On Fri, 24 Jan 2020 08:48:55 +0300
Vasily Averin <vvs@xxxxxxxxxxxxx> 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@xxxxxxxxxxxxx>
> ---
> 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@xxxxxxxxxx>
