gpu: nvgpu: return ENOSPC if no private command buffer space

If we run out of gpfifo space or private command
buffer space, we currently return EAGAIN as error code

Instead of EAGAIN, return ENOSPC as error code so
that caller (user space) can read the error code
and do some re-trials

As the jobs are processed, it is possible to free up
some space. And hence such re-trials could succeed

Bug 1715291

Change-Id: I9a2ed7134d2496b383899b3c02c0e70452b26115
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/929402
Reviewed-by: Sachin Nikam <snikam@nvidia.com>
Tested-by: Sachin Nikam <snikam@nvidia.com>

1 files changed, 2 insertions, 2 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/channel_gk20a.c b/drivers/gpu/nvgpu/gk20a/channel_gk20a.c
index 2ec1ffe4..f34df520 100644
--- a/drivers/gpu/nvgpu/gk20a/channel_gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/channel_gk20a.c
@@ -1327,7 +1327,7 @@ int gk20a_channel_alloc_priv_cmdbuf(struct channel_gk20a *c, u32 orig_size,
         free_count = (q->size - (q->put - q->get) - 1) % q->size;
 
         if (size > free_count)
-                return -EAGAIN;
+                return -ENOSPC;
 
         e = kzalloc(sizeof(struct priv_cmd_entry), GFP_KERNEL);
         if (!e) {
@@ -2022,7 +2022,7 @@ int gk20a_submit_channel_gpfifo(struct channel_gk20a *c,
 
         if (err) {
                 gk20a_err(d, "timeout waiting for gpfifo space");
-                err = -EAGAIN;
+                err = -ENOSPC;
                 goto clean_up;
         }