[Xen-bugs] [Bug 1294] New: Kernel Dom0 Oops on high network traffic load, xen 3.2.1-testing

[bugzilla-daemon@xxxxxxxxxxxxxxxxxxx]

http://bugzilla.xensource.com/bugzilla/show_bug.cgi?id=1294

           Summary: Kernel Dom0 Oops on high network traffic load, xen
                    3.2.1-testing
           Product: Xen
           Version: 3.0-testing
          Platform: x86-64
        OS/Version: Linux-2.6
            Status: NEW
          Severity: normal
          Priority: P2
         Component: Hypervisor
        AssignedTo: xen-bugs@xxxxxxxxxxxxxxxxxxx
        ReportedBy: rmoesbergen@xxxxxxxxxxxxxx


Hi,

I'm running xen 3.2.1 (the testing branch) on a HP DL380 G5. The hypervisor and
Dom0 kernel are 64 bit. The kernel is the 2.6.18.8 kernel from the 3.2 testing
mercurial repo, no kernel configuration changes. DomU kernels are mostly 64 bit
linux and HVM Windows 2003. Version info:

(XEN) Xen version 3.2.1 (root@xxxxxxxxxxxxxxxxx) (gcc version 4.1.2 20061115
(prerelease) (Debian 4.1.1-21)) Wed Jul  9 11:21:03 CEST 2008
(XEN) Latest ChangeSet: Wed Jul 02 11:53:16 2008 +0100 16947:f66bb3b80661

I will attach full 'xm dmesg' output to this bug report.

I'm experiencing a bug (kernel panic) when there is high network load on Dom0.
The kernel oops is as follows:

Unable to handle kernel NULL pointer dereference at 00000000000000e8 RIP:
[<ffffffff8808ae83>] :bnx2:bnx2_poll+0xf8/0xc42
PGD 25fff1067 PUD 245dd6067 PMD 0
Oops: 0000 [1] SMP
CPU 0
Modules linked in: netconsole xt_physdev iptable_filter ip_tables x_tables tun
drbd bridge ipv6 button ac battery pcspkr tsdev joydev usbhid ext3 jbd
dm_mirror dm_snapshot dm_mod ide_cd cdrom bnx2 ehci_hcd uhci_hcd piix usbcore
cciss scsi_mod thermal fan
Pid: 0, comm: swapper Not tainted 2.6.18.8-xen #2
RIP: e030:[<ffffffff8808ae83>]  [<ffffffff8808ae83>] :bnx2:bnx2_poll+0xf8/0xc42
RSP: e02b:ffffffff80531da0  EFLAGS: 00010286
RAX: 00000000000079c4 RBX: ffff88026a4fbc00 RCX: 00000000000079c3
RDX: 0000000000000001 RSI: 00000000000000c0 RDI: ffff88026b8e2000
RBP: ffff88026b8e2500 R08: 0000000000000000 R09: ffffffff804f3ea8
R10: ffffffff80000000 R11: ffff8801b653f822 R12: 0000000079c379c0
R13: 0000000000000000 R14: 00000001017a4b11 R15: ffff88026a4d5000
FS:  00002b693a2945f0(0000) GS:ffffffff804db000(0000) knlGS:0000000000000000
CS:  e033 DS: 0000 ES: 0000
Process swapper (pid: 0, threadinfo ffffffff804f2000, task ffffffff804654e0)
Stack:  ffff8801cabcad00 ffff88026cea0070 ffffffff80531eac ffff88026b8e2000
0000000500000040 ffffffff8035f0d1 ffffffffff578000 000005ea00000008
00000000bf93f810 ffffc2000001a000 ffff88026ab17000 0000000000000000
Call Trace:
<IRQ> [<ffffffff8035f0d1>] net_rx_action+0x887/0x902
[<ffffffff8020ace6>] do_hypervisor_callback+0x1e/0x2c
[<ffffffff8039d2fe>] net_rx_action+0xe3/0x24a
[<ffffffff80234d54>] __do_softirq+0x83/0x117
[<ffffffff8020b1b0>] call_softirq+0x1c/0x28
[<ffffffff8020d011>] do_softirq+0x6a/0xed
[<ffffffff8020cf9e>] do_IRQ+0x6a/0x73
[<ffffffff8034e6de>] evtchn_do_upcall+0x13c/0x1fb
[<ffffffff8020ace6>] do_hypervisor_callback+0x1e/0x2c
<EOI> [<ffffffff802063aa>] hypercall_page+0x3aa/0x1000
[<ffffffff802063aa>] hypercall_page+0x3aa/0x1000
[<ffffffff8020622a>] hypercall_page+0x22a/0x1000
[<ffffffff8020e39c>] raw_safe_halt+0xb8/0xdd
[<ffffffff8020984d>] xen_idle+0x6d/0x80
[<ffffffff80209024>] cpu_idle+0xab/0xce
[<ffffffff804fc7d2>] start_kernel+0x269/0x26e
[<ffffffff804fc215>] _sinittext+0x215/0x21b


Code: 49 8b 85 e8 00 00 00 66 83 78 06 00 74 20 8b 40 04 ff c0 41  <0>Kernel
panic - not syncing: Aiee, killing interrupt handler!

As a result the netwerk interface is dead an does not send and receive any
packets. Commands on the interface (such as ifconfig down) block in 'D' state
and never return.

The network card is a broadcom:

05:00.0 Ethernet controller: Broadcom Corporation NetXtreme II BCM5708 Gigabit
Ethernet (rev 12)
Subsystem: Hewlett-Packard Company Unknown device 7038
Flags: bus master, 66MHz, medium devsel, latency 64, IRQ 17
Memory at fa000000 (64-bit, non-prefetchable) [size=32M]
[virtual] Expansion ROM at d1200000 [disabled] [size=2K]
Capabilities: [40] PCI-X non-bridge device
Capabilities: [48] Power Management version 2
Capabilities: [50] Vital Product Data
Capabilities: [58] Message Signalled Interrupts: Mask- 64bit+ Queue=0/0 Enable-

I was able to capture this oops using netconsole via a different (non-crashed)
network interface. I have tried running different versions of xen (from 3.2.0
up to 3.2.1-latest), but all have the same issue. Also with a 32bit hypervisor
and dom0 kernel the same problem occurs. If I run a non-xen kernel, the problem
does not occur. Is this a bug in xen?

Please let me know if more information is required. Thanks in advance for your
help.


-- 
Configure bugmail: 
http://bugzilla.xensource.com/bugzilla/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.

_______________________________________________
Xen-bugs mailing list
Xen-bugs@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-bugs