Re: [PATCH] Fix memory order issue inside pv spinlock

["Yang, Xiaowei" <xiaowei.yang@intel.com>]

Jeremy Fitzhardinge wrote:
> On 09/07/09 00:40, Yang, Xiaowei wrote:
>> barrier() can't prevent reads after it not being reordered with older
>> writes to different locates before it. Because of it, I can't bring up
>>> 4 HVM guests on one SMP machine. Use mb() instead.
> 
> Which read is happening too early?  Is it "xl->spinners"?  How does it fail?

Yes. If read of xl->spinners happens earlier than write 0 to xl->lock, 
notifications to wake up other spinners can be omitted incorrectly, resulting in 
others polling indefinitely (because of poll evtchn not pending) with the lock 
is uncontended.

Thanks,
xiaowei

> 
> Thanks,
>     J
> 
>> Signed-off-by: Yang Xiaowei <xiaowei.yang@intel.com>
>>
>> diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
>> index 5601506..9dee5f8 100644
>> --- a/arch/x86/xen/spinlock.c
>> +++ b/arch/x86/xen/spinlock.c
>> @@ -324,7 +325,7 @@ static void xen_spin_unlock(struct raw_spinlock
>> *lock)
>>         xl->lock = 0;           /* release lock */
>>
>>         /* make sure unlock happens before kick */
>> -       barrier();
>> +       mb();
>>
>>         if (unlikely(xl->spinners))
>>                 xen_spin_unlock_slow(xl);
>>
>> Thanks,
>> Xiaowei
>>
>