[background] when unloading amdgpu driver right after running a
workload, drain_workqueue is causing "Fence fallback timer
expired on ring sdma0.0". Under sriov, this issue will cause sriov
full access timeout and a reset happening.
move drain_workqueue before shutdown is set to allow ih process and
before enter full access under sriov to avoid full access time cost.
Signed-off-by: Victor Zhao <Victor.Zhao@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index da06705f0026..f06e1f408f20 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4531,6 +4531,9 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
{
dev_info(adev->dev, "amdgpu: finishing device.\n");
flush_delayed_work(&adev->delayed_init_work);
+
+ if (adev->mman.initialized)
+ drain_workqueue(adev->mman.bdev.wq);
adev->shutdown = true;
/* make sure IB test finished before entering exclusive mode
@@ -4551,9 +4554,6 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
}
amdgpu_fence_driver_hw_fini(adev);
- if (adev->mman.initialized)
- drain_workqueue(adev->mman.bdev.wq);
-
if (adev->pm.sysfs_initialized)
amdgpu_pm_sysfs_fini(adev);
if (adev->ucode_sysfs_en)
--
2.34.1
