drm/i915: Use VMA for scratch page tracking

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1471254551-25805-19-git-send-email-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/i915_gem_context.c

@@ -660,7 +660,7 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 					MI_STORE_REGISTER_MEM |
 					MI_SRM_LRM_GLOBAL_GTT);
 			intel_ring_emit_reg(ring, last_reg);
-			intel_ring_emit(ring, engine->scratch.gtt_offset);
+			intel_ring_emit(ring, engine->scratch->node.start);
 			intel_ring_emit(ring, MI_NOOP);
 		}
 		intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -1101,7 +1101,7 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 			if (HAS_BROKEN_CS_TLB(dev_priv))
 				ee->wa_batchbuffer =
 					i915_error_ggtt_object_create(dev_priv,
-								      engine->scratch.obj);
+								      engine->scratch->obj);
 
 			if (request->ctx->engine[i].state) {
 				ee->ctx = i915_error_ggtt_object_create(dev_priv,

drivers/gpu/drm/i915/intel_display.c

@@ -11795,7 +11795,7 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 			intel_ring_emit(ring, MI_STORE_REGISTER_MEM |
 					      MI_SRM_LRM_GLOBAL_GTT);
 		intel_ring_emit_reg(ring, DERRMR);
-		intel_ring_emit(ring, req->engine->scratch.gtt_offset + 256);
+		intel_ring_emit(ring, req->engine->scratch->node.start + 256);
 		if (IS_GEN8(dev)) {
 			intel_ring_emit(ring, 0);
 			intel_ring_emit(ring, MI_NOOP);

drivers/gpu/drm/i915/intel_lrc.c

@@ -914,7 +914,7 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine,
 	wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 |
 				   MI_SRM_LRM_GLOBAL_GTT));
 	wa_ctx_emit_reg(batch, index, GEN8_L3SQCREG4);
-	wa_ctx_emit(batch, index, engine->scratch.gtt_offset + 256);
+	wa_ctx_emit(batch, index, engine->scratch->node.start + 256);
 	wa_ctx_emit(batch, index, 0);
 
 	wa_ctx_emit(batch, index, MI_LOAD_REGISTER_IMM(1));
@@ -932,7 +932,7 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine,
 	wa_ctx_emit(batch, index, (MI_LOAD_REGISTER_MEM_GEN8 |
 				   MI_SRM_LRM_GLOBAL_GTT));
 	wa_ctx_emit_reg(batch, index, GEN8_L3SQCREG4);
-	wa_ctx_emit(batch, index, engine->scratch.gtt_offset + 256);
+	wa_ctx_emit(batch, index, engine->scratch->node.start + 256);
 	wa_ctx_emit(batch, index, 0);
 
 	return index;
@@ -993,7 +993,7 @@ static int gen8_init_indirectctx_bb(struct intel_engine_cs *engine,
 
 	/* WaClearSlmSpaceAtContextSwitch:bdw,chv */
 	/* Actual scratch location is at 128 bytes offset */
-	scratch_addr = engine->scratch.gtt_offset + 2*CACHELINE_BYTES;
+	scratch_addr = engine->scratch->node.start + 2 * CACHELINE_BYTES;
 
 	wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
 	wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 |
@@ -1072,8 +1072,8 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine,
 	/* WaClearSlmSpaceAtContextSwitch:kbl */
 	/* Actual scratch location is at 128 bytes offset */
 	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)) {
-		uint32_t scratch_addr
-			= engine->scratch.gtt_offset + 2*CACHELINE_BYTES;
+		u32 scratch_addr =
+			engine->scratch->node.start + 2 * CACHELINE_BYTES;
 
 		wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
 		wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 |
@@ -1215,7 +1215,7 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine)
 	}
 
 	/* some WA perform writes to scratch page, ensure it is valid */
-	if (engine->scratch.obj == NULL) {
+	if (!engine->scratch) {
 		DRM_ERROR("scratch page not allocated for %s\n", engine->name);
 		return -EINVAL;
 	}
@@ -1483,7 +1483,7 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
 {
 	struct intel_ring *ring = request->ring;
 	struct intel_engine_cs *engine = request->engine;
-	u32 scratch_addr = engine->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+	u32 scratch_addr = engine->scratch->node.start + 2 * CACHELINE_BYTES;
 	bool vf_flush_wa = false, dc_flush_wa = false;
 	u32 flags = 0;
 	int ret;
@@ -1844,11 +1844,11 @@ int logical_render_ring_init(struct intel_engine_cs *engine)
 	else
 		engine->init_hw = gen8_init_render_ring;
 	engine->init_context = gen8_init_rcs_context;
-	engine->cleanup = intel_fini_pipe_control;
+	engine->cleanup = intel_engine_cleanup_scratch;
 	engine->emit_flush = gen8_emit_flush_render;
 	engine->emit_request = gen8_emit_request_render;
 
-	ret = intel_init_pipe_control(engine, 4096);
+	ret = intel_engine_create_scratch(engine, 4096);
 	if (ret)
 		return ret;
 

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -176,7 +176,7 @@ intel_emit_post_sync_nonzero_flush(struct drm_i915_gem_request *req)
 {
 	struct intel_ring *ring = req->ring;
 	u32 scratch_addr =
-		req->engine->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+		req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
 	int ret;
 
 	ret = intel_ring_begin(req, 6);
@@ -212,7 +212,7 @@ gen6_render_ring_flush(struct drm_i915_gem_request *req, u32 mode)
 {
 	struct intel_ring *ring = req->ring;
 	u32 scratch_addr =
-		req->engine->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+		req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
 	u32 flags = 0;
 	int ret;
 
@@ -286,7 +286,7 @@ gen7_render_ring_flush(struct drm_i915_gem_request *req, u32 mode)
 {
 	struct intel_ring *ring = req->ring;
 	u32 scratch_addr =
-		req->engine->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+		req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
 	u32 flags = 0;
 	int ret;
 
@@ -370,7 +370,8 @@ gen8_emit_pipe_control(struct drm_i915_gem_request *req,
 static int
 gen8_render_ring_flush(struct drm_i915_gem_request *req, u32 mode)
 {
-	u32 scratch_addr = req->engine->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+	u32 scratch_addr =
+		req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
 	u32 flags = 0;
 	int ret;
 
@@ -612,45 +613,51 @@ out:
 	return ret;
 }
 
-void intel_fini_pipe_control(struct intel_engine_cs *engine)
+void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
 {
-	if (engine->scratch.obj == NULL)
+	struct i915_vma *vma;
+
+	vma = fetch_and_zero(&engine->scratch);
+	if (!vma)
 		return;
 
-	i915_gem_object_ggtt_unpin(engine->scratch.obj);
-	i915_gem_object_put(engine->scratch.obj);
-	engine->scratch.obj = NULL;
+	i915_vma_unpin(vma);
+	i915_vma_put(vma);
 }
 
-int intel_init_pipe_control(struct intel_engine_cs *engine, int size)
+int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
 {
 	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
 	int ret;
 
-	WARN_ON(engine->scratch.obj);
+	WARN_ON(engine->scratch);
 
 	obj = i915_gem_object_create_stolen(&engine->i915->drm, size);
 	if (!obj)
 		obj = i915_gem_object_create(&engine->i915->drm, size);
 	if (IS_ERR(obj)) {
 		DRM_ERROR("Failed to allocate scratch page\n");
-		ret = PTR_ERR(obj);
-		goto err;
+		return PTR_ERR(obj);
 	}
 
-	ret = i915_gem_object_ggtt_pin(obj, NULL, 0, 4096, PIN_HIGH);
+	vma = i915_vma_create(obj, &engine->i915->ggtt.base, NULL);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto err_unref;
+	}
+
+	ret = i915_vma_pin(vma, 0, 4096, PIN_GLOBAL | PIN_HIGH);
 	if (ret)
 		goto err_unref;
 
-	engine->scratch.obj = obj;
-	engine->scratch.gtt_offset = i915_gem_obj_ggtt_offset(obj);
-	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08x\n",
-			 engine->name, engine->scratch.gtt_offset);
+	engine->scratch = vma;
+	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08llx\n",
+			 engine->name, vma->node.start);
 	return 0;
 
 err_unref:
-	i915_gem_object_put(engine->scratch.obj);
-err:
+	i915_gem_object_put(obj);
 	return ret;
 }
 
@@ -1305,7 +1312,7 @@ static void render_ring_cleanup(struct intel_engine_cs *engine)
 		dev_priv->semaphore_obj = NULL;
 	}
 
-	intel_fini_pipe_control(engine);
+	intel_engine_cleanup_scratch(engine);
 }
 
 static int gen8_rcs_signal(struct drm_i915_gem_request *req)
@@ -1763,7 +1770,7 @@ i830_emit_bb_start(struct drm_i915_gem_request *req,
 		   unsigned int dispatch_flags)
 {
 	struct intel_ring *ring = req->ring;
-	u32 cs_offset = req->engine->scratch.gtt_offset;
+	u32 cs_offset = req->engine->scratch->node.start;
 	int ret;
 
 	ret = intel_ring_begin(req, 6);
@@ -2793,11 +2800,11 @@ int intel_init_render_ring_buffer(struct intel_engine_cs *engine)
 		return ret;
 
 	if (INTEL_GEN(dev_priv) >= 6) {
-		ret = intel_init_pipe_control(engine, 4096);
+		ret = intel_engine_create_scratch(engine, 4096);
 		if (ret)
 			return ret;
 	} else if (HAS_BROKEN_CS_TLB(dev_priv)) {
-		ret = intel_init_pipe_control(engine, I830_WA_SIZE);
+		ret = intel_engine_create_scratch(engine, I830_WA_SIZE);
 		if (ret)
 			return ret;
 	}

drivers/gpu/drm/i915/intel_ringbuffer.h

@@ -198,6 +198,7 @@ struct intel_engine_cs {
 
 	struct intel_hw_status_page status_page;
 	struct i915_ctx_workarounds wa_ctx;
+	struct i915_vma *scratch;
 
 	u32             irq_keep_mask; /* always keep these interrupts */
 	u32		irq_enable_mask; /* bitmask to enable ring interrupt */
@@ -320,11 +321,6 @@ struct intel_engine_cs {
 
 	struct intel_engine_hangcheck hangcheck;
 
-	struct {
-		struct drm_i915_gem_object *obj;
-		u32 gtt_offset;
-	} scratch;
-
 	bool needs_cmd_parser;
 
 	/*
@@ -476,8 +472,8 @@ void intel_ring_update_space(struct intel_ring *ring);
 
 void intel_engine_init_seqno(struct intel_engine_cs *engine, u32 seqno);
 
-int intel_init_pipe_control(struct intel_engine_cs *engine, int size);
-void intel_fini_pipe_control(struct intel_engine_cs *engine);
+int intel_engine_create_scratch(struct intel_engine_cs *engine, int size);
+void intel_engine_cleanup_scratch(struct intel_engine_cs *engine);
 
 void intel_engine_setup_common(struct intel_engine_cs *engine);
 int intel_engine_init_common(struct intel_engine_cs *engine);