[Intel-gfx] [CI] drm/i915: Mark GEM wedged right after marking device unplugged

Chris Wilson chris at chris-wilson.co.uk
Sat Apr 6 10:40:34 UTC 2019


From: Janusz Krzysztofik <janusz.krzysztofik at linux.intel.com>

As soon as a device is considered unplugged, not only prevent pending
users from accessing the device structures but also cancel all their
pending requests so all consumed resources can be cleaned up as soon
as possible.

Suggested-by: Chris Wilson <chris at chris-wilson.co.uk>
Signed-off-by: Janusz Krzysztofik <janusz.krzysztofik at linux.intel.com>
Reviewed-by: Chris Wilson <chris at chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.c | 7 +++++++
 drivers/gpu/drm/i915/i915_drv.h | 1 +
 2 files changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 0bbf3f5db5fc..c695b3a4deae 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1907,6 +1907,13 @@ void i915_driver_unload(struct drm_device *dev)
 
 	i915_driver_unregister(dev_priv);
 
+	/*
+	 * After unregistering the device to prevent any new users, cancel
+	 * all in-flight requests so that we can quickly unbind the active
+	 * resources.
+	 */
+	i915_gem_set_wedged(dev_priv);
+
 	/* Flush any external code that still may be under the RCU lock */
 	synchronize_rcu();
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 4af815c3c02d..b9bedfa9652d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2917,6 +2917,7 @@ static inline void i915_gem_drain_workqueue(struct drm_i915_private *i915)
 	int pass = 2;
 	do {
 		rcu_barrier();
+		i915_gem_drain_freed_objects(i915);
 		drain_workqueue(i915->wq);
 	} while (--pass);
 }
-- 
2.20.1



More information about the Intel-gfx mailing list