public-mirrors/linux
1
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-08-05 16:54:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

drm/amdgpu: check recovery status of xgmi hive in ras_reset_error_count

Browse source 
Handle xgmi hive case.

Suggested-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Stanley.Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Tao Zhou 2023-10-30 20:44:37 +08:00 • committed by Alex Deucher
parent 88e5c8f874
commit 18eae367cb
1 changed files with 10 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
View file

@ -1222,6 +1222,8 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev,
struct amdgpu_ras_block_object *block_obj = amdgpu_ras_get_ras_block(adev, block, 0);
struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
struct amdgpu_hive_info *hive;
int hive_ras_recovery = 0;
if (!block_obj || !block_obj->hw_ops) {
dev_dbg_once(adev->dev, "%s doesn't config RAS function\n",
@ -1233,8 +1235,15 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev,
!amdgpu_ras_get_mca_debug_mode(adev))
return -EOPNOTSUPP;
hive = amdgpu_get_xgmi_hive(adev);
if (hive) {
hive_ras_recovery = atomic_read(&hive->ras_recovery);
amdgpu_put_xgmi_hive(hive);
}
/* skip ras error reset in gpu reset */
if ((amdgpu_in_reset(adev) || atomic_read(&ras->in_recovery)) &&
if ((amdgpu_in_reset(adev) || atomic_read(&ras->in_recovery) ||
hive_ras_recovery) &&
mca_funcs && mca_funcs->mca_set_debug_mode)
return -EOPNOTSUPP;