gpu: nvgpu: suppress prints in submit path

When we run out of gpfifo space or private command buffer
space, we have error spew like below :
__gk20a_channel_syncpt_incr: not enough priv cmd buffer space
gk20a_submit_channel_gpfifo: fail

Dumping these prints to UART cause increase in submit
latencies

But on these failures, we return -ENOSPC to UMD and then
UMD retries the submit, hence it might be unnecessary to dump
these prints

Hence, remove the error prints of insufficient space
and use gk20a_dbg_fn() instead of gk20a_err() to print failure
in gk20a_submit_channel_gpfifo()

Bug 200202653

Change-Id: I49efd7c6c554dd4fbfa4e66d196eb352e69f92c6
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/1152378
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
This commit is contained in:
Deepak Nibade
2016-05-24 13:51:26 +05:30
committed by Terje Bergstrom
parent e82c840119
commit dc7af18bf8
2 changed files with 2 additions and 6 deletions

View File

@@ -2081,7 +2081,6 @@ int gk20a_submit_channel_gpfifo(struct channel_gk20a *c,
}
if (err) {
gk20a_err(d, "timeout waiting for gpfifo space");
err = -ENOSPC;
goto clean_up;
}
@@ -2279,7 +2278,7 @@ int gk20a_submit_channel_gpfifo(struct channel_gk20a *c,
return err;
clean_up:
gk20a_err(d, "fail");
gk20a_dbg_fn("fail");
free_priv_cmdbuf(c, wait_cmd);
free_priv_cmdbuf(c, incr_cmd);
gk20a_fence_put(pre_fence);

View File

@@ -204,11 +204,8 @@ static int __gk20a_channel_syncpt_incr(struct gk20a_channel_sync *s,
incr_cmd_size += 2;
err = gk20a_channel_alloc_priv_cmdbuf(c, incr_cmd_size, &incr_cmd);
if (err) {
gk20a_err(dev_from_gk20a(c->g),
"not enough priv cmd buffer space");
if (err)
return err;
}
off = incr_cmd->off;