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>

drivers/scsi/be2iscsi/be.h

@@ -89,7 +89,7 @@ struct be_aic_obj {		/* Adaptive interrupt coalescing (AIC) info */
 	u32 max_eqd;		/* in usecs */
 	u32 prev_eqd;		/* in usecs */
 	u32 et_eqd;		/* configured val when aic is off */
-	ulong jiffs;
+	ulong jiffies;
 	u64 eq_prev;		/* Used to calculate eqe */
 };
 
@@ -111,9 +111,10 @@ struct be_mcc_obj {
 
 struct beiscsi_mcc_tag_state {
 	unsigned long tag_state;
-#define MCC_TAG_STATE_RUNNING	1
-#define MCC_TAG_STATE_TIMEOUT	2
-#define MCC_TAG_STATE_ASYNC	3
+#define MCC_TAG_STATE_RUNNING	0
+#define MCC_TAG_STATE_TIMEOUT	1
+#define MCC_TAG_STATE_ASYNC	2
+#define MCC_TAG_STATE_IGNORE	3
 	void (*cbfn)(struct beiscsi_hba *, unsigned int);
 	struct be_dma_mem tag_mem_state;
 };

drivers/scsi/be2iscsi/be_cmds.c

@@ -515,6 +515,13 @@ int beiscsi_process_mcc_compl(struct be_ctrl_info *ctrl,
 		return 0;
 	}
 
+	if (test_bit(MCC_TAG_STATE_IGNORE, &ctrl->ptag_state[tag].tag_state)) {
+		/* just check completion status and free wrb */
+		__beiscsi_mcc_compl_status(phba, tag, NULL, NULL);
+		free_mcc_wrb(ctrl, tag);
+		return 0;
+	}
+
 	wake_up_interruptible(&ctrl->mcc_wait[tag]);
 	return 0;
 }

drivers/scsi/be2iscsi/be_cmds.h

@@ -743,7 +743,7 @@ unsigned int be_cmd_get_initname(struct beiscsi_hba *phba);
 
 void free_mcc_wrb(struct be_ctrl_info *ctrl, unsigned int tag);
 
-int be_cmd_modify_eq_delay(struct beiscsi_hba *phba, struct be_set_eqd *,
+int beiscsi_modify_eq_delay(struct beiscsi_hba *phba, struct be_set_eqd *,
 			    int num);
 int beiscsi_mccq_compl_wait(struct beiscsi_hba *phba,
 			    unsigned int tag,

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");

drivers/scsi/be2iscsi/be_main.h

@@ -414,7 +414,12 @@ struct beiscsi_hba {
 				 (1 << BEISCSI_HBA_IN_UE))
 
 	u8 optic_state;
-	struct delayed_work beiscsi_hw_check_task;
+	struct delayed_work eqd_update;
+	/* update EQ delay timer every 1000ms */
+#define BEISCSI_EQD_UPDATE_INTERVAL	1000
+	struct timer_list hw_check;
+	/* check for UE every 1000ms */
+#define BEISCSI_UE_DETECT_INTERVAL	1000
 
 	bool mac_addr_set;
 	u8 mac_address[ETH_ALEN];

drivers/scsi/be2iscsi/be_mgmt.c

@@ -97,7 +97,7 @@ static const char * const desc_ue_status_hi[] = {
 };
 
 /*
- * beiscsi_ue_detec()- Detect Unrecoverable Error on adapter
+ * beiscsi_ue_detect()- Detect Unrecoverable Error on adapter
  * @phba: Driver priv structure
  *
  * Read registers linked to UE and check for the UE status
@@ -152,8 +152,9 @@ void beiscsi_ue_detect(struct beiscsi_hba *phba)
 	}
 }
 
-int be_cmd_modify_eq_delay(struct beiscsi_hba *phba,
-		 struct be_set_eqd *set_eqd, int num)
+int beiscsi_modify_eq_delay(struct beiscsi_hba *phba,
+			    struct be_set_eqd *set_eqd,
+			    int num)
 {
 	struct be_ctrl_info *ctrl = &phba->ctrl;
 	struct be_mcc_wrb *wrb;
@@ -181,6 +182,8 @@ int be_cmd_modify_eq_delay(struct beiscsi_hba *phba,
 				cpu_to_le32(set_eqd[i].delay_multiplier);
 	}
 
+	/* ignore the completion of this mbox command */
+	set_bit(MCC_TAG_STATE_IGNORE, &ctrl->ptag_state[tag].tag_state);
 	be_mcc_notify(phba, tag);
 	mutex_unlock(&ctrl->mbox_lock);
 	return tag;