gpu: nvgpu: expose deterministic submit support

Add these bits in the gpu characteristics flags:

NVGPU_GPU_FLAGS_SUPPORT_DETERMINISTIC_SUBMIT_NO_JOBTRACKING - fast
submits with no in-kernel job tracking are supported.

NVGPU_GPU_FLAGS_SUPPORT_DETERMINISTIC_SUBMIT_FULL - deterministic
submits also with job tracking and num_inflight_jobs set are supported.

Either of these may get disabled if the particular channel or submit
still requires features that block these.

Make gk20a_channel_sync_needs_sync_framework() take a gk20a pointer
instead of a channel pointer so that it can be called without a channel.
It does not need any per-channel data.

Bug 200291300

Change-Id: I5f82510b6d39b53bcf6f1006dd83bdd9053963a0
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/1456845
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 2 insertions, 4 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/channel_sync_gk20a.c b/drivers/gpu/nvgpu/gk20a/channel_sync_gk20a.c
index ddd94a2d..ed83663d 100644
--- a/drivers/gpu/nvgpu/gk20a/channel_sync_gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/channel_sync_gk20a.c
@@ -972,9 +972,7 @@ struct gk20a_channel_sync *gk20a_channel_sync_create(struct channel_gk20a *c)
         return gk20a_channel_semaphore_create(c);
 }
 
-bool gk20a_channel_sync_needs_sync_framework(struct channel_gk20a *c)
+bool gk20a_channel_sync_needs_sync_framework(struct gk20a *g)
 {
-        if (gk20a_platform_has_syncpoints(c->g))
-                return false;
-        return true;
+        return !gk20a_platform_has_syncpoints(g);
 }