Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> writes:
> If the idle_pulse fails to flush the i915_active, dump the tree to see
> if that has any clues.
>
> Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
> ---
> .../drm/i915/gt/selftest_engine_heartbeat.c | 4 ++
> drivers/gpu/drm/i915/i915_active.h | 2 +
> drivers/gpu/drm/i915/selftests/i915_active.c | 45 +++++++++++++++++++
> 3 files changed, 51 insertions(+)
>
> diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
> index 155c508024df..131c49ddf33f 100644
> --- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
> +++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
> @@ -100,8 +100,12 @@ static int __live_idle_pulse(struct intel_engine_cs *engine,
> pulse_unlock_wait(p); /* synchronize with the retirement callback */
>
> if (!i915_active_is_idle(&p->active)) {
> + struct drm_printer m = drm_err_printer("pulse");
> +
> pr_err("%s: heartbeat pulse did not flush idle tasks\n",
> engine->name);
> + i915_active_print(&p->active, &m);
> +
> err = -EINVAL;
> goto out;
> }
> diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
> index 4f52fe6146d2..44859356ce97 100644
> --- a/drivers/gpu/drm/i915/i915_active.h
> +++ b/drivers/gpu/drm/i915/i915_active.h
> @@ -214,4 +214,6 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
> void i915_active_acquire_barrier(struct i915_active *ref);
> void i915_request_add_active_barriers(struct i915_request *rq);
>
> +void i915_active_print(struct i915_active *ref, struct drm_printer *m);
> +
> #endif /* _I915_ACTIVE_H_ */
> diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c
> index 96513a7d4739..260b0ee5d1e3 100644
> --- a/drivers/gpu/drm/i915/selftests/i915_active.c
> +++ b/drivers/gpu/drm/i915/selftests/i915_active.c
> @@ -205,3 +205,48 @@ int i915_active_live_selftests(struct drm_i915_private *i915)
>
> return i915_subtests(tests, i915);
> }
> +
> +static struct intel_engine_cs *node_to_barrier(struct active_node *it)
> +{
> + struct intel_engine_cs *engine;
> +
> + if (!is_barrier(&it->base))
> + return NULL;
> +
> + engine = __barrier_to_engine(it);
> + smp_rmb(); /* serialise with add_active_barriers */
I did find the pair. Builds confidence.
> + if (!is_barrier(&it->base))
> + return NULL;
> +
> + return engine;
> +}
> +
> +void i915_active_print(struct i915_active *ref, struct drm_printer *m)
> +{
> + drm_printf(m, "active %pS:%pS\n", ref->active, ref->retire);
> + drm_printf(m, "\tcount: %d\n", atomic_read(&ref->count));
> + drm_printf(m, "\tpreallocated barriers? %s\n",
> + yesno(!llist_empty(&ref->preallocated_barriers)));
> +
> + if (i915_active_acquire_if_busy(ref)) {
> + struct active_node *it, *n;
> +
> + rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) {
> + struct intel_engine_cs *engine;
> +
Does the aquire of ref keep the other lefs alive?
we seem to be safe on interation but the poking about
the fence set and timeline below is a question mark.
-Mika
> + engine = node_to_barrier(it);
> + if (engine) {
> + drm_printf(m, "\tbarrier: %s\n", engine->name);
> + continue;
> + }
> +
> + if (i915_active_fence_isset(&it->base)) {
> + drm_printf(m,
> + "\ttimeline: %llx\n", it->timeline);
> + continue;
> + }
> + }
> +
> + i915_active_release(ref);
> + }
> +}
> --
> 2.24.0.rc1
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
