gpu: nvgpu: map patch ctx in set_preemption_mode

The per-write map/unmap feature from gr_gk20a_ctx_patch_write_begin() is
dropped, so call begin/end explicitly from gr_gp10b_set_preemption_mode
for the commit_global_cb_manager call.

Change-Id: I7bf952fffb54d4f18706e77dea015ffe4b68bcfe
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/1157835
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
This commit is contained in:
Konsta Holtta
2016-05-25 13:23:52 +03:00
committed by Deepak Nibade
parent 11e9ba82de
commit 8403bb6300

View File

@@ -2077,7 +2077,15 @@ static int gr_gp10b_set_preemption_mode(struct channel_gk20a *ch,
if (g->ops.gr.update_ctxsw_preemption_mode) {
g->ops.gr.update_ctxsw_preemption_mode(ch->g, ch_ctx, mem);
err = gr_gk20a_ctx_patch_write_begin(g, ch_ctx);
if (err) {
gk20a_err(dev_from_gk20a(g),
"can't map patch context");
goto enable_ch;
}
g->ops.gr.commit_global_cb_manager(g, ch, true);
gr_gk20a_ctx_patch_write_end(g, ch_ctx);
}
enable_ch: