linux-kernel - Re: [PATCH v2] ata:libata-eh:Cleanup ata_scsi_cmd_error

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <3767474a-a87c-19d5-8dd2-4f5907d1fab5@opensource.wdc.com>
Date:   Thu, 15 Dec 2022 20:33:18 +0900
From:   Damien Le Moal <damien.lemoal@...nsource.wdc.com>
To:     Wenchao Hao <haowenchao@...wei.com>, linux-ide@...r.kernel.org,
        linux-kernel@...r.kernel.org
Cc:     liuzhiqiang26@...wei.com, linfeilong@...wei.com
Subject: Re: [PATCH v2] ata:libata-eh:Cleanup ata_scsi_cmd_error_handler

On 12/15/22 19:57, Wenchao Hao wrote:
> If ap->ops->error_handler is NULL, just return.
> 
> V2:
> - Check ap->ops->error_handler without taking the spin lock

Changelog needs to go after the "---" below your SoB.

> 
> Signed-off-by: Wenchao Hao <haowenchao@...wei.com>
> ---
>  drivers/ata/libata-eh.c | 96 ++++++++++++++++++++---------------------
>  1 file changed, 48 insertions(+), 48 deletions(-)
> 
> diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
> index 34303ce67c14..c445c272e77f 100644
> --- a/drivers/ata/libata-eh.c
> +++ b/drivers/ata/libata-eh.c
> @@ -565,10 +565,15 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
>  {
>  	int i;
>  	unsigned long flags;
> +	struct scsi_cmnd *scmd, *tmp;
> +	int nr_timedout = 0;
>  
>  	/* make sure sff pio task is not running */
>  	ata_sff_flush_pio_task(ap);
>  
> +	if (!ap->ops->error_handler)
> +		return;
> +
>  	/* synchronize with host lock and sort out timeouts */
>  
>  	/* For new EH, all qcs are finished in one of three ways -
> @@ -584,62 +589,57 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
>  	 * timed out iff its associated qc is active and not failed.
>  	 */
>  	spin_lock_irqsave(ap->lock, flags);
> -	if (ap->ops->error_handler) {
> -		struct scsi_cmnd *scmd, *tmp;
> -		int nr_timedout = 0;
> -
> -		/* This must occur under the ap->lock as we don't want
> -		   a polled recovery to race the real interrupt handler
> -
> -		   The lost_interrupt handler checks for any completed but
> -		   non-notified command and completes much like an IRQ handler.
>  
> -		   We then fall into the error recovery code which will treat
> -		   this as if normal completion won the race */
> -
> -		if (ap->ops->lost_interrupt)
> -			ap->ops->lost_interrupt(ap);
> +	/* This must occur under the ap->lock as we don't want

While at it, please fix the comment style. Multi-line comments should
start with a "/*" empty line.

> +	 * a polled recovery to race the real interrupt handler
> +	 *
> +	 * The lost_interrupt handler checks for any completed but
> +	 * non-notified command and completes much like an IRQ handler.
> +	 *
> +	 * We then fall into the error recovery code which will treat
> +	 * this as if normal completion won the race
> +	 */
> +	if (ap->ops->lost_interrupt)
> +		ap->ops->lost_interrupt(ap);
>  
> -		list_for_each_entry_safe(scmd, tmp, eh_work_q, eh_entry) {
> -			struct ata_queued_cmd *qc;
> +	list_for_each_entry_safe(scmd, tmp, eh_work_q, eh_entry) {
> +		struct ata_queued_cmd *qc;
>  
> -			ata_qc_for_each_raw(ap, qc, i) {
> -				if (qc->flags & ATA_QCFLAG_ACTIVE &&
> -				    qc->scsicmd == scmd)
> -					break;
> -			}
> +		ata_qc_for_each_raw(ap, qc, i) {
> +			if (qc->flags & ATA_QCFLAG_ACTIVE &&
> +			    qc->scsicmd == scmd)
> +				break;
> +		}
>  
> -			if (i < ATA_MAX_QUEUE) {
> -				/* the scmd has an associated qc */
> -				if (!(qc->flags & ATA_QCFLAG_FAILED)) {
> -					/* which hasn't failed yet, timeout */
> -					qc->err_mask |= AC_ERR_TIMEOUT;
> -					qc->flags |= ATA_QCFLAG_FAILED;
> -					nr_timedout++;
> -				}
> -			} else {
> -				/* Normal completion occurred after
> -				 * SCSI timeout but before this point.
> -				 * Successfully complete it.
> -				 */
> -				scmd->retries = scmd->allowed;
> -				scsi_eh_finish_cmd(scmd, &ap->eh_done_q);
> +		if (i < ATA_MAX_QUEUE) {
> +			/* the scmd has an associated qc */
> +			if (!(qc->flags & ATA_QCFLAG_FAILED)) {
> +				/* which hasn't failed yet, timeout */
> +				qc->err_mask |= AC_ERR_TIMEOUT;
> +				qc->flags |= ATA_QCFLAG_FAILED;
> +				nr_timedout++;
>  			}
> +		} else {
> +			/* Normal completion occurred after
> +			 * SCSI timeout but before this point.
> +			 * Successfully complete it.
> +			 */
> +			scmd->retries = scmd->allowed;
> +			scsi_eh_finish_cmd(scmd, &ap->eh_done_q);
>  		}
> +	}
>  
> -		/* If we have timed out qcs.  They belong to EH from
> -		 * this point but the state of the controller is
> -		 * unknown.  Freeze the port to make sure the IRQ
> -		 * handler doesn't diddle with those qcs.  This must
> -		 * be done atomically w.r.t. setting QCFLAG_FAILED.
> -		 */
> -		if (nr_timedout)
> -			__ata_port_freeze(ap);
> -
> +	/* If we have timed out qcs.  They belong to EH from

Same here. Fix the comment style please.

> +	 * this point but the state of the controller is
> +	 * unknown.  Freeze the port to make sure the IRQ
> +	 * handler doesn't diddle with those qcs.  This must
> +	 * be done atomically w.r.t. setting QCFLAG_FAILED.
> +	 */
> +	if (nr_timedout)
> +		__ata_port_freeze(ap);
>  
> -		/* initialize eh_tries */
> -		ap->eh_tries = ATA_EH_MAX_TRIES;
> -	}
> +	/* initialize eh_tries */
> +	ap->eh_tries = ATA_EH_MAX_TRIES;
>  	spin_unlock_irqrestore(ap->lock, flags);
>  
>  }

-- 
Damien Le Moal
Western Digital Research