[SCSI] lpfc 8.2.6 : Multiple discovery fixes
Multiple Discovery Fixes:
- Fix race on discovery due to link events coinciding with vport_delete.
- Use NLP_FABRIC state to filter out switch-based pseudo initiators that
reuse the same WWNs.
- Correct erroneous setting of DID=0 in lpfc_matchdid()
- Correct extra reference count that was in the lookup path for the
remoteid from an unsolicited ELS.
- Correct double-free bug in els abort path.
- Correct FDMI server discovery logic for switch that return a WWN of 0.
- Fix bugs in ndlp mgmt when a node changes address
- Correct bug that did not delete RSCNs for vports upon link transitions
- Fix "0216 Link event during NS query" error which pops up when vports
are swapped to different switch ports.
- Add sanity checks on ndlp structures
- Fix devloss log message to dump WWN correctly
- Hold off mgmt commands that were interferring with discovery mailbox cmds
- Remove unnecessary FC_ESTABLISH_LINK logic.
- Correct some race conditions in the worker thread, resulting in devloss:
- Clear the work_port_events field before handling the work port events
- Clear the deferred ring event before handling a deferred ring event
- Hold the hba lock when waking up the work thread
- Send an acc for the rscn even when we aren't going to handle it
- Fix locking behavior that was not properly protecting the ACTIVE flag,
thus allowing mailbox command order to shift.
Signed-off-by: James Smart <james.smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 9766534..7c8c3e6 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -69,7 +69,7 @@
rdata = rport->dd_data;
ndlp = rdata->pnode;
- if (!ndlp) {
+ if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) {
if (rport->roles & FC_RPORT_ROLE_FCP_TARGET)
printk(KERN_ERR "Cannot find remote node"
" to terminate I/O Data x%x\n",
@@ -114,7 +114,7 @@
rdata = rport->dd_data;
ndlp = rdata->pnode;
- if (!ndlp)
+ if (!ndlp || !NLP_CHK_NODE_ACT(ndlp))
return;
vport = ndlp->vport;
@@ -243,8 +243,8 @@
if (warn_on) {
lpfc_printf_vlog(vport, KERN_ERR, LOG_DISCOVERY,
"0203 Devloss timeout on "
- "WWPN %x:%x:%x:%x:%x:%x:%x:%x "
- "NPort x%x Data: x%x x%x x%x\n",
+ "WWPN %02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x "
+ "NPort x%06x Data: x%x x%x x%x\n",
*name, *(name+1), *(name+2), *(name+3),
*(name+4), *(name+5), *(name+6), *(name+7),
ndlp->nlp_DID, ndlp->nlp_flag,
@@ -252,8 +252,8 @@
} else {
lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
"0204 Devloss timeout on "
- "WWPN %x:%x:%x:%x:%x:%x:%x:%x "
- "NPort x%x Data: x%x x%x x%x\n",
+ "WWPN %02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x "
+ "NPort x%06x Data: x%x x%x x%x\n",
*name, *(name+1), *(name+2), *(name+3),
*(name+4), *(name+5), *(name+6), *(name+7),
ndlp->nlp_DID, ndlp->nlp_flag,
@@ -399,7 +399,10 @@
vport = vports[i];
if (vport == NULL)
break;
+ spin_lock_irq(&vport->work_port_lock);
work_port_events = vport->work_port_events;
+ vport->work_port_events &= ~work_port_events;
+ spin_unlock_irq(&vport->work_port_lock);
if (work_port_events & WORKER_DISC_TMO)
lpfc_disc_timeout_handler(vport);
if (work_port_events & WORKER_ELS_TMO)
@@ -416,9 +419,6 @@
lpfc_ramp_down_queue_handler(phba);
if (work_port_events & WORKER_RAMP_UP_QUEUE)
lpfc_ramp_up_queue_handler(phba);
- spin_lock_irq(&vport->work_port_lock);
- vport->work_port_events &= ~work_port_events;
- spin_unlock_irq(&vport->work_port_lock);
}
lpfc_destroy_vport_work_array(phba, vports);
@@ -430,10 +430,10 @@
if (pring->flag & LPFC_STOP_IOCB_EVENT) {
pring->flag |= LPFC_DEFERRED_RING_EVENT;
} else {
+ pring->flag &= ~LPFC_DEFERRED_RING_EVENT;
lpfc_sli_handle_slow_ring_event(phba, pring,
(status &
HA_RXMASK));
- pring->flag &= ~LPFC_DEFERRED_RING_EVENT;
}
/*
* Turn on Ring interrupts
@@ -519,7 +519,9 @@
schedule();
}
}
+ spin_lock_irq(&phba->hbalock);
phba->work_wait = NULL;
+ spin_unlock_irq(&phba->hbalock);
return 0;
}
@@ -809,11 +811,9 @@
mempool_free(pmb, phba->mbox_mem_pool);
spin_lock_irq(shost->host_lock);
- vport->fc_flag &= ~(FC_ABORT_DISCOVERY | FC_ESTABLISH_LINK);
+ vport->fc_flag &= ~FC_ABORT_DISCOVERY;
spin_unlock_irq(shost->host_lock);
- del_timer_sync(&phba->fc_estabtmo);
-
lpfc_can_disctmo(vport);
/* turn on Link Attention interrupts */
@@ -1340,10 +1340,14 @@
i++) {
if (vports[i]->port_type == LPFC_PHYSICAL_PORT)
continue;
+ if (phba->fc_topology == TOPOLOGY_LOOP) {
+ lpfc_vport_set_state(vports[i],
+ FC_VPORT_LINKDOWN);
+ continue;
+ }
if (phba->link_flag & LS_NPIV_FAB_SUPPORTED)
lpfc_initial_fdisc(vports[i]);
- else if (phba->sli3_options &
- LPFC_SLI3_NPIV_ENABLED) {
+ else {
lpfc_vport_set_state(vports[i],
FC_VPORT_NO_FABRIC_SUPP);
lpfc_printf_vlog(vport, KERN_ERR,
@@ -2190,10 +2194,6 @@
if (did == Bcast_DID)
return 0;
- if (ndlp->nlp_DID == 0) {
- return 0;
- }
-
/* First check for Direct match */
if (ndlp->nlp_DID == did)
return 1;
@@ -2301,7 +2301,8 @@
return ndlp;
}
- if (vport->fc_flag & FC_RSCN_MODE) {
+ if ((vport->fc_flag & FC_RSCN_MODE) &&
+ !(vport->fc_flag & FC_NDISC_ACTIVE)) {
if (lpfc_rscn_payload_check(vport, did)) {
/* If we've already recieved a PLOGI from this NPort
* we don't need to try to discover it again.