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

1 files changed, 157 insertions, 51 deletions

diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index cadc5f81ed72..b29a35d441b4 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -81,12 +81,16 @@ void intel_device_info_dump_flags(const struct intel_device_info *info,
 
 static void sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p)
 {
+	int s;
+
 	drm_printf(p, "slice mask: %04x\n", sseu->slice_mask);
 	drm_printf(p, "slice total: %u\n", hweight8(sseu->slice_mask));
 	drm_printf(p, "subslice total: %u\n", sseu_subslice_total(sseu));
-	drm_printf(p, "subslice mask %04x\n", sseu->subslice_mask);
-	drm_printf(p, "subslice per slice: %u\n",
-		   hweight8(sseu->subslice_mask));
+	for (s = 0; s < ARRAY_SIZE(sseu->subslice_mask); s++) {
+		drm_printf(p, "slice%d %u subslices mask=%04x\n",
+			   s, hweight8(sseu->subslice_mask[s]),
+			   sseu->subslice_mask[s]);
+	}
 	drm_printf(p, "EU total: %u\n", sseu->eu_total);
 	drm_printf(p, "EU per subslice: %u\n", sseu->eu_per_subslice);
 	drm_printf(p, "has slice power gating: %s\n",
@@ -120,22 +124,76 @@ void intel_device_info_dump(const struct intel_device_info *info,
 	intel_device_info_dump_flags(info, p);
 }
 
+static u16 compute_eu_total(const struct sseu_dev_info *sseu)
+{
+	u16 i, total = 0;
+
+	for (i = 0; i < ARRAY_SIZE(sseu->eu_mask); i++)
+		total += hweight8(sseu->eu_mask[i]);
+
+	return total;
+}
+
 static void gen10_sseu_info_init(struct drm_i915_private *dev_priv)
 {
 	struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu;
 	const u32 fuse2 = I915_READ(GEN8_FUSE2);
+	int s, ss;
+	const int eu_mask = 0xff;
+	u32 subslice_mask, eu_en;
 
 	sseu->slice_mask = (fuse2 & GEN10_F2_S_ENA_MASK) >>
 			    GEN10_F2_S_ENA_SHIFT;
-	sseu->subslice_mask = (1 << 4) - 1;
-	sseu->subslice_mask &= ~((fuse2 & GEN10_F2_SS_DIS_MASK) >>
-				 GEN10_F2_SS_DIS_SHIFT);
+	sseu->max_slices = 6;
+	sseu->max_subslices = 4;
+	sseu->max_eus_per_subslice = 8;
 
-	sseu->eu_total = hweight32(~I915_READ(GEN8_EU_DISABLE0));
-	sseu->eu_total += hweight32(~I915_READ(GEN8_EU_DISABLE1));
-	sseu->eu_total += hweight32(~I915_READ(GEN8_EU_DISABLE2));
-	sseu->eu_total += hweight8(~(I915_READ(GEN10_EU_DISABLE3) &
-				     GEN10_EU_DIS_SS_MASK));
+	subslice_mask = (1 << 4) - 1;
+	subslice_mask &= ~((fuse2 & GEN10_F2_SS_DIS_MASK) >>
+			   GEN10_F2_SS_DIS_SHIFT);
+
+	/*
+	 * Slice0 can have up to 3 subslices, but there are only 2 in
+	 * slice1/2.
+	 */
+	sseu->subslice_mask[0] = subslice_mask;
+	for (s = 1; s < sseu->max_slices; s++)
+		sseu->subslice_mask[s] = subslice_mask & 0x3;
+
+	/* Slice0 */
+	eu_en = ~I915_READ(GEN8_EU_DISABLE0);
+	for (ss = 0; ss < sseu->max_subslices; ss++)
+		sseu_set_eus(sseu, 0, ss, (eu_en >> (8 * ss)) & eu_mask);
+	/* Slice1 */
+	sseu_set_eus(sseu, 1, 0, (eu_en >> 24) & eu_mask);
+	eu_en = ~I915_READ(GEN8_EU_DISABLE1);
+	sseu_set_eus(sseu, 1, 1, eu_en & eu_mask);
+	/* Slice2 */
+	sseu_set_eus(sseu, 2, 0, (eu_en >> 8) & eu_mask);
+	sseu_set_eus(sseu, 2, 1, (eu_en >> 16) & eu_mask);
+	/* Slice3 */
+	sseu_set_eus(sseu, 3, 0, (eu_en >> 24) & eu_mask);
+	eu_en = ~I915_READ(GEN8_EU_DISABLE2);
+	sseu_set_eus(sseu, 3, 1, eu_en & eu_mask);
+	/* Slice4 */
+	sseu_set_eus(sseu, 4, 0, (eu_en >> 8) & eu_mask);
+	sseu_set_eus(sseu, 4, 1, (eu_en >> 16) & eu_mask);
+	/* Slice5 */
+	sseu_set_eus(sseu, 5, 0, (eu_en >> 24) & eu_mask);
+	eu_en = ~I915_READ(GEN10_EU_DISABLE3);
+	sseu_set_eus(sseu, 5, 1, eu_en & eu_mask);
+
+	/* Do a second pass where we mark the subslices disabled if all their
+	 * eus are off.
+	 */
+	for (s = 0; s < sseu->max_slices; s++) {
+		for (ss = 0; ss < sseu->max_subslices; ss++) {
+			if (sseu_get_eus(sseu, s, ss) == 0)
+				sseu->subslice_mask[s] &= ~BIT(ss);
+		}
+	}
+
+	sseu->eu_total = compute_eu_total(sseu);
 
 	/*
 	 * CNL is expected to always have a uniform distribution
@@ -156,26 +214,39 @@ static void gen10_sseu_info_init(struct drm_i915_private *dev_priv)
 static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
 {
 	struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu;
-	u32 fuse, eu_dis;
+	u32 fuse;
 
 	fuse = I915_READ(CHV_FUSE_GT);
 
 	sseu->slice_mask = BIT(0);
+	sseu->max_slices = 1;
+	sseu->max_subslices = 2;
+	sseu->max_eus_per_subslice = 8;
 
 	if (!(fuse & CHV_FGT_DISABLE_SS0)) {
-		sseu->subslice_mask |= BIT(0);
-		eu_dis = fuse & (CHV_FGT_EU_DIS_SS0_R0_MASK |
-				 CHV_FGT_EU_DIS_SS0_R1_MASK);
-		sseu->eu_total += 8 - hweight32(eu_dis);
+		u8 disabled_mask =
+			((fuse & CHV_FGT_EU_DIS_SS0_R0_MASK) >>
+			 CHV_FGT_EU_DIS_SS0_R0_SHIFT) |
+			(((fuse & CHV_FGT_EU_DIS_SS0_R1_MASK) >>
+			  CHV_FGT_EU_DIS_SS0_R1_SHIFT) << 4);
+
+		sseu->subslice_mask[0] |= BIT(0);
+		sseu_set_eus(sseu, 0, 0, ~disabled_mask);
 	}
 
 	if (!(fuse & CHV_FGT_DISABLE_SS1)) {
-		sseu->subslice_mask |= BIT(1);
-		eu_dis = fuse & (CHV_FGT_EU_DIS_SS1_R0_MASK |
-				 CHV_FGT_EU_DIS_SS1_R1_MASK);
-		sseu->eu_total += 8 - hweight32(eu_dis);
+		u8 disabled_mask =
+			((fuse & CHV_FGT_EU_DIS_SS1_R0_MASK) >>
+			 CHV_FGT_EU_DIS_SS1_R0_SHIFT) |
+			(((fuse & CHV_FGT_EU_DIS_SS1_R1_MASK) >>
+			  CHV_FGT_EU_DIS_SS1_R1_SHIFT) << 4);
+
+		sseu->subslice_mask[0] |= BIT(1);
+		sseu_set_eus(sseu, 0, 1, ~disabled_mask);
 	}
 
+	sseu->eu_total = compute_eu_total(sseu);
+
 	/*
 	 * CHV expected to always have a uniform distribution of EU
 	 * across subslices.
@@ -197,41 +268,52 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 {
 	struct intel_device_info *info = mkwrite_device_info(dev_priv);
 	struct sseu_dev_info *sseu = &info->sseu;
-	int s_max = 3, ss_max = 4, eu_max = 8;
 	int s, ss;
-	u32 fuse2, eu_disable;
-	u8 eu_mask = 0xff;
+	u32 fuse2, eu_disable, subslice_mask;
+	const u8 eu_mask = 0xff;
 
 	fuse2 = I915_READ(GEN8_FUSE2);
 	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
 
+	/* BXT has a single slice and at most 3 subslices. */
+	sseu->max_slices = IS_GEN9_LP(dev_priv) ? 1 : 3;
+	sseu->max_subslices = IS_GEN9_LP(dev_priv) ? 3 : 4;
+	sseu->max_eus_per_subslice = 8;
+
 	/*
 	 * The subslice disable field is global, i.e. it applies
 	 * to each of the enabled slices.
 	*/
-	sseu->subslice_mask = (1 << ss_max) - 1;
-	sseu->subslice_mask &= ~((fuse2 & GEN9_F2_SS_DIS_MASK) >>
-				 GEN9_F2_SS_DIS_SHIFT);
+	subslice_mask = (1 << sseu->max_subslices) - 1;
+	subslice_mask &= ~((fuse2 & GEN9_F2_SS_DIS_MASK) >>
+			   GEN9_F2_SS_DIS_SHIFT);
 
 	/*
 	 * Iterate through enabled slices and subslices to
 	 * count the total enabled EU.
 	*/
-	for (s = 0; s < s_max; s++) {
+	for (s = 0; s < sseu->max_slices; s++) {
 		if (!(sseu->slice_mask & BIT(s)))
 			/* skip disabled slice */
 			continue;
 
+		sseu->subslice_mask[s] = subslice_mask;
+
 		eu_disable = I915_READ(GEN9_EU_DISABLE(s));
-		for (ss = 0; ss < ss_max; ss++) {
+		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			int eu_per_ss;
+			u8 eu_disabled_mask;
 
-			if (!(sseu->subslice_mask & BIT(ss)))
+			if (!(sseu->subslice_mask[s] & BIT(ss)))
 				/* skip disabled subslice */
 				continue;
 
-			eu_per_ss = eu_max - hweight8((eu_disable >> (ss*8)) &
-						      eu_mask);
+			eu_disabled_mask = (eu_disable >> (ss*8)) & eu_mask;
+
+			sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
+
+			eu_per_ss = sseu->max_eus_per_subslice -
+				hweight8(eu_disabled_mask);
 
 			/*
 			 * Record which subslice(s) has(have) 7 EUs. we
@@ -240,11 +322,11 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 			 */
 			if (eu_per_ss == 7)
 				sseu->subslice_7eu[s] |= BIT(ss);
-
-			sseu->eu_total += eu_per_ss;
 		}
 	}
 
+	sseu->eu_total = compute_eu_total(sseu);
+
 	/*
 	 * SKL is expected to always have a uniform distribution
 	 * of EU across subslices with the exception that any one
@@ -270,8 +352,8 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 	sseu->has_eu_pg = sseu->eu_per_subslice > 2;
 
 	if (IS_GEN9_LP(dev_priv)) {
-#define IS_SS_DISABLED(ss)	(!(sseu->subslice_mask & BIT(ss)))
-		info->has_pooled_eu = hweight8(sseu->subslice_mask) == 3;
+#define IS_SS_DISABLED(ss)	(!(sseu->subslice_mask[0] & BIT(ss)))
+		info->has_pooled_eu = hweight8(sseu->subslice_mask[0]) == 3;
 
 		sseu->min_eu_in_pool = 0;
 		if (info->has_pooled_eu) {
@@ -289,19 +371,22 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
 {
 	struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu;
-	const int s_max = 3, ss_max = 3, eu_max = 8;
 	int s, ss;
-	u32 fuse2, eu_disable[3]; /* s_max */
+	u32 fuse2, subslice_mask, eu_disable[3]; /* s_max */
 
 	fuse2 = I915_READ(GEN8_FUSE2);
 	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
+	sseu->max_slices = 3;
+	sseu->max_subslices = 3;
+	sseu->max_eus_per_subslice = 8;
+
 	/*
 	 * The subslice disable field is global, i.e. it applies
 	 * to each of the enabled slices.
 	 */
-	sseu->subslice_mask = GENMASK(ss_max - 1, 0);
-	sseu->subslice_mask &= ~((fuse2 & GEN8_F2_SS_DIS_MASK) >>
-				 GEN8_F2_SS_DIS_SHIFT);
+	subslice_mask = GENMASK(sseu->max_subslices - 1, 0);
+	subslice_mask &= ~((fuse2 & GEN8_F2_SS_DIS_MASK) >>
+			   GEN8_F2_SS_DIS_SHIFT);
 
 	eu_disable[0] = I915_READ(GEN8_EU_DISABLE0) & GEN8_EU_DIS0_S0_MASK;
 	eu_disable[1] = (I915_READ(GEN8_EU_DISABLE0) >> GEN8_EU_DIS0_S1_SHIFT) |
@@ -315,30 +400,38 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
 	 * Iterate through enabled slices and subslices to
 	 * count the total enabled EU.
 	 */
-	for (s = 0; s < s_max; s++) {
+	for (s = 0; s < sseu->max_slices; s++) {
 		if (!(sseu->slice_mask & BIT(s)))
 			/* skip disabled slice */
 			continue;
 
-		for (ss = 0; ss < ss_max; ss++) {
+		sseu->subslice_mask[s] = subslice_mask;
+
+		for (ss = 0; ss < sseu->max_subslices; ss++) {
+			u8 eu_disabled_mask;
 			u32 n_disabled;
 
-			if (!(sseu->subslice_mask & BIT(ss)))
+			if (!(sseu->subslice_mask[ss] & BIT(ss)))
 				/* skip disabled subslice */
 				continue;
 
-			n_disabled = hweight8(eu_disable[s] >> (ss * eu_max));
+			eu_disabled_mask =
+				eu_disable[s] >> (ss * sseu->max_eus_per_subslice);
+
+			sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
+
+			n_disabled = hweight8(eu_disabled_mask);
 
 			/*
 			 * Record which subslices have 7 EUs.
 			 */
-			if (eu_max - n_disabled == 7)
+			if (sseu->max_eus_per_subslice - n_disabled == 7)
 				sseu->subslice_7eu[s] |= 1 << ss;
-
-			sseu->eu_total += eu_max - n_disabled;
 		}
 	}
 
+	sseu->eu_total = compute_eu_total(sseu);
+
 	/*
 	 * BDW is expected to always have a uniform distribution of EU across
 	 * subslices with the exception that any one EU in any one subslice may
@@ -362,6 +455,7 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 	struct intel_device_info *info = mkwrite_device_info(dev_priv);
 	struct sseu_dev_info *sseu = &info->sseu;
 	u32 fuse1;
+	int s, ss;
 
 	/*
 	 * There isn't a register to tell us how many slices/subslices. We
@@ -373,18 +467,22 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 		/* fall through */
 	case 1:
 		sseu->slice_mask = BIT(0);
-		sseu->subslice_mask = BIT(0);
+		sseu->subslice_mask[0] = BIT(0);
 		break;
 	case 2:
 		sseu->slice_mask = BIT(0);
-		sseu->subslice_mask = BIT(0) | BIT(1);
+		sseu->subslice_mask[0] = BIT(0) | BIT(1);
 		break;
 	case 3:
 		sseu->slice_mask = BIT(0) | BIT(1);
-		sseu->subslice_mask = BIT(0) | BIT(1);
+		sseu->subslice_mask[0] = BIT(0) | BIT(1);
+		sseu->subslice_mask[1] = BIT(0) | BIT(1);
 		break;
 	}
 
+	sseu->max_slices = hweight8(sseu->slice_mask);
+	sseu->max_subslices = hweight8(sseu->subslice_mask[0]);
+
 	fuse1 = I915_READ(HSW_PAVP_FUSE1);
 	switch ((fuse1 & HSW_F1_EU_DIS_MASK) >> HSW_F1_EU_DIS_SHIFT) {
 	default:
@@ -401,8 +499,16 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 		sseu->eu_per_subslice = 6;
 		break;
 	}
+	sseu->max_eus_per_subslice = sseu->eu_per_subslice;
+
+	for (s = 0; s < sseu->max_slices; s++) {
+		for (ss = 0; ss < sseu->max_subslices; ss++) {
+			sseu_set_eus(sseu, s, ss,
+				     (1UL << sseu->eu_per_subslice) - 1);
+		}
+	}
 
-	sseu->eu_total = sseu_subslice_total(sseu) * sseu->eu_per_subslice;
+	sseu->eu_total = compute_eu_total(sseu);
 
 	/* No powergating for you. */
 	sseu->has_slice_pg = 0;