drm/i915: disable interrupts earlier in the driver unload code
Our rps code relies on the interrupts being off to prevent re-arming
of the work items at inopportune moments.
Also drop the redundant cancel_work for the main rps work,
disable_gt_powersave already takes care of that.
Finally add a WARN_ON to ensure we obey that piece of ordering
constraint. Long term I want to lock down the setup/teardown code in a
similar way to how we painstakingly check modeset sequence constraints
already.
v2: Disable polling after hpd handling is shut down - since Egbert's
hpd irq storm handling the hotplug work can re-arm the polling
handler. Spotted by Jani Nikula.
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 74156e2..988e543 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9530,12 +9530,23 @@
struct drm_crtc *crtc;
struct intel_crtc *intel_crtc;
+ /*
+ * Interrupts and polling as the first thing to avoid creating havoc.
+ * Too much stuff here (turning of rps, connectors, ...) would
+ * experience fancy races otherwise.
+ */
+ drm_irq_uninstall(dev);
+ cancel_work_sync(&dev_priv->hotplug_work);
+ /*
+ * Due to the hpd irq storm handling the hotplug work can re-arm the
+ * poll handlers. Hence disable polling after hpd handling is shut down.
+ */
drm_kms_helper_poll_fini(dev);
+
mutex_lock(&dev->struct_mutex);
intel_unregister_dsm_handler();
-
list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
/* Skip inactive CRTCs */
if (!crtc->fb)
@@ -9553,12 +9564,6 @@
mutex_unlock(&dev->struct_mutex);
- /* Disable the irq before mode object teardown, for the irq might
- * enqueue unpin/hotplug work. */
- drm_irq_uninstall(dev);
- cancel_work_sync(&dev_priv->hotplug_work);
- cancel_work_sync(&dev_priv->rps.work);
-
/* flush any delayed tasks or pending work */
flush_scheduled_work();