nv-tegra-mirror/linux-nvgpu
1
0
Fork 0
mirror of git://nv-tegra.nvidia.com/linux-nvgpu.git synced 2025-12-22 17:36:20 +03:00
Code Issues Packages Projects Releases Wiki Activity

gpu: nvgpu: rename has_timedout and make it thread safe

Browse Source 
Currently has_timedout variable is protected by wmb at places
where it is being set and there is no correspoding rmb whenever
has_timedout variable is read. This is prone to errors for
concurrent execution. This change is supposed to fix this issue.
Rename has_timedout variable of channel struct to ch_timedout.
Also to avoid rmb every time ch_timedout is read,
ch_timedout_spinlock is added to protect ch_timedout
variable for taking care of concurrent execution.

Bug 2404865
Bug 2092051

Change-Id: I0bee9f50af0a48720aa8b54cbc3af97ef9f6df00
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1930935
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This commit is contained in:
Seema Khowala
2018-10-19 12:08:46 -07:00
committed by mobile promotions
parent 503b897b45
commit 1f54ea09e3
9 changed files with 54 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
drivers/gpu/nvgpu/os/linux/cde.c
View File

@@ -1275,7 +1275,7 @@ __releases(&cde_app->mutex)
nvgpu_log_info(g, "double finish cde context %p on channel %p",
cde_ctx, ch);
if (ch->has_timedout) {
if (gk20a_channel_check_timedout(ch)) {
if (cde_ctx->is_temporary) {
nvgpu_warn(g,
"cde: channel had timed out"
@@ -1302,8 +1302,9 @@ __releases(&cde_app->mutex)
msecs_to_jiffies(CTX_DELETE_TIME));
}
if (!ch->has_timedout)
if (!gk20a_channel_check_timedout(ch)) {
gk20a_cde_ctx_release(cde_ctx);
}
}
static int gk20a_cde_load(struct gk20a_cde_ctx *cde_ctx)