scsi: lpfc: fcoe: Fix link down issue after 1000+ link bounces

BugLink: https://bugs.launchpad.net/bugs/1854855

[ Upstream commit 036cad1f ]

On FCoE adapters, when running link bounce test in a loop, initiator
failed to login with switch switch and required driver reload to
recover. Switch reached a point where all subsequent FLOGIs would be
LS_RJT'd. Further testing showed the condition to be related to not
performing FCF discovery between FLOGI's.

Fix by monitoring FLOGI failures and once a repeated error is seen
repeat FCF discovery.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Connor Kuehl <connor.kuehl@canonical.com>
Signed-off-by: Kleber Sacilotto de Souza <kleber.souza@canonical.com>

drivers/scsi/lpfc/lpfc_els.c

@@ -1139,6 +1139,7 @@ lpfc_cmpl_els_flogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			phba->fcf.fcf_flag &= ~FCF_DISCOVERY;
 			phba->hba_flag &= ~(FCF_RR_INPROG | HBA_DEVLOSS_TMO);
 			spin_unlock_irq(&phba->hbalock);
+			phba->fcf.fcf_redisc_attempted = 0; /* reset */
 			goto out;
 		}
 		if (!rc) {
@@ -1153,6 +1154,7 @@ lpfc_cmpl_els_flogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			phba->fcf.fcf_flag &= ~FCF_DISCOVERY;
 			phba->hba_flag &= ~(FCF_RR_INPROG | HBA_DEVLOSS_TMO);
 			spin_unlock_irq(&phba->hbalock);
+			phba->fcf.fcf_redisc_attempted = 0; /* reset */
 			goto out;
 		}
 	}

drivers/scsi/lpfc/lpfc_hbadisc.c

@@ -1964,6 +1964,26 @@ int lpfc_sli4_fcf_rr_next_proc(struct lpfc_vport *vport, uint16_t fcf_index)
 				"failover and change port state:x%x/x%x\n",
 				phba->pport->port_state, LPFC_VPORT_UNKNOWN);
 		phba->pport->port_state = LPFC_VPORT_UNKNOWN;
+
+		if (!phba->fcf.fcf_redisc_attempted) {
+			lpfc_unregister_fcf(phba);
+
+			rc = lpfc_sli4_redisc_fcf_table(phba);
+			if (!rc) {
+				lpfc_printf_log(phba, KERN_INFO, LOG_FIP,
+						"3195 Rediscover FCF table\n");
+				phba->fcf.fcf_redisc_attempted = 1;
+				lpfc_sli4_clear_fcf_rr_bmask(phba);
+			} else {
+				lpfc_printf_log(phba, KERN_WARNING, LOG_FIP,
+						"3196 Rediscover FCF table "
+						"failed. Status:x%x\n", rc);
+			}
+		} else {
+			lpfc_printf_log(phba, KERN_WARNING, LOG_FIP,
+					"3197 Already rediscover FCF table "
+					"attempted. No more retry\n");
+		}
 		goto stop_flogi_current_fcf;
 	} else {
 		lpfc_printf_log(phba, KERN_INFO, LOG_FIP | LOG_ELS,

drivers/scsi/lpfc/lpfc_init.c

@@ -4366,7 +4366,7 @@ lpfc_sli4_async_fip_evt(struct lpfc_hba *phba,
 			break;
 		}
 		/* If fast FCF failover rescan event is pending, do nothing */
-		if (phba->fcf.fcf_flag & FCF_REDISC_EVT) {
+		if (phba->fcf.fcf_flag & (FCF_REDISC_EVT | FCF_REDISC_PEND)) {
 			spin_unlock_irq(&phba->hbalock);
 			break;
 		}

drivers/scsi/lpfc/lpfc_sli.c

@@ -16350,15 +16350,8 @@ lpfc_sli4_fcf_rr_next_index_get(struct lpfc_hba *phba)
 			goto initial_priority;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FIP,
 				"2844 No roundrobin failover FCF available\n");
-		if (next_fcf_index >= LPFC_SLI4_FCF_TBL_INDX_MAX)
-			return LPFC_FCOE_FCF_NEXT_NONE;
-		else {
-			lpfc_printf_log(phba, KERN_WARNING, LOG_FIP,
-				"3063 Only FCF available idx %d, flag %x\n",
-				next_fcf_index,
-			phba->fcf.fcf_pri[next_fcf_index].fcf_rec.flag);
-			return next_fcf_index;
-		}
+
+		return LPFC_FCOE_FCF_NEXT_NONE;
 	}
 
 	if (next_fcf_index < LPFC_SLI4_FCF_TBL_INDX_MAX &&

drivers/scsi/lpfc/lpfc_sli4.h

@@ -237,6 +237,7 @@ struct lpfc_fcf {
 #define FCF_REDISC_EVT	0x100 /* FCF rediscovery event to worker thread */
 #define FCF_REDISC_FOV	0x200 /* Post FCF rediscovery fast failover */
 #define FCF_REDISC_PROG (FCF_REDISC_PEND | FCF_REDISC_EVT)
+	uint16_t fcf_redisc_attempted;
 	uint32_t addr_mode;
 	uint32_t eligible_fcf_cnt;
 	struct lpfc_fcf_rec current_rec;