drm/i915/gt: Avoid using the GPU before initialisation

Mark the GT as wedged so that we are not tempted to use it prior to
initialisation.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191229183153.3719869-3-chris@chris-wilson.co.uk

4 files changed, 13 insertions, 5 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 010620b78202..cd82f0baef49 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -123,16 +123,16 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	unsigned long flags;
 	bool result = true;
 
+	/* GPU is pointing to the void, as good as in the kernel context. */
+	if (intel_gt_is_wedged(engine->gt))
+		return true;
+
 	GEM_BUG_ON(!intel_context_is_barrier(ce));
 
 	/* Already inside the kernel context, safe to power down. */
 	if (engine->wakeref_serial == engine->serial)
 		return true;
 
-	/* GPU is pointing to the void, as good as in the kernel context. */
-	if (intel_gt_is_wedged(engine->gt))
-		return true;
-
 	/*
 	 * Note, we do this without taking the timeline->mutex. We cannot
 	 * as we may be called while retiring the kernel context and so
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index 3cda837d64c9..9b220c930ebc 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -179,7 +179,7 @@ int intel_gt_resume(struct intel_gt *gt)
 	enum intel_engine_id id;
 	int err;
 
-	err = intel_gt_terminally_wedged(gt);
+	err = intel_gt_has_init_error(gt);
 	if (err)
 		return err;
 
@@ -196,6 +196,10 @@ int intel_gt_resume(struct intel_gt *gt)
 	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
 	intel_rc6_sanitize(&gt->rc6);
 	gt_sanitize(gt, true);
+	if (intel_gt_is_wedged(gt)) {
+		err = -EIO;
+		goto out_fw;
+	}
 
 	/* Only when the HW is re-initialised, can we replay the requests */
 	err = intel_gt_init_hw(gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 8af253334f52..fe919a1af904 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -1353,6 +1353,9 @@ void intel_gt_init_reset(struct intel_gt *gt)
 	init_waitqueue_head(&gt->reset.queue);
 	mutex_init(&gt->reset.mutex);
 	init_srcu_struct(&gt->reset.backoff_srcu);
+
+	/* no GPU until we are ready! */
+	__set_bit(I915_WEDGED, &gt->reset.flags);
 }
 
 void intel_gt_fini_reset(struct intel_gt *gt)
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index ac641f5360e1..2b01094e4318 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -184,6 +184,7 @@ struct drm_i915_private *mock_gem_device(void)
 	if (mock_engine_init(i915->engine[RCS0]))
 		goto err_context;
 
+	__clear_bit(I915_WEDGED, &i915->gt.reset.flags);
 	intel_engines_driver_register(i915);
 
 	return i915;