Re: deadlock in ath9k, 3.3.0+ kernel.

[Ben Greear <greearb@candelatech.com>]

On 04/02/2012 08:52 PM, Sujith Manoharan wrote:
> Ben Greear wrote:
>> On 04/02/2012 09:34 AM, Manoharan, Sujith wrote:
>>> Patch sent:  http://marc.info/?l=linux-wireless&m=133282325727326&w=2
>>
>> My 3.3.0 ath9k code doesn't look like that patch at all.  Is some
>> extra back-porting needed for 3.3.0???
>>
>>
>> static void ath_node_attach(struct ath_softc *sc, struct ieee80211_sta *sta,
>> 			    struct ieee80211_vif *vif)
>> {
>> 	struct ath_node *an;
>> 	an = (struct ath_node *)sta->drv_priv;
>>
>> #ifdef CONFIG_ATH9K_DEBUGFS
>> 	spin_lock(&sc->nodes_lock);
>> 	list_add(&an->list,&sc->nodes);
>> 	spin_unlock(&sc->nodes_lock);
>> #endif
>> 	an->sta = sta;
>> 	an->vif = vif;
>> 	if (sc->sc_flags&  SC_OP_TXAGGR) {
>> 		ath_tx_node_init(sc, an);
>> 		an->maxampdu = 1<<  (IEEE80211_HT_MAX_AMPDU_FACTOR +
>> 				     sta->ht_cap.ampdu_factor);
>> 		an->mpdudensity = parse_mpdudensity(sta->ht_cap.ampdu_density);
>> 	}
>> }
>
> Yeah, this looks like a different issue. What does decodecode (in scripts/ in the kernel
> source tree) show ?

I'm updating to 3.3.1 and will see if I can reproduce the problem.  It could
well be that there was some initial condition that caused this..but nothing
was logged to /var/log/messages, and my serial console buffer didn't show
the start of the problem, so I have no way to tell.

So, I'll let you know if I can hit it again.

Thanks,
Ben

-- 
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc  http://www.candelatech.com