scsi: lpfc: Implement health checking when aborting I/O

Several errors have occurred where the adapter stops or fails but does not
raise the register values for the driver to detect failure. Thus driver is
unaware of the failure. The failure typically results in I/O timeouts, the
I/O timeout handler failing (after several seconds), and the error handler
escalating recovery policy and resulting in more errors. Eventually, the
driver is in a position where things have spiraled and it can't do recovery
because other recovery ops are still outstanding and it becomes unusable.

Resolve the situation by having the I/O timeout handler (actually a els,
SCSI I/O, NVMe ls, or NVMe I/O timeout), in addition to aborting the I/O,
perform a mailbox command and look for a response from the hardware.  If
the mailbox command fails, it will mark the adapter offline and then invoke
the adapter reset handler to clean up.

The new I/O timeout test will be limited to a test every 5s. If there are
multiple I/O timeouts concurrently, only the 1st I/O timeout will generate
the mailbox command. Further testing will only occur once a timeout occurs
after a 5s delay from the last mailbox command has expired.

Link: https://lore.kernel.org/r/20210104180240.46824-14-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, 41 insertions, 3 deletions

diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 176706aaebf5..d51d86959bbc 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -4246,6 +4246,8 @@ lpfc_sli_abort_iocb_ring(struct lpfc_hba *phba, struct lpfc_sli_ring *pring)
 			lpfc_sli_issue_abort_iotag(phba, pring, iocb, NULL);
 		spin_unlock_irq(&phba->hbalock);
 	}
+	/* Make sure HBA is alive */
+	lpfc_issue_hb_tmo(phba);
 
 	/* Cancel all the IOCBs from the completions list */
 	lpfc_sli_cancel_iocbs(phba, &completions, IOSTAT_LOCAL_REJECT,
@@ -8044,7 +8046,7 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 	/* Start heart beat timer */
 	mod_timer(&phba->hb_tmofunc,
 		  jiffies + msecs_to_jiffies(1000 * LPFC_HB_MBOX_INTERVAL));
-	phba->hb_outstanding = 0;
+	phba->hba_flag &= ~(HBA_HBEAT_INP | HBA_HBEAT_TMO);
 	phba->last_completion_time = jiffies;
 
 	/* start eq_delay heartbeat */
@@ -11218,6 +11220,9 @@ lpfc_sli_host_down(struct lpfc_vport *vport)
 	}
 	spin_unlock_irqrestore(&phba->hbalock, flags);
 
+	/* Make sure HBA is alive */
+	lpfc_issue_hb_tmo(phba);
+
 	/* Cancel all the IOCBs from the completions list */
 	lpfc_sli_cancel_iocbs(phba, &completions, IOSTAT_LOCAL_REJECT,
 			      IOERR_SLI_DOWN);
@@ -13029,7 +13034,21 @@ lpfc_sli_sp_intr_handler(int irq, void *dev_id)
 				spin_unlock_irqrestore(
 						&phba->pport->work_port_lock,
 						iflag);
-				lpfc_mbox_cmpl_put(phba, pmb);
+
+				/* Do NOT queue MBX_HEARTBEAT to the worker
+				 * thread for processing.
+				 */
+				if (pmbox->mbxCommand == MBX_HEARTBEAT) {
+					/* Process mbox now */
+					phba->sli.mbox_active = NULL;
+					phba->sli.sli_flag &=
+						~LPFC_SLI_MBOX_ACTIVE;
+					if (pmb->mbox_cmpl)
+						pmb->mbox_cmpl(phba, pmb);
+				} else {
+					/* Queue to worker thread to process */
+					lpfc_mbox_cmpl_put(phba, pmb);
+				}
 			}
 		} else
 			spin_unlock_irqrestore(&phba->hbalock, iflag);
@@ -13625,7 +13644,26 @@ lpfc_sli4_sp_handle_mbox_event(struct lpfc_hba *phba, struct lpfc_mcqe *mcqe)
 	phba->pport->work_port_events &= ~WORKER_MBOX_TMO;
 	spin_unlock_irqrestore(&phba->pport->work_port_lock, iflags);
 
-	/* There is mailbox completion work to do */
+	/* Do NOT queue MBX_HEARTBEAT to the worker thread for processing. */
+	if (pmbox->mbxCommand == MBX_HEARTBEAT) {
+		spin_lock_irqsave(&phba->hbalock, iflags);
+		/* Release the mailbox command posting token */
+		phba->sli.sli_flag &= ~LPFC_SLI_MBOX_ACTIVE;
+		phba->sli.mbox_active = NULL;
+		if (bf_get(lpfc_trailer_consumed, mcqe))
+			lpfc_sli4_mq_release(phba->sli4_hba.mbx_wq);
+		spin_unlock_irqrestore(&phba->hbalock, iflags);
+
+		/* Post the next mbox command, if there is one */
+		lpfc_sli4_post_async_mbox(phba);
+
+		/* Process cmpl now */
+		if (pmb->mbox_cmpl)
+			pmb->mbox_cmpl(phba, pmb);
+		return false;
+	}
+
+	/* There is mailbox completion work to queue to the worker thread */
 	spin_lock_irqsave(&phba->hbalock, iflags);
 	__lpfc_mbox_cmpl_put(phba, pmb);
 	phba->work_ha |= HA_MBATT;