diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 31 |
1 files changed, 16 insertions, 15 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index 83b54efcaa877..09a6f8bc1a5a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -727,11 +727,9 @@ amdgpu_ras_eeprom_append_table(struct amdgpu_ras_eeprom_control *control, - control->ras_fri) % control->ras_max_record_count; - if (control->rec_type == AMDGPU_RAS_EEPROM_REC_PA) - control->ras_num_bad_pages = control->ras_num_recs; - else - control->ras_num_bad_pages = - control->ras_num_recs * adev->umc.retire_unit; + control->ras_num_mca_recs += num; + control->ras_num_bad_pages += num * adev->umc.retire_unit; + Out: kfree(buf); return res; @@ -749,7 +747,7 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control) /* Modify the header if it exceeds. */ if (amdgpu_bad_page_threshold != 0 && - control->ras_num_bad_pages >= ras->bad_page_cnt_threshold) { + control->ras_num_bad_pages > ras->bad_page_cnt_threshold) { dev_warn(adev->dev, "Saved bad pages %d reaches threshold value %d\n", control->ras_num_bad_pages, ras->bad_page_cnt_threshold); @@ -808,7 +806,7 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control) */ if (amdgpu_bad_page_threshold != 0 && control->tbl_hdr.version == RAS_TABLE_VER_V2_1 && - control->ras_num_bad_pages < ras->bad_page_cnt_threshold) + control->ras_num_bad_pages <= ras->bad_page_cnt_threshold) control->tbl_rai.health_percent = ((ras->bad_page_cnt_threshold - control->ras_num_bad_pages) * 100) / ras->bad_page_cnt_threshold; @@ -852,6 +850,7 @@ int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control, { struct amdgpu_device *adev = to_amdgpu_device(control); int res, i; + uint64_t nps = AMDGPU_NPS1_PARTITION_MODE; if (!__is_ras_eeprom_supported(adev)) return 0; @@ -865,9 +864,12 @@ int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control, return -EINVAL; } + if (adev->gmc.gmc_funcs->query_mem_partition_mode) + nps = adev->gmc.gmc_funcs->query_mem_partition_mode(adev); + /* set the new channel index flag */ for (i = 0; i < num; i++) - record[i].retired_page |= UMC_CHANNEL_IDX_V2; + record[i].retired_page |= (nps << UMC_NPS_SHIFT); mutex_lock(&control->ras_tbl_mutex); @@ -881,7 +883,7 @@ int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control, /* clear channel index flag, the flag is only saved on eeprom */ for (i = 0; i < num; i++) - record[i].retired_page &= ~UMC_CHANNEL_IDX_V2; + record[i].retired_page &= ~(nps << UMC_NPS_SHIFT); return res; } @@ -1392,6 +1394,8 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control) } control->ras_fri = RAS_OFFSET_TO_INDEX(control, hdr->first_rec_offset); + control->ras_num_mca_recs = 0; + control->ras_num_pa_recs = 0; return 0; } @@ -1412,11 +1416,8 @@ int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control) if (!__get_eeprom_i2c_addr(adev, control)) return -EINVAL; - if (control->rec_type == AMDGPU_RAS_EEPROM_REC_PA) - control->ras_num_bad_pages = control->ras_num_recs; - else - control->ras_num_bad_pages = - control->ras_num_recs * adev->umc.retire_unit; + control->ras_num_bad_pages = control->ras_num_pa_recs + + control->ras_num_mca_recs * adev->umc.retire_unit; if (hdr->header == RAS_TABLE_HDR_VAL) { DRM_DEBUG_DRIVER("Found existing EEPROM table with %d records", @@ -1455,7 +1456,7 @@ int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control) res); return -EINVAL; } - if (ras->bad_page_cnt_threshold > control->ras_num_bad_pages) { + if (ras->bad_page_cnt_threshold >= control->ras_num_bad_pages) { /* This means that, the threshold was increased since * the last time the system was booted, and now, * ras->bad_page_cnt_threshold - control->num_recs > 0, |