[Bug 204340] [panic] nfsd, em, msix, fatal trap 9

[bugzilla-noreply at freebsd.org]

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=204340

Andriy Gapon <avg at FreeBSD.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |avg at FreeBSD.org

--- Comment #17 from Andriy Gapon <avg at FreeBSD.org> ---
Rick,
we got what looks like a very similar crash in FreeBSD 10.3:

db_trace_self_wrapper+0x2a
kdb_backtrace+0x37
vpanic+0xf7
panic+0x67
trap_fatal+0x264
trap_pfault+0x216
trap+0x32b
calltrap+0x8
__mtx_lock_sleep+0xa2
xprt_active+0xe7
svc_vc_soupcall+0x25
sowakeup+0x69
tcp_do_segment+0x319e
tcp_input+0x701
ip_input+0x14c
netisr_dispatch_src+0x228
ether_demux+0x1a5
ether_nh_input+0x1fc
netisr_dispatch_src+0x228
tcp_lro_flush+0x2b
ixgbe_rxeof+0x30d
ixgbe_msix_que+0x88
intr_event_execute_handlers+0x102
ithread_loop+0x9a
fork_exit+0x11f
fork_trampoline+0xe

It's this lock:
void                                                                            
xprt_active(SVCXPRT *xprt)                                                      
{                                                                               
        SVCGROUP *grp = xprt->xp_group;                                         

        mtx_lock(&grp->sg_lock);

Do you have any suggestions?
Thank you!

-- 
You are receiving this mail because:
You are on the CC list for the bug.