[Intel-gfx] [PATCH 7/8] drm/i915: Record the sseu configuration per-context & engine

[Lionel Landwerlin]

From: Chris Wilson <chris at chris-wilson.co.uk>

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)

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
---
 drivers/gpu/drm/i915/i915_gem_context.c | 22 ++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_gem_context.h | 10 ++++++++++
 drivers/gpu/drm/i915/intel_lrc.c        | 24 ++++++++++++------------
 3 files changed, 44 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 74435affe23f..bdf050beeb94 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -261,11 +261,26 @@ static u32 default_desc_template(const struct drm_i915_private *i915,
 	return desc;
 }
 
+static struct i915_gem_context_sseu
+i915_gem_context_sseu_from_device_sseu(const struct sseu_dev_info *sseu)
+{
+	struct i915_gem_context_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;
+}
+
 static struct i915_gem_context *
 __create_hw_context(struct drm_i915_private *dev_priv,
 		    struct drm_i915_file_private *file_priv)
 {
 	struct i915_gem_context *ctx;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int ret;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -314,6 +329,13 @@ __create_hw_context(struct drm_i915_private *dev_priv,
 	 * is no remap info, it will be a NOP. */
 	ctx->remap_slice = ALL_L3_SLICES(dev_priv);
 
+	/* On all engines, use the whole device by default */
+	for_each_engine(engine, dev_priv, id) {
+		ctx->engine[id].sseu =
+			i915_gem_context_sseu_from_device_sseu(
+				&INTEL_INFO(dev_priv)->sseu);
+	}
+
 	i915_gem_context_set_bannable(ctx);
 	ctx->ring_size = 4 * PAGE_SIZE;
 	ctx->desc_template =
diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index b12a8a8c5af9..2294be644574 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -30,6 +30,7 @@
 #include <linux/radix-tree.h>
 
 #include "i915_gem.h"
+#include "intel_device_info.h"
 
 struct pid;
 
@@ -45,6 +46,13 @@ struct intel_ring;
 
 #define DEFAULT_CONTEXT_HANDLE 0
 
+struct i915_gem_context_sseu {
+	u8 slice_mask;
+	u8 subslice_mask;
+	u8 min_eus_per_subslice;
+	u8 max_eus_per_subslice;
+};
+
 /**
  * struct i915_gem_context - client state
  *
@@ -149,6 +157,8 @@ struct i915_gem_context {
 		u32 *lrc_reg_state;
 		u64 lrc_desc;
 		int pin_count;
+		/** sseu: Control eu/slice partitioning */
+		struct i915_gem_context_sseu sseu;
 	} engine[I915_NUM_ENGINES];
 
 	/** ring_size: size for allocating the per-engine ring buffer */
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index a0f72fcda0d9..dca17ef24de5 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -2387,8 +2387,8 @@ int logical_xcs_ring_init(struct intel_engine_cs *engine)
 	return logical_ring_init(engine);
 }
 
-static u32
-make_rpcs(struct drm_i915_private *dev_priv)
+static u32 make_rpcs(const struct sseu_dev_info *sseu,
+		     const struct i915_gem_context_sseu *ctx_sseu)
 {
 	u32 rpcs = 0;
 
@@ -2398,24 +2398,23 @@ make_rpcs(struct drm_i915_private *dev_priv)
 	 * must make an explicit request through RPCS for full
 	 * enablement.
 	*/
-	if (INTEL_INFO(dev_priv)->sseu.has_slice_pg) {
+	if (sseu->has_slice_pg) {
 		rpcs |= GEN8_RPCS_S_CNT_ENABLE;
-		rpcs |= hweight8(INTEL_INFO(dev_priv)->sseu.slice_mask) <<
-			GEN8_RPCS_S_CNT_SHIFT;
+		rpcs |= hweight8(ctx_sseu->slice_mask) << GEN8_RPCS_S_CNT_SHIFT;
 		rpcs |= GEN8_RPCS_ENABLE;
 	}
 
-	if (INTEL_INFO(dev_priv)->sseu.has_subslice_pg) {
+	if (sseu->has_subslice_pg) {
 		rpcs |= GEN8_RPCS_SS_CNT_ENABLE;
-		rpcs |= hweight8(INTEL_INFO(dev_priv)->sseu.subslice_mask[0]) <<
-			GEN8_RPCS_SS_CNT_SHIFT;
+		rpcs |= hweight8(ctx_sseu->subslice_mask) <<
+		        GEN8_RPCS_SS_CNT_SHIFT;
 		rpcs |= GEN8_RPCS_ENABLE;
 	}
 
-	if (INTEL_INFO(dev_priv)->sseu.has_eu_pg) {
-		rpcs |= INTEL_INFO(dev_priv)->sseu.eu_per_subslice <<
+	if (sseu->has_eu_pg) {
+		rpcs |= ctx_sseu->min_eus_per_subslice <<
 			GEN8_RPCS_EU_MIN_SHIFT;
-		rpcs |= INTEL_INFO(dev_priv)->sseu.eu_per_subslice <<
+		rpcs |= ctx_sseu->max_eus_per_subslice <<
 			GEN8_RPCS_EU_MAX_SHIFT;
 		rpcs |= GEN8_RPCS_ENABLE;
 	}
@@ -2548,7 +2547,8 @@ static void execlists_init_reg_state(u32 *regs,
 	if (rcs) {
 		regs[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
 		CTX_REG(regs, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE,
-			make_rpcs(dev_priv));
+			make_rpcs(&INTEL_INFO(dev_priv)->sseu,
+				  &ctx->engine[engine->id].sseu));
 
 		i915_oa_init_reg_state(engine, ctx, regs);
 	}
-- 
2.17.0