diff mbox

[12/15] megaraid_sas: MFI adapter's OCR changes

Message ID 1450445228-26571-13-git-send-email-Sumit.Saxena@avagotech.com (mailing list archive)
State Changes Requested, archived
Headers show

Commit Message

Sumit Saxena Dec. 18, 2015, 1:27 p.m. UTC
Optimized MFI adapters' OCR path, particularly megasas_wait_for_outstanding() function.

Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
---
 drivers/scsi/megaraid/megaraid_sas_base.c |  104 +++++++++++++++--------------
 1 files changed, 54 insertions(+), 50 deletions(-)

Comments

Tomas Henzl Jan. 19, 2016, 2:22 p.m. UTC | #1
On 18.12.2015 14:27, Sumit Saxena wrote:
> Optimized MFI adapters' OCR path, particularly megasas_wait_for_outstanding() function.
>
> Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
> Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
> ---
>  drivers/scsi/megaraid/megaraid_sas_base.c |  104 +++++++++++++++--------------
>  1 files changed, 54 insertions(+), 50 deletions(-)
>
> diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
> index 5eaf6fd..cc843d6 100644
> --- a/drivers/scsi/megaraid/megaraid_sas_base.c
> +++ b/drivers/scsi/megaraid/megaraid_sas_base.c
> @@ -2456,15 +2456,19 @@ void megasas_sriov_heartbeat_handler(unsigned long instance_addr)
>   */
>  static int megasas_wait_for_outstanding(struct megasas_instance *instance)
>  {
> -	int i;
> +	int i, sl, outstanding;
>  	u32 reset_index;
>  	u32 wait_time = MEGASAS_RESET_WAIT_TIME;
>  	unsigned long flags;
>  	struct list_head clist_local;
>  	struct megasas_cmd *reset_cmd;
>  	u32 fw_state;
> -	u8 kill_adapter_flag;
>  
> +	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
> +		dev_info(&instance->pdev->dev, "%s:%d HBA is killed.\n",
> +		__func__, __LINE__);
> +		return FAILED;
> +	}
>  
>  	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) {
>  
> @@ -2521,7 +2525,7 @@ static int megasas_wait_for_outstanding(struct megasas_instance *instance)
>  	}
>  
>  	for (i = 0; i < resetwaittime; i++) {
> -		int outstanding = atomic_read(&instance->fw_outstanding);
> +		outstanding = atomic_read(&instance->fw_outstanding);
>  
>  		if (!outstanding)
>  			break;
> @@ -2540,65 +2544,65 @@ static int megasas_wait_for_outstanding(struct megasas_instance *instance)
>  	}
>  
>  	i = 0;
> -	kill_adapter_flag = 0;
> +	outstanding = atomic_read(&instance->fw_outstanding);
> +	fw_state = instance->instancet->read_fw_status_reg(instance->reg_set) & MFI_STATE_MASK;
> +
> +	if ((!outstanding && (fw_state == MFI_STATE_OPERATIONAL)))
> +		goto no_outstanding;
> +
> +	if (instance->disableOnlineCtrlReset)
> +		goto kill_hba_and_failed;
>  	do {
> -		fw_state = instance->instancet->read_fw_status_reg(
> -					instance->reg_set) & MFI_STATE_MASK;
> -		if ((fw_state == MFI_STATE_FAULT) &&
> -			(instance->disableOnlineCtrlReset == 0)) {
> -			if (i == 3) {
> -				kill_adapter_flag = 2;
> -				break;
> -			}
> +		if ((fw_state == MFI_STATE_FAULT) || atomic_read(&instance->fw_outstanding)) {
> +			dev_info(&instance->pdev->dev,
> +				"%s:%d waiting_for_outstanding: before issue OCR. FW state = 0x%x, oustanding 0x%x\n",
> +				__func__, __LINE__, fw_state, atomic_read(&instance->fw_outstanding));
> +			if (i == 3)
> +				goto kill_hba_and_failed;
>  			megasas_do_ocr(instance);
> -			kill_adapter_flag = 1;
>  
> -			/* wait for 1 secs to let FW finish the pending cmds */
> -			msleep(1000);
> +			if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
> +				dev_info(&instance->pdev->dev, "%s:%d OCR failed and HBA is killed.\n",
> +				__func__, __LINE__);
> +				return FAILED;
> +			}
> +			dev_info(&instance->pdev->dev, "%s:%d waiting_for_outstanding: after issue OCR.\n",
> +				__func__, __LINE__);
> +
> +			for (sl = 0; sl < 10; sl++)
> +				msleep(500);

		ssleep(5); ?

> +
> +			outstanding = atomic_read(&instance->fw_outstanding);
> +
> +			fw_state = instance->instancet->read_fw_status_reg(instance->reg_set) & MFI_STATE_MASK;
> +			if ((!outstanding && (fw_state == MFI_STATE_OPERATIONAL)))
> +				goto no_outstanding;
>  		}
>  		i++;
>  	} while (i <= 3);
>  
> -	if (atomic_read(&instance->fw_outstanding) && !kill_adapter_flag) {
> -		if (instance->disableOnlineCtrlReset == 0) {
> -			megasas_do_ocr(instance);
> +no_outstanding:
>  
> -			/* wait for 5 secs to let FW finish the pending cmds */
> -			for (i = 0; i < wait_time; i++) {
> -				int outstanding =
> -					atomic_read(&instance->fw_outstanding);
> -				if (!outstanding)
> -					return SUCCESS;
> -				msleep(1000);
> -			}
> -		}
> -	}
> +	dev_info(&instance->pdev->dev, "%s:%d no more pending commands remain after reset handling.\n",
> +		__func__, __LINE__);
> +	return SUCCESS;
>  
> -	if (atomic_read(&instance->fw_outstanding) ||
> -					(kill_adapter_flag == 2)) {
> -		dev_notice(&instance->pdev->dev, "pending cmds after reset\n");
> -		/*
> -		 * Send signal to FW to stop processing any pending cmds.
> -		 * The controller will be taken offline by the OS now.
> -		 */
> -		if ((instance->pdev->device ==
> -			PCI_DEVICE_ID_LSI_SAS0073SKINNY) ||
> -			(instance->pdev->device ==
> -			PCI_DEVICE_ID_LSI_SAS0071SKINNY)) {
> -			writel(MFI_STOP_ADP,
> -				&instance->reg_set->doorbell);
> -		} else {
> -			writel(MFI_STOP_ADP,
> -				&instance->reg_set->inbound_doorbell);
> -		}
> +kill_hba_and_failed:
> +
> +	fw_state = instance->instancet->read_fw_status_reg(instance->reg_set) & MFI_STATE_MASK;
> +	if (instance->disableOnlineCtrlReset ||
> +		atomic_read(&instance->fw_outstanding) ||
> +		(fw_state == MFI_STATE_FAULT)) {

You have tested all that many times before (fw_state etc.), so when you after all that
have arrived at kill_hba_and_failed: please just kill the HBA and return FAILED.

> +		/* Reset not supported, kill adapter */
> +		dev_info(&instance->pdev->dev, "%s:%d killing adapter scsi%d"
> +			" disableOnlineCtrlReset %d fw_outstanding %d \n",
> +			__func__, __LINE__, instance->host->host_no, instance->disableOnlineCtrlReset,
> +			atomic_read(&instance->fw_outstanding));
>  		megasas_dump_pending_frames(instance);
> -		atomic_set(&instance->adprecovery, MEGASAS_HW_CRITICAL_ERROR);
> -		return FAILED;
> +		megaraid_sas_kill_hba(instance);
>  	}
>  
> -	dev_notice(&instance->pdev->dev, "no pending cmds after reset\n");
> -
> -	return SUCCESS;
> +	return FAILED;
>  }
>  
>  /**

--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Sumit Saxena Jan. 28, 2016, 11:12 a.m. UTC | #2
> -----Original Message-----
> From: Tomas Henzl [mailto:thenzl@redhat.com]
> Sent: Tuesday, January 19, 2016 7:53 PM
> To: Sumit Saxena; jbottomley@parallels.com; hch@infradead.org;
> martin.petersen@oracle.com
> Cc: linux-scsi@vger.kernel.org; kashyap.desai@avagotech.com
> Subject: Re: [PATCH 12/15] megaraid_sas: MFI adapter's OCR changes
>
> On 18.12.2015 14:27, Sumit Saxena wrote:
> > Optimized MFI adapters' OCR path, particularly
> megasas_wait_for_outstanding() function.
> >
> > Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
> > Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
> > ---
> >  drivers/scsi/megaraid/megaraid_sas_base.c |  104
> > +++++++++++++++--------------
> >  1 files changed, 54 insertions(+), 50 deletions(-)
> >
> > diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c
> > b/drivers/scsi/megaraid/megaraid_sas_base.c
> > index 5eaf6fd..cc843d6 100644
> > --- a/drivers/scsi/megaraid/megaraid_sas_base.c
> > +++ b/drivers/scsi/megaraid/megaraid_sas_base.c
> > @@ -2456,15 +2456,19 @@ void megasas_sriov_heartbeat_handler(unsigned
> long instance_addr)
> >   */
> >  static int megasas_wait_for_outstanding(struct megasas_instance
> > *instance)  {
> > -	int i;
> > +	int i, sl, outstanding;
> >  	u32 reset_index;
> >  	u32 wait_time = MEGASAS_RESET_WAIT_TIME;
> >  	unsigned long flags;
> >  	struct list_head clist_local;
> >  	struct megasas_cmd *reset_cmd;
> >  	u32 fw_state;
> > -	u8 kill_adapter_flag;
> >
> > +	if (atomic_read(&instance->adprecovery) ==
> MEGASAS_HW_CRITICAL_ERROR) {
> > +		dev_info(&instance->pdev->dev, "%s:%d HBA is killed.\n",
> > +		__func__, __LINE__);
> > +		return FAILED;
> > +	}
> >
> >  	if (atomic_read(&instance->adprecovery) !=
> MEGASAS_HBA_OPERATIONAL)
> > {
> >
> > @@ -2521,7 +2525,7 @@ static int megasas_wait_for_outstanding(struct
> megasas_instance *instance)
> >  	}
> >
> >  	for (i = 0; i < resetwaittime; i++) {
> > -		int outstanding = atomic_read(&instance->fw_outstanding);
> > +		outstanding = atomic_read(&instance->fw_outstanding);
> >
> >  		if (!outstanding)
> >  			break;
> > @@ -2540,65 +2544,65 @@ static int megasas_wait_for_outstanding(struct
> megasas_instance *instance)
> >  	}
> >
> >  	i = 0;
> > -	kill_adapter_flag = 0;
> > +	outstanding = atomic_read(&instance->fw_outstanding);
> > +	fw_state =
> > +instance->instancet->read_fw_status_reg(instance->reg_set) &
> > +MFI_STATE_MASK;
> > +
> > +	if ((!outstanding && (fw_state == MFI_STATE_OPERATIONAL)))
> > +		goto no_outstanding;
> > +
> > +	if (instance->disableOnlineCtrlReset)
> > +		goto kill_hba_and_failed;
> >  	do {
> > -		fw_state = instance->instancet->read_fw_status_reg(
> > -					instance->reg_set) &
> MFI_STATE_MASK;
> > -		if ((fw_state == MFI_STATE_FAULT) &&
> > -			(instance->disableOnlineCtrlReset == 0)) {
> > -			if (i == 3) {
> > -				kill_adapter_flag = 2;
> > -				break;
> > -			}
> > +		if ((fw_state == MFI_STATE_FAULT) ||
atomic_read(&instance-
> >fw_outstanding)) {
> > +			dev_info(&instance->pdev->dev,
> > +				"%s:%d waiting_for_outstanding: before
issue
> OCR. FW state = 0x%x, oustanding 0x%x\n",
> > +				__func__, __LINE__, fw_state,
> atomic_read(&instance->fw_outstanding));
> > +			if (i == 3)
> > +				goto kill_hba_and_failed;
> >  			megasas_do_ocr(instance);
> > -			kill_adapter_flag = 1;
> >
> > -			/* wait for 1 secs to let FW finish the pending
cmds */
> > -			msleep(1000);
> > +			if (atomic_read(&instance->adprecovery) ==
> MEGASAS_HW_CRITICAL_ERROR) {
> > +				dev_info(&instance->pdev->dev, "%s:%d OCR
> failed and HBA is killed.\n",
> > +				__func__, __LINE__);
> > +				return FAILED;
> > +			}
> > +			dev_info(&instance->pdev->dev, "%s:%d
> waiting_for_outstanding: after issue OCR.\n",
> > +				__func__, __LINE__);
> > +
> > +			for (sl = 0; sl < 10; sl++)
> > +				msleep(500);
>
> 		ssleep(5); ?
>
> > +
> > +			outstanding = atomic_read(&instance-
> >fw_outstanding);
> > +
> > +			fw_state = instance->instancet-
> >read_fw_status_reg(instance->reg_set) & MFI_STATE_MASK;
> > +			if ((!outstanding && (fw_state ==
> MFI_STATE_OPERATIONAL)))
> > +				goto no_outstanding;
> >  		}
> >  		i++;
> >  	} while (i <= 3);
> >
> > -	if (atomic_read(&instance->fw_outstanding) && !kill_adapter_flag)
{
> > -		if (instance->disableOnlineCtrlReset == 0) {
> > -			megasas_do_ocr(instance);
> > +no_outstanding:
> >
> > -			/* wait for 5 secs to let FW finish the pending
cmds */
> > -			for (i = 0; i < wait_time; i++) {
> > -				int outstanding =
> > -					atomic_read(&instance-
> >fw_outstanding);
> > -				if (!outstanding)
> > -					return SUCCESS;
> > -				msleep(1000);
> > -			}
> > -		}
> > -	}
> > +	dev_info(&instance->pdev->dev, "%s:%d no more pending commands
> remain after reset handling.\n",
> > +		__func__, __LINE__);
> > +	return SUCCESS;
> >
> > -	if (atomic_read(&instance->fw_outstanding) ||
> > -					(kill_adapter_flag == 2)) {
> > -		dev_notice(&instance->pdev->dev, "pending cmds after
> reset\n");
> > -		/*
> > -		 * Send signal to FW to stop processing any pending cmds.
> > -		 * The controller will be taken offline by the OS now.
> > -		 */
> > -		if ((instance->pdev->device ==
> > -			PCI_DEVICE_ID_LSI_SAS0073SKINNY) ||
> > -			(instance->pdev->device ==
> > -			PCI_DEVICE_ID_LSI_SAS0071SKINNY)) {
> > -			writel(MFI_STOP_ADP,
> > -				&instance->reg_set->doorbell);
> > -		} else {
> > -			writel(MFI_STOP_ADP,
> > -				&instance->reg_set->inbound_doorbell);
> > -		}
> > +kill_hba_and_failed:
> > +
> > +	fw_state =
instance->instancet->read_fw_status_reg(instance->reg_set)
> & MFI_STATE_MASK;
> > +	if (instance->disableOnlineCtrlReset ||
> > +		atomic_read(&instance->fw_outstanding) ||
> > +		(fw_state == MFI_STATE_FAULT)) {
>
> You have tested all that many times before (fw_state etc.), so when you
after all
> that have arrived at kill_hba_and_failed: please just kill the HBA and
return
> FAILED.

Agree..will be accommodating this while resending patch.
>
> > +		/* Reset not supported, kill adapter */
> > +		dev_info(&instance->pdev->dev, "%s:%d killing adapter
scsi%d"
> > +			" disableOnlineCtrlReset %d fw_outstanding %d \n",
> > +			__func__, __LINE__, instance->host->host_no,
> instance->disableOnlineCtrlReset,
> > +			atomic_read(&instance->fw_outstanding));
> >  		megasas_dump_pending_frames(instance);
> > -		atomic_set(&instance->adprecovery,
> MEGASAS_HW_CRITICAL_ERROR);
> > -		return FAILED;
> > +		megaraid_sas_kill_hba(instance);
> >  	}
> >
> > -	dev_notice(&instance->pdev->dev, "no pending cmds after reset\n");
> > -
> > -	return SUCCESS;
> > +	return FAILED;
> >  }
> >
> >  /**
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 5eaf6fd..cc843d6 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -2456,15 +2456,19 @@  void megasas_sriov_heartbeat_handler(unsigned long instance_addr)
  */
 static int megasas_wait_for_outstanding(struct megasas_instance *instance)
 {
-	int i;
+	int i, sl, outstanding;
 	u32 reset_index;
 	u32 wait_time = MEGASAS_RESET_WAIT_TIME;
 	unsigned long flags;
 	struct list_head clist_local;
 	struct megasas_cmd *reset_cmd;
 	u32 fw_state;
-	u8 kill_adapter_flag;
 
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
+		dev_info(&instance->pdev->dev, "%s:%d HBA is killed.\n",
+		__func__, __LINE__);
+		return FAILED;
+	}
 
 	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) {
 
@@ -2521,7 +2525,7 @@  static int megasas_wait_for_outstanding(struct megasas_instance *instance)
 	}
 
 	for (i = 0; i < resetwaittime; i++) {
-		int outstanding = atomic_read(&instance->fw_outstanding);
+		outstanding = atomic_read(&instance->fw_outstanding);
 
 		if (!outstanding)
 			break;
@@ -2540,65 +2544,65 @@  static int megasas_wait_for_outstanding(struct megasas_instance *instance)
 	}
 
 	i = 0;
-	kill_adapter_flag = 0;
+	outstanding = atomic_read(&instance->fw_outstanding);
+	fw_state = instance->instancet->read_fw_status_reg(instance->reg_set) & MFI_STATE_MASK;
+
+	if ((!outstanding && (fw_state == MFI_STATE_OPERATIONAL)))
+		goto no_outstanding;
+
+	if (instance->disableOnlineCtrlReset)
+		goto kill_hba_and_failed;
 	do {
-		fw_state = instance->instancet->read_fw_status_reg(
-					instance->reg_set) & MFI_STATE_MASK;
-		if ((fw_state == MFI_STATE_FAULT) &&
-			(instance->disableOnlineCtrlReset == 0)) {
-			if (i == 3) {
-				kill_adapter_flag = 2;
-				break;
-			}
+		if ((fw_state == MFI_STATE_FAULT) || atomic_read(&instance->fw_outstanding)) {
+			dev_info(&instance->pdev->dev,
+				"%s:%d waiting_for_outstanding: before issue OCR. FW state = 0x%x, oustanding 0x%x\n",
+				__func__, __LINE__, fw_state, atomic_read(&instance->fw_outstanding));
+			if (i == 3)
+				goto kill_hba_and_failed;
 			megasas_do_ocr(instance);
-			kill_adapter_flag = 1;
 
-			/* wait for 1 secs to let FW finish the pending cmds */
-			msleep(1000);
+			if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
+				dev_info(&instance->pdev->dev, "%s:%d OCR failed and HBA is killed.\n",
+				__func__, __LINE__);
+				return FAILED;
+			}
+			dev_info(&instance->pdev->dev, "%s:%d waiting_for_outstanding: after issue OCR.\n",
+				__func__, __LINE__);
+
+			for (sl = 0; sl < 10; sl++)
+				msleep(500);
+
+			outstanding = atomic_read(&instance->fw_outstanding);
+
+			fw_state = instance->instancet->read_fw_status_reg(instance->reg_set) & MFI_STATE_MASK;
+			if ((!outstanding && (fw_state == MFI_STATE_OPERATIONAL)))
+				goto no_outstanding;
 		}
 		i++;
 	} while (i <= 3);
 
-	if (atomic_read(&instance->fw_outstanding) && !kill_adapter_flag) {
-		if (instance->disableOnlineCtrlReset == 0) {
-			megasas_do_ocr(instance);
+no_outstanding:
 
-			/* wait for 5 secs to let FW finish the pending cmds */
-			for (i = 0; i < wait_time; i++) {
-				int outstanding =
-					atomic_read(&instance->fw_outstanding);
-				if (!outstanding)
-					return SUCCESS;
-				msleep(1000);
-			}
-		}
-	}
+	dev_info(&instance->pdev->dev, "%s:%d no more pending commands remain after reset handling.\n",
+		__func__, __LINE__);
+	return SUCCESS;
 
-	if (atomic_read(&instance->fw_outstanding) ||
-					(kill_adapter_flag == 2)) {
-		dev_notice(&instance->pdev->dev, "pending cmds after reset\n");
-		/*
-		 * Send signal to FW to stop processing any pending cmds.
-		 * The controller will be taken offline by the OS now.
-		 */
-		if ((instance->pdev->device ==
-			PCI_DEVICE_ID_LSI_SAS0073SKINNY) ||
-			(instance->pdev->device ==
-			PCI_DEVICE_ID_LSI_SAS0071SKINNY)) {
-			writel(MFI_STOP_ADP,
-				&instance->reg_set->doorbell);
-		} else {
-			writel(MFI_STOP_ADP,
-				&instance->reg_set->inbound_doorbell);
-		}
+kill_hba_and_failed:
+
+	fw_state = instance->instancet->read_fw_status_reg(instance->reg_set) & MFI_STATE_MASK;
+	if (instance->disableOnlineCtrlReset ||
+		atomic_read(&instance->fw_outstanding) ||
+		(fw_state == MFI_STATE_FAULT)) {
+		/* Reset not supported, kill adapter */
+		dev_info(&instance->pdev->dev, "%s:%d killing adapter scsi%d"
+			" disableOnlineCtrlReset %d fw_outstanding %d \n",
+			__func__, __LINE__, instance->host->host_no, instance->disableOnlineCtrlReset,
+			atomic_read(&instance->fw_outstanding));
 		megasas_dump_pending_frames(instance);
-		atomic_set(&instance->adprecovery, MEGASAS_HW_CRITICAL_ERROR);
-		return FAILED;
+		megaraid_sas_kill_hba(instance);
 	}
 
-	dev_notice(&instance->pdev->dev, "no pending cmds after reset\n");
-
-	return SUCCESS;
+	return FAILED;
 }
 
 /**