Return-path: Received: from mail-wg0-f49.google.com ([74.125.82.49]:63418 "EHLO mail-wg0-f49.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750963AbaKZPjs (ORCPT ); Wed, 26 Nov 2014 10:39:48 -0500 Received: by mail-wg0-f49.google.com with SMTP id x12so4030024wgg.8 for ; Wed, 26 Nov 2014 07:39:47 -0800 (PST) MIME-Version: 1.0 In-Reply-To: <20141126152810.GN25677@wotan.suse.de> References: <1416754941-4439-1-git-send-email-arik@wizery.com> <20141125193846.GJ25677@wotan.suse.de> <20141126152810.GN25677@wotan.suse.de> From: Arik Nemtsov Date: Wed, 26 Nov 2014 17:39:31 +0200 Message-ID: (sfid-20141126_163956_975993_19A939FB) Subject: Re: [PATCH v3 1/3] cfg80211: leave invalid channels on regdomain change To: "Luis R. Rodriguez" Cc: "linux-wireless@vger.kernel.org" , Johannes Berg Content-Type: text/plain; charset=UTF-8 Sender: linux-wireless-owner@vger.kernel.org List-ID: On Wed, Nov 26, 2014 at 5:28 PM, Luis R. Rodriguez wrote: > 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 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 >> >> --- >> >> 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. I thought we agreed this to be opt-in, even if all interfaces are supported? I still think an untested driver might be hurt by this patch. For instance if it requires a different grace period, etc. Arik