zpcictl - Manage defective PCIe devices

7.1 LPAR mode z/VM guest

Use the zpcictl to manage PCIe devices on Linux® in LPAR mode and Linux on z/VM®. In particular, use this command to initiate recovery actions and to report defective PCIe devices to the Support Element (SE).

Note: With the smartmontools package installed, diagnostic data might be collected and sent with the recovery action. Whether diagnostic data is collected and which data is available depends on the type of PCIe device.

zpcictl syntax


1  zpcictl 
2.1 --reset-fw
2.1 --reset
2.1 --deconfigure
2.1 --report-error
2.1 <function_address>
2.1 <device_node>
Where:
--reset-fw

starts a firmware-driven device reset that triggers automatic recovery and reports an error to the Support Element (SE).

--reset
disruptively resets the device and reports an error to the Support Element (SE). Use this reset option only if automatic recovery failed or if it did not succeed to restore regular operations of the device and manual intervention is required.

This reset method includes a controlled shutdown and a subsequent re-enabling of the device. As a result, higher level interfaces such as network interfaces and block devices are destroyed and re-created. Manual configuration steps might be required to re-integrate the device, for example, in bonded interfaces or software RAIDs.

--deconfigure
deconfigures the device to prepare for any repair action.
--report-error
reports the device error to the SE.
<function_address>
the PCI function address of the device, for example, 0000:00:00.0.
<device_node>
a device node that represents the device, for example, /dev/nvme0.
-h or --help
displays help information for the command. To view the man page, enter man zpcictl.
-v or --version
displays version information.

Examples

  • In this example, firmware-driven recovery is triggered for a PCIe device with function address 0000:00:00.0.
    # zpcictl --reset-fw 0000:00:00.0
  • In this example, an error is reported for a PCIe device with function address 0000:00:00.0.
    # zpcictl --report-error 0000:00:00.0