drm/radeon: don't leave fence blocked process on failed GPU reset

Force all fence to signal if GPU reset failed so no process get stuck
on waiting fence.

Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

3 files changed, 21 insertions, 0 deletions

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 5dc744d43d1..aae73141d63 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -225,6 +225,7 @@ struct radeon_fence {
 int radeon_fence_driver_start_ring(struct radeon_device *rdev, int ring);
 int radeon_fence_driver_init(struct radeon_device *rdev);
 void radeon_fence_driver_fini(struct radeon_device *rdev);
+void radeon_fence_driver_force_completion(struct radeon_device *rdev);
 int radeon_fence_emit(struct radeon_device *rdev, struct radeon_fence **fence, int ring);
 void radeon_fence_process(struct radeon_device *rdev, int ring);
 bool radeon_fence_signaled(struct radeon_fence *fence);
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 49b06590001..e81d6cab995 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1358,6 +1358,7 @@ retry:
                         }
                 }
         } else {
+                radeon_fence_driver_force_completion(rdev);
                 for (i = 0; i < RADEON_NUM_RINGS; ++i) {
                         kfree(ring_data[i]);
                 }
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 410a975a8ee..a9b0fa5608e 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -868,6 +868,25 @@ void radeon_fence_driver_fini(struct radeon_device *rdev)
         mutex_unlock(&rdev->ring_lock);
 }
 
+/**
+ * radeon_fence_driver_force_completion - force all fence waiter to complete
+ *
+ * @rdev: radeon device pointer
+ *
+ * In case of GPU reset failure make sure no process keep waiting on fence
+ * that will never complete.
+ */
+void radeon_fence_driver_force_completion(struct radeon_device *rdev)
+{
+        int ring;
+
+        for (ring = 0; ring < RADEON_NUM_RINGS; ring++) {
+                if (!rdev->fence_drv[ring].initialized)
+                        continue;
+                radeon_fence_write(rdev, rdev->fence_drv[ring].sync_seq[ring], ring);
+        }
+}
+
 
 /*
  * Fence debugfs