drm/amd/amdgpu: add error handling to amdgpu_virt_read_pf2vf_data

[ Upstream commit 64dcf2f01d59cf9fad19b1a387bd39736a8f4d69 ]

[Why]
when vram lost happened in guest, try to write vram can lead to
kernel stuck.

[How]
When the readback data is invalid, don't do write work, directly
reschedule a new work.

Signed-off-by: Jingwen Chen <Jingwen.Chen2@amd.com>
Reviewed-by: Monk Liu<monk.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index d0aea5e..e7678ba 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -558,10 +558,14 @@ static int amdgpu_virt_write_vf2pf_data(struct amdgpu_device *adev)
 void amdgpu_virt_update_vf2pf_work_item(struct work_struct *work)
 {
        struct amdgpu_device *adev = container_of(work, struct amdgpu_device, virt.vf2pf_work.work);
+       int ret;
 
-       amdgpu_virt_read_pf2vf_data(adev);
+       ret = amdgpu_virt_read_pf2vf_data(adev);
+       if (ret)
+               goto out;
        amdgpu_virt_write_vf2pf_data(adev);
 
+out:
        schedule_delayed_work(&(adev->virt.vf2pf_work), adev->virt.vf2pf_update_interval_ms);
 }