1 files changed, 90 insertions, 13 deletions

diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 73073fb08369..0bd0fd1042df 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -333,6 +333,21 @@ MODULE_PARM_DESC(ql2xabts_wait_nvme,
 		 "To wait for ABTS response on I/O timeouts for NVMe. (default: 1)");
 
 
+u32 ql2xdelay_before_pci_error_handling = 5;
+module_param(ql2xdelay_before_pci_error_handling, uint, 0644);
+MODULE_PARM_DESC(ql2xdelay_before_pci_error_handling,
+	"Number of seconds delayed before qla begin PCI error self-handling (default: 5).\n");
+
+int ql2xrspq_follow_inptr = 1;
+module_param(ql2xrspq_follow_inptr, int, 0644);
+MODULE_PARM_DESC(ql2xrspq_follow_inptr,
+		 "Follow RSP IN pointer for RSP updates for HBAs 27xx and newer (default: 1).");
+
+int ql2xrspq_follow_inptr_legacy = 1;
+module_param(ql2xrspq_follow_inptr_legacy, int, 0644);
+MODULE_PARM_DESC(ql2xrspq_follow_inptr_legacy,
+		 "Follow RSP IN pointer for RSP updates for HBAs older than 27XX. (default: 1).");
+
 static void qla2x00_clear_drv_active(struct qla_hw_data *);
 static void qla2x00_free_device(scsi_qla_host_t *);
 static int qla2xxx_map_queues(struct Scsi_Host *shost);
@@ -1337,21 +1352,20 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd)
 /*
  * Returns: QLA_SUCCESS or QLA_FUNCTION_FAILED.
  */
-int
-qla2x00_eh_wait_for_pending_commands(scsi_qla_host_t *vha, unsigned int t,
-	uint64_t l, enum nexus_wait_type type)
+static int
+__qla2x00_eh_wait_for_pending_commands(struct qla_qpair *qpair, unsigned int t,
+				       uint64_t l, enum nexus_wait_type type)
 {
 	int cnt, match, status;
 	unsigned long flags;
-	struct qla_hw_data *ha = vha->hw;
-	struct req_que *req;
+	scsi_qla_host_t *vha = qpair->vha;
+	struct req_que *req = qpair->req;
 	srb_t *sp;
 	struct scsi_cmnd *cmd;
 
 	status = QLA_SUCCESS;
 
-	spin_lock_irqsave(&ha->hardware_lock, flags);
-	req = vha->req;
+	spin_lock_irqsave(qpair->qp_lock_ptr, flags);
 	for (cnt = 1; status == QLA_SUCCESS &&
 		cnt < req->num_outstanding_cmds; cnt++) {
 		sp = req->outstanding_cmds[cnt];
@@ -1378,12 +1392,32 @@ qla2x00_eh_wait_for_pending_commands(scsi_qla_host_t *vha, unsigned int t,
 		if (!match)
 			continue;
 
-		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+		spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
 		status = qla2x00_eh_wait_on_command(cmd);
-		spin_lock_irqsave(&ha->hardware_lock, flags);
+		spin_lock_irqsave(qpair->qp_lock_ptr, flags);
 	}
-	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+	spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
+
+	return status;
+}
+
+int
+qla2x00_eh_wait_for_pending_commands(scsi_qla_host_t *vha, unsigned int t,
+				     uint64_t l, enum nexus_wait_type type)
+{
+	struct qla_qpair *qpair;
+	struct qla_hw_data *ha = vha->hw;
+	int i, status = QLA_SUCCESS;
 
+	status = __qla2x00_eh_wait_for_pending_commands(ha->base_qpair, t, l,
+							type);
+	for (i = 0; status == QLA_SUCCESS && i < ha->max_qpairs; i++) {
+		qpair = ha->queue_pair_map[i];
+		if (!qpair)
+			continue;
+		status = __qla2x00_eh_wait_for_pending_commands(qpair, t, l,
+								type);
+	}
 	return status;
 }
 
@@ -1420,7 +1454,7 @@ qla2xxx_eh_device_reset(struct scsi_cmnd *cmd)
 		return err;
 
 	if (fcport->deleted)
-		return SUCCESS;
+		return FAILED;
 
 	ql_log(ql_log_info, vha, 0x8009,
 	    "DEVICE RESET ISSUED nexus=%ld:%d:%llu cmd=%p.\n", vha->host_no,
@@ -1488,7 +1522,7 @@ qla2xxx_eh_target_reset(struct scsi_cmnd *cmd)
 		return err;
 
 	if (fcport->deleted)
-		return SUCCESS;
+		return FAILED;
 
 	ql_log(ql_log_info, vha, 0x8009,
 	    "TARGET RESET ISSUED nexus=%ld:%d cmd=%p.\n", vha->host_no,
@@ -5472,7 +5506,7 @@ qla2x00_do_work(struct scsi_qla_host *vha)
 			    e->u.fcport.fcport, false);
 			break;
 		case QLA_EVT_SA_REPLACE:
-			qla24xx_issue_sa_replace_iocb(vha, e);
+			rc = qla24xx_issue_sa_replace_iocb(vha, e);
 			break;
 		}
 
@@ -7238,6 +7272,44 @@ static void qla_heart_beat(struct scsi_qla_host *vha, u16 dpc_started)
 	}
 }
 
+static void qla_wind_down_chip(scsi_qla_host_t *vha)
+{
+	struct qla_hw_data *ha = vha->hw;
+
+	if (!ha->flags.eeh_busy)
+		return;
+	if (ha->pci_error_state)
+		/* system is trying to recover */
+		return;
+
+	/*
+	 * Current system is not handling PCIE error.  At this point, this is
+	 * best effort to wind down the adapter.
+	 */
+	if (time_after_eq(jiffies, ha->eeh_jif + ql2xdelay_before_pci_error_handling * HZ) &&
+	    !ha->flags.eeh_flush) {
+		ql_log(ql_log_info, vha, 0x9009,
+		    "PCI Error detected, attempting to reset hardware.\n");
+
+		ha->isp_ops->reset_chip(vha);
+		ha->isp_ops->disable_intrs(ha);
+
+		ha->flags.eeh_flush = EEH_FLUSH_RDY;
+		ha->eeh_jif = jiffies;
+
+	} else if (ha->flags.eeh_flush == EEH_FLUSH_RDY &&
+	    time_after_eq(jiffies, ha->eeh_jif +  5 * HZ)) {
+		pci_clear_master(ha->pdev);
+
+		/* flush all command */
+		qla2x00_abort_isp_cleanup(vha);
+		ha->flags.eeh_flush = EEH_FLUSH_DONE;
+
+		ql_log(ql_log_info, vha, 0x900a,
+		    "PCI Error handling complete, all IOs aborted.\n");
+	}
+}
+
 /**************************************************************************
 *   qla2x00_timer
 *
@@ -7261,6 +7333,8 @@ qla2x00_timer(struct timer_list *t)
 	fc_port_t *fcport = NULL;
 
 	if (ha->flags.eeh_busy) {
+		qla_wind_down_chip(vha);
+
 		ql_dbg(ql_dbg_timer, vha, 0x6000,
 		    "EEH = %d, restarting timer.\n",
 		    ha->flags.eeh_busy);
@@ -7841,6 +7915,9 @@ void qla_pci_set_eeh_busy(struct scsi_qla_host *vha)
 
 	spin_lock_irqsave(&base_vha->work_lock, flags);
 	if (!ha->flags.eeh_busy) {
+		ha->eeh_jif = jiffies;
+		ha->flags.eeh_flush = 0;
+
 		ha->flags.eeh_busy = 1;
 		do_cleanup = true;
 	}