Re: [PATCH 1/1] cio_ignore_proc_seq_next should increase position index

[Cornelia Huck <cohuck@redhat.com>]

On Fri, 24 Jan 2020 08:48:55 +0300
Vasily Averin <vvs@virtuozzo.com> wrote:

$SUBJECT: "s390/cio: ..." ?

> if seq_file .next fuction does not change position index,
> read after some lseek can generate unexpected output.
> 

Fixes: 678a395b356a ("[PATCH] s390: convert /proc/cio_ignore")

> https://bugzilla.kernel.org/show_bug.cgi?id=206283
> Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
> ---
>  drivers/s390/cio/blacklist.c | 5 +++--
>  1 file changed, 3 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c
> index 2a3f874..9cebff8 100644
> --- a/drivers/s390/cio/blacklist.c
> +++ b/drivers/s390/cio/blacklist.c
> @@ -303,8 +303,10 @@ struct ccwdev_iter {
>  cio_ignore_proc_seq_next(struct seq_file *s, void *it, loff_t *offset)
>  {
>  	struct ccwdev_iter *iter;
> +	loff_t p = *offset;

I was asking myself if we could avoid the new variable, but anything I
could think of looked worse.

>  
> -	if (*offset >= (__MAX_SUBCHANNEL + 1) * (__MAX_SSID + 1))
> +	(*offset)++;
> +	if (p >= (__MAX_SUBCHANNEL + 1) * (__MAX_SSID + 1))
>  		return NULL;
>  	iter = it;
>  	if (iter->devno == __MAX_SUBCHANNEL) {
> @@ -314,7 +316,6 @@ struct ccwdev_iter {
>  			return NULL;
>  	} else
>  		iter->devno++;
> -	(*offset)++;
>  	return iter;
>  }
>  

Reviewed-by: Cornelia Huck <cohuck@redhat.com>