extern int amdgpu_ras_enable;
extern uint amdgpu_ras_mask;
extern int amdgpu_bad_page_threshold;
+extern bool amdgpu_ignore_bad_page_threshold;
extern struct amdgpu_watchdog_timer amdgpu_watchdog_timer;
extern int amdgpu_async_gfx_ring;
extern int amdgpu_mcbp;
* result in the GPU entering bad status when the number of total
* faulty pages by ECC exceeds the threshold value.
*/
-MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement)");
+MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement, -2 = ignore bad page threshold)");
module_param_named(bad_page_threshold, amdgpu_bad_page_threshold, int, 0444);
MODULE_PARM_DESC(num_kcq, "number of kernel compute queue user want to setup (8 if set to greater than 8 or less than 0, only affect gfx 8+)");
res = amdgpu_ras_eeprom_correct_header_tag(control,
RAS_TABLE_HDR_VAL);
} else {
- *exceed_err_limit = true;
- dev_err(adev->dev,
- "RAS records:%d exceed threshold:%d, "
- "GPU will not be initialized. Replace this GPU or increase the threshold",
+ dev_err(adev->dev, "RAS records:%d exceed threshold:%d",
control->ras_num_recs, ras->bad_page_cnt_threshold);
+ if (amdgpu_bad_page_threshold == -2) {
+ dev_warn(adev->dev, "GPU will be initialized due to bad_page_threshold = -2.");
+ res = 0;
+ } else {
+ *exceed_err_limit = true;
+ dev_err(adev->dev,
+ "RAS records:%d exceed threshold:%d, "
+ "GPU will not be initialized. Replace this GPU or increase the threshold",
+ control->ras_num_recs, ras->bad_page_cnt_threshold);
+ }
}
} else {
DRM_INFO("Creating a new EEPROM table");