scsi: lpfc: Rework remote port ref counting and node freeing
When a remote port is disconnected and disappears, its node structure
(ndlp) stays allocated and on a vport node list. While on the list it can
be matched, thus requires validation checks on state to be added in
numerous code paths. If the node comes back, its possible for there to be
multiple node structures for the same device on the vport node list. There
is no reason to keep the node structure around after it is no longer in
existence, and the current implementation creates problems for itself
(multiple nodes) and lots of unnecessary code for state validation.
Additionally, the reference taking on the node structure didn't follow the
normal model used by the kernel kref api. It included lots of odd logic to
match state with reference count. The combination of this odd logic plus
the way it was implicitly used in the discovery engine made its reference
taking implementation suspect and extremely hard to follow.
Change the driver such that the reference taking routines are now normal
ref increments/decrements and callout on refcount=0.
With this in place, the rework can be done such that the node structure is
fully removed and deallocated when the remote port no longer exists and all
references are removed. This removal logic, and the basic ref counting are
intrically tied, thus in a single patch.
Link: https://lore.kernel.org/r/20201115192646.12977-2-james.smart@broadcom.com
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index eaa5fb5..4974bf6 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -860,7 +860,7 @@ lpfc_clr_rrq_active(struct lpfc_hba *phba,
{
struct lpfc_nodelist *ndlp = NULL;
- if ((rrq->vport) && NLP_CHK_NODE_ACT(rrq->ndlp))
+ if (rrq->vport)
ndlp = lpfc_findnode_did(rrq->vport, rrq->nlp_DID);
/* The target DID could have been swapped (cable swap)
@@ -1061,12 +1061,6 @@ lpfc_set_rrq_active(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp,
goto out;
}
- /*
- * set the active bit even if there is no mem available.
- */
- if (NLP_CHK_FREE_REQ(ndlp))
- goto out;
-
if (ndlp->vport && (ndlp->vport->load_flag & FC_UNLOADING))
goto out;
@@ -1289,6 +1283,11 @@ __lpfc_sli_release_iocbq_s4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
(sglq->state != SGL_XRI_ABORTED)) {
spin_lock_irqsave(&phba->sli4_hba.sgl_list_lock,
iflag);
+
+ /* Check if we can get a reference on ndlp */
+ if (sglq->ndlp && !lpfc_nlp_get(sglq->ndlp))
+ sglq->ndlp = NULL;
+
list_add(&sglq->list,
&phba->sli4_hba.lpfc_abts_els_sgl_list);
spin_unlock_irqrestore(
@@ -2589,11 +2588,11 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
vport, KERN_INFO, LOG_MBOX | LOG_SLI,
"0010 UNREG_LOGIN vpi:%x "
"rpi:%x DID:%x defer x%x flg x%x "
- "map:%x %px\n",
+ "%px\n",
vport->vpi, ndlp->nlp_rpi,
ndlp->nlp_DID, ndlp->nlp_defer_did,
ndlp->nlp_flag,
- ndlp->nlp_usg_map, ndlp);
+ ndlp);
ndlp->nlp_flag &= ~NLP_LOGO_ACC;
lpfc_nlp_put(ndlp);
@@ -2852,7 +2851,7 @@ lpfc_nvme_unsol_ls_handler(struct lpfc_hba *phba, struct lpfc_iocbq *piocb)
/* validate the source of the LS is logged in */
ndlp = lpfc_findnode_did(phba->pport, sid);
- if (!ndlp || !NLP_CHK_NODE_ACT(ndlp) ||
+ if (!ndlp ||
((ndlp->nlp_state != NLP_STE_UNMAPPED_NODE) &&
(ndlp->nlp_state != NLP_STE_MAPPED_NODE))) {
lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC,
@@ -10426,7 +10425,7 @@ lpfc_sli_abts_err_handler(struct lpfc_hba *phba,
if (!vport)
goto err_exit;
ndlp = lpfc_findnode_rpi(vport, rpi);
- if (!ndlp || !NLP_CHK_NODE_ACT(ndlp))
+ if (!ndlp)
goto err_exit;
if (iocbq->iocb.ulpStatus == IOSTAT_LOCAL_REJECT)
@@ -10459,7 +10458,7 @@ lpfc_sli4_abts_err_handler(struct lpfc_hba *phba,
struct lpfc_vport *vport;
uint32_t ext_status = 0;
- if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) {
+ if (!ndlp) {
lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
"3115 Node Context not found, driver "
"ignoring abts err event\n");
@@ -17901,15 +17900,6 @@ lpfc_sli4_seq_abort_rsp(struct lpfc_vport *vport,
}
/* Put ndlp onto pport node list */
lpfc_enqueue_node(vport, ndlp);
- } else if (!NLP_CHK_NODE_ACT(ndlp)) {
- /* re-setup ndlp without removing from node list */
- ndlp = lpfc_enable_node(vport, ndlp, NLP_STE_UNUSED_NODE);
- if (!ndlp) {
- lpfc_printf_vlog(vport, KERN_WARNING, LOG_ELS,
- "3275 Failed to active ndlp found "
- "for oxid:x%x SID:x%x\n", oxid, sid);
- return;
- }
}
/* Allocate buffer for rsp iocb */