drm/i915/ringbuffer: Serialize load of PD_DIR

After triggering the mm switch with a load of PD_DIR, which may be
deferred unto the MI_SET_CONTEXT on rcs, serialise the next commands
with that load by posting a read of PD_DIR (or else those subsequent
commands may access the stale page tables).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611171825.13678-2-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/intel_engine_cs.c

@@ -499,7 +499,8 @@ 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, int size)
+int intel_engine_create_scratch(struct intel_engine_cs *engine,
+				unsigned int size)
 {
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
@@ -533,7 +534,7 @@ err_unref:
 	return ret;
 }
 
-static void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
+void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
 {
 	i915_vma_unpin_and_release(&engine->scratch);
 }

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -1361,8 +1361,9 @@ intel_ring_context_pin(struct intel_engine_cs *engine,
 
 static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 {
-	struct intel_ring *ring;
 	struct i915_timeline *timeline;
+	struct intel_ring *ring;
+	unsigned int size;
 	int err;
 
 	intel_engine_setup_common(engine);
@@ -1388,12 +1389,21 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 	GEM_BUG_ON(engine->buffer);
 	engine->buffer = ring;
 
-	err = intel_engine_init_common(engine);
+	size = PAGE_SIZE;
+	if (HAS_BROKEN_CS_TLB(engine->i915))
+		size = I830_WA_SIZE;
+	err = intel_engine_create_scratch(engine, size);
 	if (err)
 		goto err_unpin;
 
+	err = intel_engine_init_common(engine);
+	if (err)
+		goto err_scratch;
+
 	return 0;
 
+err_scratch:
+	intel_engine_cleanup_scratch(engine);
 err_unpin:
 	intel_ring_unpin(ring);
 err_ring:
@@ -1455,6 +1465,25 @@ static int load_pd_dir(struct i915_request *rq,
 	return 0;
 }
 
+static int flush_pd_dir(struct i915_request *rq)
+{
+	const struct intel_engine_cs * const engine = rq->engine;
+	u32 *cs;
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	/* Stall until the page table load is complete */
+	*cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
+	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine));
+	*cs++ = i915_ggtt_offset(engine->scratch);
+	*cs++ = MI_NOOP;
+
+	intel_ring_advance(rq, cs);
+	return 0;
+}
+
 static inline int mi_set_context(struct i915_request *rq, u32 flags)
 {
 	struct drm_i915_private *i915 = rq->i915;
@@ -1638,6 +1667,12 @@ static int switch_context(struct i915_request *rq)
 			goto err_mm;
 	}
 
+	if (ppgtt) {
+		ret = flush_pd_dir(rq);
+		if (ret)
+			goto err_mm;
+	}
+
 	if (ctx->remap_slice) {
 		for (i = 0; i < MAX_L3_SLICES; i++) {
 			if (!(ctx->remap_slice & BIT(i)))
@@ -2158,16 +2193,6 @@ int intel_init_render_ring_buffer(struct intel_engine_cs *engine)
 	if (ret)
 		return ret;
 
-	if (INTEL_GEN(dev_priv) >= 6) {
-		ret = intel_engine_create_scratch(engine, PAGE_SIZE);
-		if (ret)
-			return ret;
-	} else if (HAS_BROKEN_CS_TLB(dev_priv)) {
-		ret = intel_engine_create_scratch(engine, I830_WA_SIZE);
-		if (ret)
-			return ret;
-	}
-
 	return 0;
 }
 

drivers/gpu/drm/i915/intel_ringbuffer.h

@@ -869,9 +869,12 @@ void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno);
 
 void intel_engine_setup_common(struct intel_engine_cs *engine);
 int intel_engine_init_common(struct intel_engine_cs *engine);
-int intel_engine_create_scratch(struct intel_engine_cs *engine, int size);
 void intel_engine_cleanup_common(struct intel_engine_cs *engine);
 
+int intel_engine_create_scratch(struct intel_engine_cs *engine,
+				unsigned int size);
+void intel_engine_cleanup_scratch(struct intel_engine_cs *engine);
+
 int intel_init_render_ring_buffer(struct intel_engine_cs *engine);
 int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine);
 int intel_init_blt_ring_buffer(struct intel_engine_cs *engine);