Return-path: Received: from fg-out-1718.google.com ([72.14.220.153]:32272 "EHLO fg-out-1718.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752393AbZGYWby (ORCPT ); Sat, 25 Jul 2009 18:31:54 -0400 Received: by fg-out-1718.google.com with SMTP id e12so288835fga.17 for ; Sat, 25 Jul 2009 15:31:54 -0700 (PDT) Subject: Re: [BUG] Current head of wireless testing unusable From: Maxim Levitsky To: Pavel Roskin Cc: linux-wireless , iwlwifi maling list In-Reply-To: <1248558755.11389.21.camel@mj> References: <1248531054.15242.16.camel@maxim-laptop> <1248558755.11389.21.camel@mj> Content-Type: text/plain Date: Sun, 26 Jul 2009 01:31:49 +0300 Message-Id: <1248561109.4753.9.camel@maxim-laptop> Mime-Version: 1.0 Sender: linux-wireless-owner@vger.kernel.org List-ID: On Sat, 2009-07-25 at 17:52 -0400, Pavel Roskin wrote: > On Sat, 2009-07-25 at 17:10 +0300, Maxim Levitsky wrote: > > I probably should work more to did these bugs out myself, but anyway I > > want to let you know what I currently see. > > > > First system oopses just after NM starts up, happens always, and after > > planting few test points bug happens somewhere in following lines. > > We are discussing a bug in the scan state machine in another thread, > which could have nasty consequences in not caught. And I don't quite > understand why my system was catching it immediately, maybe because I'm > using gcc 4.4, which has array bounds checking. Yea, there are two patches with same title for this, I applied the newer. Currently thanks to Johannes Berg, the patch [PATCH] nl80211: add missing parameter clearing Fixes this nasty oops, now wireless more or less works, but plenty of problems still, first it oopses on reconnect as inilialized from wpa_supplicant, second iwconfig misses most of its settings, and probably thus NM think signal level is zero. If I switch to good old wext in wpa_supplicant, it works just fine and none of above problems present (I recheck this again to be sure) Thanks, I soon run kmemcheck as well. Best regards, Maxim Levitsky > > I have also seen two oopses in the code unrelated to wireless > networking, one of which lead to my .bash_history becoming empty. > > So please be extra careful. It would be great if somebody could test > the current kernel extensively with kmemcheck an other options and > bisect the bad commit, whether it's wireless related or not. Thanks!