On Thu. 19 Aug 2021 at 16:45, Marc Kleine-Budde <mkl@xxxxxxxxxxxxxx> wrote:
> On 15.08.2021 12:32:42, Vincent Mailhol wrote:
> > The sanity checks on the control modes will reject any request related
> > to an unsupported features, even turning it off.
> >
> > Example on an interface which does not support CAN-FD:
> >
> > $ ip link set can0 type can bitrate 500000 fd off
> > RTNETLINK answers: Operation not supported
> >
> > This patch lets such command go through (but requests to turn on an
> > unsupported feature are, of course, still denied).
> >
> > Signed-off-by: Vincent Mailhol <mailhol.vincent@xxxxxxxxxx>
>
> I'm planing to send a pull request to net-next today. I want to do some
> more tests with this series
Ack, I am also preparing a new version. But first, I am just
waiting for your reply on the tdc-mode {auto, manual, off}. :)
> but this patch is more or less unrelated,
> so I can take it in this PR, should I?
FYI, the reason to add it to the series is that when setting TDC to
off, the ip tool sets both CAN_CTRLMODE_TDC_AUTO and
CAN_CTRLMODE_TDC_MANUAL to zero (which the corresponding bits in
can_ctrlmode::mask set to 1). Without this patch, netlink would
return -ENOTSUPP if the driver only supported one of
CAN_CTRLMODE_TDC_{AUTO,MANUAL}.
Regardless, this patch makes sense as a standalone, I am fine if
you include it in your PR.
Also, if you want, you can include the latest patch of the series as well:
https://lore.kernel.org/linux-can/20210815033248.98111-8-mailhol.vincent@xxxxxxxxxx/
It's a comment fix, it should be pretty harmless.
Yours sincerely,
Vincent
