drm/vc4: Fulfill user BO creation requests from the kernel BO cache.

The from_cache flag was actually "the BO is invisible to userspace",
so we can repurpose to just zero out a cached BO and return it to
userspace.

Improves wall time for a loop of 5 glsl-algebraic-add-add-1 by
-1.44989% +/- 0.862891% (n=28, 1 outlier removed from each that
appeared to be other system noise)

Note that there's an intel-gpu-tools test to check for the proper
zeroing behavior here, which we continue to pass.

Signed-off-by: Eric Anholt <eric@anholt.net>

diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index ec9023bd935b6755b3c2b6a7e171cb269562234c..fd83a28076564b9ea5cf0f2ba29b884ee3c5af43 100644 (file)
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -208,21 +208,22 @@ struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size)
 }
 
 struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size,
-                            bool from_cache)
+                            bool allow_unzeroed)
 {
        size_t size = roundup(unaligned_size, PAGE_SIZE);
        struct vc4_dev *vc4 = to_vc4_dev(dev);
        struct drm_gem_cma_object *cma_obj;
+       struct vc4_bo *bo;
 
        if (size == 0)
                return ERR_PTR(-EINVAL);
 
        /* First, try to get a vc4_bo from the kernel BO cache. */
-       if (from_cache) {
-               struct vc4_bo *bo = vc4_bo_get_from_cache(dev, size);
-
-               if (bo)
-                       return bo;
+       bo = vc4_bo_get_from_cache(dev, size);
+       if (bo) {
+               if (!allow_unzeroed)
+                       memset(bo->base.vaddr, 0, bo->base.base.size);
+               return bo;
        }
 
        cma_obj = drm_gem_cma_create(dev, size);