Comment 19 for bug 1308341

I was able to work around this by downgrading the kernel on a Ubuntu 14 box to 3.12.20-031220-generic #201405160935 (and of course wasn't seeing this with Ubuntu 12).

I've periodically tried booting back to the standard Ubuntu 14 3.13 kernel to see if it's been fixed (and also tried 3.13-lowlatency) but I get a W2k8R2 server hang with KVM within the first ~24 hours of boot each time.

This is a dual-processor machine. Also, with 3.13, I was getting these messages on a semi-periodic basis (may be related):

May 30 20:23:53 kernel: [ 0.000000] Linux version 3.13.0-27-lowlatency (buildd@akateko) (gcc version 4.8.2 (Ubuntu 4.8.2-19ubuntu1) ) #50-Ubuntu SMP PREEMPT Thu May 15 18:36:04 UTC 2014 (Ubuntu 3.13.0-27.50-lowlatency 3.13.11

May 31 14:15:40 kernel: [64348.760175] INFO: task qemu-system-x86:4151 blocked for more than 120 seconds.
May 31 14:15:40 kernel: [64348.767491] Not tainted 3.13.0-27-lowlatency #50-Ubuntu
May 31 14:15:40 kernel: [64348.773291] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
May 31 14:15:40 kernel: [64348.781205] qemu-system-x86 D ffff881fffc34600 0 4151 1 0x00000000
May 31 14:15:40 kernel: [64348.781210] ffff881fcf5e3de8 0000000000000002 ffff881fbf140000 ffff881fcf5e3fd8
May 31 14:15:40 kernel: [64348.781215] 0000000000014600 0000000000014600 ffff881fbf140000 ffff881fbf140000
May 31 14:15:40 kernel: [64348.781218] ffff883fcfac7060 ffff883fcfac7068 00007f3809e00000 ffff881fbf140000
May 31 14:15:40 kernel: [64348.781221] Call Trace:
May 31 14:15:40 kernel: [64348.781230] [<ffffffff81722b89>] schedule+0x29/0x70
May 31 14:15:40 kernel: [64348.781237] [<ffffffff8172552d>] rwsem_down_read_failed+0xcd/0x130
May 31 14:15:40 kernel: [64348.781243] [<ffffffff81374b04>] call_rwsem_down_read_failed+0x14/0x30
May 31 14:15:40 kernel: [64348.781247] [<ffffffff81725007>] ? down_read+0x17/0x20
May 31 14:15:40 kernel: [64348.781252] [<ffffffff810a0db2>] task_numa_work+0xd2/0x300
May 31 14:15:40 kernel: [64348.781254] [<ffffffff8109f87b>] ? account_user_time+0x8b/0xa0
May 31 14:15:40 kernel: [64348.781259] [<ffffffff81089e87>] task_work_run+0xa7/0xe0
May 31 14:15:40 kernel: [64348.781264] [<ffffffff81014e57>] do_notify_resume+0x97/0xb0
May 31 14:15:40 kernel: [64348.781268] [<ffffffff8172e52a>] int_signal+0x12/0x17

I'm not seeing any kernel errors with the 3.12 kernel.