Re: CURRENT (r316844): Fatal trap 12: page fault while in kernel mode (syslogd)

On Sat, Apr 15, 2017 at 11:18:41AM +0200, O. Hartmann wrote:
> Am Fri, 14 Apr 2017 20:18:57 +0300
> Konstantin Belousov <kostikbel_at_gmail.com> schrieb:
> 
> > On Fri, Apr 14, 2017 at 06:58:27PM +0200, O. Hartmann wrote:
> > > Fatal trap 12: page fault while in kernel mode
> > > cpuid = 2; apic id = 02
> > > fault virtual address   = 0xfffff8001282fb00
> > > fault code              = supervisor read instruction, protection violation  
> > 
> > > ??() at 0xfffff8001282fb00
> > > bpf_mtap() at bpf_mtap+0x1ab/frame 0xfffffe012d2aefb0
> > > iflib_txq_drain() at iflib_txq_drain+0x1383/frame 0xfffffe012d2af130
> > > drain_ring_lockless() at drain_ring_lockless+0xc0/frame 0xfffffe012d2af190
> > > ifmp_ring_enqueue() at ifmp_ring_enqueue+0x32e/frame 0xfffffe012d2af200
> > > iflib_if_transmit() at iflib_if_transmit+0xb0/frame 0xfffffe012d2af240
> > > ether_output() at ether_output+0x730/frame 0xfffffe012d2af2e0
> > > arprequest() at arprequest+0x426/frame 0xfffffe012d2af3e0
> > > arpresolve_full() at arpresolve_full+0x3d1/frame 0xfffffe012d2af460
> > > arpresolve() at arpresolve+0x10c/frame 0xfffffe012d2af4d0
> > > ether_output() at ether_output+0x4e1/frame 0xfffffe012d2af570
> > > ip_output() at ip_output+0x14e6/frame 0xfffffe012d2af6b0
> > > udp_send() at udp_send+0xab1/frame 0xfffffe012d2af780
> > > sosend_dgram() at sosend_dgram+0x3e4/frame 0xfffffe012d2af7f0
> > > kern_sendit() at kern_sendit+0x229/frame 0xfffffe012d2af890
> > > sendit() at sendit+0x1a7/frame 0xfffffe012d2af8e0
> > > sys_sendto() at sys_sendto+0x4d/frame 0xfffffe012d2af930
> > > amd64_syscall() at amd64_syscall+0x4c2/frame 0xfffffe012d2afab0
> > > Xfast_syscall() at Xfast_syscall+0xfb/frame 0xfffffe012d2afab0
> > > syscall (133, FreeBSD ELF64, sys_sendto), rip = 0x800b8a5fa, rsp = 0x7fffffffd6b8,
> > > rbp = 0x7fffffffdcc0 ---  
> > 
> > You probably have BPF_JITTER option in your kernel config.  Either set
> > net.bpf_jitter.enable to 0 for now, or remove the option.
> > 
> > It is due to r316767. The issue is known and a solution is being discussed.
> 
> simply setting "net.bpf_jitter.enable=0" in /boot/loader.conf.local doesn't help, the
> Trap 12 still occurs.

It is sysctl, not tunable.