drm/radeon: force fence completion only on problematic rings (v2)

Instead of resetting all fence numbers, only reset the
number of the problematic ring. Split out from a patch
from Maarten Lankhorst <maarten.lankhorst@canonical.com>

v2 (agd5f): rebase build fix
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NMaarten Lankhorst <maarten.lankhorst@canonical.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/radeon/radeon.h

@@ -371,7 +371,7 @@ 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);
+void radeon_fence_driver_force_completion(struct radeon_device *rdev, int ring);
 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);

drivers/gpu/drm/radeon/radeon_device.c

@@ -1488,7 +1488,6 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon)
 	struct drm_crtc *crtc;
 	struct drm_connector *connector;
 	int i, r;
-	bool force_completion = false;
 
 	if (dev == NULL || dev->dev_private == NULL) {
 		return -ENODEV;
@@ -1532,12 +1531,9 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon)
 		r = radeon_fence_wait_empty(rdev, i);
 		if (r) {
 			/* delay GPU reset to resume */
-			force_completion = true;
+			radeon_fence_driver_force_completion(rdev, i);
 		}
 	}
-	if (force_completion) {
-		radeon_fence_driver_force_completion(rdev);
-	}
 
 	radeon_save_bios_scratch_regs(rdev);
 
@@ -1722,8 +1718,8 @@ int radeon_gpu_reset(struct radeon_device *rdev)
 			}
 		}
 	} else {
-		radeon_fence_driver_force_completion(rdev);
 		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+			radeon_fence_driver_force_completion(rdev, i);
 			kfree(ring_data[i]);
 		}
 	}

drivers/gpu/drm/radeon/radeon_fence.c

@@ -758,7 +758,7 @@ void radeon_fence_driver_fini(struct radeon_device *rdev)
 		r = radeon_fence_wait_empty(rdev, ring);
 		if (r) {
 			/* no need to trigger GPU reset as we are unloading */
-			radeon_fence_driver_force_completion(rdev);
+			radeon_fence_driver_force_completion(rdev, ring);
 		}
 		wake_up_all(&rdev->fence_queue);
 		radeon_scratch_free(rdev, rdev->fence_drv[ring].scratch_reg);
@@ -771,19 +771,15 @@ void radeon_fence_driver_fini(struct radeon_device *rdev)
  * radeon_fence_driver_force_completion - force all fence waiter to complete
  *
  * @rdev: radeon device pointer
+ * @ring: the ring to complete
  *
  * 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)
+void radeon_fence_driver_force_completion(struct radeon_device *rdev, int ring)
 {
-	int ring;
-
-	for (ring = 0; ring < RADEON_NUM_RINGS; ring++) {
-		if (!rdev->fence_drv[ring].initialized)
-			continue;
+	if (rdev->fence_drv[ring].initialized)
 		radeon_fence_write(rdev, rdev->fence_drv[ring].sync_seq[ring], ring);
-	}
 }
 
 

drivers/gpu/drm/radeon/radeon_ib.c

@@ -269,6 +269,7 @@ int radeon_ib_ring_tests(struct radeon_device *rdev)
 
 		r = radeon_ib_test(rdev, i, ring);
 		if (r) {
+			radeon_fence_driver_force_completion(rdev, i);
 			ring->ready = false;
 			rdev->needs_reset = false;