drm/amdgpu: Log UE corrected by replay as correctable error

Support replay mode where UE could be converted to CE.

Signed-off-by: Candice Li <candice.li@amd.com>
Reviewed-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:
Candice Li 2023-10-18 15:16:39 +08:00 committed by Alex Deucher
parent 207430b76a
commit afcf949cf3

View file

@ -105,7 +105,9 @@ static void umc_v12_0_query_correctable_error_count(struct amdgpu_device *adev,
RREG64_PCIE_EXT((mc_umc_status_addr + umc_reg_offset) * 4);
if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)
(REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1 ||
(REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 &&
REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UC) == 0)))
*error_count += 1;
}
@ -125,7 +127,6 @@ static void umc_v12_0_query_uncorrectable_error_count(struct amdgpu_device *adev
if ((REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) &&
(REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1 ||
REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 ||
REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, PCC) == 1 ||
REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UC) == 1 ||
REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, TCC) == 1))
@ -293,7 +294,7 @@ static int umc_v12_0_query_error_address(struct amdgpu_device *adev,
/* calculate error address if ue error is detected */
if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, AddrV) == 1 &&
REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) {
REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UC) == 1) {
mc_umc_addrt0 =
SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_ADDRT0);