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

commit 76903b96adbfbb38b049765add21e02e44c387a5 upstream.

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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 8c42d54c2e26ad56ce7d0c7873128f466e60b801..f5b79dd92d3c9a9ee46b0db51c14b47cdb33b0bd 100644 (file)
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -220,6 +220,7 @@ 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 ffd5534e301cb035dcf75884603f074adc1be45f..9582b65586eeb5b6c91a87774126ab6c7220c2b4 100644 (file)
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1356,6 +1356,7 @@ 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 22bd6c2c2740b0748dd8413efd22547bfe7493bf..bf7b20ec53dd9357cf82f00877f952c78ed8c2ca 100644 (file)
--- 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