[PATCH 2/4] drm/i915: introduce i915_gem_object_adjust_fencing

[Daniel Vetter <daniel.vetter@ffwll.ch>]

Pipelining tiling changes will complicate all places that need
a correct fence register to be set up. So hide this complexity
behind a small helper function.

i915_gem_object_get_fence loses all it's external callers by these
changes, so convert it into a static function

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.h      |    2 +-
 drivers/gpu/drm/i915/i915_gem.c      |   52 ++++++++++++++++++++++++++++-----
 drivers/gpu/drm/i915/intel_display.c |   16 ++--------
 3 files changed, 49 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 242993b..7aec3ec 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -918,7 +918,7 @@ void i915_gem_release_mmap(struct drm_gem_object *obj);
 void i915_gem_lastclose(struct drm_device *dev);
 uint32_t i915_get_gem_seqno(struct drm_device *dev);
 bool i915_seqno_passed(uint32_t seq1, uint32_t seq2);
-int i915_gem_object_get_fence_reg(struct drm_gem_object *obj);
+int i915_gem_object_adjust_fencing(struct drm_gem_object *obj);
 int i915_gem_object_put_fence_reg(struct drm_gem_object *obj);
 void i915_gem_retire_requests(struct drm_device *dev);
 void i915_gem_retire_work_handler(struct work_struct *work);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 47c46ed..8e73a12 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -974,6 +974,10 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		ret = i915_gem_phys_pwrite(dev, obj, args, file_priv);
 	else if (obj_priv->tiling_mode == I915_TILING_NONE &&
 		 dev->gtt_total != 0) {
+		ret = i915_gem_object_adjust_fencing(obj);
+		if (ret != 0)
+			return ret;
+
 		ret = i915_gem_gtt_pwrite_fast(dev, obj, args, file_priv);
 		if (ret == -EFAULT) {
 			ret = i915_gem_gtt_pwrite_slow(dev, obj, args,
@@ -1191,12 +1195,9 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 			goto unlock;
 	}
 
-	/* Need a new fence register? */
-	if (obj_priv->tiling_mode != I915_TILING_NONE) {
-		ret = i915_gem_object_get_fence_reg(obj);
-		if (ret)
-			goto unlock;
-	}
+	ret = i915_gem_object_adjust_fencing(obj);
+	if (ret)
+		goto unlock;
 
 	pfn = ((dev->agp->base + obj_priv->gtt_offset) >> PAGE_SHIFT) +
 		page_offset;
@@ -2475,7 +2476,7 @@ static int i915_find_fence_reg(struct drm_device *dev)
  * It then sets up the reg based on the object's properties: address, pitch
  * and tiling format.
  */
-int
+static int
 i915_gem_object_get_fence_reg(struct drm_gem_object *obj)
 {
 	struct drm_device *dev = obj->dev;
@@ -2536,6 +2537,41 @@ i915_gem_object_get_fence_reg(struct drm_gem_object *obj)
 }
 
 /**
+ * i915_gem_object_adjust_fencing - ensure correct fencing for an object
+ * @obj: object to map through a fence reg
+ *
+ * Tiling changes may be delayed untill fenced access is actually needed.
+ * Batchbuffer submitted via execbuf2 may not need a fence, so delaying
+ * gtt remapping and fence register changes (which all stall the gpu) as
+ * long as possible is beneficial.
+ *
+ * This function ensures that all delayed operations have been carried out and
+ * the object can be correctly accessed via fences.
+ */
+int
+i915_gem_object_adjust_fencing(struct drm_gem_object *obj)
+{
+	struct drm_i915_gem_object *obj_priv = to_intel_bo(obj);
+	int ret;
+
+	if (!i915_gem_object_fence_offset_ok(obj, obj_priv->tiling_mode)) {
+		ret = i915_gem_object_unbind(obj);
+		if (ret != 0)
+			return ret;
+		ret = i915_gem_object_bind_to_gtt(obj, 0);
+		if (ret != 0)
+			return ret;
+	}
+
+	if (obj_priv->tiling_mode != I915_TILING_NONE) {
+		ret = i915_gem_object_get_fence_reg(obj);
+		if (ret != 0)
+			return ret;
+	}
+	return 0;
+}
+
+/**
  * i915_gem_clear_fence_reg - clear out fence register info
  * @obj: object to clear
  *
@@ -3309,7 +3345,7 @@ i915_gem_object_pin_and_relocate(struct drm_gem_object *obj,
 	 * properly handle blits to/from tiled surfaces.
 	 */
 	if (need_fence) {
-		ret = i915_gem_object_get_fence_reg(obj);
+		ret = i915_gem_object_adjust_fencing(obj);
 		if (ret != 0) {
 			if (ret != -EBUSY && ret != -ERESTARTSYS)
 				DRM_ERROR("Failure to install fence: %d\n",
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3836f56..56b673d 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1249,18 +1249,10 @@ intel_pin_and_fence_fb_obj(struct drm_device *dev, struct drm_gem_object *obj)
 	if (ret != 0)
 		return ret;
 
-	/* Install a fence for tiled scan-out. Pre-i965 always needs a
-	 * fence, whereas 965+ only requires a fence if using
-	 * framebuffer compression.  For simplicity, we always install
-	 * a fence as the cost is not that onerous.
-	 */
-	if (obj_priv->fence_reg == I915_FENCE_REG_NONE &&
-	    obj_priv->tiling_mode != I915_TILING_NONE) {
-		ret = i915_gem_object_get_fence_reg(obj);
-		if (ret != 0) {
-			i915_gem_object_unpin(obj);
-			return ret;
-		}
+	ret = i915_gem_object_adjust_fencing(obj);
+	if (ret != 0) {
+		i915_gem_object_unpin(obj);
+		return ret;
 	}
 
 	return 0;
-- 
1.6.6.1