diff options
| author | Hawking Zhang <Hawking.Zhang@amd.com> | 2021-03-08 20:43:15 +0800 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2021-04-09 16:50:56 -0400 |
| commit | 3f903560d1f0a42575fc7b14608004291772572a (patch) | |
| tree | 16263bca2e69d58dc424b1a75e49cedd5b60fbcc /drivers/gpu/drm/amd/amdgpu/umc_v6_7.c | |
| parent | 1696bf35896b7805499c3dfe32e94ecd6a2ae08b (diff) | |
| download | linux-3f903560d1f0a42575fc7b14608004291772572a.tar.bz2 | |
drm/amdgpu: add helper funtion to query umc ras error
Add helper functions to query correctable and
uncorrectable umc ras error.
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: John Clements <John.Clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/umc_v6_7.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/umc_v6_7.c | 70 |
1 files changed, 70 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c index 37aa1cf6b2ef..05fec10b1ed9 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c @@ -24,6 +24,76 @@ #include "amdgpu_ras.h" #include "amdgpu.h" +#include "umc/umc_6_7_0_offset.h" +#include "umc/umc_6_7_0_sh_mask.h" + +static void umc_v6_7_query_correctable_error_count(struct amdgpu_device *adev, + uint32_t umc_reg_offset, + unsigned long *error_count) +{ + uint32_t ecc_err_cnt_sel, ecc_err_cnt_sel_addr; + uint32_t ecc_err_cnt, ecc_err_cnt_addr; + uint64_t mc_umc_status; + uint32_t mc_umc_status_addr; + + /* UMC 6_1_1 registers */ + ecc_err_cnt_sel_addr = + SOC15_REG_OFFSET(UMC, 0, regUMCCH0_0_EccErrCntSel); + ecc_err_cnt_addr = + SOC15_REG_OFFSET(UMC, 0, regUMCCH0_0_EccErrCnt); + mc_umc_status_addr = + SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_STATUST0); + + /* select the lower chip and check the error count */ + ecc_err_cnt_sel = RREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4); + ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel, + EccErrCntCsSel, 0); + WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel); + + ecc_err_cnt = RREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4); + *error_count += + (REG_GET_FIELD(ecc_err_cnt, UMCCH0_0_EccErrCnt, EccErrCnt) - + UMC_V6_7_CE_CNT_INIT); + + /* select the higher chip and check the err counter */ + ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel, + EccErrCntCsSel, 1); + WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel); + + ecc_err_cnt = RREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4); + *error_count += + (REG_GET_FIELD(ecc_err_cnt, UMCCH0_0_EccErrCnt, EccErrCnt) - + UMC_V6_7_CE_CNT_INIT); + + /* check for SRAM correctable error + MCUMC_STATUS is a 64 bit register */ + mc_umc_status = RREG64_PCIE((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) + *error_count += 1; +} + +static void umc_v6_7_querry_uncorrectable_error_count(struct amdgpu_device *adev, + uint32_t umc_reg_offset, + unsigned long *error_count) +{ + uint64_t mc_umc_status; + uint32_t mc_umc_status_addr; + + mc_umc_status_addr = + SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_STATUST0); + + /* check the MCUMC_STATUS */ + mc_umc_status = RREG64_PCIE((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, 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)) + *error_count += 1; +} + const struct amdgpu_umc_funcs umc_v6_7_funcs = { .ras_late_init = amdgpu_umc_ras_late_init, }; |