drm/i915: store all subslice masks

Up to now, subslice mask was assumed to be uniform across slices. But
starting with Cannonlake, slices can be asymmetric (for example slice0
has different number of subslices as slice1+). This change stores all
subslices masks for all slices rather than having a single mask that
applies to all slices.

v2: Rework how we store total numbers in sseu_dev_info (Tvrtko)
    Fix CHV eu masks, was reading disabled as enabled (Tvrtko)
    Readability changes (Tvrtko)
    Add EU index helper (Tvrtko)

v3: Turn ALIGN(v, 8) / 8 into DIV_ROUND_UP(v, BITS_PER_BYTE) (Tvrtko)
    Reuse sseu_eu_idx() for setting eu_mask on CHV (Tvrtko)
    Reformat debug prints for subslices (Tvrtko)

v4: Change eu_mask helper into sseu_set_eus() (Tvrtko)

v5: With Haswell reporting masks & counts, bump sseu_*_eus() functions
    to use u16 (Lionel)

v6: Fix sseu_get_eus() for > 8 EUs per subslice (Lionel)

v7: Change debugfs enabels for number of subslices per slice, will
    need a small igt/pm_sseu change (Lionel)
    Drop subslice_total field from sseu_dev_info, rely on
    sseu_subslice_total() to recompute the value instead (Lionel)

v8: Remove unused function compute_subslice_total() (Lionel)
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180306122857.27317-2-lionel.g.landwerlin@intel.com

drivers/gpu/drm/i915/i915_debugfs.c

@@ -4323,7 +4323,7 @@ static void cherryview_sseu_device_status(struct drm_i915_private *dev_priv,
 			continue;
 
 		sseu->slice_mask = BIT(0);
-		sseu->subslice_mask |= BIT(ss);
+		sseu->subslice_mask[0] |= BIT(ss);
 		eu_cnt = ((sig1[ss] & CHV_EU08_PG_ENABLE) ? 0 : 2) +
 			 ((sig1[ss] & CHV_EU19_PG_ENABLE) ? 0 : 2) +
 			 ((sig1[ss] & CHV_EU210_PG_ENABLE) ? 0 : 2) +
@@ -4370,7 +4370,7 @@ static void gen10_sseu_device_status(struct drm_i915_private *dev_priv,
 			continue;
 
 		sseu->slice_mask |= BIT(s);
-		sseu->subslice_mask = info->sseu.subslice_mask;
+		sseu->subslice_mask[s] = info->sseu.subslice_mask[s];
 
 		for (ss = 0; ss < ss_max; ss++) {
 			unsigned int eu_cnt;
@@ -4425,8 +4425,8 @@ 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 =
-				INTEL_INFO(dev_priv)->sseu.subslice_mask;
+			sseu->subslice_mask[s] =
+				INTEL_INFO(dev_priv)->sseu.subslice_mask[s];
 
 		for (ss = 0; ss < ss_max; ss++) {
 			unsigned int eu_cnt;
@@ -4436,7 +4436,7 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
 					/* skip disabled subslice */
 					continue;
 
-				sseu->subslice_mask |= BIT(ss);
+				sseu->subslice_mask[s] |= BIT(ss);
 			}
 
 			eu_cnt = 2 * hweight32(eu_reg[2*s + ss/2] &
@@ -4458,9 +4458,12 @@ static void broadwell_sseu_device_status(struct drm_i915_private *dev_priv,
 	sseu->slice_mask = slice_info & GEN8_LSLICESTAT_MASK;
 
 	if (sseu->slice_mask) {
-		sseu->subslice_mask = INTEL_INFO(dev_priv)->sseu.subslice_mask;
 		sseu->eu_per_subslice =
 				INTEL_INFO(dev_priv)->sseu.eu_per_subslice;
+		for (s = 0; s < fls(sseu->slice_mask); s++) {
+			sseu->subslice_mask[s] =
+				INTEL_INFO(dev_priv)->sseu.subslice_mask[s];
+		}
 		sseu->eu_total = sseu->eu_per_subslice *
 				 sseu_subslice_total(sseu);
 
@@ -4479,6 +4482,7 @@ static void i915_print_sseu_info(struct seq_file *m, bool is_available_info,
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	const char *type = is_available_info ? "Available" : "Enabled";
+	int s;
 
 	seq_printf(m, "  %s Slice Mask: %04x\n", type,
 		   sseu->slice_mask);
@@ -4486,10 +4490,10 @@ static void i915_print_sseu_info(struct seq_file *m, bool is_available_info,
 		   hweight8(sseu->slice_mask));
 	seq_printf(m, "  %s Subslice Total: %u\n", type,
 		   sseu_subslice_total(sseu));
-	seq_printf(m, "  %s Subslice Mask: %04x\n", type,
-		   sseu->subslice_mask);
-	seq_printf(m, "  %s Subslice Per Slice: %u\n", type,
-		   hweight8(sseu->subslice_mask));
+	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]));
+	}
 	seq_printf(m, "  %s EU Total: %u\n", type,
 		   sseu->eu_total);
 	seq_printf(m, "  %s EU Per Subslice: %u\n", type,
@@ -4523,6 +4527,10 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
 
 	seq_puts(m, "SSEU Device Status\n");
 	memset(&sseu, 0, sizeof(sseu));
+	sseu.max_slices = INTEL_INFO(dev_priv)->sseu.max_slices;
+	sseu.max_subslices = INTEL_INFO(dev_priv)->sseu.max_subslices;
+	sseu.max_eus_per_subslice =
+		INTEL_INFO(dev_priv)->sseu.max_eus_per_subslice;
 
 	intel_runtime_pm_get(dev_priv);
 

drivers/gpu/drm/i915/i915_drv.c

@@ -428,7 +428,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 			return -ENODEV;
 		break;
 	case I915_PARAM_SUBSLICE_MASK:
-		value = INTEL_INFO(dev_priv)->sseu.subslice_mask;
+		value = INTEL_INFO(dev_priv)->sseu.subslice_mask[0];
 		if (!value)
 			return -ENODEV;
 		break;

drivers/gpu/drm/i915/intel_device_info.h

@@ -113,10 +113,13 @@ enum intel_platform {
 	func(supports_tv); \
 	func(has_ipc);
 
+#define GEN_MAX_SLICES		(6) /* CNL upper bound */
+#define GEN_MAX_SUBSLICES	(7)
+
 struct sseu_dev_info {
 	u8 slice_mask;
-	u8 subslice_mask;
-	u8 eu_total;
+	u8 subslice_mask[GEN_MAX_SUBSLICES];
+	u16 eu_total;
 	u8 eu_per_subslice;
 	u8 min_eu_in_pool;
 	/* For each slice, which subslice(s) has(have) 7 EUs (bitfield)? */
@@ -124,6 +127,17 @@ struct sseu_dev_info {
 	u8 has_slice_pg:1;
 	u8 has_subslice_pg:1;
 	u8 has_eu_pg:1;
+
+	/* Topology fields */
+	u8 max_slices;
+	u8 max_subslices;
+	u8 max_eus_per_subslice;
+
+	/* 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.
+	 */
+	u8 eu_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICES];
 };
 
 typedef u8 intel_ring_mask_t;
@@ -176,7 +190,49 @@ struct intel_driver_caps {
 
 static inline unsigned int sseu_subslice_total(const struct sseu_dev_info *sseu)
 {
-	return hweight8(sseu->slice_mask) * hweight8(sseu->subslice_mask);
+	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 = DIV_ROUND_UP(sseu->max_eus_per_subslice,
+					   BITS_PER_BYTE);
+	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 < 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 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 < DIV_ROUND_UP(sseu->max_eus_per_subslice, BITS_PER_BYTE); i++) {
+		sseu->eu_mask[offset + i] =
+			(eu_mask >> (BITS_PER_BYTE * i)) & 0xff;
+	}
 }
 
 const char *intel_platform_name(enum intel_platform platform);

drivers/gpu/drm/i915/intel_lrc.c

@@ -2248,7 +2248,7 @@ make_rpcs(struct drm_i915_private *dev_priv)
 
 	if (INTEL_INFO(dev_priv)->sseu.has_subslice_pg) {
 		rpcs |= GEN8_RPCS_SS_CNT_ENABLE;
-		rpcs |= hweight8(INTEL_INFO(dev_priv)->sseu.subslice_mask) <<
+		rpcs |= hweight8(INTEL_INFO(dev_priv)->sseu.subslice_mask[0]) <<
 			GEN8_RPCS_SS_CNT_SHIFT;
 		rpcs |= GEN8_RPCS_ENABLE;
 	}

drivers/gpu/drm/i915/intel_ringbuffer.h

@@ -92,7 +92,7 @@ hangcheck_action_to_str(const enum intel_engine_hangcheck_action a)
 
 #define instdone_subslice_mask(dev_priv__) \
 	(INTEL_GEN(dev_priv__) == 7 ? \
-	 1 : INTEL_INFO(dev_priv__)->sseu.subslice_mask)
+	 1 : INTEL_INFO(dev_priv__)->sseu.subslice_mask[0])
 
 #define for_each_instdone_slice_subslice(dev_priv__, slice__, subslice__) \
 	for ((slice__) = 0, (subslice__) = 0; \