Re: [Qemu-devel] [PATCH] hw/virtio: enable common virtio feature for mmio device

[Ming Lei]

On Mon, Jun 30, 2014 at 6:09 PM, Michael S. Tsirkin <address@hidden> wrote:
> On Mon, Jun 16, 2014 at 05:26:33PM +0800, Ming Lei wrote:
>> On Mon, Jun 16, 2014 at 3:54 PM, Paolo Bonzini <address@hidden> wrote:
>> > Il 09/06/2014 10:00, Ming Lei ha scritto:
>> >
>> >> On Wed, Jun 4, 2014 at 10:05 AM, Ming Lei <address@hidden> wrote:
>> >>>
>> >>> Both 'indirect_desc' and 'event_idx' are bus independent features,
>> >>> and they should be enabled for mmio devices too.
>> >>>
>> >>> On arm64 quad core VM(qemu-kvm), the patch can increase block I/O
>> >>> performance a lot with latest linux tree:
>> >>>         - without the patch: 14K IOPS
>> >>>         - with the patch: 34K IOPS
>> >>>
>> >>> fio script:
>> >>>         [global]
>> >>>         direct=1
>> >>>         bsrange=4k-4k
>> >>>         timeout=10
>> >>>         numjobs=4
>> >>>         ioengine=libaio
>> >>>         iodepth=64
>> >>>
>> >>>         filename=/dev/vdc
>> >>>         group_reporting=1
>> >>>
>> >>>         [f1]
>> >>>         rw=randread
>> >>>
>> >>> Cc: Peter Maydell <address@hidden>
>> >>> Signed-off-by: Ming Lei <address@hidden>
>> >>> ---
>> >>>  hw/virtio/virtio-mmio.c |    6 ++++++
>> >>>  1 file changed, 6 insertions(+)
>> >>>
>> >>> diff --git a/hw/virtio/virtio-mmio.c b/hw/virtio/virtio-mmio.c
>> >>> index 8829eb0..18c6e5b 100644
>> >>> --- a/hw/virtio/virtio-mmio.c
>> >>> +++ b/hw/virtio/virtio-mmio.c
>> >>> @@ -369,10 +369,16 @@ static void virtio_mmio_realizefn(DeviceState *d,
>> >>> Error **errp)
>> >>>      sysbus_init_mmio(sbd, &proxy->iomem);
>> >>>  }
>> >>>
>> >>> +static Property virtio_mmio_properties[] = {
>> >>> +    DEFINE_VIRTIO_COMMON_FEATURES(VirtIOMMIOProxy, host_features),
>> >>> +    DEFINE_PROP_END_OF_LIST(),
>> >>> +};
>> >>> +
>> >>>  static void virtio_mmio_class_init(ObjectClass *klass, void *data)
>> >>>  {
>> >>>      DeviceClass *dc = DEVICE_CLASS(klass);
>> >>>
>> >>> +    dc->props = virtio_mmio_properties;
>> >>>      dc->realize = virtio_mmio_realizefn;
>> >>>      dc->reset = virtio_mmio_reset;
>> >>>      set_bit(DEVICE_CATEGORY_MISC, dc->categories);
>> >>> --
>> >>> 1.7.9.5
>> >
>> >
>> > Looks good.
>>
>> Paolo, thanks for your review.
>>
>> > Can you look into moving DEFINE_VIRTIO_COMMON_FEATURES
>> > from all virtio pci devices to TYPE_VIRTIO_PCI, too?
>>
>> OK, that looks a good cleanup, how about the attached patch?
>> If it is OK, I will prepare a formal one for submitting.
>>
>>
>> Thanks,
>> --
>> Ming Lei
>
> I applied the original patch for now.
> Pls address Paolo's comments and resubmit this one.

I have addresses all comments for the virtio-pci changes, and
will reply you on that thread.

Thanks,
--
Ming Lei