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 it 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>
Reviewed-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170301185602.6873-1-eric@anholt.net

1 files changed, 7 insertions, 6 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index 7abcd9c5dbe2..e5c7aa935b4b 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -211,21 +211,22 @@ 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);