scsi: lpfc: Fix node handling for Fabric Controller and Domain Controller

jsmart-gh · martinkpetersen · commit fe83e3b9b422 · 2021-05-21T23:23:28.000-04:00
During link bounce testing, RPI counts were seen to differ from the number of nodes. For fabric and domain controllers, a temporary RPI is assigned, but the code isn't registering it. If the nodes do go away, such as on link down, the temporary RPI isn't being released. Change the way these two fabric services are managed, make them behave like any other remote port. Register the RPI and register with the transport. Never leave the nodes in a NPR or UNUSED state where their RPI is in limbo. This allows them to follow normal dev_loss_tmo handling, RPI refcounting, and normal removal rules. It also allows fabric I/Os to use the RPI for traffic requests. Note: There is some logic that still has a couple of exceptions when the Domain controller (0xfffcXX). There are cases where the fabric won't have a valid login but will send RDP. Other times, it will it send a LOGO then an RDP. It makes for ad-hoc behavior to manage the node. Exceptions are documented in the code. Link: https://lore.kernel.org/r/20210514195559.119853-7-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>
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -80,6 +80,7 @@ void lpfc_mbx_cmpl_reg_login(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_mbx_cmpl_dflt_rpi(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_mbx_cmpl_fabric_reg_login(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_mbx_cmpl_ns_reg_login(struct lpfc_hba *, LPFC_MBOXQ_t *);
+void lpfc_mbx_cmpl_fc_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb);
 void lpfc_mbx_cmpl_fdmi_reg_login(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_mbx_cmpl_reg_vfi(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_unregister_vfi_cmpl(struct lpfc_hba *, LPFC_MBOXQ_t *);
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -863,10 +863,10 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 		len += scnprintf(buf+len, size-len, "%s DID:x%06x ",
 				statep, ndlp->nlp_DID);
 		len += scnprintf(buf+len, size-len,
-				"WWPN x%llx ",
+				"WWPN x%016llx ",
 				wwn_to_u64(ndlp->nlp_portname.u.wwn));
 		len += scnprintf(buf+len, size-len,
-				"WWNN x%llx ",
+				"WWNN x%016llx ",
 				wwn_to_u64(ndlp->nlp_nodename.u.wwn));
 		len += scnprintf(buf+len, size-len, "RPI:x%04x ",
 				 ndlp->nlp_rpi);
diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
@@ -86,6 +86,7 @@ enum lpfc_fc4_xpt_flags {
 
 struct lpfc_nodelist {
 	struct list_head nlp_listp;
+	struct serv_parm fc_sparam;		/* buffer for service params */
 	struct lpfc_name nlp_portname;
 	struct lpfc_name nlp_nodename;
 
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
@@ -3085,6 +3085,95 @@ lpfc_cmpl_els_cmd(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	lpfc_nlp_put(free_ndlp);
 }
 
+/**
+ * lpfc_reg_fab_ctrl_node - RPI register the fabric controller node.
+ * @vport: pointer to lpfc_vport data structure.
+ * @fc_ndlp: pointer to the fabric controller (0xfffffd) node.
+ *
+ * This routine registers the rpi assigned to the fabric controller
+ * NPort_ID (0xfffffd) with the port and moves the node to UNMAPPED
+ * state triggering a registration with the SCSI transport.
+ *
+ * This routine is single out because the fabric controller node
+ * does not receive a PLOGI.  This routine is consumed by the
+ * SCR and RDF ELS commands.  Callers are expected to qualify
+ * with SLI4 first.
+ **/
+static int
+lpfc_reg_fab_ctrl_node(struct lpfc_vport *vport, struct lpfc_nodelist *fc_ndlp)
+{
+	int rc = 0;
+	struct lpfc_hba *phba = vport->phba;
+	struct lpfc_nodelist *ns_ndlp;
+	LPFC_MBOXQ_t *mbox;
+	struct lpfc_dmabuf *mp;
+
+	if (fc_ndlp->nlp_flag & NLP_RPI_REGISTERED)
+		return rc;
+
+	ns_ndlp = lpfc_findnode_did(vport, NameServer_DID);
+	if (!ns_ndlp)
+		return -ENODEV;
+
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
+			 "0935 %s: Reg FC RPI x%x on FC DID x%x NSSte: x%x\n",
+			 __func__, fc_ndlp->nlp_rpi, fc_ndlp->nlp_DID,
+			 ns_ndlp->nlp_state);
+	if (ns_ndlp->nlp_state != NLP_STE_UNMAPPED_NODE)
+		return -ENODEV;
+
+	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!mbox) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE,
+				 "0936 %s: no memory for reg_login "
+				 "Data: x%x x%x x%x x%x\n", __func__,
+				 fc_ndlp->nlp_DID, fc_ndlp->nlp_state,
+				 fc_ndlp->nlp_flag, fc_ndlp->nlp_rpi);
+		return -ENOMEM;
+	}
+	rc = lpfc_reg_rpi(phba, vport->vpi, fc_ndlp->nlp_DID,
+			  (u8 *)&vport->fc_sparam, mbox, fc_ndlp->nlp_rpi);
+	if (rc) {
+		rc = -EACCES;
+		goto out;
+	}
+
+	fc_ndlp->nlp_flag |= NLP_REG_LOGIN_SEND;
+	mbox->mbox_cmpl = lpfc_mbx_cmpl_fc_reg_login;
+	mbox->ctx_ndlp = lpfc_nlp_get(fc_ndlp);
+	if (!mbox->ctx_ndlp) {
+		rc = -ENOMEM;
+		goto out_mem;
+	}
+
+	mbox->vport = vport;
+	rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
+	if (rc == MBX_NOT_FINISHED) {
+		rc = -ENODEV;
+		lpfc_nlp_put(fc_ndlp);
+		goto out_mem;
+	}
+	/* Success path. Exit. */
+	lpfc_nlp_set_state(vport, fc_ndlp,
+			   NLP_STE_REG_LOGIN_ISSUE);
+	return 0;
+
+ out_mem:
+	fc_ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
+	mp = (struct lpfc_dmabuf *)mbox->ctx_buf;
+	lpfc_mbuf_free(phba, mp->virt, mp->phys);
+	kfree(mp);
+
+ out:
+	mempool_free(mbox, phba->mbox_mem_pool);
+	lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE,
+			 "0938 %s: failed to format reg_login "
+			 "Data: x%x x%x x%x x%x\n", __func__,
+			 fc_ndlp->nlp_DID, fc_ndlp->nlp_state,
+			 fc_ndlp->nlp_flag, fc_ndlp->nlp_rpi);
+	return rc;
+}
+
 /**
  * lpfc_cmpl_els_disc_cmd - Completion callback function for Discovery ELS cmd
  * @phba: pointer to lpfc hba data structure.
@@ -3231,10 +3320,18 @@ lpfc_issue_els_scr(struct lpfc_vport *vport, uint8_t retry)
 
 	elsiocb = lpfc_prep_els_iocb(vport, 1, cmdsize, retry, ndlp,
 				     ndlp->nlp_DID, ELS_CMD_SCR);
-
 	if (!elsiocb)
 		return 1;
 
+	if (phba->sli_rev == LPFC_SLI_REV4) {
+		rc = lpfc_reg_fab_ctrl_node(vport, ndlp);
+		if (rc) {
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE,
+					 "0937 %s: Failed to reg fc node, rc %d\n",
+					 __func__, rc);
+			return 1;
+		}
+	}
 	pcmd = (uint8_t *) (((struct lpfc_dmabuf *) elsiocb->context2)->virt);
 
 	*((uint32_t *) (pcmd)) = ELS_CMD_SCR;
@@ -3522,6 +3619,17 @@ lpfc_issue_els_rdf(struct lpfc_vport *vport, uint8_t retry)
 	if (!elsiocb)
 		return -ENOMEM;
 
+	if (phba->sli_rev == LPFC_SLI_REV4 &&
+	    !(ndlp->nlp_flag & NLP_RPI_REGISTERED)) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE,
+				 "0939 %s: FC_NODE x%x RPI x%x flag x%x "
+				 "ste x%x type x%x Not registered\n",
+				 __func__, ndlp->nlp_DID, ndlp->nlp_rpi,
+				 ndlp->nlp_flag, ndlp->nlp_state,
+				 ndlp->nlp_type);
+		return -ENODEV;
+	}
+
 	/* Configure the payload for the supported FPIN events. */
 	prdf = (struct lpfc_els_rdf_req *)
 		(((struct lpfc_dmabuf *)elsiocb->context2)->virt);
@@ -4396,7 +4504,6 @@ lpfc_cmpl_els_logo_acc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	struct lpfc_nodelist *ndlp = (struct lpfc_nodelist *) cmdiocb->context1;
 	struct lpfc_vport *vport = cmdiocb->vport;
 	IOCB_t *irsp;
-	u32 xpt_flags = 0, did_mask = 0;
 
 	irsp = &rspiocb->iocb;
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
@@ -4409,23 +4516,27 @@ lpfc_cmpl_els_logo_acc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			 ndlp->nlp_DID, kref_read(&ndlp->kref), ndlp->nlp_flag,
 			 ndlp->nlp_state, ndlp->nlp_rpi);
 
+	/* This clause allows the LOGO ACC to complete and free resources
+	 * for the Fabric Domain Controller.  It does deliberately skip
+	 * the unreg_rpi and release rpi because some fabrics send RDP
+	 * requests after logging out from the initiator.
+	 */
+	if (ndlp->nlp_type & NLP_FABRIC &&
+	    ((ndlp->nlp_DID & WELL_KNOWN_DID_MASK) != WELL_KNOWN_DID_MASK))
+		goto out;
+
 	if (ndlp->nlp_state == NLP_STE_NPR_NODE) {
 		/* NPort Recovery mode or node is just allocated */
 		if (!lpfc_nlp_not_used(ndlp)) {
 			/* A LOGO is completing and the node is in NPR state.
 			 * If this a fabric node that cleared its transport
 			 * registration, release the rpi.
 			 */
-			xpt_flags = SCSI_XPT_REGD | NVME_XPT_REGD;
-			did_mask = ndlp->nlp_DID & Fabric_DID_MASK;
-			if (did_mask == Fabric_DID_MASK &&
-			    !(ndlp->fc4_xpt_flags & xpt_flags)) {
-				spin_lock_irq(&ndlp->lock);
-				ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-				if (phba->sli_rev == LPFC_SLI_REV4)
-					ndlp->nlp_flag |= NLP_RELEASE_RPI;
-				spin_unlock_irq(&ndlp->lock);
-			}
+			spin_lock_irq(&ndlp->lock);
+			ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
+			if (phba->sli_rev == LPFC_SLI_REV4)
+				ndlp->nlp_flag |= NLP_RELEASE_RPI;
+			spin_unlock_irq(&ndlp->lock);
 			lpfc_unreg_rpi(vport, ndlp);
 		} else {
 			/* Indicate the node has already released, should
@@ -4434,7 +4545,7 @@ lpfc_cmpl_els_logo_acc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			cmdiocb->context1 = NULL;
 		}
 	}
-
+ out:
 	/*
 	 * The driver received a LOGO from the rport and has ACK'd it.
 	 * At this point, the driver is done so release the IOCB
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -77,9 +77,7 @@ static int
 lpfc_valid_xpt_node(struct lpfc_nodelist *ndlp)
 {
 	if (ndlp->nlp_fc4_type ||
-	    ndlp->nlp_DID == Fabric_DID ||
-	    ndlp->nlp_DID == NameServer_DID ||
-	    ndlp->nlp_DID == FDMI_DID)
+	    ndlp->nlp_type & NLP_FABRIC)
 		return 1;
 	return 0;
 }
@@ -826,7 +824,8 @@ lpfc_cleanup_rpis(struct lpfc_vport *vport, int remove)
 		if ((phba->sli3_options & LPFC_SLI3_VPORT_TEARDOWN) ||
 		    ((vport->port_type == LPFC_NPIV_PORT) &&
 		     ((ndlp->nlp_DID == NameServer_DID) ||
-		      (ndlp->nlp_DID == FDMI_DID))))
+		      (ndlp->nlp_DID == FDMI_DID) ||
+		      (ndlp->nlp_DID == Fabric_Cntl_DID))))
 			lpfc_unreg_rpi(vport, ndlp);
 
 		/* Leave Fabric nodes alone on link down */
@@ -4160,6 +4159,53 @@ lpfc_mbx_cmpl_ns_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	return;
 }
 
+/*
+ * This routine handles processing a Fabric Controller REG_LOGIN mailbox
+ * command upon completion. It is setup in the LPFC_MBOXQ
+ * as the completion routine when the command is handed off to the SLI layer.
+ */
+void
+lpfc_mbx_cmpl_fc_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
+{
+	struct lpfc_vport *vport = pmb->vport;
+	MAILBOX_t *mb = &pmb->u.mb;
+	struct lpfc_dmabuf *mp = (struct lpfc_dmabuf *)(pmb->ctx_buf);
+	struct lpfc_nodelist *ndlp;
+
+	ndlp = (struct lpfc_nodelist *)pmb->ctx_ndlp;
+	pmb->ctx_ndlp = NULL;
+	pmb->ctx_buf = NULL;
+
+	if (mb->mbxStatus) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
+				 "0933 %s: Register FC login error: 0x%x\n",
+				 __func__, mb->mbxStatus);
+		goto out;
+	}
+
+	if (phba->sli_rev < LPFC_SLI_REV4)
+		ndlp->nlp_rpi = mb->un.varWords[0];
+
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
+			 "0934 %s: Complete FC x%x RegLogin rpi x%x ste x%x\n",
+			 __func__, ndlp->nlp_DID, ndlp->nlp_rpi,
+			 ndlp->nlp_state);
+
+	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+	ndlp->nlp_type |= NLP_FABRIC;
+	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
+
+ out:
+	lpfc_mbuf_free(phba, mp->virt, mp->phys);
+	kfree(mp);
+	mempool_free(pmb, phba->mbox_mem_pool);
+
+	/* Drop the reference count from the mbox at the end after
+	 * all the current reference to the ndlp have been done.
+	 */
+	lpfc_nlp_put(ndlp);
+}
+
 static void
 lpfc_register_remote_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 {
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -785,6 +785,15 @@ lpfc_rcv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	else
 		lpfc_els_rsp_acc(vport, ELS_CMD_ACC, cmdiocb, ndlp, NULL);
 
+	/* This clause allows the initiator to ACC the LOGO back to the
+	 * Fabric Domain Controller.  It does deliberately skip all other
+	 * steps because some fabrics send RDP requests after logging out
+	 * from the initiator.
+	 */
+	if (ndlp->nlp_type & NLP_FABRIC &&
+	    ((ndlp->nlp_DID & WELL_KNOWN_DID_MASK) != WELL_KNOWN_DID_MASK))
+		return 0;
+
 	/* Notify transport of connectivity loss to trigger cleanup. */
 	if (phba->nvmet_support &&
 	    ndlp->nlp_state == NLP_STE_UNMAPPED_NODE)
@@ -1423,6 +1432,8 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 		switch (ndlp->nlp_DID) {
 		case NameServer_DID:
 			mbox->mbox_cmpl = lpfc_mbx_cmpl_ns_reg_login;
+			/* Fabric Controller Node needs these parameters. */
+			memcpy(&ndlp->fc_sparam, sp, sizeof(struct serv_parm));
 			break;
 		case FDMI_DID:
 			mbox->mbox_cmpl = lpfc_mbx_cmpl_fdmi_reg_login;
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
@@ -2755,7 +2755,6 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 				} else {
 					__lpfc_sli_rpi_release(vport, ndlp);
 				}
-
 				lpfc_nlp_put(ndlp);
 			}
 		}

Original file line number	Diff line number	Diff line change
`@@ -2755,7 +2755,6 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba phba, LPFC_MBOXQ_t pmb)`
`2755`	`2755`	`} else {`
`2756`	`2756`	`__lpfc_sli_rpi_release(vport, ndlp);`
`2757`	`2757`	`}`
`2758`		`-`
`2759`	`2758`	`lpfc_nlp_put(ndlp);`
`2760`	`2759`	`}`
`2761`	`2760`	`}`