drm/i915: Expand subslice mask

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

v2: fix spacing in set_sseu_info args
    use set_sseu_info to initialize sseu data when building
    device status in debugfs
    rename variables in intel_engine_types.h to avoid checkpatch
    warnings
v3: update headers in intel_sseu.h
v4: add const to some sseu_dev_info variables
    use sseu->eu_stride for EU stride calculations
v5: address review comments from Tvrtko and Daniele
v6: remove extra space in intel_sseu_get_subslices
    return the correct subslice enable in for_each_instdone
    add GEM_BUG_ON to ensure user doesn't pass invalid ss_mask size
    use printk formatted string for subslice mask
v7: remove string.h header and rebase

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Acked-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190524154022.13575-6-stuart.summers@intel.com

6 files changed, 112 insertions, 21 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 6b838948ba24..158722b50691 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -953,12 +953,30 @@ 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) |
@@ -1034,6 +1052,7 @@ 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;
@@ -1051,7 +1070,8 @@ void intel_engine_get_instdone(struct intel_engine_cs *engine,
 
 		instdone->slice_common =
 			intel_uncore_read(uncore, GEN7_SC_INSTDONE);
-		for_each_instdone_slice_subslice(dev_priv, slice, subslice) {
+		for_each_instdone_slice_subslice(dev_priv, sseu, slice,
+						 subslice) {
 			instdone->sampler[slice][subslice] =
 				read_subslice_reg(dev_priv, slice, subslice,
 						  GEN7_SAMPLER_INSTDONE);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 01223864237a..4f311ceeab89 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -552,20 +552,20 @@ intel_engine_is_virtual(const struct intel_engine_cs *engine)
 	return engine->flags & I915_ENGINE_IS_VIRTUAL;
 }
 
-#define instdone_slice_mask(dev_priv__) \
-	(IS_GEN(dev_priv__, 7) ? \
-	 1 : RUNTIME_INFO(dev_priv__)->sseu.slice_mask)
-
-#define instdone_subslice_mask(dev_priv__) \
-	(IS_GEN(dev_priv__, 7) ? \
-	 1 : RUNTIME_INFO(dev_priv__)->sseu.subslice_mask[0])
-
-#define for_each_instdone_slice_subslice(dev_priv__, slice__, subslice__) \
-	for ((slice__) = 0, (subslice__) = 0; \
-	     (slice__) < I915_MAX_SLICES; \
-	     (subslice__) = ((subslice__) + 1) < I915_MAX_SUBSLICES ? (subslice__) + 1 : 0, \
-	       (slice__) += ((subslice__) == 0)) \
-		for_each_if((BIT(slice__) & instdone_slice_mask(dev_priv__)) && \
-			    (BIT(subslice__) & instdone_subslice_mask(dev_priv__)))
+#define instdone_has_slice(dev_priv___, sseu___, slice___) \
+	((IS_GEN(dev_priv___, 7) ? 1 : ((sseu___)->slice_mask)) & \
+	BIT(slice___))
+
+#define instdone_has_subslice(dev_priv__, sseu__, slice__, subslice__) \
+	(IS_GEN(dev_priv__, 7) ? (1 & BIT(subslice__)) : \
+	 intel_sseu_has_subslice(sseu__, slice__, subslice__))
+
+#define for_each_instdone_slice_subslice(dev_priv_, sseu_, slice_, subslice_) \
+	for ((slice_) = 0, (subslice_) = 0; (slice_) < I915_MAX_SLICES; \
+	     (subslice_) = ((subslice_) + 1) % I915_MAX_SUBSLICES, \
+	     (slice_) += ((subslice_) == 0)) \
+		for_each_if((instdone_has_slice(dev_priv_, sseu_, slice_)) && \
+			    (instdone_has_subslice(dev_priv_, sseu_, slice_, \
+						    subslice_)))
 
 #endif /* __INTEL_ENGINE_TYPES_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_hangcheck.c b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
index 3a4d09b80fa0..b19cd4cdcb5c 100644
--- a/drivers/gpu/drm/i915/gt/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
@@ -51,6 +51,7 @@ static bool instdone_unchanged(u32 current_instdone, u32 *old_instdone)
 static bool subunits_stuck(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
+	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	struct intel_instdone instdone;
 	struct intel_instdone *accu_instdone = &engine->hangcheck.instdone;
 	bool stuck;
@@ -72,7 +73,7 @@ static bool subunits_stuck(struct intel_engine_cs *engine)
 	stuck &= instdone_unchanged(instdone.slice_common,
 				    &accu_instdone->slice_common);
 
-	for_each_instdone_slice_subslice(dev_priv, slice, subslice) {
+	for_each_instdone_slice_subslice(dev_priv, sseu, slice, subslice) {
 		stuck &= instdone_unchanged(instdone.sampler[slice][subslice],
 					    &accu_instdone->sampler[slice][subslice]);
 		stuck &= instdone_unchanged(instdone.row[slice][subslice],
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index a0756f006f5f..763b811f2c9d 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -8,6 +8,17 @@
 #include "intel_lrc_reg.h"
 #include "intel_sseu.h"
 
+void intel_sseu_set_info(struct sseu_dev_info *sseu, u8 max_slices,
+			 u8 max_subslices, u8 max_eus_per_subslice)
+{
+	sseu->max_slices = max_slices;
+	sseu->max_subslices = max_subslices;
+	sseu->max_eus_per_subslice = max_eus_per_subslice;
+
+	sseu->ss_stride = GEN_SSEU_STRIDE(sseu->max_subslices);
+	sseu->eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
+}
+
 unsigned int
 intel_sseu_subslice_total(const struct sseu_dev_info *sseu)
 {
@@ -19,10 +30,44 @@ intel_sseu_subslice_total(const struct sseu_dev_info *sseu)
 	return total;
 }
 
+void intel_sseu_copy_subslices(const struct sseu_dev_info *sseu, int slice,
+			       u8 *to_mask)
+{
+	int offset = slice * sseu->ss_stride;
+
+	memcpy(&to_mask[offset], &sseu->subslice_mask[offset], sseu->ss_stride);
+}
+
+u32 intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice)
+{
+	int i, offset = slice * sseu->ss_stride;
+	u32 mask;
+
+	GEM_BUG_ON(slice >= sseu->max_slices);
+
+	GEM_BUG_ON(sseu->ss_stride > sizeof(mask));
+
+	for (i = 0; i < sseu->ss_stride; i++)
+		mask |= (u32)sseu->subslice_mask[offset + i] <<
+			i * BITS_PER_BYTE;
+
+	return mask;
+}
+
+void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
+			      u32 ss_mask)
+{
+	int i, offset = slice * sseu->ss_stride;
+
+	for (i = 0; i < sseu->ss_stride; i++)
+		sseu->subslice_mask[offset + i] =
+			(ss_mask >> (BITS_PER_BYTE * i)) & 0xff;
+}
+
 unsigned int
 intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice)
 {
-	return hweight8(sseu->subslice_mask[slice]);
+	return hweight32(intel_sseu_get_subslices(sseu, slice));
 }
 
 u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index b50d0401a4e2..eee21d9f320e 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;
@@ -33,6 +34,9 @@ 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 +67,33 @@ intel_sseu_from_device_info(const struct sseu_dev_info *sseu)
 	return value;
 }
 
+static inline bool
+intel_sseu_has_subslice(const struct sseu_dev_info *sseu, int slice,
+			int subslice)
+{
+	u8 mask = sseu->subslice_mask[slice * sseu->ss_stride +
+				      subslice / BITS_PER_BYTE];
+
+	return mask & BIT(subslice % BITS_PER_BYTE);
+}
+
+void intel_sseu_set_info(struct sseu_dev_info *sseu, u8 max_slices,
+			 u8 max_subslices, u8 max_eus_per_subslice);
+
 unsigned int
 intel_sseu_subslice_total(const struct sseu_dev_info *sseu);
 
 unsigned int
 intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice);
 
+void intel_sseu_copy_subslices(const struct sseu_dev_info *sseu, int slice,
+			       u8 *to_mask);
+
+u32  intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice);
+
+void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
+			      u32 ss_mask);
+
 u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
 			 const struct intel_sseu *req_sseu);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 133d069244f4..fbc853085809 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -784,7 +784,7 @@ 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;