Re: [PATCH 1/2] PTP: introduce new versions of IOCTLs

[Joe Perches]

On Sat, 2019-08-17 at 08:59 -0700, Richard Cochran wrote:
> On Wed, Aug 14, 2019 at 10:47:11AM +0300, Felipe Balbi wrote:
> > The current version of the IOCTL have a small problem which prevents us
> > from extending the API by making use of reserved fields. In these new
> > IOCTLs, we are now making sure that flags and rsv fields are zero which
> > will allow us to extend the API in the future.
> > 
> > Signed-off-by: Felipe Balbi <felipe.balbi@xxxxxxxxxxxxxxx>
> > ---
> >  drivers/ptp/ptp_chardev.c      | 58 ++++++++++++++++++++++++++++++++--
> >  include/uapi/linux/ptp_clock.h | 12 +++++++
> >  2 files changed, 68 insertions(+), 2 deletions(-)
> > 
> > diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
[]
> > @@ -123,9 +123,11 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
> >  	struct timespec64 ts;
> >  	int enable, err = 0;
> >  
> > +	memset(&req, 0, sizeof(req));
> 
> Nit: please leave a blank line between memset() and switch/case.

or just initialize the declaration of req with = {}

Is there a case where this initialization is
unnecessary such that it impacts performance
given the use in ptp_ioctl?

caps for instance is memset to zero only in
PTP_CLOCK_GETCAP

req is used in only 3 of the case blocks.

	case PTP_EXTTS_REQUEST:
	case PTP_PEROUT_REQUEST:
	case PTP_ENABLE_PPS:

Maybe it would be better to move the memset(&req...)
into each of the case blocks.

> >  	switch (cmd) {
> >  
> >  	case PTP_CLOCK_GETCAPS:
> > +	case PTP_CLOCK_GETCAPS2:
> >  		memset(&caps, 0, sizeof(caps));
> >  		caps.max_adj = ptp->info->max_adj;
> >  		caps.n_alarm = ptp->info->n_alarm;
> 
> Reviewed-by: Richard Cochran <richardcochran@xxxxxxxxx>
>