3 files changed, 53 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
index b6492fe3722b..5026a6267a88 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.c
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -73,6 +73,24 @@ free_gem:
 	return ret;
 }
 
+/*
+ * Macro to add commands to auxiliary batch.
+ * This macro only checks for page overflow before inserting the commands,
+ * this is sufficient as the null state generator makes the final batch
+ * with two passes to build command and state separately. At this point
+ * the size of both are known and it compacts them by relocating the state
+ * right after the commands taking care of aligment so we should sufficient
+ * space below them for adding new commands.
+ */
+#define OUT_BATCH(batch, i, val)				\
+	do {							\
+		if (WARN_ON((i) >= PAGE_SIZE / sizeof(u32))) {	\
+			ret = -ENOSPC;				\
+			goto err_out;				\
+		}						\
+		(batch)[(i)++] = (val);				\
+	} while(0)
+
 static int render_state_setup(struct render_state *so)
 {
 	const struct intel_renderstate_rodata *rodata = so->rodata;
@@ -110,6 +128,21 @@ static int render_state_setup(struct render_state *so)
 
 		d[i++] = s;
 	}
+
+	while (i % CACHELINE_DWORDS)
+		OUT_BATCH(d, i, MI_NOOP);
+
+	so->aux_batch_offset = i * sizeof(u32);
+
+	OUT_BATCH(d, i, MI_BATCH_BUFFER_END);
+	so->aux_batch_size = (i * sizeof(u32)) - so->aux_batch_offset;
+
+	/*
+	 * Since we are sending length, we need to strictly conform to
+	 * all requirements. For Gen2 this must be a multiple of 8.
+	 */
+	so->aux_batch_size = ALIGN(so->aux_batch_size, 8);
+
 	kunmap(page);
 
 	ret = i915_gem_object_set_to_gtt_domain(so->obj, false);
@@ -128,6 +161,8 @@ err_out:
 	return ret;
 }
 
+#undef OUT_BATCH
+
 void i915_gem_render_state_fini(struct render_state *so)
 {
 	i915_gem_object_ggtt_unpin(so->obj);
@@ -176,6 +211,16 @@ int i915_gem_render_state_init(struct drm_i915_gem_request *req)
 	if (ret)
 		goto out;
 
+	if (so.aux_batch_size > 8) {
+		ret = req->ring->dispatch_execbuffer(req,
+						     (so.ggtt_offset +
+						      so.aux_batch_offset),
+						     so.aux_batch_size,
+						     I915_DISPATCH_SECURE);
+		if (ret)
+			goto out;
+	}
+
 	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req);
 
 out:
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.h b/drivers/gpu/drm/i915/i915_gem_render_state.h
index 7aa73728178a..e641bb093a90 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.h
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.h
@@ -37,6 +37,8 @@ struct render_state {
 	struct drm_i915_gem_object *obj;
 	u64 ggtt_offset;
 	int gen;
+	u32 aux_batch_size;
+	u32 aux_batch_offset;
 };
 
 int i915_gem_render_state_init(struct drm_i915_gem_request *req);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 9faad82c42ec..99bba8ece464 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1740,6 +1740,12 @@ static int intel_lr_context_render_state_init(struct drm_i915_gem_request *req)
 	if (ret)
 		goto out;
 
+	ret = req->ring->emit_bb_start(req,
+				       (so.ggtt_offset + so.aux_batch_offset),
+				       I915_DISPATCH_SECURE);
+	if (ret)
+		goto out;
+
 	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req);
 
 out: