Re: [PATCH v3 1/3] cfg80211: leave invalid channels on regdomain change

["Luis R. Rodriguez" <mcgrof@suse.com>]

On Wed, Nov 26, 2014 at 05:06:37PM +0200, Arik Nemtsov wrote:
> On Tue, Nov 25, 2014 at 9:38 PM, Luis R. Rodriguez <mcgrof@suse.com> wrote:
> > On Sun, Nov 23, 2014 at 05:02:19PM +0200, Arik Nemtsov wrote:
> >> When the regulatory settings change, some channels might become invalid.
> >> Disconnect interfaces acting on these channels, after giving userspace
> >> code a grace period to leave them.
> >>
> >> This mode is currently opt-in, and not all interface operating modes are
> >> supported for regulatory-enforcement checks. A wiphy that wishes to use
> >> the new enforcement code must specify an appropriate regulatory flag,
> >> and all its supported interface modes must be supported by the chekcing
> >> code.
> >
> > This is all looking beter now, since I had a few requests for the last patch
> > I'll ask for some other things here without asking  to negage the flag purpose
> > as I originally wanted.
> >
> >> Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
> >> ---
> >>  include/net/regulatory.h |   6 +++
> >>  net/wireless/core.c      |  13 ++++++
> >>  net/wireless/reg.c       | 106 ++++++++++++++++++++++++++++++++++++++++++++++-
> >>  3 files changed, 124 insertions(+), 1 deletion(-)
> >>
> >> diff --git a/include/net/regulatory.h b/include/net/regulatory.h
> >> index dad7ab2..701177c 100644
> >> --- a/include/net/regulatory.h
> >> +++ b/include/net/regulatory.h
> >> @@ -136,6 +136,11 @@ struct regulatory_request {
> >>   *      otherwise initiating radiation is not allowed. This will enable the
> >>   *      relaxations enabled under the CFG80211_REG_RELAX_NO_IR configuration
> >>   *      option
> >> + * @REGULATORY_ENFORCE_CHANNELS: the regulatory core will make sure all
> >> + *   interfaces on this wiphy reside on allowed channels. Upon a regdomain
> >> + *   change, the interfaces are given a grace period to disconnect or move
> >> + *   to an allowed channels. Interfaces on forbidden channels are forcibly
> >> + *   disconnected.
> >
> > Please rename to REGULATORY_IGNORE_STALE_KICKOFF, also please add
> > some information about the amount current of grace period used,
> > and types of interfaces supported. Since this is a regulatory flag
> > this information will help folks decide whether to enable or not.
> > Also encourage its use, and mention that once all supported devices
> > get support for this will be enabled by default. In the meantime
> > I'd prefer if this feature was enabled by default if the supported
> > interface types of a dveice match the white list of supported
> > interfaces.
> 
> btw, I think you meant REGULATORY_STALE_KICKOFF, since it's an opt-in flag.

Indeed, the REGULATORY_IGNORE_STALE_KICKOFF would be the inversion, which
is really a better way to deal with this but Johannes considered it more
work. I'll leave it up to you but if the supported interfaces on a driver
work with it we should enable this by default. This is why the inversion
(REGULATORY_IGNORE_STALE_KICKOFF) would work better in the end, as we want
to keep this on by default and only let folks opt out.

 Luis