[PATCH 10/10] drm/i915: Expand subslice mask

[Stuart Summers]

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

v2: Fix 32-bit build

Signed-off-by: Stuart Summers <stuart.summers at intel.com>
---
 drivers/gpu/drm/i915/gt/intel_sseu.c        | 27 ++++++++++++++++++++-
 drivers/gpu/drm/i915/gt/intel_sseu.h        |  5 +++-
 drivers/gpu/drm/i915/gt/intel_workarounds.c |  3 +--
 drivers/gpu/drm/i915/i915_debugfs.c         |  5 +++-
 drivers/gpu/drm/i915/intel_device_info.c    |  8 +++---
 5 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index 607c1447287c..e426f34b4dd6 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -30,6 +30,31 @@ intel_sseu_subslice_total(const struct sseu_dev_info *sseu)
 	return total;
 }
 
+u32 intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice)
+{
+	int i, offset = slice * sseu->ss_stride;
+	u32 mask = 0;
+
+	if (slice >= sseu->max_slices) {
+		DRM_ERROR("%s: invalid slice %d, max: %d\n",
+			  __func__, slice, sseu->max_slices);
+		return 0;
+	}
+
+	if (sseu->ss_stride > sizeof(mask)) {
+		DRM_ERROR("%s: invalid subslice stride %d, max: %u\n",
+			  __func__, sseu->ss_stride,
+			 (unsigned int)sizeof(mask));
+		return 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)
 {
@@ -43,7 +68,7 @@ void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
 unsigned int
 intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice)
 {
-	return hweight8(sseu->subslice_mask[slice]);
+	return hweight32(intel_sseu_get_subslices(sseu, slice));
 }
 
 u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 0ecc1c35a7a1..2291764b7db5 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -15,10 +15,11 @@ 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;
@@ -85,6 +86,8 @@ 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_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);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 704ace01e7f5..7ec60435d871 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -794,8 +794,7 @@ wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal)
 	}
 
 	slice = fls(sseu->slice_mask) - 1;
-	GEM_BUG_ON(slice >= ARRAY_SIZE(sseu->subslice_mask));
-	subslice = fls(l3_en & sseu->subslice_mask[slice]);
+	subslice = fls(l3_en & intel_sseu_get_subslices(sseu, slice));
 	if (!subslice) {
 		DRM_WARN("No common index found between subslice mask %x and L3 bank mask %x!\n",
 			 sseu->subslice_mask[slice], l3_en);
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 7bbd00c07c44..970f00785259 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3944,13 +3944,16 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
 
 		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] &
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 66fe68875d1b..7fe3afd0a738 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -93,9 +93,9 @@ static void sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p)
 		   hweight8(sseu->slice_mask), sseu->slice_mask);
 	drm_printf(p, "subslice total: %u\n", intel_sseu_subslice_total(sseu));
 	for (s = 0; s < sseu->max_slices; s++) {
-		drm_printf(p, "slice%d: %u subslices, mask=%04x\n",
+		drm_printf(p, "slice%d: %u subslices, mask=%08x\n",
 			   s, intel_sseu_subslices_per_slice(sseu, s),
-			   sseu->subslice_mask[s]);
+			   intel_sseu_get_subslices(sseu, s));
 	}
 	drm_printf(p, "EU total: %u\n", sseu->eu_total);
 	drm_printf(p, "EU per subslice: %u\n", sseu->eu_per_subslice);
@@ -159,9 +159,9 @@ void intel_device_info_dump_topology(const struct sseu_dev_info *sseu,
 	}
 
 	for (s = 0; s < sseu->max_slices; s++) {
-		drm_printf(p, "slice%d: %u subslice(s) (0x%hhx):\n",
+		drm_printf(p, "slice%d: %u subslice(s) (0x%08x):\n",
 			   s, intel_sseu_subslices_per_slice(sseu, s),
-			   sseu->subslice_mask[s]);
+			   intel_sseu_get_subslices(sseu, s));
 
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			u16 enabled_eus = sseu_get_eus(sseu, s, ss);
-- 
2.21.0.5.gaeb582a983