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: add RAS poison handling for MCA

Browse source 
For MCA poison, if unmap queue fails, only gpu reset should be
triggered without page retirement handling, MCA notifier will do it.

v2: handle MCA poison consumption in umc_poison_handler directly.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Tao Zhou 2022-10-17 18:31:20 +08:00 • committed by Alex Deucher
parent 24b822928b
commit ae45a18b80
1 changed files with 20 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

31
drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
View file

@ -169,19 +169,28 @@ int amdgpu_umc_poison_handler(struct amdgpu_device *adev,
void *ras_error_status,
bool reset)
{
int ret;
struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
struct ras_common_if head = {
.block = AMDGPU_RAS_BLOCK__UMC,
};
struct ras_manager *obj = amdgpu_ras_find_obj(adev, &head);
int ret = AMDGPU_RAS_SUCCESS;
ret =
amdgpu_umc_do_page_retirement(adev, ras_error_status, NULL, reset);
if (!adev->gmc.xgmi.connected_to_cpu) {
struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
struct ras_common_if head = {
.block = AMDGPU_RAS_BLOCK__UMC,
};
struct ras_manager *obj = amdgpu_ras_find_obj(adev, &head);
if (ret == AMDGPU_RAS_SUCCESS && obj) {
obj->err_data.ue_count += err_data->ue_count;
obj->err_data.ce_count += err_data->ce_count;
ret =
amdgpu_umc_do_page_retirement(adev, ras_error_status, NULL, reset);
if (ret == AMDGPU_RAS_SUCCESS && obj) {
obj->err_data.ue_count += err_data->ue_count;
obj->err_data.ce_count += err_data->ce_count;
}
} else if (reset) {
/* MCA poison handler is only responsible for GPU reset,
* let MCA notifier do page retirement.
*/
kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
amdgpu_ras_reset_gpu(adev);
}
return ret;