summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorChris Wilson <chris@chris-wilson.co.uk>2015-02-27 13:58:43 +0000
committerDaniel Vetter <daniel.vetter@ffwll.ch>2015-02-27 19:01:48 +0100
commite8dec1dde016258af7c8a2ce9ddfb7243176a344 (patch)
treecbfdd630bb404d72bd712321be03bac98ded4ff1
parent9a8f0a1290993c86c4e35756a2624bfe461f9036 (diff)
drm/i915: Clarify obj->map_and_fenceable
For an object right on the boundary of mappable space, as the fenceable size is stricly greater than the actual size, its fence region may extend out of mappable space. Note that only pnv/g33 has fence_size > obj.size and an unmappable range in the gtt, and there alignment constraints prevent bad things from happening. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> [danvet: Clarify why this shouldn't change anything as per the discussion on intel-gfx.] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
-rw-r--r--drivers/gpu/drm/i915/i915_gem.c2
1 files changed, 1 insertions, 1 deletions
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index be991789df2d..f8c12693f7cf 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4219,7 +4219,7 @@ i915_gem_object_pin_view(struct drm_i915_gem_object *obj,
fenceable = (vma->node.size == fence_size &&
(vma->node.start & (fence_alignment - 1)) == 0);
- mappable = (vma->node.start + obj->base.size <=
+ mappable = (vma->node.start + fence_size <=
dev_priv->gtt.mappable_end);
obj->map_and_fenceable = mappable && fenceable;