scsi: qla2xxx: Fix laggy FC remote port session recovery

For session recovery, driver relies on the dpc thread to initiate certain
operations. The dpc thread runs exclusively without the Mailbox interface
being occupied. A recent code change for heartbeat check via mailbox cmd 0
is preventing the dpc thread from carrying out its operation. This patch
allows the higher priority error recovery to run first before running the
lower priority heartbeat check.

Link: https://lore.kernel.org/r/20220310092604.22950-9-njavali@marvell.com
Fixes: 6874cad05532 ("scsi: qla2xxx: Add heartbeat check")
Cc: stable@vger.kernel.org
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 8aa1cccebab1323548b3042571d055555d0fb961..d76c0e9f114c2f405d3227c145d9eda51abc1404 100644 (file)
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -4624,6 +4624,7 @@ struct qla_hw_data {
        struct workqueue_struct *wq;
        struct work_struct heartbeat_work;
        struct qlfc_fw fw_buf;
+       unsigned long last_heartbeat_run_jiffies;
 
        /* FCP_CMND priority support */
        struct qla_fcp_prio_cfg *fcp_prio_cfg;

diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 9c4f2b38b34e461efbf79b6b75592dcafbaec786..81451c11eef4d7e823cf0860b9162c120eb2dcc6 100644 (file)
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -7215,7 +7215,7 @@ skip:
        return do_heartbeat;
 }
 
-static void qla_heart_beat(struct scsi_qla_host *vha)
+static void qla_heart_beat(struct scsi_qla_host *vha, u16 dpc_started)
 {
        struct qla_hw_data *ha = vha->hw;
 
@@ -7225,8 +7225,19 @@ static void qla_heart_beat(struct scsi_qla_host *vha)
        if (vha->hw->flags.eeh_busy || qla2x00_chip_is_down(vha))
                return;
 
-       if (qla_do_heartbeat(vha))
+       /*
+        * dpc thread cannot run if heartbeat is running at the same time.
+        * We also do not want to starve heartbeat task. Therefore, do
+        * heartbeat task at least once every 5 seconds.
+        */
+       if (dpc_started &&
+           time_before(jiffies, ha->last_heartbeat_run_jiffies + 5 * HZ))
+               return;
+
+       if (qla_do_heartbeat(vha)) {
+               ha->last_heartbeat_run_jiffies = jiffies;
                queue_work(ha->wq, &ha->heartbeat_work);
+       }
 }
 
 /**************************************************************************
@@ -7417,6 +7428,8 @@ qla2x00_timer(struct timer_list *t)
                start_dpc++;
        }
 
+       /* borrowing w to signify dpc will run */
+       w = 0;
        /* Schedule the DPC routine if needed */
        if ((test_bit(ISP_ABORT_NEEDED, &vha->dpc_flags) ||
            test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags) ||
@@ -7449,9 +7462,10 @@ qla2x00_timer(struct timer_list *t)
                    test_bit(RELOGIN_NEEDED, &vha->dpc_flags),
                    test_bit(PROCESS_PUREX_IOCB, &vha->dpc_flags));
                qla2xxx_wake_dpc(vha);
+               w = 1;
        }
 
-       qla_heart_beat(vha);
+       qla_heart_beat(vha, w);
 
        qla2x00_restart_timer(vha, WATCH_INTERVAL);
 }