Linux PCI Error Recovery

Documentation/PCI/pci-error-recovery.txt

link_rest沒人用，倒是系統有提供一個reset_link

include/linux/pci.h

/* PCI bus error event callbacks */
struct pci_error_handlers {
 /* PCI bus error detected on this device */
 pci_ers_result_t (*error_detected)(struct pci_dev *dev,
        enum pci_channel_state error);

 /* MMIO has been re-enabled, but not DMA */
 pci_ers_result_t (*mmio_enabled)(struct pci_dev *dev);

 /* PCI Express link has been reset */
 pci_ers_result_t (* link_reset)(struct pci_dev *dev);

 /* PCI slot has been reset */
 pci_ers_result_t (*slot_reset)(struct pci_dev *dev);

 /* Device driver may resume normal operations */
 void (*resume)(struct pci_dev *dev);
};

drivers/pci/pcie/aer/aerdrv_core.c

/**
 * do_recovery - handle nonfatal/fatal error recovery process
 * @aerdev: pointer to a pcie_device data structure of root port
 * @dev: pointer to a pci_dev data structure of agent detecting an error
 * @severity: error severity type
 *
 * Invoked when an error is nonfatal/fatal. Once being invoked, broadcast
 * error detected message to all downstream drivers within a hierarchy in
 * question and return the returned code.
 */
static pci_ers_result_t do_recovery(struct pcie_device *aerdev,
  struct pci_dev *dev,
  int severity)
{
 pci_ers_result_t status, result = PCI_ERS_RESULT_RECOVERED;
 enum pci_channel_state state;

 if (severity == AER_FATAL)
  state = pci_channel_io_frozen;
 else
  state = pci_channel_io_normal;

 status = broadcast_error_message(dev,
   state,
   "error_detected",
   report_error_detected);

 if (severity == AER_FATAL) {
  result =  reset_link(aerdev, dev);
  if (result != PCI_ERS_RESULT_RECOVERED) {
   /* TODO: Should panic here? */
   return result;
  }
 }

 if (status == PCI_ERS_RESULT_CAN_RECOVER)
  status = broadcast_error_message(dev,
    state,
    "mmio_enabled",
    report_mmio_enabled);

 if (status == PCI_ERS_RESULT_NEED_RESET) {
  /*
   * TODO: Should call platform-specific
   * functions to reset slot before calling
   * drivers' slot_reset callbacks?
   */
  status = broadcast_error_message(dev,
    state,
    "slot_reset",
    report_slot_reset);
 }

 if (status == PCI_ERS_RESULT_RECOVERED)
  broadcast_error_message(dev,
    state,
    "resume",
    report_resume);

 return status;
}