drm/i915/xehpsdv: Add compute DSS type

Starting in XeHP, the concept of slice has been removed in favor of
DSS (Dual-Subslice) masks for various workload types. These workloads have
been divided into those enabled for geometry and those enabled for compute.

i915 currently maintains a single set of S/SS/EU masks for the device.
The goal of this patch set is to minimize the amount of impact to prior
generations while still giving the user maximum flexibility.

v2:
- Generalize a comment about uapi access to geometry/compute masks; the
proposed uapi has changed since the comment was first written, and
will show up in a future series once the userspace code is published.
(Lucas)

v3:
- Eliminate unnecessary has_compute_dss flag. (Lucas)
- Drop unwanted comment change in uapi header. (Lucas)

Bspec: 33117, 33118, 20376
Cc: Daniele Ceraolo Spurio <[e-mail]>
Cc: Matt Roper <[e-mail]>
Cc: Lucas De Marchi <[e-mail]>
Signed-off-by: Stuart Summers <[e-mail]>
Signed-off-by: Steve Hampson <[e-mail]>
Signed-off-by: Matt Roper <[e-mail]>
Reviewed-by: Lucas De Marchi <[e-mail]>
Link: https://patchwork.freedesktop.org/patch/msgid/[e-mail]

drivers/gpu/drm/i915/gt/intel_sseu.c

···
 }
 
 void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
-			      u32 ss_mask)
+			      u8 *subslice_mask, u32 ss_mask)
 {
 	int offset = slice * sseu->ss_stride;
 
-	memcpy(&sseu->subslice_mask[offset], &ss_mask, sseu->ss_stride);
+	memcpy(&subslice_mask[offset], &ss_mask, sseu->ss_stride);
 }
 
 unsigned int
···
 	return total;
 }
 
-static void gen11_compute_sseu_info(struct sseu_dev_info *sseu,
-				    u8 s_en, u32 ss_en, u16 eu_en)
+static u32 get_ss_stride_mask(struct sseu_dev_info *sseu, u8 s, u32 ss_en)
+{
+	u32 ss_mask;
+
+	ss_mask = ss_en >> (s * sseu->max_subslices);
+	ss_mask &= GENMASK(sseu->max_subslices - 1, 0);
+
+	return ss_mask;
+}
+
+static void gen11_compute_sseu_info(struct sseu_dev_info *sseu, u8 s_en,
+				    u32 g_ss_en, u32 c_ss_en, u16 eu_en)
 {
 	int s, ss;
 
-	/* ss_en represents entire subslice mask across all slices */
+	/* g_ss_en/c_ss_en represent entire subslice mask across all slices */
 	GEM_BUG_ON(sseu->max_slices * sseu->max_subslices >
-		   sizeof(ss_en) * BITS_PER_BYTE);
+		   sizeof(g_ss_en) * BITS_PER_BYTE);
 
 	for (s = 0; s < sseu->max_slices; s++) {
 		if ((s_en & BIT(s)) == 0)
···
 
 		sseu->slice_mask |= BIT(s);
 
-		intel_sseu_set_subslices(sseu, s, ss_en);
+		/*
+		 * XeHP introduces the concept of compute vs geometry DSS. To
+		 * reduce variation between GENs around subslice usage, store a
+		 * mask for both the geometry and compute enabled masks since
+		 * userspace will need to be able to query these masks
+		 * independently.  Also compute a total enabled subslice count
+		 * for the purposes of selecting subslices to use in a
+		 * particular GEM context.
+		 */
+		intel_sseu_set_subslices(sseu, s, sseu->compute_subslice_mask,
+					 get_ss_stride_mask(sseu, s, c_ss_en));
+		intel_sseu_set_subslices(sseu, s, sseu->geometry_subslice_mask,
+					 get_ss_stride_mask(sseu, s, g_ss_en));
+		intel_sseu_set_subslices(sseu, s, sseu->subslice_mask,
+					 get_ss_stride_mask(sseu, s,
+							    g_ss_en | c_ss_en));
 
 		for (ss = 0; ss < sseu->max_subslices; ss++)
 			if (intel_sseu_has_subslice(sseu, s, ss))
···
 {
 	struct sseu_dev_info *sseu = &gt->info.sseu;
 	struct intel_uncore *uncore = gt->uncore;
-	u32 dss_en;
+	u32 g_dss_en, c_dss_en = 0;
 	u16 eu_en = 0;
 	u8 eu_en_fuse;
 	u8 s_en;
···
 		s_en = intel_uncore_read(uncore, GEN11_GT_SLICE_ENABLE) &
 		       GEN11_GT_S_ENA_MASK;
 
-	dss_en = intel_uncore_read(uncore, GEN12_GT_DSS_ENABLE);
+	g_dss_en = intel_uncore_read(uncore, GEN12_GT_GEOMETRY_DSS_ENABLE);
+	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
+		c_dss_en = intel_uncore_read(uncore, GEN12_GT_COMPUTE_DSS_ENABLE);
 
 	/* one bit per pair of EUs */
 	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
···
 		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);
+	gen11_compute_sseu_info(sseu, s_en, g_dss_en, c_dss_en, eu_en);
 
 	/* TGL only supports slice-level power gating */
 	sseu->has_slice_pg = 1;
···
 	eu_en = ~(intel_uncore_read(uncore, GEN11_EU_DISABLE) &
 		  GEN11_EU_DIS_MASK);
 
-	gen11_compute_sseu_info(sseu, s_en, ss_en, eu_en);
+	gen11_compute_sseu_info(sseu, s_en, ss_en, 0, eu_en);
 
 	/* ICL has no power gating restrictions. */
 	sseu->has_slice_pg = 1;
···
 		sseu_set_eus(sseu, 0, 1, ~disabled_mask);
 	}
 
-	intel_sseu_set_subslices(sseu, 0, subslice_mask);
+	intel_sseu_set_subslices(sseu, 0, sseu->subslice_mask, subslice_mask);
 
 	sseu->eu_total = compute_eu_total(sseu);
 
···
 			/* skip disabled slice */
 			continue;
 
-		intel_sseu_set_subslices(sseu, s, subslice_mask);
+		intel_sseu_set_subslices(sseu, s, sseu->subslice_mask,
+					 subslice_mask);
 
 		eu_disable = intel_uncore_read(uncore, GEN9_EU_DISABLE(s));
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
···
 			/* skip disabled slice */
 			continue;
 
-		intel_sseu_set_subslices(sseu, s, subslice_mask);
+		intel_sseu_set_subslices(sseu, s, sseu->subslice_mask,
+					 subslice_mask);
 
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			u8 eu_disabled_mask;
···
 			    sseu->eu_per_subslice);
 
 	for (s = 0; s < sseu->max_slices; s++) {
-		intel_sseu_set_subslices(sseu, s, subslice_mask);
+		intel_sseu_set_subslices(sseu, s, sseu->subslice_mask,
+					 subslice_mask);
 
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			sseu_set_eus(sseu, s, ss,

drivers/gpu/drm/i915/gt/intel_sseu.h

···
 struct sseu_dev_info {
 	u8 slice_mask;
 	u8 subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
+	u8 geometry_subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
+	u8 compute_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;
···
 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);
+			      u8 *subslice_mask, u32 ss_mask);
 
 void intel_sseu_info_init(struct intel_gt *gt);
 

drivers/gpu/drm/i915/i915_reg.h

···
 
 #define GEN11_GT_SUBSLICE_DISABLE _MMIO(0x913C)
 
-#define GEN12_GT_DSS_ENABLE _MMIO(0x913C)
+#define GEN12_GT_GEOMETRY_DSS_ENABLE _MMIO(0x913C)
+#define GEN12_GT_COMPUTE_DSS_ENABLE _MMIO(0x9144)
 
 #define XEHP_EU_ENABLE			_MMIO(0x9134)
 #define XEHP_EU_ENA_MASK		0xFF