lpfc: Fix premature release of rpi bit in bitmask

Currently, the driver plays off the fact that older sli4 adapters have a
different rpi access pattern that allowed for the rpi reference to be
released earlier in the teardown sequence, allowing the driver to recycle
the rpi value sooner. Newer sli4 adapters have a different access pattern that
requires us to wait for a later mailbox completion. This changes the put
call location on the newer sli4 adapters.

Symptoms of the error are "0110 ELS" and the "0372 iotag" errors.

Signed-off-by: Dick Kennedy <dick.kennedy@emulex.com>
Signed-off-by: James Smart <james.smart@emulex.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: James Bottomley <JBottomley@Odin.com>

1 files changed, 53 insertions, 7 deletions

diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 9d06d4592c3a..2a51df7bdb0c 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -3439,6 +3439,11 @@ lpfc_mbx_cmpl_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	pmb->context1 = NULL;
 	pmb->context2 = NULL;
 
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI,
+			 "0002 rpi:%x DID:%x flg:%x %d map:%x %p\n",
+			 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
+			 atomic_read(&ndlp->kref.refcount),
+			 ndlp->nlp_usg_map, ndlp);
 	if (ndlp->nlp_flag & NLP_REG_LOGIN_SEND)
 		ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
 
@@ -3855,6 +3860,11 @@ out:
 	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
 	ndlp->nlp_type |= NLP_FABRIC;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI,
+			 "0003 rpi:%x DID:%x flg:%x %d map%x %p\n",
+			 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
+			 atomic_read(&ndlp->kref.refcount),
+			 ndlp->nlp_usg_map, ndlp);
 
 	if (vport->port_state < LPFC_VPORT_READY) {
 		/* Link up discovery requires Fabric registration. */
@@ -4250,8 +4260,15 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		ndlp->active_rrqs_xri_bitmap = active_rrqs_xri_bitmap;
 
 	spin_unlock_irqrestore(&phba->ndlp_lock, flags);
-	if (vport->phba->sli_rev == LPFC_SLI_REV4)
+	if (vport->phba->sli_rev == LPFC_SLI_REV4) {
 		ndlp->nlp_rpi = lpfc_sli4_alloc_rpi(vport->phba);
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
+				 "0008 rpi:%x DID:%x flg:%x refcnt:%d "
+				 "map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID,
+				 ndlp->nlp_flag,
+				 atomic_read(&ndlp->kref.refcount),
+				 ndlp->nlp_usg_map, ndlp);
+	}
 
 
 	if (state != NLP_STE_UNUSED_NODE)
@@ -4276,9 +4293,12 @@ lpfc_drop_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	if (ndlp->nlp_state == NLP_STE_UNUSED_NODE)
 		return;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNUSED_NODE);
-	if (vport->phba->sli_rev == LPFC_SLI_REV4)
+	if (vport->phba->sli_rev == LPFC_SLI_REV4) {
 		lpfc_cleanup_vports_rrqs(vport, ndlp);
-	lpfc_nlp_put(ndlp);
+		lpfc_unreg_rpi(vport, ndlp);
+	} else {
+		lpfc_nlp_put(ndlp);
+	}
 	return;
 }
 
@@ -4515,7 +4535,17 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 				mbox->context1 = ndlp;
 				mbox->mbox_cmpl = lpfc_nlp_logo_unreg;
 			} else {
-				mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
+				if (phba->sli_rev == LPFC_SLI_REV4 &&
+				    (!(vport->load_flag & FC_UNLOADING)) &&
+				    (bf_get(lpfc_sli_intf_if_type,
+				     &phba->sli4_hba.sli_intf) ==
+				      LPFC_SLI_INTF_IF_TYPE_2)) {
+					mbox->context1 = lpfc_nlp_get(ndlp);
+					mbox->mbox_cmpl =
+						lpfc_sli4_unreg_rpi_cmpl_clr;
+				} else
+					mbox->mbox_cmpl =
+						lpfc_sli_def_mbox_cmpl;
 			}
 
 			rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
@@ -4741,6 +4771,11 @@ lpfc_nlp_remove(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		/* For this case we need to cleanup the default rpi
 		 * allocated by the firmware.
 		 */
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
+				 "0005 rpi:%x DID:%x flg:%x %d map:%x %p\n",
+				 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
+				 atomic_read(&ndlp->kref.refcount),
+				 ndlp->nlp_usg_map, ndlp);
 		if ((mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL))
 			!= NULL) {
 			rc = lpfc_reg_rpi(phba, vport->vpi, ndlp->nlp_DID,
@@ -5482,7 +5517,11 @@ lpfc_mbx_cmpl_fdmi_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
 	ndlp->nlp_type |= NLP_FABRIC;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
-
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI,
+			 "0004 rpi:%x DID:%x flg:%x %d map:%x %p\n",
+			 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
+			 atomic_read(&ndlp->kref.refcount),
+			 ndlp->nlp_usg_map, ndlp);
 	/*
 	 * Start issuing Fabric-Device Management Interface (FDMI) command to
 	 * 0xfffffa (FDMI well known port) or Delay issuing FDMI command if
@@ -5648,6 +5687,13 @@ lpfc_nlp_init(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	INIT_LIST_HEAD(&ndlp->nlp_listp);
 	if (vport->phba->sli_rev == LPFC_SLI_REV4) {
 		ndlp->nlp_rpi = lpfc_sli4_alloc_rpi(vport->phba);
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
+				 "0007 rpi:%x DID:%x flg:%x refcnt:%d "
+				 "map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID,
+				 ndlp->nlp_flag,
+				 atomic_read(&ndlp->kref.refcount),
+				 ndlp->nlp_usg_map, ndlp);
+
 		ndlp->active_rrqs_xri_bitmap =
 				mempool_alloc(vport->phba->active_rrq_pool,
 					      GFP_KERNEL);
@@ -5682,9 +5728,9 @@ lpfc_nlp_release(struct kref *kref)
 
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE,
 			"0279 lpfc_nlp_release: ndlp:x%p did %x "
-			"usgmap:x%x refcnt:%d\n",
+			"usgmap:x%x refcnt:%d rpi:%x\n",
 			(void *)ndlp, ndlp->nlp_DID, ndlp->nlp_usg_map,
-			atomic_read(&ndlp->kref.refcount));
+			atomic_read(&ndlp->kref.refcount), ndlp->nlp_rpi);
 
 	/* remove ndlp from action. */
 	lpfc_nlp_remove(ndlp->vport, ndlp);