gpu: nvgpu: cancel all wdt timeouts while handling SCHED errors

A SCHED error might cause multiple channels' watchdogs to trigger
simultaneously

Hence, to avoid this conflict cancel watchdog timeout on all
channels before recovering from SCHED errors

Also, define API gk20a_channel_timeout_stop_all_channels()
to cancel wdt timeout on all channels

Bug 200133289

Change-Id: I8324c397891f0a711327b77d0677cd6718af6d01
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/810959
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>

1 files changed, 6 insertions, 0 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c b/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c
index ae36478e..4f3363f2 100644
--- a/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c
@@ -1450,6 +1450,7 @@ static bool gk20a_fifo_handle_sched_error(struct gk20a *g)
                 struct channel_gk20a *ch = &f->channel[id];
 
                 if (is_tsg) {
+                        gk20a_channel_timeout_stop_all_channels(g);
                         gk20a_fifo_recover(g, BIT(engine_id), id, true,
                                         true, true);
                         ret = true;
@@ -1467,6 +1468,11 @@ static bool gk20a_fifo_handle_sched_error(struct gk20a *g)
                                 "fifo sched ctxsw timeout error:"
                                 "engine = %u, ch = %d", engine_id, id);
                         gk20a_gr_debug_dump(g->dev);
+                        /*
+                         * Cancel all channels' timeout since SCHED error might
+                         * trigger multiple watchdogs at a time
+                         */
+                        gk20a_channel_timeout_stop_all_channels(g);
                         gk20a_fifo_recover(g, BIT(engine_id), id, false,
                                 true, ch->timeout_debug_dump);
                         ret = true;