drm/i915: Skip error capture when wedged on init

Trying to capture uninitialised engines when we wedged on init ends in tears. Skip that together with uC capture, since failure to initialise the latter can actually be one of the reasons for wedging on init. v2: * Use i915_disable_error_state when wedging on init/fini. v3: * Handle mock tests. Signed-off-by: Tvrtko Ursulin <[email protected]> Reviewed-by: Matthew Auld <[email protected]> # v1 Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
sm00th · Nov 16, 2021 · 9a7fc95 · 9a7fc95
1 parent fac7354
commit 9a7fc95
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 0 deletions.
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -1448,6 +1448,7 @@ void intel_gt_set_wedged_on_init(struct intel_gt *gt)
 	BUILD_BUG_ON(I915_RESET_ENGINE + I915_NUM_ENGINES >
 		     I915_WEDGED_ON_INIT);
 	intel_gt_set_wedged(gt);
+	i915_disable_error_state(gt->i915, -ENODEV);
 	set_bit(I915_WEDGED_ON_INIT, &gt->reset.flags);
 
 	/* Wedged on init is non-recoverable */
@@ -1457,6 +1458,7 @@ void intel_gt_set_wedged_on_init(struct intel_gt *gt)
 void intel_gt_set_wedged_on_fini(struct intel_gt *gt)
 {
 	intel_gt_set_wedged(gt);
+	i915_disable_error_state(gt->i915, -ENODEV);
 	set_bit(I915_WEDGED_ON_FINI, &gt->reset.flags);
 	intel_gt_retire_requests(gt); /* cleanup any wedged requests */
 }

diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -177,6 +177,8 @@ struct drm_i915_private *mock_gem_device(void)
 
 	mock_uncore_init(&i915->uncore, i915);
 
+	spin_lock_init(&i915->gpu_error.lock);
+
 	i915_gem_init__mm(i915);
 	intel_gt_init_early(&i915->gt, i915);
 	atomic_inc(&i915->gt.wakeref.count); /* disable; no hw support */