scsi: lpfc: fcoe: Fix link down issue after 1000+ link bounces
authorJames Smart <jsmart2021@gmail.com>
Tue, 23 Oct 2018 20:41:06 +0000 (13:41 -0700)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Sun, 1 Dec 2019 08:14:10 +0000 (09:14 +0100)
[ Upstream commit 036cad1f1ac9ce03e2db94b8460f98eaf1e1ee4c ]

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>
drivers/scsi/lpfc/lpfc_els.c
drivers/scsi/lpfc/lpfc_hbadisc.c
drivers/scsi/lpfc/lpfc_init.c
drivers/scsi/lpfc/lpfc_sli.c
drivers/scsi/lpfc/lpfc_sli4.h

index ddd29752d96dc3731651528d6c8109b088114aac..95449f97101d38c614d93340cbf996c90b712943 100644 (file)
@@ -1152,6 +1152,7 @@ stop_rr_fcf_flogi:
                        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) {
@@ -1166,6 +1167,7 @@ stop_rr_fcf_flogi:
                        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;
                }
        }
index b970933a218d5f26ed3521964e168d9f5e108af6..d850077c5e226fbacc5d4ff21b16c9f3e0f02aca 100644 (file)
@@ -1999,6 +1999,26 @@ 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,
index 25612ccf6ff28e76a3a876c73bffe8c21bfc5ad9..15bcd00dd7a23b906ae6995cc92b74b92b058042 100644 (file)
@@ -4997,7 +4997,7 @@ 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;
                }
index 6c2b098b760956f90ec954e753b9b8950ccbe261..ebf7d3cda36772f3e67d0ab19652fa79c6ededf4 100644 (file)
@@ -18056,15 +18056,8 @@ next_priority:
                        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 &&
index 60200385fe009bfff2ca3f03af6a2607a6b027f4..a132a83ef233c36f4dba7321cb1d99543a66de1c 100644 (file)
@@ -265,6 +265,7 @@ 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;