drm/i915: Simplify and fix object to display tracking

Purpose of this tracking is to know when to flush the cache between
the CPU and the non-coherent display engine. Prior to:

   commit 121920faf2ccce9aa66a7e2588415c9647b66104
   Author: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
   Date:   Mon Mar 23 11:10:37 2015 +0000

       drm/i915/skl: Query display address through a wrapper

This worked by a mix of direct flag manipulation and checking for
existence of a pinned GGTT VMA.

With the introduction of rotated display mappings this approach is
no longer correct.

New simpler approach is to just keep this count over calls which pin
and unpin objects to and from display, at the slight cost of extra
space in every bo.

(Inspired and extracted code from a larger rework by Chris Wilson.)

v2: Remove the limit since it is not well defined. (Chris Wilson, Ville Syrjälä)
v3: Commit message corrections. (Chris Wilson)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_drv.h

@@ -1969,7 +1969,6 @@ struct drm_i915_gem_object {
 	 * accurate mappable working set.
 	 */
 	unsigned int fault_mappable:1;
-	unsigned int pin_display:1;
 
 	/*
 	 * Is the object to be mapped as read-only to the GPU
@@ -1983,6 +1982,8 @@ struct drm_i915_gem_object {
 
 	unsigned int frontbuffer_bits:INTEL_FRONTBUFFER_BITS;
 
+	unsigned int pin_display;
+
 	struct sg_table *pages;
 	int pages_pin_count;
 	struct get_page {

drivers/gpu/drm/i915/i915_gem.c

@@ -3914,24 +3914,6 @@ unlock:
 	return ret;
 }
 
-static bool is_pin_display(struct drm_i915_gem_object *obj)
-{
-	struct i915_vma *vma;
-
-	vma = i915_gem_obj_to_ggtt(obj);
-	if (!vma)
-		return false;
-
-	/* There are 2 sources that pin objects:
-	 *   1. The display engine (scanouts, sprites, cursors);
-	 *   2. Reservations for execbuffer;
-	 *
-	 * We can ignore reservations as we hold the struct_mutex and
-	 * are only called outside of the reservation path.
-	 */
-	return vma->pin_count;
-}
-
 /*
  * Prepare buffer for display plane (scanout, cursors, etc).
  * Can be called from an uninterruptible phase (modesetting) and allows
@@ -3944,7 +3926,6 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 				     const struct i915_ggtt_view *view)
 {
 	u32 old_read_domains, old_write_domain;
-	bool was_pin_display;
 	int ret;
 
 	if (pipelined != i915_gem_request_get_ring(obj->last_read_req)) {
@@ -3956,8 +3937,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	/* Mark the pin_display early so that we account for the
 	 * display coherency whilst setting up the cache domains.
 	 */
-	was_pin_display = obj->pin_display;
-	obj->pin_display = true;
+	obj->pin_display++;
 
 	/* The display engine is not coherent with the LLC cache on gen6.  As
 	 * a result, we make sure that the pinning that is about to occur is
@@ -4001,8 +3981,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	return 0;
 
 err_unpin_display:
-	WARN_ON(was_pin_display != is_pin_display(obj));
-	obj->pin_display = was_pin_display;
+	obj->pin_display--;
 	return ret;
 }
 
@@ -4010,9 +3989,12 @@ void
 i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj,
 					 const struct i915_ggtt_view *view)
 {
+	if (WARN_ON(obj->pin_display == 0))
+		return;
+
 	i915_gem_object_ggtt_unpin_view(obj, view);
 
-	obj->pin_display = is_pin_display(obj);
+	obj->pin_display--;
 }
 
 int