gpu: nvgpu: do not bind already active channels to TSG

If a channel is already scheduled as regular channel, we should not
allow it to be marked as TSG since it will fail book keeping of
number of active channels in a TSG

This way we can force to bind the channels first and then only
make them active

Also, remove duplicate function declaration added during branch merge
and one unnecessary comparison with zero

Bug 1470692

Change-Id: I88f9678919e4b76de472c6dda21e4537520241c4
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/497903
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>

1 files changed, 1 insertions, 1 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c b/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c
index 56ff4c87..6383b8c8 100644
--- a/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c
@@ -1779,7 +1779,7 @@ static int gk20a_fifo_update_runlist_locked(struct gk20a *g, u32 runlist_id,
                         if (test_and_set_bit(hw_chid,
                                 runlist->active_channels) == 1)
                                 return 0;
-                        if (tsg && ++tsg->num_active_channels > 0)
+                        if (tsg && ++tsg->num_active_channels)
                                 set_bit(f->channel[hw_chid].tsgid,
                                         runlist->active_tsgs);
                 } else {