Return-path: Received: from mail-lb0-f180.google.com ([209.85.217.180]:41018 "EHLO mail-lb0-f180.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750945AbaKZP7H (ORCPT ); Wed, 26 Nov 2014 10:59:07 -0500 Received: by mail-lb0-f180.google.com with SMTP id l4so2706467lbv.11 for ; Wed, 26 Nov 2014 07:59:05 -0800 (PST) MIME-Version: 1.0 In-Reply-To: References: <1416754941-4439-1-git-send-email-arik@wizery.com> <20141125193846.GJ25677@wotan.suse.de> <20141126152810.GN25677@wotan.suse.de> From: "Luis R. Rodriguez" Date: Wed, 26 Nov 2014 10:58:45 -0500 Message-ID: (sfid-20141126_165911_931064_CDBA7F96) Subject: Re: [PATCH v3 1/3] cfg80211: leave invalid channels on regdomain change To: Arik Nemtsov 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 10:39 AM, Arik Nemtsov wrote: > 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, We agreed to not have to require this to be opt-out, that's different than having it enabled by default for supported devices. > 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. This is a generic feature and I think its important to enable it by default, if a different grace period can be used it sounds like you can easily fold that in as an alternative to override the default. Luis