drm/i915: Record the sseu configuration per-context & engine

We want to expose the ability to reconfigure the slices, subslice and
eu per context and per engine. To facilitate that, store the current
configuration on the context for each engine, which is initially set
to the device default upon creation.

v2: record sseu configuration per context & engine (Chris)

v3: introduce the i915_gem_context_sseu to store powergating
    programming, sseu_dev_info has grown quite a bit (Lionel)

v4: rename i915_gem_sseu into intel_sseu (Chris)
    use to_intel_context() (Chris)

v5: More to_intel_context() (Tvrtko)
    Switch intel_sseu from union to struct (Tvrtko)
    Move context default sseu in existing loop (Chris)

v6: s/intel_sseu_from_device_sseu/intel_device_default_sseu/ (Tvrtko)

Tvrtko Ursulin:

v7:
 * Pass intel_sseu by pointer instead of value to make_rpcs.
 * Rebase for make_rpcs changes.

v8:
 * Rebase for RPCS edit on pin.

v9:
 * Rebase for context image setup changes.

v10:
 * Rename dev_priv to i915. (Chris Wilson)

v11:
 * Rebase.

v12:
 * Rebase for IS_GEN changes.

v13:
 * Rebase for RUNTIME_INFO.

v14:
 * Rebase for intel_context_init.

v15:
 * Rebase for drm-tip changes.

v16:
 * Moved struct intel_sseu definition to i915_gem_context.h.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-1-tvrtko.ursulin@linux.intel.com

drivers/gpu/drm/i915/i915_drv.h

@@ -3305,6 +3305,20 @@ mkwrite_device_info(struct drm_i915_private *dev_priv)
 	return (struct intel_device_info *)INTEL_INFO(dev_priv);
 }
 
+static inline struct intel_sseu
+intel_device_default_sseu(struct drm_i915_private *i915)
+{
+	const struct sseu_dev_info *sseu = &RUNTIME_INFO(i915)->sseu;
+	struct intel_sseu value = {
+		.slice_mask = sseu->slice_mask,
+		.subslice_mask = sseu->subslice_mask[0],
+		.min_eus_per_subslice = sseu->max_eus_per_subslice,
+		.max_eus_per_subslice = sseu->max_eus_per_subslice,
+	};
+
+	return value;
+}
+
 /* modesetting */
 extern void intel_modeset_init_hw(struct drm_device *dev);
 extern int intel_modeset_init(struct drm_device *dev);

drivers/gpu/drm/i915/i915_gem_context.c

@@ -330,6 +330,9 @@ intel_context_init(struct intel_context *ce,
 
 	INIT_LIST_HEAD(&ce->signal_link);
 	INIT_LIST_HEAD(&ce->signals);
+
+	/* Use the whole device by default */
+	ce->sseu = intel_device_default_sseu(ctx->i915);
 }
 
 static struct i915_gem_context *

drivers/gpu/drm/i915/i915_gem_context.h

@@ -31,6 +31,7 @@
 
 #include "i915_gem.h"
 #include "i915_scheduler.h"
+#include "intel_device_info.h"
 
 struct pid;
 
@@ -53,6 +54,16 @@ struct intel_context_ops {
 	void (*destroy)(struct intel_context *ce);
 };
 
+/*
+ * Powergating configuration for a particular (context,engine).
+ */
+struct intel_sseu {
+	u8 slice_mask;
+	u8 subslice_mask;
+	u8 min_eus_per_subslice;
+	u8 max_eus_per_subslice;
+};
+
 /**
  * struct i915_gem_context - client state
  *
@@ -173,6 +184,9 @@ struct i915_gem_context {
 		int pin_count;
 
 		const struct intel_context_ops *ops;
+
+		/** sseu: Control eu/slice partitioning */
+		struct intel_sseu sseu;
 	} __engine[I915_NUM_ENGINES];
 
 	/** ring_size: size for allocating the per-engine ring buffer */

drivers/gpu/drm/i915/intel_lrc.c

@@ -1266,7 +1266,8 @@ static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma)
 	return i915_vma_pin(vma, 0, 0, flags);
 }
 
-static u32 make_rpcs(struct drm_i915_private *dev_priv);
+static u32
+make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu);
 
 static void
 __execlists_update_reg_state(struct intel_engine_cs *engine,
@@ -1281,7 +1282,8 @@ __execlists_update_reg_state(struct intel_engine_cs *engine,
 
 	/* RPCS */
 	if (engine->class == RENDER_CLASS)
-		regs[CTX_R_PWR_CLK_STATE + 1] = make_rpcs(engine->i915);
+		regs[CTX_R_PWR_CLK_STATE + 1] = make_rpcs(engine->i915,
+							  &ce->sseu);
 }
 
 static struct intel_context *
@@ -2432,18 +2434,19 @@ int logical_xcs_ring_init(struct intel_engine_cs *engine)
 }
 
 static u32
-make_rpcs(struct drm_i915_private *dev_priv)
+make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu)
 {
-	bool subslice_pg = RUNTIME_INFO(dev_priv)->sseu.has_subslice_pg;
-	u8 slices = hweight8(RUNTIME_INFO(dev_priv)->sseu.slice_mask);
-	u8 subslices = hweight8(RUNTIME_INFO(dev_priv)->sseu.subslice_mask[0]);
+	const struct sseu_dev_info *sseu = &RUNTIME_INFO(i915)->sseu;
+	bool subslice_pg = sseu->has_subslice_pg;
+	u8 slices = hweight8(ctx_sseu->slice_mask);
+	u8 subslices = hweight8(ctx_sseu->subslice_mask);
 	u32 rpcs = 0;
 
 	/*
 	 * No explicit RPCS request is needed to ensure full
 	 * slice/subslice/EU enablement prior to Gen9.
 	*/
-	if (INTEL_GEN(dev_priv) < 9)
+	if (INTEL_GEN(i915) < 9)
 		return 0;
 
 	/*
@@ -2471,7 +2474,7 @@ make_rpcs(struct drm_i915_private *dev_priv)
 	 * subslices are enabled, or a count between one and four on the first
 	 * slice.
 	 */
-	if (IS_GEN(dev_priv, 11) && slices == 1 && subslices >= 4) {
+	if (IS_GEN(i915, 11) && slices == 1 && subslices >= 4) {
 		GEM_BUG_ON(subslices & 1);
 
 		subslice_pg = false;
@@ -2484,10 +2487,10 @@ make_rpcs(struct drm_i915_private *dev_priv)
 	 * must make an explicit request through RPCS for full
 	 * enablement.
 	*/
-	if (RUNTIME_INFO(dev_priv)->sseu.has_slice_pg) {
+	if (sseu->has_slice_pg) {
 		u32 mask, val = slices;
 
-		if (INTEL_GEN(dev_priv) >= 11) {
+		if (INTEL_GEN(i915) >= 11) {
 			mask = GEN11_RPCS_S_CNT_MASK;
 			val <<= GEN11_RPCS_S_CNT_SHIFT;
 		} else {
@@ -2512,18 +2515,16 @@ make_rpcs(struct drm_i915_private *dev_priv)
 		rpcs |= GEN8_RPCS_ENABLE | GEN8_RPCS_SS_CNT_ENABLE | val;
 	}
 
-	if (RUNTIME_INFO(dev_priv)->sseu.has_eu_pg) {
+	if (sseu->has_eu_pg) {
 		u32 val;
 
-		val = RUNTIME_INFO(dev_priv)->sseu.eu_per_subslice <<
-		      GEN8_RPCS_EU_MIN_SHIFT;
+		val = ctx_sseu->min_eus_per_subslice << GEN8_RPCS_EU_MIN_SHIFT;
 		GEM_BUG_ON(val & ~GEN8_RPCS_EU_MIN_MASK);
 		val &= GEN8_RPCS_EU_MIN_MASK;
 
 		rpcs |= val;
 
-		val = RUNTIME_INFO(dev_priv)->sseu.eu_per_subslice <<
-		      GEN8_RPCS_EU_MAX_SHIFT;
+		val = ctx_sseu->max_eus_per_subslice << GEN8_RPCS_EU_MAX_SHIFT;
 		GEM_BUG_ON(val & ~GEN8_RPCS_EU_MAX_MASK);
 		val &= GEN8_RPCS_EU_MAX_MASK;