[4/8] lpfc: Fix driver crash when re-registering NVME rports.

Commit Message

James Smart Aug. 1, 2018, 12:23 a.m. UTC

During remote port loss fault testing, the driver crashed
with the following trace:

general protection fault: 0000 [#1] SMP
RIP: ... lpfc_nvme_register_port+0x250/0x480 [lpfc]
Call Trace:
 lpfc_nlp_state_cleanup+0x1b3/0x7a0 [lpfc]
 lpfc_nlp_set_state+0xa6/0x1d0 [lpfc]
 lpfc_cmpl_prli_prli_issue+0x213/0x440
 lpfc_disc_state_machine+0x7e/0x1e0 [lpfc]
 lpfc_cmpl_els_prli+0x18a/0x200 [lpfc]
 lpfc_sli_sp_handle_rspiocb+0x3b5/0x6f0 [lpfc]
 lpfc_sli_handle_slow_ring_event_s4+0x161/0x240 [lpfc]
 lpfc_work_done+0x948/0x14c0 [lpfc]
 lpfc_do_work+0x16f/0x180 [lpfc]
 kthread+0xc9/0xe0
 ret_from_fork+0x55/0x80

After registering a new remoteport, the driver is pulling an
ndlp pointer from the lpfc rport associated with the private
area of a newly registered remoteport. The private area is
uninitialized, so it's garbage.

Correct by pulling the the lpfc rport pointer from the entering
ndlp point, then ndlp value from at rport. Note the entering
ndlp may be replacing by the rport->ndlp due to an address
change swap.

Signed-off-by: Dick Kennedy <[e-mail]>
Signed-off-by: James Smart <[e-mail]>
---
 drivers/scsi/lpfc/lpfc_nvme.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

Patch

diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 4cc6783b6a9f..32053424d546 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -2687,7 +2687,7 @@  lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	struct lpfc_nvme_rport *oldrport;
 	struct nvme_fc_remote_port *remote_port;
 	struct nvme_fc_port_info rpinfo;
-	struct lpfc_nodelist *prev_ndlp;
+	struct lpfc_nodelist *prev_ndlp = NULL;
 
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NVME_DISC,
 			 "6006 Register NVME PORT. DID x%06x nlptype x%x\n",
@@ -2736,23 +2736,29 @@  lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		spin_unlock_irq(&vport->phba->hbalock);
 		rport = remote_port->private;
 		if (oldrport) {
+			/* New remoteport record does not guarantee valid
+			 * host private memory area.
+			 */
+			prev_ndlp = oldrport->ndlp;
 			if (oldrport == remote_port->private) {
-				/* Same remoteport.  Just reuse. */
+				/* Same remoteport - ndlp should match.
+				 * Just reuse.
+				 */
 				lpfc_printf_vlog(ndlp->vport, KERN_INFO,
 						 LOG_NVME_DISC,
 						 "6014 Rebinding lport to "
 						 "remoteport %p wwpn 0x%llx, "
-						 "Data: x%x x%x %p x%x x%06x\n",
+						 "Data: x%x x%x %p %p x%x x%06x\n",
 						 remote_port,
 						 remote_port->port_name,
 						 remote_port->port_id,
 						 remote_port->port_role,
+						 prev_ndlp,
 						 ndlp,
 						 ndlp->nlp_type,
 						 ndlp->nlp_DID);
 				return 0;
 			}
-			prev_ndlp = rport->ndlp;
 
 			/* Sever the ndlp<->rport association
 			 * before dropping the ndlp ref from
@@ -2786,13 +2792,13 @@  lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		lpfc_printf_vlog(vport, KERN_INFO,
 				 LOG_NVME_DISC | LOG_NODE,
 				 "6022 Binding new rport to "
-				 "lport %p Remoteport %p  WWNN 0x%llx, "
+				 "lport %p Remoteport %p rport %p WWNN 0x%llx, "
 				 "Rport WWPN 0x%llx DID "
-				 "x%06x Role x%x, ndlp %p\n",
-				 lport, remote_port,
+				 "x%06x Role x%x, ndlp %p prev_ndlp %p\n",
+				 lport, remote_port, rport,
 				 rpinfo.node_name, rpinfo.port_name,
 				 rpinfo.port_id, rpinfo.port_role,
-				 ndlp);
+				 ndlp, prev_ndlp);
 	} else {
 		lpfc_printf_vlog(vport, KERN_ERR,
 				 LOG_NVME_DISC | LOG_NODE,