drm/amdgpu: avoid over-handle of fence driver fini in s3 test (v2)

In amdgpu_fence_driver_hw_fini, no need to call drm_sched_fini to stop
scheduler in s3 test, otherwise, fence related failure will arrive
after resume. To fix this and for a better clean up, move drm_sched_fini
from fence_hw_fini to fence_sw_fini, as it's part of driver shutdown, and
should never be called in hw_fini.

v2: rename amdgpu_fence_driver_init to amdgpu_fence_driver_sw_init,
to keep sw_init and sw_fini paired.

Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1668
Fixes: 8d35a2596164c1 ("drm/amdgpu: adjust fence driver enable sequence")
Suggested-by: Christian König <christian.koenig@amd.com>
Tested-by: Mike Lothian <mike@fireburn.co.uk>
Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6ca9fe54ee0af42429af49d52b58003ad80a71fb..d7cc45e68dbdaa67e9c781fed78a023c80d0f37c 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3647,9 +3647,9 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 
 fence_driver_init:
        /* Fence driver */
-       r = amdgpu_fence_driver_init(adev);
+       r = amdgpu_fence_driver_sw_init(adev);
        if (r) {
-               dev_err(adev->dev, "amdgpu_fence_driver_init failed\n");
+               dev_err(adev->dev, "amdgpu_fence_driver_sw_init failed\n");
                amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_FENCE_INIT_FAIL, 0, 0);
                goto failed;
        }
@@ -3989,7 +3989,6 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
        }
        amdgpu_fence_driver_hw_init(adev);
 
-
        r = amdgpu_device_ip_late_init(adev);
        if (r)
                return r;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 0b1c48590c436a8e12b345394fe8cce5bf857ba2..6ed53669f3e0183c4dcdc0096c636af87b6aa88f 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -498,7 +498,7 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
 }
 
 /**
- * amdgpu_fence_driver_init - init the fence driver
+ * amdgpu_fence_driver_sw_init - init the fence driver
  * for all possible rings.
  *
  * @adev: amdgpu device pointer
@@ -509,13 +509,13 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
  * amdgpu_fence_driver_start_ring().
  * Returns 0 for success.
  */
-int amdgpu_fence_driver_init(struct amdgpu_device *adev)
+int amdgpu_fence_driver_sw_init(struct amdgpu_device *adev)
 {
        return 0;
 }
 
 /**
- * amdgpu_fence_driver_fini - tear down the fence driver
+ * amdgpu_fence_driver_hw_fini - tear down the fence driver
  * for all possible rings.
  *
  * @adev: amdgpu device pointer
@@ -531,8 +531,7 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev)
 
                if (!ring || !ring->fence_drv.initialized)
                        continue;
-               if (!ring->no_scheduler)
-                       drm_sched_fini(&ring->sched);
+
                /* You can't wait for HW to signal if it's gone */
                if (!drm_dev_is_unplugged(&adev->ddev))
                        r = amdgpu_fence_wait_empty(ring);
@@ -560,6 +559,9 @@ void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev)
                if (!ring || !ring->fence_drv.initialized)
                        continue;
 
+               if (!ring->no_scheduler)
+                       drm_sched_fini(&ring->sched);
+
                for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
                        dma_fence_put(ring->fence_drv.fences[j]);
                kfree(ring->fence_drv.fences);

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 27adffa7658d613875810d6f85e94787c6f47f4c..9c11ced4312c84bb45166ed819cfcf45534ef52d 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -106,7 +106,6 @@ struct amdgpu_fence_driver {
        struct dma_fence                **fences;
 };
 
-int amdgpu_fence_driver_init(struct amdgpu_device *adev);
 void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring);
 
 int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
@@ -115,9 +114,10 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
 int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
                                   struct amdgpu_irq_src *irq_src,
                                   unsigned irq_type);
+void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev);
 void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev);
+int amdgpu_fence_driver_sw_init(struct amdgpu_device *adev);
 void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev);
-void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev);
 int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **fence,
                      unsigned flags);
 int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s,