drm/i915/tgl: s/ss/eu fuse reading support

Gen12 has dual-subslices (DSS), which compared to gen11 subslices have
some duplicated resources/paths. Although DSS behave similarly to 2
subslices, instead of splitting this and presenting userspace with bits
not directly representative of hardware resources, present userspace
with a subslice_mask made up of DSS bits instead.

v2: GEM_BUG_ON on mask size (Lionel)

Bspec: 29547
Bspec: 12247
Cc: Kelvin Gardiner <kelvin.gardiner@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
CC: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com> #v1
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: James Ausmus <james.ausmus@intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Signed-off-by: Sudeep Dutt <sudeep.dutt@intel.com>
Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190913075137.18476-2-chris@chris-wilson.co.uk
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

4 files changed, 68 insertions, 29 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 4070f6ff1db6..d1d225204f09 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -18,12 +18,13 @@ struct drm_i915_private;
 #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)
-#define GEN_MAX_EUS		(10) /* HSW upper bound */
+#define GEN_MAX_EUS		(16) /* TGL upper bound */
 #define GEN_MAX_EU_STRIDE GEN_SSEU_STRIDE(GEN_MAX_EUS)
 
 struct sseu_dev_info {
 	u8 slice_mask;
 	u8 subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
+	u8 eu_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICES * GEN_MAX_EU_STRIDE];
 	u16 eu_total;
 	u8 eu_per_subslice;
 	u8 min_eu_in_pool;
@@ -40,12 +41,6 @@ struct sseu_dev_info {
 
 	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.
-	 */
-	u8 eu_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICES];
 };
 
 /*
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 43db50095257..b5b449a88cf1 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3823,7 +3823,8 @@ static void gen10_sseu_device_status(struct drm_i915_private *dev_priv,
 		for (ss = 0; ss < info->sseu.max_subslices; ss++) {
 			unsigned int eu_cnt;
 
-			if (!(s_reg[s] & (GEN9_PGCTL_SS_ACK(ss))))
+			if (info->sseu.has_subslice_pg &&
+			    !(s_reg[s] & (GEN9_PGCTL_SS_ACK(ss))))
 				/* skip disabled subslice */
 				continue;
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index acbda6d89a9b..7c64768976ac 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2956,6 +2956,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 
 #define GEN11_GT_SUBSLICE_DISABLE _MMIO(0x913C)
 
+#define GEN12_GT_DSS_ENABLE _MMIO(0x913C)
+
 #define GEN6_BSD_SLEEP_PSMI_CONTROL	_MMIO(0x12050)
 #define   GEN6_BSD_SLEEP_MSG_DISABLE	(1 << 0)
 #define   GEN6_BSD_SLEEP_FLUSH_DISABLE	(1 << 2)
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 728c881718a2..85e480bdc673 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -182,13 +182,69 @@ static u16 compute_eu_total(const struct sseu_dev_info *sseu)
 	return total;
 }
 
+static void gen11_compute_sseu_info(struct sseu_dev_info *sseu,
+				    u8 s_en, u32 ss_en, u16 eu_en)
+{
+	int s, ss;
+
+	/* ss_en represents entire subslice mask across all slices */
+	GEM_BUG_ON(sseu->max_slices * sseu->max_subslices >
+		   sizeof(ss_en) * BITS_PER_BYTE);
+
+	for (s = 0; s < sseu->max_slices; s++) {
+		if ((s_en & BIT(s)) == 0)
+			continue;
+
+		sseu->slice_mask |= BIT(s);
+
+		intel_sseu_set_subslices(sseu, s, ss_en);
+
+		for (ss = 0; ss < sseu->max_subslices; ss++)
+			if (intel_sseu_has_subslice(sseu, s, ss))
+				sseu_set_eus(sseu, s, ss, eu_en);
+	}
+	sseu->eu_per_subslice = hweight16(eu_en);
+	sseu->eu_total = compute_eu_total(sseu);
+}
+
+static void gen12_sseu_info_init(struct drm_i915_private *dev_priv)
+{
+	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
+	u8 s_en;
+	u32 dss_en;
+	u16 eu_en = 0;
+	u8 eu_en_fuse;
+	int eu;
+
+	/*
+	 * Gen12 has Dual-Subslices, which behave similarly to 2 gen11 SS.
+	 * Instead of splitting these, provide userspace with an array
+	 * of DSS to more closely represent the hardware resource.
+	 */
+	intel_sseu_set_info(sseu, 1, 6, 16);
+
+	s_en = I915_READ(GEN11_GT_SLICE_ENABLE) & GEN11_GT_S_ENA_MASK;
+
+	dss_en = I915_READ(GEN12_GT_DSS_ENABLE);
+
+	/* one bit per pair of EUs */
+	eu_en_fuse = ~(I915_READ(GEN11_EU_DISABLE) & GEN11_EU_DIS_MASK);
+	for (eu = 0; eu < sseu->max_eus_per_subslice / 2; eu++)
+		if (eu_en_fuse & BIT(eu))
+			eu_en |= BIT(eu * 2) | BIT(eu * 2 + 1);
+
+	gen11_compute_sseu_info(sseu, s_en, dss_en, eu_en);
+
+	/* TGL only supports slice-level power gating */
+	sseu->has_slice_pg = 1;
+}
+
 static void gen11_sseu_info_init(struct drm_i915_private *dev_priv)
 {
 	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	u8 s_en;
-	u32 ss_en, ss_en_mask;
+	u32 ss_en;
 	u8 eu_en;
-	int s;
 
 	if (IS_ELKHARTLAKE(dev_priv))
 		intel_sseu_set_info(sseu, 1, 4, 8);
@@ -197,26 +253,9 @@ static void gen11_sseu_info_init(struct drm_i915_private *dev_priv)
 
 	s_en = I915_READ(GEN11_GT_SLICE_ENABLE) & GEN11_GT_S_ENA_MASK;
 	ss_en = ~I915_READ(GEN11_GT_SUBSLICE_DISABLE);
-	ss_en_mask = BIT(sseu->max_subslices) - 1;
 	eu_en = ~(I915_READ(GEN11_EU_DISABLE) & GEN11_EU_DIS_MASK);
 
-	for (s = 0; s < sseu->max_slices; s++) {
-		if (s_en & BIT(s)) {
-			int ss_idx = sseu->max_subslices * s;
-			int ss;
-
-			sseu->slice_mask |= BIT(s);
-
-			intel_sseu_set_subslices(sseu, s, (ss_en >> ss_idx) &
-							  ss_en_mask);
-
-			for (ss = 0; ss < sseu->max_subslices; ss++)
-				if (intel_sseu_has_subslice(sseu, s, ss))
-					sseu_set_eus(sseu, s, ss, eu_en);
-		}
-	}
-	sseu->eu_per_subslice = hweight8(eu_en);
-	sseu->eu_total = compute_eu_total(sseu);
+	gen11_compute_sseu_info(sseu, s_en, ss_en, eu_en);
 
 	/* ICL has no power gating restrictions. */
 	sseu->has_slice_pg = 1;
@@ -955,8 +994,10 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 		gen9_sseu_info_init(dev_priv);
 	else if (IS_GEN(dev_priv, 10))
 		gen10_sseu_info_init(dev_priv);
-	else if (INTEL_GEN(dev_priv) >= 11)
+	else if (IS_GEN(dev_priv, 11))
 		gen11_sseu_info_init(dev_priv);
+	else if (INTEL_GEN(dev_priv) >= 12)
+		gen12_sseu_info_init(dev_priv);
 
 	if (IS_GEN(dev_priv, 6) && intel_vtd_active()) {
 		DRM_INFO("Disabling ppGTT for VT-d support\n");