[Intel-gfx] [PATCH v2 2/4] drm/i915: Update render power clock state configuration for given context

[Ankit Navik]

From: Praveen Diwakar <praveen.diwakar at intel.com>

This patch will update power clock state register at runtime base on the
flag which can set by any governor which computes load and want to update
rpcs register.
subsequent patches will have a timer based governor which computes pending
load/request.

Signed-off-by: Praveen Diwakar <praveen.diwakar at intel.com>
Signed-off-by: Yogesh Marathe <yogesh.marathe at intel.com>
Signed-off-by: Aravindan Muthukumar <aravindan.muthukumar at intel.com>
Signed-off-by: Kedar J Karanje <kedar.j.karanje at intel.com>
Signed-off-by: Ankit Navik <ankit.p.navik at intel.com>
Suggested-by: Tvrtko Ursulin <tvrtko.ursulin at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem_context.c |  4 ++++
 drivers/gpu/drm/i915/i915_gem_context.h |  9 +++++++++
 drivers/gpu/drm/i915/intel_lrc.c        | 12 +++++++++++-
 3 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 0bcbe32..d040858 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -388,6 +388,10 @@ i915_gem_create_context(struct drm_i915_private *dev_priv,
 
 	trace_i915_context_create(ctx);
 	atomic_set(&ctx->req_cnt, 0);
+	ctx->slice_cnt = hweight8(INTEL_INFO(dev_priv)->sseu.slice_mask);
+	ctx->subslice_cnt = hweight8(
+			INTEL_INFO(dev_priv)->sseu.subslice_mask[0]);
+	ctx->eu_cnt = INTEL_INFO(dev_priv)->sseu.eu_per_subslice;
 
 	return ctx;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index 04e3ff7..2b3bf09 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -200,6 +200,15 @@ struct i915_gem_context {
 	 * controlled via a mutex
 	 */
 	atomic_t req_cnt;
+
+	/** slice_cnt: used to set the # of slices to be enabled. */
+	u8 slice_cnt;
+
+	/** subslice_cnt: used to set the # of subslices to be enabled. */
+	u8 subslice_cnt;
+
+	/** eu_cnt: used to set the # of eu to be enabled. */
+	u8 eu_cnt;
 };
 
 static inline bool i915_gem_context_is_closed(const struct i915_gem_context *ctx)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index bcbb66b..a8ab71a 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -171,6 +171,7 @@ static void execlists_init_reg_state(u32 *reg_state,
 				     struct i915_gem_context *ctx,
 				     struct intel_engine_cs *engine,
 				     struct intel_ring *ring);
+static u32 make_rpcs(struct drm_i915_private *dev_priv);
 
 static inline struct i915_priolist *to_priolist(struct rb_node *rb)
 {
@@ -417,12 +418,21 @@ execlists_update_context_pdps(struct i915_hw_ppgtt *ppgtt, u32 *reg_state)
 
 static u64 execlists_update_context(struct i915_request *rq)
 {
+	u32 rpcs_config = 0;
 	struct intel_context *ce = rq->hw_context;
+	u32 *reg_state = ce->lrc_reg_state;
+	struct i915_gem_context *ctx = rq->gem_context;
 	struct i915_hw_ppgtt *ppgtt =
 		rq->gem_context->ppgtt ?: rq->i915->mm.aliasing_ppgtt;
-	u32 *reg_state = ce->lrc_reg_state;
 
 	reg_state[CTX_RING_TAIL+1] = intel_ring_set_tail(rq->ring, rq->tail);
+	/* FIXME: To avoid stale rpcs config, move it to context_pin */
+	if (ctx->pid && ctx->name && (rq->engine->id == RCS)) {
+		rpcs_config = make_rpcs(ctx->i915);
+		reg_state[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
+		CTX_REG(reg_state, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE,
+				rpcs_config);
+	}
 
 	/* True 32b PPGTT with dynamic page allocation: update PDP
 	 * registers and point the unallocated PDPs to scratch page.
-- 
2.7.4