From: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxxx>
When waiting on syncobjs the current code allocates a temporary array only
to fill it up with all zeros.
We can avoid that by relying on the allocated entry array already being
zero allocated. For the timeline mode we fetch the timeline point values
as we populate the entries array so also do not need this additional
temporary allocation.
"vkgears -present-mailbox" average framerate:
Before: 21410.1089
After: 21609.7225
With a disclaimer that measuring with vkgears feels a bit variable,
nevertheless it did not look like noise.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxxx>
---
drivers/gpu/drm/drm_syncobj.c | 38 +++++++++++++----------------------
1 file changed, 14 insertions(+), 24 deletions(-)
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 2fb95d6f6c82..059d6be3ff1f 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -1027,7 +1027,7 @@ static void syncobj_wait_syncobj_func(struct drm_syncobj *syncobj,
}
static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
- void __user *user_points,
+ u64 __user *user_points,
uint32_t count,
uint32_t flags,
signed long timeout,
@@ -1035,9 +1035,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
ktime_t *deadline)
{
struct syncobj_wait_entry *entries;
- struct dma_fence *fence;
- uint64_t *points;
uint32_t signaled_count, i;
+ struct dma_fence *fence;
if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT |
DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) {
@@ -1045,24 +1044,14 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
lockdep_assert_none_held_once();
}
- points = kmalloc_array(count, sizeof(*points), GFP_KERNEL);
- if (points == NULL)
- return -ENOMEM;
-
- if (!user_points) {
- memset(points, 0, count * sizeof(uint64_t));
-
- } else if (copy_from_user(points, user_points,
- sizeof(uint64_t) * count)) {
- timeout = -EFAULT;
- goto err_free_points;
- }
+ if (user_points &&
+ !access_ok(user_points, count * sizeof(*user_points)))
+ return -EFAULT;
entries = kcalloc(count, sizeof(*entries), GFP_KERNEL);
- if (!entries) {
- timeout = -ENOMEM;
- goto err_free_points;
- }
+ if (!entries)
+ return -ENOMEM;
+
/* Walk the list of sync objects and initialize entries. We do
* this up-front so that we can properly return -EINVAL if there is
* a syncobj with a missing fence and then never have the chance of
@@ -1073,9 +1062,13 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
struct dma_fence *fence;
entries[i].task = current;
- entries[i].point = points[i];
+ if (user_points && get_user(entries[i].point, user_points++)) {
+ timeout = -EFAULT;
+ goto cleanup_entries;
+ }
fence = drm_syncobj_fence_get(syncobjs[i]);
- if (!fence || dma_fence_chain_find_seqno(&fence, points[i])) {
+ if (!fence ||
+ dma_fence_chain_find_seqno(&fence, entries[i].point)) {
dma_fence_put(fence);
if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT |
DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) {
@@ -1181,9 +1174,6 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
}
kfree(entries);
-err_free_points:
- kfree(points);
-
return timeout;
}
--
2.47.1
