Return-path: Received: from cassarossa.samfundet.no ([193.35.52.29]:57926 "EHLO cassarossa.samfundet.no" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751679AbaIPXrt (ORCPT ); Tue, 16 Sep 2014 19:47:49 -0400 Date: Wed, 17 Sep 2014 01:47:43 +0200 From: "Steinar H. Gunderson" To: Johannes Berg Cc: linux-wireless@vger.kernel.org Subject: Re: [PATCH v6 2/2] mac80211: support DTPC IE (from Cisco Client eXtensions) Message-ID: <20140916234647.GA2238@sesse.net> (sfid-20140917_014752_317985_A204746F) References: <20140903133328.GC18933@sesse.net> <1410166400.7983.9.camel@jlt4.sipsolutions.net> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 In-Reply-To: <1410166400.7983.9.camel@jlt4.sipsolutions.net> Sender: linux-wireless-owner@vger.kernel.org List-ID: On Mon, Sep 08, 2014 at 10:53:20AM +0200, Johannes Berg wrote: >> Linux already supports 802.11h, where the access point can tell the >> client to reduce its transmission power. However, 802.11h is only >> defined for 5 GHz, where the need for this is much smaller than on >> 2.4 GHz. >> >> Cisco has their own solution, called DTPC (Dynamic Transmit Power >> Control). Cisco APs on a controller sometimes but not always send >> 802.11h; they always send DTPC, even on 2.4 GHz. This patch adds support >> for parsing and honoring the DTPC IE in addition to the 802.11h >> element (they do not always contain the same limits, so both must >> be honored); the format is not documented, but very simple. >> >> Tested (on top of wireless.git and on 3.16.1) against a Cisco Aironet >> 1142 joined to a Cisco 2504 WLC, by setting various transmit power >> levels for the given access points and observing the results. >> The Wireshark 802.11 dissector agrees with the interpretation of the >> element, except for negative numbers, which seem to never happen >> anyway. > Applied both. I found what I believe is an edge case: What happens if the element suddenly goes away from one beacon to another? Shouldn't there be a reset of the power level and then a new call to __ieee80211_recalc_txpower()? (If so, I believe this bug was already present in the code before my first patch, as I understand the existing logic.) /* Steinar */ -- Homepage: http://www.sesse.net/