Re: [RFC PATCH v3 04/19] scsi: scsi_error: Add helper scsi_eh_sdev_stu to do START_UNIT

[Diangang Li <lidiangang@bytedance.com>]

On Fri, Mar 14, 2025 at 09:29:12AM +0800, JiangJianJun wrote:
> From: Wenchao Hao <haowenchao2@huawei.com>
> 
> Add helper function scsi_eh_sdev_stu() to perform START_UNIT and check
> if to finish some error commands.
> 
> This is preparation for a genernal LUN/target based error handle
> strategy and did not change original logic.
> 
> Signed-off-by: Wenchao Hao <haowenchao2@huawei.com>
> ---
>  drivers/scsi/scsi_error.c | 50 +++++++++++++++++++++++----------------
>  1 file changed, 29 insertions(+), 21 deletions(-)
> 
> diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
> index cc3a5adb9daa..3b55642fb585 100644
> --- a/drivers/scsi/scsi_error.c
> +++ b/drivers/scsi/scsi_error.c
> @@ -1567,6 +1567,31 @@ static int scsi_eh_try_stu(struct scsi_cmnd *scmd)
>  	return 1;
>  }
>  
> +static int scsi_eh_sdev_stu(struct scsi_cmnd *scmd,
> +			      struct list_head *work_q,
> +			      struct list_head *done_q)
> +{
> +	struct scsi_device *sdev = scmd->device;
> +	struct scsi_cmnd *next;
> +
> +	SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev,
> +				"%s: Sending START_UNIT\n", current->comm));
> +

As in the scsi_eh_stu, SCSI_SENSE_VALID and scsi_check_sense is required
before calling scsi_eh_try_stu.

> +	if (scsi_eh_try_stu(scmd)) {
> +		SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev,
> +				    "%s: START_UNIT failed\n", current->comm));
> +		return 0;
> +	}
> +
> +	if (!scsi_device_online(sdev) || !scsi_eh_tur(scmd))
> +		list_for_each_entry_safe(scmd, next, work_q, eh_entry)
> +			if (scmd->device == sdev &&
> +			    scsi_eh_action(scmd, SUCCESS) == SUCCESS)
> +				scsi_eh_finish_cmd(scmd, done_q);
> +
> +	return list_empty(work_q);
> +}
> +
>   /**
>   * scsi_eh_stu - send START_UNIT if needed
>   * @shost:	&scsi host being recovered.
> @@ -1581,7 +1606,7 @@ static int scsi_eh_stu(struct Scsi_Host *shost,
>  			      struct list_head *work_q,
>  			      struct list_head *done_q)
>  {
> -	struct scsi_cmnd *scmd, *stu_scmd, *next;
> +	struct scsi_cmnd *scmd, *stu_scmd;
>  	struct scsi_device *sdev;
>  
>  	shost_for_each_device(sdev, shost) {
> @@ -1604,26 +1629,9 @@ static int scsi_eh_stu(struct Scsi_Host *shost,
>  		if (!stu_scmd)
>  			continue;
>  
> -		SCSI_LOG_ERROR_RECOVERY(3,
> -			sdev_printk(KERN_INFO, sdev,
> -				     "%s: Sending START_UNIT\n",
> -				    current->comm));
> -
> -		if (!scsi_eh_try_stu(stu_scmd)) {
> -			if (!scsi_device_online(sdev) ||
> -			    !scsi_eh_tur(stu_scmd)) {
> -				list_for_each_entry_safe(scmd, next,
> -							  work_q, eh_entry) {
> -					if (scmd->device == sdev &&
> -					    scsi_eh_action(scmd, SUCCESS) == SUCCESS)
> -						scsi_eh_finish_cmd(scmd, done_q);
> -				}
> -			}
> -		} else {
> -			SCSI_LOG_ERROR_RECOVERY(3,
> -				sdev_printk(KERN_INFO, sdev,
> -					    "%s: START_UNIT failed\n",
> -					    current->comm));
> +		if (scsi_eh_sdev_stu(stu_scmd, work_q, done_q)) {
> +			scsi_device_put(sdev);
> +			break;

Maybe this shouldn't break early. If one scsi_device fails to try STU,
the next one might succeed.

>  		}
>  	}
>  
> -- 
> 2.33.0
>

Thanks,

Diangang Li