drm/amdgpu: add new aca_smu_type support

Add new types to distinguish between ACA error type and smu mca type.

e.g.:
the ACA_ERROR_TYPE_DEFERRED is not matched any smu mca valid bank
channel, so add new type 'aca_smu_type' to distinguish aca error type
and smu mca type.

Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Yang Wang
2024-01-31 17:48:34 +08:00
committed by Alex Deucher
parent a43dbeaba8
commit abc3b5d21d
8 changed files with 139 additions and 94 deletions

View File

@@ -2190,24 +2190,27 @@ static const struct amdgpu_ras_block_hw_ops sdma_v4_4_2_ras_hw_ops = {
};
static int sdma_v4_4_2_aca_bank_generate_report(struct aca_handle *handle,
struct aca_bank *bank, enum aca_error_type type,
struct aca_bank *bank, enum aca_smu_type type,
struct aca_bank_report *report, void *data)
{
u64 status, misc0;
u64 misc0;
int ret;
status = bank->regs[ACA_REG_IDX_STATUS];
if ((type == ACA_ERROR_TYPE_UE &&
ACA_REG__STATUS__ERRORCODEEXT(status) == ACA_EXTERROR_CODE_FAULT) ||
(type == ACA_ERROR_TYPE_CE &&
ACA_REG__STATUS__ERRORCODEEXT(status) == ACA_EXTERROR_CODE_CE)) {
ret = aca_bank_info_decode(bank, &report->info);
if (ret)
return ret;
ret = aca_bank_info_decode(bank, &report->info);
if (ret)
return ret;
misc0 = bank->regs[ACA_REG_IDX_MISC0];
misc0 = bank->regs[ACA_REG_IDX_MISC0];
report->count[type] = ACA_REG__MISC0__ERRCNT(misc0);
switch (type) {
case ACA_SMU_TYPE_UE:
report->count[ACA_ERROR_TYPE_UE] = 1ULL;
break;
case ACA_SMU_TYPE_CE:
report->count[ACA_ERROR_TYPE_CE] = ACA_REG__MISC0__ERRCNT(misc0);
break;
default:
return -EINVAL;
}
return 0;
@@ -2217,7 +2220,7 @@ static int sdma_v4_4_2_aca_bank_generate_report(struct aca_handle *handle,
static int sdma_v4_4_2_err_codes[] = { 33, 34, 35, 36 };
static bool sdma_v4_4_2_aca_bank_is_valid(struct aca_handle *handle, struct aca_bank *bank,
enum aca_error_type type, void *data)
enum aca_smu_type type, void *data)
{
u32 instlo;