gpu: nvgpu: allocate separate client managed syncpoint for User

We right now allocate a nvgpu managed syncpoint in c->sync and share
that with user space

But to avoid conflicts between user space and kernel space increments
allocate a separate "client managed" syncpoint for User space in c->user_sync

Add new API nvgpu_nvhost_get_syncpt_client_managed() to request a client managed
syncpoint from nvhost.
Note that nvhost/nvgpu do not keep track of MAX/threshold value of this syncpoint

Update gk20a_channel_syncpt_create() to receive a flag to indicate whether a
User space syncpoint is required or not

Unset NVGPU_SUPPORT_USER_SYNCPOINT for gp10b since we don't want to allocate
double syncpoints per channel on that platform

For gv11b, once we move to use user space submits, support for c->sync will be
dropped so we keep using only one syncpoint per channel

Bug 200326065
Jira NVGPU-179

Change-Id: I78d94de4276db1c897ea2a4fe4c2db8b2a179722
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1665828
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 5 insertions, 1 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/channel_gk20a.c b/drivers/gpu/nvgpu/gk20a/channel_gk20a.c
index 2f5ea301..2c98797d 100644
--- a/drivers/gpu/nvgpu/gk20a/channel_gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/channel_gk20a.c
@@ -438,6 +438,10 @@ static void gk20a_free_channel(struct channel_gk20a *ch, bool force)
                 gk20a_channel_sync_destroy(ch->sync);
                 ch->sync = NULL;
         }
+        if (ch->user_sync) {
+                gk20a_channel_sync_destroy(ch->user_sync);
+                ch->user_sync = NULL;
+        }
         nvgpu_mutex_release(&ch->sync_lock);
 
         /*
@@ -1147,7 +1151,7 @@ int gk20a_channel_alloc_gpfifo(struct channel_gk20a *c,
 
         if (!g->aggressive_sync_destroy_thresh) {
                 nvgpu_mutex_acquire(&c->sync_lock);
-                c->sync = gk20a_channel_sync_create(c);
+                c->sync = gk20a_channel_sync_create(c, false);
                 if (!c->sync) {
                         err = -ENOMEM;
                         nvgpu_mutex_release(&c->sync_lock);