scsi: lpfc: Fix NVMe recovery after mailbox timeout

If a mailbox command times out, the SLI port is deemed in error and the
port is reset.  The HBA cleanup is not returning I/Os to the NVMe layer
before the port is unregistered. This is due to the HBA being marked
offline (!SLI_ACTIVE) and cleanup being done by the mailbox timeout handler
rather than an general adapter reset routine.  The mailbox timeout handler
mailbox handler only cleaned up SCSI I/Os.

Fix by reworking the mailbox handler to:

 - After handling the mailbox error, detect the board is already in
   failure (may be due to another error), and leave cleanup to the
   other handler.

 - If the mailbox command timeout is initial detector of the port error,
   continue with the board cleanup and marking the adapter offline
   (!SLI_ACTIVE). Remove the SCSI-only I/O cleanup routine. The generic
   reset adapter routine that is subsequently invoked, will clean up the
   I/Os.

 - Have the reset adapter routine flush all NVMe and SCSI I/Os if the
   adapter has been marked failed (!SLI_ACTIVE).

 - Rework the NVMe I/O terminate routine to take a status code to fail the
   I/O with and update so that cleaned up I/O calls the wqe completion
   routine. Currently it is bypassing the wqe cleanup and calling the NVMe
   I/O completion directly. The wqe completion routine will take care of
   data structure and node cleanup then call the NVMe I/O completion
   handler.

Link: https://lore.kernel.org/r/20210104180240.46824-11-jsmart2021@gmail.com
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 12 insertions, 8 deletions

diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 735fa1d484eb..dedea5de7d78 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -1532,15 +1532,19 @@ lpfc_sli_cancel_iocbs(struct lpfc_hba *phba, struct list_head *iocblist,
 
 	while (!list_empty(iocblist)) {
 		list_remove_head(iocblist, piocb, struct lpfc_iocbq, list);
-		if (!piocb->iocb_cmpl) {
+		if (piocb->wqe_cmpl) {
 			if (piocb->iocb_flag & LPFC_IO_NVME)
-				lpfc_nvme_cancel_iocb(phba, piocb);
+				lpfc_nvme_cancel_iocb(phba, piocb,
+						      ulpstatus, ulpWord4);
 			else
 				lpfc_sli_release_iocbq(phba, piocb);
-		} else {
+
+		} else if (piocb->iocb_cmpl) {
 			piocb->iocb.ulpStatus = ulpstatus;
 			piocb->iocb.un.ulpWord[4] = ulpWord4;
 			(piocb->iocb_cmpl) (phba, piocb, piocb);
+		} else {
+			lpfc_sli_release_iocbq(phba, piocb);
 		}
 	}
 	return;
@@ -8269,8 +8273,10 @@ lpfc_mbox_timeout_handler(struct lpfc_hba *phba)
 
 	struct lpfc_sli *psli = &phba->sli;
 
-	/* If the mailbox completed, process the completion and return */
-	if (lpfc_sli4_process_missed_mbox_completions(phba))
+	/* If the mailbox completed, process the completion */
+	lpfc_sli4_process_missed_mbox_completions(phba);
+
+	if (!(psli->sli_flag & LPFC_SLI_ACTIVE))
 		return;
 
 	if (pmbox != NULL)
@@ -8311,8 +8317,6 @@ lpfc_mbox_timeout_handler(struct lpfc_hba *phba)
 	psli->sli_flag &= ~LPFC_SLI_ACTIVE;
 	spin_unlock_irq(&phba->hbalock);
 
-	lpfc_sli_abort_fcp_rings(phba);
-
 	lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
 			"0345 Resetting board due to mailbox timeout\n");
 
@@ -11783,7 +11787,7 @@ lpfc_sli_validate_fcp_iocb(struct lpfc_iocbq *iocbq, struct lpfc_vport *vport,
 	struct lpfc_io_buf *lpfc_cmd;
 	int rc = 1;
 
-	if (iocbq->vport != vport)
+	if (!iocbq || iocbq->vport != vport)
 		return rc;
 
 	if (!(iocbq->iocb_flag &  LPFC_IO_FCP) ||