[PATCH 1/5] use-pphwsp-for-flush

[Michał Winiarski]

---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 33 ++++++++---------------------
 drivers/gpu/drm/i915/gt/intel_lrc.h |  4 ++++
 2 files changed, 13 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index a3f0e4999744..c87a4f9740e9 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1927,12 +1927,6 @@ gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch)
 	return batch;
 }
 
-static u32 slm_offset(struct intel_engine_cs *engine)
-{
-	return intel_gt_scratch_offset(engine->gt,
-				       INTEL_GT_SCRATCH_FIELD_CLEAR_SLM_WA);
-}
-
 /*
  * Typically we only have one indirect_ctx and per_ctx batch buffer which are
  * initialized at the beginning and shared across all contexts but this field
@@ -1961,10 +1955,10 @@ static u32 *gen8_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
 	/* Actual scratch location is at 128 bytes offset */
 	batch = gen8_emit_pipe_control(batch,
 				       PIPE_CONTROL_FLUSH_L3 |
-				       PIPE_CONTROL_GLOBAL_GTT_IVB |
+				       PIPE_CONTROL_STORE_DATA_INDEX |
 				       PIPE_CONTROL_CS_STALL |
 				       PIPE_CONTROL_QW_WRITE,
-				       slm_offset(engine));
+				       LRC_PPHWSP_SCRATCH_ADDR);
 
 	*batch++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;
 
@@ -2671,7 +2665,7 @@ static int gen8_emit_flush(struct i915_request *request, u32 mode)
 	}
 
 	*cs++ = cmd;
-	*cs++ = I915_GEM_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT;
+	*cs++ = LRC_PPHWSP_SCRATCH_ADDR;
 	*cs++ = 0; /* upper addr */
 	*cs++ = 0; /* value */
 	intel_ring_advance(request, cs);
@@ -2682,10 +2676,6 @@ static int gen8_emit_flush(struct i915_request *request, u32 mode)
 static int gen8_emit_flush_render(struct i915_request *request,
 				  u32 mode)
 {
-	struct intel_engine_cs *engine = request->engine;
-	u32 scratch_addr =
-		intel_gt_scratch_offset(engine->gt,
-					INTEL_GT_SCRATCH_FIELD_RENDER_FLUSH);
 	bool vf_flush_wa = false, dc_flush_wa = false;
 	u32 *cs, flags = 0;
 	int len;
@@ -2707,7 +2697,7 @@ static int gen8_emit_flush_render(struct i915_request *request,
 		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_QW_WRITE;
-		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
 
 		/*
 		 * On GEN9: before VF_CACHE_INVALIDATE we need to emit a NULL
@@ -2740,7 +2730,7 @@ static int gen8_emit_flush_render(struct i915_request *request,
 		cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_DC_FLUSH_ENABLE,
 					    0);
 
-	cs = gen8_emit_pipe_control(cs, flags, scratch_addr);
+	cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
 
 	if (dc_flush_wa)
 		cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_CS_STALL, 0);
@@ -2753,11 +2743,6 @@ static int gen8_emit_flush_render(struct i915_request *request,
 static int gen11_emit_flush_render(struct i915_request *request,
 				   u32 mode)
 {
-	struct intel_engine_cs *engine = request->engine;
-	const u32 scratch_addr =
-		intel_gt_scratch_offset(engine->gt,
-					INTEL_GT_SCRATCH_FIELD_RENDER_FLUSH);
-
 	if (mode & EMIT_FLUSH) {
 		u32 *cs;
 		u32 flags = 0;
@@ -2770,13 +2755,13 @@ static int gen11_emit_flush_render(struct i915_request *request,
 		flags |= PIPE_CONTROL_DC_FLUSH_ENABLE;
 		flags |= PIPE_CONTROL_FLUSH_ENABLE;
 		flags |= PIPE_CONTROL_QW_WRITE;
-		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
 
 		cs = intel_ring_begin(request, 6);
 		if (IS_ERR(cs))
 			return PTR_ERR(cs);
 
-		cs = gen8_emit_pipe_control(cs, flags, scratch_addr);
+		cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
 		intel_ring_advance(request, cs);
 	}
 
@@ -2794,13 +2779,13 @@ static int gen11_emit_flush_render(struct i915_request *request,
 		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_QW_WRITE;
-		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
 
 		cs = intel_ring_begin(request, 6);
 		if (IS_ERR(cs))
 			return PTR_ERR(cs);
 
-		cs = gen8_emit_pipe_control(cs, flags, scratch_addr);
+		cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
 		intel_ring_advance(request, cs);
 	}
 
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index dc0252e0589e..66ac616361c1 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -104,6 +104,10 @@ int intel_execlists_submission_init(struct intel_engine_cs *engine);
  */
 #define LRC_HEADER_PAGES LRC_PPHWSP_PN
 
+/* Space within PPHWSP reserved to be used as scratch */
+#define LRC_PPHWSP_SCRATCH		0x34
+#define LRC_PPHWSP_SCRATCH_ADDR		(LRC_PPHWSP_SCRATCH * sizeof(u32))
+
 void intel_execlists_set_default_submission(struct intel_engine_cs *engine);
 
 void intel_lr_context_reset(struct intel_engine_cs *engine,
-- 
2.21.0