gpu: nvgpu: set PMU "queue full" as debug message

Queue full message is not an error, it informs queue is full
& wait till it gets space in queue to upload pending request.

Bug 200256603

Change-Id: I14f4196b391cd54e1b9616f0555a5ce0856af428
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: http://git-master/r/1260494
(cherry picked from commit e7360fb52b2030c9c68aa5ed06ecd7c32b47a8c5)
Reviewed-on: http://git-master/r/1271619
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 2 insertions, 1 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/pmu_gk20a.c b/drivers/gpu/nvgpu/gk20a/pmu_gk20a.c
index f9072cec..01b9dddf 100644
--- a/drivers/gpu/nvgpu/gk20a/pmu_gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/pmu_gk20a.c
@@ -2852,7 +2852,8 @@ static int pmu_queue_open_write(struct pmu_gk20a *pmu,
                 BUG();
 
         if (!pmu_queue_has_room(pmu, queue, size, &rewind)) {
-                gk20a_err(dev_from_gk20a(gk20a_from_pmu(pmu)), "queue full");
+                gk20a_dbg_pmu("queue full: queue-id %d: index %d",
+                                queue->id, queue->index);
                 pmu_queue_unlock(pmu, queue);
                 return -EAGAIN;
         }