[Intel-gfx] [PATCH v7 2/7] 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)

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)

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 |  2 ++
 drivers/gpu/drm/i915/i915_gem_context.h | 17 +++++++++++++++++
 drivers/gpu/drm/i915/i915_request.h     | 10 ++++++++++
 drivers/gpu/drm/i915/intel_lrc.c        | 22 +++++++++++-----------
 4 files changed, 40 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index b69b18ef8120..c5ad468dae56 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -282,6 +282,8 @@ __create_hw_context(struct drm_i915_private *dev_priv,
 		struct intel_context *ce = &ctx->__engine[n];
 
 		ce->gem_context = ctx;
+		/* Use the whole device by default */
+		ce->sseu = intel_sseu_from_device_sseu(&INTEL_INFO(dev_priv)->sseu);
 	}
 
 	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index c3262b4dd2ee..3389b5249342 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;
 
@@ -157,6 +158,9 @@ 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 */
@@ -335,4 +339,17 @@ static inline void i915_gem_context_put(struct i915_gem_context *ctx)
 	kref_put(&ctx->ref, i915_gem_context_release);
 }
 
+static inline struct intel_sseu
+intel_sseu_from_device_sseu(const struct sseu_dev_info *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;
+}
+
 #endif /* !__I915_GEM_CONTEXT_H__ */
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 1bbbb7a9fa03..82c5dd153bfd 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -39,6 +39,16 @@ struct drm_i915_gem_object;
 struct i915_request;
 struct i915_timeline;
 
+/*
+ * 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 intel_wait {
 	struct rb_node node;
 	struct task_struct *tsk;
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index c2500c209c63..a8e139f7c337 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -2481,8 +2481,8 @@ 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,
+		     struct intel_sseu ctx_sseu)
 {
 	u32 rpcs = 0;
 
@@ -2492,24 +2492,23 @@ 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]) <<
+		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;
 	}
@@ -2633,7 +2632,8 @@ 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,
+				  to_intel_context(ctx, engine)->sseu));
 
 		i915_oa_init_reg_state(engine, ctx, regs);
 	}
-- 
2.17.0