From: Quinn Tran <qutran@xxxxxxxxxxx> commit 713b415726f100f6644971e75ebfe1edbef1a390 upstream. 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@xxxxxxxxxxx Fixes: d94d8158e184 ("scsi: qla2xxx: Add heartbeat check") Cc: stable@xxxxxxxxxxxxxxx Reviewed-by: Himanshu Madhani <himanshu.madhani@xxxxxxxxxx> Signed-off-by: Quinn Tran <qutran@xxxxxxxxxxx> Signed-off-by: Nilesh Javali <njavali@xxxxxxxxxxx> Signed-off-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- drivers/scsi/qla2xxx/qla_def.h | 1 + drivers/scsi/qla2xxx/qla_os.c | 20 +++++++++++++++++--- 2 files changed, 18 insertions(+), 3 deletions(-) --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -4621,6 +4621,7 @@ 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; --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -7209,7 +7209,7 @@ 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; @@ -7219,8 +7219,19 @@ static void qla_heart_beat(struct scsi_q 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); + } } /************************************************************************** @@ -7411,6 +7422,8 @@ 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) || @@ -7443,9 +7456,10 @@ 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); } Patches currently in stable-queue which might be from qutran@xxxxxxxxxxx are queue-5.16/scsi-qla2xxx-fix-hang-due-to-session-stuck.patch queue-5.16/scsi-qla2xxx-fix-laggy-fc-remote-port-session-recovery.patch queue-5.16/scsi-qla2xxx-fix-disk-failure-to-rediscover.patch queue-5.16/scsi-qla2xxx-fix-scheduling-while-atomic.patch queue-5.16/scsi-qla2xxx-fix-stuck-session-in-gpdb.patch queue-5.16/scsi-qla2xxx-fix-premature-hw-access-after-pci-error.patch queue-5.16/scsi-qla2xxx-fix-n2n-inconsistent-plogi.patch queue-5.16/scsi-qla2xxx-fix-warning-message-due-to-adisc-being-flushed.patch queue-5.16/scsi-qla2xxx-fix-stuck-session-of-prli-reject.patch queue-5.16/scsi-qla2xxx-edif-fix-clang-warning.patch queue-5.16/scsi-qla2xxx-reduce-false-trigger-to-login.patch queue-5.16/scsi-qla2xxx-fix-incorrect-reporting-of-task-management-failure.patch