On Fri, Feb 12, 2016 at 11:17 AM, Stefan Sperling <s...@stsp.name> wrote:
> On Fri, Feb 12, 2016 at 10:47:16AM -0500, Donald Allen wrote:
> > On Fri, Feb 12, 2016 at 10:45 AM, Chris Cappuccio <ch...@nmedia.net>
> wrote:
> >
> > > Donald Allen [donaldcal...@gmail.com] wrote:
> > > > On Feb 12, 2016 05:08, "Stefan Sperling" <s...@stsp.name> wrote:
> > > > >
> > > > > On Thu, Feb 11, 2016 at 08:42:21PM -0500, Donald Allen wrote:
> > > > > > When attempting to install the 2/8 snapshot on my Thinkpad
> x-250, I
> > > > chose
> > > > > > to configure the wireless network interface (iwm). This resulted
> in
> > > the
> > > > > > following:
> > > > > >
> > > > > > iwm0: could not read firmware iwm-7265-9 (error 2)
> > > > > > panic: attempt to execute user address 0x0 in supervisor mode
> > > > >
> > > > > Do you have a trace from ddb please?
> > > >
> > > > There was no entry to ddb. There was one additional message after the
> > > above:
> > > >
> > > > syncing disks... done
> > > >
> > > > and that was all she wrote. (I took a photo of the screen.)
> > > >
> > > > If you have a suggestion for how to get the trace, I will certainly
> try
> > > to
> > > > help. Or maybe build a kernel with some additional printfs to try to
> > > > isolate where this is happening?
> > >
> > > sysctl ddb.panic=1 ??
> > >
> >
> > Ah .. thank you. I'll give it a try.
> >
>
> No need. I could reproduce locally. The problem also shows up with
> a GENERIC kernel when the firmware is not installed.
>
> For some reason, the callbacks into the wireless stack aren't hooked
> up until after the firmware is loaded. There is no reason not do hook
> them up ealier. This diff fixes the crash for me.
>
Thanks.
I just used this exchange as an example to a friend who buys everything
Apple and then complains when their software is buggy. This is a perfect
example of how a direct negative feedback path makes software converge
quickly to correctness, something you don't get with the big proprietary
players like Apple, Microsoft, etc.
>
> Index: if_iwm.c
> ===================================================================
> RCS file: /cvs/src/sys/dev/pci/if_iwm.c,v
> retrieving revision 1.77
> diff -u -p -r1.77 if_iwm.c
> --- if_iwm.c 5 Feb 2016 16:08:44 -0000 1.77
> +++ if_iwm.c 12 Feb 2016 16:10:48 -0000
> @@ -6642,18 +6642,6 @@ iwm_preinit(struct iwm_softc *sc)
> printf("%s: could not set MAC address (error %d)\n",
> DEVNAME(sc), error);
>
> - ic->ic_node_alloc = iwm_node_alloc;
> -
> - /* Override 802.11 state transition machine. */
> - sc->sc_newstate = ic->ic_newstate;
> - ic->ic_newstate = iwm_newstate;
> - ic->ic_update_htprot = iwm_update_htprot;
> - ic->ic_ampdu_rx_start = iwm_ampdu_rx_start;
> - ic->ic_ampdu_rx_stop = iwm_ampdu_rx_stop;
> -#ifdef notyet
> - ic->ic_ampdu_tx_start = iwm_ampdu_tx_start;
> - ic->ic_ampdu_tx_stop = iwm_ampdu_tx_stop;
> -#endif
> ieee80211_media_init(ifp, iwm_media_change,
> ieee80211_media_status);
>
> return 0;
> @@ -6886,6 +6874,18 @@ iwm_attach(struct device *parent, struct
> task_set(&sc->ba_task, iwm_ba_task, sc);
> task_set(&sc->htprot_task, iwm_htprot_task, sc);
>
> + ic->ic_node_alloc = iwm_node_alloc;
> +
> + /* Override 802.11 state transition machine. */
> + sc->sc_newstate = ic->ic_newstate;
> + ic->ic_newstate = iwm_newstate;
> + ic->ic_update_htprot = iwm_update_htprot;
> + ic->ic_ampdu_rx_start = iwm_ampdu_rx_start;
> + ic->ic_ampdu_rx_stop = iwm_ampdu_rx_stop;
> +#ifdef notyet
> + ic->ic_ampdu_tx_start = iwm_ampdu_tx_start;
> + ic->ic_ampdu_tx_stop = iwm_ampdu_tx_stop;
> +#endif
> /*
> * We cannot read the MAC address without loading the
> * firmware from disk. Postpone until mountroot is done.
