drm/i915: clflush on pin_to_display after pwrite to UC bo in LLC

Currently we don't clflush on pin_to_display if the bo is already
UC/WT and is not in the CPU write domain. This causes problems with
pwrite since pwrite doesn't change the write domain, and it avoids
clflushing on UC/WT buffers on LLC platforms unless the buffer is
currently being scanned out.

Fix the problem by marking the cache dirty and adjusting
i915_gem_object_set_cache_level() to clflush when the cache is dirty
even if the cache_level doesn't change.

My last attempt [1] at fixing this via write domain frobbing was shot
down, but now with the cache_dirty flag we can do things in a nicer way.

[1] http://lists.freedesktop.org/archives/intel-gfx/2014-November/055390.html

v2: Drop the I915_CACHE_NONE/WT checks from pwrite

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=86422
Testcase: igt/kms_pwrite_crc
Testcase: igt/gem_pwrite_snooped
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 6d0f834..407b6b3 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1005,12 +1005,14 @@
 		if (!needs_clflush_after &&
 		    obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
 			if (i915_gem_clflush_object(obj, obj->pin_display))
-				i915_gem_chipset_flush(dev);
+				needs_clflush_after = true;
 		}
 	}
 
 	if (needs_clflush_after)
 		i915_gem_chipset_flush(dev);
+	else
+		obj->cache_dirty = true;
 
 	intel_fb_obj_flush(obj, false, ORIGIN_CPU);
 	return ret;
@@ -3639,10 +3641,10 @@
 {
 	struct drm_device *dev = obj->base.dev;
 	struct i915_vma *vma, *next;
-	int ret;
+	int ret = 0;
 
 	if (obj->cache_level == cache_level)
-		return 0;
+		goto out;
 
 	if (i915_gem_obj_is_pinned(obj)) {
 		DRM_DEBUG("can not change the cache level of pinned objects\n");
@@ -3687,6 +3689,7 @@
 		vma->node.color = cache_level;
 	obj->cache_level = cache_level;
 
+out:
 	if (obj->cache_dirty &&
 	    obj->base.write_domain != I915_GEM_DOMAIN_CPU &&
 	    cpu_write_needs_clflush(obj)) {