Date: Thu, 20 Nov 2014 21:27:00 +0100
From: "Luis R. Rodriguez" <mcgrof@suse.com>
To: Arik Nemtsov <arik@wizery.com>
Cc: "linux-wireless@vger.kernel.org" <linux-wireless@vger.kernel.org>,
	Jonathan Doron <jond@wizery.com>
Subject: Re: [PATCH v2 3/4] cfg80211: allow wiphy specific regdomain
	management
Message-ID: <20141120202700.GO24486@wotan.suse.de> (sfid-20141120_212712_678946_DF1A2A57)
References: <1415895219-19848-1-git-send-email-arik@wizery.com> <1415895219-19848-3-git-send-email-arik@wizery.com> <20141113231137.GF24486@wotan.suse.de> <CA+XVXfd5ZsC3-6eEy=JYbvwm=S5ocdv=Mj1E7=sLMkwcba_x_w@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
In-Reply-To: <CA+XVXfd5ZsC3-6eEy=JYbvwm=S5ocdv=Mj1E7=sLMkwcba_x_w@mail.gmail.com>
Sender: linux-wireless-owner@vger.kernel.org

On Sun, Nov 16, 2014 at 01:06:00PM +0200, Arik Nemtsov wrote:
> On Fri, Nov 14, 2014 at 1:11 AM, Luis R. Rodriguez <mcgrof@suse.com> wrote:
> >> index a4d2792..656a1b1 100644
> >> --- a/net/wireless/core.c
> >> +++ b/net/wireless/core.c
> >> @@ -541,6 +541,13 @@ int wiphy_register(struct wiphy *wiphy)
> >>                   !wiphy->wowlan->tcp))
> >>               return -EINVAL;
> >>  #endif
> >> +     if (WARN_ON((wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) &&
> >> +                 (wiphy->regulatory_flags &
> >> +                  (REGULATORY_CUSTOM_REG | REGULATORY_STRICT_REG |
> >> +                   REGULATORY_COUNTRY_IE_FOLLOW_POWER |
> >> +                   REGULATORY_COUNTRY_IE_IGNORE |
> >> +                   REGULATORY_DISABLE_BEACON_HINTS))))
> >> +             return -EINVAL;
> >
> > Look at all those heuristics go away... That's alot. The documetnation should
> > reflect all this not being used because of this decision. I also want you to
> > think of the issues that may come up when combining devices that, one that
> > uses this feature and one that does not.
> 
> Since this is a private regdomain, I guess this just means the
> cfg80211 using device will be alone in the system for all regulatory
> purposes.
> I don't really see possible interoperability issues here. Am I missing
> something?

It means you can technically end up with two devices that operate with
different interpretation of rules, this can mean for example that some
expectations of having two devices may fail and since this will be all hard
coded you can't fix it.  The worst of the issues will be caused by the fact
that we simply won't know what issues will creep up until the two data sets
conflict and create an unexpected user facing issue. This is precicely why
having support for querying information about all regulatory data is critical,
and I'm glad you are doing that work.

What will happen when say a user / user interface wants to restrict all devices
to say a country like Israel, 'iw reg set IL' is used, so the cfg80211 regulatory
abiding devices follow the rules, but this Intel device does not?

 Luis