[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>

1 files changed, 15 insertions, 11 deletions

diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 70255c11d3ad..6df8bc003a88 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -578,14 +578,14 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
                             lpfc_cmd->result == IOERR_NO_RESOURCES ||
                             lpfc_cmd->result == RJT_LOGIN_REQUIRED) {
                                 cmd->result = ScsiResult(DID_REQUEUE, 0);
-                        break;
-                } /* else: fall through */
+                                break;
+                        } /* else: fall through */
                 default:
                         cmd->result = ScsiResult(DID_ERROR, 0);
                         break;
                 }
 
-                if ((pnode == NULL )
+                if (!pnode || !NLP_CHK_NODE_ACT(pnode)
                     || (pnode->nlp_state != NLP_STE_MAPPED_NODE))
                         cmd->result = ScsiResult(DID_BUS_BUSY, SAM_STAT_BUSY);
         } else {
@@ -626,7 +626,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
         if (!result)
                 lpfc_rampup_queue_depth(vport, sdev);
 
-        if (!result && pnode != NULL &&
+        if (!result && pnode && NLP_CHK_NODE_ACT(pnode) &&
            ((jiffies - pnode->last_ramp_up_time) >
                 LPFC_Q_RAMP_UP_INTERVAL * HZ) &&
            ((jiffies - pnode->last_q_full_time) >
@@ -654,7 +654,8 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
          * Check for queue full.  If the lun is reporting queue full, then
          * back off the lun queue depth to prevent target overloads.
          */
-        if (result == SAM_STAT_TASK_SET_FULL && pnode != NULL) {
+        if (result == SAM_STAT_TASK_SET_FULL && pnode &&
+            NLP_CHK_NODE_ACT(pnode)) {
                 pnode->last_q_full_time = jiffies;
 
                 shost_for_each_device(tmp_sdev, sdev->host) {
@@ -704,6 +705,9 @@ lpfc_scsi_prep_cmnd(struct lpfc_vport *vport, struct lpfc_scsi_buf *lpfc_cmd,
         int datadir = scsi_cmnd->sc_data_direction;
         char tag[2];
 
+        if (!pnode || !NLP_CHK_NODE_ACT(pnode))
+                return;
+
         lpfc_cmd->fcp_rsp->rspSnsLen = 0;
         /* clear task management bits */
         lpfc_cmd->fcp_cmnd->fcpCntl2 = 0;
@@ -785,9 +789,9 @@ lpfc_scsi_prep_task_mgmt_cmd(struct lpfc_vport *vport,
         struct lpfc_rport_data *rdata = lpfc_cmd->rdata;
         struct lpfc_nodelist *ndlp = rdata->pnode;
 
-        if ((ndlp == NULL) || (ndlp->nlp_state != NLP_STE_MAPPED_NODE)) {
+        if (!ndlp || !NLP_CHK_NODE_ACT(ndlp) ||
+            ndlp->nlp_state != NLP_STE_MAPPED_NODE)
                 return 0;
-        }
 
         piocbq = &(lpfc_cmd->cur_iocbq);
         piocbq->vport = vport;
@@ -842,7 +846,7 @@ lpfc_scsi_tgt_reset(struct lpfc_scsi_buf *lpfc_cmd, struct lpfc_vport *vport,
         struct lpfc_iocbq *iocbqrsp;
         int ret;
 
-        if (!rdata->pnode)
+        if (!rdata->pnode || !NLP_CHK_NODE_ACT(rdata->pnode))
                 return FAILED;
 
         lpfc_cmd->rdata = rdata;
@@ -959,7 +963,7 @@ lpfc_queuecommand(struct scsi_cmnd *cmnd, void (*done) (struct scsi_cmnd *))
          * Catch race where our node has transitioned, but the
          * transport is still transitioning.
          */
-        if (!ndlp) {
+        if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) {
                 cmnd->result = ScsiResult(DID_BUS_BUSY, 0);
                 goto out_fail_command;
         }
@@ -1146,7 +1150,7 @@ lpfc_device_reset_handler(struct scsi_cmnd *cmnd)
          * target is rediscovered or devloss timeout expires.
          */
         while (1) {
-                if (!pnode)
+                if (!pnode || !NLP_CHK_NODE_ACT(pnode))
                         goto out;
 
                 if (pnode->nlp_state != NLP_STE_MAPPED_NODE) {
@@ -1162,7 +1166,7 @@ lpfc_device_reset_handler(struct scsi_cmnd *cmnd)
                                 goto out;
                         }
                         pnode = rdata->pnode;
-                        if (!pnode)
+                        if (!pnode || !NLP_CHK_NODE_ACT(pnode))
                                 goto out;
                 }
                 if (pnode->nlp_state == NLP_STE_MAPPED_NODE)