nv-tegra-mirror/linux-nvgpu
1
0
Fork 0
mirror of git://nv-tegra.nvidia.com/linux-nvgpu.git synced 2025-12-24 10:34:43 +03:00
Code Issues Packages Projects Releases Wiki Activity

gpu: nvgpu: support tuning per-ch deterministic opts

Browse Source 
Add a new ioctl NVGPU_GPU_IOCTL_SET_DETERMINISTIC_OPTS to adjust
deterministic options on a per-channel basis. Currently, the only
supported option is to relax the no-railgating requirement on open
deterministic channels. This also disallows submits on such channels,
until the railgate option is reset.

Bug 200327089

Change-Id: If4f0f51fd1d40ad7407d13638150d7402479aff0
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1554563
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This commit is contained in:
Konsta Holtta
2017-11-06 14:25:47 +02:00
committed by mobile promotions
parent 1480afeb01
commit 8bdce5337e
7 changed files with 179 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
drivers/gpu/nvgpu/common/linux/channel.c
View File

@@ -537,6 +537,17 @@ int gk20a_submit_channel_gpfifo(struct channel_gk20a *c,
if (c->deterministic)
nvgpu_rwsem_down_read(&g->deterministic_busy);
if (c->deterministic && c->deterministic_railgate_allowed) {
/*
* Nope - this channel has dropped its own power ref. As
* deterministic submits don't hold power on per each submitted
* job like normal ones do, the GPU might railgate any time now
* and thus submit is disallowed.
*/
err = -EINVAL;
goto clean_up;
}
trace_gk20a_channel_submit_gpfifo(g->name,
c->chid,
num_entries,