nv-tegra-mirror/linux-nvgpu
1
0
Fork 0
mirror of git://nv-tegra.nvidia.com/linux-nvgpu.git synced 2025-12-25 02:52:51 +03:00
Code Issues Packages Projects Releases Wiki Activity

gpu: nvgpu: write with ack for mailbox1 during fecs trace

Browse Source 
FECS ucode does a priv holdoff around the assertion of context
reset. So, priv transactions (e.g. mailbox1 register write) might
fail due to this. Hence, do write with ack i.e. write and read
it back to make sure write happened for mailbox1.

Bug 200417403

Change-Id: I463be1cb8fdd477106b87786cb0603327a22cebe
Signed-off-by: Vaibhav Kachore <vkachore@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2023494
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This commit is contained in:
Vaibhav Kachore
2019-02-20 11:32:45 +05:30
committed by mobile promotions
parent b65d697533
commit 0e2a013e3b
1 changed files with 11 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
drivers/gpu/nvgpu/gk20a/fecs_trace_gk20a.c
View File

@@ -266,6 +266,17 @@ int gk20a_fecs_trace_poll(struct gk20a *g)
nvgpu_wmb();
gk20a_fecs_trace_set_read_index(g, read);
/*
* FECS ucode does a priv holdoff around the assertion of context
* reset. So, pri transactions (e.g. mailbox1 register write) might
* fail due to this. Hence, do write with ack i.e. write and read
* it back to make sure write happened for mailbox1.
*/
while (gk20a_fecs_trace_get_read_index(g) != read) {
nvgpu_log(g, gpu_dbg_ctxsw, "mailbox1 update failed");
gk20a_fecs_trace_set_read_index(g, read);
}
done:
nvgpu_mutex_release(&trace->poll_lock);
gk20a_idle(g);