scsi: lpfc: Fix LOGO/PLOGI handling when triggerd by ABTS Timeout event

[ Upstream commit 30e196cacefdd9a38c857caed23cefc9621bc5c1 ]

After a LOGO in response to an ABTS timeout, a PLOGI wasn't issued to
re-establish the login.  An nlp_type check in the LOGO completion
handler failed to restart discovery for NVME targets.  Revised the
nlp_type check for NVME as well as SCSI.

While reviewing the LOGO handling a few other issues were seen and
were addressed:

- Better lock synchronization around ndlp data types

- When the ABTS times out, unregister the RPI before sending the LOGO
  so that all local exchange contexts are cleared and nothing received
  while awaiting LOGO/PLOGI handling will be accepted.

- LOGO handling optimized to:
   Wait only R_A_TOV for a response.
   It doesn't need to be retried on timeout. If there wasn't a
     response, a PLOGI will be sent, thus an implicit logout
     applies as well when the other port sees it.
   If there is a response, any kind of response is considered "good"
     and the XRI quarantined for a exchange qualifier window.

- PLOGI is issued as soon a LOGO state is resolved.

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>

diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 56a4f62..0d214e6 100644 (file)
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -242,6 +242,8 @@ lpfc_prep_els_iocb(struct lpfc_vport *vport, uint8_t expectRsp,
                icmd->ulpCommand = CMD_ELS_REQUEST64_CR;
                if (elscmd == ELS_CMD_FLOGI)
                        icmd->ulpTimeout = FF_DEF_RATOV * 2;
+               else if (elscmd == ELS_CMD_LOGO)
+                       icmd->ulpTimeout = phba->fc_ratov;
                else
                        icmd->ulpTimeout = phba->fc_ratov * 2;
        } else {
@@ -2682,16 +2684,15 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
                goto out;
        }
 
+       /* The LOGO will not be retried on failure.  A LOGO was
+        * issued to the remote rport and a ACC or RJT or no Answer are
+        * all acceptable.  Note the failure and move forward with
+        * discovery.  The PLOGI will retry.
+        */
        if (irsp->ulpStatus) {
-               /* Check for retry */
-               if (lpfc_els_retry(phba, cmdiocb, rspiocb)) {
-                       /* ELS command is being retried */
-                       skip_recovery = 1;
-                       goto out;
-               }
                /* LOGO failed */
                lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
-                                "2756 LOGO failure DID:%06X Status:x%x/x%x\n",
+                                "2756 LOGO failure, No Retry DID:%06X Status:x%x/x%x\n",
                                 ndlp->nlp_DID, irsp->ulpStatus,
                                 irsp->un.ulpWord[4]);
                /* Do not call DSM for lpfc_els_abort'ed ELS cmds */
@@ -2737,7 +2738,8 @@ out:
         * For any other port type, the rpi is unregistered as an implicit
         * LOGO.
         */
-       if ((ndlp->nlp_type & NLP_FCP_TARGET) && (skip_recovery == 0)) {
+       if (ndlp->nlp_type & (NLP_FCP_TARGET | NLP_NVME_TARGET) &&
+           skip_recovery == 0) {
                lpfc_cancel_retry_delay_tmo(vport, ndlp);
                spin_lock_irqsave(shost->host_lock, flags);
                ndlp->nlp_flag |= NLP_NPR_2B_DISC;
@@ -2770,6 +2772,8 @@ out:
  * will be stored into the context1 field of the IOCB for the completion
  * callback function to the LOGO ELS command.
  *
+ * Callers of this routine are expected to unregister the RPI first
+ *
  * Return code
  *   0 - successfully issued logo
  *   1 - failed to issue logo
@@ -2811,22 +2815,6 @@ lpfc_issue_els_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
                "Issue LOGO:      did:x%x",
                ndlp->nlp_DID, 0, 0);
 
-       /*
-        * If we are issuing a LOGO, we may try to recover the remote NPort
-        * by issuing a PLOGI later. Even though we issue ELS cmds by the
-        * VPI, if we have a valid RPI, and that RPI gets unreg'ed while
-        * that ELS command is in-flight, the HBA returns a IOERR_INVALID_RPI
-        * for that ELS cmd. To avoid this situation, lets get rid of the
-        * RPI right now, before any ELS cmds are sent.
-        */
-       spin_lock_irq(shost->host_lock);
-       ndlp->nlp_flag |= NLP_ISSUE_LOGO;
-       spin_unlock_irq(shost->host_lock);
-       if (lpfc_unreg_rpi(vport, ndlp)) {
-               lpfc_els_free_iocb(phba, elsiocb);
-               return 0;
-       }
-
        phba->fc_stat.elsXmitLOGO++;
        elsiocb->iocb_cmpl = lpfc_cmpl_els_logo;
        spin_lock_irq(shost->host_lock);
@@ -2834,7 +2822,6 @@ lpfc_issue_els_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
        ndlp->nlp_flag &= ~NLP_ISSUE_LOGO;
        spin_unlock_irq(shost->host_lock);
        rc = lpfc_sli_issue_iocb(phba, LPFC_ELS_RING, elsiocb, 0);
-
        if (rc == IOCB_ERROR) {
                spin_lock_irq(shost->host_lock);
                ndlp->nlp_flag &= ~NLP_LOGO_SND;
@@ -2842,6 +2829,11 @@ lpfc_issue_els_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
                lpfc_els_free_iocb(phba, elsiocb);
                return 1;
        }
+
+       spin_lock_irq(shost->host_lock);
+       ndlp->nlp_prev_state = ndlp->nlp_state;
+       spin_unlock_irq(shost->host_lock);
+       lpfc_nlp_set_state(vport, ndlp, NLP_STE_LOGO_ISSUE);
        return 0;
 }
 
@@ -9505,7 +9497,8 @@ lpfc_sli_abts_recover_port(struct lpfc_vport *vport,
                                "rport in state 0x%x\n", ndlp->nlp_state);
                return;
        }
-       lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
+       lpfc_printf_log(phba, KERN_ERR,
+                       LOG_ELS | LOG_FCP_ERROR | LOG_NVME_IOERR,
                        "3094 Start rport recovery on shost id 0x%x "
                        "fc_id 0x%06x vpi 0x%x rpi 0x%x state 0x%x "
                        "flags 0x%x\n",
@@ -9518,8 +9511,8 @@ lpfc_sli_abts_recover_port(struct lpfc_vport *vport,
         */
        spin_lock_irqsave(shost->host_lock, flags);
        ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
+       ndlp->nlp_flag |= NLP_ISSUE_LOGO;
        spin_unlock_irqrestore(shost->host_lock, flags);
-       lpfc_issue_els_logo(vport, ndlp, 0);
-       lpfc_nlp_set_state(vport, ndlp, NLP_STE_LOGO_ISSUE);
+       lpfc_unreg_rpi(vport, ndlp);
 }
 

diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index bd9bce9..a6619fd 100644 (file)
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -836,7 +836,9 @@ lpfc_disc_set_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
        struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
 
        if (!(ndlp->nlp_flag & NLP_RPI_REGISTERED)) {
+               spin_lock_irq(shost->host_lock);
                ndlp->nlp_flag &= ~NLP_NPR_ADISC;
+               spin_unlock_irq(shost->host_lock);
                return 0;
        }
 
@@ -851,7 +853,10 @@ lpfc_disc_set_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
                        return 1;
                }
        }
+
+       spin_lock_irq(shost->host_lock);
        ndlp->nlp_flag &= ~NLP_NPR_ADISC;
+       spin_unlock_irq(shost->host_lock);
        lpfc_unreg_rpi(vport, ndlp);
        return 0;
 }