scsi: lpfc: Fix discovery failures during port failovers with lots of vports

The driver is getting hit with 100s of RSCNs during remote port address
changes. Each of those RSCN's ends up generating UNREG_RPI and REG_PRI
mailbox commands.  The discovery engine within the driver doesn't wait for
the mailbox command completions. Instead it sets state flags and moves
forward. At some point, there's a massive backlog of mailbox commands which
take time for the adapter to process. Additionally, it appears there were
duplicate events from the switch so the driver generated duplicate mailbox
commands for the same remote port.  During this window, failures on PLOGI
and PRLI ELS's are see as the adapter is rejecting them as they are for
remote ports that still have pending mailbox commands.

Streamline the discovery engine so that PLOGI log checks for outstanding
UNREG_RPIs and defer the processing until the commands complete. This
better synchronizes the ELS transmission vs the RPI registrations.

Filter out multiple UNREG_RPIs being queued up for the same remote port.

Beef up log messages in this area.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 53 insertions, 6 deletions

diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 0653f29af4a5..353652fbc954 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -2493,6 +2493,30 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	if (pmb->u.mb.mbxCommand == MBX_REG_LOGIN64) {
 		ndlp = (struct lpfc_nodelist *)pmb->ctx_ndlp;
 		lpfc_nlp_put(ndlp);
+		pmb->ctx_buf = NULL;
+		pmb->ctx_ndlp = NULL;
+	}
+
+	if (pmb->u.mb.mbxCommand == MBX_UNREG_LOGIN) {
+		ndlp = (struct lpfc_nodelist *)pmb->ctx_ndlp;
+
+		/* Check to see if there are any deferred events to process */
+		if (ndlp) {
+			lpfc_printf_vlog(
+				vport,
+				KERN_INFO, LOG_MBOX | LOG_DISCOVERY,
+				"1438 UNREG cmpl deferred mbox x%x "
+				"on NPort x%x Data: x%x x%x %p\n",
+				ndlp->nlp_rpi, ndlp->nlp_DID,
+				ndlp->nlp_flag, ndlp->nlp_defer_did, ndlp);
+
+			if ((ndlp->nlp_flag & NLP_UNREG_INP) &&
+			    (ndlp->nlp_defer_did != NLP_EVT_NOTHING_PENDING)) {
+				ndlp->nlp_defer_did = NLP_EVT_NOTHING_PENDING;
+				lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
+			}
+			ndlp->nlp_flag &= ~NLP_UNREG_INP;
+		}
 		pmb->ctx_ndlp = NULL;
 	}
 
@@ -2534,14 +2558,37 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		     &phba->sli4_hba.sli_intf) >=
 		     LPFC_SLI_INTF_IF_TYPE_2)) {
 			if (ndlp) {
-				lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI,
-						 "0010 UNREG_LOGIN vpi:%x "
-						 "rpi:%x DID:%x map:%x %p\n",
-						 vport->vpi, ndlp->nlp_rpi,
-						 ndlp->nlp_DID,
-						 ndlp->nlp_usg_map, ndlp);
+				lpfc_printf_vlog(
+					vport, KERN_INFO, LOG_MBOX | LOG_SLI,
+					 "0010 UNREG_LOGIN vpi:%x "
+					 "rpi:%x DID:%x defer x%x flg x%x "
+					 "map:%x %p\n",
+					 vport->vpi, ndlp->nlp_rpi,
+					 ndlp->nlp_DID, ndlp->nlp_defer_did,
+					 ndlp->nlp_flag,
+					 ndlp->nlp_usg_map, ndlp);
 				ndlp->nlp_flag &= ~NLP_LOGO_ACC;
 				lpfc_nlp_put(ndlp);
+
+				/* Check to see if there are any deferred
+				 * events to process
+				 */
+				if ((ndlp->nlp_flag & NLP_UNREG_INP) &&
+				    (ndlp->nlp_defer_did !=
+				    NLP_EVT_NOTHING_PENDING)) {
+					lpfc_printf_vlog(
+						vport, KERN_INFO, LOG_DISCOVERY,
+						"4111 UNREG cmpl deferred "
+						"clr x%x on "
+						"NPort x%x Data: x%x %p\n",
+						ndlp->nlp_rpi, ndlp->nlp_DID,
+						ndlp->nlp_defer_did, ndlp);
+					ndlp->nlp_defer_did =
+						NLP_EVT_NOTHING_PENDING;
+					lpfc_issue_els_plogi(
+						vport, ndlp->nlp_DID, 0);
+				}
+				ndlp->nlp_flag &= ~NLP_UNREG_INP;
 			}
 		}
 	}