From 88f7702984e6e562223ecc07c38ac4e61713780a Mon Sep 17 00:00:00 2001 From: James Smart Date: Fri, 10 Sep 2021 16:31:49 -0700 Subject: [PATCH] scsi: lpfc: Fix hang on unload due to stuck fport node A test scenario encountered an unload hang while an FLOGI ELS was in flight when a link down condition occurred. The driver fails unload as it never releases the fport node. For most nodes, when the link drops, devloss tmo is started and the timeout will cause the final node release. For the Fport, as it has not yet registered with the SCSI transport, there is no devloss timer to be started, so there is no final release. Additionally, the link down sequence causes ABORTS to be issued for pending ELS's. The completions from the ABORTS perform the release of node references. However, as the adapter is being reset to be unloaded, those completions will never occur. Fix by the following: - In the ELS cleanup, recognize when unloading and place the ELS's on a different list that immediately cleans up/completes the ELS's. It's recognized that this condition primarily affects only the fport, with other ports having normal clean up logic that handles things. - Resolve the devloss issue by, when cleaning up nodes on after link down, recognizing when the fabric node does not have a completed state (its state is UNUSED) and removing a reference so the node can delete after the ELS reference is released. Link: https://lore.kernel.org/r/20210910233159.115896-5-jsmart2021@gmail.com 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 | 14 ++++++++++++++ drivers/scsi/lpfc/lpfc_hbadisc.c | 14 +++++++++++++- 2 files changed, 27 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 262101e..6c9cb87 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -11386,6 +11386,7 @@ lpfc_sli4_vport_delete_els_xri_aborted(struct lpfc_vport *vport) { struct lpfc_hba *phba = vport->phba; struct lpfc_sglq *sglq_entry = NULL, *sglq_next = NULL; + struct lpfc_nodelist *ndlp = NULL; unsigned long iflag = 0; spin_lock_irqsave(&phba->sli4_hba.sgl_list_lock, iflag); @@ -11393,7 +11394,20 @@ lpfc_sli4_vport_delete_els_xri_aborted(struct lpfc_vport *vport) &phba->sli4_hba.lpfc_abts_els_sgl_list, list) { if (sglq_entry->ndlp && sglq_entry->ndlp->vport == vport) { lpfc_nlp_put(sglq_entry->ndlp); + ndlp = sglq_entry->ndlp; sglq_entry->ndlp = NULL; + + /* If the xri on the abts_els_sgl list is for the Fport + * node and the vport is unloading, the xri aborted wcqe + * likely isn't coming back. Just release the sgl. + */ + if ((vport->load_flag & FC_UNLOADING) && + ndlp->nlp_DID == Fabric_DID) { + list_del(&sglq_entry->list); + sglq_entry->state = SGL_FREED; + list_add_tail(&sglq_entry->list, + &phba->sli4_hba.lpfc_els_sgl_list); + } } } spin_unlock_irqrestore(&phba->sli4_hba.sgl_list_lock, iflag); diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 6f2e07c3..4ff93ae 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -966,8 +966,20 @@ lpfc_cleanup_rpis(struct lpfc_vport *vport, int remove) struct lpfc_nodelist *ndlp, *next_ndlp; list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, nlp_listp) { - if (ndlp->nlp_state == NLP_STE_UNUSED_NODE) + if (ndlp->nlp_state == NLP_STE_UNUSED_NODE) { + /* It's possible the FLOGI to the fabric node never + * successfully completed and never registered with the + * transport. In this case there is no way to clean up + * the node. + */ + if (ndlp->nlp_DID == Fabric_DID) { + if (ndlp->nlp_prev_state == + NLP_STE_UNUSED_NODE && + !ndlp->fc4_xpt_flags) + lpfc_nlp_put(ndlp); + } continue; + } if ((phba->sli3_options & LPFC_SLI3_VPORT_TEARDOWN) || ((vport->port_type == LPFC_NPIV_PORT) && -- 2.7.4