Re: [Qemu-devel] [PATCH V3 10/11] vcpu: introduce lockmap

[Jan Kiszka]

On 2012-09-11 11:44, liu ping fan wrote:
> On Tue, Sep 11, 2012 at 4:35 PM, Avi Kivity <address@hidden> wrote:
>> On 09/11/2012 10:51 AM, Liu Ping Fan wrote:
>>> From: Liu Ping Fan <address@hidden>
>>>
>>> The func call chain can suffer from recursively hold
>>> qemu_mutex_lock_iothread. We introduce lockmap to record the
>>> lock depth.
>>
>> What is the root cause?  io handlers initiating I/O?
>>
> cpu_physical_memory_rw() can be called nested, and when called, it can
> be protected by no-lock/device lock/ big-lock.
> I think without big lock, io-dispatcher should face the same issue.
> As to main-loop, have not carefully consider, but at least, dma-helper
> will call cpu_physical_memory_rw() with big-lock.

That is our core problem: inconsistent invocation of existing services
/wrt locking. For portio, I was lucky that there is no nesting and I was
able to drop the big lock around all (x86) call sites. But MMIO is way
more tricky due to DMA nesting.

We could try to introduce a different version of cpu_physical_memory_rw,
cpu_physical_memory_rw_unlocked. But the problem remains that an MMIO
request can trigger the very same access in a nested fashion, and we
will have to detect this to avoid locking up QEMU (locking up the guest
might be OK).

Jan

-- 
Siemens AG, Corporate Technology, CT RTC ITP SDP-DE
Corporate Competence Center Embedded Linux