivers/gpu/drm/i915/i915_query.c
> > b/drivers/gpu/drm/i915/i915_query.c
> > index 7c1708c22811..000dcb145ce0 100644
> > --- a/drivers/gpu/drm/i915/i915_query.c
> > +++ b/drivers/gpu/drm/i915/i915_query.c
> > @@ -37,8 +37,6 @@ static int query_topology_info(struct
> > drm_i915_private *dev_priv,
> >   	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)-
> > >sseu;
> >   	struct drm_i915_query_topology_info topo;
> >   	u32 slice_length, subslice_length, eu_length, total_length;
> > -	u8 subslice_stride = GEN_SSEU_STRIDE(sseu->max_subslices);
> > -	u8 eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
> >   	int ret;
> >   
> >   	if (query_item->flags != 0)
> > @@ -50,8 +48,8 @@ static int query_topology_info(struct
> > drm_i915_private *dev_priv,
> >   	BUILD_BUG_ON(sizeof(u8) != sizeof(sseu->slice_mask));
> >   
> >   	slice_length = sizeof(sseu->slice_mask);
> > -	subslice_length = sseu->max_slices * subslice_stride;
> > -	eu_length = sseu->max_slices * sseu->max_subslices * eu_stride;
> > +	subslice_length = sseu->max_slices * sseu->ss_stride;
> > +	eu_length = sseu->max_slices * sseu->max_subslices * sseu-
> > >eu_stride;
> >   	total_length = sizeof(topo) + slice_length + subslice_length +
> >   		       eu_length;
> >   
> > @@ -69,9 +67,9 @@ static int query_topology_info(struct
> > drm_i915_private *dev_priv,
> >   	topo.max_eus_per_subslice = sseu->max_eus_per_subslice;
> >   
> >   	topo.subslice_offset = slice_length;
> > -	topo.subslice_stride = subslice_stride;
> > +	topo.subslice_stride = sseu->ss_stride;
> >   	topo.eu_offset = slice_length + subslice_length;
> > -	topo.eu_stride = eu_stride;
> > +	topo.eu_stride = sseu->eu_stride;
> >   
> >   	if (__copy_to_user(u64_to_user_ptr(query_item->data_ptr),
> >   			   &topo, sizeof(topo)))
> > diff --git a/drivers/gpu/drm/i915/intel_device_info.c
> > b/drivers/gpu/drm/i915/intel_device_info.c
> > index 97f742530fa1..3625f777f3a3 100644
> > --- a/drivers/gpu/drm/i915/intel_device_info.c
> > +++ b/drivers/gpu/drm/i915/intel_device_info.c
> > @@ -92,9 +92,9 @@ static void sseu_dump(const struct sseu_dev_info
> > *sseu, struct drm_printer *p)
> >   		   hweight8(sseu->slice_mask), sseu->slice_mask);
> >   	drm_printf(p, "subslice total: %u\n",
> > intel_sseu_subslice_total(sseu));
> >   	for (s = 0; s < sseu->max_slices; s++) {
> > -		drm_printf(p, "slice%d: %u subslices, mask=%04x\n",
> > +		drm_printf(p, "slice%d: %u subslices, mask=%08x\n",
> >   			   s, intel_sseu_subslices_per_slice(sseu, s),
> > -			   sseu->subslice_mask[s]);
> > +			   intel_sseu_get_subslices(sseu, s));
> >   	}
> >   	drm_printf(p, "EU total: %u\n", sseu->eu_total);
> >   	drm_printf(p, "EU per subslice: %u\n", sseu->eu_per_subslice);
> > @@ -117,10 +117,9 @@ void intel_device_info_dump_runtime(const
> > struct intel_runtime_info *info,
> >   static int sseu_eu_idx(const struct sseu_dev_info *sseu, int
> > slice,
> >   		       int subslice)
> >   {
> > -	int subslice_stride = GEN_SSEU_STRIDE(sseu-
> > >max_eus_per_subslice);
> > -	int slice_stride = sseu->max_subslices * subslice_stride;
> > +	int slice_stride = sseu->max_subslices * sseu->eu_stride;
> >   
> > -	return slice * slice_stride + subslice * subslice_stride;
> > +	return slice * slice_stride + subslice * sseu->eu_stride;
> >   }
> >   
> >   static u16 sseu_get_eus(const struct sseu_dev_info *sseu, int
> > slice,
> > @@ -129,7 +128,7 @@ static u16 sseu_get_eus(const struct
> > sseu_dev_info *sseu, int slice,
> >   	int i, offset = sseu_eu_idx(sseu, slice, subslice);
> >   	u16 eu_mask = 0;
> >   
> > -	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
> > i++) {
> > +	for (i = 0; i < sseu->eu_stride; i++) {
> >   		eu_mask |= ((u16)sseu->eu_mask[offset + i]) <<
> >   			(i * BITS_PER_BYTE);
> >   	}
> > @@ -142,7 +141,7 @@ static void sseu_set_eus(struct sseu_dev_info
> > *sseu, int slice, int subslice,
> >   {
> >   	int i, offset = sseu_eu_idx(sseu, slice, subslice);
> >   
> > -	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
> > i++) {
> > +	for (i = 0; i < sseu->eu_stride; i++) {
> >   		sseu->eu_mask[offset + i] =
> >   			(eu_mask >> (BITS_PER_BYTE * i)) & 0xff;
> >   	}
> > @@ -159,9 +158,9 @@ void intel_device_info_dump_topology(const
> > struct sseu_dev_info *sseu,
> >   	}
> >   
> >   	for (s = 0; s < sseu->max_slices; s++) {
> > -		drm_printf(p, "slice%d: %u subslice(s) (0x%hhx):\n",
> > +		drm_printf(p, "slice%d: %u subslice(s) (0x%08x):\n",
> >   			   s, intel_sseu_subslices_per_slice(sseu, s),
> > -			   sseu->subslice_mask[s]);
> > +			   intel_sseu_get_subslices(sseu, s));
> >   
> >   		for (ss = 0; ss < sseu->max_subslices; ss++) {
> >   			u16 enabled_eus = sseu_get_eus(sseu, s, ss);
> > @@ -190,15 +189,10 @@ static void gen11_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >   	u8 eu_en;
> >   	int s;
> >   
> > -	if (IS_ELKHARTLAKE(dev_priv)) {
> > -		sseu->max_slices = 1;
> > -		sseu->max_subslices = 4;
> > -		sseu->max_eus_per_subslice = 8;
> > -	} else {
> > -		sseu->max_slices = 1;
> > -		sseu->max_subslices = 8;
> > -		sseu->max_eus_per_subslice = 8;
> > -	}
> > +	if (IS_ELKHARTLAKE(dev_priv))
> > +		intel_sseu_set_info(sseu, 1, 4, 8);
> > +	else
> > +		intel_sseu_set_info(sseu, 1, 8, 8);
> >   
> >   	s_en = I915_READ(GEN11_GT_SLICE_ENABLE) & GEN11_GT_S_ENA_MASK;
> >   	ss_en = ~I915_READ(GEN11_GT_SUBSLICE_DISABLE);
> > @@ -207,15 +201,15 @@ static void gen11_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >   
> >   	for (s = 0; s < sseu->max_slices; s++) {
> >   		if (s_en & BIT(s)) {
> > -			int ss_idx = sseu->max_subslices * s;
> >   			int ss;
> >   
> >   			sseu->slice_mask |= BIT(s);
> > -			sseu->subslice_mask[s] = (ss_en >> ss_idx) &
> > ss_en_mask;
> > -			for (ss = 0; ss < sseu->max_subslices; ss++) {
> > -				if (sseu->subslice_mask[s] & BIT(ss))
> > +
> > +			intel_sseu_set_subslices(sseu, s, ss_en_mask);
> > +
> > +			for (ss = 0; ss < sseu->max_subslices; ss++)
> > +				if (intel_sseu_has_subslice(sseu, s,
> > ss))
> >   					sseu_set_eus(sseu, s, ss,
> > eu_en);
> > -			}
> >   		}
> >   	}
> >   	sseu->eu_per_subslice = hweight8(eu_en);
> > @@ -235,23 +229,10 @@ static void gen10_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >   	const int eu_mask = 0xff;
> >   	u32 subslice_mask, eu_en;
> >   
> > +	intel_sseu_set_info(sseu, 6, 4, 8);
> > +
> >   	sseu->slice_mask = (fuse2 & GEN10_F2_S_ENA_MASK) >>
> >   			    GEN10_F2_S_ENA_SHIFT;
> > -	sseu->max_slices = 6;
> > -	sseu->max_subslices = 4;
> > -	sseu->max_eus_per_subslice = 8;
> > -
> > -	subslice_mask = (1 << 4) - 1;
> > -	subslice_mask &= ~((fuse2 & GEN10_F2_SS_DIS_MASK) >>
> > -			   GEN10_F2_SS_DIS_SHIFT);
> > -
> > -	/*
> > -	 * Slice0 can have up to 3 subslices, but there are only 2 in
> > -	 * slice1/2.
> > -	 */
> > -	sseu->subslice_mask[0] = subslice_mask;
> > -	for (s = 1; s < sseu->max_slices; s++)
> > -		sseu->subslice_mask[s] = subslice_mask & 0x3;
> >   
> >   	/* Slice0 */
> >   	eu_en = ~I915_READ(GEN8_EU_DISABLE0);
> > @@ -276,14 +257,22 @@ static void gen10_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >   	eu_en = ~I915_READ(GEN10_EU_DISABLE3);
> >   	sseu_set_eus(sseu, 5, 1, eu_en & eu_mask);
> >   
> > -	/* Do a second pass where we mark the subslices disabled if all
> > their
> > -	 * eus are off.
> > -	 */
> > +	subslice_mask = (1 << 4) - 1;
> > +	subslice_mask &= ~((fuse2 & GEN10_F2_SS_DIS_MASK) >>
> > +			   GEN10_F2_SS_DIS_SHIFT);
> > +
> >   	for (s = 0; s < sseu->max_slices; s++) {
> >   		for (ss = 0; ss < sseu->max_subslices; ss++) {
> >   			if (sseu_get_eus(sseu, s, ss) == 0)
> > -				sseu->subslice_mask[s] &= ~BIT(ss);
> > +				subslice_mask &= ~BIT(ss);
> >   		}
> > +
> > +		/*
> > +		 * Slice0 can have up to 3 subslices, but there are
> > only 2 in
> > +		 * slice1/2.
> > +		 */
> > +		intel_sseu_set_subslices(sseu, s, s == 0 ?
> > subslice_mask :
> > +							   subslice_mas
> > k & 0x3);
> >   	}
> >   
> >   	sseu->eu_total = compute_eu_total(sseu);
> > @@ -309,13 +298,12 @@ static void cherryview_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >   {
> >   	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
> >   	u32 fuse;
> > +	u8 subslice_mask;
> >   
> >   	fuse = I915_READ(CHV_FUSE_GT);
> >   
> >   	sseu->slice_mask = BIT(0);
> > -	sseu->max_slices = 1;
> > -	sseu->max_subslices = 2;
> > -	sseu->max_eus_per_subslice = 8;
> > +	intel_sseu_set_info(sseu, 1, 2, 8);
> >   
> >   	if (!(fuse & CHV_FGT_DISABLE_SS0)) {
> >   		u8 disabled_mask =
> > @@ -324,7 +312,7 @@ static void cherryview_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >   			(((fuse & CHV_FGT_EU_DIS_SS0_R1_MASK) >>
> >   			  CHV_FGT_EU_DIS_SS0_R1_SHIFT) << 4);
> >   
> > -		sseu->subslice_mask[0] |= BIT(0);
> > +		subslice_mask |= BIT(0);
> >   		sseu_set_eus(sseu, 0, 0, ~disabled_mask);
> >   	}
> >   
> > @@ -335,10 +323,12 @@ static void cherryview_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >   			(((fuse & CHV_FGT_EU_DIS_SS1_R1_MASK) >>
> >   			  CHV_FGT_EU_DIS_SS1_R1_SHIFT) << 4);
> >   
> > -		sseu->subslice_mask[0] |= BIT(1);
> > +		subslice_mask |= BIT(1);
> >   		sseu_set_eus(sseu, 0, 1, ~disabled_mask);
> >   	}
> >   
> > +	intel_sseu_set_subslices(sseu, 0, subslice_mask);
> > +
> >   	sseu->eu_total = compute_eu_total(sseu);
> >   
> >   	/*
> > @@ -371,9 +361,8 @@ static void gen9_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >   	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >>
> > GEN8_F2_S_ENA_SHIFT;
> >   
> >   	/* BXT has a single slice and at most 3 subslices. */
> > -	sseu->max_slices = IS_GEN9_LP(dev_priv) ? 1 : 3;
> > -	sseu->max_subslices = IS_GEN9_LP(dev_priv) ? 3 : 4;
> > -	sseu->max_eus_per_subslice = 8;
> > +	intel_sseu_set_info(sseu, IS_GEN9_LP(dev_priv) ? 1 : 3,
> > +			    IS_GEN9_LP(dev_priv) ? 3 : 4, 8);
> >   
> >   	/*
> >   	 * The subslice disable field is global, i.e. it applies
> > @@ -392,14 +381,14 @@ static void gen9_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >   			/* skip disabled slice */
> >   			continue;
> >   
> > -		sseu->subslice_mask[s] = subslice_mask;
> > +		intel_sseu_set_subslices(sseu, s, subslice_mask);
> >   
> >   		eu_disable = I915_READ(GEN9_EU_DISABLE(s));
> >   		for (ss = 0; ss < sseu->max_subslices; ss++) {
> >   			int eu_per_ss;
> >   			u8 eu_disabled_mask;
> >   
> > -			if (!(sseu->subslice_mask[s] & BIT(ss)))
> > +			if (!intel_sseu_has_subslice(sseu, s, ss))
> >   				/* skip disabled subslice */
> >   				continue;
> >   
> > @@ -472,9 +461,7 @@ static void broadwell_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >   
> >   	fuse2 = I915_READ(GEN8_FUSE2);
> >   	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >>
> > GEN8_F2_S_ENA_SHIFT;
> > -	sseu->max_slices = 3;
> > -	sseu->max_subslices = 3;
> > -	sseu->max_eus_per_subslice = 8;
> > +	intel_sseu_set_info(sseu, 3, 3, 8);
> >   
> >   	/*
> >   	 * The subslice disable field is global, i.e. it applies
> > @@ -501,18 +488,19 @@ static void broadwell_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >   			/* skip disabled slice */
> >   			continue;
> >   
> > -		sseu->subslice_mask[s] = subslice_mask;
> > +		intel_sseu_set_subslices(sseu, s, subslice_mask);
> >   
> >   		for (ss = 0; ss < sseu->max_subslices; ss++) {
> >   			u8 eu_disabled_mask;
> >   			u32 n_disabled;
> >   
> > -			if (!(sseu->subslice_mask[s] & BIT(ss)))
> > +			if (!intel_sseu_has_subslice(sseu, s, ss))
> >   				/* skip disabled subslice */
> >   				continue;
> >   
> >   			eu_disabled_mask =
> > -				eu_disable[s] >> (ss * sseu-
> > >max_eus_per_subslice);
> > +				eu_disable[s] >>
> > +					(ss * sseu-
> > >max_eus_per_subslice);
> >   
> >   			sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
> >   
> > @@ -552,6 +540,7 @@ static void haswell_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >   	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
> >   	u32 fuse1;
> >   	int s, ss;
> > +	u32 subslice_mask;
> >   
> >   	/*
> >   	 * There isn't a register to tell us how many slices/subslices.
> > We
> > @@ -563,22 +552,18 @@ static void haswell_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >   		/* fall through */
> >   	case 1:
> >   		sseu->slice_mask = BIT(0);
> > -		sseu->subslice_mask[0] = BIT(0);
> > +		subslice_mask = BIT(0);
> >   		break;
> >   	case 2:
> >   		sseu->slice_mask = BIT(0);
> > -		sseu->subslice_mask[0] = BIT(0) | BIT(1);
> > +		subslice_mask = BIT(0) | BIT(1);
> >   		break;
> >   	case 3:
> >   		sseu->slice_mask = BIT(0) | BIT(1);
> > -		sseu->subslice_mask[0] = BIT(0) | BIT(1);
> > -		sseu->subslice_mask[1] = BIT(0) | BIT(1);
> > +		subslice_mask = BIT(0) | BIT(1);
> >   		break;
> >   	}
> >   
> > -	sseu->max_slices = hweight8(sseu->slice_mask);
> > -	sseu->max_subslices = hweight8(sseu->subslice_mask[0]);
> > -
> >   	fuse1 = I915_READ(HSW_PAVP_FUSE1);
> >   	switch ((fuse1 & HSW_F1_EU_DIS_MASK) >> HSW_F1_EU_DIS_SHIFT) {
> >   	default:
> > @@ -595,9 +580,14 @@ static void haswell_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >   		sseu->eu_per_subslice = 6;
> >   		break;
> >   	}
> > -	sseu->max_eus_per_subslice = sseu->eu_per_subslice;
> > +
> > +	intel_sseu_set_info(sseu, hweight8(sseu->slice_mask),
> > +			    hweight8(subslice_mask),
> > +			    sseu->eu_per_subslice);
> >   
> >   	for (s = 0; s < sseu->max_slices; s++) {
> > +		intel_sseu_set_subslices(sseu, s, subslice_mask);
> > +
> >   		for (ss = 0; ss < sseu->max_subslices; ss++) {
> >   			sseu_set_eus(sseu, s, ss,
> >   				     (1UL << sseu->eu_per_subslice) -
> > 1);
> > 

[-- Attachment #1.2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 3270 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✗ Fi.CI.CHECKPATCH: warning for Refactor to expand subslice mask (rev9)

[Patchwork]

== Series Details ==

Series: Refactor to expand subslice mask (rev9)
URL   : https://patchwork.freedesktop.org/series/59742/
State : warning

== Summary ==

$ dim checkpatch origin/drm-tip
4475a01ca163 drm/i915: Use local variable for SSEU info in GETPARAM ioctl
5bdea443d9df drm/i915: Add macro for SSEU stride calculation
a38d3b81273b drm/i915: Move calculation of subslices per slice to new function
9aa78d4fdd9e drm/i915: Refactor sseu helper functions
a10b5645e5d4 drm/i915: Expand subslice mask
-:113: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'subslice__' - possible side-effects?
#113: FILE: drivers/gpu/drm/i915/gt/intel_engine_types.h:541:
+#define instdone_has_subslice(dev_priv__, sseu__, slice__, subslice__) \
+	(IS_GEN(dev_priv__, 7) ? (1 & BIT(subslice__)) : \
+	 intel_sseu_has_subslice(sseu__, slice__, subslice__))

-:117: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'dev_priv_' - possible side-effects?
#117: FILE: drivers/gpu/drm/i915/gt/intel_engine_types.h:545:
+#define for_each_instdone_slice_subslice(dev_priv_, sseu_, slice_, subslice_) \
+	for ((slice_) = 0, (subslice_) = 0; (slice_) < I915_MAX_SLICES; \
+	     (subslice_) = ((subslice_) + 1) % I915_MAX_SUBSLICES, \
+	     (slice_) += ((subslice_) == 0)) \
+		for_each_if((instdone_has_slice(dev_priv_, sseu_, slice_)) && \
+			    (instdone_has_subslice(dev_priv_, sseu_, slice_, \
+						    subslice_)))

-:117: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'sseu_' - possible side-effects?
#117: FILE: drivers/gpu/drm/i915/gt/intel_engine_types.h:545:
+#define for_each_instdone_slice_subslice(dev_priv_, sseu_, slice_, subslice_) \
+	for ((slice_) = 0, (subslice_) = 0; (slice_) < I915_MAX_SLICES; \
+	     (subslice_) = ((subslice_) + 1) % I915_MAX_SUBSLICES, \
+	     (slice_) += ((subslice_) == 0)) \
+		for_each_if((instdone_has_slice(dev_priv_, sseu_, slice_)) && \
+			    (instdone_has_subslice(dev_priv_, sseu_, slice_, \
+						    subslice_)))

-:117: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'slice_' - possible side-effects?
#117: FILE: drivers/gpu/drm/i915/gt/intel_engine_types.h:545:
+#define for_each_instdone_slice_subslice(dev_priv_, sseu_, slice_, subslice_) \
+	for ((slice_) = 0, (subslice_) = 0; (slice_) < I915_MAX_SLICES; \
+	     (subslice_) = ((subslice_) + 1) % I915_MAX_SUBSLICES, \
+	     (slice_) += ((subslice_) == 0)) \
+		for_each_if((instdone_has_slice(dev_priv_, sseu_, slice_)) && \
+			    (instdone_has_subslice(dev_priv_, sseu_, slice_, \
+						    subslice_)))

-:117: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'subslice_' - possible side-effects?
#117: FILE: drivers/gpu/drm/i915/gt/intel_engine_types.h:545:
+#define for_each_instdone_slice_subslice(dev_priv_, sseu_, slice_, subslice_) \
+	for ((slice_) = 0, (subslice_) = 0; (slice_) < I915_MAX_SLICES; \
+	     (subslice_) = ((subslice_) + 1) % I915_MAX_SUBSLICES, \
+	     (slice_) += ((subslice_) == 0)) \
+		for_each_if((instdone_has_slice(dev_priv_, sseu_, slice_)) && \
+			    (instdone_has_subslice(dev_priv_, sseu_, slice_, \
+						    subslice_)))

total: 0 errors, 0 warnings, 5 checks, 686 lines checked

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✗ Fi.CI.SPARSE: warning for Refactor to expand subslice mask (rev9)

[Patchwork]

== Series Details ==

Series: Refactor to expand subslice mask (rev9)
URL   : https://patchwork.freedesktop.org/series/59742/
State : warning

== Summary ==

$ dim sparse origin/drm-tip
Sparse version: v0.5.2
Commit: drm/i915: Use local variable for SSEU info in GETPARAM ioctl
Okay!

Commit: drm/i915: Add macro for SSEU stride calculation
Okay!

Commit: drm/i915: Move calculation of subslices per slice to new function
Okay!

Commit: drm/i915: Refactor sseu helper functions
Okay!

Commit: drm/i915: Expand subslice mask
+drivers/gpu/drm/i915/i915_drv.c:465:24: warning: expression using sizeof(void)

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✓ Fi.CI.BAT: success for Refactor to expand subslice mask (rev9)

[Patchwork]

== Series Details ==

Series: Refactor to expand subslice mask (rev9)
URL   : https://patchwork.freedesktop.org/series/59742/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_6077 -> Patchwork_13011
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/

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

  Here are the changes found in Patchwork_13011 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@i915_module_load@reload:
    - fi-blb-e6850:       [PASS][1] -> [INCOMPLETE][2] ([fdo#107718])
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6077/fi-blb-e6850/igt@i915_module_load@reload.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/fi-blb-e6850/igt@i915_module_load@reload.html

  
  [fdo#107718]: https://bugs.freedesktop.org/show_bug.cgi?id=107718


Participating hosts (53 -> 41)
------------------------------

  Missing    (12): fi-kbl-soraka fi-kbl-7567u fi-ilk-m540 fi-hsw-4200u fi-byt-squawks fi-icl-u2 fi-bsw-cyan fi-byt-clapper fi-icl-u3 fi-icl-y fi-icl-dsi fi-bdw-samus 


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

  * Linux: CI_DRM_6077 -> Patchwork_13011

  CI_DRM_6077: f175074b17cfeb7d64cfcfd6b2641641a10d4deb @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_4984: 66c887d2f7a92a4a97acd9611d5342afc5d4f815 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_13011: a10b5645e5d40c83f76dfbfbfb7a2a26b889f661 @ git://anongit.freedesktop.org/gfx-ci/linux


== Linux commits ==

a10b5645e5d4 drm/i915: Expand subslice mask
9aa78d4fdd9e drm/i915: Refactor sseu helper functions
a38d3b81273b drm/i915: Move calculation of subslices per slice to new function
5bdea443d9df drm/i915: Add macro for SSEU stride calculation
4475a01ca163 drm/i915: Use local variable for SSEU info in GETPARAM ioctl

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✓ Fi.CI.IGT: success for Refactor to expand subslice mask (rev9)

[Patchwork]

== Series Details ==

Series: Refactor to expand subslice mask (rev9)
URL   : https://patchwork.freedesktop.org/series/59742/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_6077_full -> Patchwork_13011_full
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  

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

  Here are the unknown changes that may have been introduced in Patchwork_13011_full:

### IGT changes ###

#### Suppressed ####

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

  * {igt@kms_cursor_crc@pipe-a-cursor-suspend}:
    - shard-apl:          [PASS][1] -> [DMESG-WARN][2] +1 similar issue
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6077/shard-apl2/igt@kms_cursor_crc@pipe-a-cursor-suspend.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/shard-apl7/igt@kms_cursor_crc@pipe-a-cursor-suspend.html

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

  Here are the changes found in Patchwork_13011_full that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@gem_softpin@softpin:
    - shard-snb:          [PASS][3] -> [INCOMPLETE][4] ([fdo#105411])
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6077/shard-snb4/igt@gem_softpin@softpin.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/shard-snb1/igt@gem_softpin@softpin.html

  * igt@i915_pm_rpm@gem-idle:
    - shard-skl:          [PASS][5] -> [INCOMPLETE][6] ([fdo#107807]) +1 similar issue
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6077/shard-skl7/igt@i915_pm_rpm@gem-idle.html
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/shard-skl8/igt@i915_pm_rpm@gem-idle.html

  * igt@kms_pipe_crc_basic@suspend-read-crc-pipe-b:
    - shard-apl:          [PASS][7] -> [DMESG-WARN][8] ([fdo#108566]) +2 similar issues
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6077/shard-apl6/igt@kms_pipe_crc_basic@suspend-read-crc-pipe-b.html
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/shard-apl4/igt@kms_pipe_crc_basic@suspend-read-crc-pipe-b.html

  * igt@tools_test@tools_test:
    - shard-hsw:          [PASS][9] -> [SKIP][10] ([fdo#109271])
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6077/shard-hsw5/igt@tools_test@tools_test.html
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/shard-hsw6/igt@tools_test@tools_test.html

  
#### Possible fixes ####

  * igt@i915_pm_rpm@i2c:
    - shard-skl:          [INCOMPLETE][11] ([fdo#107807]) -> [PASS][12] +1 similar issue
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6077/shard-skl1/igt@i915_pm_rpm@i2c.html
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/shard-skl3/igt@i915_pm_rpm@i2c.html

  * igt@i915_pm_rps@waitboost:
    - shard-apl:          [FAIL][13] ([fdo#102250]) -> [PASS][14]
   [13]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6077/shard-apl6/igt@i915_pm_rps@waitboost.html
   [14]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/shard-apl2/igt@i915_pm_rps@waitboost.html

  * igt@i915_suspend@fence-restore-untiled:
    - shard-apl:          [DMESG-WARN][15] ([fdo#108566]) -> [PASS][16] +2 similar issues
   [15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6077/shard-apl5/igt@i915_suspend@fence-restore-untiled.html
   [16]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/shard-apl5/igt@i915_suspend@fence-restore-untiled.html

  * igt@kms_flip@flip-vs-suspend:
    - shard-skl:          [INCOMPLETE][17] ([fdo#109507]) -> [PASS][18]
   [17]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6077/shard-skl6/igt@kms_flip@flip-vs-suspend.html
   [18]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/shard-skl4/igt@kms_flip@flip-vs-suspend.html

  * igt@kms_flip_tiling@flip-changes-tiling-y:
    - shard-skl:          [FAIL][19] ([fdo#107931] / [fdo#108303]) -> [PASS][20]
   [19]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6077/shard-skl6/igt@kms_flip_tiling@flip-changes-tiling-y.html
   [20]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/shard-skl10/igt@kms_flip_tiling@flip-changes-tiling-y.html

  * igt@kms_plane_alpha_blend@pipe-b-coverage-7efc:
    - shard-skl:          [FAIL][21] ([fdo#108145] / [fdo#110403]) -> [PASS][22]
   [21]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6077/shard-skl4/igt@kms_plane_alpha_blend@pipe-b-coverage-7efc.html
   [22]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/shard-skl2/igt@kms_plane_alpha_blend@pipe-b-coverage-7efc.html

  
#### Warnings ####

  * igt@i915_pm_rpm@gem-execbuf-stress-pc8:
    - shard-skl:          [SKIP][23] ([fdo#109271]) -> [INCOMPLETE][24] ([fdo#107807])
   [23]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6077/shard-skl3/igt@i915_pm_rpm@gem-execbuf-stress-pc8.html
   [24]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/shard-skl6/igt@i915_pm_rpm@gem-execbuf-stress-pc8.html

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

  [fdo#102250]: https://bugs.freedesktop.org/show_bug.cgi?id=102250
  [fdo#103927]: https://bugs.freedesktop.org/show_bug.cgi?id=103927
  [fdo#105411]: https://bugs.freedesktop.org/show_bug.cgi?id=105411
  [fdo#107807]: https://bugs.freedesktop.org/show_bug.cgi?id=107807
  [fdo#107931]: https://bugs.freedesktop.org/show_bug.cgi?id=107931
  [fdo#108145]: https://bugs.freedesktop.org/show_bug.cgi?id=108145
  [fdo#108303]: https://bugs.freedesktop.org/show_bug.cgi?id=108303
  [fdo#108566]: https://bugs.freedesktop.org/show_bug.cgi?id=108566
  [fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271
  [fdo#109507]: https://bugs.freedesktop.org/show_bug.cgi?id=109507
  [fdo#110403]: https://bugs.freedesktop.org/show_bug.cgi?id=110403


Participating hosts (10 -> 8)
------------------------------

  Missing    (2): pig-skl-6260u shard-iclb 


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

  * Linux: CI_DRM_6077 -> Patchwork_13011

  CI_DRM_6077: f175074b17cfeb7d64cfcfd6b2641641a10d4deb @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_4984: 66c887d2f7a92a4a97acd9611d5342afc5d4f815 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_13011: a10b5645e5d40c83f76dfbfbfb7a2a26b889f661 @ git://anongit.freedesktop.org/gfx-ci/linux
  piglit_4509: fdc5a4ca11124ab8413c7988896eec4c97336694 @ git://anongit.freedesktop.org/piglit

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13011/
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 0/5] Refactor to expand subslice mask

[Stuart Summers]

This patch series contains a few code clean-up patches, followed
by a patch which changes the storage of the subslice mask to better
match the userspace access through the I915_QUERY_TOPOLOGY_INFO
ioctl. The index into the subslice_mask array is then calculated:
  slice * subslice stride + subslice index / 8

v2: fix i915_pm_sseu test failure
v3: no changes to patches in the series, just resending to pick up
    in CI correctly
v4: rebase
v5: fix header test
v6: address review comments from Jari
    address minor checkpatch warning in existing code
    use eu_stride for EU div-by-8
v7: another rebase
v8: address review comments from Tvrtko and Daniele

Stuart Summers (5):
  drm/i915: Use local variable for SSEU info in GETPARAM ioctl
  drm/i915: Add macro for SSEU stride calculation
  drm/i915: Move calculation of subslices per slice to new function
  drm/i915: Refactor sseu helper functions
  drm/i915: Expand subslice mask

 drivers/gpu/drm/i915/gt/intel_engine_cs.c    |  24 +-
 drivers/gpu/drm/i915/gt/intel_engine_types.h |  30 +--
 drivers/gpu/drm/i915/gt/intel_hangcheck.c    |   3 +-
 drivers/gpu/drm/i915/gt/intel_sseu.c         |  58 +++++
 drivers/gpu/drm/i915/gt/intel_sseu.h         |  36 ++-
 drivers/gpu/drm/i915/gt/intel_workarounds.c  |   2 +-
 drivers/gpu/drm/i915/i915_debugfs.c          |  46 ++--
 drivers/gpu/drm/i915/i915_drv.c              |  15 +-
 drivers/gpu/drm/i915/i915_gpu_error.c        |   5 +-
 drivers/gpu/drm/i915/i915_query.c            |  15 +-
 drivers/gpu/drm/i915/intel_device_info.c     | 246 ++++++++++++-------
 drivers/gpu/drm/i915/intel_device_info.h     |  47 ----
 12 files changed, 327 insertions(+), 200 deletions(-)

-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 1/5] drm/i915: Use local variable for SSEU info in GETPARAM ioctl

[Stuart Summers]

In the GETPARAM ioctl handler, use a local variable to consolidate
usage of SSEU runtime info.

v2: add const to sseu_dev_info variable

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 5ed864752c7b..dcc872f9c676 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -328,6 +328,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct pci_dev *pdev = dev_priv->drm.pdev;
+	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	drm_i915_getparam_t *param = data;
 	int value;
 
@@ -381,12 +382,12 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = i915_cmd_parser_get_version(dev_priv);
 		break;
 	case I915_PARAM_SUBSLICE_TOTAL:
-		value = sseu_subslice_total(&RUNTIME_INFO(dev_priv)->sseu);
+		value = sseu_subslice_total(sseu);
 		if (!value)
 			return -ENODEV;
 		break;
 	case I915_PARAM_EU_TOTAL:
-		value = RUNTIME_INFO(dev_priv)->sseu.eu_total;
+		value = sseu->eu_total;
 		if (!value)
 			return -ENODEV;
 		break;
@@ -403,7 +404,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = HAS_POOLED_EU(dev_priv);
 		break;
 	case I915_PARAM_MIN_EU_IN_POOL:
-		value = RUNTIME_INFO(dev_priv)->sseu.min_eu_in_pool;
+		value = sseu->min_eu_in_pool;
 		break;
 	case I915_PARAM_HUC_STATUS:
 		value = intel_huc_check_status(&dev_priv->huc);
@@ -453,12 +454,12 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = intel_engines_has_context_isolation(dev_priv);
 		break;
 	case I915_PARAM_SLICE_MASK:
-		value = RUNTIME_INFO(dev_priv)->sseu.slice_mask;
+		value = sseu->slice_mask;
 		if (!value)
 			return -ENODEV;
 		break;
 	case I915_PARAM_SUBSLICE_MASK:
-		value = RUNTIME_INFO(dev_priv)->sseu.subslice_mask[0];
+		value = sseu->subslice_mask[0];
 		if (!value)
 			return -ENODEV;
 		break;
-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 0/5] Refactor to expand subslice mask

[Stuart Summers]

This patch series contains a few code clean-up patches, followed
by a patch which changes the storage of the subslice mask to better
match the userspace access through the I915_QUERY_TOPOLOGY_INFO
ioctl. The index into the subslice_mask array is then calculated:
  slice * subslice stride + subslice index / 8

v2: fix i915_pm_sseu test failure
v3: no changes to patches in the series, just resending to pick up
    in CI correctly
v4: rebase
v5: fix header test

Stuart Summers (5):
  drm/i915: Use local variable for SSEU info in GETPARAM ioctl
  drm/i915: Add macro for SSEU stride calculation
  drm/i915: Move calculation of subslices per slice to new function
  drm/i915: Move sseu helper functions to intel_sseu.h
  drm/i915: Expand subslice mask

 drivers/gpu/drm/i915/gt/intel_engine_cs.c    |   6 +-
 drivers/gpu/drm/i915/gt/intel_engine_types.h |  32 +++--
 drivers/gpu/drm/i915/gt/intel_hangcheck.c    |   3 +-
 drivers/gpu/drm/i915/gt/intel_sseu.h         |  98 ++++++++++++-
 drivers/gpu/drm/i915/gt/intel_workarounds.c  |   2 +-
 drivers/gpu/drm/i915/i915_debugfs.c          |  45 +++---
 drivers/gpu/drm/i915/i915_drv.c              |  15 +-
 drivers/gpu/drm/i915/i915_gpu_error.c        |   5 +-
 drivers/gpu/drm/i915/i915_query.c            |  15 +-
 drivers/gpu/drm/i915/intel_device_info.c     | 143 +++++++++++--------
 drivers/gpu/drm/i915/intel_device_info.h     |  47 ------
 11 files changed, 247 insertions(+), 164 deletions(-)

-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 1/5] drm/i915: Use local variable for SSEU info in GETPARAM ioctl

[Stuart Summers]

In the GETPARAM ioctl handler, use a local variable to consolidate
usage of SSEU runtime info.

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index aacc8dd6ecfd..b6ce7580d414 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -321,6 +321,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	drm_i915_getparam_t *param = data;
 	int value;
 
@@ -374,12 +375,12 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = i915_cmd_parser_get_version(dev_priv);
 		break;
 	case I915_PARAM_SUBSLICE_TOTAL:
-		value = sseu_subslice_total(&RUNTIME_INFO(dev_priv)->sseu);
+		value = sseu_subslice_total(sseu);
 		if (!value)
 			return -ENODEV;
 		break;
 	case I915_PARAM_EU_TOTAL:
-		value = RUNTIME_INFO(dev_priv)->sseu.eu_total;
+		value = sseu->eu_total;
 		if (!value)
 			return -ENODEV;
 		break;
@@ -396,7 +397,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = HAS_POOLED_EU(dev_priv);
 		break;
 	case I915_PARAM_MIN_EU_IN_POOL:
-		value = RUNTIME_INFO(dev_priv)->sseu.min_eu_in_pool;
+		value = sseu->min_eu_in_pool;
 		break;
 	case I915_PARAM_HUC_STATUS:
 		value = intel_huc_check_status(&dev_priv->huc);
@@ -446,12 +447,12 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = intel_engines_has_context_isolation(dev_priv);
 		break;
 	case I915_PARAM_SLICE_MASK:
-		value = RUNTIME_INFO(dev_priv)->sseu.slice_mask;
+		value = sseu->slice_mask;
 		if (!value)
 			return -ENODEV;
 		break;
 	case I915_PARAM_SUBSLICE_MASK:
-		value = RUNTIME_INFO(dev_priv)->sseu.subslice_mask[0];
+		value = sseu->subslice_mask[0];
 		if (!value)
 			return -ENODEV;
 		break;
-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 1/5] drm/i915: Use local variable for SSEU info in GETPARAM ioctl

[Jani Nikula]

On Mon, 29 Apr 2019, Stuart Summers <stuart.summers@intel.com> wrote:
> In the GETPARAM ioctl handler, use a local variable to consolidate
> usage of SSEU runtime info.
>
> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
> Signed-off-by: Stuart Summers <stuart.summers@intel.com>
> ---
>  drivers/gpu/drm/i915/i915_drv.c | 11 ++++++-----
>  1 file changed, 6 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
> index aacc8dd6ecfd..b6ce7580d414 100644
> --- a/drivers/gpu/drm/i915/i915_drv.c
> +++ b/drivers/gpu/drm/i915/i915_drv.c
> @@ -321,6 +321,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
>  {
>  	struct drm_i915_private *dev_priv = to_i915(dev);
>  	struct pci_dev *pdev = dev_priv->drm.pdev;
> +	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;

const?

>  	drm_i915_getparam_t *param = data;
>  	int value;
>  
> @@ -374,12 +375,12 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
>  		value = i915_cmd_parser_get_version(dev_priv);
>  		break;
>  	case I915_PARAM_SUBSLICE_TOTAL:
> -		value = sseu_subslice_total(&RUNTIME_INFO(dev_priv)->sseu);
> +		value = sseu_subslice_total(sseu);
>  		if (!value)
>  			return -ENODEV;
>  		break;
>  	case I915_PARAM_EU_TOTAL:
> -		value = RUNTIME_INFO(dev_priv)->sseu.eu_total;
> +		value = sseu->eu_total;
>  		if (!value)
>  			return -ENODEV;
>  		break;
> @@ -396,7 +397,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
>  		value = HAS_POOLED_EU(dev_priv);
>  		break;
>  	case I915_PARAM_MIN_EU_IN_POOL:
> -		value = RUNTIME_INFO(dev_priv)->sseu.min_eu_in_pool;
> +		value = sseu->min_eu_in_pool;
>  		break;
>  	case I915_PARAM_HUC_STATUS:
>  		value = intel_huc_check_status(&dev_priv->huc);
> @@ -446,12 +447,12 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
>  		value = intel_engines_has_context_isolation(dev_priv);
>  		break;
>  	case I915_PARAM_SLICE_MASK:
> -		value = RUNTIME_INFO(dev_priv)->sseu.slice_mask;
> +		value = sseu->slice_mask;
>  		if (!value)
>  			return -ENODEV;
>  		break;
>  	case I915_PARAM_SUBSLICE_MASK:
> -		value = RUNTIME_INFO(dev_priv)->sseu.subslice_mask[0];
> +		value = sseu->subslice_mask[0];
>  		if (!value)
>  			return -ENODEV;
>  		break;

-- 
Jani Nikula, Intel Open Source Graphics Center
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 1/5] drm/i915: Use local variable for SSEU info in GETPARAM ioctl

[Summers, Stuart]

[-- Attachment #1.1: Type: text/plain, Size: 2743 bytes --]

On Tue, 2019-04-30 at 11:58 +0300, Jani Nikula wrote:
> On Mon, 29 Apr 2019, Stuart Summers <stuart.summers@intel.com> wrote:
> > In the GETPARAM ioctl handler, use a local variable to consolidate
> > usage of SSEU runtime info.
> > 
> > Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
> > Signed-off-by: Stuart Summers <stuart.summers@intel.com>
> > ---
> >  drivers/gpu/drm/i915/i915_drv.c | 11 ++++++-----
> >  1 file changed, 6 insertions(+), 5 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/i915/i915_drv.c
> > b/drivers/gpu/drm/i915/i915_drv.c
> > index aacc8dd6ecfd..b6ce7580d414 100644
> > --- a/drivers/gpu/drm/i915/i915_drv.c
> > +++ b/drivers/gpu/drm/i915/i915_drv.c
> > @@ -321,6 +321,7 @@ static int i915_getparam_ioctl(struct
> > drm_device *dev, void *data,
> >  {
> >  	struct drm_i915_private *dev_priv = to_i915(dev);
> >  	struct pci_dev *pdev = dev_priv->drm.pdev;
> > +	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
> 
> const?

Somehow I had missed this email, sorry for the late response. I'll make
this change and post a quick update.

Thanks,
Stuart

> 
> >  	drm_i915_getparam_t *param = data;
> >  	int value;
> >  
> > @@ -374,12 +375,12 @@ static int i915_getparam_ioctl(struct
> > drm_device *dev, void *data,
> >  		value = i915_cmd_parser_get_version(dev_priv);
> >  		break;
> >  	case I915_PARAM_SUBSLICE_TOTAL:
> > -		value = sseu_subslice_total(&RUNTIME_INFO(dev_priv)-
> > >sseu);
> > +		value = sseu_subslice_total(sseu);
> >  		if (!value)
> >  			return -ENODEV;
> >  		break;
> >  	case I915_PARAM_EU_TOTAL:
> > -		value = RUNTIME_INFO(dev_priv)->sseu.eu_total;
> > +		value = sseu->eu_total;
> >  		if (!value)
> >  			return -ENODEV;
> >  		break;
> > @@ -396,7 +397,7 @@ static int i915_getparam_ioctl(struct
> > drm_device *dev, void *data,
> >  		value = HAS_POOLED_EU(dev_priv);
> >  		break;
> >  	case I915_PARAM_MIN_EU_IN_POOL:
> > -		value = RUNTIME_INFO(dev_priv)->sseu.min_eu_in_pool;
> > +		value = sseu->min_eu_in_pool;
> >  		break;
> >  	case I915_PARAM_HUC_STATUS:
> >  		value = intel_huc_check_status(&dev_priv->huc);
> > @@ -446,12 +447,12 @@ static int i915_getparam_ioctl(struct
> > drm_device *dev, void *data,
> >  		value = intel_engines_has_context_isolation(dev_priv);
> >  		break;
> >  	case I915_PARAM_SLICE_MASK:
> > -		value = RUNTIME_INFO(dev_priv)->sseu.slice_mask;
> > +		value = sseu->slice_mask;
> >  		if (!value)
> >  			return -ENODEV;
> >  		break;
> >  	case I915_PARAM_SUBSLICE_MASK:
> > -		value = RUNTIME_INFO(dev_priv)->sseu.subslice_mask[0];
> > +		value = sseu->subslice_mask[0];
> >  		if (!value)
> >  			return -ENODEV;
> >  		break;
> 
> 

[-- Attachment #1.2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 3270 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 0/5] Refactor to expand subslice mask

[Stuart Summers]

This patch series contains a few code clean-up patches, followed
by a patch which changes the storage of the subslice mask to better
match the userspace access through the I915_QUERY_TOPOLOGY_INFO
ioctl. The index into the subslice_mask array is then calculated:
  slice * subslice stride + subslice index / 8

v2: fix i915_pm_sseu test failure
v3: no changes to patches in the series, just resending to pick up
    in CI correctly
v4: rebase

Stuart Summers (5):
  drm/i915: Use local variable for SSEU info in GETPARAM ioctl
  drm/i915: Add macro for SSEU stride calculation
  drm/i915: Move calculation of subslices per slice to new function
  drm/i915: Move sseu helper functions to intel_sseu.h
  drm/i915: Expand subslice mask

 drivers/gpu/drm/i915/gt/intel_engine_cs.c    |   6 +-
 drivers/gpu/drm/i915/gt/intel_engine_types.h |  32 +++--
 drivers/gpu/drm/i915/gt/intel_hangcheck.c    |   3 +-
 drivers/gpu/drm/i915/gt/intel_sseu.h         |  96 ++++++++++++-
 drivers/gpu/drm/i915/gt/intel_workarounds.c  |   2 +-
 drivers/gpu/drm/i915/i915_debugfs.c          |  45 +++---
 drivers/gpu/drm/i915/i915_drv.c              |  15 +-
 drivers/gpu/drm/i915/i915_gpu_error.c        |   5 +-
 drivers/gpu/drm/i915/i915_query.c            |  15 +-
 drivers/gpu/drm/i915/intel_device_info.c     | 143 +++++++++++--------
 drivers/gpu/drm/i915/intel_device_info.h     |  47 ------
 11 files changed, 245 insertions(+), 164 deletions(-)

-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 1/5] drm/i915: Use local variable for SSEU info in GETPARAM ioctl

[Stuart Summers]

In the GETPARAM ioctl handler, use a local variable to consolidate
usage of SSEU runtime info.

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index aacc8dd6ecfd..b6ce7580d414 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -321,6 +321,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	drm_i915_getparam_t *param = data;
 	int value;
 
@@ -374,12 +375,12 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = i915_cmd_parser_get_version(dev_priv);
 		break;
 	case I915_PARAM_SUBSLICE_TOTAL:
-		value = sseu_subslice_total(&RUNTIME_INFO(dev_priv)->sseu);
+		value = sseu_subslice_total(sseu);
 		if (!value)
 			return -ENODEV;
 		break;
 	case I915_PARAM_EU_TOTAL:
-		value = RUNTIME_INFO(dev_priv)->sseu.eu_total;
+		value = sseu->eu_total;
 		if (!value)
 			return -ENODEV;
 		break;
@@ -396,7 +397,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = HAS_POOLED_EU(dev_priv);
 		break;
 	case I915_PARAM_MIN_EU_IN_POOL:
-		value = RUNTIME_INFO(dev_priv)->sseu.min_eu_in_pool;
+		value = sseu->min_eu_in_pool;
 		break;
 	case I915_PARAM_HUC_STATUS:
 		value = intel_huc_check_status(&dev_priv->huc);
@@ -446,12 +447,12 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = intel_engines_has_context_isolation(dev_priv);
 		break;
 	case I915_PARAM_SLICE_MASK:
-		value = RUNTIME_INFO(dev_priv)->sseu.slice_mask;
+		value = sseu->slice_mask;
 		if (!value)
 			return -ENODEV;
 		break;
 	case I915_PARAM_SUBSLICE_MASK:
-		value = RUNTIME_INFO(dev_priv)->sseu.subslice_mask[0];
+		value = sseu->subslice_mask[0];
 		if (!value)
 			return -ENODEV;
 		break;
-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 0/5] Refactor to expand subslice mask

[Stuart Summers]

This patch series contains a few code clean-up patches, followed
by a patch which changes the storage of the subslice mask to better
match the userspace access through the I915_QUERY_TOPOLOGY_INFO
ioctl. The index into the subslice_mask array is then calculated:
  slice * subslice stride + subslice index / 8

v2: fix i915_pm_sseu test failure
v3: no changes to patches in the series, just resending to pick up
    in CI correctly

Stuart Summers (5):
  drm/i915: Use local variable for SSEU info in GETPARAM ioctl
  drm/i915: Add macro for SSEU stride calculation
  drm/i915: Move calculation of subslices per slice to new function
  drm/i915: Move sseu helper functions to intel_sseu.h
  drm/i915: Expand subslice mask

 drivers/gpu/drm/i915/i915_debugfs.c       |  45 ++++---
 drivers/gpu/drm/i915/i915_drv.c           |  15 ++-
 drivers/gpu/drm/i915/i915_gpu_error.c     |   5 +-
 drivers/gpu/drm/i915/i915_query.c         |  15 +--
 drivers/gpu/drm/i915/intel_device_info.c  | 143 +++++++++++++---------
 drivers/gpu/drm/i915/intel_device_info.h  |  47 -------
 drivers/gpu/drm/i915/intel_engine_cs.c    |   6 +-
 drivers/gpu/drm/i915/intel_engine_types.h |  32 ++---
 drivers/gpu/drm/i915/intel_hangcheck.c    |   3 +-
 drivers/gpu/drm/i915/intel_sseu.h         |  96 ++++++++++++++-
 drivers/gpu/drm/i915/intel_workarounds.c  |   2 +-
 11 files changed, 245 insertions(+), 164 deletions(-)

-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 1/5] drm/i915: Use local variable for SSEU info in GETPARAM ioctl

[Stuart Summers]

In the GETPARAM ioctl handler, use a local variable to consolidate
usage of SSEU runtime info.

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 6354c68c94b3..27021a7546a2 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -319,6 +319,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	drm_i915_getparam_t *param = data;
 	int value;
 
@@ -372,12 +373,12 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = i915_cmd_parser_get_version(dev_priv);
 		break;
 	case I915_PARAM_SUBSLICE_TOTAL:
-		value = sseu_subslice_total(&RUNTIME_INFO(dev_priv)->sseu);
+		value = sseu_subslice_total(sseu);
 		if (!value)
 			return -ENODEV;
 		break;
 	case I915_PARAM_EU_TOTAL:
-		value = RUNTIME_INFO(dev_priv)->sseu.eu_total;
+		value = sseu->eu_total;
 		if (!value)
 			return -ENODEV;
 		break;
@@ -394,7 +395,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = HAS_POOLED_EU(dev_priv);
 		break;
 	case I915_PARAM_MIN_EU_IN_POOL:
-		value = RUNTIME_INFO(dev_priv)->sseu.min_eu_in_pool;
+		value = sseu->min_eu_in_pool;
 		break;
 	case I915_PARAM_HUC_STATUS:
 		value = intel_huc_check_status(&dev_priv->huc);
@@ -444,12 +445,12 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = intel_engines_has_context_isolation(dev_priv);
 		break;
 	case I915_PARAM_SLICE_MASK:
-		value = RUNTIME_INFO(dev_priv)->sseu.slice_mask;
+		value = sseu->slice_mask;
 		if (!value)
 			return -ENODEV;
 		break;
 	case I915_PARAM_SUBSLICE_MASK:
-		value = RUNTIME_INFO(dev_priv)->sseu.subslice_mask[0];
+		value = sseu->subslice_mask[0];
 		if (!value)
 			return -ENODEV;
 		break;
-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 0/4] Refactor to expand subslice mask

[Stuart Summers]

This patch series contains a few code clean-up patches, followed
by a patch which changes the storage of the subslice mask to better
match the userspace access through the I915_QUERY_TOPOLOGY_INFO
ioctl. The index into the subslice_mask array is then calculated:
  slice * subslice stride + subslice index / 8

Stuart Summers (4):
  drm/i915: Use local variable for SSEU info in GETPARAM ioctl
  drm/i915: Add macro for SSEU stride calculation
  drm/i915: Move calculation of subslices per slice to new function
  drm/i915: Expand subslice mask

 drivers/gpu/drm/i915/i915_debugfs.c       |  46 ++++---
 drivers/gpu/drm/i915/i915_drv.c           |  15 ++-
 drivers/gpu/drm/i915/i915_gpu_error.c     |   5 +-
 drivers/gpu/drm/i915/i915_query.c         |  15 +--
 drivers/gpu/drm/i915/intel_device_info.c  | 154 +++++++++++++---------
 drivers/gpu/drm/i915/intel_device_info.h  |  52 ++++++--
 drivers/gpu/drm/i915/intel_engine_cs.c    |   6 +-
 drivers/gpu/drm/i915/intel_engine_types.h |  32 ++---
 drivers/gpu/drm/i915/intel_hangcheck.c    |   3 +-
 drivers/gpu/drm/i915/intel_workarounds.c  |   2 +-
 10 files changed, 203 insertions(+), 127 deletions(-)

-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 0/5] Refactor to expand subslice mask

[Stuart Summers]

This patch series contains a few code clean-up patches, followed
by a patch which changes the storage of the subslice mask to better
match the userspace access through the I915_QUERY_TOPOLOGY_INFO
ioctl. The index into the subslice_mask array is then calculated:
  slice * subslice stride + subslice index / 8

v2: fix i915_pm_sseu test failure

Stuart Summers (5):
  drm/i915: Use local variable for SSEU info in GETPARAM ioctl
  drm/i915: Add macro for SSEU stride calculation
  drm/i915: Move calculation of subslices per slice to new function
  drm/i915: Move sseu helper functions to intel_sseu.h
  drm/i915: Expand subslice mask

 drivers/gpu/drm/i915/i915_debugfs.c       |  45 ++++---
 drivers/gpu/drm/i915/i915_drv.c           |  15 ++-
 drivers/gpu/drm/i915/i915_gpu_error.c     |   5 +-
 drivers/gpu/drm/i915/i915_query.c         |  15 +--
 drivers/gpu/drm/i915/intel_device_info.c  | 143 +++++++++++++---------
 drivers/gpu/drm/i915/intel_device_info.h  |  47 -------
 drivers/gpu/drm/i915/intel_engine_cs.c    |   6 +-
 drivers/gpu/drm/i915/intel_engine_types.h |  32 ++---
 drivers/gpu/drm/i915/intel_hangcheck.c    |   3 +-
 drivers/gpu/drm/i915/intel_sseu.h         |  96 ++++++++++++++-
 drivers/gpu/drm/i915/intel_workarounds.c  |   2 +-
 11 files changed, 245 insertions(+), 164 deletions(-)

-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 1/5] drm/i915: Use local variable for SSEU info in GETPARAM ioctl

[Stuart Summers]

In the GETPARAM ioctl handler, use a local variable to consolidate
usage of SSEU runtime info.

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 6354c68c94b3..27021a7546a2 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -319,6 +319,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	drm_i915_getparam_t *param = data;
 	int value;
 
@@ -372,12 +373,12 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = i915_cmd_parser_get_version(dev_priv);
 		break;
 	case I915_PARAM_SUBSLICE_TOTAL:
-		value = sseu_subslice_total(&RUNTIME_INFO(dev_priv)->sseu);
+		value = sseu_subslice_total(sseu);
 		if (!value)
 			return -ENODEV;
 		break;
 	case I915_PARAM_EU_TOTAL:
-		value = RUNTIME_INFO(dev_priv)->sseu.eu_total;
+		value = sseu->eu_total;
 		if (!value)
 			return -ENODEV;
 		break;
@@ -394,7 +395,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = HAS_POOLED_EU(dev_priv);
 		break;
 	case I915_PARAM_MIN_EU_IN_POOL:
-		value = RUNTIME_INFO(dev_priv)->sseu.min_eu_in_pool;
+		value = sseu->min_eu_in_pool;
 		break;
 	case I915_PARAM_HUC_STATUS:
 		value = intel_huc_check_status(&dev_priv->huc);
@@ -444,12 +445,12 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = intel_engines_has_context_isolation(dev_priv);
 		break;
 	case I915_PARAM_SLICE_MASK:
-		value = RUNTIME_INFO(dev_priv)->sseu.slice_mask;
+		value = sseu->slice_mask;
 		if (!value)
 			return -ENODEV;
 		break;
 	case I915_PARAM_SUBSLICE_MASK:
-		value = RUNTIME_INFO(dev_priv)->sseu.subslice_mask[0];
+		value = sseu->subslice_mask[0];
 		if (!value)
 			return -ENODEV;
 		break;
-- 
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx