[AMD Official Use Only - General]
Let's drop the following message.
+ dev_info(adev->dev, "%ld uncorrectable hardware errors and "
+ "%ld deferred hardware errors detected in UMC block\n",
+ err_data->ue_count, err_data->de_count);
With that fixed, the series is
Reviewed-by: Hawking Zhang <Hawking.Zhang@xxxxxxx>
Regards,
Hawking
-----Original Message-----
From: amd-gfx <amd-gfx-bounces@xxxxxxxxxxxxxxxxxxxxx> On Behalf Of Candice Li
Sent: Wednesday, January 10, 2024 16:39
To: amd-gfx@xxxxxxxxxxxxxxxxxxxxx
Cc: Li, Candice <Candice.Li@xxxxxxx>
Subject: [PATCH 2/2] drm/amdgpu: Do bad page retirement for deferred errors
Needs to do bad page retirement for deferred errors.
Signed-off-by: Candice Li <candice.li@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index 848df7acdd3210..df61df7e9b155f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -93,6 +93,7 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
int ret = 0;
+ unsigned long err_count;
kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
ret = amdgpu_dpm_get_ecc_info(adev, (void *)&(con->umc_ecc)); @@ -147,16 +148,17 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
}
/* only uncorrectable error needs gpu reset */
- if (err_data->ue_count) {
- dev_info(adev->dev, "%ld uncorrectable hardware errors "
- "detected in UMC block\n",
- err_data->ue_count);
+ if (err_data->ue_count || err_data->de_count) {
+ dev_info(adev->dev, "%ld uncorrectable hardware errors and "
+ "%ld deferred hardware errors detected in UMC block\n",
+ err_data->ue_count, err_data->de_count);
+ err_count = err_data->ue_count + err_data->de_count;
if ((amdgpu_bad_page_threshold != 0) &&
err_data->err_addr_cnt) {
amdgpu_ras_add_bad_pages(adev, err_data->err_addr,
err_data->err_addr_cnt);
- amdgpu_ras_save_bad_pages(adev, &(err_data->ue_count));
+ amdgpu_ras_save_bad_pages(adev, &err_count);
amdgpu_dpm_send_hbm_bad_pages_num(adev, con->eeprom_control.ras_num_recs);
--
2.25.1
