On Wed, Dec 10, 2014 at 5:21 PM, Ryota Ozaki <[email protected]> wrote:
> On Wed, Dec 10, 2014 at 1:11 AM, Ryota Ozaki <[email protected]> wrote:
>> On Wed, Dec 10, 2014 at 12:13 AM, Masao Uebayashi <[email protected]> wrote:
>>> On Tue, Dec 9, 2014 at 5:41 PM, Ryota Ozaki <[email protected]> wrote:
>>>> In the case of softint-ed interrupts on, I think we can safely
>>>> remove the indirection. OTOH, in the case of off, I'm not sure
>>>> we can do the same thing.
>>>
>>> As far as you don't break other virtio(4) drivers than vioif(4)...
>>
>> The patch doesn't change other drivers' behavior though, I'll check if
>> the change affects the other virtio drivers. (I hope they're well isolated.)
>
> My code inspection and tests under disk/net io loads don't show
> any problems at this point.
>
> Though, I fixed a bug in the case of SOFTINT_INTR && MPSAFE_NET :-/
>
> Here is a updated patch: 
> http://www.netbsd.org/~ozaki-r/vioif-softint-intr.diff

I forgot to take care of SOFTINT_INTR && !NET_MPSAFE case :-/ Anyway fixed
and updated the patch.

  ozaki-r

Reply via email to