drm/amdgpu: change default behavior of bad_page_threshold parameter

Ignore ras umc bad page threshold by default, GPU initialization won't
be stopped in this mode.

v2: refine the description of bad_page_threshold.

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

Author: Tao Zhou

drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c

@@ -924,7 +924,7 @@ 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, -2 = ignore bad page threshold)");
+MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = ignore threshold (default value), 0 = disable bad page retirement, -2 = driver sets 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+)");

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c

@@ -2196,11 +2196,12 @@ static void amdgpu_ras_validate_threshold(struct amdgpu_device *adev,
 	/*
 	 * Justification of value bad_page_cnt_threshold in ras structure
 	 *
-	 * Generally, -1 <= amdgpu_bad_page_threshold <= max record length
-	 * in eeprom, and introduce two scenarios accordingly.
+	 * Generally, 0 <= amdgpu_bad_page_threshold <= max record length
+	 * in eeprom or amdgpu_bad_page_threshold == -2, introduce two
+	 * scenarios accordingly.
 	 *
 	 * Bad page retirement enablement:
-	 *    - If amdgpu_bad_page_threshold = -1,
+	 *    - If amdgpu_bad_page_threshold = -2,
 	 *      bad_page_cnt_threshold = typical value by formula.
 	 *
 	 *    - When the value from user is 0 < amdgpu_bad_page_threshold <

drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c

@@ -1191,8 +1191,8 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
 		} else {
 			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.");
+			if (amdgpu_bad_page_threshold == -1) {
+				dev_warn(adev->dev, "GPU will be initialized due to bad_page_threshold = -1.");
 				res = 0;
 			} else {
 				*exceed_err_limit = true;