[panic] netmap(4) and if_lagg(4)

[Vincenzo Maffione]

Hi Harry,


2017-05-26 14:22 GMT+02:00 Harry Schmalzbauer <freebsd at omnilan.de>:

> Bezüglich Vincenzo Maffione's Nachricht vom 26.05.2017 11:06 (localtime):
> > Yes, it should integrate and compile out of the box, I've done that
> > several times with FreeBSD-11.0 and 10.3.
>
> Impressive, it needed just a small addition to sys/conf/files to make
> the linker happy :-)
>

Exactly!


>
> I also recomplied vale-ctl, but I get the following error when trying to
> add em0 (lagg-unrelated):
> 389.083433 [ 835] netmap_obj_malloc         netmap_ring request size
> 65792 too large
> 389.091593 [1693] netmap_mem2_rings_create  Cannot allocate RX_ring
>

It means that you are giving too many slot to each RX ring, probably 4096.
Try to use less slots, or to increase the dev.netmap.ring_size sysctl
(default value is less than 65792).


>
> Adding lagg still results in a panci, but with your latest
> "return()"-patch, it's different:
>
> 0xffffffff8042aefb is in freebsd_generic_rx_handler
> (/usr/local/share/deploy-tools/RELENG_11/src/sys/dev/
> netmap/netmap_freebsd.c:276).
> 271             struct netmap_generic_adapter *gna =
> 272                             (struct netmap_generic_adapter *)NA(ifp);
> 273             int stolen = generic_rx_handler(ifp, m);
> 274
> 275             if (!stolen) {
> 276                     gna->save_if_input(ifp, m);
> 277             }
> 278     }
> 279
> 280     /*
>
> KDB: stack backtrace:
> #0 0xffffffff805e4a17 at kdb_backtrace+0x67
> #1 0xffffffff805a34b6 at vpanic+0x186
> #2 0xffffffff805a3323 at panic+0x43
> #3 0xffffffff808a49b2 at trap_fatal+0x322
> #4 0xffffffff808a4a09 at trap_pfault+0x49
> #5 0xffffffff808a4246 at trap+0x286
> #6 0xffffffff8088a521 at calltrap+0x8
> #7 0xffffffff806aa3e0 at vlan_input+0x1f0
> #8 0xffffffff8069b298 at ether_demux+0x128
> #9 0xffffffff8069bf3b at ether_nh_input+0x31b
> #10 0xffffffff806b7c00 at netisr_dispatch_src+0xa0
> #11 0xffffffff8069b546 at ether_input+0x26
> #12 0xffffffff803a0278 at igb_rxeof+0x738
> #13 0xffffffff8039f63f at igb_msix_que+0x10f
> #14 0xffffffff8056ae1c at intr_event_execute_handlers+0xec
> #15 0xffffffff8056b106 at ithread_loop+0xd6
> #16 0xffffffff80568475 at fork_exit+0x85
> #17 0xffffffff8088aa5e at fork_trampoline+0xe
>
>
Yeah, the same bug jist slipped back. Discard the previous patch and
replace it with the attached one.

Cheers,
  Vincenzo


> Any hints how I can get adding em0 (lagg and vlan-less) via vale-ctl
> again? (netmap_obj_malloc netmap_ring request size 65792 too large)
>
> Thanks,
>
> -harry
>
>
>


-- 
Vincenzo Maffione
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 2-bugfix.patch
Type: text/x-patch
Size: 583 bytes
Desc: not available
URL: <http://lists.freebsd.org/pipermail/freebsd-net/attachments/20170528/05ab3609/attachment.bin>