Re: [BUG] Current head of wireless testing unusable

[Maxim Levitsky <maximlevitsky@gmail.com>]

On Sun, 2009-07-26 at 01:31 +0300, Maxim Levitsky wrote:
> 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)
Except very frequent reconnects, 
"[  919.250097] No probe response from AP 00:1b:9e:d8:77:02 after 200ms, disconnecting."

Rest works fine.

Best regards,
	Maxim Levitsky

> 
> 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!
>