drm/i915/execlists: Use per-process HWSP as scratch

Some of our commands (MI_FLUSH_DW / PIPE_CONTROL) require a post-sync write
operation to be performed. Currently we're using dedicated VMA for
PIPE_CONTROL and global HWSP for MI_FLUSH_DW.
On execlists platforms, each of our contexts has an area that can be
used as scratch space. Let's use that instead.

Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190926133142.2838-2-chris@chris-wilson.co.uk

3 files changed, 17 insertions, 35 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index 3039cef64b11..e64db4c13df6 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -90,9 +90,6 @@ enum intel_gt_scratch_field {
 	INTEL_GT_SCRATCH_FIELD_DEFAULT = 0,
 
 	/* 8 bytes */
-	INTEL_GT_SCRATCH_FIELD_CLEAR_SLM_WA = 128,
-
-	/* 8 bytes */
 	INTEL_GT_SCRATCH_FIELD_RENDER_FLUSH = 128,
 
 	/* 8 bytes */
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index ab725a6ca0ac..fa385218ce92 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2308,12 +2308,6 @@ 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
@@ -2342,10 +2336,10 @@ 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;
 
@@ -3052,7 +3046,7 @@ 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);
@@ -3063,10 +3057,6 @@ 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;
@@ -3088,7 +3078,7 @@ 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
@@ -3121,7 +3111,7 @@ 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);
@@ -3134,11 +3124,6 @@ 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;
@@ -3151,13 +3136,13 @@ 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);
 	}
 
@@ -3175,13 +3160,13 @@ 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);
 	}
 
@@ -3196,10 +3181,6 @@ static u32 preparser_disable(bool state)
 static int gen12_emit_flush_render(struct i915_request *request,
 				   u32 mode)
 {
-	const u32 scratch_addr =
-		intel_gt_scratch_offset(request->engine->gt,
-					INTEL_GT_SCRATCH_FIELD_RENDER_FLUSH);
-
 	if (mode & EMIT_FLUSH) {
 		u32 flags = 0;
 		u32 *cs;
@@ -3210,7 +3191,7 @@ static int gen12_emit_flush_render(struct i915_request *request,
 		flags |= PIPE_CONTROL_DC_FLUSH_ENABLE;
 		flags |= PIPE_CONTROL_FLUSH_ENABLE;
 
-		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
 		flags |= PIPE_CONTROL_QW_WRITE;
 
 		flags |= PIPE_CONTROL_CS_STALL;
@@ -3219,7 +3200,7 @@ static int gen12_emit_flush_render(struct i915_request *request,
 		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);
 	}
 
@@ -3235,7 +3216,7 @@ static int gen12_emit_flush_render(struct i915_request *request,
 		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
 
-		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
 		flags |= PIPE_CONTROL_QW_WRITE;
 
 		flags |= PIPE_CONTROL_CS_STALL;
@@ -3251,7 +3232,7 @@ static int gen12_emit_flush_render(struct i915_request *request,
 		 */
 		*cs++ = preparser_disable(true);
 
-		cs = gen8_emit_pipe_control(cs, flags, scratch_addr);
+		cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
 
 		*cs++ = preparser_disable(false);
 		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,