Re: Broadcom bge(4) panics while shutting down

On Thu, May 14, 2009 at 5:00 PM, John Baldwin <jhb_at_freebsd.org> wrote:
> On Thursday 14 May 2009 3:47:16 pm Xin LI wrote:
>> Hi, Alexander,
>>
>> Alexander Sack wrote:
>> > Hello:
>> >
>> > Under heavy traffic (100% utilization GIGE on a 2 port BGE card)
>> > running BGE CURRENT driver I see panics on shutdown.  The reason is
>> > because bge_rxeof() while processing its RX ring of BD's drops the
>> > softc lock when it hands it off to its input function.  If bge_stop()
>> > is waiting for it, it will then proceed to acquire lock and then
>> > quiesce the hardware (reseting the card, clearing out BDs etc.).  Once
>> > bge_stop() releases the softc lock, then bge_rxeof() under an
>> > interrupt context (no polling here) will reacquire and continue to
>> > process the ring which is a bad idea.  It should check to see if the
>> > card is still running before continuing processing BDs (i.e. once
>> > IF_DRV_RUNNING has been reset by bge_stop(), bge_rxeof() is done, bail
>> > out).
>> >
>> > Here is my first go around with this patch:
>> >
>> >
>> > -- if_bge.c.CURRENT 2009-05-14 14:39:39.000000000 -0400
>> > +++ if_bge.c        2009-05-14 14:39:24.000000000 -0400
>> > _at__at_ -3081,6 +3081,10 _at__at_
>> >             uint16_t                vlan_tag = 0;
>> >             int                     have_tag = 0;
>> >
>> > +           if (!(ifp->if_drv_flags & IFF_DRV_RUNNING)) {
>> > +                   return;
>> > +           }
>> > +
>> >  #ifdef DEVICE_POLLING
>> >             if (ifp->if_capenable & IFCAP_POLLING) {
>> >                     if (sc->rxcycles <= 0)
>> >
>> >
>> > This prevents any panics during shutdown under heavy load and AS IT
>> > TURNS out (I feel stupid for not looking) that em(4) already had this
>> > check in its em_rxeof() function (right at the top of the loop).  I'm
>> > more than happy changing it to the em style but above seems reasonable
>> > to me though I have to verify there isn't anything missing off the
>> > loop from a hardware standpoint (I don't think so because bge_stop()
>> > did all the dirty work so I believe touching any registers after that
>> > from bge_rxeof() is a bad idea).
>> >
>> > Preliminary testing shows no more panics start and stopping ports
>> > under heavy load (panics were almost immediate otherwise).
>> >
>> > Thoughts?
>>
>> I think this would solve the problem but I'm not sure whether this would
>> increase some overhead on the RX path.  It seems that there is a race
>> between bge_release_resources() and bge_intr(), I mean, it might be a
>> good idea to "drain" bge_intr() instead?
>
> Usually just detach() drains the interrupt handler.  However, an 'ifconfig
> bge0 down' could probably provoke this as well.  I would probably do the
> check right after re-acquiring the lock at the bottom of the loop before
> touching anything else.

Yea John, you got a point about that.  I submitted the patch with the
check in the while logic thinking that which I BELIEVE is
functionality equivalent (don't ask me which one is faster), i.e. as
soon as we require it, check it since bge_stop() might have reset it.

If you get a chance, can you look at the PR and let me know if you
think it looks good?  I really want this fixed in 7.x to be honest
since its a pain in the headache (I was working on another subsystem
when I ran into this).

-aps