drm/amdgpu: Save PA of bad pages for old asics

for old asics that do not support mca translating, we
just save PA for them

Signed-off-by: ganglxie <ganglxie@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 285e3aa2bb2f9cf03686aaff2d6c3882e82427b9..7cf8a303682811b87eeaa4bce599763da66430b0 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2836,6 +2836,13 @@ static int __amdgpu_ras_convert_rec_array_from_rom(struct amdgpu_device *adev,
 
        save_nps = (bps[0].retired_page >> UMC_NPS_SHIFT) & UMC_NPS_MASK;
 
+       /*old asics just have pa in eeprom*/
+       if (IP_VERSION_MAJ(amdgpu_ip_version(adev, UMC_HWIP, 0)) < 12) {
+               memcpy(err_data->err_addr, bps,
+                       sizeof(struct eeprom_table_record) * adev->umc.retire_unit);
+               goto out;
+       }
+
        for (i = 0; i < adev->umc.retire_unit; i++)
                bps[i].retired_page &= ~(UMC_NPS_MASK << UMC_NPS_SHIFT);
 
@@ -2858,6 +2865,7 @@ static int __amdgpu_ras_convert_rec_array_from_rom(struct amdgpu_device *adev,
                }
        }
 
+out:
        return __amdgpu_ras_restore_bad_pages(adev, err_data->err_addr, adev->umc.retire_unit);
 }
 
@@ -2981,14 +2989,24 @@ int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev,
 
        /* only new entries are saved */
        if (save_count > 0) {
-               for (i = 0; i < unit_num; i++) {
+               /*old asics only save pa to eeprom like before*/
+               if (IP_VERSION_MAJ(amdgpu_ip_version(adev, UMC_HWIP, 0)) < 12) {
                        if (amdgpu_ras_eeprom_append(control,
-                                       &data->bps[bad_page_num + i * adev->umc.retire_unit],
-                                       1)) {
+                                       &data->bps[bad_page_num], save_count)) {
                                dev_err(adev->dev, "Failed to save EEPROM table data!");
                                return -EIO;
                        }
+               } else {
+                       for (i = 0; i < unit_num; i++) {
+                               if (amdgpu_ras_eeprom_append(control,
+                                               &data->bps[bad_page_num +
+                                               i * adev->umc.retire_unit], 1)) {
+                                       dev_err(adev->dev, "Failed to save EEPROM table data!");
+                                       return -EIO;
+                               }
+                       }
                }
+
                dev_info(adev->dev, "Saved %d pages to EEPROM table.\n", save_count);
        }
 

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 09a6f8bc1a5a944ddab77126b1327c32ceea11c4..3597ecd9baca34ceacc1120397d672c8c214a0a4 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -727,9 +727,14 @@ amdgpu_ras_eeprom_append_table(struct amdgpu_ras_eeprom_control *control,
                                     - control->ras_fri)
                % control->ras_max_record_count;
 
-       control->ras_num_mca_recs += num;
-       control->ras_num_bad_pages += num * adev->umc.retire_unit;
+       /*old asics only save pa to eeprom like before*/
+       if (IP_VERSION_MAJ(amdgpu_ip_version(adev, UMC_HWIP, 0)) < 12)
+               control->ras_num_pa_recs += num;
+       else
+               control->ras_num_mca_recs += num;
 
+       control->ras_num_bad_pages = control->ras_num_pa_recs +
+                               control->ras_num_mca_recs * adev->umc.retire_unit;
 Out:
        kfree(buf);
        return res;