From 982fc3965d1350d3332e04046b0e101006184ba9 Mon Sep 17 00:00:00 2001 From: James Smart Date: Fri, 10 Sep 2021 16:31:47 -0700 Subject: [PATCH] scsi: lpfc: Don't release final kref on Fport node while ABTS outstanding In a rarely executed path, FLOGI failure, there is a refcounting error. If FLOGI completed with an error, typically a timeout, the initial completion handler would remove the job reference. However, the job completion isn't the actual end of the job/exchange as the timeout usually initiates an ABTS, and upon that ABTS completion, a final completion is sent. The driver removes the reference again in the final completion. Thus the imbalance. In the buggy cases, if there was a link bounce while the delayed response is outstanding, the fport node may be referenced again but there was no additional reference as it is already present. The delayed completion then occurs and removes the last reference freeing the node and causing issues in the link up processed that is using the node. Fix this scenario by removing the snippet that removed the reference in the initial FLOGI completion. The bad snippet was poorly trying to identify the FLOGI as OK to do so by realizing the node was not registered with either SCSI or NVMe transport. Link: https://lore.kernel.org/r/20210910233159.115896-3-jsmart2021@gmail.com Fixes: 618e2ee146d4 ("scsi: lpfc: Fix FLOGI failure due to accessing a freed node") Cc: # v5.13+ Co-developed-by: Justin Tee Signed-off-by: Justin Tee Signed-off-by: James Smart Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_els.c | 11 +++++------ drivers/scsi/lpfc/lpfc_hbadisc.c | 10 ++++++---- drivers/scsi/lpfc/lpfc_nvme.c | 5 +++-- 3 files changed, 14 insertions(+), 12 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 1254a57..df5fc22 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -1059,9 +1059,10 @@ stop_rr_fcf_flogi: lpfc_printf_vlog(vport, KERN_WARNING, LOG_TRACE_EVENT, "0150 FLOGI failure Status:x%x/x%x " - "xri x%x TMO:x%x\n", + "xri x%x TMO:x%x refcnt %d\n", irsp->ulpStatus, irsp->un.ulpWord[4], - cmdiocb->sli4_xritag, irsp->ulpTimeout); + cmdiocb->sli4_xritag, irsp->ulpTimeout, + kref_read(&ndlp->kref)); /* If this is not a loop open failure, bail out */ if (!(irsp->ulpStatus == IOSTAT_LOCAL_REJECT && @@ -1122,12 +1123,12 @@ stop_rr_fcf_flogi: /* FLOGI completes successfully */ lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS, "0101 FLOGI completes successfully, I/O tag:x%x, " - "xri x%x Data: x%x x%x x%x x%x x%x x%x x%x\n", + "xri x%x Data: x%x x%x x%x x%x x%x x%x x%x %d\n", cmdiocb->iotag, cmdiocb->sli4_xritag, irsp->un.ulpWord[4], sp->cmn.e_d_tov, sp->cmn.w2.r_a_tov, sp->cmn.edtovResolution, vport->port_state, vport->fc_flag, - sp->cmn.priority_tagging); + sp->cmn.priority_tagging, kref_read(&ndlp->kref)); if (sp->cmn.priority_tagging) vport->vmid_flag |= LPFC_VMID_ISSUE_QFPA; @@ -1205,8 +1206,6 @@ flogifail: phba->fcf.fcf_flag &= ~FCF_DISCOVERY; spin_unlock_irq(&phba->hbalock); - if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD))) - lpfc_nlp_put(ndlp); if (!lpfc_error_lost_link(irsp)) { /* FLOGI failed, so just use loop map to make discovery list */ lpfc_disc_list_loopmap(vport); diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 7195ca0..6f2e07c3 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -4449,8 +4449,9 @@ lpfc_register_remote_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) fc_remote_port_rolechg(rport, rport_ids.roles); lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, - "3183 %s rport x%px DID x%x, role x%x\n", - __func__, rport, rport->port_id, rport->roles); + "3183 %s rport x%px DID x%x, role x%x refcnt %d\n", + __func__, rport, rport->port_id, rport->roles, + kref_read(&ndlp->kref)); if ((rport->scsi_target_id != -1) && (rport->scsi_target_id < LPFC_MAX_TARGET)) { @@ -4475,8 +4476,9 @@ lpfc_unregister_remote_port(struct lpfc_nodelist *ndlp) lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, "3184 rport unregister x%06x, rport x%px " - "xptflg x%x\n", - ndlp->nlp_DID, rport, ndlp->fc4_xpt_flags); + "xptflg x%x refcnt %d\n", + ndlp->nlp_DID, rport, ndlp->fc4_xpt_flags, + kref_read(&ndlp->kref)); fc_remote_port_delete(rport); lpfc_nlp_put(ndlp); diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 73a3568..bd88477 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -209,8 +209,9 @@ lpfc_nvme_remoteport_delete(struct nvme_fc_remote_port *remoteport) * calling state machine to remove the node. */ lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC, - "6146 remoteport delete of remoteport x%px\n", - remoteport); + "6146 remoteport delete of remoteport x%px, ndlp x%px " + "DID x%x xflags x%x\n", + remoteport, ndlp, ndlp->nlp_DID, ndlp->fc4_xpt_flags); spin_lock_irq(&ndlp->lock); /* The register rebind might have occurred before the delete -- 2.7.4