scsi: qedi: Add support for handling PCIe errors

The error recovery is handled by management firmware (MFW) with the help of
qed/qedi drivers. Upon detecting errors, driver informs MFW about this
event which in turn starts a recovery process. MFW sends ERROR_RECOVERY
notification to the driver which performs the required cleanup/recovery
from the driver side.

Link: https://lore.kernel.org/r/20200908095657.26821-9-mrangankar@marvell.comSigned-off-by: Manish Rangankar <mrangankar@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/qedi/qedi_main.c

@@ -2390,6 +2390,25 @@ static int qedi_setup_boot_info(struct qedi_ctx *qedi)
 	return -ENOMEM;
 }
 
+static pci_ers_result_t qedi_io_error_detected(struct pci_dev *pdev,
+					       pci_channel_state_t state)
+{
+	struct qedi_ctx *qedi = pci_get_drvdata(pdev);
+
+	QEDI_ERR(&qedi->dbg_ctx, "%s: PCI error detected [%d]\n",
+		 __func__, state);
+
+	if (test_and_set_bit(QEDI_IN_RECOVERY, &qedi->flags)) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "Recovery already in progress.\n");
+		return PCI_ERS_RESULT_NONE;
+	}
+
+	qedi_ops->common->recovery_process(qedi->cdev);
+
+	return PCI_ERS_RESULT_CAN_RECOVER;
+}
+
 static void __qedi_remove(struct pci_dev *pdev, int mode)
 {
 	struct qedi_ctx *qedi = pci_get_drvdata(pdev);
@@ -2819,12 +2838,17 @@ MODULE_DEVICE_TABLE(pci, qedi_pci_tbl);
 
 static enum cpuhp_state qedi_cpuhp_state;
 
+static struct pci_error_handlers qedi_err_handler = {
+	.error_detected = qedi_io_error_detected,
+};
+
 static struct pci_driver qedi_pci_driver = {
 	.name = QEDI_MODULE_NAME,
 	.id_table = qedi_pci_tbl,
 	.probe = qedi_probe,
 	.remove = qedi_remove,
 	.shutdown = qedi_shutdown,
+	.err_handler = &qedi_err_handler,
 };
 
 static int __init qedi_init(void)