gpu: nvgpu: use inplace allocation in sync framework

This change is the first of a series of changes to
support the usage of pre-allocated job tracking resources
in the submit path. With this change, we still maintain a
dynamically-allocated joblist, but make the necessary changes
in the channel_sync & fence framework to use in-place
allocations. Specifically, we:

1) Update channel sync framework routines to take in
pre-allocated priv_cmd_entry(s) & gk20a_fence(s) rather
than dynamically allocating themselves

2) Move allocation of priv_cmd_entry(s) & gk20a_fence(s)
to gk20a_submit_prepare_syncs

3) Modify fence framework to have seperate allocation
and init APIs. We expose allocation as a seperate API, so
the client can allocate the object before passing it into
the channel sync framework.

4) Fix clean_up logic in channel sync framework

Bug 1795076

Change-Id: I96db457683cd207fd029c31c45f548f98055e844
Signed-off-by: Sachit Kadle <skadle@nvidia.com>
Reviewed-on: http://git-master/r/1206725
(cherry picked from commit 9d196fd10db6c2f934c2a53b1fc0500eb4626624)
Reviewed-on: http://git-master/r/1223933
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 10 insertions, 5 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/fence_gk20a.h b/drivers/gpu/nvgpu/gk20a/fence_gk20a.h
index 35488ea3..3fe2d8b2 100644
--- a/drivers/gpu/nvgpu/gk20a/fence_gk20a.h
+++ b/drivers/gpu/nvgpu/gk20a/fence_gk20a.h
@@ -31,6 +31,7 @@ struct gk20a_fence_ops;
 
 struct gk20a_fence {
         /* Valid for all fence types: */
+        bool valid;
         struct kref ref;
         bool wfi;
         struct sync_fence *sync_fence;
@@ -47,21 +48,25 @@ struct gk20a_fence {
 };
 
 /* Fences can be created from semaphores or syncpoint (id, value) pairs */
-struct gk20a_fence *gk20a_fence_from_semaphore(
+int gk20a_fence_from_semaphore(
+                struct gk20a_fence *fence_out,
                 struct sync_timeline *timeline,
                 struct gk20a_semaphore *semaphore,
                 wait_queue_head_t *semaphore_wq,
                 struct sync_fence *dependency,
                 bool wfi, bool need_sync_fence);
 
-struct gk20a_fence *gk20a_fence_from_syncpt(
+int gk20a_fence_from_syncpt(
+                struct gk20a_fence *fence_out,
                 struct platform_device *host1x_pdev,
                 u32 id, u32 value, bool wfi,
                 bool need_sync_fence);
 
-struct gk20a_fence *gk20a_alloc_fence(const struct gk20a_fence_ops *ops,
-                                      struct sync_fence *sync_fence,
-                                      bool wfi);
+struct gk20a_fence *gk20a_alloc_fence(struct channel_gk20a *c);
+
+void gk20a_init_fence(struct gk20a_fence *f,
+                const struct gk20a_fence_ops *ops,
+                struct sync_fence *sync_fence, bool wfi);
 
 /* Fence operations */
 void gk20a_fence_put(struct gk20a_fence *f);