@@ -157,7 +157,7 @@ _base_fault_reset_work(struct work_struct *work)
spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags);
- if (ioc->shost_recovery)
+ if (ioc->shost_recovery || ioc->pci_error_recovery)
goto rearm_timer;
spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags);
@@ -166,6 +166,20 @@ _base_fault_reset_work(struct work_struct *work)
pr_err(MPT3SAS_FMT "SAS host is non-operational !!!!\n",
ioc->name);
+ /* It may be possible that EEH recovery can resolve some of
+ * pci bus failure issues rather removing the dead ioc function
+ * by considering controller is in a non-operational state. So
+ * here priority is given to the EEH recovery. If it doesn't
+ * not resolve this issue, mpt3sas driver will consider this
+ * controller to non-operational state and remove the dead ioc
+ * function.
+ */
+ if (ioc->non_operational_loop++ < 5) {
+ spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock,
+ flags);
+ goto rearm_timer;
+ }
+
/*
* Call _scsih_flush_pending_cmds callback so that we flush all
* pending commands back to OS. This call is required to aovid
@@ -193,6 +207,8 @@ _base_fault_reset_work(struct work_struct *work)
return; /* don't rearm timer */
}
+ ioc->non_operational_loop = 0;
+
if ((doorbell & MPI2_IOC_STATE_MASK) != MPI2_IOC_STATE_OPERATIONAL) {
rc = mpt3sas_base_hard_reset_handler(ioc, CAN_SLEEP,
FORCE_BIG_HAMMER);
@@ -5162,6 +5178,7 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
if (r)
goto out_free_resources;
+ ioc->non_operational_loop = 0;
return 0;
out_free_resources:
@@ -845,6 +845,7 @@ struct MPT3SAS_ADAPTER {
u16 cpu_msix_table_sz;
u32 ioc_reset_count;
MPT3SAS_FLUSH_RUNNING_CMDS schedule_dead_ioc_flush_running_cmds;
+ u32 non_operational_loop;
/* internal commands, callback index */
u8 scsi_io_cb_idx;