[Intel-gfx] [CI 1/4] drm/i915/selftests: Check we can recover a wedged device

[Chris Wilson]

After declaring a terminally wedged device, we allow ourselves to
recover on the next GPU reset (manually triggered), or resume. Check
that resetting a wedged device does work.

v2: Add rpm (taken explicitly in the subtest in case we remove the outer
wakeref) and early warning to i915_reset() for missed wakerefs

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c               |  1 +
 .../gpu/drm/i915/selftests/intel_hangcheck.c  | 25 +++++++++++++++++++
 2 files changed, 26 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 77c0f97fe77c..caa055ac9472 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -2226,6 +2226,7 @@ void i915_reset(struct drm_i915_private *i915,
 
 	might_sleep();
 	lockdep_assert_held(&i915->drm.struct_mutex);
+	assert_rpm_wakelock_held(i915);
 	GEM_BUG_ON(!test_bit(I915_RESET_BACKOFF, &error->flags));
 
 	if (!test_bit(I915_RESET_HANDOFF, &error->flags))
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 805e40aff407..5562dfab1791 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -385,6 +385,30 @@ static int igt_global_reset(void *arg)
 	return err;
 }
 
+static int igt_wedged_reset(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+
+	/* Check that we can recover a wedged device with a GPU reset */
+
+	igt_global_reset_lock(i915);
+	mutex_lock(&i915->drm.struct_mutex);
+	intel_runtime_pm_get(i915);
+
+	i915_gem_set_wedged(i915);
+	GEM_BUG_ON(!i915_terminally_wedged(&i915->gpu_error));
+
+	set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags);
+	i915_reset(i915, ALL_ENGINES, NULL);
+	GEM_BUG_ON(test_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags));
+
+	intel_runtime_pm_put(i915);
+	mutex_unlock(&i915->drm.struct_mutex);
+	igt_global_reset_unlock(i915);
+
+	return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0;
+}
+
 static bool wait_for_idle(struct intel_engine_cs *engine)
 {
 	return wait_for(intel_engine_is_idle(engine), IGT_IDLE_TIMEOUT) == 0;
@@ -1452,6 +1476,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_global_reset), /* attempt to recover GPU first */
+		SUBTEST(igt_wedged_reset),
 		SUBTEST(igt_hang_sanitycheck),
 		SUBTEST(igt_reset_idle_engine),
 		SUBTEST(igt_reset_active_engine),
-- 
2.20.0