drm/amdgpu: break driver init process when it's bad GPU(v5)

When retrieving bad gpu tag from eeprom, GPU init should
fail as the GPU needs to be retired for further check.

v2: Fix spelling typo, correct the condition to detect
    bad gpu tag and refine error message.

v3: Refine function argument name.

v4: Fix missing check of returning value of i2c
    initialization error case.

v5: Use dev_err to print PCI information in dmesg instead
    of DRM_ERROR.

Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -2055,13 +2055,19 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	 * it should be called after amdgpu_device_ip_hw_init_phase2  since
 	 * for some ASICs the RAS EEPROM code relies on SMU fully functioning
 	 * for I2C communication which only true at this point.
-	 * recovery_init may fail, but it can free all resources allocated by
+	 *
-	 * itself and its failure should not stop amdgpu init process.
+	 * amdgpu_ras_recovery_init may fail, but the upper only cares the
+	 * failure from bad gpu situation and stop amdgpu init process
+	 * accordingly. For other failed cases, it will still release all
+	 * the resource and print error message, rather than returning one
+	 * negative value to upper level.
 	 *
 	 * Note: theoretically, this should be called before all vram allocations
 	 * to protect retired page from abusing
 	 */
-	amdgpu_ras_recovery_init(adev);
+	r = amdgpu_ras_recovery_init(adev);
+	if (r)
+		goto init_failed;
 
 	if (adev->gmc.xgmi.num_physical_nodes > 1)
 		amdgpu_xgmi_add_device(adev);

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

@@ -1821,6 +1821,7 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_err_handler_data **data;
 	uint32_t max_eeprom_records_len = 0;
+	bool exc_err_limit = false;
 	int ret;
 
 	if (con)
@@ -1842,8 +1843,12 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 	max_eeprom_records_len = amdgpu_ras_eeprom_get_record_max_length();
 	amdgpu_ras_validate_threshold(adev, max_eeprom_records_len);
 
-	ret = amdgpu_ras_eeprom_init(&con->eeprom_control);
+	ret = amdgpu_ras_eeprom_init(&con->eeprom_control, &exc_err_limit);
-	if (ret)
+	/*
+	 * This calling fails when exc_err_limit is true or
+	 * ret != 0.
+	 */
+	if (exc_err_limit || ret)
 		goto free;
 
 	if (con->eeprom_control.num_recs) {
@@ -1867,6 +1872,15 @@ free:
 out:
 	dev_warn(adev->dev, "Failed to initialize ras recovery!\n");
 
+	/*
+	 * Except error threshold exceeding case, other failure cases in this
+	 * function would not fail amdgpu driver init.
+	 */
+	if (!exc_err_limit)
+		ret = 0;
+	else
+		ret = -EINVAL;
+
 	return ret;
 }
 

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

@@ -241,7 +241,8 @@ int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control)
 
 }
 
-int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
+int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
+			bool *exceed_err_limit)
 {
 	int ret = 0;
 	struct amdgpu_device *adev = to_amdgpu_device(control);
@@ -254,6 +255,8 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 			.buf	= buff,
 	};
 
+	*exceed_err_limit = false;
+
 	/* Verify i2c adapter is initialized */
 	if (!adev->pm.smu_i2c.algo)
 		return -ENOENT;
@@ -282,6 +285,11 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 		DRM_DEBUG_DRIVER("Found existing EEPROM table with %d records",
 				 control->num_recs);
 
+	} else if ((hdr->header == EEPROM_TABLE_HDR_BAD) &&
+			(amdgpu_bad_page_threshold != 0)) {
+		*exceed_err_limit = true;
+		dev_err(adev->dev, "Exceeding the bad_page_threshold parameter, "
+				"disabling the GPU.\n");
 	} else {
 		DRM_INFO("Creating new EEPROM table");
 

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

@@ -76,7 +76,8 @@ struct eeprom_table_record {
 	unsigned char mcumc_id;
 }__attribute__((__packed__));
 
-int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control);
+int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
+			bool *exceed_err_limit);
 int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control);
 
 int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,