[v3,17/19] lpfc: Fix nonrecovery of NVME controller after cable swap.

Commit Message

James Smart Jan. 30, 2018, 11:59 p.m. UTC

In a test that is doing large numbers of cable swaps on the target,
the nvme controllers wouldn't reconnect.

During the cable swaps, the targets n_port_id would change. This
information was passed to the nvme-fc transport, in the new remoteport
registration. However, the nvme-fc transport didn't update the n_port_id
value in the remoteport struct when it reused an existing structure.
Later, when a new association was attempted on the remoteport, the
driver's NVME LS routine would use the stale n_port_id from the remoteport
struct to address the LS. As the device is no longer at that address,
the LS would go into never never land.

Separately, the nvme-fc transport will be corrected to update the
n_port_id value on a re-registration.

However, for now, there's no reason to use the transports values.
The private pointer points to the drivers node structure and the
node structure is up to date. Therefore, revise the LS routine to
use the drivers data structures for the LS. Augmented the debug
message for better debugging in the future.

Also removed a duplicate if check that seems to have slipped in.

Signed-off-by: Dick Kennedy <[e-mail]>
Signed-off-by: James Smart <[e-mail]>
Reviewed-by: Hannes Reinecke <[e-mail]>
---
 drivers/scsi/lpfc/lpfc_nvme.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

Patch

diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index c6e5b9972585..6327f858c4c8 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -241,10 +241,11 @@  lpfc_nvme_cmpl_gen_req(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	ndlp = (struct lpfc_nodelist *)cmdwqe->context1;
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
 			 "6047 nvme cmpl Enter "
-			 "Data %p DID %x Xri: %x status %x cmd:%p lsreg:%p "
-			 "bmp:%p ndlp:%p\n",
+			 "Data %p DID %x Xri: %x status %x reason x%x cmd:%p "
+			 "lsreg:%p bmp:%p ndlp:%p\n",
 			 pnvme_lsreq, ndlp ? ndlp->nlp_DID : 0,
 			 cmdwqe->sli4_xritag, status,
+			 (wcqe->parameter & 0xffff),
 			 cmdwqe, pnvme_lsreq, cmdwqe->context3, ndlp);
 
 	lpfc_nvmeio_data(phba, "NVME LS  CMPL: xri x%x stat x%x parm x%x\n",
@@ -419,6 +420,7 @@  lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport,
 {
 	int ret = 0;
 	struct lpfc_nvme_lport *lport;
+	struct lpfc_nvme_rport *rport;
 	struct lpfc_vport *vport;
 	struct lpfc_nodelist *ndlp;
 	struct ulp_bde64 *bpl;
@@ -437,19 +439,18 @@  lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport,
 	 */
 
 	lport = (struct lpfc_nvme_lport *)pnvme_lport->private;
+	rport = (struct lpfc_nvme_rport *)pnvme_rport->private;
 	vport = lport->vport;
 
 	if (vport->load_flag & FC_UNLOADING)
 		return -ENODEV;
 
-	if (vport->load_flag & FC_UNLOADING)
-		return -ENODEV;
-
-	ndlp = lpfc_findnode_did(vport, pnvme_rport->port_id);
+	/* Need the ndlp.  It is stored in the driver's rport. */
+	ndlp = rport->ndlp;
 	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_IOERR,
-				 "6051 DID x%06x not an active rport.\n",
-				 pnvme_rport->port_id);
+				 "6051 Remoteport %p, rport has invalid ndlp. "
+				 "Failing LS Req\n", pnvme_rport);
 		return -ENODEV;
 	}
 
@@ -500,8 +501,9 @@  lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport,
 
 	/* Expand print to include key fields. */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
-			 "6149 ENTER.  lport %p, rport %p lsreq%p rqstlen:%d "
-			 "rsplen:%d %pad %pad\n",
+			 "6149 Issue LS Req to DID 0x%06x lport %p, rport %p "
+			 "lsreq%p rqstlen:%d rsplen:%d %pad %pad\n",
+			 ndlp->nlp_DID,
 			 pnvme_lport, pnvme_rport,
 			 pnvme_lsreq, pnvme_lsreq->rqstlen,
 			 pnvme_lsreq->rsplen, &pnvme_lsreq->rqstdma,
@@ -517,7 +519,7 @@  lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport,
 				ndlp, 2, 30, 0);
 	if (ret != WQE_SUCCESS) {
 		atomic_inc(&lport->xmt_ls_err);
-		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
 				 "6052 EXIT. issue ls wqe failed lport %p, "
 				 "rport %p lsreq%p Status %x DID %x\n",
 				 pnvme_lport, pnvme_rport, pnvme_lsreq,