Ras error occurs while gpu recovery. We can not add its list head
to two lists at same time.
Signed-off-by: xinhui pan <xinhui....@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 18 +++++++-----------
1 file changed, 7 insertions(+), 11 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 68b82f7b0b80..d753c38c3b1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1449,20 +1449,16 @@ static void amdgpu_ras_do_recovery(struct work_struct
*work)
container_of(work, struct amdgpu_ras, recovery_work);
struct amdgpu_device *remote_adev = NULL;
struct amdgpu_device *adev = ras->adev;
- struct list_head device_list, *device_list_handle = NULL;
struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, false);
/* Build list of devices to query RAS related errors */
- if (hive && adev->gmc.xgmi.num_physical_nodes > 1)
- device_list_handle = &hive->device_list;
- else {
- INIT_LIST_HEAD(&device_list);
- list_add_tail(&adev->gmc.xgmi.head, &device_list);
- device_list_handle = &device_list;
- }
-
- list_for_each_entry(remote_adev, device_list_handle, gmc.xgmi.head) {
- amdgpu_ras_log_on_err_counter(remote_adev);
+ if (hive && adev->gmc.xgmi.num_physical_nodes > 1) {
+ list_for_each_entry(remote_adev, &hive->device_list,
+ gmc.xgmi.head) {
+ amdgpu_ras_log_on_err_counter(remote_adev);
+ }
+ } else {
+ amdgpu_ras_log_on_err_counter(adev);
}
if (amdgpu_device_should_recover_gpu(ras->adev))
--
2.17.1
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
