scsi: lpfc: Delay unregistering from transport until GIDFT or ADISC completes

On an RSCN event, the nodes specified in RSCN payload and in MAPPED state
are moved to NPR state in order to revalidate the login. This triggers an
immediate unregister from SCSI/NVMe backend. The assumption is that the
node may be missing. The re-registration with the backend happens after
either relogin (PLOGI/PRLI; if ADISC is disabled or login truly lost) or
when ADISC completes successfully (rediscover with ADISC enabled).

However, the NVMe-FC standard provides for an RSCN to be triggered when
the remote port supports a discovery controller and there was a change
of discovery log content. As the remote port typically also supports
storage subsystems, this unregister causes all storage controller
connections to fail and require reconnect.

Correct by reworking the code to ensure that the unregistration only occurs
when a login state is truly terminated, thereby leaving the NVMe storage
controllers in place.

The changes made are:

 - Retain node state in ADISC_ISSUE when scheduling ADISC ELS retry.

 - Do not clear wwpn/wwnn values upon ADISC failure.

 - Move MAPPED nodes to NPR during RSCN processing, but do not unregister
   with transport.  On GIDFT completion, identify missing nodes (not marked
   NLP_NPR_2B_DISC) and unregister them.

 - Perform unregistration for nodes that will go through ADISC processing
   if ADISC completion fails.

 - Successful ADISC completion will move node back to MAPPED state.

Link: https://lore.kernel.org/r/20210707184351.67872-16-jsmart2021@gmail.com
Co-developed-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 40 insertions, 26 deletions

diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 94dc80dc99b7..32f5f00f0a85 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1664,6 +1664,12 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 	if (!new_ndlp || (new_ndlp == ndlp))
 		return ndlp;
 
+	/*
+	 * Unregister from backend if not done yet. Could have been skipped
+	 * due to ADISC
+	 */
+	lpfc_nlp_unreg_node(vport, new_ndlp);
+
 	if (phba->sli_rev == LPFC_SLI_REV4) {
 		active_rrqs_xri_bitmap = mempool_alloc(phba->active_rrq_pool,
 						       GFP_KERNEL);
@@ -4365,7 +4371,7 @@ out_retry:
 			    (cmd == ELS_CMD_NVMEPRLI))
 				lpfc_nlp_set_state(vport, ndlp,
 					NLP_STE_PRLI_ISSUE);
-			else
+			else if (cmd != ELS_CMD_ADISC)
 				lpfc_nlp_set_state(vport, ndlp,
 					NLP_STE_NPR_NODE);
 			ndlp->nlp_last_elscmd = cmd;
@@ -5653,25 +5659,40 @@ lpfc_els_disc_adisc(struct lpfc_vport *vport)
 
 	/* go thru NPR nodes and issue any remaining ELS ADISCs */
 	list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, nlp_listp) {
-		if (ndlp->nlp_state == NLP_STE_NPR_NODE &&
-		    (ndlp->nlp_flag & NLP_NPR_2B_DISC) != 0 &&
-		    (ndlp->nlp_flag & NLP_NPR_ADISC) != 0) {
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-			spin_unlock_irq(&ndlp->lock);
-			ndlp->nlp_prev_state = ndlp->nlp_state;
-			lpfc_nlp_set_state(vport, ndlp, NLP_STE_ADISC_ISSUE);
-			lpfc_issue_els_adisc(vport, ndlp, 0);
-			sentadisc++;
-			vport->num_disc_nodes++;
-			if (vport->num_disc_nodes >=
-			    vport->cfg_discovery_threads) {
-				spin_lock_irq(shost->host_lock);
-				vport->fc_flag |= FC_NLP_MORE;
-				spin_unlock_irq(shost->host_lock);
-				break;
-			}
+
+		if (ndlp->nlp_state != NLP_STE_NPR_NODE ||
+		    !(ndlp->nlp_flag & NLP_NPR_ADISC))
+			continue;
+
+		spin_lock_irq(&ndlp->lock);
+		ndlp->nlp_flag &= ~NLP_NPR_ADISC;
+		spin_unlock_irq(&ndlp->lock);
+
+		if (!(ndlp->nlp_flag & NLP_NPR_2B_DISC)) {
+			/* This node was marked for ADISC but was not picked
+			 * for discovery. This is possible if the node was
+			 * missing in gidft response.
+			 *
+			 * At time of marking node for ADISC, we skipped unreg
+			 * from backend
+			 */
+			lpfc_nlp_unreg_node(vport, ndlp);
+			continue;
 		}
+
+		ndlp->nlp_prev_state = ndlp->nlp_state;
+		lpfc_nlp_set_state(vport, ndlp, NLP_STE_ADISC_ISSUE);
+		lpfc_issue_els_adisc(vport, ndlp, 0);
+		sentadisc++;
+		vport->num_disc_nodes++;
+		if (vport->num_disc_nodes >=
+				vport->cfg_discovery_threads) {
+			spin_lock_irq(shost->host_lock);
+			vport->fc_flag |= FC_NLP_MORE;
+			spin_unlock_irq(shost->host_lock);
+			break;
+		}
+
 	}
 	if (sentadisc == 0) {
 		spin_lock_irq(shost->host_lock);
@@ -6882,13 +6903,6 @@ lpfc_rscn_recovery_check(struct lpfc_vport *vport)
 			continue;
 		}
 
-		/* Check to see if we need to NVME rescan this target
-		 * remoteport.
-		 */
-		if (ndlp->nlp_fc4_type & NLP_FC4_NVME &&
-		    ndlp->nlp_type & (NLP_NVME_TARGET | NLP_NVME_DISCOVERY))
-			lpfc_nvme_rescan_port(vport, ndlp);
-
 		lpfc_disc_state_machine(vport, ndlp, NULL,
 					NLP_EVT_DEVICE_RECOVERY);
 		lpfc_cancel_retry_delay_tmo(vport, ndlp);