diff options
| author | Hawking Zhang <Hawking.Zhang@amd.com> | 2023-01-22 23:36:25 +0800 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2023-06-09 09:53:32 -0400 |
| commit | 00c145222b6ac93ee9926a8ef2e41dae55b97b7e (patch) | |
| tree | 7b9c1d6e215ff6bd04f5cfd182480de3e373f0db /drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c | |
| parent | a0cdb3d09332900e145fb99f52d1d571d7030183 (diff) | |
drm/amdgpu: Add query_ras_error_status for mmhub v1_8
Add query_ras_error_status callback for mmhub
v1_8. It will be used to log mmhub error status.
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c | 56 |
1 files changed, 56 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c index f40a6a9f3c6d..2923304e653a 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c @@ -700,3 +700,59 @@ static void mmhub_v1_8_reset_ras_error_count(struct amdgpu_device *adev) for_each_inst(i, inst_mask) mmhub_v1_8_inst_reset_ras_error_count(adev, i); } + +static const uint32_t mmhub_v1_8_mmea_err_status_reg[] = { + regMMEA0_ERR_STATUS, + regMMEA1_ERR_STATUS, + regMMEA2_ERR_STATUS, + regMMEA3_ERR_STATUS, + regMMEA4_ERR_STATUS, +}; + +static void mmhub_v1_8_inst_query_ras_err_status(struct amdgpu_device *adev, + uint32_t mmhub_inst) +{ + uint32_t reg_value; + uint32_t mmea_err_status_addr_dist; + uint32_t i; + + /* query mmea ras err status */ + mmea_err_status_addr_dist = regMMEA1_ERR_STATUS - regMMEA0_ERR_STATUS; + for (i = 0; i < ARRAY_SIZE(mmhub_v1_8_mmea_err_status_reg); i++) { + reg_value = RREG32_SOC15_OFFSET(MMHUB, mmhub_inst, + regMMEA0_ERR_STATUS, + i * mmea_err_status_addr_dist); + if (REG_GET_FIELD(reg_value, MMEA0_ERR_STATUS, SDP_RDRSP_STATUS) || + REG_GET_FIELD(reg_value, MMEA0_ERR_STATUS, SDP_WRRSP_STATUS) || + REG_GET_FIELD(reg_value, MMEA0_ERR_STATUS, SDP_RDRSP_DATAPARITY_ERROR)) { + dev_warn(adev->dev, + "Detected MMEA%d err in MMHUB%d, status: 0x%x\n", + i, mmhub_inst, reg_value); + } + } + + /* query mm_cane ras err status */ + reg_value = RREG32_SOC15(MMHUB, mmhub_inst, regMM_CANE_ERR_STATUS); + if (REG_GET_FIELD(reg_value, MM_CANE_ERR_STATUS, SDPM_RDRSP_STATUS) || + REG_GET_FIELD(reg_value, MM_CANE_ERR_STATUS, SDPM_WRRSP_STATUS) || + REG_GET_FIELD(reg_value, MM_CANE_ERR_STATUS, SDPM_RDRSP_DATAPARITY_ERROR)) { + dev_warn(adev->dev, + "Detected MM CANE err in MMHUB%d, status: 0x%x\n", + mmhub_inst, reg_value); + } +} + +static void mmhub_v1_8_query_ras_error_status(struct amdgpu_device *adev) +{ + uint32_t inst_mask; + uint32_t i; + + if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__MMHUB)) { + dev_warn(adev->dev, "MMHUB RAS is not supported\n"); + return; + } + + inst_mask = adev->aid_mask; + for_each_inst(i, inst_mask) + mmhub_v1_8_inst_query_ras_err_status(adev, i); +} |