Re: [Qemu-devel] [BUG] Redhat-6.4_64bit-guest kernel panic with cpu-passthrough and guest numa

[Gonglei <arei.gonglei@huawei.com>]

On 2014/11/28 1:20, Paolo Bonzini wrote:

> 
> On 27/11/2014 14:00, Gonglei (Arei) wrote:
>>> >> 
>>> >> Running a redhat-6.4-64bit (kernel 2.6.32-358.el6.x86_64) or elder guest on
>>> >> qemu-2.1, with kvm enabled and -cpu host, non default cpu-topology and guest
>>> >> numa
>>> >> I'm seeing a reliable kernel panic from the guest shortly after boot. It is
>>> >> happening in
>>> >> find_busiest_group().
>>> >> 
>>> >> We also found it happend since commit
>>> >> 787aaf5703a702094f395db6795e74230282cd62 by git bisect.
>>> >> 
>>> >> The reproducer:
>>> >> 
>>> >> (1) full qemu cmd line:
>>> >> qemu-system-x86_64 -machine pc-i440fx-2.1,accel=kvm,usb=off \
>>> >> -cpu host -m 16384 \
>>> >> -smp 16,sockets=2,cores=4,threads=2 \
>>> >> -object memory-backend-ram,size=8192M,id=ram-node0 \
>>> >> -numa node,nodeid=0,cpus=0-7,memdev=ram-node0 \
>>> >> -object memory-backend-ram,size=8192M,id=ram-node1 \
>>> >> -numa node,nodeid=1,cpus=8-15,memdev=ram-node1 \
>>> >> -boot c -drive file=/data/wxin/vm/redhat_6.4_64 \
>>> >> -vnc 0.0.0.0:0 -device
>>> >> cirrus-vga,id=video0,vgamem_mb=8,bus=pci.0,addr=0x1.0x4 \
>>> >> -msg timestamp=on
>>> >> 
>>> >> (2)the guest kernel messages:
> Can you find what line of kernel/sched.c it is?

Yes, of course. See below please:
"sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power; "
in update_sg_lb_stats(), file sched.c, line 4094
And I can share the cause of we found. After commit 787aaf57(target-i386:
forward CPUID cache leaves when -cpu host is used), guest will get cpu cache
from host when -cpu host is used. But if we configure guest numa:
  node 0 cpus 0~7
  node 1 cpus 8~15
then the numa nodes lie in the same host cpu cache (cpus 0~16).
When the guest os boot, calculate group->cpu_power, but the guest find thoes
two different nodes own the same cache, then node1's group->cpu_power
will not be valued, just is the initial value '0'. And when vcpu is scheduled,
division by 0 causes kernel panic.

Regards,
-Gonglei