diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c | 48 |
1 files changed, 26 insertions, 22 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index e629156173d3..eadc9526d33f 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -302,6 +302,7 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device uint32_t bif_doorbell_intr_cntl; struct ras_manager *obj = amdgpu_ras_find_obj(adev, adev->nbio.ras_if); struct ras_err_data err_data = {0, 0, 0, NULL}; + struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL); if (REG_GET_FIELD(bif_doorbell_intr_cntl, @@ -312,28 +313,31 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device RAS_CNTLR_INTERRUPT_CLEAR, 1); WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl); - /* - * clear error status after ras_controller_intr according to - * hw team and count ue number for query - */ - nbio_v7_4_query_ras_error_count(adev, &err_data); - - /* logging on error counter and printing for awareness */ - obj->err_data.ue_count += err_data.ue_count; - obj->err_data.ce_count += err_data.ce_count; - - if (err_data.ce_count) - dev_info(adev->dev, "%ld correctable hardware " - "errors detected in %s block, " - "no user action is needed.\n", - obj->err_data.ce_count, - adev->nbio.ras_if->name); - - if (err_data.ue_count) - dev_info(adev->dev, "%ld uncorrectable hardware " - "errors detected in %s block\n", - obj->err_data.ue_count, - adev->nbio.ras_if->name); + if (!ras->disable_ras_err_cnt_harvest) { + /* + * clear error status after ras_controller_intr + * according to hw team and count ue number + * for query + */ + nbio_v7_4_query_ras_error_count(adev, &err_data); + + /* logging on error cnt and printing for awareness */ + obj->err_data.ue_count += err_data.ue_count; + obj->err_data.ce_count += err_data.ce_count; + + if (err_data.ce_count) + dev_info(adev->dev, "%ld correctable hardware " + "errors detected in %s block, " + "no user action is needed.\n", + obj->err_data.ce_count, + adev->nbio.ras_if->name); + + if (err_data.ue_count) + dev_info(adev->dev, "%ld uncorrectable hardware " + "errors detected in %s block\n", + obj->err_data.ue_count, + adev->nbio.ras_if->name); + } dev_info(adev->dev, "RAS controller interrupt triggered " "by NBIF error\n"); |