Patchwork [10/12] virtio-net: multiqueue support

login
register
mail settings
Submitter Jason Wang
Date Jan. 10, 2013, 6:43 a.m.
Message ID <1606987.aihbek5aXM@jason-thinkpad-t430s>
Download mbox | patch
Permalink /patch/210938/
State New
Headers show

Comments

Jason Wang - Jan. 10, 2013, 6:43 a.m.
On Wednesday, January 09, 2013 11:26:33 PM Jason Wang wrote:
> On 01/09/2013 06:01 PM, Wanlong Gao wrote:
> > On 01/09/2013 05:30 PM, Jason Wang wrote:
> >> On 01/09/2013 04:23 PM, Wanlong Gao wrote:
> >>> On 01/08/2013 06:14 PM, Jason Wang wrote:
> >>>> On 01/08/2013 06:00 PM, Wanlong Gao wrote:
> >>>>> On 01/08/2013 05:51 PM, Jason Wang wrote:
> >>>>>> On 01/08/2013 05:49 PM, Wanlong Gao wrote:
> >>>>>>> On 01/08/2013 05:29 PM, Jason Wang wrote:
> >>>>>>>> On 01/08/2013 05:07 PM, Wanlong Gao wrote:
> >>>>>>>>> On 12/28/2012 06:32 PM, Jason Wang wrote:
> >>>>>>>>>> +    } else if (nc->peer->info->type != 
> >>>>>>>>>> NET_CLIENT_OPTIONS_KIND_TAP) {
> >>>>>>>>>> +        ret = -1;
> >>>>>>>>>> +    } else {
> >>>>>>>>>> +        ret = tap_detach(nc->peer);
> >>>>>>>>>> +    }
> >>>>>>>>>> +
> >>>>>>>>>> +    return ret;
> >>>>>>>>>> +}
> >>>>>>>>>> +
[...]
> >>> I got guest kernel panic when using this way and set queues=4.
> >> 
> >> Does it happens w/o or w/ a fd parameter? What's the qemu command line?
> >> Did you meet it during boot time?
> > 
> > The QEMU command line is
> > 
> > /work/git/qemu/x86_64-softmmu/qemu-system-x86_64 -name f17 -M pc-0.15
> > -enable-kvm -m 3096 \ -smp 4,sockets=4,cores=1,threads=1 \
> > -uuid c31a9f3e-4161-c53a-339c-5dc36d0497cb -no-user-config -nodefaults \
> > -chardev
> > socket,id=charmonitor,path=/var/lib/libvirt/qemu/f17.monitor,server,nowai
> > t \ -mon chardev=charmonitor,id=monitor,mode=control \
> > -rtc base=utc -no-shutdown \
> > -device piix3-usb-uhci,id=usb,bus=pci.0,addr=0x1.0x2 \
> > -device
> > virtio-scsi-pci,id=scsi0,bus=pci.0,addr=0xb,num_queues=4,hotplug=on \
> > -device virtio-serial-pci,id=virtio-serial0,bus=pci.0,addr=0x5 \
> > -drive file=/vm/f17.img,if=none,id=drive-virtio-disk0,format=qcow2 \
> > -device
> > virtio-blk-pci,scsi=off,bus=pci.0,addr=0x6,drive=drive-virtio-disk0,id=vi
> > rtio-disk0,bootindex=1 \ -drive
> > file=/vm2/f17-kernel.img,if=none,id=drive-virtio-disk1,format=qcow2 \
> > -device
> > virtio-blk-pci,scsi=off,bus=pci.0,addr=0x8,drive=drive-virtio-disk1,id=vi
> > rtio-disk1 \ -drive
> > file=/vm/virtio-scsi/scsi3.img,if=none,id=drive-scsi0-0-2-0,format=raw \
> > -device
> > scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=2,drive=drive-scsi0-0-2-0,id=
> > scsi0-0-2-0,removable=on \ -drive
> > file=/vm/virtio-scsi/scsi4.img,if=none,id=drive-scsi0-0-3-0,format=raw \
> > -device
> > scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=3,drive=drive-scsi0-0-3-0,id=
> > scsi0-0-3-0 \ -drive
> > file=/vm/virtio-scsi/scsi1.img,if=none,id=drive-scsi0-0-0-0,format=raw \
> > -device
> > scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0-0-0-0,id=
> > scsi0-0-0-0 \ -drive
> > file=/vm/virtio-scsi/scsi2.img,if=none,id=drive-scsi0-0-1-0,format=raw \
> > -device
> > scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=1,drive=drive-scsi0-0-1-0,id=
> > scsi0-0-1-0 \ -chardev pty,id=charserial0 -device
> > isa-serial,chardev=charserial0,id=serial0 \ -chardev
> > file,id=charserial1,path=/vm/f17.log \
> > -device isa-serial,chardev=charserial1,id=serial1 \
> > -device usb-tablet,id=input0 -vga std \
> > -device virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x7 \
> > -netdev tap,id=hostnet0,vhost=on,queues=4 \
> > -device
> > virtio-net-pci,netdev=hostnet0,id=net0,mac=52:54:00:ce:7b:29,bus=pci.0,ad
> > dr=0x3 \ -monitor stdio
> > 
> > I got panic just after booting the system, did nothing,  waited for a
> > while, the guest panicked.
> > 
> > [   28.053004] BUG: soft lockup - CPU#1 stuck for 23s! [ip:592]
> > [   28.053004] Modules linked in: ip6t_REJECT nf_conntrack_ipv6
> > nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables uinput
> > joydev microcode virtio_balloon pcspkr virtio_net i2c_piix4 i2c_core
> > virtio_scsi virtio_blk floppy [   28.053004] CPU 1
> > [   28.053004] Pid: 592, comm: ip Not tainted 3.8.0-rc1-net+ #3 Bochs
> > Bochs
> > [   28.053004] RIP: 0010:[<ffffffff8137a9ab>]  [<ffffffff8137a9ab>]
> > virtqueue_get_buf+0xb/0x120 [   28.053004] RSP: 0018:ffff8800bc913550 
> > EFLAGS: 00000246
> > [   28.053004] RAX: 0000000000000000 RBX: ffff8800bc49c000 RCX:
> > ffff8800bc49e000 [   28.053004] RDX: 0000000000000000 RSI:
> > ffff8800bc913584 RDI: ffff8800bcfd4000 [   28.053004] RBP:
> > ffff8800bc913558 R08: ffff8800bcfd0800 R09: 0000000000000000 [  
> > 28.053004] R10: ffff8800bc49c000 R11: ffff880036cc4de0 R12:
> > ffff8800bcfd4000 [   28.053004] R13: ffff8800bc913558 R14:
> > ffffffff8137ad73 R15: 00000000000200d0 [   28.053004] FS: 
> > 00007fb27a589740(0000) GS:ffff8800c1480000(0000) knlGS:0000000000000000 [
> >   28.053004] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> > [   28.053004] CR2: 0000000000640530 CR3: 00000000baeff000 CR4:
> > 00000000000006e0 [   28.053004] DR0: 0000000000000000 DR1:
> > 0000000000000000 DR2: 0000000000000000 [   28.053004] DR3:
> > 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [  
> > 28.053004] Process ip (pid: 592, threadinfo ffff8800bc912000, task
> > ffff880036da2e20) [   28.053004] Stack:
> > [   28.053004]  ffff8800bcfd0800 ffff8800bc913638 ffffffffa003e9bb
> > ffff8800bc913656 [   28.053004]  0000000100000002 ffff8800c17ebb08
> > 000000500000ff10 ffffea0002f244c0 [   28.053004]  0000000200000582
> > 0000000000000000 0000000000000000 ffffea0002f244c0 [   28.053004] Call
> > Trace:
> > [   28.053004]  [<ffffffffa003e9bb>]
> > virtnet_send_command.constprop.26+0x24b/0x270 [virtio_net] [   28.053004]
> >  [<ffffffff812ed963>] ? sg_init_table+0x23/0x50
> > [   28.053004]  [<ffffffffa0040629>] virtnet_set_rx_mode+0x99/0x300
> > [virtio_net] [   28.053004]  [<ffffffff8152306f>]
> > __dev_set_rx_mode+0x5f/0xb0
> > [   28.053004]  [<ffffffff815230ef>] dev_set_rx_mode+0x2f/0x50
> > [   28.053004]  [<ffffffff815231b7>] __dev_open+0xa7/0xf0
> > [   28.053004]  [<ffffffff81523461>] __dev_change_flags+0xa1/0x180
> > [   28.053004]  [<ffffffff815235f8>] dev_change_flags+0x28/0x70
> > [   28.053004]  [<ffffffff8152ff20>] do_setlink+0x3b0/0xa50
> > [   28.053004]  [<ffffffff812fb6b1>] ? nla_parse+0x31/0xe0
> > [   28.053004]  [<ffffffff815325de>] rtnl_newlink+0x36e/0x580
> > [   28.053004]  [<ffffffff811355cc>] ? get_page_from_freelist+0x37c/0x730
> > [   28.053004]  [<ffffffff81531e13>] rtnetlink_rcv_msg+0x113/0x2f0
> > [   28.053004]  [<ffffffff8117d973>] ?
> > __kmalloc_node_track_caller+0x63/0x1c0 [   28.053004] 
> > [<ffffffff8151526b>] ? __alloc_skb+0x8b/0x2a0
> > [   28.053004]  [<ffffffff81531d00>] ? __rtnl_unlock+0x20/0x20
> > [   28.053004]  [<ffffffff8154b571>] netlink_rcv_skb+0xb1/0xc0
> > [   28.053004]  [<ffffffff8152ea05>] rtnetlink_rcv+0x25/0x40
> > [   28.053004]  [<ffffffff8154ae91>] netlink_unicast+0x1a1/0x220
> > [   28.053004]  [<ffffffff8154b211>] netlink_sendmsg+0x301/0x3c0
> > [   28.053004]  [<ffffffff81508530>] sock_sendmsg+0xb0/0xe0
> > [   28.053004]  [<ffffffff8113a45b>] ? lru_cache_add_lru+0x3b/0x60
> > [   28.053004]  [<ffffffff811608b7>] ? page_add_new_anon_rmap+0xc7/0x180
> > [   28.053004]  [<ffffffff81509efc>] __sys_sendmsg+0x3ac/0x3c0
> > [   28.053004]  [<ffffffff8162e47c>] ? __do_page_fault+0x23c/0x4d0
> > [   28.053004]  [<ffffffff8115c9ef>] ? do_brk+0x1ff/0x370
> > [   28.053004]  [<ffffffff8150bec9>] sys_sendmsg+0x49/0x90
> > [   28.053004]  [<ffffffff81632d59>] system_call_fastpath+0x16/0x1b
> > [   28.053004] Code: 04 0f ae f0 48 8b 47 50 5d 0f b7 50 02 66 39 57 64 0f
> > 94 c0 c3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41
> > 54 <53> 80 7f 59 00 48 89 fb 0f 85 90 00 00 00 48 8b 47 50 0f b7 50
> > 
> > 
> > The QEMU tree I used is git://github.com/jasowang/qemu.git
> 
> Thanks a lot, will try to reproduce my self tomorrow. From the
> calltrace, looks like we send a command to a rx/tx queue.

Right, the virtqueue that will not be used by single queue were initialized.
Please try to following patch or use the my qemu.git with this fix in github.
Wanlong Gao - Jan. 10, 2013, 6:49 a.m.
On 01/10/2013 02:43 PM, Jason Wang wrote:
> On Wednesday, January 09, 2013 11:26:33 PM Jason Wang wrote:
>> On 01/09/2013 06:01 PM, Wanlong Gao wrote:
>>> On 01/09/2013 05:30 PM, Jason Wang wrote:
>>>> On 01/09/2013 04:23 PM, Wanlong Gao wrote:
>>>>> On 01/08/2013 06:14 PM, Jason Wang wrote:
>>>>>> On 01/08/2013 06:00 PM, Wanlong Gao wrote:
>>>>>>> On 01/08/2013 05:51 PM, Jason Wang wrote:
>>>>>>>> On 01/08/2013 05:49 PM, Wanlong Gao wrote:
>>>>>>>>> On 01/08/2013 05:29 PM, Jason Wang wrote:
>>>>>>>>>> On 01/08/2013 05:07 PM, Wanlong Gao wrote:
>>>>>>>>>>> On 12/28/2012 06:32 PM, Jason Wang wrote:
>>>>>>>>>>>> +    } else if (nc->peer->info->type != 
>>>>>>>>>>>> NET_CLIENT_OPTIONS_KIND_TAP) {
>>>>>>>>>>>> +        ret = -1;
>>>>>>>>>>>> +    } else {
>>>>>>>>>>>> +        ret = tap_detach(nc->peer);
>>>>>>>>>>>> +    }
>>>>>>>>>>>> +
>>>>>>>>>>>> +    return ret;
>>>>>>>>>>>> +}
>>>>>>>>>>>> +
> [...]
>>>>> I got guest kernel panic when using this way and set queues=4.
>>>>
>>>> Does it happens w/o or w/ a fd parameter? What's the qemu command line?
>>>> Did you meet it during boot time?
>>>
>>> The QEMU command line is
>>>
>>> /work/git/qemu/x86_64-softmmu/qemu-system-x86_64 -name f17 -M pc-0.15
>>> -enable-kvm -m 3096 \ -smp 4,sockets=4,cores=1,threads=1 \
>>> -uuid c31a9f3e-4161-c53a-339c-5dc36d0497cb -no-user-config -nodefaults \
>>> -chardev
>>> socket,id=charmonitor,path=/var/lib/libvirt/qemu/f17.monitor,server,nowai
>>> t \ -mon chardev=charmonitor,id=monitor,mode=control \
>>> -rtc base=utc -no-shutdown \
>>> -device piix3-usb-uhci,id=usb,bus=pci.0,addr=0x1.0x2 \
>>> -device
>>> virtio-scsi-pci,id=scsi0,bus=pci.0,addr=0xb,num_queues=4,hotplug=on \
>>> -device virtio-serial-pci,id=virtio-serial0,bus=pci.0,addr=0x5 \
>>> -drive file=/vm/f17.img,if=none,id=drive-virtio-disk0,format=qcow2 \
>>> -device
>>> virtio-blk-pci,scsi=off,bus=pci.0,addr=0x6,drive=drive-virtio-disk0,id=vi
>>> rtio-disk0,bootindex=1 \ -drive
>>> file=/vm2/f17-kernel.img,if=none,id=drive-virtio-disk1,format=qcow2 \
>>> -device
>>> virtio-blk-pci,scsi=off,bus=pci.0,addr=0x8,drive=drive-virtio-disk1,id=vi
>>> rtio-disk1 \ -drive
>>> file=/vm/virtio-scsi/scsi3.img,if=none,id=drive-scsi0-0-2-0,format=raw \
>>> -device
>>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=2,drive=drive-scsi0-0-2-0,id=
>>> scsi0-0-2-0,removable=on \ -drive
>>> file=/vm/virtio-scsi/scsi4.img,if=none,id=drive-scsi0-0-3-0,format=raw \
>>> -device
>>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=3,drive=drive-scsi0-0-3-0,id=
>>> scsi0-0-3-0 \ -drive
>>> file=/vm/virtio-scsi/scsi1.img,if=none,id=drive-scsi0-0-0-0,format=raw \
>>> -device
>>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0-0-0-0,id=
>>> scsi0-0-0-0 \ -drive
>>> file=/vm/virtio-scsi/scsi2.img,if=none,id=drive-scsi0-0-1-0,format=raw \
>>> -device
>>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=1,drive=drive-scsi0-0-1-0,id=
>>> scsi0-0-1-0 \ -chardev pty,id=charserial0 -device
>>> isa-serial,chardev=charserial0,id=serial0 \ -chardev
>>> file,id=charserial1,path=/vm/f17.log \
>>> -device isa-serial,chardev=charserial1,id=serial1 \
>>> -device usb-tablet,id=input0 -vga std \
>>> -device virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x7 \
>>> -netdev tap,id=hostnet0,vhost=on,queues=4 \
>>> -device
>>> virtio-net-pci,netdev=hostnet0,id=net0,mac=52:54:00:ce:7b:29,bus=pci.0,ad
>>> dr=0x3 \ -monitor stdio
>>>
>>> I got panic just after booting the system, did nothing,  waited for a
>>> while, the guest panicked.
>>>
>>> [   28.053004] BUG: soft lockup - CPU#1 stuck for 23s! [ip:592]
>>> [   28.053004] Modules linked in: ip6t_REJECT nf_conntrack_ipv6
>>> nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables uinput
>>> joydev microcode virtio_balloon pcspkr virtio_net i2c_piix4 i2c_core
>>> virtio_scsi virtio_blk floppy [   28.053004] CPU 1
>>> [   28.053004] Pid: 592, comm: ip Not tainted 3.8.0-rc1-net+ #3 Bochs
>>> Bochs
>>> [   28.053004] RIP: 0010:[<ffffffff8137a9ab>]  [<ffffffff8137a9ab>]
>>> virtqueue_get_buf+0xb/0x120 [   28.053004] RSP: 0018:ffff8800bc913550 
>>> EFLAGS: 00000246
>>> [   28.053004] RAX: 0000000000000000 RBX: ffff8800bc49c000 RCX:
>>> ffff8800bc49e000 [   28.053004] RDX: 0000000000000000 RSI:
>>> ffff8800bc913584 RDI: ffff8800bcfd4000 [   28.053004] RBP:
>>> ffff8800bc913558 R08: ffff8800bcfd0800 R09: 0000000000000000 [  
>>> 28.053004] R10: ffff8800bc49c000 R11: ffff880036cc4de0 R12:
>>> ffff8800bcfd4000 [   28.053004] R13: ffff8800bc913558 R14:
>>> ffffffff8137ad73 R15: 00000000000200d0 [   28.053004] FS: 
>>> 00007fb27a589740(0000) GS:ffff8800c1480000(0000) knlGS:0000000000000000 [
>>>   28.053004] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
>>> [   28.053004] CR2: 0000000000640530 CR3: 00000000baeff000 CR4:
>>> 00000000000006e0 [   28.053004] DR0: 0000000000000000 DR1:
>>> 0000000000000000 DR2: 0000000000000000 [   28.053004] DR3:
>>> 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [  
>>> 28.053004] Process ip (pid: 592, threadinfo ffff8800bc912000, task
>>> ffff880036da2e20) [   28.053004] Stack:
>>> [   28.053004]  ffff8800bcfd0800 ffff8800bc913638 ffffffffa003e9bb
>>> ffff8800bc913656 [   28.053004]  0000000100000002 ffff8800c17ebb08
>>> 000000500000ff10 ffffea0002f244c0 [   28.053004]  0000000200000582
>>> 0000000000000000 0000000000000000 ffffea0002f244c0 [   28.053004] Call
>>> Trace:
>>> [   28.053004]  [<ffffffffa003e9bb>]
>>> virtnet_send_command.constprop.26+0x24b/0x270 [virtio_net] [   28.053004]
>>>  [<ffffffff812ed963>] ? sg_init_table+0x23/0x50
>>> [   28.053004]  [<ffffffffa0040629>] virtnet_set_rx_mode+0x99/0x300
>>> [virtio_net] [   28.053004]  [<ffffffff8152306f>]
>>> __dev_set_rx_mode+0x5f/0xb0
>>> [   28.053004]  [<ffffffff815230ef>] dev_set_rx_mode+0x2f/0x50
>>> [   28.053004]  [<ffffffff815231b7>] __dev_open+0xa7/0xf0
>>> [   28.053004]  [<ffffffff81523461>] __dev_change_flags+0xa1/0x180
>>> [   28.053004]  [<ffffffff815235f8>] dev_change_flags+0x28/0x70
>>> [   28.053004]  [<ffffffff8152ff20>] do_setlink+0x3b0/0xa50
>>> [   28.053004]  [<ffffffff812fb6b1>] ? nla_parse+0x31/0xe0
>>> [   28.053004]  [<ffffffff815325de>] rtnl_newlink+0x36e/0x580
>>> [   28.053004]  [<ffffffff811355cc>] ? get_page_from_freelist+0x37c/0x730
>>> [   28.053004]  [<ffffffff81531e13>] rtnetlink_rcv_msg+0x113/0x2f0
>>> [   28.053004]  [<ffffffff8117d973>] ?
>>> __kmalloc_node_track_caller+0x63/0x1c0 [   28.053004] 
>>> [<ffffffff8151526b>] ? __alloc_skb+0x8b/0x2a0
>>> [   28.053004]  [<ffffffff81531d00>] ? __rtnl_unlock+0x20/0x20
>>> [   28.053004]  [<ffffffff8154b571>] netlink_rcv_skb+0xb1/0xc0
>>> [   28.053004]  [<ffffffff8152ea05>] rtnetlink_rcv+0x25/0x40
>>> [   28.053004]  [<ffffffff8154ae91>] netlink_unicast+0x1a1/0x220
>>> [   28.053004]  [<ffffffff8154b211>] netlink_sendmsg+0x301/0x3c0
>>> [   28.053004]  [<ffffffff81508530>] sock_sendmsg+0xb0/0xe0
>>> [   28.053004]  [<ffffffff8113a45b>] ? lru_cache_add_lru+0x3b/0x60
>>> [   28.053004]  [<ffffffff811608b7>] ? page_add_new_anon_rmap+0xc7/0x180
>>> [   28.053004]  [<ffffffff81509efc>] __sys_sendmsg+0x3ac/0x3c0
>>> [   28.053004]  [<ffffffff8162e47c>] ? __do_page_fault+0x23c/0x4d0
>>> [   28.053004]  [<ffffffff8115c9ef>] ? do_brk+0x1ff/0x370
>>> [   28.053004]  [<ffffffff8150bec9>] sys_sendmsg+0x49/0x90
>>> [   28.053004]  [<ffffffff81632d59>] system_call_fastpath+0x16/0x1b
>>> [   28.053004] Code: 04 0f ae f0 48 8b 47 50 5d 0f b7 50 02 66 39 57 64 0f
>>> 94 c0 c3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41
>>> 54 <53> 80 7f 59 00 48 89 fb 0f 85 90 00 00 00 48 8b 47 50 0f b7 50
>>>
>>>
>>> The QEMU tree I used is git://github.com/jasowang/qemu.git
>>
>> Thanks a lot, will try to reproduce my self tomorrow. From the
>> calltrace, looks like we send a command to a rx/tx queue.
> 
> Right, the virtqueue that will not be used by single queue were initialized.
> Please try to following patch or use the my qemu.git with this fix in github.

It's odd, why didn't I get guest panic by using your python start script this morning?

Thanks,
Wanlong Gao

> 
> diff --git a/hw/virtio-net.c b/hw/virtio-net.c
> index 8b4f079..cfd9af1 100644
> --- a/hw/virtio-net.c
> +++ b/hw/virtio-net.c
> @@ -186,7 +186,7 @@ static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
>              continue;
>          }
>  
> -        if (virtio_net_started(n, status) && !q->vhost_started) {
> +        if (virtio_net_started(n, queue_status) && !q->vhost_started) {
>              if (q->tx_timer) {
>                  qemu_mod_timer(q->tx_timer,
>                                 qemu_get_clock_ns(vm_clock) + n->tx_timeout);
> @@ -545,7 +545,8 @@ static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd,
>  
>      if (s.virtqueue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN ||
>          s.virtqueue_pairs > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX ||
> -        s.virtqueue_pairs > n->max_queues) {
> +        s.virtqueue_pairs > n->max_queues ||
> +        !n->multiqueue) {
>          return VIRTIO_NET_ERR;
>      }
>  
> @@ -1026,19 +1027,15 @@ static void virtio_net_tx_bh(void *opaque)
>  static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue, int ctrl)
>  {
>      VirtIODevice *vdev = &n->vdev;
> -    int i;
> +    int i, max = multiqueue ? n->max_queues : 1;
>  
>      n->multiqueue = multiqueue;
>  
> -    if (!multiqueue) {
> -        n->max_queues = 1;
> -    }
> -
>      for (i = 2; i <= n->max_queues * 2 + 1; i++) {
>          virtio_del_queue(vdev, i);
>      }
>  
> -    for (i = 1; i < n->max_queues; i++) {
> +    for (i = 1; i < max; i++) {
>          n->vqs[i].rx_vq = virtio_add_queue(vdev, 256, virtio_net_handle_rx);
>          if (n->vqs[i].tx_timer) {
>              n->vqs[i].tx_vq =
>
Jason Wang - Jan. 10, 2013, 7:16 a.m.
On Thursday, January 10, 2013 02:49:14 PM Wanlong Gao wrote:
> On 01/10/2013 02:43 PM, Jason Wang wrote:
> > On Wednesday, January 09, 2013 11:26:33 PM Jason Wang wrote:
> >> On 01/09/2013 06:01 PM, Wanlong Gao wrote:
> >>> On 01/09/2013 05:30 PM, Jason Wang wrote:
> >>>> On 01/09/2013 04:23 PM, Wanlong Gao wrote:
> >>>>> On 01/08/2013 06:14 PM, Jason Wang wrote:
> >>>>>> On 01/08/2013 06:00 PM, Wanlong Gao wrote:
> >>>>>>> On 01/08/2013 05:51 PM, Jason Wang wrote:
> >>>>>>>> On 01/08/2013 05:49 PM, Wanlong Gao wrote:
> >>>>>>>>> On 01/08/2013 05:29 PM, Jason Wang wrote:
> >>>>>>>>>> On 01/08/2013 05:07 PM, Wanlong Gao wrote:
> >>>>>>>>>>> On 12/28/2012 06:32 PM, Jason Wang wrote:
> >>>>>>>>>>>> +    } else if (nc->peer->info->type !=
> >>>>>>>>>>>> NET_CLIENT_OPTIONS_KIND_TAP) {
> >>>>>>>>>>>> +        ret = -1;
> >>>>>>>>>>>> +    } else {
> >>>>>>>>>>>> +        ret = tap_detach(nc->peer);
> >>>>>>>>>>>> +    }
> >>>>>>>>>>>> +
> >>>>>>>>>>>> +    return ret;
> >>>>>>>>>>>> +}
> >>>>>>>>>>>> +
> > 
> > [...]
> > 
> >>>>> I got guest kernel panic when using this way and set queues=4.
> >>>> 
> >>>> Does it happens w/o or w/ a fd parameter? What's the qemu command line?
> >>>> Did you meet it during boot time?
> >>> 
> >>> The QEMU command line is
> >>> 
> >>> /work/git/qemu/x86_64-softmmu/qemu-system-x86_64 -name f17 -M pc-0.15
> >>> -enable-kvm -m 3096 \ -smp 4,sockets=4,cores=1,threads=1 \
> >>> -uuid c31a9f3e-4161-c53a-339c-5dc36d0497cb -no-user-config -nodefaults \
> >>> -chardev
> >>> socket,id=charmonitor,path=/var/lib/libvirt/qemu/f17.monitor,server,nowa
> >>> i
> >>> t \ -mon chardev=charmonitor,id=monitor,mode=control \
> >>> -rtc base=utc -no-shutdown \
> >>> -device piix3-usb-uhci,id=usb,bus=pci.0,addr=0x1.0x2 \
> >>> -device
> >>> virtio-scsi-pci,id=scsi0,bus=pci.0,addr=0xb,num_queues=4,hotplug=on \
> >>> -device virtio-serial-pci,id=virtio-serial0,bus=pci.0,addr=0x5 \
> >>> -drive file=/vm/f17.img,if=none,id=drive-virtio-disk0,format=qcow2 \
> >>> -device
> >>> virtio-blk-pci,scsi=off,bus=pci.0,addr=0x6,drive=drive-virtio-disk0,id=v
> >>> i
> >>> rtio-disk0,bootindex=1 \ -drive
> >>> file=/vm2/f17-kernel.img,if=none,id=drive-virtio-disk1,format=qcow2 \
> >>> -device
> >>> virtio-blk-pci,scsi=off,bus=pci.0,addr=0x8,drive=drive-virtio-disk1,id=v
> >>> i
> >>> rtio-disk1 \ -drive
> >>> file=/vm/virtio-scsi/scsi3.img,if=none,id=drive-scsi0-0-2-0,format=raw \
> >>> -device
> >>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=2,drive=drive-scsi0-0-2-0,id
> >>> =
> >>> scsi0-0-2-0,removable=on \ -drive
> >>> file=/vm/virtio-scsi/scsi4.img,if=none,id=drive-scsi0-0-3-0,format=raw \
> >>> -device
> >>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=3,drive=drive-scsi0-0-3-0,id
> >>> =
> >>> scsi0-0-3-0 \ -drive
> >>> file=/vm/virtio-scsi/scsi1.img,if=none,id=drive-scsi0-0-0-0,format=raw \
> >>> -device
> >>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0-0-0-0,id
> >>> =
> >>> scsi0-0-0-0 \ -drive
> >>> file=/vm/virtio-scsi/scsi2.img,if=none,id=drive-scsi0-0-1-0,format=raw \
> >>> -device
> >>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=1,drive=drive-scsi0-0-1-0,id
> >>> =
> >>> scsi0-0-1-0 \ -chardev pty,id=charserial0 -device
> >>> isa-serial,chardev=charserial0,id=serial0 \ -chardev
> >>> file,id=charserial1,path=/vm/f17.log \
> >>> -device isa-serial,chardev=charserial1,id=serial1 \
> >>> -device usb-tablet,id=input0 -vga std \
> >>> -device virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x7 \
> >>> -netdev tap,id=hostnet0,vhost=on,queues=4 \
> >>> -device
> >>> virtio-net-pci,netdev=hostnet0,id=net0,mac=52:54:00:ce:7b:29,bus=pci.0,a
> >>> d
> >>> dr=0x3 \ -monitor stdio
> >>> 
> >>> I got panic just after booting the system, did nothing,  waited for a
> >>> while, the guest panicked.
> >>> 
> >>> [   28.053004] BUG: soft lockup - CPU#1 stuck for 23s! [ip:592]
> >>> [   28.053004] Modules linked in: ip6t_REJECT nf_conntrack_ipv6
> >>> nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables uinput
> >>> joydev microcode virtio_balloon pcspkr virtio_net i2c_piix4 i2c_core
> >>> virtio_scsi virtio_blk floppy [   28.053004] CPU 1
> >>> [   28.053004] Pid: 592, comm: ip Not tainted 3.8.0-rc1-net+ #3 Bochs
> >>> Bochs
> >>> [   28.053004] RIP: 0010:[<ffffffff8137a9ab>]  [<ffffffff8137a9ab>]
> >>> virtqueue_get_buf+0xb/0x120 [   28.053004] RSP: 0018:ffff8800bc913550
> >>> EFLAGS: 00000246
> >>> [   28.053004] RAX: 0000000000000000 RBX: ffff8800bc49c000 RCX:
> >>> ffff8800bc49e000 [   28.053004] RDX: 0000000000000000 RSI:
> >>> ffff8800bc913584 RDI: ffff8800bcfd4000 [   28.053004] RBP:
> >>> ffff8800bc913558 R08: ffff8800bcfd0800 R09: 0000000000000000 [
> >>> 28.053004] R10: ffff8800bc49c000 R11: ffff880036cc4de0 R12:
> >>> ffff8800bcfd4000 [   28.053004] R13: ffff8800bc913558 R14:
> >>> ffffffff8137ad73 R15: 00000000000200d0 [   28.053004] FS:
> >>> 00007fb27a589740(0000) GS:ffff8800c1480000(0000) knlGS:0000000000000000
> >>> [
> >>> 
> >>>   28.053004] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> >>> 
> >>> [   28.053004] CR2: 0000000000640530 CR3: 00000000baeff000 CR4:
> >>> 00000000000006e0 [   28.053004] DR0: 0000000000000000 DR1:
> >>> 0000000000000000 DR2: 0000000000000000 [   28.053004] DR3:
> >>> 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [
> >>> 28.053004] Process ip (pid: 592, threadinfo ffff8800bc912000, task
> >>> ffff880036da2e20) [   28.053004] Stack:
> >>> [   28.053004]  ffff8800bcfd0800 ffff8800bc913638 ffffffffa003e9bb
> >>> ffff8800bc913656 [   28.053004]  0000000100000002 ffff8800c17ebb08
> >>> 000000500000ff10 ffffea0002f244c0 [   28.053004]  0000000200000582
> >>> 0000000000000000 0000000000000000 ffffea0002f244c0 [   28.053004] Call
> >>> Trace:
> >>> [   28.053004]  [<ffffffffa003e9bb>]
> >>> virtnet_send_command.constprop.26+0x24b/0x270 [virtio_net] [  
> >>> 28.053004]
> >>> 
> >>>  [<ffffffff812ed963>] ? sg_init_table+0x23/0x50
> >>> 
> >>> [   28.053004]  [<ffffffffa0040629>] virtnet_set_rx_mode+0x99/0x300
> >>> [virtio_net] [   28.053004]  [<ffffffff8152306f>]
> >>> __dev_set_rx_mode+0x5f/0xb0
> >>> [   28.053004]  [<ffffffff815230ef>] dev_set_rx_mode+0x2f/0x50
> >>> [   28.053004]  [<ffffffff815231b7>] __dev_open+0xa7/0xf0
> >>> [   28.053004]  [<ffffffff81523461>] __dev_change_flags+0xa1/0x180
> >>> [   28.053004]  [<ffffffff815235f8>] dev_change_flags+0x28/0x70
> >>> [   28.053004]  [<ffffffff8152ff20>] do_setlink+0x3b0/0xa50
> >>> [   28.053004]  [<ffffffff812fb6b1>] ? nla_parse+0x31/0xe0
> >>> [   28.053004]  [<ffffffff815325de>] rtnl_newlink+0x36e/0x580
> >>> [   28.053004]  [<ffffffff811355cc>] ?
> >>> get_page_from_freelist+0x37c/0x730
> >>> [   28.053004]  [<ffffffff81531e13>] rtnetlink_rcv_msg+0x113/0x2f0
> >>> [   28.053004]  [<ffffffff8117d973>] ?
> >>> __kmalloc_node_track_caller+0x63/0x1c0 [   28.053004]
> >>> [<ffffffff8151526b>] ? __alloc_skb+0x8b/0x2a0
> >>> [   28.053004]  [<ffffffff81531d00>] ? __rtnl_unlock+0x20/0x20
> >>> [   28.053004]  [<ffffffff8154b571>] netlink_rcv_skb+0xb1/0xc0
> >>> [   28.053004]  [<ffffffff8152ea05>] rtnetlink_rcv+0x25/0x40
> >>> [   28.053004]  [<ffffffff8154ae91>] netlink_unicast+0x1a1/0x220
> >>> [   28.053004]  [<ffffffff8154b211>] netlink_sendmsg+0x301/0x3c0
> >>> [   28.053004]  [<ffffffff81508530>] sock_sendmsg+0xb0/0xe0
> >>> [   28.053004]  [<ffffffff8113a45b>] ? lru_cache_add_lru+0x3b/0x60
> >>> [   28.053004]  [<ffffffff811608b7>] ? page_add_new_anon_rmap+0xc7/0x180
> >>> [   28.053004]  [<ffffffff81509efc>] __sys_sendmsg+0x3ac/0x3c0
> >>> [   28.053004]  [<ffffffff8162e47c>] ? __do_page_fault+0x23c/0x4d0
> >>> [   28.053004]  [<ffffffff8115c9ef>] ? do_brk+0x1ff/0x370
> >>> [   28.053004]  [<ffffffff8150bec9>] sys_sendmsg+0x49/0x90
> >>> [   28.053004]  [<ffffffff81632d59>] system_call_fastpath+0x16/0x1b
> >>> [   28.053004] Code: 04 0f ae f0 48 8b 47 50 5d 0f b7 50 02 66 39 57 64
> >>> 0f
> >>> 94 c0 c3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41
> >>> 54 <53> 80 7f 59 00 48 89 fb 0f 85 90 00 00 00 48 8b 47 50 0f b7 50
> >>> 
> >>> 
> >>> The QEMU tree I used is git://github.com/jasowang/qemu.git
> >> 
> >> Thanks a lot, will try to reproduce my self tomorrow. From the
> >> calltrace, looks like we send a command to a rx/tx queue.
> > 
> > Right, the virtqueue that will not be used by single queue were
> > initialized. Please try to following patch or use the my qemu.git with
> > this fix in github.
> It's odd, why didn't I get guest panic by using your python start script
> this morning?
> 
That's strange, I can reproduce it. Did you try booting a single queue guest 
under a multiqueue virtio-net?

It could be only triggered when you want to boot a single queue guest with 
queues >= 2. Let's take 2 as an example. Without the patch, all virtqueues 
will be initialized even if guest don't support multiqueue. So ctrl vq will be 
4th but guest think it's 2th. So guest will send the command to a rx/tx queue, 
so it won't get any response.

So if you're using the python script to boot a single queue guest with queue = 
1, or boot a multiqueue guest. It would not be triggerable.

Thanks
> Thanks,
> Wanlong Gao
> 
> > diff --git a/hw/virtio-net.c b/hw/virtio-net.c
> > index 8b4f079..cfd9af1 100644
> > --- a/hw/virtio-net.c
> > +++ b/hw/virtio-net.c
[...]
Wanlong Gao - Jan. 10, 2013, 9:06 a.m.
On 01/10/2013 03:16 PM, Jason Wang wrote:
> On Thursday, January 10, 2013 02:49:14 PM Wanlong Gao wrote:
>> On 01/10/2013 02:43 PM, Jason Wang wrote:
>>> On Wednesday, January 09, 2013 11:26:33 PM Jason Wang wrote:
>>>> On 01/09/2013 06:01 PM, Wanlong Gao wrote:
>>>>> On 01/09/2013 05:30 PM, Jason Wang wrote:
>>>>>> On 01/09/2013 04:23 PM, Wanlong Gao wrote:
>>>>>>> On 01/08/2013 06:14 PM, Jason Wang wrote:
>>>>>>>> On 01/08/2013 06:00 PM, Wanlong Gao wrote:
>>>>>>>>> On 01/08/2013 05:51 PM, Jason Wang wrote:
>>>>>>>>>> On 01/08/2013 05:49 PM, Wanlong Gao wrote:
>>>>>>>>>>> On 01/08/2013 05:29 PM, Jason Wang wrote:
>>>>>>>>>>>> On 01/08/2013 05:07 PM, Wanlong Gao wrote:
>>>>>>>>>>>>> On 12/28/2012 06:32 PM, Jason Wang wrote:
>>>>>>>>>>>>>> +    } else if (nc->peer->info->type !=
>>>>>>>>>>>>>> NET_CLIENT_OPTIONS_KIND_TAP) {
>>>>>>>>>>>>>> +        ret = -1;
>>>>>>>>>>>>>> +    } else {
>>>>>>>>>>>>>> +        ret = tap_detach(nc->peer);
>>>>>>>>>>>>>> +    }
>>>>>>>>>>>>>> +
>>>>>>>>>>>>>> +    return ret;
>>>>>>>>>>>>>> +}
>>>>>>>>>>>>>> +
>>>
>>> [...]
>>>
>>>>>>> I got guest kernel panic when using this way and set queues=4.
>>>>>>
>>>>>> Does it happens w/o or w/ a fd parameter? What's the qemu command line?
>>>>>> Did you meet it during boot time?
>>>>>
>>>>> The QEMU command line is
>>>>>
>>>>> /work/git/qemu/x86_64-softmmu/qemu-system-x86_64 -name f17 -M pc-0.15
>>>>> -enable-kvm -m 3096 \ -smp 4,sockets=4,cores=1,threads=1 \
>>>>> -uuid c31a9f3e-4161-c53a-339c-5dc36d0497cb -no-user-config -nodefaults \
>>>>> -chardev
>>>>> socket,id=charmonitor,path=/var/lib/libvirt/qemu/f17.monitor,server,nowa
>>>>> i
>>>>> t \ -mon chardev=charmonitor,id=monitor,mode=control \
>>>>> -rtc base=utc -no-shutdown \
>>>>> -device piix3-usb-uhci,id=usb,bus=pci.0,addr=0x1.0x2 \
>>>>> -device
>>>>> virtio-scsi-pci,id=scsi0,bus=pci.0,addr=0xb,num_queues=4,hotplug=on \
>>>>> -device virtio-serial-pci,id=virtio-serial0,bus=pci.0,addr=0x5 \
>>>>> -drive file=/vm/f17.img,if=none,id=drive-virtio-disk0,format=qcow2 \
>>>>> -device
>>>>> virtio-blk-pci,scsi=off,bus=pci.0,addr=0x6,drive=drive-virtio-disk0,id=v
>>>>> i
>>>>> rtio-disk0,bootindex=1 \ -drive
>>>>> file=/vm2/f17-kernel.img,if=none,id=drive-virtio-disk1,format=qcow2 \
>>>>> -device
>>>>> virtio-blk-pci,scsi=off,bus=pci.0,addr=0x8,drive=drive-virtio-disk1,id=v
>>>>> i
>>>>> rtio-disk1 \ -drive
>>>>> file=/vm/virtio-scsi/scsi3.img,if=none,id=drive-scsi0-0-2-0,format=raw \
>>>>> -device
>>>>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=2,drive=drive-scsi0-0-2-0,id
>>>>> =
>>>>> scsi0-0-2-0,removable=on \ -drive
>>>>> file=/vm/virtio-scsi/scsi4.img,if=none,id=drive-scsi0-0-3-0,format=raw \
>>>>> -device
>>>>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=3,drive=drive-scsi0-0-3-0,id
>>>>> =
>>>>> scsi0-0-3-0 \ -drive
>>>>> file=/vm/virtio-scsi/scsi1.img,if=none,id=drive-scsi0-0-0-0,format=raw \
>>>>> -device
>>>>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0-0-0-0,id
>>>>> =
>>>>> scsi0-0-0-0 \ -drive
>>>>> file=/vm/virtio-scsi/scsi2.img,if=none,id=drive-scsi0-0-1-0,format=raw \
>>>>> -device
>>>>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=1,drive=drive-scsi0-0-1-0,id
>>>>> =
>>>>> scsi0-0-1-0 \ -chardev pty,id=charserial0 -device
>>>>> isa-serial,chardev=charserial0,id=serial0 \ -chardev
>>>>> file,id=charserial1,path=/vm/f17.log \
>>>>> -device isa-serial,chardev=charserial1,id=serial1 \
>>>>> -device usb-tablet,id=input0 -vga std \
>>>>> -device virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x7 \
>>>>> -netdev tap,id=hostnet0,vhost=on,queues=4 \
>>>>> -device
>>>>> virtio-net-pci,netdev=hostnet0,id=net0,mac=52:54:00:ce:7b:29,bus=pci.0,a
>>>>> d
>>>>> dr=0x3 \ -monitor stdio
>>>>>
>>>>> I got panic just after booting the system, did nothing,  waited for a
>>>>> while, the guest panicked.
>>>>>
>>>>> [   28.053004] BUG: soft lockup - CPU#1 stuck for 23s! [ip:592]
>>>>> [   28.053004] Modules linked in: ip6t_REJECT nf_conntrack_ipv6
>>>>> nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables uinput
>>>>> joydev microcode virtio_balloon pcspkr virtio_net i2c_piix4 i2c_core
>>>>> virtio_scsi virtio_blk floppy [   28.053004] CPU 1
>>>>> [   28.053004] Pid: 592, comm: ip Not tainted 3.8.0-rc1-net+ #3 Bochs
>>>>> Bochs
>>>>> [   28.053004] RIP: 0010:[<ffffffff8137a9ab>]  [<ffffffff8137a9ab>]
>>>>> virtqueue_get_buf+0xb/0x120 [   28.053004] RSP: 0018:ffff8800bc913550
>>>>> EFLAGS: 00000246
>>>>> [   28.053004] RAX: 0000000000000000 RBX: ffff8800bc49c000 RCX:
>>>>> ffff8800bc49e000 [   28.053004] RDX: 0000000000000000 RSI:
>>>>> ffff8800bc913584 RDI: ffff8800bcfd4000 [   28.053004] RBP:
>>>>> ffff8800bc913558 R08: ffff8800bcfd0800 R09: 0000000000000000 [
>>>>> 28.053004] R10: ffff8800bc49c000 R11: ffff880036cc4de0 R12:
>>>>> ffff8800bcfd4000 [   28.053004] R13: ffff8800bc913558 R14:
>>>>> ffffffff8137ad73 R15: 00000000000200d0 [   28.053004] FS:
>>>>> 00007fb27a589740(0000) GS:ffff8800c1480000(0000) knlGS:0000000000000000
>>>>> [
>>>>>
>>>>>   28.053004] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
>>>>>
>>>>> [   28.053004] CR2: 0000000000640530 CR3: 00000000baeff000 CR4:
>>>>> 00000000000006e0 [   28.053004] DR0: 0000000000000000 DR1:
>>>>> 0000000000000000 DR2: 0000000000000000 [   28.053004] DR3:
>>>>> 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [
>>>>> 28.053004] Process ip (pid: 592, threadinfo ffff8800bc912000, task
>>>>> ffff880036da2e20) [   28.053004] Stack:
>>>>> [   28.053004]  ffff8800bcfd0800 ffff8800bc913638 ffffffffa003e9bb
>>>>> ffff8800bc913656 [   28.053004]  0000000100000002 ffff8800c17ebb08
>>>>> 000000500000ff10 ffffea0002f244c0 [   28.053004]  0000000200000582
>>>>> 0000000000000000 0000000000000000 ffffea0002f244c0 [   28.053004] Call
>>>>> Trace:
>>>>> [   28.053004]  [<ffffffffa003e9bb>]
>>>>> virtnet_send_command.constprop.26+0x24b/0x270 [virtio_net] [  
>>>>> 28.053004]
>>>>>
>>>>>  [<ffffffff812ed963>] ? sg_init_table+0x23/0x50
>>>>>
>>>>> [   28.053004]  [<ffffffffa0040629>] virtnet_set_rx_mode+0x99/0x300
>>>>> [virtio_net] [   28.053004]  [<ffffffff8152306f>]
>>>>> __dev_set_rx_mode+0x5f/0xb0
>>>>> [   28.053004]  [<ffffffff815230ef>] dev_set_rx_mode+0x2f/0x50
>>>>> [   28.053004]  [<ffffffff815231b7>] __dev_open+0xa7/0xf0
>>>>> [   28.053004]  [<ffffffff81523461>] __dev_change_flags+0xa1/0x180
>>>>> [   28.053004]  [<ffffffff815235f8>] dev_change_flags+0x28/0x70
>>>>> [   28.053004]  [<ffffffff8152ff20>] do_setlink+0x3b0/0xa50
>>>>> [   28.053004]  [<ffffffff812fb6b1>] ? nla_parse+0x31/0xe0
>>>>> [   28.053004]  [<ffffffff815325de>] rtnl_newlink+0x36e/0x580
>>>>> [   28.053004]  [<ffffffff811355cc>] ?
>>>>> get_page_from_freelist+0x37c/0x730
>>>>> [   28.053004]  [<ffffffff81531e13>] rtnetlink_rcv_msg+0x113/0x2f0
>>>>> [   28.053004]  [<ffffffff8117d973>] ?
>>>>> __kmalloc_node_track_caller+0x63/0x1c0 [   28.053004]
>>>>> [<ffffffff8151526b>] ? __alloc_skb+0x8b/0x2a0
>>>>> [   28.053004]  [<ffffffff81531d00>] ? __rtnl_unlock+0x20/0x20
>>>>> [   28.053004]  [<ffffffff8154b571>] netlink_rcv_skb+0xb1/0xc0
>>>>> [   28.053004]  [<ffffffff8152ea05>] rtnetlink_rcv+0x25/0x40
>>>>> [   28.053004]  [<ffffffff8154ae91>] netlink_unicast+0x1a1/0x220
>>>>> [   28.053004]  [<ffffffff8154b211>] netlink_sendmsg+0x301/0x3c0
>>>>> [   28.053004]  [<ffffffff81508530>] sock_sendmsg+0xb0/0xe0
>>>>> [   28.053004]  [<ffffffff8113a45b>] ? lru_cache_add_lru+0x3b/0x60
>>>>> [   28.053004]  [<ffffffff811608b7>] ? page_add_new_anon_rmap+0xc7/0x180
>>>>> [   28.053004]  [<ffffffff81509efc>] __sys_sendmsg+0x3ac/0x3c0
>>>>> [   28.053004]  [<ffffffff8162e47c>] ? __do_page_fault+0x23c/0x4d0
>>>>> [   28.053004]  [<ffffffff8115c9ef>] ? do_brk+0x1ff/0x370
>>>>> [   28.053004]  [<ffffffff8150bec9>] sys_sendmsg+0x49/0x90
>>>>> [   28.053004]  [<ffffffff81632d59>] system_call_fastpath+0x16/0x1b
>>>>> [   28.053004] Code: 04 0f ae f0 48 8b 47 50 5d 0f b7 50 02 66 39 57 64
>>>>> 0f
>>>>> 94 c0 c3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41
>>>>> 54 <53> 80 7f 59 00 48 89 fb 0f 85 90 00 00 00 48 8b 47 50 0f b7 50
>>>>>
>>>>>
>>>>> The QEMU tree I used is git://github.com/jasowang/qemu.git
>>>>
>>>> Thanks a lot, will try to reproduce my self tomorrow. From the
>>>> calltrace, looks like we send a command to a rx/tx queue.
>>>
>>> Right, the virtqueue that will not be used by single queue were
>>> initialized. Please try to following patch or use the my qemu.git with
>>> this fix in github.
>> It's odd, why didn't I get guest panic by using your python start script
>> this morning?
>>
> That's strange, I can reproduce it. Did you try booting a single queue guest 
> under a multiqueue virtio-net?
> 
> It could be only triggered when you want to boot a single queue guest with 
> queues >= 2. Let's take 2 as an example. Without the patch, all virtqueues 
> will be initialized even if guest don't support multiqueue. So ctrl vq will be 
> 4th but guest think it's 2th. So guest will send the command to a rx/tx queue, 
> so it won't get any response.

Anyway, with your updated github tree, the guest panic has gone.
As you say here, the guest panic is triggered by using single-queue-supported guest
kernel? But I think my guest kernel was always support multi-queue virtio-net,
Am I missing something on the guest kernel supporting multi-queue virtio-net ?

Thanks,
Wanlong Gao

> 
> So if you're using the python script to boot a single queue guest with queue = 
> 1, or boot a multiqueue guest. It would not be triggerable.
> 
> Thanks
>> Thanks,
>> Wanlong Gao
>>
>>> diff --git a/hw/virtio-net.c b/hw/virtio-net.c
>>> index 8b4f079..cfd9af1 100644
>>> --- a/hw/virtio-net.c
>>> +++ b/hw/virtio-net.c
> [...]
>
Jason Wang - Jan. 10, 2013, 9:40 a.m.
On 01/10/2013 05:06 PM, Wanlong Gao wrote:
> On 01/10/2013 03:16 PM, Jason Wang wrote:
>> On Thursday, January 10, 2013 02:49:14 PM Wanlong Gao wrote:
>>> On 01/10/2013 02:43 PM, Jason Wang wrote:
>>>> On Wednesday, January 09, 2013 11:26:33 PM Jason Wang wrote:
>>>>> On 01/09/2013 06:01 PM, Wanlong Gao wrote:
>>>>>> On 01/09/2013 05:30 PM, Jason Wang wrote:
>>>>>>> On 01/09/2013 04:23 PM, Wanlong Gao wrote:
>>>>>>>> On 01/08/2013 06:14 PM, Jason Wang wrote:
>>>>>>>>> On 01/08/2013 06:00 PM, Wanlong Gao wrote:
>>>>>>>>>> On 01/08/2013 05:51 PM, Jason Wang wrote:
>>>>>>>>>>> On 01/08/2013 05:49 PM, Wanlong Gao wrote:
>>>>>>>>>>>> On 01/08/2013 05:29 PM, Jason Wang wrote:
>>>>>>>>>>>>> On 01/08/2013 05:07 PM, Wanlong Gao wrote:
>>>>>>>>>>>>>> On 12/28/2012 06:32 PM, Jason Wang wrote:
>>>>>>>>>>>>>>> +    } else if (nc->peer->info->type !=
>>>>>>>>>>>>>>> NET_CLIENT_OPTIONS_KIND_TAP) {
>>>>>>>>>>>>>>> +        ret = -1;
>>>>>>>>>>>>>>> +    } else {
>>>>>>>>>>>>>>> +        ret = tap_detach(nc->peer);
>>>>>>>>>>>>>>> +    }
>>>>>>>>>>>>>>> +
>>>>>>>>>>>>>>> +    return ret;
>>>>>>>>>>>>>>> +}
>>>>>>>>>>>>>>> +
>>>> [...]
>>>>
>>>>>>>> I got guest kernel panic when using this way and set queues=4.
>>>>>>> Does it happens w/o or w/ a fd parameter? What's the qemu command line?
>>>>>>> Did you meet it during boot time?
>>>>>> The QEMU command line is
>>>>>>
>>>>>> /work/git/qemu/x86_64-softmmu/qemu-system-x86_64 -name f17 -M pc-0.15
>>>>>> -enable-kvm -m 3096 \ -smp 4,sockets=4,cores=1,threads=1 \
>>>>>> -uuid c31a9f3e-4161-c53a-339c-5dc36d0497cb -no-user-config -nodefaults \
>>>>>> -chardev
>>>>>> socket,id=charmonitor,path=/var/lib/libvirt/qemu/f17.monitor,server,nowa
>>>>>> i
>>>>>> t \ -mon chardev=charmonitor,id=monitor,mode=control \
>>>>>> -rtc base=utc -no-shutdown \
>>>>>> -device piix3-usb-uhci,id=usb,bus=pci.0,addr=0x1.0x2 \
>>>>>> -device
>>>>>> virtio-scsi-pci,id=scsi0,bus=pci.0,addr=0xb,num_queues=4,hotplug=on \
>>>>>> -device virtio-serial-pci,id=virtio-serial0,bus=pci.0,addr=0x5 \
>>>>>> -drive file=/vm/f17.img,if=none,id=drive-virtio-disk0,format=qcow2 \
>>>>>> -device
>>>>>> virtio-blk-pci,scsi=off,bus=pci.0,addr=0x6,drive=drive-virtio-disk0,id=v
>>>>>> i
>>>>>> rtio-disk0,bootindex=1 \ -drive
>>>>>> file=/vm2/f17-kernel.img,if=none,id=drive-virtio-disk1,format=qcow2 \
>>>>>> -device
>>>>>> virtio-blk-pci,scsi=off,bus=pci.0,addr=0x8,drive=drive-virtio-disk1,id=v
>>>>>> i
>>>>>> rtio-disk1 \ -drive
>>>>>> file=/vm/virtio-scsi/scsi3.img,if=none,id=drive-scsi0-0-2-0,format=raw \
>>>>>> -device
>>>>>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=2,drive=drive-scsi0-0-2-0,id
>>>>>> =
>>>>>> scsi0-0-2-0,removable=on \ -drive
>>>>>> file=/vm/virtio-scsi/scsi4.img,if=none,id=drive-scsi0-0-3-0,format=raw \
>>>>>> -device
>>>>>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=3,drive=drive-scsi0-0-3-0,id
>>>>>> =
>>>>>> scsi0-0-3-0 \ -drive
>>>>>> file=/vm/virtio-scsi/scsi1.img,if=none,id=drive-scsi0-0-0-0,format=raw \
>>>>>> -device
>>>>>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0-0-0-0,id
>>>>>> =
>>>>>> scsi0-0-0-0 \ -drive
>>>>>> file=/vm/virtio-scsi/scsi2.img,if=none,id=drive-scsi0-0-1-0,format=raw \
>>>>>> -device
>>>>>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=1,drive=drive-scsi0-0-1-0,id
>>>>>> =
>>>>>> scsi0-0-1-0 \ -chardev pty,id=charserial0 -device
>>>>>> isa-serial,chardev=charserial0,id=serial0 \ -chardev
>>>>>> file,id=charserial1,path=/vm/f17.log \
>>>>>> -device isa-serial,chardev=charserial1,id=serial1 \
>>>>>> -device usb-tablet,id=input0 -vga std \
>>>>>> -device virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x7 \
>>>>>> -netdev tap,id=hostnet0,vhost=on,queues=4 \
>>>>>> -device
>>>>>> virtio-net-pci,netdev=hostnet0,id=net0,mac=52:54:00:ce:7b:29,bus=pci.0,a
>>>>>> d
>>>>>> dr=0x3 \ -monitor stdio
>>>>>>
>>>>>> I got panic just after booting the system, did nothing,  waited for a
>>>>>> while, the guest panicked.
>>>>>>
>>>>>> [   28.053004] BUG: soft lockup - CPU#1 stuck for 23s! [ip:592]
>>>>>> [   28.053004] Modules linked in: ip6t_REJECT nf_conntrack_ipv6
>>>>>> nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables uinput
>>>>>> joydev microcode virtio_balloon pcspkr virtio_net i2c_piix4 i2c_core
>>>>>> virtio_scsi virtio_blk floppy [   28.053004] CPU 1
>>>>>> [   28.053004] Pid: 592, comm: ip Not tainted 3.8.0-rc1-net+ #3 Bochs
>>>>>> Bochs
>>>>>> [   28.053004] RIP: 0010:[<ffffffff8137a9ab>]  [<ffffffff8137a9ab>]
>>>>>> virtqueue_get_buf+0xb/0x120 [   28.053004] RSP: 0018:ffff8800bc913550
>>>>>> EFLAGS: 00000246
>>>>>> [   28.053004] RAX: 0000000000000000 RBX: ffff8800bc49c000 RCX:
>>>>>> ffff8800bc49e000 [   28.053004] RDX: 0000000000000000 RSI:
>>>>>> ffff8800bc913584 RDI: ffff8800bcfd4000 [   28.053004] RBP:
>>>>>> ffff8800bc913558 R08: ffff8800bcfd0800 R09: 0000000000000000 [
>>>>>> 28.053004] R10: ffff8800bc49c000 R11: ffff880036cc4de0 R12:
>>>>>> ffff8800bcfd4000 [   28.053004] R13: ffff8800bc913558 R14:
>>>>>> ffffffff8137ad73 R15: 00000000000200d0 [   28.053004] FS:
>>>>>> 00007fb27a589740(0000) GS:ffff8800c1480000(0000) knlGS:0000000000000000
>>>>>> [
>>>>>>
>>>>>>   28.053004] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
>>>>>>
>>>>>> [   28.053004] CR2: 0000000000640530 CR3: 00000000baeff000 CR4:
>>>>>> 00000000000006e0 [   28.053004] DR0: 0000000000000000 DR1:
>>>>>> 0000000000000000 DR2: 0000000000000000 [   28.053004] DR3:
>>>>>> 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [
>>>>>> 28.053004] Process ip (pid: 592, threadinfo ffff8800bc912000, task
>>>>>> ffff880036da2e20) [   28.053004] Stack:
>>>>>> [   28.053004]  ffff8800bcfd0800 ffff8800bc913638 ffffffffa003e9bb
>>>>>> ffff8800bc913656 [   28.053004]  0000000100000002 ffff8800c17ebb08
>>>>>> 000000500000ff10 ffffea0002f244c0 [   28.053004]  0000000200000582
>>>>>> 0000000000000000 0000000000000000 ffffea0002f244c0 [   28.053004] Call
>>>>>> Trace:
>>>>>> [   28.053004]  [<ffffffffa003e9bb>]
>>>>>> virtnet_send_command.constprop.26+0x24b/0x270 [virtio_net] [  
>>>>>> 28.053004]
>>>>>>
>>>>>>  [<ffffffff812ed963>] ? sg_init_table+0x23/0x50
>>>>>>
>>>>>> [   28.053004]  [<ffffffffa0040629>] virtnet_set_rx_mode+0x99/0x300
>>>>>> [virtio_net] [   28.053004]  [<ffffffff8152306f>]
>>>>>> __dev_set_rx_mode+0x5f/0xb0
>>>>>> [   28.053004]  [<ffffffff815230ef>] dev_set_rx_mode+0x2f/0x50
>>>>>> [   28.053004]  [<ffffffff815231b7>] __dev_open+0xa7/0xf0
>>>>>> [   28.053004]  [<ffffffff81523461>] __dev_change_flags+0xa1/0x180
>>>>>> [   28.053004]  [<ffffffff815235f8>] dev_change_flags+0x28/0x70
>>>>>> [   28.053004]  [<ffffffff8152ff20>] do_setlink+0x3b0/0xa50
>>>>>> [   28.053004]  [<ffffffff812fb6b1>] ? nla_parse+0x31/0xe0
>>>>>> [   28.053004]  [<ffffffff815325de>] rtnl_newlink+0x36e/0x580
>>>>>> [   28.053004]  [<ffffffff811355cc>] ?
>>>>>> get_page_from_freelist+0x37c/0x730
>>>>>> [   28.053004]  [<ffffffff81531e13>] rtnetlink_rcv_msg+0x113/0x2f0
>>>>>> [   28.053004]  [<ffffffff8117d973>] ?
>>>>>> __kmalloc_node_track_caller+0x63/0x1c0 [   28.053004]
>>>>>> [<ffffffff8151526b>] ? __alloc_skb+0x8b/0x2a0
>>>>>> [   28.053004]  [<ffffffff81531d00>] ? __rtnl_unlock+0x20/0x20
>>>>>> [   28.053004]  [<ffffffff8154b571>] netlink_rcv_skb+0xb1/0xc0
>>>>>> [   28.053004]  [<ffffffff8152ea05>] rtnetlink_rcv+0x25/0x40
>>>>>> [   28.053004]  [<ffffffff8154ae91>] netlink_unicast+0x1a1/0x220
>>>>>> [   28.053004]  [<ffffffff8154b211>] netlink_sendmsg+0x301/0x3c0
>>>>>> [   28.053004]  [<ffffffff81508530>] sock_sendmsg+0xb0/0xe0
>>>>>> [   28.053004]  [<ffffffff8113a45b>] ? lru_cache_add_lru+0x3b/0x60
>>>>>> [   28.053004]  [<ffffffff811608b7>] ? page_add_new_anon_rmap+0xc7/0x180
>>>>>> [   28.053004]  [<ffffffff81509efc>] __sys_sendmsg+0x3ac/0x3c0
>>>>>> [   28.053004]  [<ffffffff8162e47c>] ? __do_page_fault+0x23c/0x4d0
>>>>>> [   28.053004]  [<ffffffff8115c9ef>] ? do_brk+0x1ff/0x370
>>>>>> [   28.053004]  [<ffffffff8150bec9>] sys_sendmsg+0x49/0x90
>>>>>> [   28.053004]  [<ffffffff81632d59>] system_call_fastpath+0x16/0x1b
>>>>>> [   28.053004] Code: 04 0f ae f0 48 8b 47 50 5d 0f b7 50 02 66 39 57 64
>>>>>> 0f
>>>>>> 94 c0 c3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41
>>>>>> 54 <53> 80 7f 59 00 48 89 fb 0f 85 90 00 00 00 48 8b 47 50 0f b7 50
>>>>>>
>>>>>>
>>>>>> The QEMU tree I used is git://github.com/jasowang/qemu.git
>>>>> Thanks a lot, will try to reproduce my self tomorrow. From the
>>>>> calltrace, looks like we send a command to a rx/tx queue.
>>>> Right, the virtqueue that will not be used by single queue were
>>>> initialized. Please try to following patch or use the my qemu.git with
>>>> this fix in github.
>>> It's odd, why didn't I get guest panic by using your python start script
>>> this morning?
>>>
>> That's strange, I can reproduce it. Did you try booting a single queue guest 
>> under a multiqueue virtio-net?
>>
>> It could be only triggered when you want to boot a single queue guest with 
>> queues >= 2. Let's take 2 as an example. Without the patch, all virtqueues 
>> will be initialized even if guest don't support multiqueue. So ctrl vq will be 
>> 4th but guest think it's 2th. So guest will send the command to a rx/tx queue, 
>> so it won't get any response.
> Anyway, with your updated github tree, the guest panic has gone.

Good to know that.
> As you say here, the guest panic is triggered by using single-queue-supported guest
> kernel? But I think my guest kernel was always support multi-queue virtio-net,
> Am I missing something on the guest kernel supporting multi-queue virtio-net ?

I didn't know the steps of how you did the setting of you guest. I
assume your step is:

1) boot a 'legacy' kernel without a multiqueue virtio-net driver
2) install the new kernel with multiqueue support
3) reboot

So, looks like the hang can occurred only in step 1 and only if you
start qemu with queues > 1. If you use queue = 1 in step one, you will
not get the hang. If you still keep the old kernel, you can reproduce it
by booting the old one with queues > 1.

> Thanks,
> Wanlong Gao
>
>> So if you're using the python script to boot a single queue guest with queue = 
>> 1, or boot a multiqueue guest. It would not be triggerable.
>>
>> Thanks
>>> Thanks,
>>> Wanlong Gao
>>>
>>>> diff --git a/hw/virtio-net.c b/hw/virtio-net.c
>>>> index 8b4f079..cfd9af1 100644
>>>> --- a/hw/virtio-net.c
>>>> +++ b/hw/virtio-net.c
>> [...]
>>
>

Patch

diff --git a/hw/virtio-net.c b/hw/virtio-net.c
index 8b4f079..cfd9af1 100644
--- a/hw/virtio-net.c
+++ b/hw/virtio-net.c
@@ -186,7 +186,7 @@  static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
             continue;
         }
 
-        if (virtio_net_started(n, status) && !q->vhost_started) {
+        if (virtio_net_started(n, queue_status) && !q->vhost_started) {
             if (q->tx_timer) {
                 qemu_mod_timer(q->tx_timer,
                                qemu_get_clock_ns(vm_clock) + n->tx_timeout);
@@ -545,7 +545,8 @@  static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd,
 
     if (s.virtqueue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN ||
         s.virtqueue_pairs > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX ||
-        s.virtqueue_pairs > n->max_queues) {
+        s.virtqueue_pairs > n->max_queues ||
+        !n->multiqueue) {
         return VIRTIO_NET_ERR;
     }
 
@@ -1026,19 +1027,15 @@  static void virtio_net_tx_bh(void *opaque)
 static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue, int ctrl)
 {
     VirtIODevice *vdev = &n->vdev;
-    int i;
+    int i, max = multiqueue ? n->max_queues : 1;
 
     n->multiqueue = multiqueue;
 
-    if (!multiqueue) {
-        n->max_queues = 1;
-    }
-
     for (i = 2; i <= n->max_queues * 2 + 1; i++) {
         virtio_del_queue(vdev, i);
     }
 
-    for (i = 1; i < n->max_queues; i++) {
+    for (i = 1; i < max; i++) {
         n->vqs[i].rx_vq = virtio_add_queue(vdev, 256, virtio_net_handle_rx);
         if (n->vqs[i].tx_timer) {
             n->vqs[i].tx_vq =