On Wed, Jan 27, 2010 at 11:46:32AM +0200, Avi Kivity wrote:
> On 01/27/2010 11:36 AM, Michael S. Tsirkin wrote:
>>
>>
>>> smp_mb() is used for processor-vs-processor ordering, which can't happen
>>> on UP systems, but for process-vs-device, we must use mb().
>>>
>>> (this shows up if running a UP g
On 01/27/2010 11:36 AM, Michael S. Tsirkin wrote:
>
>
>> smp_mb() is used for processor-vs-processor ordering, which can't happen
>> on UP systems, but for process-vs-device, we must use mb().
>>
>> (this shows up if running a UP guest on an SMP host).
>>
> Currently, yes. But virtio is not a
On Wed, Jan 27, 2010 at 11:28:32AM +0200, Avi Kivity wrote:
> On 01/21/2010 07:10 PM, Michael S. Tsirkin wrote:
>> Documentation/memory-barriers.txt says:
>> Mandatory barriers should not be used to control SMP effects, since
>> mandatory barriers unnecessarily impose overhead on UP systems.
>>
>>
On 01/21/2010 07:10 PM, Michael S. Tsirkin wrote:
> Documentation/memory-barriers.txt says:
> Mandatory barriers should not be used to control SMP effects, since
> mandatory barriers unnecessarily impose overhead on UP systems.
>
> This rule applies to virtio, so let's do it correctly.
>
>
Thi
Documentation/memory-barriers.txt says:
Mandatory barriers should not be used to control SMP effects, since
mandatory barriers unnecessarily impose overhead on UP systems.
This rule applies to virtio, so let's do it correctly.
Signed-off-by: Michael S. Tsirkin
---
drivers/virtio/virtio_ring.c |