summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu.h1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c15
3 files changed, 13 insertions, 5 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index d58e37fd01f4..b85b67a88a3d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -205,6 +205,7 @@ extern struct amdgpu_mgpu_info mgpu_info;
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;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index c718fb5f3f8a..4cefe867ccf2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -877,7 +877,7 @@ module_param_named(reset_method, amdgpu_reset_method, int, 0444);
* 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+)");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 3978152e5ccc..05117eda105b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -1105,11 +1105,18 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
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");