scsi: be2iscsi: Fix to add timer for UE detection

UE detection in health check is done in a work scheduled in global wq.
UE caused due to transient parity errors are recoverable and reported
within 1s. If this check for TPE gets delayed, PF0 might initiate
soft-reset and then status of UE recoverable is lost.

Handle UE detection in timer routine. Move out EQ delay update work
from health check. Make the IOCTL for EQ delay update non-blocking
as the completion status is ignored.

Signed-off-by: Jitendra Bhivare <jitendra.bhivare@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 49 insertions, 41 deletions

diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index eb4ce17a683d..3dd4f9d126ae 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -4999,8 +4999,9 @@ static void beiscsi_quiesce(struct beiscsi_hba *phba)
 		if (phba->pcidev->irq)
 			free_irq(phba->pcidev->irq, phba);
 	pci_disable_msix(phba->pcidev);
-	cancel_delayed_work_sync(&phba->beiscsi_hw_check_task);
+	cancel_delayed_work_sync(&phba->eqd_update);
 	cancel_work_sync(&phba->boot_work);
+	del_timer_sync(&phba->hw_check);
 
 	for (i = 0; i < phba->num_cpus; i++) {
 		pbe_eq = &phwi_context->be_eq[i];
@@ -5339,18 +5340,32 @@ static void beiscsi_boot_work(struct work_struct *work)
 	}
 }
 
-static void be_eqd_update(struct beiscsi_hba *phba)
+static void beiscsi_hw_health_check(unsigned long ptr)
 {
+	struct beiscsi_hba *phba;
+
+	phba = (struct beiscsi_hba *)ptr;
+	beiscsi_ue_detect(phba);
+	if (test_bit(BEISCSI_HBA_IN_UE, &phba->state))
+		return;
+
+	mod_timer(&phba->hw_check,
+		  jiffies + msecs_to_jiffies(BEISCSI_UE_DETECT_INTERVAL));
+}
+
+static void beiscsi_eqd_update_work(struct work_struct *work)
+{
+	struct hwi_context_memory *phwi_context;
 	struct be_set_eqd set_eqd[MAX_CPUS];
-	struct be_aic_obj *aic;
-	struct be_eq_obj *pbe_eq;
 	struct hwi_controller *phwi_ctrlr;
-	struct hwi_context_memory *phwi_context;
+	struct be_eq_obj *pbe_eq;
+	struct beiscsi_hba *phba;
+	unsigned int pps, delta;
+	struct be_aic_obj *aic;
 	int eqd, i, num = 0;
-	ulong now;
-	u32 pps, delta;
-	unsigned int tag;
+	unsigned long now;
 
+	phba = container_of(work, struct beiscsi_hba, eqd_update.work);
 	if (beiscsi_hba_in_error(phba))
 		return;
 
@@ -5361,13 +5376,13 @@ static void be_eqd_update(struct beiscsi_hba *phba)
 		aic = &phba->aic_obj[i];
 		pbe_eq = &phwi_context->be_eq[i];
 		now = jiffies;
-		if (!aic->jiffs || time_before(now, aic->jiffs) ||
+		if (!aic->jiffies || time_before(now, aic->jiffies) ||
 		    pbe_eq->cq_count < aic->eq_prev) {
-			aic->jiffs = now;
+			aic->jiffies = now;
 			aic->eq_prev = pbe_eq->cq_count;
 			continue;
 		}
-		delta = jiffies_to_msecs(now - aic->jiffs);
+		delta = jiffies_to_msecs(now - aic->jiffies);
 		pps = (((u32)(pbe_eq->cq_count - aic->eq_prev) * 1000) / delta);
 		eqd = (pps / 1500) << 2;
 
@@ -5376,7 +5391,7 @@ static void be_eqd_update(struct beiscsi_hba *phba)
 		eqd = min_t(u32, eqd, phwi_context->max_eqd);
 		eqd = max_t(u32, eqd, phwi_context->min_eqd);
 
-		aic->jiffs = now;
+		aic->jiffies = now;
 		aic->eq_prev = pbe_eq->cq_count;
 
 		if (eqd != aic->prev_eqd) {
@@ -5386,32 +5401,12 @@ static void be_eqd_update(struct beiscsi_hba *phba)
 			num++;
 		}
 	}
-	if (num) {
-		tag = be_cmd_modify_eq_delay(phba, set_eqd, num);
-		if (tag)
-			beiscsi_mccq_compl_wait(phba, tag, NULL, NULL);
-	}
-}
+	if (num)
+		/* completion of this is ignored */
+		beiscsi_modify_eq_delay(phba, set_eqd, num);
 
-/*
- * beiscsi_hw_health_check()- Check adapter health
- * @work: work item to check HW health
- *
- * Check if adapter in an unrecoverable state or not.
- **/
-static void
-beiscsi_hw_health_check(struct work_struct *work)
-{
-	struct beiscsi_hba *phba =
-		container_of(work, struct beiscsi_hba,
-			     beiscsi_hw_check_task.work);
-
-	be_eqd_update(phba);
-
-	beiscsi_ue_detect(phba);
-
-	schedule_delayed_work(&phba->beiscsi_hw_check_task,
-			      msecs_to_jiffies(1000));
+	schedule_delayed_work(&phba->eqd_update,
+			      msecs_to_jiffies(BEISCSI_EQD_UPDATE_INTERVAL));
 }
 
 
@@ -5560,6 +5555,11 @@ static void beiscsi_eeh_resume(struct pci_dev *pdev)
 	hwi_enable_intr(phba);
 	clear_bit(BEISCSI_HBA_PCI_ERR, &phba->state);
 
+	/* start hw_check timer and eqd_update work */
+	schedule_delayed_work(&phba->eqd_update,
+			      msecs_to_jiffies(BEISCSI_EQD_UPDATE_INTERVAL));
+	mod_timer(&phba->hw_check,
+		  jiffies + msecs_to_jiffies(BEISCSI_UE_DETECT_INTERVAL));
 	return;
 ret_err:
 	beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
@@ -5707,8 +5707,7 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 		goto free_twq;
 	}
 
-	INIT_DELAYED_WORK(&phba->beiscsi_hw_check_task,
-			  beiscsi_hw_health_check);
+	INIT_DELAYED_WORK(&phba->eqd_update, beiscsi_eqd_update_work);
 
 	phwi_ctrlr = phba->phwi_ctrlr;
 	phwi_context = phwi_ctrlr->phwi_ctxt;
@@ -5749,8 +5748,17 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 	}
 
 	beiscsi_iface_create_default(phba);
-	schedule_delayed_work(&phba->beiscsi_hw_check_task,
-			      msecs_to_jiffies(1000));
+	schedule_delayed_work(&phba->eqd_update,
+			      msecs_to_jiffies(BEISCSI_EQD_UPDATE_INTERVAL));
+	/**
+	 * Start UE detection here. UE before this will cause stall in probe
+	 * and eventually fail the probe.
+	 */
+	init_timer(&phba->hw_check);
+	phba->hw_check.function = beiscsi_hw_health_check;
+	phba->hw_check.data = (unsigned long)phba;
+	mod_timer(&phba->hw_check,
+		  jiffies + msecs_to_jiffies(BEISCSI_UE_DETECT_INTERVAL));
 
 	beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_INIT,
 		    "\n\n\n BM_%d : SUCCESS - DRIVER LOADED\n\n\n");