Blob Blame History Raw
From 2ec9eeaa03ff3d2450febe661d1241542544eef5 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Thu, 11 Nov 2021 13:06:34 +0000
Subject: drm/i915: Skip error capture when wedged on init
Git-commit: 9a7fc952717ea63d13eb9d42581af52ba34c3914
Patch-mainline: v5.17-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225

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 <tvrtko.ursulin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com> # v1
Link: https://patchwork.freedesktop.org/patch/msgid/20211111130634.266098-1-tvrtko.ursulin@linux.intel.com
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/i915/gt/intel_reset.c            | 2 ++
 drivers/gpu/drm/i915/selftests/mock_gem_device.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 51b56b8e5003..0fbd6dbadce7 100644
--- 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
index 9ab3f284d1dd..d0e2e61de8d4 100644
--- 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 */
-- 
2.38.1