drm/amdgpu: querry umc error count

check umc error count in both ras querry function and
ras interrupt handler

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Dennis Li <dennis.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Hawking Zhang 2019-07-17 21:49:53 +08:00 committed by Alex Deucher
parent 5b6b35aaac
commit 939e2258ce
2 changed files with 13 additions and 1 deletions

View File

@ -588,11 +588,19 @@ int amdgpu_ras_error_query(struct amdgpu_device *adev,
struct ras_query_if *info)
{
struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head);
struct ras_err_data err_data = {0, 0};
if (!obj)
return -EINVAL;
/* TODO might read the register to read the count */
switch (info->head.block) {
case AMDGPU_RAS_BLOCK__UMC:
if (adev->umc_funcs->query_ras_error_count)
adev->umc_funcs->query_ras_error_count(adev, &err_data);
break;
default:
break;
}
info->ue_count = obj->err_data.ue_count;
info->ce_count = obj->err_data.ce_count;
@ -986,6 +994,7 @@ static void amdgpu_ras_interrupt_handler(struct ras_manager *obj)
struct ras_ih_data *data = &obj->ih_data;
struct amdgpu_iv_entry entry;
int ret;
struct ras_err_data err_data = {0, 0};
while (data->rptr != data->wptr) {
rmb();

View File

@ -245,7 +245,10 @@ static int gmc_v9_0_ecc_interrupt_state(struct amdgpu_device *adev,
static int gmc_v9_0_process_ras_data_cb(struct amdgpu_device *adev,
struct amdgpu_iv_entry *entry)
{
struct ras_err_data err_data = {0, 0};
kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
if (adev->umc_funcs->query_ras_error_count)
adev->umc_funcs->query_ras_error_count(adev, &err_data);
amdgpu_ras_reset_gpu(adev, 0);
return AMDGPU_RAS_UE;
}