Skip to contentSkip to conversation

Refactor to expand subslice mask

PATCH In review Stuart Summers 3 participants 16 messages May 3, 2019 – May 7, 2019

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

cover Refactor to expand subslice mask

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(-)
Signature · 6 lines
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#1 lore raw

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

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

v2: add const to sseu_dev_info variable

---
 drivers/gpu/drm/i915/i915_drv.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)
drivers/gpu/drm/i915/i915_drv.c +6 -5
index 5ed864752c7b..dcc872f9c676 100644
@@ -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;
Signature · 6 lines
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#2 lore raw

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

In reply to 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

---
 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(-)
drivers/gpu/drm/i915/gt/intel_sseu.h +2 -0
index 73bc824094e8..d20b7f96907d 100644
@@ -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;
drivers/gpu/drm/i915/i915_query.c +8 -9
index 782183b78f49..7c1708c22811 100644
@@ -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)))
drivers/gpu/drm/i915/intel_device_info.h +3 -6
index 5a2e17d6146b..9d43f7edfd63 100644
@@ -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;
 	}
Signature · 6 lines
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#3 lore raw

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

In reply to 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

---
 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(-)
drivers/gpu/drm/i915/gt/intel_sseu.h +6 -0
index d20b7f96907d..9618dff46d83 100644
@@ -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);
 
drivers/gpu/drm/i915/i915_debugfs.c +1 -1
index 14cd83e9ea8b..dceb32a16c5c 100644
@@ -4187,7 +4187,7 @@ 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);
drivers/gpu/drm/i915/intel_device_info.c +2 -2
index 6af480b95bc6..9d6b9c45bc5e 100644
@@ -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++) {
Signature · 6 lines
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#4 lore raw

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

In reply to 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

---
 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 | 103 ++++++++++++++++-------
 drivers/gpu/drm/i915/intel_device_info.h |  44 ----------
 6 files changed, 97 insertions(+), 83 deletions(-)
drivers/gpu/drm/i915/gt/intel_sseu.c +17 -0
index 7f448f3bea0b..a0756f006f5f 100644
@@ -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)
 {
drivers/gpu/drm/i915/gt/intel_sseu.h +5 -5
index 9618dff46d83..b50d0401a4e2 100644
@@ -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);
drivers/gpu/drm/i915/i915_debugfs.c +2 -2
index dceb32a16c5c..fce3ccd87f76 100644
@@ -4160,7 +4160,7 @@ 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++) {
@@ -4184,7 +4184,7 @@ 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));
drivers/gpu/drm/i915/i915_drv.c +1 -1
index dcc872f9c676..c2ea3f0992b2 100644
@@ -382,7 +382,7 @@ 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;
drivers/gpu/drm/i915/intel_device_info.c +72 -31

216 lines not on this page · raw message

drivers/gpu/drm/i915/intel_device_info.h +0 -44

50 lines not on this page · raw message

Signature · 6 lines
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Reviewed-by on v1 4/5
#5 lore raw

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

Quoted 119 lines · 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

---
  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 | 103 ++++++++++++++++-------
  drivers/gpu/drm/i915/intel_device_info.h |  44 ----------
  6 files changed, 97 insertions(+), 83 deletions(-)
drivers/gpu/drm/i915/gt/intel_sseu.c +17 -0
index 7f448f3bea0b..a0756f006f5f 100644
@@ -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)
  {
drivers/gpu/drm/i915/gt/intel_sseu.h +5 -5
index 9618dff46d83..b50d0401a4e2 100644
@@ -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);
drivers/gpu/drm/i915/i915_debugfs.c +2 -2
index dceb32a16c5c..fce3ccd87f76 100644
@@ -4160,7 +4160,7 @@ 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++) {
@@ -4184,7 +4184,7 @@ 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));
drivers/gpu/drm/i915/i915_drv.c +1 -1
index dcc872f9c676..c2ea3f0992b2 100644
@@ -382,7 +382,7 @@ 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;
drivers/gpu/drm/i915/intel_device_info.c +1 -1
index 9d6b9c45bc5e..689702b28e80 100644
@@ -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),

drivers/gpu/drm/i915/intel_device_info.c void intel_device_info_dump_runtime(const struct intel_runtime_info *info, · line 117

Quoted 4 lines
drivers/gpu/drm/i915/intel_device_info.c +1 -0
@@ -114,6 +114,43 @@ void intel_device_info_dump_runtime(const struct intel_runtime_info *info,
  		   info->cs_timestamp_frequency_khz);
  }
 
+static int intel_sseu_eu_idx(const struct sseu_dev_info *sseu, int slice,

No need for intel_ prefix for these functions if they're static (which also helps reducing the diff).

drivers/gpu/drm/i915/intel_device_info.c void intel_device_info_dump_runtime(const struct intel_runtime_info *info, · line 121

Quoted 4 lines
drivers/gpu/drm/i915/intel_device_info.c +4 -0
+			     int subslice)
+{
+	int subslice_stride = DIV_ROUND_UP(sseu->max_eus_per_subslice,
+					   BITS_PER_BYTE);

This was GEN_SSEU_STRIDE in the deleted code (other occurrences below as well).

With these addressed:

Daniele

Quoted 260 lines
drivers/gpu/drm/i915/intel_device_info.c +66 -30
+	int slice_stride = sseu->max_subslices * subslice_stride;
+
+	return slice * slice_stride + subslice * subslice_stride;
+}
+
+static u16 intel_sseu_get_eus(const struct sseu_dev_info *sseu, int slice,
+			      int subslice)
+{
+	int i, offset = intel_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++) {
+		eu_mask |= ((u16)sseu->eu_mask[offset + i]) <<
+			(i * BITS_PER_BYTE);
+	}
+
+	return eu_mask;
+}
+
+static void intel_sseu_set_eus(struct sseu_dev_info *sseu, int slice,
+			       int subslice, u16 eu_mask)
+{
+	int i, offset = intel_sseu_eu_idx(sseu, slice, subslice);
+
+	for (i = 0;
+	     i < DIV_ROUND_UP(sseu->max_eus_per_subslice, BITS_PER_BYTE); 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)
  {
@@ -130,7 +167,7 @@ void intel_device_info_dump_topology(const struct sseu_dev_info *sseu,
  			   sseu->subslice_mask[s]);
 
  		for (ss = 0; ss < sseu->max_subslices; ss++) {
-			u16 enabled_eus = sseu_get_eus(sseu, s, ss);
+			u16 enabled_eus = intel_sseu_get_eus(sseu, s, ss);
 
  			drm_printf(p, "\tsubslice%d: %u EUs (0x%hx)\n",
  				   ss, hweight16(enabled_eus), enabled_eus);
@@ -180,7 +217,7 @@ static void gen11_sseu_info_init(struct drm_i915_private *dev_priv)
  			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))
-					sseu_set_eus(sseu, s, ss, eu_en);
+					intel_sseu_set_eus(sseu, s, ss, eu_en);
  			}
  		}
  	}
@@ -222,32 +259,32 @@ static void gen10_sseu_info_init(struct drm_i915_private *dev_priv)
  	/* Slice0 */
  	eu_en = ~I915_READ(GEN8_EU_DISABLE0);
  	for (ss = 0; ss < sseu->max_subslices; ss++)
-		sseu_set_eus(sseu, 0, ss, (eu_en >> (8 * ss)) & eu_mask);
+		intel_sseu_set_eus(sseu, 0, ss, (eu_en >> (8 * ss)) & eu_mask);
  	/* Slice1 */
-	sseu_set_eus(sseu, 1, 0, (eu_en >> 24) & eu_mask);
+	intel_sseu_set_eus(sseu, 1, 0, (eu_en >> 24) & eu_mask);
  	eu_en = ~I915_READ(GEN8_EU_DISABLE1);
-	sseu_set_eus(sseu, 1, 1, eu_en & eu_mask);
+	intel_sseu_set_eus(sseu, 1, 1, eu_en & eu_mask);
  	/* Slice2 */
-	sseu_set_eus(sseu, 2, 0, (eu_en >> 8) & eu_mask);
-	sseu_set_eus(sseu, 2, 1, (eu_en >> 16) & eu_mask);
+	intel_sseu_set_eus(sseu, 2, 0, (eu_en >> 8) & eu_mask);
+	intel_sseu_set_eus(sseu, 2, 1, (eu_en >> 16) & eu_mask);
  	/* Slice3 */
-	sseu_set_eus(sseu, 3, 0, (eu_en >> 24) & eu_mask);
+	intel_sseu_set_eus(sseu, 3, 0, (eu_en >> 24) & eu_mask);
  	eu_en = ~I915_READ(GEN8_EU_DISABLE2);
-	sseu_set_eus(sseu, 3, 1, eu_en & eu_mask);
+	intel_sseu_set_eus(sseu, 3, 1, eu_en & eu_mask);
  	/* Slice4 */
-	sseu_set_eus(sseu, 4, 0, (eu_en >> 8) & eu_mask);
-	sseu_set_eus(sseu, 4, 1, (eu_en >> 16) & eu_mask);
+	intel_sseu_set_eus(sseu, 4, 0, (eu_en >> 8) & eu_mask);
+	intel_sseu_set_eus(sseu, 4, 1, (eu_en >> 16) & eu_mask);
  	/* Slice5 */
-	sseu_set_eus(sseu, 5, 0, (eu_en >> 24) & eu_mask);
+	intel_sseu_set_eus(sseu, 5, 0, (eu_en >> 24) & eu_mask);
  	eu_en = ~I915_READ(GEN10_EU_DISABLE3);
-	sseu_set_eus(sseu, 5, 1, eu_en & eu_mask);
+	intel_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.
  	 */
  	for (s = 0; s < sseu->max_slices; s++) {
  		for (ss = 0; ss < sseu->max_subslices; ss++) {
-			if (sseu_get_eus(sseu, s, ss) == 0)
+			if (intel_sseu_get_eus(sseu, s, ss) == 0)
  				sseu->subslice_mask[s] &= ~BIT(ss);
  		}
  	}
@@ -260,9 +297,10 @@ 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;
@@ -290,7 +328,7 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
  			  CHV_FGT_EU_DIS_SS0_R1_SHIFT) << 4);
 
  		sseu->subslice_mask[0] |= BIT(0);
-		sseu_set_eus(sseu, 0, 0, ~disabled_mask);
+		intel_sseu_set_eus(sseu, 0, 0, ~disabled_mask);
  	}
 
  	if (!(fuse & CHV_FGT_DISABLE_SS1)) {
@@ -301,7 +339,7 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
  			  CHV_FGT_EU_DIS_SS1_R1_SHIFT) << 4);
 
  		sseu->subslice_mask[0] |= BIT(1);
-		sseu_set_eus(sseu, 0, 1, ~disabled_mask);
+		intel_sseu_set_eus(sseu, 0, 1, ~disabled_mask);
  	}
 
  	sseu->eu_total = compute_eu_total(sseu);
@@ -310,8 +348,9 @@ 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 +358,7 @@ 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);
  }
 
@@ -369,7 +408,7 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 
  			eu_disabled_mask = (eu_disable >> (ss * 8)) & eu_mask;
 
-			sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
+			intel_sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
 
  			eu_per_ss = sseu->max_eus_per_subslice -
  				hweight8(eu_disabled_mask);
@@ -393,9 +432,10 @@ 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 +447,7 @@ 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)) {
@@ -477,7 +517,7 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
  			eu_disabled_mask =
  				eu_disable[s] >> (ss * sseu->max_eus_per_subslice);
 
-			sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
+			intel_sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
 
  			n_disabled = hweight8(eu_disabled_mask);
 
@@ -496,9 +536,10 @@ 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
@@ -561,8 +602,8 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 
  	for (s = 0; s < sseu->max_slices; s++) {
  		for (ss = 0; ss < sseu->max_subslices; ss++) {
-			sseu_set_eus(sseu, s, ss,
-				     (1UL << sseu->eu_per_subslice) - 1);
+			intel_sseu_set_eus(sseu, s, ss,
+					   (1UL << sseu->eu_per_subslice) - 1);
  		}
  	}
 
drivers/gpu/drm/i915/intel_device_info.h +0 -37
index 9d43f7edfd63..6412a9c72898 100644
@@ -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);

drivers/gpu/drm/i915/intel_device_info.h struct intel_driver_caps { · line 223

Quoted 10 lines
drivers/gpu/drm/i915/intel_device_info.h +0 -7
-
-	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);

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#6 lore raw

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

Quoted 158 lines · Daniele Ceraolo Spurio
Quoted 136 lines · 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

---
  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 | 103 ++++++++++++++++
-------
  drivers/gpu/drm/i915/intel_device_info.h |  44 ----------
  6 files changed, 97 insertions(+), 83 deletions(-)
drivers/gpu/drm/i915/gt/intel_sseu.c +17 -0
index 7f448f3bea0b..a0756f006f5f 100644
@@ -8,6 +8,23 @@
  #include "intel_lrc_reg.h"ther occurrences below a
  #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)
  {
drivers/gpu/drm/i915/gt/intel_sseu.h +5 -5
index 9618dff46d83..b50d0401a4e2 100644
@@ -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);

drivers/gpu/drm/i915/i915_debugfs.c +1 -1
index dceb32a16c5c..fce3ccd87f76 100644
@@ -4160,7 +4160,7 @@ 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++) {
drivers/gpu/drm/i915/i915_debugfs.c +1 -1
@@ -4184,7 +4184,7 @@ 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));
drivers/gpu/drm/i915/i915_drv.c +1 -1
index dcc872f9c676..c2ea3f0992b2 100644
@@ -382,7 +382,7 @@ 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;

drivers/gpu/drm/i915/intel_device_info.c +1 -1
index 9d6b9c45bc5e..689702b28e80 100644
@@ -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),

drivers/gpu/drm/i915/intel_device_info.c void intel_device_info_dump_runtime(const · line 119

Quoted 6 lines
drivers/gpu/drm/i915/intel_device_info.c +1 -0
@@ -114,6 +114,43 @@ void intel_device_info_dump_runtime(const
 struct intel_runtime_info *info,
  		   info->cs_timestamp_frequency_khz);
  }
 
+static int intel_sseu_eu_idx(const struct sseu_dev_info *sseu, int
 slice,

No need for intel_ prefix for these functions if they're static (which
also helps reducing the diff).

drivers/gpu/drm/i915/intel_device_info.c void intel_device_info_dump_runtime(const struct intel_runtime_info *info, · line 121

Quoted 4 lines
drivers/gpu/drm/i915/intel_device_info.c +4 -0
+			     int subslice)
+{
+	int subslice_stride = DIV_ROUND_UP(sseu->max_eus_per_subslice,
+					   BITS_PER_BYTE);

This was GEN_SSEU_STRIDE in the deleted code (other occurrences below as
well).

Quoted 1 line

With these addressed:

Nice catch, I obviously missed this case. Will address both of these in the next revision.

Thanks for the review!

-Stuart

Quoted 322 lines

Daniele

Quoted 317 lines
drivers/gpu/drm/i915/intel_device_info.c +13 -0
+	int slice_stride = sseu->max_subslices * subslice_stride;
+
+	return slice * slice_stride + subslice * subslice_stride;
+}
+
+static u16 intel_sseu_get_eus(const struct sseu_dev_info *sseu,
 int slice,
+			      int subslice)
+{
+	int i, offset = intel_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++) {

drivers/gpu/drm/i915/intel_device_info.c +8 -0
+		eu_mask |= ((u16)sseu->eu_mask[offset + i]) <<
+			(i * BITS_PER_BYTE);
+	}
+
+	return eu_mask;
+}
+
+static void intel_sseu_set_eus(struct sseu_dev_info *sseu, int

slice,

drivers/gpu/drm/i915/intel_device_info.c +6 -0
+			       int subslice, u16 eu_mask)
+{
+	int i, offset = intel_sseu_eu_idx(sseu, slice, subslice);
+
+	for (i = 0;
+	     i < DIV_ROUND_UP(sseu->max_eus_per_subslice,

BITS_PER_BYTE); i++) {

drivers/gpu/drm/i915/intel_device_info.c +5 -0
+		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)
{

drivers/gpu/drm/i915/intel_device_info.c +1 -1
@@ -130,7 +167,7 @@ void intel_device_info_dump_topology(const
 struct sseu_dev_info *sseu,
  			   sseu->subslice_mask[s]);
 
  		for (ss = 0; ss < sseu->max_subslices; ss++) {
-			u16 enabled_eus = sseu_get_eus(sseu, s, ss);
+			u16 enabled_eus = intel_sseu_get_eus(sseu, s,
 ss);
 

drm_printf(p, "\tsubslice%d: %u EUs (0x%hx)\n",
ss, hweight16(enabled_eus),
enabled_eus);

drivers/gpu/drm/i915/intel_device_info.c +1 -1
@@ -180,7 +217,7 @@ static void gen11_sseu_info_init(struct
 drm_i915_private *dev_priv)
  			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))
-					sseu_set_eus(sseu, s, ss,
 eu_en);
+					intel_sseu_set_eus(sseu, s, ss,

eu_en);
}
}
}

drivers/gpu/drm/i915/intel_device_info.c +11 -11
@@ -222,32 +259,32 @@ static void gen10_sseu_info_init(struct
 drm_i915_private *dev_priv)
  	/* Slice0 */
  	eu_en = ~I915_READ(GEN8_EU_DISABLE0);
  	for (ss = 0; ss < sseu->max_subslices; ss++)
-		sseu_set_eus(sseu, 0, ss, (eu_en >> (8 * ss)) &
 eu_mask);
+		intel_sseu_set_eus(sseu, 0, ss, (eu_en >> (8 * ss)) &
 eu_mask);
  	/* Slice1 */
-	sseu_set_eus(sseu, 1, 0, (eu_en >> 24) & eu_mask);
+	intel_sseu_set_eus(sseu, 1, 0, (eu_en >> 24) & eu_mask);
  	eu_en = ~I915_READ(GEN8_EU_DISABLE1);
-	sseu_set_eus(sseu, 1, 1, eu_en & eu_mask);
+	intel_sseu_set_eus(sseu, 1, 1, eu_en & eu_mask);
  	/* Slice2 */
-	sseu_set_eus(sseu, 2, 0, (eu_en >> 8) & eu_mask);
-	sseu_set_eus(sseu, 2, 1, (eu_en >> 16) & eu_mask);
+	intel_sseu_set_eus(sseu, 2, 0, (eu_en >> 8) & eu_mask);
+	intel_sseu_set_eus(sseu, 2, 1, (eu_en >> 16) & eu_mask);
  	/* Slice3 */
-	sseu_set_eus(sseu, 3, 0, (eu_en >> 24) & eu_mask);
+	intel_sseu_set_eus(sseu, 3, 0, (eu_en >> 24) & eu_mask);
  	eu_en = ~I915_READ(GEN8_EU_DISABLE2);
-	sseu_set_eus(sseu, 3, 1, eu_en & eu_mask);
+	intel_sseu_set_eus(sseu, 3, 1, eu_en & eu_mask);
  	/* Slice4 */
-	sseu_set_eus(sseu, 4, 0, (eu_en >> 8) & eu_mask);
-	sseu_set_eus(sseu, 4, 1, (eu_en >> 16) & eu_mask);
+	intel_sseu_set_eus(sseu, 4, 0, (eu_en >> 8) & eu_mask);
+	intel_sseu_set_eus(sseu, 4, 1, (eu_en >> 16) & eu_mask);
  	/* Slice5 */
-	sseu_set_eus(sseu, 5, 0, (eu_en >> 24) & eu_mask);
+	intel_sseu_set_eus(sseu, 5, 0, (eu_en >> 24) & eu_mask);
  	eu_en = ~I915_READ(GEN10_EU_DISABLE3);
-	sseu_set_eus(sseu, 5, 1, eu_en & eu_mask);
+	intel_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.
*/
for (s = 0; s < sseu->max_slices; s++) {
for (ss = 0; ss < sseu->max_subslices; ss++) {

drivers/gpu/drm/i915/intel_device_info.c +3 -3
-			if (sseu_get_eus(sseu, s, ss) == 0)
+			if (intel_sseu_get_eus(sseu, s, ss) == 0)
  				sseu->subslice_mask[s] &= ~BIT(ss);
  		}
  	}
@@ -260,9 +297,10 @@ 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)) :

drivers/gpu/drm/i915/intel_device_info.c +2 -1
+				0;
 
  	/* No restrictions on Power Gating */
  	sseu->has_slice_pg = 1;
@@ -290,7 +328,7 @@ static void cherryview_sseu_info_init(struct
 drm_i915_private *dev_priv)
  			  CHV_FGT_EU_DIS_SS0_R1_SHIFT) << 4);
 
  		sseu->subslice_mask[0] |= BIT(0);
-		sseu_set_eus(sseu, 0, 0, ~disabled_mask);
+		intel_sseu_set_eus(sseu, 0, 0, ~disabled_mask);
  	}
 
  	if (!(fuse & CHV_FGT_DISABLE_SS1)) {
drivers/gpu/drm/i915/intel_device_info.c +1 -1
@@ -301,7 +339,7 @@ static void cherryview_sseu_info_init(struct
 drm_i915_private *dev_priv)
  			  CHV_FGT_EU_DIS_SS1_R1_SHIFT) << 4);
 
  		sseu->subslice_mask[0] |= BIT(1);
-		sseu_set_eus(sseu, 0, 1, ~disabled_mask);
+		intel_sseu_set_eus(sseu, 0, 1, ~disabled_mask);
  	}
 
  	sseu->eu_total = compute_eu_total(sseu);
drivers/gpu/drm/i915/intel_device_info.c +0 -2
@@ -310,8 +348,9 @@ 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) :

drivers/gpu/drm/i915/intel_device_info.c +3 -0
+	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

drivers/gpu/drm/i915/intel_device_info.c +2 -2
@@ -319,7 +358,7 @@ 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);
  }
@@ -369,7 +408,7 @@ static void gen9_sseu_info_init(struct
 drm_i915_private *dev_priv)
 
  			eu_disabled_mask = (eu_disable >> (ss * 8)) &
 eu_mask;
 
-			sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
+			intel_sseu_set_eus(sseu, s, ss,
 ~eu_disabled_mask);
  
  			eu_per_ss = sseu->max_eus_per_subslice -
  				hweight8(eu_disabled_mask);
drivers/gpu/drm/i915/intel_device_info.c +2 -2
@@ -393,9 +432,10 @@ 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)) :

drivers/gpu/drm/i915/intel_device_info.c +2 -1
+				0;
  	/*
  	 * SKL+ supports slice power gating on devices with more than
  	 * one slice, and supports EU power gating on devices with
@@ -407,7 +447,7 @@ 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)) {
drivers/gpu/drm/i915/intel_device_info.c +1 -1
@@ -477,7 +517,7 @@ static void broadwell_sseu_info_init(struct
 drm_i915_private *dev_priv)
  			eu_disabled_mask =
  				eu_disable[s] >> (ss * sseu-
 >max_eus_per_subslice);
 
-			sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
+			intel_sseu_set_eus(sseu, s, ss,
 ~eu_disabled_mask);
  
  			n_disabled = hweight8(eu_disabled_mask);
drivers/gpu/drm/i915/intel_device_info.c +0 -0
@@ -496,9 +536,10 @@ 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.
*/

drivers/gpu/drm/i915/intel_device_info.c +1 -2
-	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;

drivers/gpu/drm/i915/intel_device_info.c +1 -0
+					     intel_sseu_subslice_total(

sseu)) :

drivers/gpu/drm/i915/intel_device_info.c +3 -2
+				0;
 
  	/*
  	 * BDW supports slice power gating on devices with more than
@@ -561,8 +602,8 @@ static void haswell_sseu_info_init(struct
 drm_i915_private *dev_priv)
 
  	for (s = 0; s < sseu->max_slices; s++) {
  		for (ss = 0; ss < sseu->max_subslices; ss++) {
-			sseu_set_eus(sseu, s, ss,
-				     (1UL << sseu->eu_per_subslice) -
 1);
+			intel_sseu_set_eus(sseu, s, ss,
+					   (1UL << sseu-
 >eu_per_subslice) - 1);
  		}
  	}
drivers/gpu/drm/i915/intel_device_info.h +0 -39
index 9d43f7edfd63..6412a9c72898 100644
@@ -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++) {

drivers/gpu/drm/i915/intel_device_info.h +0 -5
-		sseu->eu_mask[offset + i] =
-			(eu_mask >> (BITS_PER_BYTE * i)) & 0xff;
-	}
-}
-
  const char *intel_platform_name(enum intel_platform platform);
Quoted 3 lines
Quoted 3 lines

void intel_device_info_subplatform_init(struct drm_i915_private
*dev_priv);

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#7 lore raw

PATCH 5/5 drm/i915: Expand subslice mask

In reply to 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

Cc Daniele Ceraolo Spurio <[email protected]>
Cc Lionel Landwerlin <[email protected]>
---
 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         |  43 ++++-
 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     | 155 ++++++++++---------
 11 files changed, 227 insertions(+), 119 deletions(-)
drivers/gpu/drm/i915/gt/intel_engine_cs.c +22 -2
index 5907a9613641..290bda5cc82b 100644
@@ -909,12 +909,30 @@ 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) |
@@ -990,6 +1008,7 @@ 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;
@@ -1007,7 +1026,8 @@ 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);
drivers/gpu/drm/i915/gt/intel_engine_types.h +15 -15
index c0ab11b12e14..582340b55144 100644
@@ -535,20 +535,20 @@ 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 : \
+	 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__ */
drivers/gpu/drm/i915/gt/intel_hangcheck.c +2 -1
index 721ab74a382f..10e032c9ab10 100644
@@ -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],
drivers/gpu/drm/i915/gt/intel_sseu.c +42 -1

58 lines not on this page · raw message

drivers/gpu/drm/i915/gt/intel_sseu.h +27 -1
index b50d0401a4e2..3602ae54b937 100644
@@ -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);
 
drivers/gpu/drm/i915/gt/intel_workarounds.c +1 -1
index 43e290306551..8437f9d918ec 100644
@@ -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;
drivers/gpu/drm/i915/i915_debugfs.c +21 -19
index fce3ccd87f76..22ac2db98dde 100644
@@ -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]);
 }
@@ -4068,7 +4069,7 @@ 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;
@@ -4119,18 +4120,21 @@ 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] &
@@ -4147,25 +4151,23 @@ 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);
 		}
@@ -4212,6 +4214,7 @@ 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;
 
@@ -4219,14 +4222,13 @@ 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))
drivers/gpu/drm/i915/i915_drv.c +4 -2
index c2ea3f0992b2..c3432b5f9d4b 100644
@@ -330,7 +330,7 @@ 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:
@@ -459,7 +459,9 @@ 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;
drivers/gpu/drm/i915/i915_gpu_error.c +3 -2
index 4f85cbdddb0d..c760cc5b3388 100644
@@ -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]);
drivers/gpu/drm/i915/i915_query.c +4 -6
index 7c1708c22811..000dcb145ce0 100644
@@ -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)))
drivers/gpu/drm/i915/intel_device_info.c +86 -69

329 lines not on this page · raw message

Signature · 6 lines
2.21.0.5.gaeb582a983

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#8 lore raw

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

Quoted 108 lines · 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

Cc Daniele Ceraolo Spurio <[email protected]>
Cc Lionel Landwerlin <[email protected]>
---
  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         |  43 ++++-
  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     | 155 ++++++++++---------
  11 files changed, 227 insertions(+), 119 deletions(-)
drivers/gpu/drm/i915/gt/intel_engine_cs.c +22 -2
index 5907a9613641..290bda5cc82b 100644
@@ -909,12 +909,30 @@ 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) |
@@ -990,6 +1008,7 @@ 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;
@@ -1007,7 +1026,8 @@ 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);
drivers/gpu/drm/i915/gt/intel_engine_types.h +0 -11
index c0ab11b12e14..582340b55144 100644
@@ -535,20 +535,20 @@ 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; \

drivers/gpu/drm/i915/gt/intel_engine_types.h intel_engine_needs_breadcrumb_tasklet(const struct intel_engine_cs *engine) · line 543

Quoted 10 lines
drivers/gpu/drm/i915/gt/intel_engine_types.h +6 -4
-	     (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 : \

This will return true for all ss on gen7, while the original code returned 1 as the subslice mask (i.e. only has ss == 0).

Quoted 57 lines
drivers/gpu/drm/i915/gt/intel_engine_types.h +9 -0
+	 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__ */
drivers/gpu/drm/i915/gt/intel_hangcheck.c +2 -1
index 721ab74a382f..10e032c9ab10 100644
@@ -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],
drivers/gpu/drm/i915/gt/intel_sseu.c +11 -0
index a0756f006f5f..a8b98b0266b7 100644
@@ -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 +30,40 @@ intel_sseu_subslice_total(const struct sseu_dev_info *sseu)
  	return total;
  }

drivers/gpu/drm/i915/gt/intel_sseu.c intel_sseu_subslice_total(const struct sseu_dev_info *sseu) · line 41

Quoted 10 lines
drivers/gpu/drm/i915/gt/intel_sseu.c +9 -0
 
+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)

nitpick: extra space

drivers/gpu/drm/i915/gt/intel_sseu.c intel_sseu_subslice_total(const struct sseu_dev_info *sseu) · line 45

Quoted 4 lines
drivers/gpu/drm/i915/gt/intel_sseu.c +4 -0
+{
+	int i, offset = slice * sseu->ss_stride;
+	u32 mask;
+

GEM_BUG_ON(sseu->ss_stride > size(u32)) to catch the unlikely case we go over and need to update the mask size?

Quoted 25 lines
drivers/gpu/drm/i915/gt/intel_sseu.c +18 -1
+	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,

<snip>

Quoted 38 lines
drivers/gpu/drm/i915/intel_device_info.c +29 -0
@@ -84,17 +84,46 @@ void intel_device_info_dump_flags(const struct intel_device_info *info,
  #undef PRINT_FLAG
  }
 
+#define SS_STR_MAX_SIZE (GEN_MAX_SUBSLICE_STRIDE * 2 + 1)
+
+static char *
+subslice_per_slice_str(char *buf, u8 size, const struct sseu_dev_info *sseu,
+		       u8 slice)
+{
+	int i;
+	u8 ss_offset = slice * sseu->ss_stride;
+
+	GEM_BUG_ON(slice >= sseu->max_slices);
+
+	/* Two ASCII character hex plus null terminator */
+	GEM_BUG_ON(size < sseu->ss_stride * 2 + 1);
+
+	memset(buf, 0, size);
+
+	/*
+	 * Print subslice information in reverse order to match
+	 * userspace expectations.
+	 */
+	for (i = 0; i < sseu->ss_stride; i++)
+		sprintf(&buf[i * 2], "%02x",
+			sseu->subslice_mask[ss_offset + sseu->ss_stride -
+					    (i + 1)]);
+
+	return buf;
+}
+
  static void sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p)
  {
  	int s;
+	char buf[SS_STR_MAX_SIZE];

drivers/gpu/drm/i915/intel_device_info.c void intel_device_info_dump_flags(const struct intel_device_info *info, · line 126

Quoted 10 lines
drivers/gpu/drm/i915/intel_device_info.c +2 -2
 
  	drm_printf(p, "slice total: %u, mask=%04x\n",
  		   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=%s\n",
  			   s, intel_sseu_subslices_per_slice(sseu, s),
-			   sseu->subslice_mask[s]);
+			   subslice_per_slice_str(buf, ARRAY_SIZE(buf), sseu, s));

Now that we have intel_sseu_get_subslices() can't we just print the return from that instead of using the buffer?

Quoted 3 lines
drivers/gpu/drm/i915/intel_device_info.c +0 -0
  	}
  	drm_printf(p, "EU total: %u\n", sseu->eu_total);
  	drm_printf(p, "EU per subslice: %u\n", sseu->eu_per_subslice);

<snip>

Quoted 35 lines
drivers/gpu/drm/i915/intel_device_info.c +4 -7
@@ -555,6 +570,7 @@ 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
@@ -566,22 +582,18 @@ 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:

drivers/gpu/drm/i915/intel_device_info.c static void haswell_sseu_info_init(struct drm_i915_private *dev_priv) · line 616

Quoted 8 lines
drivers/gpu/drm/i915/intel_device_info.c +4 -1
@@ -598,9 +610,14 @@ 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);

I'd still prefer this to use a local variable so that we always only set sseu->eu_per_subslice from within intel_sseu_set_info.

Daniele

drivers/gpu/drm/i915/intel_device_info.c static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)

Quoted 8 lines
drivers/gpu/drm/i915/intel_device_info.c +2 -0
  	for (s = 0; s < sseu->max_slices; s++) {
+		intel_sseu_set_subslices(sseu, s, subslice_mask);
+
  		for (ss = 0; ss < sseu->max_subslices; ss++) {
  			intel_sseu_set_eus(sseu, s, ss,
  					   (1UL << sseu->eu_per_subslice) - 1);
 

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#9 lore raw

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

Quoted 135 lines · Daniele Ceraolo Spurio
Quoted 133 lines · 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

Cc Daniele Ceraolo Spurio <[email protected]>
Cc Lionel Landwerlin <[email protected]>
---
  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         |  43 ++++-
  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     | 155 ++++++++++--
-------
  11 files changed, 227 insertions(+), 119 deletions(-)
drivers/gpu/drm/i915/gt/intel_engine_cs.c +8 -0
index 5907a9613641..290bda5cc82b 100644
@@ -909,12 +909,30 @@ 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-
Quoted 1 line

ss_stride +

drivers/gpu/drm/i915/gt/intel_engine_cs.c +10 -0
+						   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)-

Quoted 1 line

sseu;

u32 mcr_s_ss_select;
u32 slice = fls(sseu->slice_mask);

drivers/gpu/drm/i915/gt/intel_engine_cs.c +2 -1
-	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) |
@@ -990,6 +1008,7 @@ 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;
drivers/gpu/drm/i915/gt/intel_engine_cs.c +2 -1
@@ -1007,7 +1026,8 @@ 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
);

drivers/gpu/drm/i915/gt/intel_engine_types.h +0 -14
index c0ab11b12e14..582340b55144 100644
@@ -535,20 +535,20 @@ 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__)) && \

drivers/gpu/drm/i915/gt/intel_engine_types.h +0 -1
-			    (BIT(subslice__) &

instdone_subslice_mask(dev_priv__)))

drivers/gpu/drm/i915/gt/intel_engine_types.h +2 -0
+#define instdone_has_slice(dev_priv___, sseu___, slice___) \
+	((IS_GEN(dev_priv___, 7) ? 1 : ((sseu___)->slice_mask)) & \
Quoted 8 lines

drivers/gpu/drm/i915/gt/intel_engine_types.h intel_engine_needs_breadcrumb_tasklet(const struct intel_engine_cs *engine) · line 543

Quoted 5 lines
drivers/gpu/drm/i915/gt/intel_engine_types.h +3 -0
+	BIT(slice___))
+
+#define instdone_has_subslice(dev_priv__, sseu__, slice__,

subslice__) \

drivers/gpu/drm/i915/gt/intel_engine_types.h +1 -0
+	(IS_GEN(dev_priv__, 7) ? 1 : \

This will return true for all ss on gen7, while the original code returned 1 as the subslice mask (i.e. only has ss == 0).

True, I'll fix this.

Quoted 82 lines
Quoted 82 lines
drivers/gpu/drm/i915/gt/intel_engine_types.h +3 -0
+	 intel_sseu_has_subslice(sseu__, slice__, subslice__))
+
+#define for_each_instdone_slice_subslice(dev_priv_, sseu_, slice_,

subslice_) \

drivers/gpu/drm/i915/gt/intel_engine_types.h +1 -0
+	for ((slice_) = 0, (subslice_) = 0; (slice_) < I915_MAX_SLICES;

\

drivers/gpu/drm/i915/gt/intel_engine_types.h +3 -0
+	     (subslice_) = ((subslice_) + 1) % I915_MAX_SUBSLICES, \
+	     (slice_) += ((subslice_) == 0)) \
+		for_each_if((instdone_has_slice(dev_priv_, sseu_,

slice_)) && \

drivers/gpu/drm/i915/gt/intel_engine_types.h +1 -0
+			    (irnstdone_has_subslice(dev_priv_, sseu_,

slice_, \

drivers/gpu/drm/i915/gt/intel_engine_types.h +1 -0
+						    subslice_)))
 
  #endif /* __INTEL_ENGINE_TYPES_H__ */
drivers/gpu/drm/i915/gt/intel_hangcheck.c +1 -0
index 721ab74a382f..10e032c9ab10 100644
@@ -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-

Quoted 1 line

hangcheck.instdone;

bool stuck;

drivers/gpu/drm/i915/gt/intel_hangcheck.c +1 -1
@@ -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-

Quoted 1 line

sampler[slice][subslice]);

stuck &=
instdone_unchanged(instdone.row[slice][subslice],

drivers/gpu/drm/i915/gt/intel_sseu.c +11 -0
index a0756f006f5f..a8b98b0266b7 100644
@@ -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)
  {
drivers/gpu/drm/i915/gt/intel_sseu.c +6 -0
@@ -19,10 +30,40 @@ 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-
Quoted 7 lines

drivers/gpu/drm/i915/gt/intel_sseu.c intel_sseu_subslice_total(const struct · line 45

Quoted 5 lines
drivers/gpu/drm/i915/gt/intel_sseu.c +3 -0
 >ss_stride);
+}
+
+u32  intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8
 slice)

nitpick: extra space

Ok.

Quoted 9 lines

drivers/gpu/drm/i915/gt/intel_sseu.c intel_sseu_subslice_total(const struct sseu_dev_info *sseu) · line 45

Quoted 5 lines
drivers/gpu/drm/i915/gt/intel_sseu.c +4 -0
+{
+	int i, offset = slice * sseu->ss_stride;
+	u32 mask;
+

GEM_BUG_ON(sseu->ss_stride > size(u32)) to catch the unlikely case we go
over and need to update the mask size?

Makes sense. I'll add this.

Quoted 74 lines
Quoted 28 lines
drivers/gpu/drm/i915/gt/intel_sseu.c +17 -0
+	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)
{

drivers/gpu/drm/i915/gt/intel_sseu.c +1 -1
-	return hweight8(sseu->subslice_mask[slice]);
+	return hweight32(intel_sseu_get_subslices(sseu, slice));
  }
 
  u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,

<snip>

Quoted 43 lines
drivers/gpu/drm/i915/intel_device_info.c +29 -1
@@ -84,17 +84,46 @@ void intel_device_info_dump_flags(const struct
 intel_device_info *info,
  #undef PRINT_FLAG
  }
 
+#define SS_STR_MAX_SIZE (GEN_MAX_SUBSLICE_STRIDE * 2 + 1)
+
+static char *
+subslice_per_slice_str(char *buf, u8 size, const struct
 sseu_dev_info *sseu,
+		       u8 slice)
+{
+	int i;
+	u8 ss_offset = slice * sseu->ss_stride;
+
+	GEM_BUG_ON(slice >= sseu->max_slices);
+
+	/* Two ASCII character hex plus null terminator */
+	GEM_BUG_ON(size < sseu->ss_stride * 2 + 1);
+
+	memset(buf, 0, size);
+
+	/*
+	 * Print subslice information in reverse order to match
+	 * userspace expectations.
+	 */
+	for (i = 0; i < sseu->ss_stride; i++)
+		sprintf(&buf[i * 2], "%02x",
+			sseu->subslice_mask[ss_offset + sseu->ss_stride 
-
+					    (i + 1)]);
+
+	return buf;
+}
+
  static void sseu_dump(const struct sseu_dev_info *sseu, struct
 drm_printer *p)
  {
  	int s;
+	char buf[SS_STR_MAX_SIZE];
 
Quoted 14 lines
Quoted 11 lines
drivers/gpu/drm/i915/intel_device_info.c +2 -2
  	drm_printf(p, "slice total: %u, mask=%04x\n",
  		   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=%s\n",
  			   s, intel_sseu_subslices_per_slice(sseu, s),
-			   sseu->subslice_mask[s]);
+			   subslice_per_slice_str(buf, ARRAY_SIZE(buf),

sseu, s));

Now that we have intel_sseu_get_subslices() can't we just print the return from that instead of using the buffer?

I personally would prefer we keep the stringify function as it gives a little more flexibility. Do you have a strong preference to move to a direct printk formatted string?

Quoted 51 lines
Quoted 5 lines

  	}
  	drm_printf(p, "EU total: %u\n", sseu->eu_total);
  	drm_printf(p, "EU per subslice: %u\n", sseu->eu_per_subslice);

<snip>

Quoted 43 lines
drivers/gpu/drm/i915/intel_device_info.c +1 -0
@@ -555,6 +570,7 @@ 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

drivers/gpu/drm/i915/intel_device_info.c +3 -7
@@ -566,22 +582,18 @@ 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:

drivers/gpu/drm/i915/intel_device_info.c +0 -1
@@ -598,9 +610,14 @@ 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;
Quoted 8 lines

drivers/gpu/drm/i915/intel_device_info.c static void haswell_sseu_info_init(struct drm_i915_private *dev_priv) · line 616

Quoted 4 lines
drivers/gpu/drm/i915/intel_device_info.c +4 -0
+
+	intel_sseu_set_info(sseu, hweight8(sseu->slice_mask),
+			    hweight8(subslice_mask),
+			    sseu->eu_per_subslice);

I'd still prefer this to use a local variable so that we always only set
sseu->eu_per_subslice from within intel_sseu_set_info.

So the reason I kept this is in intel_sseu_set_info we are really just setting the max_eus_per_subslice, not the eu_per_subslice. Are you saying you'd also like to move the code that sets eu_per_subslice in each generation's handler to local variables and/or just passed directly as an argument to intel_sseu_set_info?

I.e. should we use intel_sseu_set_info to set most or all of the members of the intel_sseu structure? Or is it OK to keep the current implementation of only using this to set default maximums per platform?

-Stuart

Quoted 12 lines

Daniele

Quoted 9 lines
drivers/gpu/drm/i915/intel_device_info.c +2 -0
  	for (s = 0; s < sseu->max_slices; s++) {
+		intel_sseu_set_subslices(sseu, s, subslice_mask);
+
  		for (ss = 0; ss < sseu->max_subslices; ss++) {
  			intel_sseu_set_eus(sseu, s, ss,
  					   (1UL << sseu-
Quoted 1 line

eu_per_subslice) - 1);

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#10 lore raw

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

<snip>

Quoted 59 lines
Quoted 44 lines
Quoted 44 lines
drivers/gpu/drm/i915/intel_device_info.c +29 -1
@@ -84,17 +84,46 @@ void intel_device_info_dump_flags(const struct
 intel_device_info *info,
   #undef PRINT_FLAG
   }
 
+#define SS_STR_MAX_SIZE (GEN_MAX_SUBSLICE_STRIDE * 2 + 1)
+
+static char *
+subslice_per_slice_str(char *buf, u8 size, const struct
 sseu_dev_info *sseu,
+		       u8 slice)
+{
+	int i;
+	u8 ss_offset = slice * sseu->ss_stride;
+
+	GEM_BUG_ON(slice >= sseu->max_slices);
+
+	/* Two ASCII character hex plus null terminator */
+	GEM_BUG_ON(size < sseu->ss_stride * 2 + 1);
+
+	memset(buf, 0, size);
+
+	/*
+	 * Print subslice information in reverse order to match
+	 * userspace expectations.
+	 */
+	for (i = 0; i < sseu->ss_stride; i++)
+		sprintf(&buf[i * 2], "%02x",
+			sseu->subslice_mask[ss_offset + sseu->ss_stride
-
+					    (i + 1)]);
+
+	return buf;
+}
+
   static void sseu_dump(const struct sseu_dev_info *sseu, struct
 drm_printer *p)
   {
   	int s;
+	char buf[SS_STR_MAX_SIZE];
 
Quoted 14 lines
Quoted 11 lines
drivers/gpu/drm/i915/intel_device_info.c +2 -2
   	drm_printf(p, "slice total: %u, mask=%04x\n",
   		   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=%s\n",
   			   s, intel_sseu_subslices_per_slice(sseu, s),
-			   sseu->subslice_mask[s]);
+			   subslice_per_slice_str(buf, ARRAY_SIZE(buf),

sseu, s));

Now that we have intel_sseu_get_subslices() can't we just print the return from that instead of using the buffer?

Quoted 4 lines

I personally would prefer we keep the stringify function as it gives a little more flexibility. Do you have a strong preference to move to a direct printk formatted string?

I do not, it just seemed like duplication since you're not really using any extra formatting or other flexibility in filling the buffer. This isn't a lot of code, so maybe we can switch to just using the u32 for now and add this back if/when we do require the flexibility?

Quoted 60 lines
Quoted 51 lines
Quoted 5 lines

   	}
   	drm_printf(p, "EU total: %u\n", sseu->eu_total);
   	drm_printf(p, "EU per subslice: %u\n", sseu->eu_per_subslice);

<snip>

Quoted 43 lines
drivers/gpu/drm/i915/intel_device_info.c +1 -0
@@ -555,6 +570,7 @@ 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

drivers/gpu/drm/i915/intel_device_info.c +3 -7
@@ -566,22 +582,18 @@ 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:

drivers/gpu/drm/i915/intel_device_info.c +0 -1
@@ -598,9 +610,14 @@ 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;
Quoted 8 lines

drivers/gpu/drm/i915/intel_device_info.c static void haswell_sseu_info_init(struct drm_i915_private *dev_priv) · line 616

Quoted 4 lines
drivers/gpu/drm/i915/intel_device_info.c +4 -0
+
+	intel_sseu_set_info(sseu, hweight8(sseu->slice_mask),
+			    hweight8(subslice_mask),
+			    sseu->eu_per_subslice);

I'd still prefer this to use a local variable so that we always only set
sseu->eu_per_subslice from within intel_sseu_set_info.

Quoted 5 lines

So the reason I kept this is in intel_sseu_set_info we are really just setting the max_eus_per_subslice, not the eu_per_subslice. Are you saying you'd also like to move the code that sets eu_per_subslice in each generation's handler to local variables and/or just passed directly as an argument to intel_sseu_set_info?

My bad, I confused eu_per_subslice and max_eus_per_subslice as the same variable. Just ignore this comment :)

Daniele

Quoted 19 lines

I.e. should we use intel_sseu_set_info to set most or all of the members of the intel_sseu structure? Or is it OK to keep the current implementation of only using this to set default maximums per platform?

-Stuart

Quoted 12 lines

Daniele

Quoted 9 lines
drivers/gpu/drm/i915/intel_device_info.c +2 -0
   	for (s = 0; s < sseu->max_slices; s++) {
+		intel_sseu_set_subslices(sseu, s, subslice_mask);
+
   		for (ss = 0; ss < sseu->max_subslices; ss++) {
   			intel_sseu_set_eus(sseu, s, ss,
   					   (1UL << sseu-
Quoted 1 line

eu_per_subslice) - 1);

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#11 lore raw

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

Quoted 77 lines · Daniele Ceraolo Spurio

<snip>

Quoted 68 lines
Quoted 59 lines
Quoted 59 lines
drivers/gpu/drm/i915/intel_device_info.c +0 -0
@@ -84,17 +84,46 @@ void intel_device_info_dump_flags(const

struct
intel_device_info *info,
#undef PRINT_FLAG
}

drivers/gpu/drm/i915/intel_device_info.c +4 -0
+#define SS_STR_MAX_SIZE (GEN_MAX_SUBSLICE_STRIDE * 2 + 1)
+
+static char *
+subslice_per_slice_str(char *buf, u8 size, const struct

sseu_dev_info *sseu,

drivers/gpu/drm/i915/intel_device_info.c +19 -0
+		       u8 slice)
+{
+	int i;
+	u8 ss_offset = slice * sseu->ss_stride;
+
+	GEM_BUG_ON(slice >= sseu->max_slices);
+
+	/* Two ASCII character hex plus null terminator */
+	GEM_BUG_ON(size < sseu->ss_stride * 2 + 1);
+
+	memset(buf, 0, size);
+
+	/*
+	 * Print subslice information in reverse order to match
+	 * userspace expectations.
+	 */
+	for (i = 0; i < sseu->ss_stride; i++)
+		sprintf(&buf[i * 2], "%02x",
+			sseu->subslice_mask[ss_offset + sseu-
Quoted 1 line

ss_stride

drivers/gpu/drm/i915/intel_device_info.c +5 -1
-
+					    (i + 1)]);
+
+	return buf;
+}
+
   static void sseu_dump(const struct sseu_dev_info *sseu,

struct
drm_printer *p)

   {
   	int s;
drivers/gpu/drm/i915/intel_device_info.c +1 -0
+	char buf[SS_STR_MAX_SIZE];
 
   	drm_printf(p, "slice total: %u, mask=%04x\n",
   		   hweight8(sseu->slice_mask), sseu-
Quoted 1 line

slice_mask);

drm_printf(p, "subslice total: %u\n",

intel_sseu_subslice_total(sseu));
   	for (s = 0; s < sseu->max_slices; s++) {
drivers/gpu/drm/i915/intel_device_info.c +0 -1
-		drm_printf(p, "slice%d: %u subslices,

mask=%04x\n",

drivers/gpu/drm/i915/intel_device_info.c +1 -0
+		drm_printf(p, "slice%d: %u subslices,

mask=%s\n",
s,
intel_sseu_subslices_per_slice(sseu, s),

Quoted 8 lines
Quoted 4 lines
drivers/gpu/drm/i915/intel_device_info.c +1 -1
-			   sseu->subslice_mask[s]);
+			   subslice_per_slice_str(buf,

ARRAY_SIZE(buf),
sseu, s));

Now that we have intel_sseu_get_subslices() can't we just print the
return from that instead of using the buffer?

Quoted 6 lines

I personally would prefer we keep the stringify function as it gives a
little more flexibility. Do you have a strong preference to move to a
direct printk formatted string?

Quoted 7 lines

I do not, it just seemed like duplication since you're not really using
any extra formatting or other flexibility in filling the buffer. This
isn't a lot of code, so maybe we can switch to just using the u32 for
now and add this back if/when we do require the flexibility?

Makes sense and thanks for the feedback. I'll revert back to the printk format.

Quoted 74 lines
Quoted 66 lines
Quoted 57 lines
Quoted 7 lines


   	}
   	drm_printf(p, "EU total: %u\n", sseu->eu_total);
   	drm_printf(p, "EU per subslice: %u\n", sseu-
Quoted 1 line

eu_per_subslice);

<snip>

Quoted 47 lines
drivers/gpu/drm/i915/intel_device_info.c +1 -0
@@ -555,6 +570,7 @@ 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

drivers/gpu/drm/i915/intel_device_info.c +3 -7
@@ -566,22 +582,18 @@ 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:

drivers/gpu/drm/i915/intel_device_info.c +1 -1
@@ -598,9 +610,14 @@ 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;
+
Quoted 8 lines

drivers/gpu/drm/i915/intel_device_info.c static void haswell_sseu_info_init(struct drm_i915_private *dev_priv) · line 616

Quoted 3 lines
drivers/gpu/drm/i915/intel_device_info.c +3 -0
+	intel_sseu_set_info(sseu, hweight8(sseu->slice_mask),
+			    hweight8(subslice_mask),
+			    sseu->eu_per_subslice);

I'd still prefer this to use a local variable so that we always only
set
sseu->eu_per_subslice from within intel_sseu_set_info.

Quoted 7 lines

So the reason I kept this is in intel_sseu_set_info we are really just
setting the max_eus_per_subslice, not the eu_per_subslice. Are you saying you'd also like to move the code that sets eu_per_subslice in
each generation's handler to local variables and/or just passed directly as an argument to intel_sseu_set_info?

Quoted 3 lines

My bad, I confused eu_per_subslice and max_eus_per_subslice as the same
variable. Just ignore this comment :)

No problem, thanks!

-Stuart

Quoted 24 lines

Daniele

Quoted 21 lines

I.e. should we use intel_sseu_set_info to set most or all of the members of the intel_sseu structure? Or is it OK to keep the current
implementation of only using this to set default maximums per platform?

-Stuart

Quoted 12 lines

Daniele

Quoted 9 lines
drivers/gpu/drm/i915/intel_device_info.c +2 -0
   	for (s = 0; s < sseu->max_slices; s++) {
+		intel_sseu_set_subslices(sseu, s,
 subslice_mask);
+
   		for (ss = 0; ss < sseu->max_subslices; ss++) {
   			intel_sseu_set_eus(sseu, s, ss,
   					   (1UL << sseu-
Quoted 1 line

eu_per_subslice) - 1);

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#12 lore raw

✗ Fi.CI.CHECKPATCH: warning for Refactor to expand subslice mask (rev8)

In reply to Stuart Summers
== Series Details ==

== Series Details ==

Series: Refactor to expand subslice mask (rev8)
URL : https://patchwork.freedesktop.org/series/59742/
State : warning

== Summary ==

$ dim checkpatch origin/drm-tip
bde01fefeccf drm/i915: Use local variable for SSEU info in GETPARAM ioctl
5b5850b4867c drm/i915: Add macro for SSEU stride calculation
2d091162979d drm/i915: Move calculation of subslices per slice to new function
9562a29d51ba drm/i915: Refactor sseu helper functions
8236a3377935 drm/i915: Expand subslice mask
-:113: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'dev_priv_' - possible side-effects?
#113: FILE: drivers/gpu/drm/i915/gt/intel_engine_types.h:546:
+#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_)))

-:113: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'sseu_' - possible side-effects? #113: FILE: drivers/gpu/drm/i915/gt/intel_engine_types.h:546:
+#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_)))

-:113: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'slice_' - possible side-effects? #113: FILE: drivers/gpu/drm/i915/gt/intel_engine_types.h:546:
+#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_)))

-:113: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'subslice_' - possible side-effects? #113: FILE: drivers/gpu/drm/i915/gt/intel_engine_types.h:546:
+#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, 4 checks, 729 lines checked

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#13 lore raw

✗ Fi.CI.SPARSE: warning for Refactor to expand subslice mask (rev8)

In reply to Stuart Summers
== Series Details ==

== Series Details ==

Series: Refactor to expand subslice mask (rev8)
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:464:24: warning: expression using sizeof(void)

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#14 lore raw

✓ Fi.CI.BAT: success for Refactor to expand subslice mask (rev8)

In reply to Stuart Summers
== Series Details ==

== Series Details ==

Series: Refactor to expand subslice mask (rev8)
URL : https://patchwork.freedesktop.org/series/59742/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_6043 -> Patchwork_12965
====================================================

Summary
-------

**WARNING**

Minor unknown changes coming with Patchwork_12965 need to be verified manually.

If you think the reported changes have nothing to do with the changes introduced in Patchwork_12965, please notify your bug team to allow them to document this new failure mode, which will reduce false positives in CI.

External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/

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

Here are the unknown changes that may have been introduced in Patchwork_12965:

### IGT changes ###

#### Warnings ####

* igt@i915_selftest@live_hangcheck:
- fi-apl-guc: [INCOMPLETE][1] ([fdo#103927] / [fdo#110581]) -> [DMESG-FAIL][2]
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/fi-apl-guc/igt@i915_selftest@live_hangcheck.html
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/fi-apl-guc/igt@i915_selftest@live_hangcheck.html

#### Suppressed ####

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

* igt@kms_chamelium@dp-crc-fast:
- {fi-cml-u2}: [PASS][3] -> [FAIL][4]
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/fi-cml-u2/igt@[email protected]
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/fi-cml-u2/igt@[email protected]

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

Here are the changes found in Patchwork_12965 that come from known issues:

### IGT changes ###

#### Issues hit ####

* igt@i915_selftest@live_hangcheck:
- fi-skl-iommu: [PASS][5] -> [INCOMPLETE][6] ([fdo#108602] / [fdo#108744] / [fdo#110581])
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/fi-skl-iommu/igt@i915_selftest@live_hangcheck.html
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/fi-skl-iommu/igt@i915_selftest@live_hangcheck.html

* igt@kms_pipe_crc_basic@suspend-read-crc-pipe-a:
- fi-apl-guc: [PASS][7] -> [DMESG-WARN][8] ([fdo#110512])
[7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/fi-apl-guc/igt@[email protected]
[8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/fi-apl-guc/igt@[email protected]

#### Possible fixes ####

* igt@gem_exec_suspend@basic-s3:
- fi-apl-guc: [DMESG-WARN][9] ([fdo#110512]) -> [PASS][10]
[9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/fi-apl-guc/igt@[email protected]
[10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/fi-apl-guc/igt@[email protected]

* igt@i915_selftest@live_contexts:
- fi-skl-gvtdvm: [DMESG-FAIL][11] ([fdo#110235]) -> [PASS][12]
[11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/fi-skl-gvtdvm/igt@i915_selftest@live_contexts.html
[12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/fi-skl-gvtdvm/igt@i915_selftest@live_contexts.html

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

[fdo#103927]: https://bugs.freedesktop.org/show_bug.cgi?id=103927
[fdo#108602]: https://bugs.freedesktop.org/show_bug.cgi?id=108602
[fdo#108744]: https://bugs.freedesktop.org/show_bug.cgi?id=108744
[fdo#110235]: https://bugs.freedesktop.org/show_bug.cgi?id=110235
[fdo#110512]: https://bugs.freedesktop.org/show_bug.cgi?id=110512
[fdo#110581]: https://bugs.freedesktop.org/show_bug.cgi?id=110581

Participating hosts (53 -> 43)
------------------------------

Missing (10): fi-kbl-soraka fi-ilk-m540 fi-hsw-4200u fi-byt-j1900 fi-byt-squawks fi-bsw-cyan fi-gdg-551 fi-icl-y fi-byt-clapper fi-bdw-samus

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

* Linux: CI_DRM_6043 -> Patchwork_12965

CI_DRM_6043: b33a03a0d9c2f7376b78c356d4e0e9e55f495f69 @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_4972: f052e49a43cc9704ea5f240df15dd9d3dfed68ab @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
Patchwork_12965: 8236a337793574e5ba805f69c4ac50598d6c7034 @ git://anongit.freedesktop.org/gfx-ci/linux

== Linux commits ==

8236a3377935 drm/i915: Expand subslice mask
9562a29d51ba drm/i915: Refactor sseu helper functions 2d091162979d drm/i915: Move calculation of subslices per slice to new function 5b5850b4867c drm/i915: Add macro for SSEU stride calculation bde01fefeccf 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_12965/
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#15 lore raw

✓ Fi.CI.IGT: success for Refactor to expand subslice mask (rev8)

In reply to Stuart Summers
== Series Details ==

== Series Details ==

Series: Refactor to expand subslice mask (rev8)
URL : https://patchwork.freedesktop.org/series/59742/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_6043_full -> Patchwork_12965_full
====================================================

Summary
-------

**SUCCESS**

No regressions found.

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

Here are the changes found in Patchwork_12965_full that come from known issues:

### IGT changes ###

#### Issues hit ####

* igt@gem_ctx_isolation@bcs0-s3:
- shard-kbl: [PASS][1] -> [DMESG-WARN][2] ([fdo#108566]) +2 similar issues
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-kbl6/igt@[email protected]
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-kbl1/igt@[email protected]

* igt@gem_softpin@noreloc-s3:
- shard-skl: [PASS][3] -> [INCOMPLETE][4] ([fdo#104108] / [fdo#107773] / [fdo#110581])
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-skl9/igt@[email protected]
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-skl5/igt@[email protected]

* igt@i915_pm_rpm@pm-caching:
- shard-skl: [PASS][5] -> [INCOMPLETE][6] ([fdo#107807] / [fdo#110581])
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-skl9/igt@[email protected]
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-skl6/igt@[email protected]

* igt@kms_cursor_legacy@2x-long-flip-vs-cursor-atomic:
- shard-glk: [PASS][7] -> [FAIL][8] ([fdo#104873])
[7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-glk4/igt@[email protected]
[8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-glk4/igt@[email protected]

* igt@kms_draw_crc@draw-method-xrgb8888-render-xtiled:
- shard-skl: [PASS][9] -> [FAIL][10] ([fdo#103184] / [fdo#103232])
[9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-skl5/igt@[email protected]
[10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-skl9/igt@[email protected]

* igt@kms_flip@2x-flip-vs-suspend-interruptible:
- shard-glk: [PASS][11] -> [INCOMPLETE][12] ([fdo#103359] / [fdo#110581] / [k.org#198133])
[11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-glk3/igt@[email protected]
[12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-glk7/igt@[email protected]

* igt@kms_flip@2x-plain-flip-fb-recreate:
- shard-glk: [PASS][13] -> [FAIL][14] ([fdo#100368])
[13]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-glk9/igt@[email protected]
[14]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-glk9/igt@[email protected]

* igt@kms_flip@flip-vs-expired-vblank:
- shard-skl: [PASS][15] -> [FAIL][16] ([fdo#105363])
[15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-skl8/igt@[email protected]
[16]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-skl2/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbc-rgb101010-draw-mmap-cpu:
- shard-skl: [PASS][17] -> [FAIL][18] ([fdo#103167] / [fdo#110379])
[17]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-skl5/igt@[email protected]
[18]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-skl9/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbc-suspend:
- shard-skl: [PASS][19] -> [INCOMPLETE][20] ([fdo#104108] / [fdo#110581])
[19]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-skl6/igt@[email protected]
[20]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-skl2/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbcpsr-1p-primscrn-cur-indfb-draw-render:
- shard-iclb: [PASS][21] -> [FAIL][22] ([fdo#103167]) +1 similar issue
[21]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-iclb5/igt@kms_frontbuffer_tracking@fbcpsr-1p-primscrn-cur-indfb-draw-render.html
[22]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-iclb8/igt@kms_frontbuffer_tracking@fbcpsr-1p-primscrn-cur-indfb-draw-render.html

* igt@kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-indfb-draw-mmap-gtt:
- shard-skl: [PASS][23] -> [FAIL][24] ([fdo#103167])
[23]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-skl5/igt@kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-indfb-draw-mmap-gtt.html
[24]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-skl9/igt@kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-indfb-draw-mmap-gtt.html

* igt@kms_pipe_crc_basic@suspend-read-crc-pipe-b:
- shard-apl: [PASS][25] -> [DMESG-WARN][26] ([fdo#108566]) +5 similar issues
[25]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-apl6/igt@[email protected]
[26]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-apl1/igt@[email protected]

* igt@kms_plane_lowres@pipe-a-tiling-x:
- shard-iclb: [PASS][27] -> [FAIL][28] ([fdo#103166]) +1 similar issue
[27]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-iclb3/igt@[email protected]
[28]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-iclb4/igt@[email protected]

* igt@kms_psr@no_drrs:
- shard-iclb: [PASS][29] -> [FAIL][30] ([fdo#108341])
[29]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-iclb5/igt@kms_psr@no_drrs.html
[30]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-iclb1/igt@kms_psr@no_drrs.html

* igt@kms_psr@psr2_sprite_plane_move:
- shard-iclb: [PASS][31] -> [SKIP][32] ([fdo#109441]) +2 similar issues
[31]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-iclb2/igt@kms_psr@psr2_sprite_plane_move.html
[32]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-iclb8/igt@kms_psr@psr2_sprite_plane_move.html

* igt@kms_rotation_crc@multiplane-rotation:
- shard-kbl: [PASS][33] -> [INCOMPLETE][34] ([fdo#103665] / [fdo#110581])
[33]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-kbl2/igt@[email protected]
[34]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-kbl5/igt@[email protected]

#### Possible fixes ####

* igt@gem_workarounds@suspend-resume:
- shard-apl: [DMESG-WARN][35] ([fdo#108566]) -> [PASS][36] +4 similar issues
[35]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-apl3/igt@[email protected]
[36]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-apl8/igt@[email protected]

* igt@i915_pm_rpm@i2c:
- shard-iclb: [FAIL][37] ([fdo#104097]) -> [PASS][38]
[37]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-iclb3/igt@[email protected]
[38]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-iclb4/igt@[email protected]

* igt@i915_suspend@debugfs-reader:
- shard-kbl: [DMESG-WARN][39] ([fdo#108566]) -> [PASS][40] +1 similar issue
[39]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-kbl1/igt@[email protected]
[40]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-kbl2/igt@[email protected]

* igt@kms_flip@plain-flip-ts-check-interruptible:
- shard-skl: [FAIL][41] ([fdo#100368]) -> [PASS][42]
[41]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-skl9/igt@[email protected]
[42]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-skl9/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbcpsr-tilingchange:
- shard-iclb: [FAIL][43] ([fdo#103167]) -> [PASS][44] +5 similar issues
[43]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-iclb4/igt@[email protected]
[44]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-iclb4/igt@[email protected]

* igt@kms_plane_alpha_blend@pipe-a-constant-alpha-min:
- shard-skl: [FAIL][45] ([fdo#108145]) -> [PASS][46]
[45]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-skl7/igt@[email protected]
[46]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-skl10/igt@[email protected]

* igt@kms_plane_alpha_blend@pipe-c-coverage-7efc:
- shard-skl: [FAIL][47] ([fdo#108145] / [fdo#110403]) -> [PASS][48]
[47]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-skl2/igt@[email protected]
[48]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-skl6/igt@[email protected]

* igt@kms_psr@psr2_primary_mmap_gtt:
- shard-iclb: [SKIP][49] ([fdo#109441]) -> [PASS][50] +2 similar issues
[49]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-iclb4/igt@kms_psr@psr2_primary_mmap_gtt.html
[50]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-iclb2/igt@kms_psr@psr2_primary_mmap_gtt.html

* igt@kms_setmode@basic:
- shard-kbl: [FAIL][51] ([fdo#99912]) -> [PASS][52]
[51]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-kbl6/igt@[email protected]
[52]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-kbl1/igt@[email protected]

#### Warnings ####

* igt@gem_eio@reset-stress:
- shard-skl: [FAIL][53] -> [FAIL][54] ([fdo#105957])
[53]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6043/shard-skl5/igt@[email protected]
[54]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12965/shard-skl2/igt@[email protected]

[fdo#100368]: https://bugs.freedesktop.org/show_bug.cgi?id=100368
[fdo#103166]: https://bugs.freedesktop.org/show_bug.cgi?id=103166
[fdo#103167]: https://bugs.freedesktop.org/show_bug.cgi?id=103167
[fdo#103184]: https://bugs.freedesktop.org/show_bug.cgi?id=103184
[fdo#103232]: https://bugs.freedesktop.org/show_bug.cgi?id=103232
[fdo#103359]: https://bugs.freedesktop.org/show_bug.cgi?id=103359
[fdo#103665]: https://bugs.freedesktop.org/show_bug.cgi?id=103665
[fdo#104097]: https://bugs.freedesktop.org/show_bug.cgi?id=104097
[fdo#104108]: https://bugs.freedesktop.org/show_bug.cgi?id=104108
[fdo#104873]: https://bugs.freedesktop.org/show_bug.cgi?id=104873
[fdo#105363]: https://bugs.freedesktop.org/show_bug.cgi?id=105363
[fdo#105957]: https://bugs.freedesktop.org/show_bug.cgi?id=105957
[fdo#107773]: https://bugs.freedesktop.org/show_bug.cgi?id=107773
[fdo#107807]: https://bugs.freedesktop.org/show_bug.cgi?id=107807
[fdo#108145]: https://bugs.freedesktop.org/show_bug.cgi?id=108145
[fdo#108341]: https://bugs.freedesktop.org/show_bug.cgi?id=108341
[fdo#108566]: https://bugs.freedesktop.org/show_bug.cgi?id=108566
[fdo#109441]: https://bugs.freedesktop.org/show_bug.cgi?id=109441
[fdo#110379]: https://bugs.freedesktop.org/show_bug.cgi?id=110379
[fdo#110403]: https://bugs.freedesktop.org/show_bug.cgi?id=110403
[fdo#110581]: https://bugs.freedesktop.org/show_bug.cgi?id=110581
[fdo#99912]: https://bugs.freedesktop.org/show_bug.cgi?id=99912
[k.org#198133]: https://bugzilla.kernel.org/show_bug.cgi?id=198133

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

No changes in participating hosts

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

* Linux: CI_DRM_6043 -> Patchwork_12965

CI_DRM_6043: b33a03a0d9c2f7376b78c356d4e0e9e55f495f69 @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_4972: f052e49a43cc9704ea5f240df15dd9d3dfed68ab @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
Patchwork_12965: 8236a337793574e5ba805f69c4ac50598d6c7034 @ 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_12965/
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx