If inside hangcheck we see that the engine has paused, but there is an
execlists interrupt still pending, we know that the tasklet did not
fire. Dump the GEM trace along with the current engine state, and kick
the tasklet to recovery without having to go through a GPU reset.
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/intel_hangcheck.c | 23 +++++++++++++++++++++++
1 file changed, 23 insertions(+)
diff --git a/drivers/gpu/drm/i915/intel_hangcheck.c b/drivers/gpu/drm/i915/intel_hangcheck.c
index 309e38b00e95..2d7f10492e35 100644
--- a/drivers/gpu/drm/i915/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/intel_hangcheck.c
@@ -267,6 +267,29 @@ engine_stuck(struct intel_engine_cs *engine, u64 acthd)
}
}
+ if (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted)) {
+ struct intel_engine_execlists *execlists = &engine->execlists;
+ enum intel_engine_hangcheck_action ret = ENGINE_WAIT;
+
+ if (GEM_SHOW_DEBUG()) {
+ struct drm_printer p = drm_debug_printer("hangcheck");
+
+ GEM_TRACE_DUMP();
+ intel_engine_dump(engine, &p,
+ "%s stuck\n", engine->name);
+ }
+
+ if (tasklet_trylock(&execlists->tasklet)) {
+ execlists->tasklet.func(execlists->tasklet.data);
+ tasklet_unlock(&execlists->tasklet);
+
+ ret = ENGINE_WAIT_KICK;
+ }
+
+ tasklet_hi_schedule(&execlists->tasklet);
+ return ret;
+ }
+
return ENGINE_DEAD;
}
--
2.17.0
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
