gpu: nvgpu: rename has_timedout and make it thread safe

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
Signed-off-by: Debarshi Dutta <ddutta@nvidia.com>
(cherry picked from commit 1f54ea09e3445d9ca3cf7a69b4967849cc9defc8
in dev-kernel)
Reviewed-on: https://git-master.nvidia.com/r/2016975
GVS: Gerrit_Virtual_Submit
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: Bibek Basu <bbasu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 4 insertions, 4 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c b/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c
index 06db0bb0..d4e386bd 100644
--- a/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c
@@ -1484,8 +1484,8 @@ static void gk20a_fifo_set_has_timedout_and_wake_up_wqs(struct gk20a *g,
 {
         if (refch) {
                 /* mark channel as faulted */
-                refch->has_timedout = true;
-                nvgpu_smp_wmb();
+                gk20a_channel_set_timedout(refch);
+
                 /* unblock pending waits */
                 nvgpu_cond_broadcast_interruptible(&refch->semaphore_wq);
                 nvgpu_cond_broadcast_interruptible(&refch->notifier_wq);
@@ -1568,7 +1568,7 @@ void gk20a_fifo_abort_tsg(struct gk20a *g, struct tsg_gk20a *tsg, bool preempt)
         nvgpu_rwsem_down_read(&tsg->ch_list_lock);
         nvgpu_list_for_each_entry(ch, &tsg->ch_list, channel_gk20a, ch_entry) {
                 if (gk20a_channel_get(ch)) {
-                        ch->has_timedout = true;
+                        gk20a_channel_set_timedout(ch);
                         if (ch->g->ops.fifo.ch_abort_clean_up) {
                                 ch->g->ops.fifo.ch_abort_clean_up(ch);
                         }
@@ -2181,7 +2181,7 @@ int gk20a_fifo_tsg_unbind_channel(struct channel_gk20a *ch)
 
         /* If one channel in TSG times out, we disable all channels */
         nvgpu_rwsem_down_write(&tsg->ch_list_lock);
-        tsg_timedout = ch->has_timedout;
+        tsg_timedout = gk20a_channel_check_timedout(ch);
         nvgpu_rwsem_up_write(&tsg->ch_list_lock);
 
         /* Disable TSG and examine status before unbinding channel */