Merge tag 'drm-intel-fixes-2018-12-12-1' of git://anongit.freedesktop…

….org/drm/drm-intel into drm-fixes

- Two fixes to avoid GPU hangs (on Braswell and Gen3)

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181212134010.GA18900@jlahtine-desk.ger.corp.intel.com

drivers/gpu/drm/i915/i915_drv.h

@@ -2150,6 +2150,8 @@ struct drm_i915_private {
 		struct delayed_work idle_work;
 
 		ktime_t last_init_time;
+
+		struct i915_vma *scratch;
 	} gt;
 
 	/* perform PHY state sanity checks? */
@@ -3872,4 +3874,9 @@ static inline int intel_hws_csb_write_index(struct drm_i915_private *i915)
 		return I915_HWS_CSB_WRITE_INDEX;
 }
 
+static inline u32 i915_scratch_offset(const struct drm_i915_private *i915)
+{
+	return i915_ggtt_offset(i915->gt.scratch);
+}
+
 #endif

drivers/gpu/drm/i915/i915_gem.c

@@ -5500,6 +5500,44 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 	goto out_ctx;
 }
 
+static int
+i915_gem_init_scratch(struct drm_i915_private *i915, unsigned int size)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	int ret;
+
+	obj = i915_gem_object_create_stolen(i915, size);
+	if (!obj)
+		obj = i915_gem_object_create_internal(i915, size);
+	if (IS_ERR(obj)) {
+		DRM_ERROR("Failed to allocate scratch page\n");
+		return PTR_ERR(obj);
+	}
+
+	vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto err_unref;
+	}
+
+	ret = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
+	if (ret)
+		goto err_unref;
+
+	i915->gt.scratch = vma;
+	return 0;
+
+err_unref:
+	i915_gem_object_put(obj);
+	return ret;
+}
+
+static void i915_gem_fini_scratch(struct drm_i915_private *i915)
+{
+	i915_vma_unpin_and_release(&i915->gt.scratch, 0);
+}
+
 int i915_gem_init(struct drm_i915_private *dev_priv)
 {
 	int ret;
@@ -5546,12 +5584,19 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 		goto err_unlock;
 	}
 
-	ret = i915_gem_contexts_init(dev_priv);
+	ret = i915_gem_init_scratch(dev_priv,
+				    IS_GEN2(dev_priv) ? SZ_256K : PAGE_SIZE);
 	if (ret) {
 		GEM_BUG_ON(ret == -EIO);
 		goto err_ggtt;
 	}
 
+	ret = i915_gem_contexts_init(dev_priv);
+	if (ret) {
+		GEM_BUG_ON(ret == -EIO);
+		goto err_scratch;
+	}
+
 	ret = intel_engines_init(dev_priv);
 	if (ret) {
 		GEM_BUG_ON(ret == -EIO);
@@ -5624,6 +5669,8 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 err_context:
 	if (ret != -EIO)
 		i915_gem_contexts_fini(dev_priv);
+err_scratch:
+	i915_gem_fini_scratch(dev_priv);
 err_ggtt:
 err_unlock:
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
@@ -5675,6 +5722,7 @@ void i915_gem_fini(struct drm_i915_private *dev_priv)
 	intel_uc_fini(dev_priv);
 	i915_gem_cleanup_engines(dev_priv);
 	i915_gem_contexts_fini(dev_priv);
+	i915_gem_fini_scratch(dev_priv);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	intel_wa_list_free(&dev_priv->gt_wa_list);

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -1268,7 +1268,7 @@ relocate_entry(struct i915_vma *vma,
 		else if (gen >= 4)
 			len = 4;
 		else
-			len = 6;
+			len = 3;
 
 		batch = reloc_gpu(eb, vma, len);
 		if (IS_ERR(batch))
@@ -1309,11 +1309,6 @@ relocate_entry(struct i915_vma *vma,
 			*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
 			*batch++ = addr;
 			*batch++ = target_offset;
-
-			/* And again for good measure (blb/pnv) */
-			*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
-			*batch++ = addr;
-			*batch++ = target_offset;
 		}
 
 		goto out;

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -1495,7 +1495,7 @@ static void gem_record_rings(struct i915_gpu_state *error)
 			if (HAS_BROKEN_CS_TLB(i915))
 				ee->wa_batchbuffer =
 					i915_error_object_create(i915,
-								 engine->scratch);
+								 i915->gt.scratch);
 			request_record_user_bo(request, ee);
 
 			ee->ctx =

drivers/gpu/drm/i915/intel_engine_cs.c

@@ -490,46 +490,6 @@ void intel_engine_setup_common(struct intel_engine_cs *engine)
 	intel_engine_init_cmd_parser(engine);
 }
 
-int intel_engine_create_scratch(struct intel_engine_cs *engine,
-				unsigned int size)
-{
-	struct drm_i915_gem_object *obj;
-	struct i915_vma *vma;
-	int ret;
-
-	WARN_ON(engine->scratch);
-
-	obj = i915_gem_object_create_stolen(engine->i915, size);
-	if (!obj)
-		obj = i915_gem_object_create_internal(engine->i915, size);
-	if (IS_ERR(obj)) {
-		DRM_ERROR("Failed to allocate scratch page\n");
-		return PTR_ERR(obj);
-	}
-
-	vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL);
-	if (IS_ERR(vma)) {
-		ret = PTR_ERR(vma);
-		goto err_unref;
-	}
-
-	ret = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
-	if (ret)
-		goto err_unref;
-
-	engine->scratch = vma;
-	return 0;
-
-err_unref:
-	i915_gem_object_put(obj);
-	return ret;
-}
-
-void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
-{
-	i915_vma_unpin_and_release(&engine->scratch, 0);
-}
-
 static void cleanup_status_page(struct intel_engine_cs *engine)
 {
 	if (HWS_NEEDS_PHYSICAL(engine->i915)) {
@@ -704,8 +664,6 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *i915 = engine->i915;
 
-	intel_engine_cleanup_scratch(engine);
-
 	cleanup_status_page(engine);
 
 	intel_engine_fini_breadcrumbs(engine);

drivers/gpu/drm/i915/intel_lrc.c

@@ -442,8 +442,13 @@ static u64 execlists_update_context(struct i915_request *rq)
 	 * may not be visible to the HW prior to the completion of the UC
 	 * register write and that we may begin execution from the context
 	 * before its image is complete leading to invalid PD chasing.
+	 *
+	 * Furthermore, Braswell, at least, wants a full mb to be sure that
+	 * the writes are coherent in memory (visible to the GPU) prior to
+	 * execution, and not just visible to other CPUs (as is the result of
+	 * wmb).
 	 */
-	wmb();
+	mb();
 	return ce->lrc_desc;
 }
 
@@ -1443,9 +1448,10 @@ static int execlists_request_alloc(struct i915_request *request)
 static u32 *
 gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch)
 {
+	/* NB no one else is allowed to scribble over scratch + 256! */
 	*batch++ = MI_STORE_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT;
 	*batch++ = i915_mmio_reg_offset(GEN8_L3SQCREG4);
-	*batch++ = i915_ggtt_offset(engine->scratch) + 256;
+	*batch++ = i915_scratch_offset(engine->i915) + 256;
 	*batch++ = 0;
 
 	*batch++ = MI_LOAD_REGISTER_IMM(1);
@@ -1459,7 +1465,7 @@ gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch)
 
 	*batch++ = MI_LOAD_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT;
 	*batch++ = i915_mmio_reg_offset(GEN8_L3SQCREG4);
-	*batch++ = i915_ggtt_offset(engine->scratch) + 256;
+	*batch++ = i915_scratch_offset(engine->i915) + 256;
 	*batch++ = 0;
 
 	return batch;
@@ -1496,7 +1502,7 @@ static u32 *gen8_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
 				       PIPE_CONTROL_GLOBAL_GTT_IVB |
 				       PIPE_CONTROL_CS_STALL |
 				       PIPE_CONTROL_QW_WRITE,
-				       i915_ggtt_offset(engine->scratch) +
+				       i915_scratch_offset(engine->i915) +
 				       2 * CACHELINE_BYTES);
 
 	*batch++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;
@@ -1573,7 +1579,7 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
 					       PIPE_CONTROL_GLOBAL_GTT_IVB |
 					       PIPE_CONTROL_CS_STALL |
 					       PIPE_CONTROL_QW_WRITE,
-					       i915_ggtt_offset(engine->scratch)
+					       i915_scratch_offset(engine->i915)
 					       + 2 * CACHELINE_BYTES);
 	}
 
@@ -2141,7 +2147,7 @@ static int gen8_emit_flush_render(struct i915_request *request,
 {
 	struct intel_engine_cs *engine = request->engine;
 	u32 scratch_addr =
-		i915_ggtt_offset(engine->scratch) + 2 * CACHELINE_BYTES;
+		i915_scratch_offset(engine->i915) + 2 * CACHELINE_BYTES;
 	bool vf_flush_wa = false, dc_flush_wa = false;
 	u32 *cs, flags = 0;
 	int len;
@@ -2478,10 +2484,6 @@ int logical_render_ring_init(struct intel_engine_cs *engine)
 	if (ret)
 		return ret;
 
-	ret = intel_engine_create_scratch(engine, PAGE_SIZE);
-	if (ret)
-		goto err_cleanup_common;
-
 	ret = intel_init_workaround_bb(engine);
 	if (ret) {
 		/*
@@ -2496,10 +2498,6 @@ int logical_render_ring_init(struct intel_engine_cs *engine)
 	intel_engine_init_workarounds(engine);
 
 	return 0;
-
-err_cleanup_common:
-	intel_engine_cleanup_common(engine);
-	return ret;
 }
 
 int logical_xcs_ring_init(struct intel_engine_cs *engine)